1207 files changed, 79627 insertions, 17865 deletions

diff --git a/CREDITS b/CREDITS
index 9a93e3e26d70..2520ba620ff1 100644
--- a/CREDITS
+++ b/CREDITS
@@ -1412,8 +1412,8 @@ P: 1024D/77D4FC9B F5C5 1C20 1DFC DEC3 3107  54A4 2332 ADFC 77D4 FC9B
 D: National Language Support
 D: Linux Internationalization Project
 D: German Localization for Linux and GNU software
-S: Kriemhildring 12a
-S: 65795 Hattersheim am Main
+S: Auf der Fittel 18
+S: 53347 Alfter
 S: Germany
 
 N: Christoph Hellwig
@@ -3580,6 +3580,12 @@ N: Dirk Verworner
 D: Co-author of German book ``Linux-Kernel-Programmierung''
 D: Co-founder of Berlin Linux User Group
 
+N: Riku Voipio
+E: riku.voipio@iki.fi
+D: Author of PCA9532 LED and Fintek f75375s hwmon driver
+D: Some random ARM board patches
+S: Finland
+
 N: Patrick Volkerding
 E: volkerdi@ftp.cdrom.com
 D: Produced the Slackware distribution, updated the SVGAlib
diff --git a/Documentation/00-INDEX b/Documentation/00-INDEX
index 2a39aeba1464..d05737aaa84b 100644
--- a/Documentation/00-INDEX
+++ b/Documentation/00-INDEX
@@ -86,6 +86,8 @@ cachetlb.txt
 	- describes the cache/TLB flushing interfaces Linux uses.
 cdrom/
 	- directory with information on the CD-ROM drivers that Linux has.
+cgroups/
+	- cgroups features, including cpusets and memory controller.
 connector/
 	- docs on the netlink based userspace<->kernel space communication mod.
 console/
@@ -98,8 +100,6 @@ cpu-load.txt
 	- document describing how CPU load statistics are collected.
 cpuidle/
 	- info on CPU_IDLE, CPU idle state management subsystem.
-cpusets.txt
-	- documents the cpusets feature; assign CPUs and Mem to a set of tasks.
 cputopology.txt
 	- documentation on how CPU topology info is exported via sysfs.
 cris/
diff --git a/Documentation/ABI/testing/sysfs-class-regulator b/Documentation/ABI/testing/sysfs-class-regulator
index 873ef1fc1569..e091fa873792 100644
--- a/Documentation/ABI/testing/sysfs-class-regulator
+++ b/Documentation/ABI/testing/sysfs-class-regulator
@@ -4,8 +4,8 @@ KernelVersion:	2.6.26
 Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
 		Some regulator directories will contain a field called
-		state. This reports the regulator enable status, for
-		regulators which can report that value.
+		state. This reports the regulator enable control, for
+		regulators which can report that input value.
 
 		This will be one of the following strings:
 
@@ -14,16 +14,54 @@ Description:
 		'unknown'
 
 		'enabled' means the regulator output is ON and is supplying
-		power to the system.
+		power to the system (assuming no error prevents it).
 
 		'disabled' means the regulator output is OFF and is not
-		supplying power to the system..
+		supplying power to the system (unless some non-Linux
+		control has enabled it).
 
 		'unknown' means software cannot determine the state, or
 		the reported state is invalid.
 
 		NOTE: this field can be used in conjunction with microvolts
-		and microamps to determine regulator output levels.
+		or microamps to determine configured regulator output levels.
+
+
+What:		/sys/class/regulator/.../status
+Description:
+		Some regulator directories will contain a field called
+		"status". This reports the current regulator status, for
+		regulators which can report that output value.
+
+		This will be one of the following strings:
+
+			off
+			on
+			error
+			fast
+			normal
+			idle
+			standby
+
+		"off" means the regulator is not supplying power to the
+		system.
+
+		"on" means the regulator is supplying power to the system,
+		and the regulator can't report a detailed operation mode.
+
+		"error" indicates an out-of-regulation status such as being
+		disabled due to thermal shutdown, or voltage being unstable
+		because of problems with the input power supply.
+
+		"fast", "normal", "idle", and "standby" are all detailed
+		regulator operation modes (described elsewhere).  They
+		imply "on", but provide more detail.
+
+		Note that regulator status is a function of many inputs,
+		not limited to control inputs from Linux.  For example,
+		the actual load presented may trigger "error" status; or
+		a regulator may be enabled by another user, even though
+		Linux did not enable it.
 
 
 What:		/sys/class/regulator/.../type
@@ -58,7 +96,7 @@ Description:
 		Some regulator directories will contain a field called
 		microvolts. This holds the regulator output voltage setting
 		measured in microvolts (i.e. E-6 Volts), for regulators
-		which can report that voltage.
+		which can report the control input for voltage.
 
 		NOTE: This value should not be used to determine the regulator
 		output voltage level as this value is the same regardless of
@@ -73,7 +111,7 @@ Description:
 		Some regulator directories will contain a field called
 		microamps. This holds the regulator output current limit
 		setting measured in microamps (i.e. E-6 Amps), for regulators
-		which can report that current.
+		which can report the control input for a current limit.
 
 		NOTE: This value should not be used to determine the regulator
 		output current level as this value is the same regardless of
@@ -87,7 +125,7 @@ Contact:	Liam Girdwood <lrg@slimlogic.co.uk>
 Description:
 		Some regulator directories will contain a field called
 		opmode. This holds the current regulator operating mode,
-		for regulators which can report it.
+		for regulators which can report that control input value.
 
 		The opmode value can be one of the following strings:
 
@@ -101,7 +139,8 @@ Description:
 
 		NOTE: This value should not be used to determine the regulator
 		output operating mode as this value is the same regardless of
-		whether the regulator is enabled or disabled.
+		whether the regulator is enabled or disabled.  A "status"
+		attribute may be available to determine the actual mode.
 
 
 What:		/sys/class/regulator/.../min_microvolts
diff --git a/Documentation/DocBook/.gitignore b/Documentation/DocBook/.gitignore
index c102c02ecf89..c6def352fe39 100644
--- a/Documentation/DocBook/.gitignore
+++ b/Documentation/DocBook/.gitignore
@@ -4,3 +4,7 @@
 *.html
 *.9.gz
 *.9
+*.aux
+*.dvi
+*.log
+*.out
diff --git a/Documentation/RCU/listRCU.txt b/Documentation/RCU/listRCU.txt
index 1fd175368a87..4349c1487e91 100644
--- a/Documentation/RCU/listRCU.txt
+++ b/Documentation/RCU/listRCU.txt
@@ -118,7 +118,7 @@ Following are the RCU equivalents for these two functions:
 		list_for_each_entry(e, list, list) {
 			if (!audit_compare_rule(rule, &e->rule)) {
 				list_del_rcu(&e->list);
-				call_rcu(&e->rcu, audit_free_rule, e);
+				call_rcu(&e->rcu, audit_free_rule);
 				return 0;
 			}
 		}
@@ -206,7 +206,7 @@ RCU ("read-copy update") its name.  The RCU code is as follows:
 				ne->rule.action = newaction;
 				ne->rule.file_count = newfield_count;
 				list_replace_rcu(e, ne);
-				call_rcu(&e->rcu, audit_free_rule, e);
+				call_rcu(&e->rcu, audit_free_rule);
 				return 0;
 			}
 		}
@@ -283,7 +283,7 @@ flag under the spinlock as follows:
 				list_del_rcu(&e->list);
 				e->deleted = 1;
 				spin_unlock(&e->lock);
-				call_rcu(&e->rcu, audit_free_rule, e);
+				call_rcu(&e->rcu, audit_free_rule);
 				return 0;
 			}
 		}
diff --git a/Documentation/RCU/rcu.txt b/Documentation/RCU/rcu.txt
index 95821a29ae41..7aa2002ade77 100644
--- a/Documentation/RCU/rcu.txt
+++ b/Documentation/RCU/rcu.txt
@@ -81,7 +81,7 @@ o	I hear that RCU needs work in order to support realtime kernels?
 	This work is largely completed.  Realtime-friendly RCU can be
 	enabled via the CONFIG_PREEMPT_RCU kernel configuration parameter.
 	However, work is in progress for enabling priority boosting of
-	preempted RCU read-side critical sections.This is needed if you
+	preempted RCU read-side critical sections.  This is needed if you
 	have CPU-bound realtime threads.
 
 o	Where can I find more information on RCU?
diff --git a/Documentation/RCU/rculist_nulls.txt b/Documentation/RCU/rculist_nulls.txt
index 239f542d48ba..6389dec33459 100644
--- a/Documentation/RCU/rculist_nulls.txt
+++ b/Documentation/RCU/rculist_nulls.txt
@@ -21,7 +21,7 @@ if (obj) {
   /*
    * Because a writer could delete object, and a writer could
    * reuse these object before the RCU grace period, we
-   * must check key after geting the reference on object
+   * must check key after getting the reference on object
    */
   if (obj->key != key) { // not the object we expected
      put_ref(obj);
@@ -117,7 +117,7 @@ a race (some writer did a delete and/or a move of an object
 to another chain) checking the final 'nulls' value if
 the lookup met the end of chain. If final 'nulls' value
 is not the slot number, then we must restart the lookup at
-the begining. If the object was moved to same chain,
+the beginning. If the object was moved to the same chain,
 then the reader doesnt care : It might eventually
 scan the list again without harm.
 
diff --git a/Documentation/cgroups/00-INDEX b/Documentation/cgroups/00-INDEX
new file mode 100644
index 000000000000..3f58fa3d6d00
--- /dev/null
+++ b/Documentation/cgroups/00-INDEX
@@ -0,0 +1,18 @@
+00-INDEX
+	- this file
+cgroups.txt
+	- Control Groups definition, implementation details, examples and API.
+cpuacct.txt
+	- CPU Accounting Controller; account CPU usage for groups of tasks.
+cpusets.txt
+	- documents the cpusets feature; assign CPUs and Mem to a set of tasks.
+devices.txt
+	- Device Whitelist Controller; description, interface and security.
+freezer-subsystem.txt
+	- checkpointing; rationale to not use signals, interface.
+memcg_test.txt
+	- Memory Resource Controller; implementation details.
+memory.txt
+	- Memory Resource Controller; design, accounting, interface, testing.
+resource_counter.txt
+	- Resource Counter API.
diff --git a/Documentation/cgroups/cgroups.txt b/Documentation/cgroups/cgroups.txt
index 93feb8444489..6eb1a97e88ce 100644
--- a/Documentation/cgroups/cgroups.txt
+++ b/Documentation/cgroups/cgroups.txt
@@ -56,7 +56,7 @@ hierarchy, and a set of subsystems; each subsystem has system-specific
 state attached to each cgroup in the hierarchy.  Each hierarchy has
 an instance of the cgroup virtual filesystem associated with it.
 
-At any one time there may be multiple active hierachies of task
+At any one time there may be multiple active hierarchies of task
 cgroups. Each hierarchy is a partition of all tasks in the system.
 
 User level code may create and destroy cgroups by name in an
@@ -124,10 +124,10 @@ following lines:
                                / \
                        Prof (15%) students (5%)
 
-Browsers like firefox/lynx go into the WWW network class, while (k)nfsd go
+Browsers like Firefox/Lynx go into the WWW network class, while (k)nfsd go
 into NFS network class.
 
-At the same time firefox/lynx will share an appropriate CPU/Memory class
+At the same time Firefox/Lynx will share an appropriate CPU/Memory class
 depending on who launched it (prof/student).
 
 With the ability to classify tasks differently for different resources
@@ -325,7 +325,7 @@ and then start a subshell 'sh' in that cgroup:
 Creating, modifying, using the cgroups can be done through the cgroup
 virtual filesystem.
 
-To mount a cgroup hierarchy will all available subsystems, type:
+To mount a cgroup hierarchy with all available subsystems, type:
 # mount -t cgroup xxx /dev/cgroup
 
 The "xxx" is not interpreted by the cgroup code, but will appear in
@@ -333,12 +333,23 @@ The "xxx" is not interpreted by the cgroup code, but will appear in
 
 To mount a cgroup hierarchy with just the cpuset and numtasks
 subsystems, type:
-# mount -t cgroup -o cpuset,numtasks hier1 /dev/cgroup
+# mount -t cgroup -o cpuset,memory hier1 /dev/cgroup
 
 To change the set of subsystems bound to a mounted hierarchy, just
 remount with different options:
+# mount -o remount,cpuset,ns hier1 /dev/cgroup
 
-# mount -o remount,cpuset,ns  /dev/cgroup
+Now memory is removed from the hierarchy and ns is added.
+
+Note this will add ns to the hierarchy but won't remove memory or
+cpuset, because the new options are appended to the old ones:
+# mount -o remount,ns /dev/cgroup
+
+To Specify a hierarchy's release_agent:
+# mount -t cgroup -o cpuset,release_agent="/sbin/cpuset_release_agent" \
+  xxx /dev/cgroup
+
+Note that specifying 'release_agent' more than once will return failure.
 
 Note that changing the set of subsystems is currently only supported
 when the hierarchy consists of a single (root) cgroup. Supporting
@@ -349,6 +360,11 @@ Then under /dev/cgroup you can find a tree that corresponds to the
 tree of the cgroups in the system. For instance, /dev/cgroup
 is the cgroup that holds the whole system.
 
+If you want to change the value of release_agent:
+# echo "/sbin/new_release_agent" > /dev/cgroup/release_agent
+
+It can also be changed via remount.
+
 If you want to create a new cgroup under /dev/cgroup:
 # cd /dev/cgroup
 # mkdir my_cgroup
@@ -476,11 +492,13 @@ cgroup->parent is still valid. (Note - can also be called for a
 newly-created cgroup if an error occurs after this subsystem's
 create() method has been called for the new cgroup).
 
-void pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp);
+int pre_destroy(struct cgroup_subsys *ss, struct cgroup *cgrp);
 
 Called before checking the reference count on each subsystem. This may
 be useful for subsystems which have some extra references even if
-there are not tasks in the cgroup.
+there are not tasks in the cgroup. If pre_destroy() returns error code,
+rmdir() will fail with it. From this behavior, pre_destroy() can be
+called multiple times against a cgroup.
 
 int can_attach(struct cgroup_subsys *ss, struct cgroup *cgrp,
 	       struct task_struct *task)
@@ -521,7 +539,7 @@ always handled well.
 void post_clone(struct cgroup_subsys *ss, struct cgroup *cgrp)
 (cgroup_mutex held by caller)
 
-Called at the end of cgroup_clone() to do any paramater
+Called at the end of cgroup_clone() to do any parameter
 initialization which might be required before a task could attach.  For
 example in cpusets, no task may attach before 'cpus' and 'mems' are set
 up.
diff --git a/Documentation/cgroups/cpusets.txt b/Documentation/cgroups/cpusets.txt
index 0611e9528c7c..f9ca389dddf4 100644
--- a/Documentation/cgroups/cpusets.txt
+++ b/Documentation/cgroups/cpusets.txt
@@ -131,7 +131,7 @@ Cpusets extends these two mechanisms as follows:
  - The hierarchy of cpusets can be mounted at /dev/cpuset, for
    browsing and manipulation from user space.
  - A cpuset may be marked exclusive, which ensures that no other
-   cpuset (except direct ancestors and descendents) may contain
+   cpuset (except direct ancestors and descendants) may contain
    any overlapping CPUs or Memory Nodes.
  - You can list all the tasks (by pid) attached to any cpuset.
 
@@ -226,7 +226,7 @@ nodes with memory--using the cpuset_track_online_nodes() hook.
 --------------------------------
 
 If a cpuset is cpu or mem exclusive, no other cpuset, other than
-a direct ancestor or descendent, may share any of the same CPUs or
+a direct ancestor or descendant, may share any of the same CPUs or
 Memory Nodes.
 
 A cpuset that is mem_exclusive *or* mem_hardwall is "hardwalled",
@@ -427,7 +427,7 @@ child cpusets have this flag enabled.
 When doing this, you don't usually want to leave any unpinned tasks in
 the top cpuset that might use non-trivial amounts of CPU, as such tasks
 may be artificially constrained to some subset of CPUs, depending on
-the particulars of this flag setting in descendent cpusets.  Even if
+the particulars of this flag setting in descendant cpusets.  Even if
 such a task could use spare CPU cycles in some other CPUs, the kernel
 scheduler might not consider the possibility of load balancing that
 task to that underused CPU.
@@ -531,9 +531,9 @@ be idle.
 
 Of course it takes some searching cost to find movable tasks and/or
 idle CPUs, the scheduler might not search all CPUs in the domain
-everytime.  In fact, in some architectures, the searching ranges on
+every time.  In fact, in some architectures, the searching ranges on
 events are limited in the same socket or node where the CPU locates,
-while the load balance on tick searchs all.
+while the load balance on tick searches all.
 
 For example, assume CPU Z is relatively far from CPU X.  Even if CPU Z
 is idle while CPU X and the siblings are busy, scheduler can't migrate
@@ -601,7 +601,7 @@ its new cpuset, then the task will continue to use whatever subset
 of MPOL_BIND nodes are still allowed in the new cpuset.  If the task
 was using MPOL_BIND and now none of its MPOL_BIND nodes are allowed
 in the new cpuset, then the task will be essentially treated as if it
-was MPOL_BIND bound to the new cpuset (even though its numa placement,
+was MPOL_BIND bound to the new cpuset (even though its NUMA placement,
 as queried by get_mempolicy(), doesn't change).  If a task is moved
 from one cpuset to another, then the kernel will adjust the tasks
 memory placement, as above, the next time that the kernel attempts
diff --git a/Documentation/cgroups/devices.txt b/Documentation/cgroups/devices.txt
index 7cc6e6a60672..57ca4c89fe5c 100644
--- a/Documentation/cgroups/devices.txt
+++ b/Documentation/cgroups/devices.txt
@@ -42,7 +42,7 @@ suffice, but we can decide the best way to adequately restrict
 movement as people get some experience with this.  We may just want
 to require CAP_SYS_ADMIN, which at least is a separate bit from
 CAP_MKNOD.  We may want to just refuse moving to a cgroup which
-isn't a descendent of the current one.  Or we may want to use
+isn't a descendant of the current one.  Or we may want to use
 CAP_MAC_ADMIN, since we really are trying to lock down root.
 
 CAP_SYS_ADMIN is needed to modify the whitelist or move another
diff --git a/Documentation/cgroups/memcg_test.txt b/Documentation/cgroups/memcg_test.txt
index 523a9c16c400..72db89ed0609 100644
--- a/Documentation/cgroups/memcg_test.txt
+++ b/Documentation/cgroups/memcg_test.txt
@@ -1,5 +1,5 @@
 Memory Resource Controller(Memcg)  Implementation Memo.
-Last Updated: 2009/1/19
+Last Updated: 2009/1/20
 Base Kernel Version: based on 2.6.29-rc2.
 
 Because VM is getting complex (one of reasons is memcg...), memcg's behavior
@@ -356,7 +356,25 @@ Under below explanation, we assume CONFIG_MEM_RES_CTRL_SWAP=y.
 	(Shell-B)
 	# move all tasks in /cgroup/test to /cgroup
 	# /sbin/swapoff -a
-	# rmdir /test/cgroup
+	# rmdir /cgroup/test
 	# kill malloc task.
 
 	Of course, tmpfs v.s. swapoff test should be tested, too.
+
+ 9.8 OOM-Killer
+	Out-of-memory caused by memcg's limit will kill tasks under
+	the memcg. When hierarchy is used, a task under hierarchy
+	will be killed by the kernel.
+	In this case, panic_on_oom shouldn't be invoked and tasks
+	in other groups shouldn't be killed.
+
+	It's not difficult to cause OOM under memcg as following.
+	Case A) when you can swapoff
+	#swapoff -a
+	#echo 50M > /memory.limit_in_bytes
+	run 51M of malloc
+
+	Case B) when you use mem+swap limitation.
+	#echo 50M > memory.limit_in_bytes
+	#echo 50M > memory.memsw.limit_in_bytes
+	run 51M of malloc
diff --git a/Documentation/cgroups/memory.txt b/Documentation/cgroups/memory.txt
index e1501964df1e..a98a7fe7aabb 100644
--- a/Documentation/cgroups/memory.txt
+++ b/Documentation/cgroups/memory.txt
@@ -302,7 +302,7 @@ will be charged as a new owner of it.
 	unevictable		- # of pages cannot be reclaimed.(mlocked etc)
 
 	Below is depend on CONFIG_DEBUG_VM.
-	inactive_ratio		- VM inernal parameter. (see mm/page_alloc.c)
+	inactive_ratio		- VM internal parameter. (see mm/page_alloc.c)
 	recent_rotated_anon	- VM internal parameter. (see mm/vmscan.c)
 	recent_rotated_file	- VM internal parameter. (see mm/vmscan.c)
 	recent_scanned_anon 	- VM internal parameter. (see mm/vmscan.c)
diff --git a/Documentation/devices.txt b/Documentation/devices.txt
index 62254d4510c6..327de1624759 100644
--- a/Documentation/devices.txt
+++ b/Documentation/devices.txt
@@ -1,7 +1,7 @@
 
 		    LINUX ALLOCATED DEVICES (2.6+ version)
 
-	     Maintained by Torben Mathiasen <device@lanana.org>
+	     Maintained by Alan Cox <device@lanana.org>
 
 		      Last revised: 29 November 2006
 
@@ -67,6 +67,11 @@ up to date.  Due to the number of registrations I have to maintain it
 in "batch mode", so there is likely additional registrations that
 haven't been listed yet.
 
+Fourth, remember that Linux now has extensive support for dynamic allocation
+of device numbering and can use sysfs and udev to handle the naming needs.
+There are still some exceptions in the serial and boot device area. Before
+asking for a device number make sure you actually need one.
+
 Finally, sometimes I have to play "namespace police."  Please don't be
 offended.  I often get submissions for /dev names that would be bound
 to cause conflicts down the road.  I am trying to avoid getting in a
@@ -101,7 +106,7 @@ Your cooperation is appreciated.
 		  0 = /dev/ram0		First RAM disk
 		  1 = /dev/ram1		Second RAM disk
 		    ...
-		250 = /dev/initrd	Initial RAM disk {2.6}
+		250 = /dev/initrd	Initial RAM disk
 
 		Older kernels had /dev/ramdisk (1, 1) here.
 		/dev/initrd refers to a RAM disk which was preloaded
@@ -340,7 +345,7 @@ Your cooperation is appreciated.
 		 14 = /dev/touchscreen/ucb1x00  UCB 1x00 touchscreen
 		 15 = /dev/touchscreen/mk712	MK712 touchscreen
 		128 = /dev/beep		Fancy beep device
-		129 = /dev/modreq	Kernel module load request {2.6}
+		129 =
 		130 = /dev/watchdog	Watchdog timer port
 		131 = /dev/temperature	Machine internal temperature
 		132 = /dev/hwtrap	Hardware fault trap
@@ -350,10 +355,10 @@ Your cooperation is appreciated.
 		139 = /dev/openprom	SPARC OpenBoot PROM
 		140 = /dev/relay8	Berkshire Products Octal relay card
 		141 = /dev/relay16	Berkshire Products ISO-16 relay card
-		142 = /dev/msr		x86 model-specific registers {2.6}
+		142 =
 		143 = /dev/pciconf	PCI configuration space
 		144 = /dev/nvram	Non-volatile configuration RAM
-		145 = /dev/hfmodem	Soundcard shortwave modem control {2.6}
+		145 = /dev/hfmodem	Soundcard shortwave modem control
 		146 = /dev/graphics	Linux/SGI graphics device
 		147 = /dev/opengl	Linux/SGI OpenGL pipe
 		148 = /dev/gfx		Linux/SGI graphics effects device
@@ -435,6 +440,9 @@ Your cooperation is appreciated.
 		228 = /dev/hpet		HPET driver
 		229 = /dev/fuse		Fuse (virtual filesystem in user-space)
 		230 = /dev/midishare	MidiShare driver
+		231 = /dev/snapshot	System memory snapshot device
+		232 = /dev/kvm		Kernel-based virtual machine (hardware virtualization extensions)
+		233 = /dev/kmview	View-OS A process with a view
 		240-254			Reserved for local use
 		255			Reserved for MISC_DYNAMIC_MINOR
 
@@ -466,10 +474,7 @@ Your cooperation is appreciated.
 		The device names specified are proposed -- if there
 		are "standard" names for these devices, please let me know.
 
- 12 block	MSCDEX CD-ROM callback support {2.6}
-		  0 = /dev/dos_cd0	First MSCDEX CD-ROM
-		  1 = /dev/dos_cd1	Second MSCDEX CD-ROM
-		    ...
+ 12 block
 
  13 char	Input core
 		  0 = /dev/input/js0	First joystick
@@ -498,7 +503,7 @@ Your cooperation is appreciated.
 		  2 = /dev/midi00	First MIDI port
 		  3 = /dev/dsp		Digital audio
 		  4 = /dev/audio	Sun-compatible digital audio
-		  6 = /dev/sndstat	Sound card status information {2.6}
+		  6 =
 		  7 = /dev/audioctl	SPARC audio control device
 		  8 = /dev/sequencer2	Sequencer -- alternate device
 		 16 = /dev/mixer1	Second soundcard mixer control
@@ -510,14 +515,7 @@ Your cooperation is appreciated.
 		 34 = /dev/midi02	Third MIDI port
 		 50 = /dev/midi03	Fourth MIDI port
 
- 14 block	BIOS harddrive callback support {2.6}
-		  0 = /dev/dos_hda	First BIOS harddrive whole disk
-		 64 = /dev/dos_hdb	Second BIOS harddrive whole disk
-		128 = /dev/dos_hdc	Third BIOS harddrive whole disk
-		192 = /dev/dos_hdd	Fourth BIOS harddrive whole disk
-
-		Partitions are handled in the same way as IDE disks
-		(see major number 3).
+ 14 block
 
  15 char	Joystick
 		  0 = /dev/js0		First analog joystick
@@ -535,14 +533,14 @@ Your cooperation is appreciated.
  16 block	GoldStar CD-ROM
 		  0 = /dev/gscd		GoldStar CD-ROM
 
- 17 char	Chase serial card
+ 17 char	OBSOLETE (was Chase serial card)
 		  0 = /dev/ttyH0	First Chase port
 		  1 = /dev/ttyH1	Second Chase port
 		    ...
  17 block	Optics Storage CD-ROM
 		  0 = /dev/optcd	Optics Storage CD-ROM
 
- 18 char	Chase serial card - alternate devices
+ 18 char	OBSOLETE (was Chase serial card - alternate devices)
 		  0 = /dev/cuh0		Callout device for ttyH0
 		  1 = /dev/cuh1		Callout device for ttyH1
 		    ...
@@ -644,8 +642,7 @@ Your cooperation is appreciated.
 		  2 = /dev/sbpcd2	Panasonic CD-ROM controller 0 unit 2
 		  3 = /dev/sbpcd3	Panasonic CD-ROM controller 0 unit 3
 
- 26 char	Quanta WinVision frame grabber {2.6}
-		  0 = /dev/wvisfgrab	Quanta WinVision frame grabber
+ 26 char
 
  26 block	Second Matsushita (Panasonic/SoundBlaster) CD-ROM
 		  0 = /dev/sbpcd4	Panasonic CD-ROM controller 1 unit 0
@@ -872,7 +869,7 @@ Your cooperation is appreciated.
 		and "user level packet I/O."  This board is also
 		accessible as a standard networking "eth" device.
 
- 38 block	Reserved for Linux/AP+
+ 38 block	OBSOLETE (was Linux/AP+)
 
  39 char	ML-16P experimental I/O board
 		  0 = /dev/ml16pa-a0	First card, first analog channel
@@ -892,29 +889,16 @@ Your cooperation is appreciated.
 		 50 = /dev/ml16pb-c1	Second card, second counter/timer
 		 51 = /dev/ml16pb-c2	Second card, third counter/timer
 		      ...
- 39 block	Reserved for Linux/AP+
+ 39 block
 
- 40 char	Matrox Meteor frame grabber {2.6}
-		  0 = /dev/mmetfgrab	Matrox Meteor frame grabber
+ 40 char
 
- 40 block	Syquest EZ135 parallel port removable drive
-		  0 = /dev/eza		Parallel EZ135 drive, whole disk
-
-		This device is obsolete and will be removed in a
-		future version of Linux.  It has been replaced with
-		the parallel port IDE disk driver at major number 45.
-		Partitions are handled in the same way as IDE disks
-		(see major number 3).
+ 40 block
 
  41 char	Yet Another Micro Monitor
 		  0 = /dev/yamm		Yet Another Micro Monitor
 
- 41 block	MicroSolutions BackPack parallel port CD-ROM
-		  0 = /dev/bpcd		BackPack CD-ROM
-
-		This device is obsolete and will be removed in a
-		future version of Linux.  It has been replaced with
-		the parallel port ATAPI CD-ROM driver at major number 46.
+ 41 block
 
  42 char	Demo/sample use
 
@@ -1681,13 +1665,7 @@ Your cooperation is appreciated.
 		disks (see major number 3) except that the limit on
 		partitions is 15.
 
- 93 char	IBM Smart Capture Card frame grabber {2.6}
-		  0 = /dev/iscc0	First Smart Capture Card
-		  1 = /dev/iscc1	Second Smart Capture Card
-		    ...
-		128 = /dev/isccctl0	First Smart Capture Card control
-		129 = /dev/isccctl1	Second Smart Capture Card control
-		    ...
+ 93 char
 
  93 block	NAND Flash Translation Layer filesystem
 		  0 = /dev/nftla	First NFTL layer
@@ -1695,10 +1673,7 @@ Your cooperation is appreciated.
 		    ...
 		240 = /dev/nftlp	16th NTFL layer
 
- 94 char	miroVIDEO DC10/30 capture/playback device {2.6}
-		  0 = /dev/dcxx0	First capture card
-		  1 = /dev/dcxx1	Second capture card
-		    ...
+ 94 char
 
  94 block	IBM S/390 DASD block storage
     		  0 = /dev/dasda First DASD device, major
@@ -1791,11 +1766,7 @@ Your cooperation is appreciated.
 		    ...
 		 15 = /dev/amiraid/ar?p15 15th partition
 
-102 char	Philips SAA5249 Teletext signal decoder {2.6}
-		  0 = /dev/tlk0		First Teletext decoder
-		  1 = /dev/tlk1		Second Teletext decoder
-		  2 = /dev/tlk2		Third Teletext decoder
-		  3 = /dev/tlk3		Fourth Teletext decoder
+102 char
 
 102 block	Compressed block device
 		  0 = /dev/cbd/a	First compressed block device, whole device
@@ -1916,10 +1887,7 @@ Your cooperation is appreciated.
 		DAC960 (see major number 48) except that the limit on
 		partitions is 15.
 
-111 char	Philips SAA7146-based audio/video card {2.6}
-		  0 = /dev/av0		First A/V card
-		  1 = /dev/av1		Second A/V card
-		    ...
+111 char
 
 111 block	Compaq Next Generation Drive Array, eighth controller
 		  0 = /dev/cciss/c7d0	First logical drive, whole disk
@@ -2079,8 +2047,8 @@ Your cooperation is appreciated.
 		    ...
 
 119 char	VMware virtual network control
-		  0 = /dev/vmnet0	1st virtual network
-		  1 = /dev/vmnet1	2nd virtual network
+		  0 = /dev/vnet0	1st virtual network
+		  1 = /dev/vnet1	2nd virtual network
 		    ...
 
 120-127 char	LOCAL/EXPERIMENTAL USE
@@ -2450,7 +2418,7 @@ Your cooperation is appreciated.
 		  2 = /dev/raw/raw2	Second raw I/O device
 		    ...
 
-163 char	UNASSIGNED (was Radio Tech BIM-XXX-RS232 radio modem - see 51)
+163 char
 
 164 char	Chase Research AT/PCI-Fast serial card
 		  0 = /dev/ttyCH0	AT/PCI-Fast board 0, port 0
@@ -2542,6 +2510,12 @@ Your cooperation is appreciated.
 		  1 = /dev/clanvi1	Second cLAN adapter
 		    ...
 
+179 block       MMC block devices
+		  0 = /dev/mmcblk0      First SD/MMC card
+		  1 = /dev/mmcblk0p1    First partition on first MMC card
+		  8 = /dev/mmcblk1      Second SD/MMC card
+		    ...
+
 179 char	CCube DVXChip-based PCI products
 		  0 = /dev/dvxirq0	First DVX device
 		  1 = /dev/dvxirq1	Second DVX device
@@ -2560,6 +2534,9 @@ Your cooperation is appreciated.
 		 96 = /dev/usb/hiddev0	1st USB HID device
 		    ...
 		111 = /dev/usb/hiddev15	16th USB HID device
+		112 = /dev/usb/auer0	1st auerswald ISDN device
+		    ...
+		127 = /dev/usb/auer15	16th auerswald ISDN device
 		128 = /dev/usb/brlvgr0	First Braille Voyager device
 		    ...
 		131 = /dev/usb/brlvgr3	Fourth Braille Voyager device
@@ -2810,6 +2787,16 @@ Your cooperation is appreciated.
 		    ...
 		 190 = /dev/ttyUL3		Xilinx uartlite - port 3
 		 191 = /dev/xvc0		Xen virtual console - port 0
+		 192 = /dev/ttyPZ0		pmac_zilog - port 0
+		    ...
+		 195 = /dev/ttyPZ3		pmac_zilog - port 3
+		 196 = /dev/ttyTX0		TX39/49 serial port 0
+		    ...
+		 204 = /dev/ttyTX7		TX39/49 serial port 7
+		 205 = /dev/ttySC0		SC26xx serial port 0
+		 206 = /dev/ttySC1		SC26xx serial port 1
+		 207 = /dev/ttySC2		SC26xx serial port 2
+		 208 = /dev/ttySC3		SC26xx serial port 3
 
 205 char	Low-density serial ports (alternate device)
 		  0 = /dev/culu0		Callout device for ttyLU0
@@ -3145,6 +3132,14 @@ Your cooperation is appreciated.
 		  1 = /dev/blockrom1	Second ROM card's translation layer interface
 		  ...
 
+259 block	Block Extended Major
+		  Used dynamically to hold additional partition minor
+		  numbers and allow large numbers of partitions per device
+
+259 char	FPGA configuration interfaces
+		  0 = /dev/icap0	First Xilinx internal configuration
+		  1 = /dev/icap1	Second Xilinx internal configuration
+
 260 char	OSD (Object-based-device) SCSI Device
 		  0 = /dev/osd0		First OSD Device
 		  1 = /dev/osd1		Second OSD Device
diff --git a/Documentation/feature-removal-schedule.txt b/Documentation/feature-removal-schedule.txt
index d0f354670646..39246fc11257 100644
--- a/Documentation/feature-removal-schedule.txt
+++ b/Documentation/feature-removal-schedule.txt
@@ -255,6 +255,16 @@ Who:	Jan Engelhardt <jengelh@computergmbh.de>
 
 ---------------------------
 
+What:	GPIO autorequest on gpio_direction_{input,output}() in gpiolib
+When:	February 2010
+Why:	All callers should use explicit gpio_request()/gpio_free().
+	The autorequest mechanism in gpiolib was provided mostly as a
+	migration aid for legacy GPIO interfaces (for SOC based GPIOs).
+	Those users have now largely migrated.  Platforms implementing
+	the GPIO interfaces without using gpiolib will see no changes.
+Who:	David Brownell <dbrownell@users.sourceforge.net>
+---------------------------
+
 What:	b43 support for firmware revision < 410
 When:	The schedule was July 2008, but it was decided that we are going to keep the
         code as long as there are no major maintanance headaches.
@@ -273,13 +283,6 @@ Who:	Glauber Costa <gcosta@redhat.com>
 
 ---------------------------
 
-What:	remove HID compat support
-When:	2.6.29
-Why:	needed only as a temporary solution until distros fix themselves up
-Who:	Jiri Slaby <jirislaby@gmail.com>
-
----------------------------
-
 What: print_fn_descriptor_symbol()
 When: October 2009
 Why:  The %pF vsprintf format provides the same functionality in a
diff --git a/Documentation/filesystems/caching/backend-api.txt b/Documentation/filesystems/caching/backend-api.txt
new file mode 100644
index 000000000000..382d52cdaf2d
--- /dev/null
+++ b/Documentation/filesystems/caching/backend-api.txt
@@ -0,0 +1,658 @@
+			  ==========================
+			  FS-CACHE CACHE BACKEND API
+			  ==========================
+
+The FS-Cache system provides an API by which actual caches can be supplied to
+FS-Cache for it to then serve out to network filesystems and other interested
+parties.
+
+This API is declared in <linux/fscache-cache.h>.
+
+
+====================================
+INITIALISING AND REGISTERING A CACHE
+====================================
+
+To start off, a cache definition must be initialised and registered for each
+cache the backend wants to make available.  For instance, CacheFS does this in
+the fill_super() operation on mounting.
+
+The cache definition (struct fscache_cache) should be initialised by calling:
+
+	void fscache_init_cache(struct fscache_cache *cache,
+				struct fscache_cache_ops *ops,
+				const char *idfmt,
+				...);
+
+Where:
+
+ (*) "cache" is a pointer to the cache definition;
+
+ (*) "ops" is a pointer to the table of operations that the backend supports on
+     this cache; and
+
+ (*) "idfmt" is a format and printf-style arguments for constructing a label
+     for the cache.
+
+
+The cache should then be registered with FS-Cache by passing a pointer to the
+previously initialised cache definition to:
+
+	int fscache_add_cache(struct fscache_cache *cache,
+			      struct fscache_object *fsdef,
+			      const char *tagname);
+
+Two extra arguments should also be supplied:
+
+ (*) "fsdef" which should point to the object representation for the FS-Cache
+     master index in this cache.  Netfs primary index entries will be created
+     here.  FS-Cache keeps the caller's reference to the index object if
+     successful and will release it upon withdrawal of the cache.
+
+ (*) "tagname" which, if given, should be a text string naming this cache.  If
+     this is NULL, the identifier will be used instead.  For CacheFS, the
+     identifier is set to name the underlying block device and the tag can be
+     supplied by mount.
+
+This function may return -ENOMEM if it ran out of memory or -EEXIST if the tag
+is already in use.  0 will be returned on success.
+
+
+=====================
+UNREGISTERING A CACHE
+=====================
+
+A cache can be withdrawn from the system by calling this function with a
+pointer to the cache definition:
+
+	void fscache_withdraw_cache(struct fscache_cache *cache);
+
+In CacheFS's case, this is called by put_super().
+
+
+========
+SECURITY
+========
+
+The cache methods are executed one of two contexts:
+
+ (1) that of the userspace process that issued the netfs operation that caused
+     the cache method to be invoked, or
+
+ (2) that of one of the processes in the FS-Cache thread pool.
+
+In either case, this may not be an appropriate context in which to access the
+cache.
+
+The calling process's fsuid, fsgid and SELinux security identities may need to
+be masqueraded for the duration of the cache driver's access to the cache.
+This is left to the cache to handle; FS-Cache makes no effort in this regard.
+
+
+===================================
+CONTROL AND STATISTICS PRESENTATION
+===================================
+
+The cache may present data to the outside world through FS-Cache's interfaces
+in sysfs and procfs - the former for control and the latter for statistics.
+
+A sysfs directory called /sys/fs/fscache/<cachetag>/ is created if CONFIG_SYSFS
+is enabled.  This is accessible through the kobject struct fscache_cache::kobj
+and is for use by the cache as it sees fit.
+
+
+========================
+RELEVANT DATA STRUCTURES
+========================
+
+ (*) Index/Data file FS-Cache representation cookie:
+
+	struct fscache_cookie {
+		struct fscache_object_def	*def;
+		struct fscache_netfs		*netfs;
+		void				*netfs_data;
+		...
+	};
+
+     The fields that might be of use to the backend describe the object
+     definition, the netfs definition and the netfs's data for this cookie.
+     The object definition contain functions supplied by the netfs for loading
+     and matching index entries; these are required to provide some of the
+     cache operations.
+
+
+ (*) In-cache object representation:
+
+	struct fscache_object {
+		int				debug_id;
+		enum {
+			FSCACHE_OBJECT_RECYCLING,
+			...
+		}				state;
+		spinlock_t			lock
+		struct fscache_cache		*cache;
+		struct fscache_cookie		*cookie;
+		...
+	};
+
+     Structures of this type should be allocated by the cache backend and
+     passed to FS-Cache when requested by the appropriate cache operation.  In
+     the case of CacheFS, they're embedded in CacheFS's internal object
+     structures.
+
+     The debug_id is a simple integer that can be used in debugging messages
+     that refer to a particular object.  In such a case it should be printed
+     using "OBJ%x" to be consistent with FS-Cache.
+
+     Each object contains a pointer to the cookie that represents the object it
+     is backing.  An object should retired when put_object() is called if it is
+     in state FSCACHE_OBJECT_RECYCLING.  The fscache_object struct should be
+     initialised by calling fscache_object_init(object).
+
+
+ (*) FS-Cache operation record:
+
+	struct fscache_operation {
+		atomic_t		usage;
+		struct fscache_object	*object;
+		unsigned long		flags;
+	#define FSCACHE_OP_EXCLUSIVE
+		void (*processor)(struct fscache_operation *op);
+		void (*release)(struct fscache_operation *op);
+		...
+	};
+
+     FS-Cache has a pool of threads that it uses to give CPU time to the
+     various asynchronous operations that need to be done as part of driving
+     the cache.  These are represented by the above structure.  The processor
+     method is called to give the op CPU time, and the release method to get
+     rid of it when its usage count reaches 0.
+
+     An operation can be made exclusive upon an object by setting the
+     appropriate flag before enqueuing it with fscache_enqueue_operation().  If
+     an operation needs more processing time, it should be enqueued again.
+
+
+ (*) FS-Cache retrieval operation record:
+
+	struct fscache_retrieval {
+		struct fscache_operation op;
+		struct address_space	*mapping;
+		struct list_head	*to_do;
+		...
+	};
+
+     A structure of this type is allocated by FS-Cache to record retrieval and
+     allocation requests made by the netfs.  This struct is then passed to the
+     backend to do the operation.  The backend may get extra refs to it by
+     calling fscache_get_retrieval() and refs may be discarded by calling
+     fscache_put_retrieval().
+
+     A retrieval operation can be used by the backend to do retrieval work.  To
+     do this, the retrieval->op.processor method pointer should be set
+     appropriately by the backend and fscache_enqueue_retrieval() called to
+     submit it to the thread pool.  CacheFiles, for example, uses this to queue
+     page examination when it detects PG_lock being cleared.
+
+     The to_do field is an empty list available for the cache backend to use as
+     it sees fit.
+
+
+ (*) FS-Cache storage operation record:
+
+	struct fscache_storage {
+		struct fscache_operation op;
+		pgoff_t			store_limit;
+		...
+	};
+
+     A structure of this type is allocated by FS-Cache to record outstanding
+     writes to be made.  FS-Cache itself enqueues this operation and invokes
+     the write_page() method on the object at appropriate times to effect
+     storage.
+
+
+================
+CACHE OPERATIONS
+================
+
+The cache backend provides FS-Cache with a table of operations that can be
+performed on the denizens of the cache.  These are held in a structure of type:
+
+	struct fscache_cache_ops
+
+ (*) Name of cache provider [mandatory]:
+
+	const char *name
+
+     This isn't strictly an operation, but should be pointed at a string naming
+     the backend.
+
+
+ (*) Allocate a new object [mandatory]:
+
+	struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
+					       struct fscache_cookie *cookie)
+
+     This method is used to allocate a cache object representation to back a
+     cookie in a particular cache.  fscache_object_init() should be called on
+     the object to initialise it prior to returning.
+
+     This function may also be used to parse the index key to be used for
+     multiple lookup calls to turn it into a more convenient form.  FS-Cache
+     will call the lookup_complete() method to allow the cache to release the
+     form once lookup is complete or aborted.
+
+
+ (*) Look up and create object [mandatory]:
+
+	void (*lookup_object)(struct fscache_object *object)
+
+     This method is used to look up an object, given that the object is already
+     allocated and attached to the cookie.  This should instantiate that object
+     in the cache if it can.
+
+     The method should call fscache_object_lookup_negative() as soon as
+     possible if it determines the object doesn't exist in the cache.  If the
+     object is found to exist and the netfs indicates that it is valid then
+     fscache_obtained_object() should be called once the object is in a
+     position to have data stored in it.  Similarly, fscache_obtained_object()
+     should also be called once a non-present object has been created.
+
+     If a lookup error occurs, fscache_object_lookup_error() should be called
+     to abort the lookup of that object.
+
+
+ (*) Release lookup data [mandatory]:
+
+	void (*lookup_complete)(struct fscache_object *object)
+
+     This method is called to ask the cache to release any resources it was
+     using to perform a lookup.
+
+
+ (*) Increment object refcount [mandatory]:
+
+	struct fscache_object *(*grab_object)(struct fscache_object *object)
+
+     This method is called to increment the reference count on an object.  It
+     may fail (for instance if the cache is being withdrawn) by returning NULL.
+     It should return the object pointer if successful.
+
+
+ (*) Lock/Unlock object [mandatory]:
+
+	void (*lock_object)(struct fscache_object *object)
+	void (*unlock_object)(struct fscache_object *object)
+
+     These methods are used to exclusively lock an object.  It must be possible
+     to schedule with the lock held, so a spinlock isn't sufficient.
+
+
+ (*) Pin/Unpin object [optional]:
+
+	int (*pin_object)(struct fscache_object *object)
+	void (*unpin_object)(struct fscache_object *object)
+
+     These methods are used to pin an object into the cache.  Once pinned an
+     object cannot be reclaimed to make space.  Return -ENOSPC if there's not
+     enough space in the cache to permit this.
+
+
+ (*) Update object [mandatory]:
+
+	int (*update_object)(struct fscache_object *object)
+
+     This is called to update the index entry for the specified object.  The
+     new information should be in object->cookie->netfs_data.  This can be
+     obtained by calling object->cookie->def->get_aux()/get_attr().
+
+
+ (*) Discard object [mandatory]:
+
+	void (*drop_object)(struct fscache_object *object)
+
+     This method is called to indicate that an object has been unbound from its
+     cookie, and that the cache should release the object's resources and
+     retire it if it's in state FSCACHE_OBJECT_RECYCLING.
+
+     This method should not attempt to release any references held by the
+     caller.  The caller will invoke the put_object() method as appropriate.
+
+
+ (*) Release object reference [mandatory]:
+
+	void (*put_object)(struct fscache_object *object)
+
+     This method is used to discard a reference to an object.  The object may
+     be freed when all the references to it are released.
+
+
+ (*) Synchronise a cache [mandatory]:
+
+	void (*sync)(struct fscache_cache *cache)
+
+     This is called to ask the backend to synchronise a cache with its backing
+     device.
+
+
+ (*) Dissociate a cache [mandatory]:
+
+	void (*dissociate_pages)(struct fscache_cache *cache)
+
+     This is called to ask a cache to perform any page dissociations as part of
+     cache withdrawal.
+
+
+ (*) Notification that the attributes on a netfs file changed [mandatory]:
+
+	int (*attr_changed)(struct fscache_object *object);
+
+     This is called to indicate to the cache that certain attributes on a netfs
+     file have changed (for example the maximum size a file may reach).  The
+     cache can read these from the netfs by calling the cookie's get_attr()
+     method.
+
+     The cache may use the file size information to reserve space on the cache.
+     It should also call fscache_set_store_limit() to indicate to FS-Cache the
+     highest byte it's willing to store for an object.
+
+     This method may return -ve if an error occurred or the cache object cannot
+     be expanded.  In such a case, the object will be withdrawn from service.
+
+     This operation is run asynchronously from FS-Cache's thread pool, and
+     storage and retrieval operations from the netfs are excluded during the
+     execution of this operation.
+
+
+ (*) Reserve cache space for an object's data [optional]:
+
+	int (*reserve_space)(struct fscache_object *object, loff_t size);
+
+     This is called to request that cache space be reserved to hold the data
+     for an object and the metadata used to track it.  Zero size should be
+     taken as request to cancel a reservation.
+
+     This should return 0 if successful, -ENOSPC if there isn't enough space
+     available, or -ENOMEM or -EIO on other errors.
+
+     The reservation may exceed the current size of the object, thus permitting
+     future expansion.  If the amount of space consumed by an object would
+     exceed the reservation, it's permitted to refuse requests to allocate
+     pages, but not required.  An object may be pruned down to its reservation
+     size if larger than that already.
+
+
+ (*) Request page be read from cache [mandatory]:
+
+	int (*read_or_alloc_page)(struct fscache_retrieval *op,
+				  struct page *page,
+				  gfp_t gfp)
+
+     This is called to attempt to read a netfs page from the cache, or to
+     reserve a backing block if not.  FS-Cache will have done as much checking
+     as it can before calling, but most of the work belongs to the backend.
+
+     If there's no page in the cache, then -ENODATA should be returned if the
+     backend managed to reserve a backing block; -ENOBUFS or -ENOMEM if it
+     didn't.
+
+     If there is suitable data in the cache, then a read operation should be
+     queued and 0 returned.  When the read finishes, fscache_end_io() should be
+     called.
+
+     The fscache_mark_pages_cached() should be called for the page if any cache
+     metadata is retained.  This will indicate to the netfs that the page needs
+     explicit uncaching.  This operation takes a pagevec, thus allowing several
+     pages to be marked at once.
+
+     The retrieval record pointed to by op should be retained for each page
+     queued and released when I/O on the page has been formally ended.
+     fscache_get/put_retrieval() are available for this purpose.
+
+     The retrieval record may be used to get CPU time via the FS-Cache thread
+     pool.  If this is desired, the op->op.processor should be set to point to
+     the appropriate processing routine, and fscache_enqueue_retrieval() should
+     be called at an appropriate point to request CPU time.  For instance, the
+     retrieval routine could be enqueued upon the completion of a disk read.
+     The to_do field in the retrieval record is provided to aid in this.
+
+     If an I/O error occurs, fscache_io_error() should be called and -ENOBUFS
+     returned if possible or fscache_end_io() called with a suitable error
+     code..
+
+
+ (*) Request pages be read from cache [mandatory]:
+
+	int (*read_or_alloc_pages)(struct fscache_retrieval *op,
+				   struct list_head *pages,
+				   unsigned *nr_pages,
+				   gfp_t gfp)
+
+     This is like the read_or_alloc_page() method, except it is handed a list
+     of pages instead of one page.  Any pages on which a read operation is
+     started must be added to the page cache for the specified mapping and also
+     to the LRU.  Such pages must also be removed from the pages list and
+     *nr_pages decremented per page.
+
+     If there was an error such as -ENOMEM, then that should be returned; else
+     if one or more pages couldn't be read or allocated, then -ENOBUFS should
+     be returned; else if one or more pages couldn't be read, then -ENODATA
+     should be returned.  If all the pages are dispatched then 0 should be
+     returned.
+
+
+ (*) Request page be allocated in the cache [mandatory]:
+
+	int (*allocate_page)(struct fscache_retrieval *op,
+			     struct page *page,
+			     gfp_t gfp)
+
+     This is like the read_or_alloc_page() method, except that it shouldn't
+     read from the cache, even if there's data there that could be retrieved.
+     It should, however, set up any internal metadata required such that
+     the write_page() method can write to the cache.
+
+     If there's no backing block available, then -ENOBUFS should be returned
+     (or -ENOMEM if there were other problems).  If a block is successfully
+     allocated, then the netfs page should be marked and 0 returned.
+
+
+ (*) Request pages be allocated in the cache [mandatory]:
+
+	int (*allocate_pages)(struct fscache_retrieval *op,
+			      struct list_head *pages,
+			      unsigned *nr_pages,
+			      gfp_t gfp)
+
+     This is an multiple page version of the allocate_page() method.  pages and
+     nr_pages should be treated as for the read_or_alloc_pages() method.
+
+
+ (*) Request page be written to cache [mandatory]:
+
+	int (*write_page)(struct fscache_storage *op,
+			  struct page *page);
+
+     This is called to write from a page on which there was a previously
+     successful read_or_alloc_page() call or similar.  FS-Cache filters out
+     pages that don't have mappings.
+
+     This method is called asynchronously from the FS-Cache thread pool.  It is
+     not required to actually store anything, provided -ENODATA is then
+     returned to the next read of this page.
+
+     If an error occurred, then a negative error code should be returned,
+     otherwise zero should be returned.  FS-Cache will take appropriate action
+     in response to an error, such as withdrawing this object.
+
+     If this method returns success then FS-Cache will inform the netfs
+     appropriately.
+
+
+ (*) Discard retained per-page metadata [mandatory]:
+
+	void (*uncache_page)(struct fscache_object *object, struct page *page)
+
+     This is called when a netfs page is being evicted from the pagecache.  The
+     cache backend should tear down any internal representation or tracking it
+     maintains for this page.
+
+
+==================
+FS-CACHE UTILITIES
+==================
+
+FS-Cache provides some utilities that a cache backend may make use of:
+
+ (*) Note occurrence of an I/O error in a cache:
+
+	void fscache_io_error(struct fscache_cache *cache)
+
+     This tells FS-Cache that an I/O error occurred in the cache.  After this
+     has been called, only resource dissociation operations (object and page
+     release) will be passed from the netfs to the cache backend for the
+     specified cache.
+
+     This does not actually withdraw the cache.  That must be done separately.
+
+
+ (*) Invoke the retrieval I/O completion function:
+
+	void fscache_end_io(struct fscache_retrieval *op, struct page *page,
+			    int error);
+
+     This is called to note the end of an attempt to retrieve a page.  The
+     error value should be 0 if successful and an error otherwise.
+
+
+ (*) Set highest store limit:
+
+	void fscache_set_store_limit(struct fscache_object *object,
+				     loff_t i_size);
+
+     This sets the limit FS-Cache imposes on the highest byte it's willing to
+     try and store for a netfs.  Any page over this limit is automatically
+     rejected by fscache_read_alloc_page() and co with -ENOBUFS.
+
+
+ (*) Mark pages as being cached:
+
+	void fscache_mark_pages_cached(struct fscache_retrieval *op,
+				       struct pagevec *pagevec);
+
+     This marks a set of pages as being cached.  After this has been called,
+     the netfs must call fscache_uncache_page() to unmark the pages.
+
+
+ (*) Perform coherency check on an object:
+
+	enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+						const void *data,
+						uint16_t datalen);
+
+     This asks the netfs to perform a coherency check on an object that has
+     just been looked up.  The cookie attached to the object will determine the
+     netfs to use.  data and datalen should specify where the auxiliary data
+     retrieved from the cache can be found.
+
+     One of three values will be returned:
+
+	(*) FSCACHE_CHECKAUX_OKAY
+
+	    The coherency data indicates the object is valid as is.
+
+	(*) FSCACHE_CHECKAUX_NEEDS_UPDATE
+
+	    The coherency data needs updating, but otherwise the object is
+	    valid.
+
+	(*) FSCACHE_CHECKAUX_OBSOLETE
+
+	    The coherency data indicates that the object is obsolete and should
+	    be discarded.
+
+
+ (*) Initialise a freshly allocated object:
+
+	void fscache_object_init(struct fscache_object *object);
+
+     This initialises all the fields in an object representation.
+
+
+ (*) Indicate the destruction of an object:
+
+	void fscache_object_destroyed(struct fscache_cache *cache);
+
+     This must be called to inform FS-Cache that an object that belonged to a
+     cache has been destroyed and deallocated.  This will allow continuation
+     of the cache withdrawal process when it is stopped pending destruction of
+     all the objects.
+
+
+ (*) Indicate negative lookup on an object:
+
+	void fscache_object_lookup_negative(struct fscache_object *object);
+
+     This is called to indicate to FS-Cache that a lookup process for an object
+     found a negative result.
+
+     This changes the state of an object to permit reads pending on lookup
+     completion to go off and start fetching data from the netfs server as it's
+     known at this point that there can't be any data in the cache.
+
+     This may be called multiple times on an object.  Only the first call is
+     significant - all subsequent calls are ignored.
+
+
+ (*) Indicate an object has been obtained:
+
+	void fscache_obtained_object(struct fscache_object *object);
+
+     This is called to indicate to FS-Cache that a lookup process for an object
+     produced a positive result, or that an object was created.  This should
+     only be called once for any particular object.
+
+     This changes the state of an object to indicate:
+
+	(1) if no call to fscache_object_lookup_negative() has been made on
+	    this object, that there may be data available, and that reads can
+	    now go and look for it; and
+
+        (2) that writes may now proceed against this object.
+
+
+ (*) Indicate that object lookup failed:
+
+	void fscache_object_lookup_error(struct fscache_object *object);
+
+     This marks an object as having encountered a fatal error (usually EIO)
+     and causes it to move into a state whereby it will be withdrawn as soon
+     as possible.
+
+
+ (*) Get and release references on a retrieval record:
+
+	void fscache_get_retrieval(struct fscache_retrieval *op);
+	void fscache_put_retrieval(struct fscache_retrieval *op);
+
+     These two functions are used to retain a retrieval record whilst doing
+     asynchronous data retrieval and block allocation.
+
+
+ (*) Enqueue a retrieval record for processing.
+
+	void fscache_enqueue_retrieval(struct fscache_retrieval *op);
+
+     This enqueues a retrieval record for processing by the FS-Cache thread
+     pool.  One of the threads in the pool will invoke the retrieval record's
+     op->op.processor callback function.  This function may be called from
+     within the callback function.
+
+
+ (*) List of object state names:
+
+	const char *fscache_object_states[];
+
+     For debugging purposes, this may be used to turn the state that an object
+     is in into a text string for display purposes.
diff --git a/Documentation/filesystems/caching/cachefiles.txt b/Documentation/filesystems/caching/cachefiles.txt
new file mode 100644
index 000000000000..c78a49b7bba6
--- /dev/null
+++ b/Documentation/filesystems/caching/cachefiles.txt
@@ -0,0 +1,501 @@
+	       ===============================================
+	       CacheFiles: CACHE ON ALREADY MOUNTED FILESYSTEM
+	       ===============================================
+
+Contents:
+
+ (*) Overview.
+
+ (*) Requirements.
+
+ (*) Configuration.
+
+ (*) Starting the cache.
+
+ (*) Things to avoid.
+
+ (*) Cache culling.
+
+ (*) Cache structure.
+
+ (*) Security model and SELinux.
+
+ (*) A note on security.
+
+ (*) Statistical information.
+
+ (*) Debugging.
+
+
+========
+OVERVIEW
+========
+
+CacheFiles is a caching backend that's meant to use as a cache a directory on
+an already mounted filesystem of a local type (such as Ext3).
+
+CacheFiles uses a userspace daemon to do some of the cache management - such as
+reaping stale nodes and culling.  This is called cachefilesd and lives in
+/sbin.
+
+The filesystem and data integrity of the cache are only as good as those of the
+filesystem providing the backing services.  Note that CacheFiles does not
+attempt to journal anything since the journalling interfaces of the various
+filesystems are very specific in nature.
+
+CacheFiles creates a misc character device - "/dev/cachefiles" - that is used
+to communication with the daemon.  Only one thing may have this open at once,
+and whilst it is open, a cache is at least partially in existence.  The daemon
+opens this and sends commands down it to control the cache.
+
+CacheFiles is currently limited to a single cache.
+
+CacheFiles attempts to maintain at least a certain percentage of free space on
+the filesystem, shrinking the cache by culling the objects it contains to make
+space if necessary - see the "Cache Culling" section.  This means it can be
+placed on the same medium as a live set of data, and will expand to make use of
+spare space and automatically contract when the set of data requires more
+space.
+
+
+============
+REQUIREMENTS
+============
+
+The use of CacheFiles and its daemon requires the following features to be
+available in the system and in the cache filesystem:
+
+	- dnotify.
+
+	- extended attributes (xattrs).
+
+	- openat() and friends.
+
+	- bmap() support on files in the filesystem (FIBMAP ioctl).
+
+	- The use of bmap() to detect a partial page at the end of the file.
+
+It is strongly recommended that the "dir_index" option is enabled on Ext3
+filesystems being used as a cache.
+
+
+=============
+CONFIGURATION
+=============
+
+The cache is configured by a script in /etc/cachefilesd.conf.  These commands
+set up cache ready for use.  The following script commands are available:
+
+ (*) brun <N>%
+ (*) bcull <N>%
+ (*) bstop <N>%
+ (*) frun <N>%
+ (*) fcull <N>%
+ (*) fstop <N>%
+
+	Configure the culling limits.  Optional.  See the section on culling
+	The defaults are 7% (run), 5% (cull) and 1% (stop) respectively.
+
+	The commands beginning with a 'b' are file space (block) limits, those
+	beginning with an 'f' are file count limits.
+
+ (*) dir <path>
+
+	Specify the directory containing the root of the cache.  Mandatory.
+
+ (*) tag <name>
+
+	Specify a tag to FS-Cache to use in distinguishing multiple caches.
+	Optional.  The default is "CacheFiles".
+
+ (*) debug <mask>
+
+	Specify a numeric bitmask to control debugging in the kernel module.
+	Optional.  The default is zero (all off).  The following values can be
+	OR'd into the mask to collect various information:
+
+		1	Turn on trace of function entry (_enter() macros)
+		2	Turn on trace of function exit (_leave() macros)
+		4	Turn on trace of internal debug points (_debug())
+
+	This mask can also be set through sysfs, eg:
+
+		echo 5 >/sys/modules/cachefiles/parameters/debug
+
+
+==================
+STARTING THE CACHE
+==================
+
+The cache is started by running the daemon.  The daemon opens the cache device,
+configures the cache and tells it to begin caching.  At that point the cache
+binds to fscache and the cache becomes live.
+
+The daemon is run as follows:
+
+	/sbin/cachefilesd [-d]* [-s] [-n] [-f <configfile>]
+
+The flags are:
+
+ (*) -d
+
+	Increase the debugging level.  This can be specified multiple times and
+	is cumulative with itself.
+
+ (*) -s
+
+	Send messages to stderr instead of syslog.
+
+ (*) -n
+
+	Don't daemonise and go into background.
+
+ (*) -f <configfile>
+
+	Use an alternative configuration file rather than the default one.
+
+
+===============
+THINGS TO AVOID
+===============
+
+Do not mount other things within the cache as this will cause problems.  The
+kernel module contains its own very cut-down path walking facility that ignores
+mountpoints, but the daemon can't avoid them.
+
+Do not create, rename or unlink files and directories in the cache whilst the
+cache is active, as this may cause the state to become uncertain.
+
+Renaming files in the cache might make objects appear to be other objects (the
+filename is part of the lookup key).
+
+Do not change or remove the extended attributes attached to cache files by the
+cache as this will cause the cache state management to get confused.
+
+Do not create files or directories in the cache, lest the cache get confused or
+serve incorrect data.
+
+Do not chmod files in the cache.  The module creates things with minimal
+permissions to prevent random users being able to access them directly.
+
+
+=============
+CACHE CULLING
+=============
+
+The cache may need culling occasionally to make space.  This involves
+discarding objects from the cache that have been used less recently than
+anything else.  Culling is based on the access time of data objects.  Empty
+directories are culled if not in use.
+
+Cache culling is done on the basis of the percentage of blocks and the
+percentage of files available in the underlying filesystem.  There are six
+"limits":
+
+ (*) brun
+ (*) frun
+
+     If the amount of free space and the number of available files in the cache
+     rises above both these limits, then culling is turned off.
+
+ (*) bcull
+ (*) fcull
+
+     If the amount of available space or the number of available files in the
+     cache falls below either of these limits, then culling is started.
+
+ (*) bstop
+ (*) fstop
+
+     If the amount of available space or the number of available files in the
+     cache falls below either of these limits, then no further allocation of
+     disk space or files is permitted until culling has raised things above
+     these limits again.
+
+These must be configured thusly:
+
+	0 <= bstop < bcull < brun < 100
+	0 <= fstop < fcull < frun < 100
+
+Note that these are percentages of available space and available files, and do
+_not_ appear as 100 minus the percentage displayed by the "df" program.
+
+The userspace daemon scans the cache to build up a table of cullable objects.
+These are then culled in least recently used order.  A new scan of the cache is
+started as soon as space is made in the table.  Objects will be skipped if
+their atimes have changed or if the kernel module says it is still using them.
+
+
+===============
+CACHE STRUCTURE
+===============
+
+The CacheFiles module will create two directories in the directory it was
+given:
+
+ (*) cache/
+
+ (*) graveyard/
+
+The active cache objects all reside in the first directory.  The CacheFiles
+kernel module moves any retired or culled objects that it can't simply unlink
+to the graveyard from which the daemon will actually delete them.
+
+The daemon uses dnotify to monitor the graveyard directory, and will delete
+anything that appears therein.
+
+
+The module represents index objects as directories with the filename "I..." or
+"J...".  Note that the "cache/" directory is itself a special index.
+
+Data objects are represented as files if they have no children, or directories
+if they do.  Their filenames all begin "D..." or "E...".  If represented as a
+directory, data objects will have a file in the directory called "data" that
+actually holds the data.
+
+Special objects are similar to data objects, except their filenames begin
+"S..." or "T...".
+
+
+If an object has children, then it will be represented as a directory.
+Immediately in the representative directory are a collection of directories
+named for hash values of the child object keys with an '@' prepended.  Into
+this directory, if possible, will be placed the representations of the child
+objects:
+
+	INDEX     INDEX      INDEX                             DATA FILES
+	========= ========== ================================= ================
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...DB1ry
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...N22ry
+	cache/@4a/I03nfs/@30/Ji000000000000000--fHg8hi8400/@75/Es0g000w...FP1ry
+
+
+If the key is so long that it exceeds NAME_MAX with the decorations added on to
+it, then it will be cut into pieces, the first few of which will be used to
+make a nest of directories, and the last one of which will be the objects
+inside the last directory.  The names of the intermediate directories will have
+'+' prepended:
+
+	J1223/@23/+xy...z/+kl...m/Epqr
+
+
+Note that keys are raw data, and not only may they exceed NAME_MAX in size,
+they may also contain things like '/' and NUL characters, and so they may not
+be suitable for turning directly into a filename.
+
+To handle this, CacheFiles will use a suitably printable filename directly and
+"base-64" encode ones that aren't directly suitable.  The two versions of
+object filenames indicate the encoding:
+
+	OBJECT TYPE	PRINTABLE	ENCODED
+	===============	===============	===============
+	Index		"I..."		"J..."
+	Data		"D..."		"E..."
+	Special		"S..."		"T..."
+
+Intermediate directories are always "@" or "+" as appropriate.
+
+
+Each object in the cache has an extended attribute label that holds the object
+type ID (required to distinguish special objects) and the auxiliary data from
+the netfs.  The latter is used to detect stale objects in the cache and update
+or retire them.
+
+
+Note that CacheFiles will erase from the cache any file it doesn't recognise or
+any file of an incorrect type (such as a FIFO file or a device file).
+
+
+==========================
+SECURITY MODEL AND SELINUX
+==========================
+
+CacheFiles is implemented to deal properly with the LSM security features of
+the Linux kernel and the SELinux facility.
+
+One of the problems that CacheFiles faces is that it is generally acting on
+behalf of a process, and running in that process's context, and that includes a
+security context that is not appropriate for accessing the cache - either
+because the files in the cache are inaccessible to that process, or because if
+the process creates a file in the cache, that file may be inaccessible to other
+processes.
+
+The way CacheFiles works is to temporarily change the security context (fsuid,
+fsgid and actor security label) that the process acts as - without changing the
+security context of the process when it the target of an operation performed by
+some other process (so signalling and suchlike still work correctly).
+
+
+When the CacheFiles module is asked to bind to its cache, it:
+
+ (1) Finds the security label attached to the root cache directory and uses
+     that as the security label with which it will create files.  By default,
+     this is:
+
+	cachefiles_var_t
+
+ (2) Finds the security label of the process which issued the bind request
+     (presumed to be the cachefilesd daemon), which by default will be:
+
+	cachefilesd_t
+
+     and asks LSM to supply a security ID as which it should act given the
+     daemon's label.  By default, this will be:
+
+	cachefiles_kernel_t
+
+     SELinux transitions the daemon's security ID to the module's security ID
+     based on a rule of this form in the policy.
+
+	type_transition <daemon's-ID> kernel_t : process <module's-ID>;
+
+     For instance:
+
+	type_transition cachefilesd_t kernel_t : process cachefiles_kernel_t;
+
+
+The module's security ID gives it permission to create, move and remove files
+and directories in the cache, to find and access directories and files in the
+cache, to set and access extended attributes on cache objects, and to read and
+write files in the cache.
+
+The daemon's security ID gives it only a very restricted set of permissions: it
+may scan directories, stat files and erase files and directories.  It may
+not read or write files in the cache, and so it is precluded from accessing the
+data cached therein; nor is it permitted to create new files in the cache.
+
+
+There are policy source files available in:
+
+	http://people.redhat.com/~dhowells/fscache/cachefilesd-0.8.tar.bz2
+
+and later versions.  In that tarball, see the files:
+
+	cachefilesd.te
+	cachefilesd.fc
+	cachefilesd.if
+
+They are built and installed directly by the RPM.
+
+If a non-RPM based system is being used, then copy the above files to their own
+directory and run:
+
+	make -f /usr/share/selinux/devel/Makefile
+	semodule -i cachefilesd.pp
+
+You will need checkpolicy and selinux-policy-devel installed prior to the
+build.
+
+
+By default, the cache is located in /var/fscache, but if it is desirable that
+it should be elsewhere, than either the above policy files must be altered, or
+an auxiliary policy must be installed to label the alternate location of the
+cache.
+
+For instructions on how to add an auxiliary policy to enable the cache to be
+located elsewhere when SELinux is in enforcing mode, please see:
+
+	/usr/share/doc/cachefilesd-*/move-cache.txt
+
+When the cachefilesd rpm is installed; alternatively, the document can be found
+in the sources.
+
+
+==================
+A NOTE ON SECURITY
+==================
+
+CacheFiles makes use of the split security in the task_struct.  It allocates
+its own task_security structure, and redirects current->act_as to point to it
+when it acts on behalf of another process, in that process's context.
+
+The reason it does this is that it calls vfs_mkdir() and suchlike rather than
+bypassing security and calling inode ops directly.  Therefore the VFS and LSM
+may deny the CacheFiles access to the cache data because under some
+circumstances the caching code is running in the security context of whatever
+process issued the original syscall on the netfs.
+
+Furthermore, should CacheFiles create a file or directory, the security
+parameters with that object is created (UID, GID, security label) would be
+derived from that process that issued the system call, thus potentially
+preventing other processes from accessing the cache - including CacheFiles's
+cache management daemon (cachefilesd).
+
+What is required is to temporarily override the security of the process that
+issued the system call.  We can't, however, just do an in-place change of the
+security data as that affects the process as an object, not just as a subject.
+This means it may lose signals or ptrace events for example, and affects what
+the process looks like in /proc.
+
+So CacheFiles makes use of a logical split in the security between the
+objective security (task->sec) and the subjective security (task->act_as).  The
+objective security holds the intrinsic security properties of a process and is
+never overridden.  This is what appears in /proc, and is what is used when a
+process is the target of an operation by some other process (SIGKILL for
+example).
+
+The subjective security holds the active security properties of a process, and
+may be overridden.  This is not seen externally, and is used whan a process
+acts upon another object, for example SIGKILLing another process or opening a
+file.
+
+LSM hooks exist that allow SELinux (or Smack or whatever) to reject a request
+for CacheFiles to run in a context of a specific security label, or to create
+files and directories with another security label.
+
+
+=======================
+STATISTICAL INFORMATION
+=======================
+
+If FS-Cache is compiled with the following option enabled:
+
+	CONFIG_CACHEFILES_HISTOGRAM=y
+
+then it will gather certain statistics and display them through a proc file.
+
+ (*) /proc/fs/cachefiles/histogram
+
+	cat /proc/fs/cachefiles/histogram
+	JIFS  SECS  LOOKUPS   MKDIRS    CREATES
+	===== ===== ========= ========= =========
+
+     This shows the breakdown of the number of times each amount of time
+     between 0 jiffies and HZ-1 jiffies a variety of tasks took to run.  The
+     columns are as follows:
+
+	COLUMN		TIME MEASUREMENT
+	=======		=======================================================
+	LOOKUPS		Length of time to perform a lookup on the backing fs
+	MKDIRS		Length of time to perform a mkdir on the backing fs
+	CREATES		Length of time to perform a create on the backing fs
+
+     Each row shows the number of events that took a particular range of times.
+     Each step is 1 jiffy in size.  The JIFS column indicates the particular
+     jiffy range covered, and the SECS field the equivalent number of seconds.
+
+
+=========
+DEBUGGING
+=========
+
+If CONFIG_CACHEFILES_DEBUG is enabled, the CacheFiles facility can have runtime
+debugging enabled by adjusting the value in:
+
+	/sys/module/cachefiles/parameters/debug
+
+This is a bitmask of debugging streams to enable:
+
+	BIT	VALUE	STREAM				POINT
+	=======	=======	===============================	=======================
+	0	1	General				Function entry trace
+	1	2					Function exit trace
+	2	4					General
+
+The appropriate set of values should be OR'd together and the result written to
+the control file.  For example:
+
+	echo $((1|4|8)) >/sys/module/cachefiles/parameters/debug
+
+will turn on all function entry debugging.
diff --git a/Documentation/filesystems/caching/fscache.txt b/Documentation/filesystems/caching/fscache.txt
new file mode 100644
index 000000000000..9e94b9491d89
--- /dev/null
+++ b/Documentation/filesystems/caching/fscache.txt
@@ -0,0 +1,333 @@
+			  ==========================
+			  General Filesystem Caching
+			  ==========================
+
+========
+OVERVIEW
+========
+
+This facility is a general purpose cache for network filesystems, though it
+could be used for caching other things such as ISO9660 filesystems too.
+
+FS-Cache mediates between cache backends (such as CacheFS) and network
+filesystems:
+
+	+---------+
+	|         |                        +--------------+
+	|   NFS   |--+                     |              |
+	|         |  |                 +-->|   CacheFS    |
+	+---------+  |   +----------+  |   |  /dev/hda5   |
+	             |   |          |  |   +--------------+
+	+---------+  +-->|          |  |
+	|         |      |          |--+
+	|   AFS   |----->| FS-Cache |
+	|         |      |          |--+
+	+---------+  +-->|          |  |
+	             |   |          |  |   +--------------+
+	+---------+  |   +----------+  |   |              |
+	|         |  |                 +-->|  CacheFiles  |
+	|  ISOFS  |--+                     |  /var/cache  |
+	|         |                        +--------------+
+	+---------+
+
+Or to look at it another way, FS-Cache is a module that provides a caching
+facility to a network filesystem such that the cache is transparent to the
+user:
+
+	+---------+
+	|         |
+	| Server  |
+	|         |
+	+---------+
+	     |                  NETWORK
+	~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
+	     |
+	     |           +----------+
+	     V           |          |
+	+---------+      |          |
+	|         |      |          |
+	|   NFS   |----->| FS-Cache |
+	|         |      |          |--+
+	+---------+      |          |  |   +--------------+   +--------------+
+	     |           |          |  |   |              |   |              |
+	     V           +----------+  +-->|  CacheFiles  |-->|  Ext3        |
+	+---------+                        |  /var/cache  |   |  /dev/sda6   |
+	|         |                        +--------------+   +--------------+
+	|   VFS   |                                ^                     ^
+	|         |                                |                     |
+	+---------+                                +--------------+      |
+	     |                  KERNEL SPACE                      |      |
+	~~~~~|~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~|~~~~~~|~~~~
+	     |                  USER SPACE                        |      |
+	     V                                                    |      |
+	+---------+                                           +--------------+
+	|         |                                           |              |
+	| Process |                                           | cachefilesd  |
+	|         |                                           |              |
+	+---------+                                           +--------------+
+
+
+FS-Cache does not follow the idea of completely loading every netfs file
+opened in its entirety into a cache before permitting it to be accessed and
+then serving the pages out of that cache rather than the netfs inode because:
+
+ (1) It must be practical to operate without a cache.
+
+ (2) The size of any accessible file must not be limited to the size of the
+     cache.
+
+ (3) The combined size of all opened files (this includes mapped libraries)
+     must not be limited to the size of the cache.
+
+ (4) The user should not be forced to download an entire file just to do a
+     one-off access of a small portion of it (such as might be done with the
+     "file" program).
+
+It instead serves the cache out in PAGE_SIZE chunks as and when requested by
+the netfs('s) using it.
+
+
+FS-Cache provides the following facilities:
+
+ (1) More than one cache can be used at once.  Caches can be selected
+     explicitly by use of tags.
+
+ (2) Caches can be added / removed at any time.
+
+ (3) The netfs is provided with an interface that allows either party to
+     withdraw caching facilities from a file (required for (2)).
+
+ (4) The interface to the netfs returns as few errors as possible, preferring
+     rather to let the netfs remain oblivious.
+
+ (5) Cookies are used to represent indices, files and other objects to the
+     netfs.  The simplest cookie is just a NULL pointer - indicating nothing
+     cached there.
+
+ (6) The netfs is allowed to propose - dynamically - any index hierarchy it
+     desires, though it must be aware that the index search function is
+     recursive, stack space is limited, and indices can only be children of
+     indices.
+
+ (7) Data I/O is done direct to and from the netfs's pages.  The netfs
+     indicates that page A is at index B of the data-file represented by cookie
+     C, and that it should be read or written.  The cache backend may or may
+     not start I/O on that page, but if it does, a netfs callback will be
+     invoked to indicate completion.  The I/O may be either synchronous or
+     asynchronous.
+
+ (8) Cookies can be "retired" upon release.  At this point FS-Cache will mark
+     them as obsolete and the index hierarchy rooted at that point will get
+     recycled.
+
+ (9) The netfs provides a "match" function for index searches.  In addition to
+     saying whether a match was made or not, this can also specify that an
+     entry should be updated or deleted.
+
+(10) As much as possible is done asynchronously.
+
+
+FS-Cache maintains a virtual indexing tree in which all indices, files, objects
+and pages are kept.  Bits of this tree may actually reside in one or more
+caches.
+
+                                           FSDEF
+                                             |
+                        +------------------------------------+
+                        |                                    |
+                       NFS                                  AFS
+                        |                                    |
+           +--------------------------+                +-----------+
+           |                          |                |           |
+        homedir                     mirror          afs.org   redhat.com
+           |                          |                            |
+     +------------+           +---------------+              +----------+
+     |            |           |               |              |          |
+   00001        00002       00007           00125        vol00001   vol00002
+     |            |           |               |                         |
+ +---+---+     +-----+      +---+      +------+------+            +-----+----+
+ |   |   |     |     |      |   |      |      |      |            |     |    |
+PG0 PG1 PG2   PG0  XATTR   PG0 PG1   DIRENT DIRENT DIRENT        R/W   R/O  Bak
+                     |                                            |
+                    PG0                                       +-------+
+                                                              |       |
+                                                            00001   00003
+                                                              |
+                                                          +---+---+
+                                                          |   |   |
+                                                         PG0 PG1 PG2
+
+In the example above, you can see two netfs's being backed: NFS and AFS.  These
+have different index hierarchies:
+
+ (*) The NFS primary index contains per-server indices.  Each server index is
+     indexed by NFS file handles to get data file objects.  Each data file
+     objects can have an array of pages, but may also have further child
+     objects, such as extended attributes and directory entries.  Extended
+     attribute objects themselves have page-array contents.
+
+ (*) The AFS primary index contains per-cell indices.  Each cell index contains
+     per-logical-volume indices.  Each of volume index contains up to three
+     indices for the read-write, read-only and backup mirrors of those volumes.
+     Each of these contains vnode data file objects, each of which contains an
+     array of pages.
+
+The very top index is the FS-Cache master index in which individual netfs's
+have entries.
+
+Any index object may reside in more than one cache, provided it only has index
+children.  Any index with non-index object children will be assumed to only
+reside in one cache.
+
+
+The netfs API to FS-Cache can be found in:
+
+	Documentation/filesystems/caching/netfs-api.txt
+
+The cache backend API to FS-Cache can be found in:
+
+	Documentation/filesystems/caching/backend-api.txt
+
+A description of the internal representations and object state machine can be
+found in:
+
+	Documentation/filesystems/caching/object.txt
+
+
+=======================
+STATISTICAL INFORMATION
+=======================
+
+If FS-Cache is compiled with the following options enabled:
+
+	CONFIG_FSCACHE_STATS=y
+	CONFIG_FSCACHE_HISTOGRAM=y
+
+then it will gather certain statistics and display them through a number of
+proc files.
+
+ (*) /proc/fs/fscache/stats
+
+     This shows counts of a number of events that can happen in FS-Cache:
+
+	CLASS	EVENT	MEANING
+	=======	=======	=======================================================
+	Cookies	idx=N	Number of index cookies allocated
+		dat=N	Number of data storage cookies allocated
+		spc=N	Number of special cookies allocated
+	Objects	alc=N	Number of objects allocated
+		nal=N	Number of object allocation failures
+		avl=N	Number of objects that reached the available state
+		ded=N	Number of objects that reached the dead state
+	ChkAux	non=N	Number of objects that didn't have a coherency check
+		ok=N	Number of objects that passed a coherency check
+		upd=N	Number of objects that needed a coherency data update
+		obs=N	Number of objects that were declared obsolete
+	Pages	mrk=N	Number of pages marked as being cached
+		unc=N	Number of uncache page requests seen
+	Acquire	n=N	Number of acquire cookie requests seen
+		nul=N	Number of acq reqs given a NULL parent
+		noc=N	Number of acq reqs rejected due to no cache available
+		ok=N	Number of acq reqs succeeded
+		nbf=N	Number of acq reqs rejected due to error
+		oom=N	Number of acq reqs failed on ENOMEM
+	Lookups	n=N	Number of lookup calls made on cache backends
+		neg=N	Number of negative lookups made
+		pos=N	Number of positive lookups made
+		crt=N	Number of objects created by lookup
+	Updates	n=N	Number of update cookie requests seen
+		nul=N	Number of upd reqs given a NULL parent
+		run=N	Number of upd reqs granted CPU time
+	Relinqs	n=N	Number of relinquish cookie requests seen
+		nul=N	Number of rlq reqs given a NULL parent
+		wcr=N	Number of rlq reqs waited on completion of creation
+	AttrChg	n=N	Number of attribute changed requests seen
+		ok=N	Number of attr changed requests queued
+		nbf=N	Number of attr changed rejected -ENOBUFS
+		oom=N	Number of attr changed failed -ENOMEM
+		run=N	Number of attr changed ops given CPU time
+	Allocs	n=N	Number of allocation requests seen
+		ok=N	Number of successful alloc reqs
+		wt=N	Number of alloc reqs that waited on lookup completion
+		nbf=N	Number of alloc reqs rejected -ENOBUFS
+		ops=N	Number of alloc reqs submitted
+		owt=N	Number of alloc reqs waited for CPU time
+	Retrvls	n=N	Number of retrieval (read) requests seen
+		ok=N	Number of successful retr reqs
+		wt=N	Number of retr reqs that waited on lookup completion
+		nod=N	Number of retr reqs returned -ENODATA
+		nbf=N	Number of retr reqs rejected -ENOBUFS
+		int=N	Number of retr reqs aborted -ERESTARTSYS
+		oom=N	Number of retr reqs failed -ENOMEM
+		ops=N	Number of retr reqs submitted
+		owt=N	Number of retr reqs waited for CPU time
+	Stores	n=N	Number of storage (write) requests seen
+		ok=N	Number of successful store reqs
+		agn=N	Number of store reqs on a page already pending storage
+		nbf=N	Number of store reqs rejected -ENOBUFS
+		oom=N	Number of store reqs failed -ENOMEM
+		ops=N	Number of store reqs submitted
+		run=N	Number of store reqs granted CPU time
+	Ops	pend=N	Number of times async ops added to pending queues
+		run=N	Number of times async ops given CPU time
+		enq=N	Number of times async ops queued for processing
+		dfr=N	Number of async ops queued for deferred release
+		rel=N	Number of async ops released
+		gc=N	Number of deferred-release async ops garbage collected
+
+
+ (*) /proc/fs/fscache/histogram
+
+	cat /proc/fs/fscache/histogram
+	JIFS  SECS  OBJ INST  OP RUNS   OBJ RUNS  RETRV DLY RETRIEVLS
+	===== ===== ========= ========= ========= ========= =========
+
+     This shows the breakdown of the number of times each amount of time
+     between 0 jiffies and HZ-1 jiffies a variety of tasks took to run.  The
+     columns are as follows:
+
+	COLUMN		TIME MEASUREMENT
+	=======		=======================================================
+	OBJ INST	Length of time to instantiate an object
+	OP RUNS		Length of time a call to process an operation took
+	OBJ RUNS	Length of time a call to process an object event took
+	RETRV DLY	Time between an requesting a read and lookup completing
+	RETRIEVLS	Time between beginning and end of a retrieval
+
+     Each row shows the number of events that took a particular range of times.
+     Each step is 1 jiffy in size.  The JIFS column indicates the particular
+     jiffy range covered, and the SECS field the equivalent number of seconds.
+
+
+=========
+DEBUGGING
+=========
+
+If CONFIG_FSCACHE_DEBUG is enabled, the FS-Cache facility can have runtime
+debugging enabled by adjusting the value in:
+
+	/sys/module/fscache/parameters/debug
+
+This is a bitmask of debugging streams to enable:
+
+	BIT	VALUE	STREAM				POINT
+	=======	=======	===============================	=======================
+	0	1	Cache management		Function entry trace
+	1	2					Function exit trace
+	2	4					General
+	3	8	Cookie management		Function entry trace
+	4	16					Function exit trace
+	5	32					General
+	6	64	Page handling			Function entry trace
+	7	128					Function exit trace
+	8	256					General
+	9	512	Operation management		Function entry trace
+	10	1024					Function exit trace
+	11	2048					General
+
+The appropriate set of values should be OR'd together and the result written to
+the control file.  For example:
+
+	echo $((1|8|64)) >/sys/module/fscache/parameters/debug
+
+will turn on all function entry debugging.
diff --git a/Documentation/filesystems/caching/netfs-api.txt b/Documentation/filesystems/caching/netfs-api.txt
new file mode 100644
index 000000000000..4db125b3a5c6
--- /dev/null
+++ b/Documentation/filesystems/caching/netfs-api.txt
@@ -0,0 +1,778 @@
+			===============================
+			FS-CACHE NETWORK FILESYSTEM API
+			===============================
+
+There's an API by which a network filesystem can make use of the FS-Cache
+facilities.  This is based around a number of principles:
+
+ (1) Caches can store a number of different object types.  There are two main
+     object types: indices and files.  The first is a special type used by
+     FS-Cache to make finding objects faster and to make retiring of groups of
+     objects easier.
+
+ (2) Every index, file or other object is represented by a cookie.  This cookie
+     may or may not have anything associated with it, but the netfs doesn't
+     need to care.
+
+ (3) Barring the top-level index (one entry per cached netfs), the index
+     hierarchy for each netfs is structured according the whim of the netfs.
+
+This API is declared in <linux/fscache.h>.
+
+This document contains the following sections:
+
+	 (1) Network filesystem definition
+	 (2) Index definition
+	 (3) Object definition
+	 (4) Network filesystem (un)registration
+	 (5) Cache tag lookup
+	 (6) Index registration
+	 (7) Data file registration
+	 (8) Miscellaneous object registration
+	 (9) Setting the data file size
+	(10) Page alloc/read/write
+	(11) Page uncaching
+	(12) Index and data file update
+	(13) Miscellaneous cookie operations
+	(14) Cookie unregistration
+	(15) Index and data file invalidation
+	(16) FS-Cache specific page flags.
+
+
+=============================
+NETWORK FILESYSTEM DEFINITION
+=============================
+
+FS-Cache needs a description of the network filesystem.  This is specified
+using a record of the following structure:
+
+	struct fscache_netfs {
+		uint32_t			version;
+		const char			*name;
+		struct fscache_cookie		*primary_index;
+		...
+	};
+
+This first two fields should be filled in before registration, and the third
+will be filled in by the registration function; any other fields should just be
+ignored and are for internal use only.
+
+The fields are:
+
+ (1) The name of the netfs (used as the key in the toplevel index).
+
+ (2) The version of the netfs (if the name matches but the version doesn't, the
+     entire in-cache hierarchy for this netfs will be scrapped and begun
+     afresh).
+
+ (3) The cookie representing the primary index will be allocated according to
+     another parameter passed into the registration function.
+
+For example, kAFS (linux/fs/afs/) uses the following definitions to describe
+itself:
+
+	struct fscache_netfs afs_cache_netfs = {
+		.version	= 0,
+		.name		= "afs",
+	};
+
+
+================
+INDEX DEFINITION
+================
+
+Indices are used for two purposes:
+
+ (1) To aid the finding of a file based on a series of keys (such as AFS's
+     "cell", "volume ID", "vnode ID").
+
+ (2) To make it easier to discard a subset of all the files cached based around
+     a particular key - for instance to mirror the removal of an AFS volume.
+
+However, since it's unlikely that any two netfs's are going to want to define
+their index hierarchies in quite the same way, FS-Cache tries to impose as few
+restraints as possible on how an index is structured and where it is placed in
+the tree.  The netfs can even mix indices and data files at the same level, but
+it's not recommended.
+
+Each index entry consists of a key of indeterminate length plus some auxilliary
+data, also of indeterminate length.
+
+There are some limits on indices:
+
+ (1) Any index containing non-index objects should be restricted to a single
+     cache.  Any such objects created within an index will be created in the
+     first cache only.  The cache in which an index is created can be
+     controlled by cache tags (see below).
+
+ (2) The entry data must be atomically journallable, so it is limited to about
+     400 bytes at present.  At least 400 bytes will be available.
+
+ (3) The depth of the index tree should be judged with care as the search
+     function is recursive.  Too many layers will run the kernel out of stack.
+
+
+=================
+OBJECT DEFINITION
+=================
+
+To define an object, a structure of the following type should be filled out:
+
+	struct fscache_cookie_def
+	{
+		uint8_t name[16];
+		uint8_t type;
+
+		struct fscache_cache_tag *(*select_cache)(
+			const void *parent_netfs_data,
+			const void *cookie_netfs_data);
+
+		uint16_t (*get_key)(const void *cookie_netfs_data,
+				    void *buffer,
+				    uint16_t bufmax);
+
+		void (*get_attr)(const void *cookie_netfs_data,
+				 uint64_t *size);
+
+		uint16_t (*get_aux)(const void *cookie_netfs_data,
+				    void *buffer,
+				    uint16_t bufmax);
+
+		enum fscache_checkaux (*check_aux)(void *cookie_netfs_data,
+						   const void *data,
+						   uint16_t datalen);
+
+		void (*get_context)(void *cookie_netfs_data, void *context);
+
+		void (*put_context)(void *cookie_netfs_data, void *context);
+
+		void (*mark_pages_cached)(void *cookie_netfs_data,
+					  struct address_space *mapping,
+					  struct pagevec *cached_pvec);
+
+		void (*now_uncached)(void *cookie_netfs_data);
+	};
+
+This has the following fields:
+
+ (1) The type of the object [mandatory].
+
+     This is one of the following values:
+
+	(*) FSCACHE_COOKIE_TYPE_INDEX
+
+	    This defines an index, which is a special FS-Cache type.
+
+	(*) FSCACHE_COOKIE_TYPE_DATAFILE
+
+	    This defines an ordinary data file.
+
+	(*) Any other value between 2 and 255
+
+	    This defines an extraordinary object such as an XATTR.
+
+ (2) The name of the object type (NUL terminated unless all 16 chars are used)
+     [optional].
+
+ (3) A function to select the cache in which to store an index [optional].
+
+     This function is invoked when an index needs to be instantiated in a cache
+     during the instantiation of a non-index object.  Only the immediate index
+     parent for the non-index object will be queried.  Any indices above that
+     in the hierarchy may be stored in multiple caches.  This function does not
+     need to be supplied for any non-index object or any index that will only
+     have index children.
+
+     If this function is not supplied or if it returns NULL then the first
+     cache in the parent's list will be chosed, or failing that, the first
+     cache in the master list.
+
+ (4) A function to retrieve an object's key from the netfs [mandatory].
+
+     This function will be called with the netfs data that was passed to the
+     cookie acquisition function and the maximum length of key data that it may
+     provide.  It should write the required key data into the given buffer and
+     return the quantity it wrote.
+
+ (5) A function to retrieve attribute data from the netfs [optional].
+
+     This function will be called with the netfs data that was passed to the
+     cookie acquisition function.  It should return the size of the file if
+     this is a data file.  The size may be used to govern how much cache must
+     be reserved for this file in the cache.
+
+     If the function is absent, a file size of 0 is assumed.
+
+ (6) A function to retrieve auxilliary data from the netfs [optional].
+
+     This function will be called with the netfs data that was passed to the
+     cookie acquisition function and the maximum length of auxilliary data that
+     it may provide.  It should write the auxilliary data into the given buffer
+     and return the quantity it wrote.
+
+     If this function is absent, the auxilliary data length will be set to 0.
+
+     The length of the auxilliary data buffer may be dependent on the key
+     length.  A netfs mustn't rely on being able to provide more than 400 bytes
+     for both.
+
+ (7) A function to check the auxilliary data [optional].
+
+     This function will be called to check that a match found in the cache for
+     this object is valid.  For instance with AFS it could check the auxilliary
+     data against the data version number returned by the server to determine
+     whether the index entry in a cache is still valid.
+
+     If this function is absent, it will be assumed that matching objects in a
+     cache are always valid.
+
+     If present, the function should return one of the following values:
+
+	(*) FSCACHE_CHECKAUX_OKAY		- the entry is okay as is
+	(*) FSCACHE_CHECKAUX_NEEDS_UPDATE	- the entry requires update
+	(*) FSCACHE_CHECKAUX_OBSOLETE		- the entry should be deleted
+
+     This function can also be used to extract data from the auxilliary data in
+     the cache and copy it into the netfs's structures.
+
+ (8) A pair of functions to manage contexts for the completion callback
+     [optional].
+
+     The cache read/write functions are passed a context which is then passed
+     to the I/O completion callback function.  To ensure this context remains
+     valid until after the I/O completion is called, two functions may be
+     provided: one to get an extra reference on the context, and one to drop a
+     reference to it.
+
+     If the context is not used or is a type of object that won't go out of
+     scope, then these functions are not required.  These functions are not
+     required for indices as indices may not contain data.  These functions may
+     be called in interrupt context and so may not sleep.
+
+ (9) A function to mark a page as retaining cache metadata [optional].
+
+     This is called by the cache to indicate that it is retaining in-memory
+     information for this page and that the netfs should uncache the page when
+     it has finished.  This does not indicate whether there's data on the disk
+     or not.  Note that several pages at once may be presented for marking.
+
+     The PG_fscache bit is set on the pages before this function would be
+     called, so the function need not be provided if this is sufficient.
+
+     This function is not required for indices as they're not permitted data.
+
+(10) A function to unmark all the pages retaining cache metadata [mandatory].
+
+     This is called by FS-Cache to indicate that a backing store is being
+     unbound from a cookie and that all the marks on the pages should be
+     cleared to prevent confusion.  Note that the cache will have torn down all
+     its tracking information so that the pages don't need to be explicitly
+     uncached.
+
+     This function is not required for indices as they're not permitted data.
+
+
+===================================
+NETWORK FILESYSTEM (UN)REGISTRATION
+===================================
+
+The first step is to declare the network filesystem to the cache.  This also
+involves specifying the layout of the primary index (for AFS, this would be the
+"cell" level).
+
+The registration function is:
+
+	int fscache_register_netfs(struct fscache_netfs *netfs);
+
+It just takes a pointer to the netfs definition.  It returns 0 or an error as
+appropriate.
+
+For kAFS, registration is done as follows:
+
+	ret = fscache_register_netfs(&afs_cache_netfs);
+
+The last step is, of course, unregistration:
+
+	void fscache_unregister_netfs(struct fscache_netfs *netfs);
+
+
+================
+CACHE TAG LOOKUP
+================
+
+FS-Cache permits the use of more than one cache.  To permit particular index
+subtrees to be bound to particular caches, the second step is to look up cache
+representation tags.  This step is optional; it can be left entirely up to
+FS-Cache as to which cache should be used.  The problem with doing that is that
+FS-Cache will always pick the first cache that was registered.
+
+To get the representation for a named tag:
+
+	struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name);
+
+This takes a text string as the name and returns a representation of a tag.  It
+will never return an error.  It may return a dummy tag, however, if it runs out
+of memory; this will inhibit caching with this tag.
+
+Any representation so obtained must be released by passing it to this function:
+
+	void fscache_release_cache_tag(struct fscache_cache_tag *tag);
+
+The tag will be retrieved by FS-Cache when it calls the object definition
+operation select_cache().
+
+
+==================
+INDEX REGISTRATION
+==================
+
+The third step is to inform FS-Cache about part of an index hierarchy that can
+be used to locate files.  This is done by requesting a cookie for each index in
+the path to the file:
+
+	struct fscache_cookie *
+	fscache_acquire_cookie(struct fscache_cookie *parent,
+			       const struct fscache_object_def *def,
+			       void *netfs_data);
+
+This function creates an index entry in the index represented by parent,
+filling in the index entry by calling the operations pointed to by def.
+
+Note that this function never returns an error - all errors are handled
+internally.  It may, however, return NULL to indicate no cookie.  It is quite
+acceptable to pass this token back to this function as the parent to another
+acquisition (or even to the relinquish cookie, read page and write page
+functions - see below).
+
+Note also that no indices are actually created in a cache until a non-index
+object needs to be created somewhere down the hierarchy.  Furthermore, an index
+may be created in several different caches independently at different times.
+This is all handled transparently, and the netfs doesn't see any of it.
+
+For example, with AFS, a cell would be added to the primary index.  This index
+entry would have a dependent inode containing a volume location index for the
+volume mappings within this cell:
+
+	cell->cache =
+		fscache_acquire_cookie(afs_cache_netfs.primary_index,
+				       &afs_cell_cache_index_def,
+				       cell);
+
+Then when a volume location was accessed, it would be entered into the cell's
+index and an inode would be allocated that acts as a volume type and hash chain
+combination:
+
+	vlocation->cache =
+		fscache_acquire_cookie(cell->cache,
+				       &afs_vlocation_cache_index_def,
+				       vlocation);
+
+And then a particular flavour of volume (R/O for example) could be added to
+that index, creating another index for vnodes (AFS inode equivalents):
+
+	volume->cache =
+		fscache_acquire_cookie(vlocation->cache,
+				       &afs_volume_cache_index_def,
+				       volume);
+
+
+======================
+DATA FILE REGISTRATION
+======================
+
+The fourth step is to request a data file be created in the cache.  This is
+identical to index cookie acquisition.  The only difference is that the type in
+the object definition should be something other than index type.
+
+	vnode->cache =
+		fscache_acquire_cookie(volume->cache,
+				       &afs_vnode_cache_object_def,
+				       vnode);
+
+
+=================================
+MISCELLANEOUS OBJECT REGISTRATION
+=================================
+
+An optional step is to request an object of miscellaneous type be created in
+the cache.  This is almost identical to index cookie acquisition.  The only
+difference is that the type in the object definition should be something other
+than index type.  Whilst the parent object could be an index, it's more likely
+it would be some other type of object such as a data file.
+
+	xattr->cache =
+		fscache_acquire_cookie(vnode->cache,
+				       &afs_xattr_cache_object_def,
+				       xattr);
+
+Miscellaneous objects might be used to store extended attributes or directory
+entries for example.
+
+
+==========================
+SETTING THE DATA FILE SIZE
+==========================
+
+The fifth step is to set the physical attributes of the file, such as its size.
+This doesn't automatically reserve any space in the cache, but permits the
+cache to adjust its metadata for data tracking appropriately:
+
+	int fscache_attr_changed(struct fscache_cookie *cookie);
+
+The cache will return -ENOBUFS if there is no backing cache or if there is no
+space to allocate any extra metadata required in the cache.  The attributes
+will be accessed with the get_attr() cookie definition operation.
+
+Note that attempts to read or write data pages in the cache over this size may
+be rebuffed with -ENOBUFS.
+
+This operation schedules an attribute adjustment to happen asynchronously at
+some point in the future, and as such, it may happen after the function returns
+to the caller.  The attribute adjustment excludes read and write operations.
+
+
+=====================
+PAGE READ/ALLOC/WRITE
+=====================
+
+And the sixth step is to store and retrieve pages in the cache.  There are
+three functions that are used to do this.
+
+Note:
+
+ (1) A page should not be re-read or re-allocated without uncaching it first.
+
+ (2) A read or allocated page must be uncached when the netfs page is released
+     from the pagecache.
+
+ (3) A page should only be written to the cache if previous read or allocated.
+
+This permits the cache to maintain its page tracking in proper order.
+
+
+PAGE READ
+---------
+
+Firstly, the netfs should ask FS-Cache to examine the caches and read the
+contents cached for a particular page of a particular file if present, or else
+allocate space to store the contents if not:
+
+	typedef
+	void (*fscache_rw_complete_t)(struct page *page,
+				      void *context,
+				      int error);
+
+	int fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+				       struct page *page,
+				       fscache_rw_complete_t end_io_func,
+				       void *context,
+				       gfp_t gfp);
+
+The cookie argument must specify a cookie for an object that isn't an index,
+the page specified will have the data loaded into it (and is also used to
+specify the page number), and the gfp argument is used to control how any
+memory allocations made are satisfied.
+
+If the cookie indicates the inode is not cached:
+
+ (1) The function will return -ENOBUFS.
+
+Else if there's a copy of the page resident in the cache:
+
+ (1) The mark_pages_cached() cookie operation will be called on that page.
+
+ (2) The function will submit a request to read the data from the cache's
+     backing device directly into the page specified.
+
+ (3) The function will return 0.
+
+ (4) When the read is complete, end_io_func() will be invoked with:
+
+     (*) The netfs data supplied when the cookie was created.
+
+     (*) The page descriptor.
+
+     (*) The context argument passed to the above function.  This will be
+         maintained with the get_context/put_context functions mentioned above.
+
+     (*) An argument that's 0 on success or negative for an error code.
+
+     If an error occurs, it should be assumed that the page contains no usable
+     data.
+
+     end_io_func() will be called in process context if the read is results in
+     an error, but it might be called in interrupt context if the read is
+     successful.
+
+Otherwise, if there's not a copy available in cache, but the cache may be able
+to store the page:
+
+ (1) The mark_pages_cached() cookie operation will be called on that page.
+
+ (2) A block may be reserved in the cache and attached to the object at the
+     appropriate place.
+
+ (3) The function will return -ENODATA.
+
+This function may also return -ENOMEM or -EINTR, in which case it won't have
+read any data from the cache.
+
+
+PAGE ALLOCATE
+-------------
+
+Alternatively, if there's not expected to be any data in the cache for a page
+because the file has been extended, a block can simply be allocated instead:
+
+	int fscache_alloc_page(struct fscache_cookie *cookie,
+			       struct page *page,
+			       gfp_t gfp);
+
+This is similar to the fscache_read_or_alloc_page() function, except that it
+never reads from the cache.  It will return 0 if a block has been allocated,
+rather than -ENODATA as the other would.  One or the other must be performed
+before writing to the cache.
+
+The mark_pages_cached() cookie operation will be called on the page if
+successful.
+
+
+PAGE WRITE
+----------
+
+Secondly, if the netfs changes the contents of the page (either due to an
+initial download or if a user performs a write), then the page should be
+written back to the cache:
+
+	int fscache_write_page(struct fscache_cookie *cookie,
+			       struct page *page,
+			       gfp_t gfp);
+
+The cookie argument must specify a data file cookie, the page specified should
+contain the data to be written (and is also used to specify the page number),
+and the gfp argument is used to control how any memory allocations made are
+satisfied.
+
+The page must have first been read or allocated successfully and must not have
+been uncached before writing is performed.
+
+If the cookie indicates the inode is not cached then:
+
+ (1) The function will return -ENOBUFS.
+
+Else if space can be allocated in the cache to hold this page:
+
+ (1) PG_fscache_write will be set on the page.
+
+ (2) The function will submit a request to write the data to cache's backing
+     device directly from the page specified.
+
+ (3) The function will return 0.
+
+ (4) When the write is complete PG_fscache_write is cleared on the page and
+     anyone waiting for that bit will be woken up.
+
+Else if there's no space available in the cache, -ENOBUFS will be returned.  It
+is also possible for the PG_fscache_write bit to be cleared when no write took
+place if unforeseen circumstances arose (such as a disk error).
+
+Writing takes place asynchronously.
+
+
+MULTIPLE PAGE READ
+------------------
+
+A facility is provided to read several pages at once, as requested by the
+readpages() address space operation:
+
+	int fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+					struct address_space *mapping,
+					struct list_head *pages,
+					int *nr_pages,
+					fscache_rw_complete_t end_io_func,
+					void *context,
+					gfp_t gfp);
+
+This works in a similar way to fscache_read_or_alloc_page(), except:
+
+ (1) Any page it can retrieve data for is removed from pages and nr_pages and
+     dispatched for reading to the disk.  Reads of adjacent pages on disk may
+     be merged for greater efficiency.
+
+ (2) The mark_pages_cached() cookie operation will be called on several pages
+     at once if they're being read or allocated.
+
+ (3) If there was an general error, then that error will be returned.
+
+     Else if some pages couldn't be allocated or read, then -ENOBUFS will be
+     returned.
+
+     Else if some pages couldn't be read but were allocated, then -ENODATA will
+     be returned.
+
+     Otherwise, if all pages had reads dispatched, then 0 will be returned, the
+     list will be empty and *nr_pages will be 0.
+
+ (4) end_io_func will be called once for each page being read as the reads
+     complete.  It will be called in process context if error != 0, but it may
+     be called in interrupt context if there is no error.
+
+Note that a return of -ENODATA, -ENOBUFS or any other error does not preclude
+some of the pages being read and some being allocated.  Those pages will have
+been marked appropriately and will need uncaching.
+
+
+==============
+PAGE UNCACHING
+==============
+
+To uncache a page, this function should be called:
+
+	void fscache_uncache_page(struct fscache_cookie *cookie,
+				  struct page *page);
+
+This function permits the cache to release any in-memory representation it
+might be holding for this netfs page.  This function must be called once for
+each page on which the read or write page functions above have been called to
+make sure the cache's in-memory tracking information gets torn down.
+
+Note that pages can't be explicitly deleted from the a data file.  The whole
+data file must be retired (see the relinquish cookie function below).
+
+Furthermore, note that this does not cancel the asynchronous read or write
+operation started by the read/alloc and write functions, so the page
+invalidation and release functions must use:
+
+	bool fscache_check_page_write(struct fscache_cookie *cookie,
+				      struct page *page);
+
+to see if a page is being written to the cache, and:
+
+	void fscache_wait_on_page_write(struct fscache_cookie *cookie,
+					struct page *page);
+
+to wait for it to finish if it is.
+
+
+==========================
+INDEX AND DATA FILE UPDATE
+==========================
+
+To request an update of the index data for an index or other object, the
+following function should be called:
+
+	void fscache_update_cookie(struct fscache_cookie *cookie);
+
+This function will refer back to the netfs_data pointer stored in the cookie by
+the acquisition function to obtain the data to write into each revised index
+entry.  The update method in the parent index definition will be called to
+transfer the data.
+
+Note that partial updates may happen automatically at other times, such as when
+data blocks are added to a data file object.
+
+
+===============================
+MISCELLANEOUS COOKIE OPERATIONS
+===============================
+
+There are a number of operations that can be used to control cookies:
+
+ (*) Cookie pinning:
+
+	int fscache_pin_cookie(struct fscache_cookie *cookie);
+	void fscache_unpin_cookie(struct fscache_cookie *cookie);
+
+     These operations permit data cookies to be pinned into the cache and to
+     have the pinning removed.  They are not permitted on index cookies.
+
+     The pinning function will return 0 if successful, -ENOBUFS in the cookie
+     isn't backed by a cache, -EOPNOTSUPP if the cache doesn't support pinning,
+     -ENOSPC if there isn't enough space to honour the operation, -ENOMEM or
+     -EIO if there's any other problem.
+
+ (*) Data space reservation:
+
+	int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size);
+
+     This permits a netfs to request cache space be reserved to store up to the
+     given amount of a file.  It is permitted to ask for more than the current
+     size of the file to allow for future file expansion.
+
+     If size is given as zero then the reservation will be cancelled.
+
+     The function will return 0 if successful, -ENOBUFS in the cookie isn't
+     backed by a cache, -EOPNOTSUPP if the cache doesn't support reservations,
+     -ENOSPC if there isn't enough space to honour the operation, -ENOMEM or
+     -EIO if there's any other problem.
+
+     Note that this doesn't pin an object in a cache; it can still be culled to
+     make space if it's not in use.
+
+
+=====================
+COOKIE UNREGISTRATION
+=====================
+
+To get rid of a cookie, this function should be called.
+
+	void fscache_relinquish_cookie(struct fscache_cookie *cookie,
+				       int retire);
+
+If retire is non-zero, then the object will be marked for recycling, and all
+copies of it will be removed from all active caches in which it is present.
+Not only that but all child objects will also be retired.
+
+If retire is zero, then the object may be available again when next the
+acquisition function is called.  Retirement here will overrule the pinning on a
+cookie.
+
+One very important note - relinquish must NOT be called for a cookie unless all
+the cookies for "child" indices, objects and pages have been relinquished
+first.
+
+
+================================
+INDEX AND DATA FILE INVALIDATION
+================================
+
+There is no direct way to invalidate an index subtree or a data file.  To do
+this, the caller should relinquish and retire the cookie they have, and then
+acquire a new one.
+
+
+===========================
+FS-CACHE SPECIFIC PAGE FLAG
+===========================
+
+FS-Cache makes use of a page flag, PG_private_2, for its own purpose.  This is
+given the alternative name PG_fscache.
+
+PG_fscache is used to indicate that the page is known by the cache, and that
+the cache must be informed if the page is going to go away.  It's an indication
+to the netfs that the cache has an interest in this page, where an interest may
+be a pointer to it, resources allocated or reserved for it, or I/O in progress
+upon it.
+
+The netfs can use this information in methods such as releasepage() to
+determine whether it needs to uncache a page or update it.
+
+Furthermore, if this bit is set, releasepage() and invalidatepage() operations
+will be called on a page to get rid of it, even if PG_private is not set.  This
+allows caching to attempted on a page before read_cache_pages() to be called
+after fscache_read_or_alloc_pages() as the former will try and release pages it
+was given under certain circumstances.
+
+This bit does not overlap with such as PG_private.  This means that FS-Cache
+can be used with a filesystem that uses the block buffering code.
+
+There are a number of operations defined on this flag:
+
+	int PageFsCache(struct page *page);
+	void SetPageFsCache(struct page *page)
+	void ClearPageFsCache(struct page *page)
+	int TestSetPageFsCache(struct page *page)
+	int TestClearPageFsCache(struct page *page)
+
+These functions are bit test, bit set, bit clear, bit test and set and bit
+test and clear operations on PG_fscache.
diff --git a/Documentation/filesystems/caching/object.txt b/Documentation/filesystems/caching/object.txt
new file mode 100644
index 000000000000..e8b0a35d8fe5
--- /dev/null
+++ b/Documentation/filesystems/caching/object.txt
@@ -0,0 +1,313 @@
+	     ====================================================
+	     IN-KERNEL CACHE OBJECT REPRESENTATION AND MANAGEMENT
+	     ====================================================
+
+By: David Howells <dhowells@redhat.com>
+
+Contents:
+
+ (*) Representation
+
+ (*) Object management state machine.
+
+     - Provision of cpu time.
+     - Locking simplification.
+
+ (*) The set of states.
+
+ (*) The set of events.
+
+
+==============
+REPRESENTATION
+==============
+
+FS-Cache maintains an in-kernel representation of each object that a netfs is
+currently interested in.  Such objects are represented by the fscache_cookie
+struct and are referred to as cookies.
+
+FS-Cache also maintains a separate in-kernel representation of the objects that
+a cache backend is currently actively caching.  Such objects are represented by
+the fscache_object struct.  The cache backends allocate these upon request, and
+are expected to embed them in their own representations.  These are referred to
+as objects.
+
+There is a 1:N relationship between cookies and objects.  A cookie may be
+represented by multiple objects - an index may exist in more than one cache -
+or even by no objects (it may not be cached).
+
+Furthermore, both cookies and objects are hierarchical.  The two hierarchies
+correspond, but the cookies tree is a superset of the union of the object trees
+of multiple caches:
+
+	    NETFS INDEX TREE               :      CACHE 1     :      CACHE 2
+	                                   :                  :
+	                                   :   +-----------+  :
+	                          +----------->|  IObject  |  :
+	      +-----------+       |        :   +-----------+  :
+	      |  ICookie  |-------+        :         |        :
+	      +-----------+       |        :         |        :   +-----------+
+	            |             +------------------------------>|  IObject  |
+	            |                      :         |        :   +-----------+
+	            |                      :         V        :         |
+	            |                      :   +-----------+  :         |
+	            V             +----------->|  IObject  |  :         |
+	      +-----------+       |        :   +-----------+  :         |
+	      |  ICookie  |-------+        :         |        :         V
+	      +-----------+       |        :         |        :   +-----------+
+	            |             +------------------------------>|  IObject  |
+	      +-----+-----+                :         |        :   +-----------+
+	      |           |                :         |        :         |
+	      V           |                :         V        :         |
+	+-----------+     |                :   +-----------+  :         |
+	|  ICookie  |------------------------->|  IObject  |  :         |
+	+-----------+     |                :   +-----------+  :         |
+	      |           V                :         |        :         V
+	      |     +-----------+          :         |        :   +-----------+
+	      |     |  ICookie  |-------------------------------->|  IObject  |
+	      |     +-----------+          :         |        :   +-----------+
+	      V           |                :         V        :         |
+	+-----------+     |                :   +-----------+  :         |
+	|  DCookie  |------------------------->|  DObject  |  :         |
+	+-----------+     |                :   +-----------+  :         |
+	                  |                :                  :         |
+	          +-------+-------+        :                  :         |
+	          |               |        :                  :         |
+	          V               V        :                  :         V
+	    +-----------+   +-----------+  :                  :   +-----------+
+	    |  DCookie  |   |  DCookie  |------------------------>|  DObject  |
+	    +-----------+   +-----------+  :                  :   +-----------+
+	                                   :                  :
+
+In the above illustration, ICookie and IObject represent indices and DCookie
+and DObject represent data storage objects.  Indices may have representation in
+multiple caches, but currently, non-index objects may not.  Objects of any type
+may also be entirely unrepresented.
+
+As far as the netfs API goes, the netfs is only actually permitted to see
+pointers to the cookies.  The cookies themselves and any objects attached to
+those cookies are hidden from it.
+
+
+===============================
+OBJECT MANAGEMENT STATE MACHINE
+===============================
+
+Within FS-Cache, each active object is managed by its own individual state
+machine.  The state for an object is kept in the fscache_object struct, in
+object->state.  A cookie may point to a set of objects that are in different
+states.
+
+Each state has an action associated with it that is invoked when the machine
+wakes up in that state.  There are four logical sets of states:
+
+ (1) Preparation: states that wait for the parent objects to become ready.  The
+     representations are hierarchical, and it is expected that an object must
+     be created or accessed with respect to its parent object.
+
+ (2) Initialisation: states that perform lookups in the cache and validate
+     what's found and that create on disk any missing metadata.
+
+ (3) Normal running: states that allow netfs operations on objects to proceed
+     and that update the state of objects.
+
+ (4) Termination: states that detach objects from their netfs cookies, that
+     delete objects from disk, that handle disk and system errors and that free
+     up in-memory resources.
+
+
+In most cases, transitioning between states is in response to signalled events.
+When a state has finished processing, it will usually set the mask of events in
+which it is interested (object->event_mask) and relinquish the worker thread.
+Then when an event is raised (by calling fscache_raise_event()), if the event
+is not masked, the object will be queued for processing (by calling
+fscache_enqueue_object()).
+
+
+PROVISION OF CPU TIME
+---------------------
+
+The work to be done by the various states is given CPU time by the threads of
+the slow work facility (see Documentation/slow-work.txt).  This is used in
+preference to the workqueue facility because:
+
+ (1) Threads may be completely occupied for very long periods of time by a
+     particular work item.  These state actions may be doing sequences of
+     synchronous, journalled disk accesses (lookup, mkdir, create, setxattr,
+     getxattr, truncate, unlink, rmdir, rename).
+
+ (2) Threads may do little actual work, but may rather spend a lot of time
+     sleeping on I/O.  This means that single-threaded and 1-per-CPU-threaded
+     workqueues don't necessarily have the right numbers of threads.
+
+
+LOCKING SIMPLIFICATION
+----------------------
+
+Because only one worker thread may be operating on any particular object's
+state machine at once, this simplifies the locking, particularly with respect
+to disconnecting the netfs's representation of a cache object (fscache_cookie)
+from the cache backend's representation (fscache_object) - which may be
+requested from either end.
+
+
+=================
+THE SET OF STATES
+=================
+
+The object state machine has a set of states that it can be in.  There are
+preparation states in which the object sets itself up and waits for its parent
+object to transit to a state that allows access to its children:
+
+ (1) State FSCACHE_OBJECT_INIT.
+
+     Initialise the object and wait for the parent object to become active.  In
+     the cache, it is expected that it will not be possible to look an object
+     up from the parent object, until that parent object itself has been looked
+     up.
+
+There are initialisation states in which the object sets itself up and accesses
+disk for the object metadata:
+
+ (2) State FSCACHE_OBJECT_LOOKING_UP.
+
+     Look up the object on disk, using the parent as a starting point.
+     FS-Cache expects the cache backend to probe the cache to see whether this
+     object is represented there, and if it is, to see if it's valid (coherency
+     management).
+
+     The cache should call fscache_object_lookup_negative() to indicate lookup
+     failure for whatever reason, and should call fscache_obtained_object() to
+     indicate success.
+
+     At the completion of lookup, FS-Cache will let the netfs go ahead with
+     read operations, no matter whether the file is yet cached.  If not yet
+     cached, read operations will be immediately rejected with ENODATA until
+     the first known page is uncached - as to that point there can be no data
+     to be read out of the cache for that file that isn't currently also held
+     in the pagecache.
+
+ (3) State FSCACHE_OBJECT_CREATING.
+
+     Create an object on disk, using the parent as a starting point.  This
+     happens if the lookup failed to find the object, or if the object's
+     coherency data indicated what's on disk is out of date.  In this state,
+     FS-Cache expects the cache to create
+
+     The cache should call fscache_obtained_object() if creation completes
+     successfully, fscache_object_lookup_negative() otherwise.
+
+     At the completion of creation, FS-Cache will start processing write
+     operations the netfs has queued for an object.  If creation failed, the
+     write ops will be transparently discarded, and nothing recorded in the
+     cache.
+
+There are some normal running states in which the object spends its time
+servicing netfs requests:
+
+ (4) State FSCACHE_OBJECT_AVAILABLE.
+
+     A transient state in which pending operations are started, child objects
+     are permitted to advance from FSCACHE_OBJECT_INIT state, and temporary
+     lookup data is freed.
+
+ (5) State FSCACHE_OBJECT_ACTIVE.
+
+     The normal running state.  In this state, requests the netfs makes will be
+     passed on to the cache.
+
+ (6) State FSCACHE_OBJECT_UPDATING.
+
+     The state machine comes here to update the object in the cache from the
+     netfs's records.  This involves updating the auxiliary data that is used
+     to maintain coherency.
+
+And there are terminal states in which an object cleans itself up, deallocates
+memory and potentially deletes stuff from disk:
+
+ (7) State FSCACHE_OBJECT_LC_DYING.
+
+     The object comes here if it is dying because of a lookup or creation
+     error.  This would be due to a disk error or system error of some sort.
+     Temporary data is cleaned up, and the parent is released.
+
+ (8) State FSCACHE_OBJECT_DYING.
+
+     The object comes here if it is dying due to an error, because its parent
+     cookie has been relinquished by the netfs or because the cache is being
+     withdrawn.
+
+     Any child objects waiting on this one are given CPU time so that they too
+     can destroy themselves.  This object waits for all its children to go away
+     before advancing to the next state.
+
+ (9) State FSCACHE_OBJECT_ABORT_INIT.
+
+     The object comes to this state if it was waiting on its parent in
+     FSCACHE_OBJECT_INIT, but its parent died.  The object will destroy itself
+     so that the parent may proceed from the FSCACHE_OBJECT_DYING state.
+
+(10) State FSCACHE_OBJECT_RELEASING.
+(11) State FSCACHE_OBJECT_RECYCLING.
+
+     The object comes to one of these two states when dying once it is rid of
+     all its children, if it is dying because the netfs relinquished its
+     cookie.  In the first state, the cached data is expected to persist, and
+     in the second it will be deleted.
+
+(12) State FSCACHE_OBJECT_WITHDRAWING.
+
+     The object transits to this state if the cache decides it wants to
+     withdraw the object from service, perhaps to make space, but also due to
+     error or just because the whole cache is being withdrawn.
+
+(13) State FSCACHE_OBJECT_DEAD.
+
+     The object transits to this state when the in-memory object record is
+     ready to be deleted.  The object processor shouldn't ever see an object in
+     this state.
+
+
+THE SET OF EVENTS
+-----------------
+
+There are a number of events that can be raised to an object state machine:
+
+ (*) FSCACHE_OBJECT_EV_UPDATE
+
+     The netfs requested that an object be updated.  The state machine will ask
+     the cache backend to update the object, and the cache backend will ask the
+     netfs for details of the change through its cookie definition ops.
+
+ (*) FSCACHE_OBJECT_EV_CLEARED
+
+     This is signalled in two circumstances:
+
+     (a) when an object's last child object is dropped and
+
+     (b) when the last operation outstanding on an object is completed.
+
+     This is used to proceed from the dying state.
+
+ (*) FSCACHE_OBJECT_EV_ERROR
+
+     This is signalled when an I/O error occurs during the processing of some
+     object.
+
+ (*) FSCACHE_OBJECT_EV_RELEASE
+ (*) FSCACHE_OBJECT_EV_RETIRE
+
+     These are signalled when the netfs relinquishes a cookie it was using.
+     The event selected depends on whether the netfs asks for the backing
+     object to be retired (deleted) or retained.
+
+ (*) FSCACHE_OBJECT_EV_WITHDRAW
+
+     This is signalled when the cache backend wants to withdraw an object.
+     This means that the object will have to be detached from the netfs's
+     cookie.
+
+Because the withdrawing releasing/retiring events are all handled by the object
+state machine, it doesn't matter if there's a collision with both ends trying
+to sever the connection at the same time.  The state machine can just pick
+which one it wants to honour, and that effects the other.
diff --git a/Documentation/filesystems/caching/operations.txt b/Documentation/filesystems/caching/operations.txt
new file mode 100644
index 000000000000..b6b070c57cbf
--- /dev/null
+++ b/Documentation/filesystems/caching/operations.txt
@@ -0,0 +1,213 @@
+		       ================================
+		       ASYNCHRONOUS OPERATIONS HANDLING
+		       ================================
+
+By: David Howells <dhowells@redhat.com>
+
+Contents:
+
+ (*) Overview.
+
+ (*) Operation record initialisation.
+
+ (*) Parameters.
+
+ (*) Procedure.
+
+ (*) Asynchronous callback.
+
+
+========
+OVERVIEW
+========
+
+FS-Cache has an asynchronous operations handling facility that it uses for its
+data storage and retrieval routines.  Its operations are represented by
+fscache_operation structs, though these are usually embedded into some other
+structure.
+
+This facility is available to and expected to be be used by the cache backends,
+and FS-Cache will create operations and pass them off to the appropriate cache
+backend for completion.
+
+To make use of this facility, <linux/fscache-cache.h> should be #included.
+
+
+===============================
+OPERATION RECORD INITIALISATION
+===============================
+
+An operation is recorded in an fscache_operation struct:
+
+	struct fscache_operation {
+		union {
+			struct work_struct fast_work;
+			struct slow_work slow_work;
+		};
+		unsigned long		flags;
+		fscache_operation_processor_t processor;
+		...
+	};
+
+Someone wanting to issue an operation should allocate something with this
+struct embedded in it.  They should initialise it by calling:
+
+	void fscache_operation_init(struct fscache_operation *op,
+				    fscache_operation_release_t release);
+
+with the operation to be initialised and the release function to use.
+
+The op->flags parameter should be set to indicate the CPU time provision and
+the exclusivity (see the Parameters section).
+
+The op->fast_work, op->slow_work and op->processor flags should be set as
+appropriate for the CPU time provision (see the Parameters section).
+
+FSCACHE_OP_WAITING may be set in op->flags prior to each submission of the
+operation and waited for afterwards.
+
+
+==========
+PARAMETERS
+==========
+
+There are a number of parameters that can be set in the operation record's flag
+parameter.  There are three options for the provision of CPU time in these
+operations:
+
+ (1) The operation may be done synchronously (FSCACHE_OP_MYTHREAD).  A thread
+     may decide it wants to handle an operation itself without deferring it to
+     another thread.
+
+     This is, for example, used in read operations for calling readpages() on
+     the backing filesystem in CacheFiles.  Although readpages() does an
+     asynchronous data fetch, the determination of whether pages exist is done
+     synchronously - and the netfs does not proceed until this has been
+     determined.
+
+     If this option is to be used, FSCACHE_OP_WAITING must be set in op->flags
+     before submitting the operation, and the operating thread must wait for it
+     to be cleared before proceeding:
+
+		wait_on_bit(&op->flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+
+
+ (2) The operation may be fast asynchronous (FSCACHE_OP_FAST), in which case it
+     will be given to keventd to process.  Such an operation is not permitted
+     to sleep on I/O.
+
+     This is, for example, used by CacheFiles to copy data from a backing fs
+     page to a netfs page after the backing fs has read the page in.
+
+     If this option is used, op->fast_work and op->processor must be
+     initialised before submitting the operation:
+
+		INIT_WORK(&op->fast_work, do_some_work);
+
+
+ (3) The operation may be slow asynchronous (FSCACHE_OP_SLOW), in which case it
+     will be given to the slow work facility to process.  Such an operation is
+     permitted to sleep on I/O.
+
+     This is, for example, used by FS-Cache to handle background writes of
+     pages that have just been fetched from a remote server.
+
+     If this option is used, op->slow_work and op->processor must be
+     initialised before submitting the operation:
+
+		fscache_operation_init_slow(op, processor)
+
+
+Furthermore, operations may be one of two types:
+
+ (1) Exclusive (FSCACHE_OP_EXCLUSIVE).  Operations of this type may not run in
+     conjunction with any other operation on the object being operated upon.
+
+     An example of this is the attribute change operation, in which the file
+     being written to may need truncation.
+
+ (2) Shareable.  Operations of this type may be running simultaneously.  It's
+     up to the operation implementation to prevent interference between other
+     operations running at the same time.
+
+
+=========
+PROCEDURE
+=========
+
+Operations are used through the following procedure:
+
+ (1) The submitting thread must allocate the operation and initialise it
+     itself.  Normally this would be part of a more specific structure with the
+     generic op embedded within.
+
+ (2) The submitting thread must then submit the operation for processing using
+     one of the following two functions:
+
+	int fscache_submit_op(struct fscache_object *object,
+			      struct fscache_operation *op);
+
+	int fscache_submit_exclusive_op(struct fscache_object *object,
+					struct fscache_operation *op);
+
+     The first function should be used to submit non-exclusive ops and the
+     second to submit exclusive ones.  The caller must still set the
+     FSCACHE_OP_EXCLUSIVE flag.
+
+     If successful, both functions will assign the operation to the specified
+     object and return 0.  -ENOBUFS will be returned if the object specified is
+     permanently unavailable.
+
+     The operation manager will defer operations on an object that is still
+     undergoing lookup or creation.  The operation will also be deferred if an
+     operation of conflicting exclusivity is in progress on the object.
+
+     If the operation is asynchronous, the manager will retain a reference to
+     it, so the caller should put their reference to it by passing it to:
+
+	void fscache_put_operation(struct fscache_operation *op);
+
+ (3) If the submitting thread wants to do the work itself, and has marked the
+     operation with FSCACHE_OP_MYTHREAD, then it should monitor
+     FSCACHE_OP_WAITING as described above and check the state of the object if
+     necessary (the object might have died whilst the thread was waiting).
+
+     When it has finished doing its processing, it should call
+     fscache_put_operation() on it.
+
+ (4) The operation holds an effective lock upon the object, preventing other
+     exclusive ops conflicting until it is released.  The operation can be
+     enqueued for further immediate asynchronous processing by adjusting the
+     CPU time provisioning option if necessary, eg:
+
+	op->flags &= ~FSCACHE_OP_TYPE;
+	op->flags |= ~FSCACHE_OP_FAST;
+
+     and calling:
+
+	void fscache_enqueue_operation(struct fscache_operation *op)
+
+     This can be used to allow other things to have use of the worker thread
+     pools.
+
+
+=====================
+ASYNCHRONOUS CALLBACK
+=====================
+
+When used in asynchronous mode, the worker thread pool will invoke the
+processor method with a pointer to the operation.  This should then get at the
+container struct by using container_of():
+
+	static void fscache_write_op(struct fscache_operation *_op)
+	{
+		struct fscache_storage *op =
+			container_of(_op, struct fscache_storage, op);
+	...
+	}
+
+The caller holds a reference on the operation, and will invoke
+fscache_put_operation() when the processor function returns.  The processor
+function is at liberty to call fscache_enqueue_operation() or to take extra
+references.
diff --git a/Documentation/filesystems/exofs.txt b/Documentation/filesystems/exofs.txt
new file mode 100644
index 000000000000..0ced74c2f73c
--- /dev/null
+++ b/Documentation/filesystems/exofs.txt
@@ -0,0 +1,176 @@
+===============================================================================
+WHAT IS EXOFS?
+===============================================================================
+
+exofs is a file system that uses an OSD and exports the API of a normal Linux
+file system. Users access exofs like any other local file system, and exofs
+will in turn issue commands to the local OSD initiator.
+
+OSD is a new T10 command set that views storage devices not as a large/flat
+array of sectors but as a container of objects, each having a length, quota,
+time attributes and more. Each object is addressed by a 64bit ID, and is
+contained in a 64bit ID partition. Each object has associated attributes
+attached to it, which are integral part of the object and provide metadata about
+the object. The standard defines some common obligatory attributes, but user
+attributes can be added as needed.
+
+===============================================================================
+ENVIRONMENT
+===============================================================================
+
+To use this file system, you need to have an object store to run it on.  You
+may download a target from:
+http://open-osd.org
+
+See Documentation/scsi/osd.txt for how to setup a working osd environment.
+
+===============================================================================
+USAGE
+===============================================================================
+
+1. Download and compile exofs and open-osd initiator:
+  You need an external Kernel source tree or kernel headers from your
+  distribution. (anything based on 2.6.26 or later).
+
+  a. download open-osd including exofs source using:
+     [parent-directory]$ git clone git://git.open-osd.org/open-osd.git
+
+  b. Build the library module like this:
+     [parent-directory]$ make -C KSRC=$(KER_DIR) open-osd
+
+     This will build both the open-osd initiator as well as the exofs kernel
+     module. Use whatever parameters you compiled your Kernel with and
+     $(KER_DIR) above pointing to the Kernel you compile against. See the file
+     open-osd/top-level-Makefile for an example.
+
+2. Get the OSD initiator and target set up properly, and login to the target.
+  See Documentation/scsi/osd.txt for farther instructions. Also see ./do-osd
+  for example script that does all these steps.
+
+3. Insmod the exofs.ko module:
+   [exofs]$ insmod exofs.ko
+
+4. Make sure the directory where you want to mount exists. If not, create it.
+   (For example, mkdir /mnt/exofs)
+
+5. At first run you will need to invoke the mkfs.exofs application
+
+   As an example, this will create the file system on:
+   /dev/osd0 partition ID 65536
+
+   mkfs.exofs --pid=65536 --format /dev/osd0
+
+   The --format is optional if not specified no OSD_FORMAT will be
+   preformed and a clean file system will be created in the specified pid,
+   in the available space of the target. (Use --format=size_in_meg to limit
+   the total LUN space available)
+
+   If pid already exist it will be deleted and a new one will be created in it's
+   place. Be careful.
+
+   An exofs lives inside a single OSD partition. You can create multiple exofs
+   filesystems on the same device using multiple pids.
+
+   (run mkfs.exofs without any parameters for usage help message)
+
+6. Mount the file system.
+
+   For example, to mount /dev/osd0, partition ID 0x10000 on /mnt/exofs:
+
+	mount -t exofs -o pid=65536 /dev/osd0 /mnt/exofs/
+
+7. For reference (See do-exofs example script):
+	do-exofs start - an example of how to perform the above steps.
+	do-exofs stop -  an example of how to unmount the file system.
+	do-exofs format - an example of how to format and mkfs a new exofs.
+
+8. Extra compilation flags (uncomment in fs/exofs/Kbuild):
+	CONFIG_EXOFS_DEBUG - for debug messages and extra checks.
+
+===============================================================================
+exofs mount options
+===============================================================================
+Similar to any mount command:
+	mount -t exofs -o exofs_options /dev/osdX mount_exofs_directory
+
+Where:
+    -t exofs: specifies the exofs file system
+
+    /dev/osdX: X is a decimal number. /dev/osdX was created after a successful
+               login into an OSD target.
+
+    mount_exofs_directory: The directory to mount the file system on
+
+    exofs specific options: Options are separated by commas (,)
+		pid=<integer> - The partition number to mount/create as
+                                container of the filesystem.
+                                This option is mandatory
+                to=<integer>  - Timeout in ticks for a single command
+                                default is (60 * HZ) [for debugging only]
+
+===============================================================================
+DESIGN
+===============================================================================
+
+* The file system control block (AKA on-disk superblock) resides in an object
+  with a special ID (defined in common.h).
+  Information included in the file system control block is used to fill the
+  in-memory superblock structure at mount time. This object is created before
+  the file system is used by mkexofs.c It contains information such as:
+	- The file system's magic number
+	- The next inode number to be allocated
+
+* Each file resides in its own object and contains the data (and it will be
+  possible to extend the file over multiple objects, though this has not been
+  implemented yet).
+
+* A directory is treated as a file, and essentially contains a list of <file
+  name, inode #> pairs for files that are found in that directory. The object
+  IDs correspond to the files' inode numbers and will be allocated according to
+  a bitmap (stored in a separate object). Now they are allocated using a
+  counter.
+
+* Each file's control block (AKA on-disk inode) is stored in its object's
+  attributes. This applies to both regular files and other types (directories,
+  device files, symlinks, etc.).
+
+* Credentials are generated per object (inode and superblock) when they is
+  created in memory (read off disk or created). The credential works for all
+  operations and is used as long as the object remains in memory.
+
+* Async OSD operations are used whenever possible, but the target may execute
+  them out of order. The operations that concern us are create, delete,
+  readpage, writepage, update_inode, and truncate. The following pairs of
+  operations should execute in the order written, and we need to prevent them
+  from executing in reverse order:
+	- The following are handled with the OBJ_CREATED and OBJ_2BCREATED
+	  flags. OBJ_CREATED is set when we know the object exists on the OSD -
+	  in create's callback function, and when we successfully do a read_inode.
+	  OBJ_2BCREATED is set in the beginning of the create function, so we
+	  know that we should wait.
+		- create/delete: delete should wait until the object is created
+		  on the OSD.
+		- create/readpage: readpage should be able to return a page
+		  full of zeroes in this case. If there was a write already
+		  en-route (i.e. create, writepage, readpage) then the page
+		  would be locked, and so it would really be the same as
+		  create/writepage.
+		- create/writepage: if writepage is called for a sync write, it
+		  should wait until the object is created on the OSD.
+		  Otherwise, it should just return.
+		- create/truncate: truncate should wait until the object is
+		  created on the OSD.
+		- create/update_inode: update_inode should wait until the
+		  object is created on the OSD.
+	- Handled by VFS locks:
+		- readpage/delete: shouldn't happen because of page lock.
+		- writepage/delete: shouldn't happen because of page lock.
+		- readpage/writepage: shouldn't happen because of page lock.
+
+===============================================================================
+LICENSE/COPYRIGHT
+===============================================================================
+The exofs file system is based on ext2 v0.5b (distributed with the Linux kernel
+version 2.6.10).  All files include the original copyrights, and the license
+is GPL version 2 (only version 2, as is true for the Linux kernel).  The
+Linux kernel can be downloaded from www.kernel.org.
diff --git a/Documentation/filesystems/ext3.txt b/Documentation/filesystems/ext3.txt
index e5f3833a6ef8..570f9bd9be2b 100644
--- a/Documentation/filesystems/ext3.txt
+++ b/Documentation/filesystems/ext3.txt
@@ -14,6 +14,11 @@ Options
 When mounting an ext3 filesystem, the following option are accepted:
 (*) == default
 
+ro			Mount filesystem read only. Note that ext3 will replay
+			the journal (and thus write to the partition) even when
+			mounted "read only". Mount options "ro,noload" can be
+			used to prevent writes to the filesystem.
+
 journal=update		Update the ext3 file system's journal to the current
 			format.
 
@@ -27,7 +32,9 @@ journal_dev=devnum	When the external journal device's major/minor numbers
 			identified through its new major/minor numbers encoded
 			in devnum.
 
-noload			Don't load the journal on mounting.
+noload			Don't load the journal on mounting. Note that this forces
+			mount of inconsistent filesystem, which can lead to
+			various problems.
 
 data=journal		All data are committed into the journal prior to being
 			written into the main file system.
@@ -92,9 +99,12 @@ nocheck
 
 debug			Extra debugging information is sent to syslog.
 
-errors=remount-ro(*)	Remount the filesystem read-only on an error.
+errors=remount-ro	Remount the filesystem read-only on an error.
 errors=continue		Keep going on a filesystem error.
 errors=panic		Panic and halt the machine if an error occurs.
+			(These mount options override the errors behavior
+			specified in the superblock, which can be
+			configured using tune2fs.)
 
 data_err=ignore(*)	Just print an error message if an error occurs
 			in a file data buffer in ordered mode.
diff --git a/Documentation/filesystems/proc.txt b/Documentation/filesystems/proc.txt
index efc4fd9f40ce..ce84cfc9eae0 100644
--- a/Documentation/filesystems/proc.txt
+++ b/Documentation/filesystems/proc.txt
@@ -5,6 +5,7 @@
                   Bodo Bauer <bb@ricochet.net>
 
 2.4.x update	  Jorge Nerin <comandante@zaralinux.com>      November 14 2000
+move /proc/sys	  Shen Feng <shen@cn.fujitsu.com>		    April 1 2009
 ------------------------------------------------------------------------------
 Version 1.3                                              Kernel version 2.2.12
 					      Kernel version 2.4.0-test11-pre4
@@ -26,25 +27,17 @@ Table of Contents
   1.6	Parallel port info in /proc/parport
   1.7	TTY info in /proc/tty
   1.8	Miscellaneous kernel statistics in /proc/stat
+  1.9 Ext4 file system parameters
 
   2	Modifying System Parameters
-  2.1	/proc/sys/fs - File system data
-  2.2	/proc/sys/fs/binfmt_misc - Miscellaneous binary formats
-  2.3	/proc/sys/kernel - general kernel parameters
-  2.4	/proc/sys/vm - The virtual memory subsystem
-  2.5	/proc/sys/dev - Device specific parameters
-  2.6	/proc/sys/sunrpc - Remote procedure calls
-  2.7	/proc/sys/net - Networking stuff
-  2.8	/proc/sys/net/ipv4 - IPV4 settings
-  2.9	Appletalk
-  2.10	IPX
-  2.11	/proc/sys/fs/mqueue - POSIX message queues filesystem
-  2.12	/proc/<pid>/oom_adj - Adjust the oom-killer score
-  2.13	/proc/<pid>/oom_score - Display current oom-killer score
-  2.14	/proc/<pid>/io - Display the IO accounting fields
-  2.15	/proc/<pid>/coredump_filter - Core dump filtering settings
-  2.16	/proc/<pid>/mountinfo - Information about mounts
-  2.17	/proc/sys/fs/epoll - Configuration options for the epoll interface
+
+  3	Per-Process Parameters
+  3.1	/proc/<pid>/oom_adj - Adjust the oom-killer score
+  3.2	/proc/<pid>/oom_score - Display current oom-killer score
+  3.3	/proc/<pid>/io - Display the IO accounting fields
+  3.4	/proc/<pid>/coredump_filter - Core dump filtering settings
+  3.5	/proc/<pid>/mountinfo - Information about mounts
+
 
 ------------------------------------------------------------------------------
 Preface
@@ -990,1021 +983,24 @@ review the kernel documentation in the directory /usr/src/linux/Documentation.
 This chapter  is  heavily  based  on the documentation included in the pre 2.2
 kernels, and became part of it in version 2.2.1 of the Linux kernel.
 
-2.1 /proc/sys/fs - File system data
------------------------------------
-
-This subdirectory  contains  specific  file system, file handle, inode, dentry
-and quota information.
-
-Currently, these files are in /proc/sys/fs:
-
-dentry-state
-------------
-
-Status of  the  directory  cache.  Since  directory  entries  are  dynamically
-allocated and  deallocated,  this  file indicates the current status. It holds
-six values, in which the last two are not used and are always zero. The others
-are listed in table 2-1.
-
-
-Table 2-1: Status files of the directory cache 
-..............................................................................
- File       Content                                                            
- nr_dentry  Almost always zero                                                 
- nr_unused  Number of unused cache entries                                     
- age_limit  
-            in seconds after the entry may be reclaimed, when memory is short 
- want_pages internally                                                         
-..............................................................................
-
-dquot-nr and dquot-max
-----------------------
-
-The file dquot-max shows the maximum number of cached disk quota entries.
-
-The file  dquot-nr  shows  the  number of allocated disk quota entries and the
-number of free disk quota entries.
-
-If the number of available cached disk quotas is very low and you have a large
-number of simultaneous system users, you might want to raise the limit.
-
-file-nr and file-max
---------------------
-
-The kernel  allocates file handles dynamically, but doesn't free them again at
-this time.
-
-The value  in  file-max  denotes  the  maximum number of file handles that the
-Linux kernel will allocate. When you get a lot of error messages about running
-out of  file handles, you might want to raise this limit. The default value is
-10% of  RAM in kilobytes.  To  change it, just  write the new number  into the
-file:
-
-  # cat /proc/sys/fs/file-max 
-  4096 
-  # echo 8192 > /proc/sys/fs/file-max 
-  # cat /proc/sys/fs/file-max 
-  8192 
-
-
-This method  of  revision  is  useful  for  all customizable parameters of the
-kernel - simply echo the new value to the corresponding file.
-
-Historically, the three values in file-nr denoted the number of allocated file
-handles,  the number of  allocated but  unused file  handles, and  the maximum
-number of file handles. Linux 2.6 always  reports 0 as the number of free file
-handles -- this  is not an error,  it just means that the  number of allocated
-file handles exactly matches the number of used file handles.
-
-Attempts to  allocate more  file descriptors than  file-max are  reported with
-printk, look for "VFS: file-max limit <number> reached".
-
-inode-state and inode-nr
-------------------------
-
-The file inode-nr contains the first two items from inode-state, so we'll skip
-to that file...
-
-inode-state contains  two  actual numbers and five dummy values. The numbers
-are nr_inodes and nr_free_inodes (in order of appearance).
-
-nr_inodes
-~~~~~~~~~
-
-Denotes the  number  of  inodes the system has allocated. This number will
-grow and shrink dynamically.
-
-nr_open
--------
-
-Denotes the maximum number of file-handles a process can
-allocate. Default value is 1024*1024 (1048576) which should be
-enough for most machines. Actual limit depends on RLIMIT_NOFILE
-resource limit.
-
-nr_free_inodes
---------------
-
-Represents the  number of free inodes. Ie. The number of inuse inodes is
-(nr_inodes - nr_free_inodes).
-
-aio-nr and aio-max-nr
----------------------
-
-aio-nr is the running total of the number of events specified on the
-io_setup system call for all currently active aio contexts.  If aio-nr
-reaches aio-max-nr then io_setup will fail with EAGAIN.  Note that
-raising aio-max-nr does not result in the pre-allocation or re-sizing
-of any kernel data structures.
-
-2.2 /proc/sys/fs/binfmt_misc - Miscellaneous binary formats
------------------------------------------------------------
-
-Besides these  files, there is the subdirectory /proc/sys/fs/binfmt_misc. This
-handles the kernel support for miscellaneous binary formats.
-
-Binfmt_misc provides  the ability to register additional binary formats to the
-Kernel without  compiling  an additional module/kernel. Therefore, binfmt_misc
-needs to  know magic numbers at the beginning or the filename extension of the
-binary.
-
-It works by maintaining a linked list of structs that contain a description of
-a binary  format,  including  a  magic  with size (or the filename extension),
-offset and  mask,  and  the  interpreter name. On request it invokes the given
-interpreter with  the  original  program  as  argument,  as  binfmt_java  and
-binfmt_em86 and  binfmt_mz  do.  Since binfmt_misc does not define any default
-binary-formats, you have to register an additional binary-format.
-
-There are two general files in binfmt_misc and one file per registered format.
-The two general files are register and status.
-
-Registering a new binary format
--------------------------------
-
-To register a new binary format you have to issue the command
-
-  echo :name:type:offset:magic:mask:interpreter: > /proc/sys/fs/binfmt_misc/register 
-
-
-
-with appropriate  name (the name for the /proc-dir entry), offset (defaults to
-0, if  omitted),  magic, mask (which can be omitted, defaults to all 0xff) and
-last but  not  least,  the  interpreter that is to be invoked (for example and
-testing /bin/echo).  Type  can be M for usual magic matching or E for filename
-extension matching (give extension in place of magic).
-
-Check or reset the status of the binary format handler
-------------------------------------------------------
-
-If you  do a cat on the file /proc/sys/fs/binfmt_misc/status, you will get the
-current status (enabled/disabled) of binfmt_misc. Change the status by echoing
-0 (disables)  or  1  (enables)  or  -1  (caution:  this  clears all previously
-registered binary  formats)  to status. For example echo 0 > status to disable
-binfmt_misc (temporarily).
-
-Status of a single handler
---------------------------
-
-Each registered  handler has an entry in /proc/sys/fs/binfmt_misc. These files
-perform the  same function as status, but their scope is limited to the actual
-binary format.  By  cating this file, you also receive all related information
-about the interpreter/magic of the binfmt.
-
-Example usage of binfmt_misc (emulate binfmt_java)
---------------------------------------------------
-
-  cd /proc/sys/fs/binfmt_misc  
-  echo ':Java:M::\xca\xfe\xba\xbe::/usr/local/java/bin/javawrapper:' > register  
-  echo ':HTML:E::html::/usr/local/java/bin/appletviewer:' > register  
-  echo ':Applet:M::<!--applet::/usr/local/java/bin/appletviewer:' > register 
-  echo ':DEXE:M::\x0eDEX::/usr/bin/dosexec:' > register 
-
-
-These four  lines  add  support  for  Java  executables and Java applets (like
-binfmt_java, additionally  recognizing the .html extension with no need to put
-<!--applet> to  every  applet  file).  You  have  to  install  the JDK and the
-shell-script /usr/local/java/bin/javawrapper  too.  It  works  around  the
-brokenness of  the Java filename handling. To add a Java binary, just create a
-link to the class-file somewhere in the path.
-
-2.3 /proc/sys/kernel - general kernel parameters
-------------------------------------------------
-
-This directory  reflects  general  kernel  behaviors. As I've said before, the
-contents depend  on  your  configuration.  Here you'll find the most important
-files, along with descriptions of what they mean and how to use them.
-
-acct
-----
-
-The file contains three values; highwater, lowwater, and frequency.
-
-It exists  only  when  BSD-style  process  accounting is enabled. These values
-control its behavior. If the free space on the file system where the log lives
-goes below  lowwater  percentage,  accounting  suspends.  If  it  goes  above
-highwater percentage,  accounting  resumes. Frequency determines how often you
-check the amount of free space (value is in seconds). Default settings are: 4,
-2, and  30.  That is, suspend accounting if there is less than 2 percent free;
-resume it  if we have a value of 3 or more percent; consider information about
-the amount of free space valid for 30 seconds
-
-ctrl-alt-del
-------------
-
-When the value in this file is 0, ctrl-alt-del is trapped and sent to the init
-program to  handle a graceful restart. However, when the value is greater that
-zero, Linux's  reaction  to  this key combination will be an immediate reboot,
-without syncing its dirty buffers.
-
-[NOTE]
-    When a  program  (like  dosemu)  has  the  keyboard  in  raw  mode,  the
-    ctrl-alt-del is  intercepted  by  the  program  before it ever reaches the
-    kernel tty  layer,  and  it is up to the program to decide what to do with
-    it.
-
-domainname and hostname
------------------------
-
-These files  can  be controlled to set the NIS domainname and hostname of your
-box. For the classic darkstar.frop.org a simple:
-
-  # echo "darkstar" > /proc/sys/kernel/hostname 
-  # echo "frop.org" > /proc/sys/kernel/domainname 
-
-
-would suffice to set your hostname and NIS domainname.
-
-osrelease, ostype and version
------------------------------
-
-The names make it pretty obvious what these fields contain:
-
-  > cat /proc/sys/kernel/osrelease 
-  2.2.12 
-   
-  > cat /proc/sys/kernel/ostype 
-  Linux 
-   
-  > cat /proc/sys/kernel/version 
-  #4 Fri Oct 1 12:41:14 PDT 1999 
-
-
-The files  osrelease and ostype should be clear enough. Version needs a little
-more clarification.  The  #4 means that this is the 4th kernel built from this
-source base and the date after it indicates the time the kernel was built. The
-only way to tune these values is to rebuild the kernel.
-
-panic
------
-
-The value  in  this  file  represents  the  number of seconds the kernel waits
-before rebooting  on  a  panic.  When  you  use  the  software  watchdog,  the
-recommended setting  is  60. If set to 0, the auto reboot after a kernel panic
-is disabled, which is the default setting.
-
-printk
-------
-
-The four values in printk denote
-* console_loglevel,
-* default_message_loglevel,
-* minimum_console_loglevel and
-* default_console_loglevel
-respectively.
-
-These values  influence  printk()  behavior  when  printing  or  logging error
-messages, which  come  from  inside  the  kernel.  See  syslog(2)  for  more
-information on the different log levels.
-
-console_loglevel
-----------------
-
-Messages with a higher priority than this will be printed to the console.
-
-default_message_level
----------------------
-
-Messages without an explicit priority will be printed with this priority.
-
-minimum_console_loglevel
-------------------------
-
-Minimum (highest) value to which the console_loglevel can be set.
-
-default_console_loglevel
-------------------------
-
-Default value for console_loglevel.
-
-sg-big-buff
------------
-
-This file  shows  the size of the generic SCSI (sg) buffer. At this point, you
-can't tune  it  yet,  but  you  can  change  it  at  compile  time  by editing
-include/scsi/sg.h and changing the value of SG_BIG_BUFF.
-
-If you use a scanner with SANE (Scanner Access Now Easy) you might want to set
-this to a higher value. Refer to the SANE documentation on this issue.
-
-modprobe
---------
-
-The location  where  the  modprobe  binary  is  located.  The kernel uses this
-program to load modules on demand.
-
-unknown_nmi_panic
------------------
-
-The value in this file affects behavior of handling NMI. When the value is
-non-zero, unknown NMI is trapped and then panic occurs. At that time, kernel
-debugging information is displayed on console.
-
-NMI switch that most IA32 servers have fires unknown NMI up, for example.
-If a system hangs up, try pressing the NMI switch.
-
-panic_on_unrecovered_nmi
-------------------------
-
-The default Linux behaviour on an NMI of either memory or unknown is to continue
-operation. For many environments such as scientific computing it is preferable
-that the box is taken out and the error dealt with than an uncorrected
-parity/ECC error get propogated.
-
-A small number of systems do generate NMI's for bizarre random reasons such as
-power management so the default is off. That sysctl works like the existing
-panic controls already in that directory.
-
-nmi_watchdog
-------------
-
-Enables/Disables the NMI watchdog on x86 systems.  When the value is non-zero
-the NMI watchdog is enabled and will continuously test all online cpus to
-determine whether or not they are still functioning properly. Currently,
-passing "nmi_watchdog=" parameter at boot time is required for this function
-to work.
-
-If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel parameter), the
-NMI watchdog shares registers with oprofile. By disabling the NMI watchdog,
-oprofile may have more registers to utilize.
-
-msgmni
-------
-
-Maximum number of message queue ids on the system.
-This value scales to the amount of lowmem. It is automatically recomputed
-upon memory add/remove or ipc namespace creation/removal.
-When a value is written into this file, msgmni's value becomes fixed, i.e. it
-is not recomputed anymore when one of the above events occurs.
-Use auto_msgmni to change this behavior.
-
-auto_msgmni
------------
-
-Enables/Disables automatic recomputing of msgmni upon memory add/remove or
-upon ipc namespace creation/removal (see the msgmni description above).
-Echoing "1" into this file enables msgmni automatic recomputing.
-Echoing "0" turns it off.
-auto_msgmni default value is 1.
-
-
-2.4 /proc/sys/vm - The virtual memory subsystem
------------------------------------------------
-
-Please see: Documentation/sysctls/vm.txt for a description of these
+Please see: Documentation/sysctls/ directory for descriptions of these
 entries.
 
+------------------------------------------------------------------------------
+Summary
+------------------------------------------------------------------------------
+Certain aspects  of  kernel  behavior  can be modified at runtime, without the
+need to  recompile  the kernel, or even to reboot the system. The files in the
+/proc/sys tree  can  not only be read, but also modified. You can use the echo
+command to write value into these files, thereby changing the default settings
+of the kernel.
+------------------------------------------------------------------------------
 
-2.5 /proc/sys/dev - Device specific parameters
-----------------------------------------------
-
-Currently there is only support for CDROM drives, and for those, there is only
-one read-only  file containing information about the CD-ROM drives attached to
-the system:
-
-  >cat /proc/sys/dev/cdrom/info 
-  CD-ROM information, Id: cdrom.c 2.55 1999/04/25 
-   
-  drive name:             sr0     hdb 
-  drive speed:            32      40 
-  drive # of slots:       1       0 
-  Can close tray:         1       1 
-  Can open tray:          1       1 
-  Can lock tray:          1       1 
-  Can change speed:       1       1 
-  Can select disk:        0       1 
-  Can read multisession:  1       1 
-  Can read MCN:           1       1 
-  Reports media changed:  1       1 
-  Can play audio:         1       1 
-
-
-You see two drives, sr0 and hdb, along with a list of their features.
-
-2.6 /proc/sys/sunrpc - Remote procedure calls
----------------------------------------------
-
-This directory  contains four files, which enable or disable debugging for the
-RPC functions NFS, NFS-daemon, RPC and NLM. The default values are 0. They can
-be set to one to turn debugging on. (The default value is 0 for each)
-
-2.7 /proc/sys/net - Networking stuff
-------------------------------------
-
-The interface  to  the  networking  parts  of  the  kernel  is  located  in
-/proc/sys/net. Table  2-3  shows all possible subdirectories. You may see only
-some of them, depending on your kernel's configuration.
-
-
-Table 2-3: Subdirectories in /proc/sys/net 
-..............................................................................
- Directory Content             Directory  Content            
- core      General parameter   appletalk  Appletalk protocol 
- unix      Unix domain sockets netrom     NET/ROM            
- 802       E802 protocol       ax25       AX25               
- ethernet  Ethernet protocol   rose       X.25 PLP layer     
- ipv4      IP version 4        x25        X.25 protocol      
- ipx       IPX                 token-ring IBM token ring     
- bridge    Bridging            decnet     DEC net            
- ipv6      IP version 6                   
-..............................................................................
-
-We will  concentrate  on IP networking here. Since AX15, X.25, and DEC Net are
-only minor players in the Linux world, we'll skip them in this chapter. You'll
-find some  short  info on Appletalk and IPX further on in this chapter. Review
-the online  documentation  and the kernel source to get a detailed view of the
-parameters for  those  protocols.  In  this  section  we'll  discuss  the
-subdirectories printed  in  bold letters in the table above. As default values
-are suitable for most needs, there is no need to change these values.
-
-/proc/sys/net/core - Network core options
------------------------------------------
-
-rmem_default
-------------
-
-The default setting of the socket receive buffer in bytes.
-
-rmem_max
---------
-
-The maximum receive socket buffer size in bytes.
-
-wmem_default
-------------
-
-The default setting (in bytes) of the socket send buffer.
-
-wmem_max
---------
-
-The maximum send socket buffer size in bytes.
-
-message_burst and message_cost
-------------------------------
-
-These parameters  are used to limit the warning messages written to the kernel
-log from  the  networking  code.  They  enforce  a  rate  limit  to  make  a
-denial-of-service attack  impossible. A higher message_cost factor, results in
-fewer messages that will be written. Message_burst controls when messages will
-be dropped.  The  default  settings  limit  warning messages to one every five
-seconds.
-
-warnings
---------
-
-This controls console messages from the networking stack that can occur because
-of problems on the network like duplicate address or bad checksums. Normally,
-this should be enabled, but if the problem persists the messages can be
-disabled.
-
-netdev_budget
--------------
-
-Maximum number of packets taken from all interfaces in one polling cycle (NAPI
-poll). In one polling cycle interfaces which are registered to polling are
-probed in a round-robin manner. The limit of packets in one such probe can be
-set per-device via sysfs class/net/<device>/weight .
-
-netdev_max_backlog
-------------------
-
-Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
-receives packets faster than kernel can process them.
-
-optmem_max
-----------
-
-Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
-of struct cmsghdr structures with appended data.
-
-/proc/sys/net/unix - Parameters for Unix domain sockets
--------------------------------------------------------
-
-There are  only  two  files  in this subdirectory. They control the delays for
-deleting and destroying socket descriptors.
-
-2.8 /proc/sys/net/ipv4 - IPV4 settings
---------------------------------------
-
-IP version  4  is  still the most used protocol in Unix networking. It will be
-replaced by  IP version 6 in the next couple of years, but for the moment it's
-the de  facto  standard  for  the  internet  and  is  used  in most networking
-environments around  the  world.  Because  of the importance of this protocol,
-we'll have a deeper look into the subtree controlling the behavior of the IPv4
-subsystem of the Linux kernel.
-
-Let's start with the entries in /proc/sys/net/ipv4.
-
-ICMP settings
--------------
-
-icmp_echo_ignore_all and icmp_echo_ignore_broadcasts
-----------------------------------------------------
-
-Turn on (1) or off (0), if the kernel should ignore all ICMP ECHO requests, or
-just those to broadcast and multicast addresses.
-
-Please note that if you accept ICMP echo requests with a broadcast/multi\-cast
-destination address  your  network  may  be  used as an exploder for denial of
-service packet flooding attacks to other hosts.
-
-icmp_destunreach_rate, icmp_echoreply_rate, icmp_paramprob_rate and icmp_timeexeed_rate
----------------------------------------------------------------------------------------
-
-Sets limits  for  sending  ICMP  packets  to specific targets. A value of zero
-disables all  limiting.  Any  positive  value sets the maximum package rate in
-hundredth of a second (on Intel systems).
-
-IP settings
------------
-
-ip_autoconfig
--------------
-
-This file contains the number one if the host received its IP configuration by
-RARP, BOOTP, DHCP or a similar mechanism. Otherwise it is zero.
-
-ip_default_ttl
---------------
-
-TTL (Time  To  Live) for IPv4 interfaces. This is simply the maximum number of
-hops a packet may travel.
-
-ip_dynaddr
-----------
-
-Enable dynamic  socket  address rewriting on interface address change. This is
-useful for dialup interface with changing IP addresses.
-
-ip_forward
-----------
-
-Enable or  disable forwarding of IP packages between interfaces. Changing this
-value resets  all other parameters to their default values. They differ if the
-kernel is configured as host or router.
-
-ip_local_port_range
--------------------
-
-Range of  ports  used  by  TCP  and UDP to choose the local port. Contains two
-numbers, the  first  number  is the lowest port, the second number the highest
-local port.  Default  is  1024-4999.  Should  be  changed  to  32768-61000 for
-high-usage systems.
-
-ip_no_pmtu_disc
----------------
-
-Global switch  to  turn  path  MTU  discovery off. It can also be set on a per
-socket basis by the applications or on a per route basis.
-
-ip_masq_debug
--------------
-
-Enable/disable debugging of IP masquerading.
-
-IP fragmentation settings
--------------------------
-
-ipfrag_high_trash and ipfrag_low_trash
---------------------------------------
-
-Maximum memory  used to reassemble IP fragments. When ipfrag_high_thresh bytes
-of memory  is  allocated  for  this  purpose,  the  fragment handler will toss
-packets until ipfrag_low_thresh is reached.
-
-ipfrag_time
------------
-
-Time in seconds to keep an IP fragment in memory.
-
-TCP settings
-------------
-
-tcp_ecn
--------
-
-This file controls the use of the ECN bit in the IPv4 headers. This is a new
-feature about Explicit Congestion Notification, but some routers and firewalls
-block traffic that has this bit set, so it could be necessary to echo 0 to
-/proc/sys/net/ipv4/tcp_ecn if you want to talk to these sites. For more info
-you could read RFC2481.
-
-tcp_retrans_collapse
---------------------
-
-Bug-to-bug compatibility with some broken printers. On retransmit, try to send
-larger packets to work around bugs in certain TCP stacks. Can be turned off by
-setting it to zero.
-
-tcp_keepalive_probes
---------------------
-
-Number of  keep  alive  probes  TCP  sends  out,  until  it  decides  that the
-connection is broken.
-
-tcp_keepalive_time
-------------------
-
-How often  TCP  sends out keep alive messages, when keep alive is enabled. The
-default is 2 hours.
-
-tcp_syn_retries
----------------
-
-Number of  times  initial  SYNs  for  a  TCP  connection  attempt  will  be
-retransmitted. Should  not  be  higher  than 255. This is only the timeout for
-outgoing connections,  for  incoming  connections the number of retransmits is
-defined by tcp_retries1.
-
-tcp_sack
---------
-
-Enable select acknowledgments after RFC2018.
-
-tcp_timestamps
---------------
-
-Enable timestamps as defined in RFC1323.
-
-tcp_stdurg
-----------
-
-Enable the  strict  RFC793 interpretation of the TCP urgent pointer field. The
-default is  to  use  the  BSD  compatible interpretation of the urgent pointer
-pointing to the first byte after the urgent data. The RFC793 interpretation is
-to have  it  point  to  the last byte of urgent data. Enabling this option may
-lead to interoperability problems. Disabled by default.
-
-tcp_syncookies
---------------
-
-Only valid  when  the  kernel  was  compiled  with CONFIG_SYNCOOKIES. Send out
-syncookies when  the  syn backlog queue of a socket overflows. This is to ward
-off the common 'syn flood attack'. Disabled by default.
-
-Note that  the  concept  of a socket backlog is abandoned. This means the peer
-may not  receive  reliable  error  messages  from  an  over loaded server with
-syncookies enabled.
-
-tcp_window_scaling
-------------------
-
-Enable window scaling as defined in RFC1323.
-
-tcp_fin_timeout
----------------
-
-The length  of  time  in  seconds  it  takes to receive a final FIN before the
-socket is  always  closed.  This  is  strictly  a  violation  of  the  TCP
-specification, but required to prevent denial-of-service attacks.
-
-tcp_max_ka_probes
------------------
-
-Indicates how  many  keep alive probes are sent per slow timer run. Should not
-be set too high to prevent bursts.
-
-tcp_max_syn_backlog
--------------------
-
-Length of  the per socket backlog queue. Since Linux 2.2 the backlog specified
-in listen(2)  only  specifies  the  length  of  the  backlog  queue of already
-established sockets. When more connection requests arrive Linux starts to drop
-packets. When  syncookies  are  enabled the packets are still answered and the
-maximum queue is effectively ignored.
-
-tcp_retries1
-------------
-
-Defines how  often  an  answer  to  a  TCP connection request is retransmitted
-before giving up.
-
-tcp_retries2
-------------
-
-Defines how often a TCP packet is retransmitted before giving up.
-
-Interface specific settings
----------------------------
-
-In the directory /proc/sys/net/ipv4/conf you'll find one subdirectory for each
-interface the  system  knows about and one directory calls all. Changes in the
-all subdirectory  affect  all  interfaces,  whereas  changes  in  the  other
-subdirectories affect  only  one  interface.  All  directories  have  the same
-entries:
-
-accept_redirects
-----------------
-
-This switch  decides  if the kernel accepts ICMP redirect messages or not. The
-default is 'yes' if the kernel is configured for a regular host and 'no' for a
-router configuration.
-
-accept_source_route
--------------------
-
-Should source  routed  packages  be  accepted  or  declined.  The  default  is
-dependent on  the  kernel  configuration.  It's 'yes' for routers and 'no' for
-hosts.
-
-bootp_relay
-~~~~~~~~~~~
-
-Accept packets  with source address 0.b.c.d with destinations not to this host
-as local ones. It is supposed that a BOOTP relay daemon will catch and forward
-such packets.
-
-The default  is  0,  since this feature is not implemented yet (kernel version
-2.2.12).
-
-forwarding
-----------
-
-Enable or disable IP forwarding on this interface.
-
-log_martians
-------------
-
-Log packets with source addresses with no known route to kernel log.
-
-mc_forwarding
--------------
-
-Do multicast routing. The kernel needs to be compiled with CONFIG_MROUTE and a
-multicast routing daemon is required.
-
-proxy_arp
----------
-
-Does (1) or does not (0) perform proxy ARP.
-
-rp_filter
----------
-
-Integer value determines if a source validation should be made. 1 means yes, 0
-means no.  Disabled by default, but local/broadcast address spoofing is always
-on.
-
-If you  set this to 1 on a router that is the only connection for a network to
-the net,  it  will  prevent  spoofing  attacks  against your internal networks
-(external addresses  can  still  be  spoofed), without the need for additional
-firewall rules.
-
-secure_redirects
-----------------
-
-Accept ICMP  redirect  messages  only  for gateways, listed in default gateway
-list. Enabled by default.
-
-shared_media
-------------
-
-If it  is  not  set  the kernel does not assume that different subnets on this
-device can communicate directly. Default setting is 'yes'.
-
-send_redirects
---------------
-
-Determines whether to send ICMP redirects to other hosts.
-
-Routing settings
-----------------
-
-The directory  /proc/sys/net/ipv4/route  contains  several  file  to  control
-routing issues.
-
-error_burst and error_cost
---------------------------
-
-These  parameters  are used to limit how many ICMP destination unreachable to 
-send  from  the  host  in question. ICMP destination unreachable messages are 
-sent  when  we  cannot reach  the next hop while trying to transmit a packet. 
-It  will also print some error messages to kernel logs if someone is ignoring 
-our   ICMP  redirects.  The  higher  the  error_cost  factor  is,  the  fewer 
-destination  unreachable  and error messages will be let through. Error_burst 
-controls  when  destination  unreachable  messages and error messages will be
-dropped. The default settings limit warning messages to five every second.
-
-flush
------
-
-Writing to this file results in a flush of the routing cache.
-
-gc_elasticity, gc_interval, gc_min_interval_ms, gc_timeout, gc_thresh
----------------------------------------------------------------------
-
-Values to  control  the  frequency  and  behavior  of  the  garbage collection
-algorithm for the routing cache. gc_min_interval is deprecated and replaced
-by gc_min_interval_ms.
-
-
-max_size
---------
-
-Maximum size  of  the routing cache. Old entries will be purged once the cache
-reached has this size.
-
-redirect_load, redirect_number
-------------------------------
-
-Factors which  determine  if  more ICPM redirects should be sent to a specific
-host. No  redirects  will be sent once the load limit or the maximum number of
-redirects has been reached.
-
-redirect_silence
-----------------
-
-Timeout for redirects. After this period redirects will be sent again, even if
-this has been stopped, because the load or number limit has been reached.
-
-Network Neighbor handling
--------------------------
-
-Settings about how to handle connections with direct neighbors (nodes attached
-to the same link) can be found in the directory /proc/sys/net/ipv4/neigh.
-
-As we  saw  it  in  the  conf directory, there is a default subdirectory which
-holds the  default  values, and one directory for each interface. The contents
-of the  directories  are identical, with the single exception that the default
-settings contain additional options to set garbage collection parameters.
-
-In the interface directories you'll find the following entries:
-
-base_reachable_time, base_reachable_time_ms
--------------------------------------------
-
-A base  value  used for computing the random reachable time value as specified
-in RFC2461.
-
-Expression of base_reachable_time, which is deprecated, is in seconds.
-Expression of base_reachable_time_ms is in milliseconds.
-
-retrans_time, retrans_time_ms
------------------------------
-
-The time between retransmitted Neighbor Solicitation messages.
-Used for address resolution and to determine if a neighbor is
-unreachable.
-
-Expression of retrans_time, which is deprecated, is in 1/100 seconds (for
-IPv4) or in jiffies (for IPv6).
-Expression of retrans_time_ms is in milliseconds.
-
-unres_qlen
-----------
-
-Maximum queue  length  for a pending arp request - the number of packets which
-are accepted from other layers while the ARP address is still resolved.
-
-anycast_delay
--------------
-
-Maximum for  random  delay  of  answers  to  neighbor solicitation messages in
-jiffies (1/100  sec). Not yet implemented (Linux does not have anycast support
-yet).
-
-ucast_solicit
--------------
-
-Maximum number of retries for unicast solicitation.
-
-mcast_solicit
--------------
-
-Maximum number of retries for multicast solicitation.
-
-delay_first_probe_time
-----------------------
-
-Delay for  the  first  time  probe  if  the  neighbor  is  reachable.  (see
-gc_stale_time)
-
-locktime
---------
-
-An ARP/neighbor  entry  is only replaced with a new one if the old is at least
-locktime old. This prevents ARP cache thrashing.
-
-proxy_delay
------------
-
-Maximum time  (real  time is random [0..proxytime]) before answering to an ARP
-request for  which  we have an proxy ARP entry. In some cases, this is used to
-prevent network flooding.
-
-proxy_qlen
-----------
-
-Maximum queue length of the delayed proxy arp timer. (see proxy_delay).
-
-app_solicit
-----------
-
-Determines the  number of requests to send to the user level ARP daemon. Use 0
-to turn off.
-
-gc_stale_time
--------------
-
-Determines how  often  to  check  for stale ARP entries. After an ARP entry is
-stale it  will  be resolved again (which is useful when an IP address migrates
-to another  machine).  When  ucast_solicit is greater than 0 it first tries to
-send an  ARP  packet  directly  to  the  known  host  When  that  fails  and
-mcast_solicit is greater than 0, an ARP request is broadcasted.
-
-2.9 Appletalk
--------------
-
-The /proc/sys/net/appletalk  directory  holds the Appletalk configuration data
-when Appletalk is loaded. The configurable parameters are:
-
-aarp-expiry-time
-----------------
-
-The amount  of  time  we keep an ARP entry before expiring it. Used to age out
-old hosts.
-
-aarp-resolve-time
------------------
-
-The amount of time we will spend trying to resolve an Appletalk address.
-
-aarp-retransmit-limit
----------------------
-
-The number of times we will retransmit a query before giving up.
-
-aarp-tick-time
---------------
-
-Controls the rate at which expires are checked.
-
-The directory  /proc/net/appletalk  holds the list of active Appletalk sockets
-on a machine.
-
-The fields  indicate  the DDP type, the local address (in network:node format)
-the remote  address,  the  size of the transmit pending queue, the size of the
-received queue  (bytes waiting for applications to read) the state and the uid
-owning the socket.
-
-/proc/net/atalk_iface lists  all  the  interfaces  configured for appletalk.It
-shows the  name  of the interface, its Appletalk address, the network range on
-that address  (or  network number for phase 1 networks), and the status of the
-interface.
-
-/proc/net/atalk_route lists  each  known  network  route.  It lists the target
-(network) that the route leads to, the router (may be directly connected), the
-route flags, and the device the route is using.
-
-2.10 IPX
---------
-
-The IPX protocol has no tunable values in proc/sys/net.
-
-The IPX  protocol  does,  however,  provide  proc/net/ipx. This lists each IPX
-socket giving  the  local  and  remote  addresses  in  Novell  format (that is
-network:node:port). In  accordance  with  the  strange  Novell  tradition,
-everything but the port is in hex. Not_Connected is displayed for sockets that
-are not  tied to a specific remote address. The Tx and Rx queue sizes indicate
-the number  of  bytes  pending  for  transmission  and  reception.  The  state
-indicates the  state  the  socket  is  in and the uid is the owning uid of the
-socket.
-
-The /proc/net/ipx_interface  file lists all IPX interfaces. For each interface
-it gives  the network number, the node number, and indicates if the network is
-the primary  network.  It  also  indicates  which  device  it  is bound to (or
-Internal for  internal  networks)  and  the  Frame  Type if appropriate. Linux
-supports 802.3,  802.2,  802.2  SNAP  and DIX (Blue Book) ethernet framing for
-IPX.
-
-The /proc/net/ipx_route  table  holds  a list of IPX routes. For each route it
-gives the  destination  network, the router node (or Directly) and the network
-address of the router (or Connected) for internal networks.
-
-2.11 /proc/sys/fs/mqueue - POSIX message queues filesystem
-----------------------------------------------------------
-
-The "mqueue"  filesystem provides  the necessary kernel features to enable the
-creation of a  user space  library that  implements  the  POSIX message queues
-API (as noted by the  MSG tag in the  POSIX 1003.1-2001 version  of the System
-Interfaces specification.)
-
-The "mqueue" filesystem contains values for determining/setting  the amount of
-resources used by the file system.
-
-/proc/sys/fs/mqueue/queues_max is a read/write  file for  setting/getting  the
-maximum number of message queues allowed on the system.
-
-/proc/sys/fs/mqueue/msg_max  is  a  read/write file  for  setting/getting  the
-maximum number of messages in a queue value.  In fact it is the limiting value
-for another (user) limit which is set in mq_open invocation. This attribute of
-a queue must be less or equal then msg_max.
-
-/proc/sys/fs/mqueue/msgsize_max is  a read/write  file for setting/getting the
-maximum  message size value (it is every  message queue's attribute set during
-its creation).
+------------------------------------------------------------------------------
+CHAPTER 3: PER-PROCESS PARAMETERS
+------------------------------------------------------------------------------
 
-2.12 /proc/<pid>/oom_adj - Adjust the oom-killer score
+3.1 /proc/<pid>/oom_adj - Adjust the oom-killer score
 ------------------------------------------------------
 
 This file can be used to adjust the score used to select which processes
@@ -2041,25 +1037,15 @@ The task with the highest badness score is then selected and its children
 are killed, process itself will be killed in an OOM situation when it does
 not have children or some of them disabled oom like described above.
 
-2.13 /proc/<pid>/oom_score - Display current oom-killer score
+3.2 /proc/<pid>/oom_score - Display current oom-killer score
 -------------------------------------------------------------
 
-------------------------------------------------------------------------------
 This file can be used to check the current score used by the oom-killer is for
 any given <pid>. Use it together with /proc/<pid>/oom_adj to tune which
 process should be killed in an out-of-memory situation.
 
-------------------------------------------------------------------------------
-Summary
-------------------------------------------------------------------------------
-Certain aspects  of  kernel  behavior  can be modified at runtime, without the
-need to  recompile  the kernel, or even to reboot the system. The files in the
-/proc/sys tree  can  not only be read, but also modified. You can use the echo
-command to write value into these files, thereby changing the default settings
-of the kernel.
-------------------------------------------------------------------------------
 
-2.14  /proc/<pid>/io - Display the IO accounting fields
+3.3  /proc/<pid>/io - Display the IO accounting fields
 -------------------------------------------------------
 
 This file contains IO statistics for each running process
@@ -2161,7 +1147,7 @@ those 64-bit counters, process A could see an intermediate result.
 More information about this can be found within the taskstats documentation in
 Documentation/accounting.
 
-2.15 /proc/<pid>/coredump_filter - Core dump filtering settings
+3.4 /proc/<pid>/coredump_filter - Core dump filtering settings
 ---------------------------------------------------------------
 When a process is dumped, all anonymous memory is written to a core file as
 long as the size of the core file isn't limited. But sometimes we don't want
@@ -2205,7 +1191,7 @@ For example:
   $ echo 0x7 > /proc/self/coredump_filter
   $ ./some_program
 
-2.16	/proc/<pid>/mountinfo - Information about mounts
+3.5	/proc/<pid>/mountinfo - Information about mounts
 --------------------------------------------------------
 
 This file contains lines of the form:
@@ -2242,30 +1228,3 @@ For more information on mount propagation see:
 
   Documentation/filesystems/sharedsubtree.txt
 
-2.17	/proc/sys/fs/epoll - Configuration options for the epoll interface
---------------------------------------------------------
-
-This directory contains configuration options for the epoll(7) interface.
-
-max_user_instances
-------------------
-
-This is the maximum number of epoll file descriptors that a single user can
-have open at a given time. The default value is 128, and should be enough
-for normal users.
-
-max_user_watches
-----------------
-
-Every epoll file descriptor can store a number of files to be monitored
-for event readiness. Each one of these monitored files constitutes a "watch".
-This configuration option sets the maximum number of "watches" that are
-allowed for each user.
-Each "watch" costs roughly 90 bytes on a 32bit kernel, and roughly 160 bytes
-on a 64bit one.
-The current default value for  max_user_watches  is the 1/32 of the available
-low memory, divided for the "watch" cost in bytes.
-
-
-------------------------------------------------------------------------------
-
diff --git a/Documentation/filesystems/udf.txt b/Documentation/filesystems/udf.txt
index fde829a756e6..902b95d0ee51 100644
--- a/Documentation/filesystems/udf.txt
+++ b/Documentation/filesystems/udf.txt
@@ -24,6 +24,8 @@ The following mount options are supported:
 
 	gid=		Set the default group.
 	umask=		Set the default umask.
+	mode=		Set the default file permissions.
+	dmode=		Set the default directory permissions.
 	uid=		Set the default user.
 	bs=		Set the block size.
 	unhide		Show otherwise hidden files.
diff --git a/Documentation/gpio.txt b/Documentation/gpio.txt
index b1b988701247..145c25a170c7 100644
--- a/Documentation/gpio.txt
+++ b/Documentation/gpio.txt
@@ -123,7 +123,10 @@ platform-specific implementation issue.
 
 Using GPIOs
 -----------
-One of the first things to do with a GPIO, often in board setup code when
+The first thing a system should do with a GPIO is allocate it, using
+the gpio_request() call; see later.
+
+One of the next things to do with a GPIO, often in board setup code when
 setting up a platform_device using the GPIO, is mark its direction:
 
 	/* set as input or output, returning 0 or negative errno */
@@ -141,8 +144,8 @@ This helps avoid signal glitching during system startup.
 
 For compatibility with legacy interfaces to GPIOs, setting the direction
 of a GPIO implicitly requests that GPIO (see below) if it has not been
-requested already.  That compatibility may be removed in the future;
-explicitly requesting GPIOs is strongly preferred.
+requested already.  That compatibility is being removed from the optional
+gpiolib framework.
 
 Setting the direction can fail if the GPIO number is invalid, or when
 that particular GPIO can't be used in that mode.  It's generally a bad
@@ -195,7 +198,7 @@ This requires sleeping, which can't be done from inside IRQ handlers.
 
 Platforms that support this type of GPIO distinguish them from other GPIOs
 by returning nonzero from this call (which requires a valid GPIO number,
-either explicitly or implicitly requested):
+which should have been previously allocated with gpio_request):
 
 	int gpio_cansleep(unsigned gpio);
 
@@ -212,10 +215,9 @@ for GPIOs that can't be accessed from IRQ handlers, these calls act the
 same as the spinlock-safe calls.
 
 
-Claiming and Releasing GPIOs (OPTIONAL)
----------------------------------------
+Claiming and Releasing GPIOs
+----------------------------
 To help catch system configuration errors, two calls are defined.
-However, many platforms don't currently support this mechanism.
 
 	/* request GPIO, returning 0 or negative errno.
 	 * non-null labels may be useful for diagnostics.
@@ -244,13 +246,6 @@ Some platforms may also use knowledge about what GPIOs are active for
 power management, such as by powering down unused chip sectors and, more
 easily, gating off unused clocks.
 
-These two calls are optional because not not all current Linux platforms
-offer such functionality in their GPIO support; a valid implementation
-could return success for all gpio_request() calls.  Unlike the other calls,
-the state they represent doesn't normally match anything from a hardware
-register; it's just a software bitmap which clearly is not necessary for
-correct operation of hardware or (bug free) drivers.
-
 Note that requesting a GPIO does NOT cause it to be configured in any
 way; it just marks that GPIO as in use.  Separate code must handle any
 pin setup (e.g. controlling which pin the GPIO uses, pullup/pulldown).
diff --git a/Documentation/ia64/kvm.txt b/Documentation/ia64/kvm.txt
index 84f7cb3d5bec..ffb5c80bec3e 100644
--- a/Documentation/ia64/kvm.txt
+++ b/Documentation/ia64/kvm.txt
@@ -42,7 +42,7 @@ Note: For step 2, please make sure that host page size == TARGET_PAGE_SIZE of qe
 		hg clone http://xenbits.xensource.com/ext/efi-vfirmware.hg
 	    you can get the firmware's binary in the directory of efi-vfirmware.hg/binaries.
 
-	(3) Rename the firware you owned to Flash.fd, and copy it to /usr/local/share/qemu
+	(3) Rename the firmware you owned to Flash.fd, and copy it to /usr/local/share/qemu
 
 4. Boot up Linux or Windows guests:
 	4.1 Create or install a image for guest boot. If you have xen experience, it should be easy.
diff --git a/Documentation/kernel-parameters.txt b/Documentation/kernel-parameters.txt
index ebdeb7c4330e..8932c58850be 100644
--- a/Documentation/kernel-parameters.txt
+++ b/Documentation/kernel-parameters.txt
@@ -618,6 +618,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	debug_objects	[KNL] Enable object debugging
 
+	no_debug_objects
+			[KNL] Disable object debugging
+
 	debugpat	[X86] Enable PAT debugging
 
 	decnet.addr=	[HW,NET]
@@ -1533,7 +1536,9 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	noclflush	[BUGS=X86] Don't use the CLFLUSH instruction
 
-	nohlt		[BUGS=ARM,SH]
+	nohlt		[BUGS=ARM,SH] Tells the kernel that the sleep(SH) or
+			wfi(ARM) instruction doesn't work correctly and not to
+			use it. This is also useful when using JTAG debugger.
 
 	no-hlt		[BUGS=X86-32] Tells the kernel that the hlt
 			instruction doesn't work correctly and not to
@@ -1613,7 +1618,7 @@ and is between 256 and 4096 characters. It is defined in the file
 	nosoftlockup	[KNL] Disable the soft-lockup detector.
 
 	noswapaccount	[KNL] Disable accounting of swap in memory resource
-			controller. (See Documentation/controllers/memory.txt)
+			controller. (See Documentation/cgroups/memory.txt)
 
 	nosync		[HW,M68K] Disables sync negotiation for all devices.
 
@@ -1963,7 +1968,7 @@ and is between 256 and 4096 characters. It is defined in the file
 
 	relax_domain_level=
 			[KNL, SMP] Set scheduler's default relax_domain_level.
-			See Documentation/cpusets.txt.
+			See Documentation/cgroups/cpusets.txt.
 
 	reserve=	[KNL,BUGS] Force the kernel to ignore some iomem area
 
diff --git a/Documentation/md.txt b/Documentation/md.txt
index 1da9d1b1793f..4edd39ec7db9 100644
--- a/Documentation/md.txt
+++ b/Documentation/md.txt
@@ -164,15 +164,19 @@ All md devices contain:
   raid_disks
      a text file with a simple number indicating the number of devices
      in a fully functional array.  If this is not yet known, the file
-     will be empty.  If an array is being resized (not currently
-     possible) this will contain the larger of the old and new sizes.
-     Some raid level (RAID1) allow this value to be set while the
-     array is active.  This will reconfigure the array.   Otherwise
-     it can only be set while assembling an array.
+     will be empty.  If an array is being resized this will contain
+     the new number of devices.
+     Some raid levels allow this value to be set while the array is
+     active.  This will reconfigure the array.   Otherwise it can only
+     be set while assembling an array.
+     A change to this attribute will not be permitted if it would
+     reduce the size of the array.  To reduce the number of drives
+     in an e.g. raid5, the array size must first be reduced by
+     setting the 'array_size' attribute.
 
   chunk_size
-     This is the size if bytes for 'chunks' and is only relevant to
-     raid levels that involve striping (1,4,5,6,10). The address space
+     This is the size in bytes for 'chunks' and is only relevant to
+     raid levels that involve striping (0,4,5,6,10). The address space
      of the array is conceptually divided into chunks and consecutive
      chunks are striped onto neighbouring devices.
      The size should be at least PAGE_SIZE (4k) and should be a power
@@ -183,6 +187,20 @@ All md devices contain:
      simply a number that is interpretted differently by different
      levels.  It can be written while assembling an array.
 
+  array_size
+     This can be used to artificially constrain the available space in
+     the array to be less than is actually available on the combined
+     devices.  Writing a number (in Kilobytes) which is less than
+     the available size will set the size.  Any reconfiguration of the
+     array (e.g. adding devices) will not cause the size to change.
+     Writing the word 'default' will cause the effective size of the
+     array to be whatever size is actually available based on
+     'level', 'chunk_size' and 'component_size'.
+
+     This can be used to reduce the size of the array before reducing
+     the number of devices in a raid4/5/6, or to support external
+     metadata formats which mandate such clipping.
+
   reshape_position
      This is either "none" or a sector number within the devices of
      the array where "reshape" is up to.  If this is set, the three
@@ -207,6 +225,11 @@ All md devices contain:
      about the array.  It can be 0.90 (traditional format), 1.0, 1.1,
      1.2 (newer format in varying locations) or "none" indicating that
      the kernel isn't managing metadata at all.
+     Alternately it can be "external:" followed by a string which
+     is set by user-space.  This indicates that metadata is managed
+     by a user-space program.  Any device failure or other event that
+     requires a metadata update will cause array activity to be
+     suspended until the event is acknowledged.
 
   resync_start
      The point at which resync should start.  If no resync is needed,
diff --git a/Documentation/networking/vxge.txt b/Documentation/networking/vxge.txt
new file mode 100644
index 000000000000..d2e2997e6fa0
--- /dev/null
+++ b/Documentation/networking/vxge.txt
@@ -0,0 +1,100 @@
+Neterion's (Formerly S2io) X3100 Series 10GbE PCIe Server Adapter Linux driver
+==============================================================================
+
+Contents
+--------
+
+1) Introduction
+2) Features supported
+3) Configurable driver parameters
+4) Troubleshooting
+
+1) Introduction:
+----------------
+This Linux driver supports all Neterion's X3100 series 10 GbE PCIe I/O
+Virtualized Server adapters.
+The X3100 series supports four modes of operation, configurable via
+firmware -
+	Single function mode
+	Multi function mode
+	SRIOV mode
+	MRIOV mode
+The functions share a 10GbE link and the pci-e bus, but hardly anything else
+inside the ASIC. Features like independent hw reset, statistics, bandwidth/
+priority allocation and guarantees, GRO, TSO, interrupt moderation etc are
+supported independently on each function.
+
+(See below for a complete list of features supported for both IPv4 and IPv6)
+
+2) Features supported:
+----------------------
+
+i)   Single function mode (up to 17 queues)
+
+ii)  Multi function mode (up to 17 functions)
+
+iii) PCI-SIG's I/O Virtualization
+       - Single Root mode: v1.0 (up to 17 functions)
+       - Multi-Root mode: v1.0 (up to 17 functions)
+
+iv)  Jumbo frames
+       X3100 Series supports MTU up to 9600 bytes, modifiable using
+       ifconfig command.
+
+v)   Offloads supported: (Enabled by default)
+       Checksum offload (TCP/UDP/IP) on transmit and receive paths
+       TCP Segmentation Offload (TSO) on transmit path
+       Generic Receive Offload (GRO) on receive path
+
+vi)  MSI-X: (Enabled by default)
+       Resulting in noticeable performance improvement (up to 7% on certain
+       platforms).
+
+vii) NAPI: (Enabled by default)
+       For better Rx interrupt moderation.
+
+viii)RTH (Receive Traffic Hash): (Enabled by default)
+       Receive side steering for better scaling.
+
+ix)  Statistics
+       Comprehensive MAC-level and software statistics displayed using
+       "ethtool -S" option.
+
+x)   Multiple hardware queues: (Enabled by default)
+       Up to 17 hardware based transmit and receive data channels, with
+       multiple steering options (transmit multiqueue enabled by default).
+
+3) Configurable driver parameters:
+----------------------------------
+
+i)  max_config_dev
+       Specifies maximum device functions to be enabled.
+       Valid range: 1-8
+
+ii) max_config_port
+       Specifies number of ports to be enabled.
+       Valid range: 1,2
+       Default: 1
+
+iii)max_config_vpath
+       Specifies maximum VPATH(s) configured for each device function.
+       Valid range: 1-17
+
+iv) vlan_tag_strip
+       Enables/disables vlan tag stripping from all received tagged frames that
+       are not replicated at the internal L2 switch.
+       Valid range: 0,1 (disabled, enabled respectively)
+       Default: 1
+
+v)  addr_learn_en
+       Enable learning the mac address of the guest OS interface in
+       virtualization environment.
+       Valid range: 0,1 (disabled, enabled respectively)
+       Default: 0
+
+4) Troubleshooting:
+-------------------
+
+To resolve an issue with the source code or X3100 series adapter, please collect
+the statistics, register dumps using ethool, relevant logs and email them to
+support@neterion.com.
diff --git a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt
index 6c238f59b2a9..249db3a15d15 100644
--- a/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt
+++ b/Documentation/powerpc/dts-bindings/fsl/cpm_qe/qe/firmware.txt
@@ -1,6 +1,6 @@
 * Uploaded QE firmware
 
-      If a new firwmare has been uploaded to the QE (usually by the
+      If a new firmware has been uploaded to the QE (usually by the
       boot loader), then a 'firmware' child node should be added to the QE
       node.  This node provides information on the uploaded firmware that
       device drivers may need.
diff --git a/Documentation/scheduler/sched-rt-group.txt b/Documentation/scheduler/sched-rt-group.txt
index 3ef339f491e0..5ba4d3fc625a 100644
--- a/Documentation/scheduler/sched-rt-group.txt
+++ b/Documentation/scheduler/sched-rt-group.txt
@@ -126,7 +126,7 @@ This uses the /cgroup virtual file system and "/cgroup/<cgroup>/cpu.rt_runtime_u
 to control the CPU time reserved for each control group instead.
 
 For more information on working with control groups, you should read
-Documentation/cgroups.txt as well.
+Documentation/cgroups/cgroups.txt as well.
 
 Group settings are checked against the following limits in order to keep the configuration
 schedulable:
diff --git a/Documentation/slow-work.txt b/Documentation/slow-work.txt
new file mode 100644
index 000000000000..ebc50f808ea4
--- /dev/null
+++ b/Documentation/slow-work.txt
@@ -0,0 +1,174 @@
+		     ====================================
+		     SLOW WORK ITEM EXECUTION THREAD POOL
+		     ====================================
+
+By: David Howells <dhowells@redhat.com>
+
+The slow work item execution thread pool is a pool of threads for performing
+things that take a relatively long time, such as making mkdir calls.
+Typically, when processing something, these items will spend a lot of time
+blocking a thread on I/O, thus making that thread unavailable for doing other
+work.
+
+The standard workqueue model is unsuitable for this class of work item as that
+limits the owner to a single thread or a single thread per CPU.  For some
+tasks, however, more threads - or fewer - are required.
+
+There is just one pool per system.  It contains no threads unless something
+wants to use it - and that something must register its interest first.  When
+the pool is active, the number of threads it contains is dynamic, varying
+between a maximum and minimum setting, depending on the load.
+
+
+====================
+CLASSES OF WORK ITEM
+====================
+
+This pool support two classes of work items:
+
+ (*) Slow work items.
+
+ (*) Very slow work items.
+
+The former are expected to finish much quicker than the latter.
+
+An operation of the very slow class may do a batch combination of several
+lookups, mkdirs, and a create for instance.
+
+An operation of the ordinarily slow class may, for example, write stuff or
+expand files, provided the time taken to do so isn't too long.
+
+Operations of both types may sleep during execution, thus tying up the thread
+loaned to it.
+
+
+THREAD-TO-CLASS ALLOCATION
+--------------------------
+
+Not all the threads in the pool are available to work on very slow work items.
+The number will be between one and one fewer than the number of active threads.
+This is configurable (see the "Pool Configuration" section).
+
+All the threads are available to work on ordinarily slow work items, but a
+percentage of the threads will prefer to work on very slow work items.
+
+The configuration ensures that at least one thread will be available to work on
+very slow work items, and at least one thread will be available that won't work
+on very slow work items at all.
+
+
+=====================
+USING SLOW WORK ITEMS
+=====================
+
+Firstly, a module or subsystem wanting to make use of slow work items must
+register its interest:
+
+	 int ret = slow_work_register_user();
+
+This will return 0 if successful, or a -ve error upon failure.
+
+
+Slow work items may then be set up by:
+
+ (1) Declaring a slow_work struct type variable:
+
+	#include <linux/slow-work.h>
+
+	struct slow_work myitem;
+
+ (2) Declaring the operations to be used for this item:
+
+	struct slow_work_ops myitem_ops = {
+		.get_ref = myitem_get_ref,
+		.put_ref = myitem_put_ref,
+		.execute = myitem_execute,
+	};
+
+     [*] For a description of the ops, see section "Item Operations".
+
+ (3) Initialising the item:
+
+	slow_work_init(&myitem, &myitem_ops);
+
+     or:
+
+	vslow_work_init(&myitem, &myitem_ops);
+
+     depending on its class.
+
+A suitably set up work item can then be enqueued for processing:
+
+	int ret = slow_work_enqueue(&myitem);
+
+This will return a -ve error if the thread pool is unable to gain a reference
+on the item, 0 otherwise.
+
+
+The items are reference counted, so there ought to be no need for a flush
+operation.  When all a module's slow work items have been processed, and the
+module has no further interest in the facility, it should unregister its
+interest:
+
+	slow_work_unregister_user();
+
+
+===============
+ITEM OPERATIONS
+===============
+
+Each work item requires a table of operations of type struct slow_work_ops.
+All members are required:
+
+ (*) Get a reference on an item:
+
+	int (*get_ref)(struct slow_work *work);
+
+     This allows the thread pool to attempt to pin an item by getting a
+     reference on it.  This function should return 0 if the reference was
+     granted, or a -ve error otherwise.  If an error is returned,
+     slow_work_enqueue() will fail.
+
+     The reference is held whilst the item is queued and whilst it is being
+     executed.  The item may then be requeued with the same reference held, or
+     the reference will be released.
+
+ (*) Release a reference on an item:
+
+	void (*put_ref)(struct slow_work *work);
+
+     This allows the thread pool to unpin an item by releasing the reference on
+     it.  The thread pool will not touch the item again once this has been
+     called.
+
+ (*) Execute an item:
+
+	void (*execute)(struct slow_work *work);
+
+     This should perform the work required of the item.  It may sleep, it may
+     perform disk I/O and it may wait for locks.
+
+
+==================
+POOL CONFIGURATION
+==================
+
+The slow-work thread pool has a number of configurables:
+
+ (*) /proc/sys/kernel/slow-work/min-threads
+
+     The minimum number of threads that should be in the pool whilst it is in
+     use.  This may be anywhere between 2 and max-threads.
+
+ (*) /proc/sys/kernel/slow-work/max-threads
+
+     The maximum number of threads that should in the pool.  This may be
+     anywhere between min-threads and 255 or NR_CPUS * 2, whichever is greater.
+
+ (*) /proc/sys/kernel/slow-work/vslow-percentage
+
+     The percentage of active threads in the pool that may be used to execute
+     very slow work items.  This may be between 1 and 99.  The resultant number
+     is bounded to between 1 and one fewer than the number of active threads.
+     This ensures there is always at least one thread that can process very
+     slow work items, and always at least one thread that won't.
diff --git a/Documentation/sysctl/00-INDEX b/Documentation/sysctl/00-INDEX
index a20a9066dc4c..1286f455992f 100644
--- a/Documentation/sysctl/00-INDEX
+++ b/Documentation/sysctl/00-INDEX
@@ -10,6 +10,8 @@ fs.txt
 	- documentation for /proc/sys/fs/*.
 kernel.txt
 	- documentation for /proc/sys/kernel/*.
+net.txt
+	- documentation for /proc/sys/net/*.
 sunrpc.txt
 	- documentation for /proc/sys/sunrpc/*.
 vm.txt
diff --git a/Documentation/sysctl/fs.txt b/Documentation/sysctl/fs.txt
index f99254327ae5..1458448436cc 100644
--- a/Documentation/sysctl/fs.txt
+++ b/Documentation/sysctl/fs.txt
@@ -1,5 +1,6 @@
 Documentation for /proc/sys/fs/*	kernel version 2.2.10
 	(c) 1998, 1999,  Rik van Riel <riel@nl.linux.org>
+	(c) 2009,        Shen Feng<shen@cn.fujitsu.com>
 
 For general info and legal blurb, please look in README.
 
@@ -14,7 +15,12 @@ kernel. Since some of the files _can_ be used to screw up your
 system, it is advisable to read both documentation and source
 before actually making adjustments.
 
+1. /proc/sys/fs
+----------------------------------------------------------
+
 Currently, these files are in /proc/sys/fs:
+- aio-max-nr
+- aio-nr
 - dentry-state
 - dquot-max
 - dquot-nr
@@ -30,8 +36,15 @@ Currently, these files are in /proc/sys/fs:
 - super-max
 - super-nr
 
-Documentation for the files in /proc/sys/fs/binfmt_misc is
-in Documentation/binfmt_misc.txt.
+==============================================================
+
+aio-nr & aio-max-nr:
+
+aio-nr is the running total of the number of events specified on the
+io_setup system call for all currently active aio contexts.  If aio-nr
+reaches aio-max-nr then io_setup will fail with EAGAIN.  Note that
+raising aio-max-nr does not result in the pre-allocation or re-sizing
+of any kernel data structures.
 
 ==============================================================
 
@@ -178,3 +191,60 @@ requests.  aio-max-nr allows you to change the maximum value
 aio-nr can grow to.
 
 ==============================================================
+
+
+2. /proc/sys/fs/binfmt_misc
+----------------------------------------------------------
+
+Documentation for the files in /proc/sys/fs/binfmt_misc is
+in Documentation/binfmt_misc.txt.
+
+
+3. /proc/sys/fs/mqueue - POSIX message queues filesystem
+----------------------------------------------------------
+
+The "mqueue"  filesystem provides  the necessary kernel features to enable the
+creation of a  user space  library that  implements  the  POSIX message queues
+API (as noted by the  MSG tag in the  POSIX 1003.1-2001 version  of the System
+Interfaces specification.)
+
+The "mqueue" filesystem contains values for determining/setting  the amount of
+resources used by the file system.
+
+/proc/sys/fs/mqueue/queues_max is a read/write  file for  setting/getting  the
+maximum number of message queues allowed on the system.
+
+/proc/sys/fs/mqueue/msg_max  is  a  read/write file  for  setting/getting  the
+maximum number of messages in a queue value.  In fact it is the limiting value
+for another (user) limit which is set in mq_open invocation. This attribute of
+a queue must be less or equal then msg_max.
+
+/proc/sys/fs/mqueue/msgsize_max is  a read/write  file for setting/getting the
+maximum  message size value (it is every  message queue's attribute set during
+its creation).
+
+
+4. /proc/sys/fs/epoll - Configuration options for the epoll interface
+--------------------------------------------------------
+
+This directory contains configuration options for the epoll(7) interface.
+
+max_user_instances
+------------------
+
+This is the maximum number of epoll file descriptors that a single user can
+have open at a given time. The default value is 128, and should be enough
+for normal users.
+
+max_user_watches
+----------------
+
+Every epoll file descriptor can store a number of files to be monitored
+for event readiness. Each one of these monitored files constitutes a "watch".
+This configuration option sets the maximum number of "watches" that are
+allowed for each user.
+Each "watch" costs roughly 90 bytes on a 32bit kernel, and roughly 160 bytes
+on a 64bit one.
+The current default value for  max_user_watches  is the 1/32 of the available
+low memory, divided for the "watch" cost in bytes.
+
diff --git a/Documentation/sysctl/kernel.txt b/Documentation/sysctl/kernel.txt
index a4ccdd1981cf..f11ca7979fa6 100644
--- a/Documentation/sysctl/kernel.txt
+++ b/Documentation/sysctl/kernel.txt
@@ -1,5 +1,6 @@
 Documentation for /proc/sys/kernel/*	kernel version 2.2.10
 	(c) 1998, 1999,  Rik van Riel <riel@nl.linux.org>
+	(c) 2009,        Shen Feng<shen@cn.fujitsu.com>
 
 For general info and legal blurb, please look in README.
 
@@ -18,6 +19,7 @@ Currently, these files might (depending on your configuration)
 show up in /proc/sys/kernel:
 - acpi_video_flags
 - acct
+- auto_msgmni
 - core_pattern
 - core_uses_pid
 - ctrl-alt-del
@@ -33,6 +35,7 @@ show up in /proc/sys/kernel:
 - msgmax
 - msgmnb
 - msgmni
+- nmi_watchdog
 - osrelease
 - ostype
 - overflowgid
@@ -40,6 +43,7 @@ show up in /proc/sys/kernel:
 - panic
 - pid_max
 - powersave-nap               [ PPC only ]
+- panic_on_unrecovered_nmi
 - printk
 - randomize_va_space
 - real-root-dev               ==> Documentation/initrd.txt
@@ -55,6 +59,7 @@ show up in /proc/sys/kernel:
 - sysrq                       ==> Documentation/sysrq.txt
 - tainted
 - threads-max
+- unknown_nmi_panic
 - version
 
 ==============================================================
@@ -381,3 +386,51 @@ can be ORed together:
  512 - A kernel warning has occurred.
 1024 - A module from drivers/staging was loaded.
 
+==============================================================
+
+auto_msgmni:
+
+Enables/Disables automatic recomputing of msgmni upon memory add/remove or
+upon ipc namespace creation/removal (see the msgmni description above).
+Echoing "1" into this file enables msgmni automatic recomputing.
+Echoing "0" turns it off.
+auto_msgmni default value is 1.
+
+==============================================================
+
+nmi_watchdog:
+
+Enables/Disables the NMI watchdog on x86 systems.  When the value is non-zero
+the NMI watchdog is enabled and will continuously test all online cpus to
+determine whether or not they are still functioning properly. Currently,
+passing "nmi_watchdog=" parameter at boot time is required for this function
+to work.
+
+If LAPIC NMI watchdog method is in use (nmi_watchdog=2 kernel parameter), the
+NMI watchdog shares registers with oprofile. By disabling the NMI watchdog,
+oprofile may have more registers to utilize.
+
+==============================================================
+
+unknown_nmi_panic:
+
+The value in this file affects behavior of handling NMI. When the value is
+non-zero, unknown NMI is trapped and then panic occurs. At that time, kernel
+debugging information is displayed on console.
+
+NMI switch that most IA32 servers have fires unknown NMI up, for example.
+If a system hangs up, try pressing the NMI switch.
+
+==============================================================
+
+panic_on_unrecovered_nmi:
+
+The default Linux behaviour on an NMI of either memory or unknown is to continue
+operation. For many environments such as scientific computing it is preferable
+that the box is taken out and the error dealt with than an uncorrected
+parity/ECC error get propogated.
+
+A small number of systems do generate NMI's for bizarre random reasons such as
+power management so the default is off. That sysctl works like the existing
+panic controls already in that directory.
+
diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt
new file mode 100644
index 000000000000..a34d55b65441
--- /dev/null
+++ b/Documentation/sysctl/net.txt
@@ -0,0 +1,175 @@
+Documentation for /proc/sys/net/*	kernel version 2.4.0-test11-pre4
+	(c) 1999		Terrehon Bowden <terrehon@pacbell.net>
+				Bodo Bauer <bb@ricochet.net>
+	(c) 2000		Jorge Nerin <comandante@zaralinux.com>
+	(c) 2009		Shen Feng <shen@cn.fujitsu.com>
+
+For general info and legal blurb, please look in README.
+
+==============================================================
+
+This file contains the documentation for the sysctl files in
+/proc/sys/net and is valid for Linux kernel version 2.4.0-test11-pre4.
+
+The interface  to  the  networking  parts  of  the  kernel  is  located  in
+/proc/sys/net. The following table shows all possible subdirectories.You may
+see only some of them, depending on your kernel's configuration.
+
+
+Table : Subdirectories in /proc/sys/net
+..............................................................................
+ Directory Content             Directory  Content
+ core      General parameter   appletalk  Appletalk protocol
+ unix      Unix domain sockets netrom     NET/ROM
+ 802       E802 protocol       ax25       AX25
+ ethernet  Ethernet protocol   rose       X.25 PLP layer
+ ipv4      IP version 4        x25        X.25 protocol
+ ipx       IPX                 token-ring IBM token ring
+ bridge    Bridging            decnet     DEC net
+ ipv6      IP version 6
+..............................................................................
+
+1. /proc/sys/net/core - Network core options
+-------------------------------------------------------
+
+rmem_default
+------------
+
+The default setting of the socket receive buffer in bytes.
+
+rmem_max
+--------
+
+The maximum receive socket buffer size in bytes.
+
+wmem_default
+------------
+
+The default setting (in bytes) of the socket send buffer.
+
+wmem_max
+--------
+
+The maximum send socket buffer size in bytes.
+
+message_burst and message_cost
+------------------------------
+
+These parameters  are used to limit the warning messages written to the kernel
+log from  the  networking  code.  They  enforce  a  rate  limit  to  make  a
+denial-of-service attack  impossible. A higher message_cost factor, results in
+fewer messages that will be written. Message_burst controls when messages will
+be dropped.  The  default  settings  limit  warning messages to one every five
+seconds.
+
+warnings
+--------
+
+This controls console messages from the networking stack that can occur because
+of problems on the network like duplicate address or bad checksums. Normally,
+this should be enabled, but if the problem persists the messages can be
+disabled.
+
+netdev_budget
+-------------
+
+Maximum number of packets taken from all interfaces in one polling cycle (NAPI
+poll). In one polling cycle interfaces which are registered to polling are
+probed in a round-robin manner. The limit of packets in one such probe can be
+set per-device via sysfs class/net/<device>/weight .
+
+netdev_max_backlog
+------------------
+
+Maximum number  of  packets,  queued  on  the  INPUT  side, when the interface
+receives packets faster than kernel can process them.
+
+optmem_max
+----------
+
+Maximum ancillary buffer size allowed per socket. Ancillary data is a sequence
+of struct cmsghdr structures with appended data.
+
+2. /proc/sys/net/unix - Parameters for Unix domain sockets
+-------------------------------------------------------
+
+There is only one file in this directory.
+unix_dgram_qlen limits the max number of datagrams queued in Unix domain
+socket's buffer. It will not take effect unless PF_UNIX flag is spicified.
+
+
+3. /proc/sys/net/ipv4 - IPV4 settings
+-------------------------------------------------------
+Please see: Documentation/networking/ip-sysctl.txt and ipvs-sysctl.txt for
+descriptions of these entries.
+
+
+4. Appletalk
+-------------------------------------------------------
+
+The /proc/sys/net/appletalk  directory  holds the Appletalk configuration data
+when Appletalk is loaded. The configurable parameters are:
+
+aarp-expiry-time
+----------------
+
+The amount  of  time  we keep an ARP entry before expiring it. Used to age out
+old hosts.
+
+aarp-resolve-time
+-----------------
+
+The amount of time we will spend trying to resolve an Appletalk address.
+
+aarp-retransmit-limit
+---------------------
+
+The number of times we will retransmit a query before giving up.
+
+aarp-tick-time
+--------------
+
+Controls the rate at which expires are checked.
+
+The directory  /proc/net/appletalk  holds the list of active Appletalk sockets
+on a machine.
+
+The fields  indicate  the DDP type, the local address (in network:node format)
+the remote  address,  the  size of the transmit pending queue, the size of the
+received queue  (bytes waiting for applications to read) the state and the uid
+owning the socket.
+
+/proc/net/atalk_iface lists  all  the  interfaces  configured for appletalk.It
+shows the  name  of the interface, its Appletalk address, the network range on
+that address  (or  network number for phase 1 networks), and the status of the
+interface.
+
+/proc/net/atalk_route lists  each  known  network  route.  It lists the target
+(network) that the route leads to, the router (may be directly connected), the
+route flags, and the device the route is using.
+
+
+5. IPX
+-------------------------------------------------------
+
+The IPX protocol has no tunable values in proc/sys/net.
+
+The IPX  protocol  does,  however,  provide  proc/net/ipx. This lists each IPX
+socket giving  the  local  and  remote  addresses  in  Novell  format (that is
+network:node:port). In  accordance  with  the  strange  Novell  tradition,
+everything but the port is in hex. Not_Connected is displayed for sockets that
+are not  tied to a specific remote address. The Tx and Rx queue sizes indicate
+the number  of  bytes  pending  for  transmission  and  reception.  The  state
+indicates the  state  the  socket  is  in and the uid is the owning uid of the
+socket.
+
+The /proc/net/ipx_interface  file lists all IPX interfaces. For each interface
+it gives  the network number, the node number, and indicates if the network is
+the primary  network.  It  also  indicates  which  device  it  is bound to (or
+Internal for  internal  networks)  and  the  Frame  Type if appropriate. Linux
+supports 802.3,  802.2,  802.2  SNAP  and DIX (Blue Book) ethernet framing for
+IPX.
+
+The /proc/net/ipx_route  table  holds  a list of IPX routes. For each route it
+gives the  destination  network, the router node (or Directly) and the network
+address of the router (or Connected) for internal networks.
diff --git a/Documentation/vm/numa_memory_policy.txt b/Documentation/vm/numa_memory_policy.txt
index 6aaaeb38730c..be45dbb9d7f2 100644
--- a/Documentation/vm/numa_memory_policy.txt
+++ b/Documentation/vm/numa_memory_policy.txt
@@ -8,7 +8,8 @@ The current memory policy support was added to Linux 2.6 around May 2004.  This
 document attempts to describe the concepts and APIs of the 2.6 memory policy
 support.
 
-Memory policies should not be confused with cpusets (Documentation/cpusets.txt)
+Memory policies should not be confused with cpusets
+(Documentation/cgroups/cpusets.txt)
 which is an administrative mechanism for restricting the nodes from which
 memory may be allocated by a set of processes. Memory policies are a
 programming interface that a NUMA-aware application can take advantage of.  When
diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration
index d5fdfd34bbaf..6513fe2d90b8 100644
--- a/Documentation/vm/page_migration
+++ b/Documentation/vm/page_migration
@@ -37,7 +37,8 @@ locations.
 
 Larger installations usually partition the system using cpusets into
 sections of nodes. Paul Jackson has equipped cpusets with the ability to
-move pages when a task is moved to another cpuset (See ../cpusets.txt).
+move pages when a task is moved to another cpuset (See
+Documentation/cgroups/cpusets.txt).
 Cpusets allows the automation of process locality. If a task is moved to
 a new cpuset then also all its pages are moved with it so that the
 performance of the process does not sink dramatically. Also the pages
diff --git a/Documentation/x86/x86_64/fake-numa-for-cpusets b/Documentation/x86/x86_64/fake-numa-for-cpusets
index 33bb56655991..0f11d9becb0b 100644
--- a/Documentation/x86/x86_64/fake-numa-for-cpusets
+++ b/Documentation/x86/x86_64/fake-numa-for-cpusets
@@ -7,7 +7,8 @@ you can create fake NUMA nodes that represent contiguous chunks of memory and
 assign them to cpusets and their attached tasks.  This is a way of limiting the
 amount of system memory that are available to a certain class of tasks.
 
-For more information on the features of cpusets, see Documentation/cpusets.txt.
+For more information on the features of cpusets, see
+Documentation/cgroups/cpusets.txt.
 There are a number of different configurations you can use for your needs.  For
 more information on the numa=fake command line option and its various ways of
 configuring fake nodes, see Documentation/x86/x86_64/boot-options.txt.
@@ -32,7 +33,7 @@ A machine may be split as follows with "numa=fake=4*512," as reported by dmesg:
 	On node 3 totalpages: 131072
 
 Now following the instructions for mounting the cpusets filesystem from
-Documentation/cpusets.txt, you can assign fake nodes (i.e. contiguous memory
+Documentation/cgroups/cpusets.txt, you can assign fake nodes (i.e. contiguous memory
 address spaces) to individual cpusets:
 
 	[root@xroads /]# mkdir exampleset
diff --git a/MAINTAINERS b/MAINTAINERS
index 25a17b49cfe1..30677193d019 100644
--- a/MAINTAINERS
+++ b/MAINTAINERS
@@ -1763,6 +1763,12 @@ M:	viro@zeniv.linux.org.uk
 L:	linux-fsdevel@vger.kernel.org
 S:	Maintained
 
+FINTEK F75375S HARDWARE MONITOR AND FAN CONTROLLER DRIVER
+P:	Riku Voipio
+M:	riku.vipio@iki.fi
+L:	lm-sensors@lm-sensors.org
+S:	Maintained
+
 FIREWIRE SUBSYSTEM (drivers/firewire, <linux/firewire*.h>)
 P:	Kristian Hoegsberg, Stefan Richter
 M:	krh@redhat.com, stefanr@s5r6.in-berlin.de
@@ -1945,6 +1951,12 @@ L:	lm-sensors@lm-sensors.org
 W:	http://www.kernel.org/pub/linux/kernel/people/fseidel/hdaps/
 S:	Maintained
 
+HYPERVISOR VIRTUAL CONSOLE DRIVER
+L:	linuxppc-dev@ozlabs.org
+L:	linux-kernel@vger.kernel.org
+S:	Odd Fixes
+F:	drivers/char/hvc_*
+
 GSPCA FINEPIX SUBDRIVER
 P:	Frank Zago
 M:	frank@zago.net
@@ -2918,6 +2930,12 @@ M:	buytenh@marvell.com
 L:	netdev@vger.kernel.org
 S:	Supported
 
+MARVELL SOC MMC/SD/SDIO CONTROLLER DRIVER
+P:	Nicolas Pitre
+M:	nico@cam.org
+L:	linux-kernel@vger.kernel.org
+S:	Maintained
+
 MARVELL YUKON / SYSKONNECT DRIVER
 P:	Mirko Lindner
 M:	mlindner@syskonnect.de
@@ -3104,7 +3122,7 @@ M:	shemminger@linux-foundation.org
 L:	netem@lists.linux-foundation.org
 S:	Maintained
 
-NETERION (S2IO) Xframe 10GbE DRIVER
+NETERION (S2IO) 10GbE DRIVER (xframe/vxge)
 P:	Ramkrishna Vepa
 M:	ram.vepa@neterion.com
 P:	Rastapur Santosh
@@ -3113,8 +3131,11 @@ P:	Sivakumar Subramani
 M:	sivakumar.subramani@neterion.com
 P:	Sreenivasa Honnur
 M:	sreenivasa.honnur@neterion.com
+P:	Anil Murthy
+M:	anil.murthy@neterion.com
 L:	netdev@vger.kernel.org
-W:	http://trac.neterion.com/cgi-bin/trac.cgi/wiki/TitleIndex?anonymous
+W:	http://trac.neterion.com/cgi-bin/trac.cgi/wiki/Linux?Anonymous
+W:	http://trac.neterion.com/cgi-bin/trac.cgi/wiki/X3100Linux?Anonymous
 S:	Supported
 
 NETFILTER/IPTABLES/IPCHAINS
@@ -3405,6 +3426,11 @@ P:	Jim Cromie
 M:	jim.cromie@gmail.com
 S:	Maintained
 
+PCA9532 LED DRIVER
+P:	Riku Voipio
+M:	riku.voipio@iki.fi
+S:	Maintained
+
 PCI ERROR RECOVERY
 P:	Linas Vepstas
 M:	linas@austin.ibm.com
@@ -3902,7 +3928,14 @@ S:	Maintained
 SECURE DIGITAL HOST CONTROLLER INTERFACE (SDHCI) DRIVER
 P:	Pierre Ossman
 M:	drzeus-sdhci@drzeus.cx
-L:	sdhci-devel@list.drzeus.cx
+L:	sdhci-devel@lists.ossman.eu
+S:	Maintained
+
+SECURE DIGITAL HOST CONTROLLER INTERFACE, OPEN FIRMWARE BINDINGS (SDHCI-OF)
+P:	Anton Vorontsov
+M:	avorontsov@ru.mvista.com
+L:	linuxppc-dev@ozlabs.org
+L:	sdhci-devel@lists.ossman.eu
 S:	Maintained
 
 SECURITY SUBSYSTEM
@@ -4380,6 +4413,11 @@ L:	tlinux-users@tce.toshiba-dme.co.jp
 W:	http://www.buzzard.org.uk/toshiba/
 S:	Maintained
 
+TMIO MMC DRIVER
+P:	Ian Molton
+M:	ian@mnementh.co.uk
+S:	Maintained
+
 TPM DEVICE DRIVER
 P:	Debora Velarde
 M:	debora@linux.vnet.ibm.com
@@ -4844,7 +4882,7 @@ M:	lrg@slimlogic.co.uk
 P:	Mark Brown
 M:	broonie@opensource.wolfsonmicro.com
 W:	http://opensource.wolfsonmicro.com/node/15
-W:	http://www.slimlogic.co.uk/?page_id=5
+W:	http://www.slimlogic.co.uk/?p=48
 T:	git kernel.org/pub/scm/linux/kernel/git/lrg/voltage-2.6.git
 S:	Supported
 
@@ -4966,7 +5004,8 @@ S:	Supported
 
 XFS FILESYSTEM
 P:	Silicon Graphics Inc
-P:	Bill O'Donnell
+P:	Felix Blyakher
+M:	felixb@sgi.com
 M:	xfs-masters@oss.sgi.com
 L:	xfs@oss.sgi.com
 W:	http://oss.sgi.com/projects/xfs
diff --git a/arch/alpha/include/asm/spinlock.h b/arch/alpha/include/asm/spinlock.h
index aeeb125f6851..e38fb95cb335 100644
--- a/arch/alpha/include/asm/spinlock.h
+++ b/arch/alpha/include/asm/spinlock.h
@@ -166,6 +166,9 @@ static inline void __raw_write_unlock(raw_rwlock_t * lock)
 	lock->lock = 0;
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
diff --git a/arch/alpha/kernel/process.c b/arch/alpha/kernel/process.c
index 8d0097f10208..3a2fb7a02db4 100644
--- a/arch/alpha/kernel/process.c
+++ b/arch/alpha/kernel/process.c
@@ -272,7 +272,7 @@ alpha_vfork(struct pt_regs *regs)
  */
 
 int
-copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+copy_thread(unsigned long clone_flags, unsigned long usp,
 	    unsigned long unused,
 	    struct task_struct * p, struct pt_regs * regs)
 {
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index 393c81641314..9e6e512f0117 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -18,7 +18,10 @@
 
 unsigned int __machine_arch_type;
 
-#include <linux/string.h>
+#include <linux/compiler.h>	/* for inline */
+#include <linux/types.h>	/* for size_t */
+#include <linux/stddef.h>	/* for NULL */
+#include <asm/string.h>
 
 #ifdef STANDALONE_DEBUG
 #define putstr printf
diff --git a/arch/arm/configs/omap_ldp_defconfig b/arch/arm/configs/omap_ldp_defconfig
index aa9d34feddc6..679a4a3e265e 100644
--- a/arch/arm/configs/omap_ldp_defconfig
+++ b/arch/arm/configs/omap_ldp_defconfig
@@ -474,14 +474,34 @@ CONFIG_NETDEVICES=y
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_VETH is not set
-# CONFIG_PHYLIB is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+CONFIG_SMSC_PHY=y
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 # CONFIG_AX88796 is not set
 # CONFIG_SMC91X is not set
 # CONFIG_DM9000 is not set
 # CONFIG_ENC28J60 is not set
-CONFIG_SMC911X=y
+# CONFIG_SMC911X is not set
+CONFIG_SMSC911X=y
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
 # CONFIG_IBM_NEW_EMAC_TAH is not set
diff --git a/arch/arm/configs/pcm037_defconfig b/arch/arm/configs/pcm037_defconfig
index 627474586470..6e37c77c4760 100644
--- a/arch/arm/configs/pcm037_defconfig
+++ b/arch/arm/configs/pcm037_defconfig
@@ -465,12 +465,33 @@ CONFIG_NETDEVICES=y
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_VETH is not set
-# CONFIG_PHYLIB is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+CONFIG_SMSC_PHY=y
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 # CONFIG_AX88796 is not set
 CONFIG_SMC91X=y
 # CONFIG_DM9000 is not set
+# CONFIG_SMC911X is not set
+CONFIG_SMSC911X=y
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
 # CONFIG_IBM_NEW_EMAC_TAH is not set
diff --git a/arch/arm/configs/realview-smp_defconfig b/arch/arm/configs/realview-smp_defconfig
index cd29824d791c..21db4b3ec8ff 100644
--- a/arch/arm/configs/realview-smp_defconfig
+++ b/arch/arm/configs/realview-smp_defconfig
@@ -496,13 +496,33 @@ CONFIG_NETDEVICES=y
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_VETH is not set
-# CONFIG_PHYLIB is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+CONFIG_SMSC_PHY=y
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 # CONFIG_AX88796 is not set
 CONFIG_SMC91X=y
 # CONFIG_DM9000 is not set
-CONFIG_SMC911X=y
+# CONFIG_SMC911X is not set
+CONFIG_SMSC911X=y
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
 # CONFIG_IBM_NEW_EMAC_TAH is not set
diff --git a/arch/arm/configs/realview_defconfig b/arch/arm/configs/realview_defconfig
index 7e253f58ed18..9a75c30b910d 100644
--- a/arch/arm/configs/realview_defconfig
+++ b/arch/arm/configs/realview_defconfig
@@ -490,13 +490,33 @@ CONFIG_NETDEVICES=y
 # CONFIG_EQUALIZER is not set
 # CONFIG_TUN is not set
 # CONFIG_VETH is not set
-# CONFIG_PHYLIB is not set
+CONFIG_PHYLIB=y
+
+#
+# MII PHY device drivers
+#
+# CONFIG_MARVELL_PHY is not set
+# CONFIG_DAVICOM_PHY is not set
+# CONFIG_QSEMI_PHY is not set
+# CONFIG_LXT_PHY is not set
+# CONFIG_CICADA_PHY is not set
+# CONFIG_VITESSE_PHY is not set
+CONFIG_SMSC_PHY=y
+# CONFIG_BROADCOM_PHY is not set
+# CONFIG_ICPLUS_PHY is not set
+# CONFIG_REALTEK_PHY is not set
+# CONFIG_NATIONAL_PHY is not set
+# CONFIG_STE10XP is not set
+# CONFIG_LSI_ET1011C_PHY is not set
+# CONFIG_FIXED_PHY is not set
+# CONFIG_MDIO_BITBANG is not set
 CONFIG_NET_ETHERNET=y
 CONFIG_MII=y
 # CONFIG_AX88796 is not set
 CONFIG_SMC91X=y
 # CONFIG_DM9000 is not set
-CONFIG_SMC911X=y
+# CONFIG_SMC911X is not set
+CONFIG_SMSC911X=y
 # CONFIG_IBM_NEW_EMAC_ZMII is not set
 # CONFIG_IBM_NEW_EMAC_RGMII is not set
 # CONFIG_IBM_NEW_EMAC_TAH is not set
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 2b41ebbfa7ff..c13681ac1ede 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -217,6 +217,9 @@ static inline int __raw_read_trylock(raw_rwlock_t *rw)
 /* read_can_lock - would read_trylock() succeed? */
 #define __raw_read_can_lock(x)		((x)->lock < 0x80000000)
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 2de14e2afdc5..c3265a2e7cd4 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -301,7 +301,7 @@ void release_thread(struct task_struct *dead_task)
 asmlinkage void ret_from_fork(void) __asm__("ret_from_fork");
 
 int
-copy_thread(int nr, unsigned long clone_flags, unsigned long stack_start,
+copy_thread(unsigned long clone_flags, unsigned long stack_start,
 	    unsigned long stk_sz, struct task_struct *p, struct pt_regs *regs)
 {
 	struct thread_info *thread = task_thread_info(p);
diff --git a/arch/arm/mach-at91/pm.c b/arch/arm/mach-at91/pm.c
index 7ac812dc055a..e26c4fe61fae 100644
--- a/arch/arm/mach-at91/pm.c
+++ b/arch/arm/mach-at91/pm.c
@@ -198,17 +198,17 @@ static int at91_pm_verify_clocks(void)
 	/* USB must not be using PLLB */
 	if (cpu_is_at91rm9200()) {
 		if ((scsr & (AT91RM9200_PMC_UHP | AT91RM9200_PMC_UDP)) != 0) {
-			pr_debug("AT91: PM - Suspend-to-RAM with USB still active\n");
+			pr_err("AT91: PM - Suspend-to-RAM with USB still active\n");
 			return 0;
 		}
 	} else if (cpu_is_at91sam9260() || cpu_is_at91sam9261() || cpu_is_at91sam9263() || cpu_is_at91sam9g20()) {
 		if ((scsr & (AT91SAM926x_PMC_UHP | AT91SAM926x_PMC_UDP)) != 0) {
-			pr_debug("AT91: PM - Suspend-to-RAM with USB still active\n");
+			pr_err("AT91: PM - Suspend-to-RAM with USB still active\n");
 			return 0;
 		}
 	} else if (cpu_is_at91cap9()) {
 		if ((scsr & AT91CAP9_PMC_UHP) != 0) {
-			pr_debug("AT91: PM - Suspend-to-RAM with USB still active\n");
+			pr_err("AT91: PM - Suspend-to-RAM with USB still active\n");
 			return 0;
 		}
 	}
@@ -223,7 +223,7 @@ static int at91_pm_verify_clocks(void)
 
 		css = at91_sys_read(AT91_PMC_PCKR(i)) & AT91_PMC_CSS;
 		if (css != AT91_PMC_CSS_SLOW) {
-			pr_debug("AT91: PM - Suspend-to-RAM with PCK%d src %d\n", i, css);
+			pr_err("AT91: PM - Suspend-to-RAM with PCK%d src %d\n", i, css);
 			return 0;
 		}
 	}
diff --git a/arch/arm/mach-gemini/include/mach/system.h b/arch/arm/mach-gemini/include/mach/system.h
index bbbd72767a02..4d9c1f872472 100644
--- a/arch/arm/mach-gemini/include/mach/system.h
+++ b/arch/arm/mach-gemini/include/mach/system.h
@@ -28,7 +28,7 @@ static inline void arch_idle(void)
 	cpu_do_idle();
 }
 
-static inline void arch_reset(char mode)
+static inline void arch_reset(char mode, const char *cmd)
 {
 	__raw_writel(RESET_GLOBAL | RESET_CPU1,
 		     IO_ADDRESS(GEMINI_GLOBAL_BASE) + GLOBAL_RESET);
diff --git a/arch/arm/mach-mmp/include/mach/system.h b/arch/arm/mach-mmp/include/mach/system.h
index 001edfefec19..4f5b0e0ce6cf 100644
--- a/arch/arm/mach-mmp/include/mach/system.h
+++ b/arch/arm/mach-mmp/include/mach/system.h
@@ -14,7 +14,7 @@ static inline void arch_idle(void)
 	cpu_do_idle();
 }
 
-static inline void arch_reset(char mode)
+static inline void arch_reset(char mode, const char *cmd)
 {
 	cpu_reset(0);
 }
diff --git a/arch/arm/mach-mx3/pcm037.c b/arch/arm/mach-mx3/pcm037.c
index 5fce022114de..c3648eff5137 100644
--- a/arch/arm/mach-mx3/pcm037.c
+++ b/arch/arm/mach-mx3/pcm037.c
@@ -24,7 +24,7 @@
 #include <linux/mtd/plat-ram.h>
 #include <linux/memory.h>
 #include <linux/gpio.h>
-#include <linux/smc911x.h>
+#include <linux/smsc911x.h>
 #include <linux/interrupt.h>
 #include <linux/i2c.h>
 #include <linux/i2c/at24.h>
@@ -70,7 +70,7 @@ static struct imxuart_platform_data uart_pdata = {
 	.flags = IMXUART_HAVE_RTSCTS,
 };
 
-static struct resource smc911x_resources[] = {
+static struct resource smsc911x_resources[] = {
 	[0] = {
 		.start		= CS1_BASE_ADDR + 0x300,
 		.end		= CS1_BASE_ADDR + 0x300 + SZ_64K - 1,
@@ -79,22 +79,25 @@ static struct resource smc911x_resources[] = {
 	[1] = {
 		.start		= IOMUX_TO_IRQ(MX31_PIN_GPIO3_1),
 		.end		= IOMUX_TO_IRQ(MX31_PIN_GPIO3_1),
-		.flags		= IORESOURCE_IRQ,
+		.flags		= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWLEVEL,
 	},
 };
 
-static struct smc911x_platdata smc911x_info = {
-	.flags		= SMC911X_USE_32BIT,
-	.irq_flags	= IRQF_SHARED | IRQF_TRIGGER_LOW,
+static struct smsc911x_platform_config smsc911x_info = {
+	.flags		= SMSC911X_USE_32BIT | SMSC911X_FORCE_INTERNAL_PHY |
+			  SMSC911X_SAVE_MAC_ADDRESS,
+	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
+	.irq_type	= SMSC911X_IRQ_TYPE_OPEN_DRAIN,
+	.phy_interface	= PHY_INTERFACE_MODE_MII,
 };
 
 static struct platform_device pcm037_eth = {
-	.name		= "smc911x",
+	.name		= "smsc911x",
 	.id		= -1,
-	.num_resources	= ARRAY_SIZE(smc911x_resources),
-	.resource	= smc911x_resources,
+	.num_resources	= ARRAY_SIZE(smsc911x_resources),
+	.resource	= smsc911x_resources,
 	.dev		= {
-		.platform_data = &smc911x_info,
+		.platform_data = &smsc911x_info,
 	},
 };
 
diff --git a/arch/arm/mach-netx/include/mach/netx-regs.h b/arch/arm/mach-netx/include/mach/netx-regs.h
index 08c60ff227be..5a03e7ccb01a 100644
--- a/arch/arm/mach-netx/include/mach/netx-regs.h
+++ b/arch/arm/mach-netx/include/mach/netx-regs.h
@@ -80,7 +80,7 @@
 #define NETX_PA_XPEC(no) (NETX_IO_PHYS + NETX_OFS_XPEC(no))
 #define NETX_PA_VIC      (NETX_IO_PHYS + NETX_OFS_VIC)
 
-/* virual addresses */
+/* virtual addresses */
 #define NETX_VA_SYSTEM   (NETX_IO_VIRT + NETX_OFS_SYSTEM)
 #define NETX_VA_MEMCR    (NETX_IO_VIRT + NETX_OFS_MEMCR)
 #define NETX_VA_DPMAS    (NETX_IO_VIRT + NETX_OFS_DPMAS)
diff --git a/arch/arm/mach-omap1/Kconfig b/arch/arm/mach-omap1/Kconfig
index 3f325d3718a9..cd8de89c5fad 100644
--- a/arch/arm/mach-omap1/Kconfig
+++ b/arch/arm/mach-omap1/Kconfig
@@ -109,7 +109,7 @@ config MACH_OMAP_PALMZ71
 	help
 	 Support for the Palm Zire71 PDA. To boot the kernel,
 	 you'll need a PalmOS compatible bootloader; check out
-	 http://hackndev.com/palm/z71 for more informations.
+	 http://hackndev.com/palm/z71 for more information.
 	 Say Y here if you have such a PDA, say N otherwise.
 
 config MACH_OMAP_PALMTT
diff --git a/arch/arm/mach-omap2/Makefile b/arch/arm/mach-omap2/Makefile
index a2c3fcc27a22..c49d9bfa3abd 100644
--- a/arch/arm/mach-omap2/Makefile
+++ b/arch/arm/mach-omap2/Makefile
@@ -47,6 +47,8 @@ obj-$(CONFIG_MACH_OMAP_3430SDP)		+= board-3430sdp.o \
 
 obj-$(CONFIG_MACH_NOKIA_RX51)		+= board-rx51.o \
 					   board-rx51-peripherals.o \
+					   mmc-twl4030.o
+
 # Platform specific device init code
 ifeq ($(CONFIG_USB_MUSB_SOC),y)
 obj-y					+= usb-musb.o
diff --git a/arch/arm/mach-omap2/board-ldp.c b/arch/arm/mach-omap2/board-ldp.c
index e096f776f996..da57b0fcda14 100644
--- a/arch/arm/mach-omap2/board-ldp.c
+++ b/arch/arm/mach-omap2/board-ldp.c
@@ -23,6 +23,7 @@
 #include <linux/spi/ads7846.h>
 #include <linux/i2c/twl4030.h>
 #include <linux/io.h>
+#include <linux/smsc911x.h>
 
 #include <mach/hardware.h>
 #include <asm/mach-types.h>
@@ -41,12 +42,12 @@
 
 #include "mmc-twl4030.h"
 
-#define LDP_SMC911X_CS		1
-#define LDP_SMC911X_GPIO	152
+#define LDP_SMSC911X_CS		1
+#define LDP_SMSC911X_GPIO	152
 #define DEBUG_BASE		0x08000000
 #define LDP_ETHR_START		DEBUG_BASE
 
-static struct resource ldp_smc911x_resources[] = {
+static struct resource ldp_smsc911x_resources[] = {
 	[0] = {
 		.start	= LDP_ETHR_START,
 		.end	= LDP_ETHR_START + SZ_4K,
@@ -59,40 +60,50 @@ static struct resource ldp_smc911x_resources[] = {
 	},
 };
 
-static struct platform_device ldp_smc911x_device = {
-	.name		= "smc911x",
+static struct smsc911x_platform_config ldp_smsc911x_config = {
+	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
+	.irq_type	= SMSC911X_IRQ_TYPE_OPEN_DRAIN,
+	.flags		= SMSC911X_USE_32BIT,
+	.phy_interface	= PHY_INTERFACE_MODE_MII,
+};
+
+static struct platform_device ldp_smsc911x_device = {
+	.name		= "smsc911x",
 	.id		= -1,
-	.num_resources	= ARRAY_SIZE(ldp_smc911x_resources),
-	.resource	= ldp_smc911x_resources,
+	.num_resources	= ARRAY_SIZE(ldp_smsc911x_resources),
+	.resource	= ldp_smsc911x_resources,
+	.dev		= {
+		.platform_data = &ldp_smsc911x_config,
+	},
 };
 
 static struct platform_device *ldp_devices[] __initdata = {
-	&ldp_smc911x_device,
+	&ldp_smsc911x_device,
 };
 
-static inline void __init ldp_init_smc911x(void)
+static inline void __init ldp_init_smsc911x(void)
 {
 	int eth_cs;
 	unsigned long cs_mem_base;
 	int eth_gpio = 0;
 
-	eth_cs = LDP_SMC911X_CS;
+	eth_cs = LDP_SMSC911X_CS;
 
 	if (gpmc_cs_request(eth_cs, SZ_16M, &cs_mem_base) < 0) {
-		printk(KERN_ERR "Failed to request GPMC mem for smc911x\n");
+		printk(KERN_ERR "Failed to request GPMC mem for smsc911x\n");
 		return;
 	}
 
-	ldp_smc911x_resources[0].start = cs_mem_base + 0x0;
-	ldp_smc911x_resources[0].end   = cs_mem_base + 0xff;
+	ldp_smsc911x_resources[0].start = cs_mem_base + 0x0;
+	ldp_smsc911x_resources[0].end   = cs_mem_base + 0xff;
 	udelay(100);
 
-	eth_gpio = LDP_SMC911X_GPIO;
+	eth_gpio = LDP_SMSC911X_GPIO;
 
-	ldp_smc911x_resources[1].start = OMAP_GPIO_IRQ(eth_gpio);
+	ldp_smsc911x_resources[1].start = OMAP_GPIO_IRQ(eth_gpio);
 
-	if (gpio_request(eth_gpio, "smc911x irq") < 0) {
-		printk(KERN_ERR "Failed to request GPIO%d for smc911x IRQ\n",
+	if (gpio_request(eth_gpio, "smsc911x irq") < 0) {
+		printk(KERN_ERR "Failed to request GPIO%d for smsc911x IRQ\n",
 				eth_gpio);
 		return;
 	}
@@ -104,7 +115,7 @@ static void __init omap_ldp_init_irq(void)
 	omap2_init_common_hw(NULL);
 	omap_init_irq();
 	omap_gpio_init();
-	ldp_init_smc911x();
+	ldp_init_smsc911x();
 }
 
 static struct omap_uart_config ldp_uart_config __initdata = {
diff --git a/arch/arm/mach-omap2/board-overo.c b/arch/arm/mach-omap2/board-overo.c
index b3f6e9d81807..b1f23bea863f 100644
--- a/arch/arm/mach-omap2/board-overo.c
+++ b/arch/arm/mach-omap2/board-overo.c
@@ -57,6 +57,9 @@
 #define GPMC_CS0_BASE  0x60
 #define GPMC_CS_SIZE   0x30
 
+#define OVERO_SMSC911X_CS      5
+#define OVERO_SMSC911X_GPIO    176
+
 #if defined(CONFIG_TOUCHSCREEN_ADS7846) || \
 	defined(CONFIG_TOUCHSCREEN_ADS7846_MODULE)
 
@@ -116,6 +119,67 @@ static void __init overo_ads7846_init(void)
 static inline void __init overo_ads7846_init(void) { return; }
 #endif
 
+#if defined(CONFIG_SMSC911X) || defined(CONFIG_SMSC911X_MODULE)
+
+#include <linux/smsc911x.h>
+
+static struct resource overo_smsc911x_resources[] = {
+	{
+		.name	= "smsc911x-memory",
+		.flags	= IORESOURCE_MEM,
+	},
+	{
+		.flags	= IORESOURCE_IRQ | IORESOURCE_IRQ_LOWLEVEL,
+	},
+};
+
+static struct smsc911x_platform_config overo_smsc911x_config = {
+	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_LOW,
+	.irq_type	= SMSC911X_IRQ_TYPE_OPEN_DRAIN,
+	.flags		= SMSC911X_USE_32BIT ,
+	.phy_interface	= PHY_INTERFACE_MODE_MII,
+};
+
+static struct platform_device overo_smsc911x_device = {
+	.name		= "smsc911x",
+	.id		= -1,
+	.num_resources	= ARRAY_SIZE(overo_smsc911x_resources),
+	.resource	= &overo_smsc911x_resources,
+	.dev		= {
+		.platform_data = &overo_smsc911x_config,
+	},
+};
+
+static inline void __init overo_init_smsc911x(void)
+{
+	unsigned long cs_mem_base;
+
+	if (gpmc_cs_request(OVERO_SMSC911X_CS, SZ_16M, &cs_mem_base) < 0) {
+		printk(KERN_ERR "Failed request for GPMC mem for smsc911x\n");
+		return;
+	}
+
+	overo_smsc911x_resources[0].start = cs_mem_base + 0x0;
+	overo_smsc911x_resources[0].end   = cs_mem_base + 0xff;
+
+	if ((gpio_request(OVERO_SMSC911X_GPIO, "SMSC911X IRQ") == 0) &&
+	    (gpio_direction_input(OVERO_SMSC911X_GPIO) == 0)) {
+		gpio_export(OVERO_SMSC911X_GPIO, 0);
+	} else {
+		printk(KERN_ERR "could not obtain gpio for SMSC911X IRQ\n");
+		return;
+	}
+
+	overo_smsc911x_resources[1].start = OMAP_GPIO_IRQ(OVERO_SMSC911X_GPIO);
+	overo_smsc911x_resources[1].end	  = 0;
+
+	platform_device_register(&overo_smsc911x_device);
+}
+
+#else
+static inline void __init overo_init_smsc911x(void) { return; }
+#endif
+
 static struct mtd_partition overo_nand_partitions[] = {
 	{
 		.name           = "xloader",
@@ -290,6 +354,7 @@ static void __init overo_init(void)
 	overo_flash_init();
 	usb_musb_init();
 	overo_ads7846_init();
+	overo_init_smsc911x();
 
 	if ((gpio_request(OVERO_GPIO_W2W_NRESET,
 			  "OVERO_GPIO_W2W_NRESET") == 0) &&
diff --git a/arch/arm/mach-realview/core.c b/arch/arm/mach-realview/core.c
index d6766685cfc7..9ab947c14f26 100644
--- a/arch/arm/mach-realview/core.c
+++ b/arch/arm/mach-realview/core.c
@@ -28,7 +28,7 @@
 #include <linux/clocksource.h>
 #include <linux/clockchips.h>
 #include <linux/io.h>
-#include <linux/smc911x.h>
+#include <linux/smsc911x.h>
 #include <linux/ata_platform.h>
 
 #include <asm/clkdev.h>
@@ -128,14 +128,15 @@ int realview_flash_register(struct resource *res, u32 num)
 	return platform_device_register(&realview_flash_device);
 }
 
-static struct smc911x_platdata realview_smc911x_platdata = {
-	.flags		= SMC911X_USE_32BIT,
-	.irq_flags	= IRQF_SHARED,
-	.irq_polarity	= 1,
+static struct smsc911x_platform_config smsc911x_config = {
+	.flags		= SMSC911X_USE_32BIT,
+	.irq_polarity	= SMSC911X_IRQ_POLARITY_ACTIVE_HIGH,
+	.irq_type	= SMSC911X_IRQ_TYPE_PUSH_PULL,
+	.phy_interface	= PHY_INTERFACE_MODE_MII,
 };
 
 static struct platform_device realview_eth_device = {
-	.name		= "smc911x",
+	.name		= "smsc911x",
 	.id		= 0,
 	.num_resources	= 2,
 };
@@ -145,8 +146,8 @@ int realview_eth_register(const char *name, struct resource *res)
 	if (name)
 		realview_eth_device.name = name;
 	realview_eth_device.resource = res;
-	if (strcmp(realview_eth_device.name, "smc911x") == 0)
-		realview_eth_device.dev.platform_data = &realview_smc911x_platdata;
+	if (strcmp(realview_eth_device.name, "smsc911x") == 0)
+		realview_eth_device.dev.platform_data = &smsc911x_config;
 
 	return platform_device_register(&realview_eth_device);
 }
diff --git a/arch/arm/mach-realview/localtimer.c b/arch/arm/mach-realview/localtimer.c
index 67d6d9cc68b2..d0d39adf6407 100644
--- a/arch/arm/mach-realview/localtimer.c
+++ b/arch/arm/mach-realview/localtimer.c
@@ -191,6 +191,7 @@ void __cpuinit local_timer_setup(void)
 	clk->name		= "dummy_timer";
 	clk->features		= CLOCK_EVT_FEAT_DUMMY;
 	clk->rating		= 200;
+	clk->mult               = 1;
 	clk->set_mode		= dummy_timer_set_mode;
 	clk->broadcast		= smp_timer_broadcast;
 	clk->cpumask		= cpumask_of(cpu);
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index 94077fbd96b7..6f7e70907e44 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -29,10 +29,10 @@ ENTRY(v6_early_abort)
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
 /*
- * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR.
+ * Faulty SWP instruction on 1136 doesn't set bit 11 in DFSR (erratum 326103).
  * The test below covers all the write situations, including Java bytecodes
  */
-	bic	r1, r1, #1 << 11 | 1 << 10	@ clear bits 11 and 10 of FSR
+	bic	r1, r1, #1 << 11		@ clear bit 11 of FSR
 	tst	r3, #PSR_J_BIT			@ Java?
 	movne	pc, lr
 	do_thumb_abort
diff --git a/arch/arm/mm/cache-feroceon-l2.c b/arch/arm/mm/cache-feroceon-l2.c
index d6dd83826f8a..6e77c042d8e9 100644
--- a/arch/arm/mm/cache-feroceon-l2.c
+++ b/arch/arm/mm/cache-feroceon-l2.c
@@ -115,6 +115,10 @@ static inline void l2_inv_pa_range(unsigned long start, unsigned long end)
 	raw_local_irq_restore(flags);
 }
 
+static inline void l2_inv_all(void)
+{
+	__asm__("mcr p15, 1, %0, c15, c11, 0" : : "r" (0));
+}
 
 /*
  * Linux primitives.
@@ -254,9 +258,7 @@ static void __init enable_dcache(void)
 
 static void __init __invalidate_icache(void)
 {
-	int dummy;
-
-	__asm__ __volatile__("mcr p15, 0, %0, c7, c5, 0" : "=r" (dummy));
+	__asm__("mcr p15, 0, %0, c7, c5, 0" : : "r" (0));
 }
 
 static int __init invalidate_and_disable_icache(void)
@@ -321,6 +323,7 @@ static void __init enable_l2(void)
 
 		d = flush_and_disable_dcache();
 		i = invalidate_and_disable_icache();
+		l2_inv_all();
 		write_extra_features(u | 0x00400000);
 		if (i)
 			enable_icache();
diff --git a/arch/arm/vfp/entry.S b/arch/arm/vfp/entry.S
index ba592a9e6fb3..a2bed62aec21 100644
--- a/arch/arm/vfp/entry.S
+++ b/arch/arm/vfp/entry.S
@@ -15,13 +15,16 @@
  *  r10 = thread_info structure
  *  lr  = failure return
  */
-#include <linux/linkage.h>
-#include <linux/init.h>
-#include <asm/asm-offsets.h>
-#include <asm/assembler.h>
+#include <asm/thread_info.h>
 #include <asm/vfpmacros.h>
+#include "../kernel/entry-header.S"
 
 ENTRY(do_vfp)
+#ifdef CONFIG_PREEMPT
+	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
+	add	r11, r4, #1		@ increment it
+	str	r11, [r10, #TI_PREEMPT]
+#endif
 	enable_irq
  	ldr	r4, .LCvfp
 	ldr	r11, [r10, #TI_CPU]	@ CPU number
@@ -30,6 +33,12 @@ ENTRY(do_vfp)
 ENDPROC(do_vfp)
 
 ENTRY(vfp_null_entry)
+#ifdef CONFIG_PREEMPT
+	get_thread_info	r10
+	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
+	sub	r11, r4, #1		@ decrement it
+	str	r11, [r10, #TI_PREEMPT]
+#endif
 	mov	pc, lr
 ENDPROC(vfp_null_entry)
 
@@ -41,6 +50,12 @@ ENDPROC(vfp_null_entry)
 
 	__INIT
 ENTRY(vfp_testing_entry)
+#ifdef CONFIG_PREEMPT
+	get_thread_info	r10
+	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
+	sub	r11, r4, #1		@ decrement it
+	str	r11, [r10, #TI_PREEMPT]
+#endif
 	ldr	r0, VFP_arch_address
 	str	r5, [r0]		@ known non-zero value
 	mov	pc, r9			@ we have handled the fault
diff --git a/arch/arm/vfp/vfphw.S b/arch/arm/vfp/vfphw.S
index a5a4e57763c3..83c4e384b16d 100644
--- a/arch/arm/vfp/vfphw.S
+++ b/arch/arm/vfp/vfphw.S
@@ -137,6 +137,12 @@ check_for_exception:
 	VFPFMXR	FPEXC, r1		@ restore FPEXC last
 	sub	r2, r2, #4
 	str	r2, [sp, #S_PC]		@ retry the instruction
+#ifdef CONFIG_PREEMPT
+	get_thread_info	r10
+	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
+	sub	r11, r4, #1		@ decrement it
+	str	r11, [r10, #TI_PREEMPT]
+#endif
 	mov	pc, r9			@ we think we have handled things
 
 
@@ -155,6 +161,12 @@ look_for_VFP_exceptions:
 	@ not recognised by VFP
 
 	DBGSTR	"not VFP"
+#ifdef CONFIG_PREEMPT
+	get_thread_info	r10
+	ldr	r4, [r10, #TI_PREEMPT]	@ get preempt count
+	sub	r11, r4, #1		@ decrement it
+	str	r11, [r10, #TI_PREEMPT]
+#endif
 	mov	pc, lr
 
 process_exception:
diff --git a/arch/arm/vfp/vfpmodule.c b/arch/arm/vfp/vfpmodule.c
index 75457b30d813..01599c4ef726 100644
--- a/arch/arm/vfp/vfpmodule.c
+++ b/arch/arm/vfp/vfpmodule.c
@@ -266,7 +266,7 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 		 * on VFP subarch 1.
 		 */
 		 vfp_raise_exceptions(VFP_EXCEPTION_ERROR, trigger, fpscr, regs);
-		 return;
+		goto exit;
 	}
 
 	/*
@@ -297,7 +297,7 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 	 * the FPEXC.FP2V bit is valid only if FPEXC.EX is 1.
 	 */
 	if (fpexc ^ (FPEXC_EX | FPEXC_FP2V))
-		return;
+		goto exit;
 
 	/*
 	 * The barrier() here prevents fpinst2 being read
@@ -310,6 +310,8 @@ void VFP_bounce(u32 trigger, u32 fpexc, struct pt_regs *regs)
 	exceptions = vfp_emulate_instruction(trigger, orig_fpscr, regs);
 	if (exceptions)
 		vfp_raise_exceptions(exceptions, trigger, orig_fpscr, regs);
+ exit:
+	preempt_enable();
 }
 
 static void vfp_enable(void *unused)
diff --git a/arch/avr32/Kconfig b/arch/avr32/Kconfig
index 05fe3053dcae..414a8ad97f52 100644
--- a/arch/avr32/Kconfig
+++ b/arch/avr32/Kconfig
@@ -127,13 +127,13 @@ config BOARD_HAMMERHEAD
 	select CPU_AT32AP7000
 	select USB_ARCH_HAS_HCD
 	help
-	  The Hammerhead platform is built around a AVR32 32-bit microcontroller from Atmel.
+	  The Hammerhead platform is built around an AVR32 32-bit microcontroller from Atmel.
 	  It offers versatile peripherals, such as ethernet, usb device, usb host etc.
 
-	  The board also incooperates a power supply and is a Power over Ethernet (PoE) Powered
+	  The board also incorporates a power supply and is a Power over Ethernet (PoE) Powered
 	  Device (PD).
 
-	  Additonally, a Cyclone III FPGA from Altera is integrated on the board. The FPGA is
+	  Additionally, a Cyclone III FPGA from Altera is integrated on the board. The FPGA is
 	  mapped into the 32-bit AVR memory bus. The FPGA offers two DDR2 SDRAM interfaces, which
 	  will cover even the most exceptional need of memory bandwidth. Together with the onboard
 	  video decoder the board is ready for video processing.
diff --git a/arch/avr32/kernel/process.c b/arch/avr32/kernel/process.c
index 43ae555ecb33..1bbe1da54869 100644
--- a/arch/avr32/kernel/process.c
+++ b/arch/avr32/kernel/process.c
@@ -332,7 +332,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 
 asmlinkage void ret_from_fork(void);
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/blackfin/Kconfig b/arch/blackfin/Kconfig
index 0c1f86e3e44a..3640cdc38aac 100644
--- a/arch/blackfin/Kconfig
+++ b/arch/blackfin/Kconfig
@@ -777,7 +777,7 @@ config CACHELINE_ALIGNED_L1
 	default n if BF54x
 	depends on !BF531
 	help
-	  If enabled, cacheline_anligned data is linked
+	  If enabled, cacheline_aligned data is linked
 	  into L1 data memory. (less latency)
 
 config SYSCALL_TAB_L1
@@ -957,7 +957,7 @@ config MPU
 	  memory they do not own.  This comes at a performance penalty
 	  and is recommended only for debugging.
 
-comment "Asynchonous Memory Configuration"
+comment "Asynchronous Memory Configuration"
 
 menu "EBIU_AMGCTL Global Control"
 config C_AMCKEN
@@ -989,7 +989,7 @@ config C_B3PEN
 	default n
 
 choice
-	prompt"Enable Asynchonous Memory Banks"
+	prompt "Enable Asynchronous Memory Banks"
 	default C_AMBEN_ALL
 
 config C_AMBEN
diff --git a/arch/blackfin/kernel/process.c b/arch/blackfin/kernel/process.c
index 33e2e8993f7f..f49427293ca1 100644
--- a/arch/blackfin/kernel/process.c
+++ b/arch/blackfin/kernel/process.c
@@ -193,7 +193,7 @@ asmlinkage int bfin_clone(struct pt_regs *regs)
 }
 
 int
-copy_thread(int nr, unsigned long clone_flags,
+copy_thread(unsigned long clone_flags,
 	    unsigned long usp, unsigned long topstk,
 	    struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/cris/Kconfig b/arch/cris/Kconfig
index 3462245fe9fb..7adac388a771 100644
--- a/arch/cris/Kconfig
+++ b/arch/cris/Kconfig
@@ -438,7 +438,7 @@ config ETRAX_SERIAL_PORT0_DMA1_IN
 	help
 	  Enables the DMA1 input channel for ser0 (ttyS0).
 	  If you do not enable DMA, an interrupt for each character will be
-	  used when receiveing data.
+	  used when receiving data.
 	  Normally you want to use DMA, unless you use the DMA channel for
 	  something else.
 
@@ -565,7 +565,7 @@ config ETRAX_SERIAL_PORT2_DMA7_IN
 	help
 	  Enables the DMA7 input channel for ser2 (ttyS2).
 	  If you do not enable DMA, an interrupt for each character will be
-	  used when receiveing data.
+	  used when receiving data.
 	  Normally you want to use DMA, unless you use the DMA channel for
 	  something else.
 
@@ -604,7 +604,7 @@ config ETRAX_SERIAL_PORT3_DMA3_IN
 	help
 	  Enables the DMA3 input channel for ser3 (ttyS3).
 	  If you do not enable DMA, an interrupt for each character will be
-	  used when receiveing data.
+	  used when receiving data.
 	  Normally you want to use DMA, unless you use the DMA channel for
 	  something else.
 
diff --git a/arch/cris/arch-v10/kernel/process.c b/arch/cris/arch-v10/kernel/process.c
index bd9b3ff63f6c..c4c69cf721e5 100644
--- a/arch/cris/arch-v10/kernel/process.c
+++ b/arch/cris/arch-v10/kernel/process.c
@@ -115,7 +115,7 @@ int kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
  */
 asmlinkage void ret_from_fork(void);
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/cris/arch-v32/Kconfig b/arch/cris/arch-v32/Kconfig
index 005ed2b3f7f4..21bbd93be34f 100644
--- a/arch/cris/arch-v32/Kconfig
+++ b/arch/cris/arch-v32/Kconfig
@@ -28,7 +28,7 @@ config	ETRAX_NBR_LED_GRP_ONE
 	help
 	  Select this if you want one Ethernet LED group. This LED group
 	  can be used for one or more Ethernet interfaces. However, it is
-	  recomended that each Ethernet interface use a dedicated LED group.
+	  recommended that each Ethernet interface use a dedicated LED group.
 
 config	ETRAX_NBR_LED_GRP_TWO
 	bool "Use two LED groups"
diff --git a/arch/cris/arch-v32/drivers/Kconfig b/arch/cris/arch-v32/drivers/Kconfig
index 7a64fcef9d07..b9e328e688be 100644
--- a/arch/cris/arch-v32/drivers/Kconfig
+++ b/arch/cris/arch-v32/drivers/Kconfig
@@ -342,7 +342,7 @@ config ETRAX_SERIAL_PORT4_DMA9_IN
 	help
 	  Enables the DMA9 input channel for ser4 (ttyS4).
 	  If you do not enable DMA, an interrupt for each character will be
-	  used when receiveing data.
+	  used when receiving data.
 	  Normally you want to use DMA, unless you use the DMA channel for
 	  something else.
 
diff --git a/arch/cris/arch-v32/kernel/process.c b/arch/cris/arch-v32/kernel/process.c
index ced5b725d9bd..120e7f796fea 100644
--- a/arch/cris/arch-v32/kernel/process.c
+++ b/arch/cris/arch-v32/kernel/process.c
@@ -131,7 +131,7 @@ kernel_thread(int (*fn)(void *), void * arg, unsigned long flags)
 extern asmlinkage void ret_from_fork(void);
 
 int
-copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+copy_thread(unsigned long clone_flags, unsigned long usp,
 	unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/cris/arch-v32/mach-fs/Kconfig b/arch/cris/arch-v32/mach-fs/Kconfig
index f6d74475f1c6..774de82abef6 100644
--- a/arch/cris/arch-v32/mach-fs/Kconfig
+++ b/arch/cris/arch-v32/mach-fs/Kconfig
@@ -59,7 +59,7 @@ config ETRAX_SDRAM_GRP1_CONFIG
 	depends on ETRAX_ARCH_V32
 	default "0"
 	help
-	  SDRAM configuration for group 1. The defult value is 0
+	  SDRAM configuration for group 1. The default value is 0
 	  because group 1 is not used in the default configuration,
 	  described in the help for SDRAM_GRP0_CONFIG.
 
diff --git a/arch/cris/include/arch-v32/arch/spinlock.h b/arch/cris/include/arch-v32/arch/spinlock.h
index 0d5709b983a1..129756b96661 100644
--- a/arch/cris/include/arch-v32/arch/spinlock.h
+++ b/arch/cris/include/arch-v32/arch/spinlock.h
@@ -121,6 +121,8 @@ static  inline int __raw_write_trylock(raw_rwlock_t *rw)
 	return 1;
 }
 
+#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock)
+#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock)
 
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
diff --git a/arch/cris/kernel/process.c b/arch/cris/kernel/process.c
index 60816e876455..4df0b320d524 100644
--- a/arch/cris/kernel/process.c
+++ b/arch/cris/kernel/process.c
@@ -19,7 +19,6 @@
 #include <asm/system.h>
 #include <linux/module.h>
 #include <linux/spinlock.h>
-#include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include <linux/sched.h>
 #include <linux/fs.h>
diff --git a/arch/frv/kernel/process.c b/arch/frv/kernel/process.c
index 9583a338e9d6..0de50df74970 100644
--- a/arch/frv/kernel/process.c
+++ b/arch/frv/kernel/process.c
@@ -204,7 +204,7 @@ void prepare_to_copy(struct task_struct *tsk)
 /*
  * set up the kernel stack and exception frames for a new process
  */
-int copy_thread(int nr, unsigned long clone_flags,
+int copy_thread(unsigned long clone_flags,
 		unsigned long usp, unsigned long topstk,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/h8300/kernel/process.c b/arch/h8300/kernel/process.c
index a8ef654a5a0b..e2f33d0f9969 100644
--- a/arch/h8300/kernel/process.c
+++ b/arch/h8300/kernel/process.c
@@ -191,7 +191,7 @@ asmlinkage int h8300_clone(struct pt_regs *regs)
 
 }
 
-int copy_thread(int nr, unsigned long clone_flags,
+int copy_thread(unsigned long clone_flags,
                 unsigned long usp, unsigned long topstk,
 		 struct task_struct * p, struct pt_regs * regs)
 {
diff --git a/arch/h8300/kernel/timer/tpu.c b/arch/h8300/kernel/timer/tpu.c
index ad383caae196..e7c6e614a758 100644
--- a/arch/h8300/kernel/timer/tpu.c
+++ b/arch/h8300/kernel/timer/tpu.c
@@ -67,7 +67,7 @@ static struct irqaction tpu_irq = {
 	.flags		= IRQF_DISABLED | IRQF_TIMER,
 };
 
-const static int __initdata divide_rate[] = {
+static const int __initdata divide_rate[] = {
 #if CONFIG_H8300_TPU_CH == 0
 	1,4,16,64,0,0,0,0,
 #elif (CONFIG_H8300_TPU_CH == 1) || (CONFIG_H8300_TPU_CH == 5)
diff --git a/arch/ia64/configs/generic_defconfig b/arch/ia64/configs/generic_defconfig
index a109db30ce55..75645495c2dd 100644
--- a/arch/ia64/configs/generic_defconfig
+++ b/arch/ia64/configs/generic_defconfig
@@ -193,7 +193,6 @@ CONFIG_BOUNCE=y
 CONFIG_NR_QUICK=1
 CONFIG_VIRT_TO_BUS=y
 CONFIG_UNEVICTABLE_LRU=y
-CONFIG_MMU_NOTIFIER=y
 CONFIG_ARCH_SELECT_MEMORY_MODEL=y
 CONFIG_ARCH_DISCONTIGMEM_ENABLE=y
 CONFIG_ARCH_FLATMEM_ENABLE=y
@@ -416,8 +415,6 @@ CONFIG_SGI_IOC4=y
 # CONFIG_ENCLOSURE_SERVICES is not set
 CONFIG_SGI_XP=m
 # CONFIG_HP_ILO is not set
-CONFIG_SGI_GRU=m
-# CONFIG_SGI_GRU_DEBUG is not set
 # CONFIG_C2PORT is not set
 CONFIG_HAVE_IDE=y
 CONFIG_IDE=y
diff --git a/arch/ia64/include/asm/intrinsics.h b/arch/ia64/include/asm/intrinsics.h
index c47830e26cb7..111ed5222892 100644
--- a/arch/ia64/include/asm/intrinsics.h
+++ b/arch/ia64/include/asm/intrinsics.h
@@ -202,7 +202,11 @@ extern long ia64_cmpxchg_called_with_bad_pointer (void);
 
 #ifndef __ASSEMBLY__
 #if defined(CONFIG_PARAVIRT) && defined(__KERNEL__)
-#define IA64_INTRINSIC_API(name)	pv_cpu_ops.name
+#ifdef ASM_SUPPORTED
+# define IA64_INTRINSIC_API(name)	paravirt_ ## name
+#else
+# define IA64_INTRINSIC_API(name)	pv_cpu_ops.name
+#endif
 #define IA64_INTRINSIC_MACRO(name)	paravirt_ ## name
 #else
 #define IA64_INTRINSIC_API(name)	ia64_native_ ## name
diff --git a/arch/ia64/include/asm/mmu_context.h b/arch/ia64/include/asm/mmu_context.h
index 040bc87db930..7f2a456603cb 100644
--- a/arch/ia64/include/asm/mmu_context.h
+++ b/arch/ia64/include/asm/mmu_context.h
@@ -87,7 +87,7 @@ get_mmu_context (struct mm_struct *mm)
 	/* re-check, now that we've got the lock: */
 	context = mm->context;
 	if (context == 0) {
-		cpus_clear(mm->cpu_vm_mask);
+		cpumask_clear(mm_cpumask(mm));
 		if (ia64_ctx.next >= ia64_ctx.limit) {
 			ia64_ctx.next = find_next_zero_bit(ia64_ctx.bitmap,
 					ia64_ctx.max_ctx, ia64_ctx.next);
@@ -166,8 +166,8 @@ activate_context (struct mm_struct *mm)
 
 	do {
 		context = get_mmu_context(mm);
-		if (!cpu_isset(smp_processor_id(), mm->cpu_vm_mask))
-			cpu_set(smp_processor_id(), mm->cpu_vm_mask);
+		if (!cpumask_test_cpu(smp_processor_id(), mm_cpumask(mm)))
+			cpumask_set_cpu(smp_processor_id(), mm_cpumask(mm));
 		reload_context(context);
 		/*
 		 * in the unlikely event of a TLB-flush by another thread,
diff --git a/arch/ia64/include/asm/module.h b/arch/ia64/include/asm/module.h
index d2da61e4c49b..908eaef42a08 100644
--- a/arch/ia64/include/asm/module.h
+++ b/arch/ia64/include/asm/module.h
@@ -16,6 +16,12 @@ struct mod_arch_specific {
 	struct elf64_shdr *got;		/* global offset table */
 	struct elf64_shdr *opd;		/* official procedure descriptors */
 	struct elf64_shdr *unwind;	/* unwind-table section */
+#ifdef CONFIG_PARAVIRT
+	struct elf64_shdr *paravirt_bundles;
+					/* paravirt_alt_bundle_patch table */
+	struct elf64_shdr *paravirt_insts;
+					/* paravirt_alt_inst_patch table */
+#endif
 	unsigned long gp;		/* global-pointer for module */
 
 	void *core_unw_table;		/* core unwind-table cookie returned by unwinder */
diff --git a/arch/ia64/include/asm/native/inst.h b/arch/ia64/include/asm/native/inst.h
index 0a1026cca4fa..d2d46efb3e6e 100644
--- a/arch/ia64/include/asm/native/inst.h
+++ b/arch/ia64/include/asm/native/inst.h
@@ -30,6 +30,9 @@
 #define __paravirt_work_processed_syscall_target \
 						ia64_work_processed_syscall
 
+#define paravirt_fsyscall_table			ia64_native_fsyscall_table
+#define paravirt_fsys_bubble_down		ia64_native_fsys_bubble_down
+
 #ifdef CONFIG_PARAVIRT_GUEST_ASM_CLOBBER_CHECK
 # define PARAVIRT_POISON	0xdeadbeefbaadf00d
 # define CLOBBER(clob)				\
@@ -74,6 +77,11 @@
 (pred)	mov reg = psr			\
 	CLOBBER(clob)
 
+#define MOV_FROM_ITC(pred, pred_clob, reg, clob)	\
+(pred)	mov reg = ar.itc				\
+	CLOBBER(clob)					\
+	CLOBBER_PRED(pred_clob)
+
 #define MOV_TO_IFA(reg, clob)	\
 	mov cr.ifa = reg	\
 	CLOBBER(clob)
@@ -158,6 +166,11 @@
 #define RSM_PSR_DT		\
 	rsm psr.dt
 
+#define RSM_PSR_BE_I(clob0, clob1)	\
+	rsm psr.be | psr.i		\
+	CLOBBER(clob0)			\
+	CLOBBER(clob1)
+
 #define SSM_PSR_DT_AND_SRLZ_I	\
 	ssm psr.dt		\
 	;;			\
diff --git a/arch/ia64/include/asm/native/patchlist.h b/arch/ia64/include/asm/native/patchlist.h
new file mode 100644
index 000000000000..be16ca9311bf
--- /dev/null
+++ b/arch/ia64/include/asm/native/patchlist.h
@@ -0,0 +1,38 @@
+/******************************************************************************
+ * arch/ia64/include/asm/native/inst.h
+ *
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#define __paravirt_start_gate_fsyscall_patchlist		\
+	__ia64_native_start_gate_fsyscall_patchlist
+#define __paravirt_end_gate_fsyscall_patchlist			\
+	__ia64_native_end_gate_fsyscall_patchlist
+#define __paravirt_start_gate_brl_fsys_bubble_down_patchlist	\
+	__ia64_native_start_gate_brl_fsys_bubble_down_patchlist
+#define __paravirt_end_gate_brl_fsys_bubble_down_patchlist	\
+	__ia64_native_end_gate_brl_fsys_bubble_down_patchlist
+#define __paravirt_start_gate_vtop_patchlist			\
+	__ia64_native_start_gate_vtop_patchlist
+#define __paravirt_end_gate_vtop_patchlist			\
+	__ia64_native_end_gate_vtop_patchlist
+#define __paravirt_start_gate_mckinley_e9_patchlist		\
+	__ia64_native_start_gate_mckinley_e9_patchlist
+#define __paravirt_end_gate_mckinley_e9_patchlist		\
+	__ia64_native_end_gate_mckinley_e9_patchlist
diff --git a/arch/ia64/include/asm/native/pvchk_inst.h b/arch/ia64/include/asm/native/pvchk_inst.h
index b8e6eb1090d7..8d72962ec838 100644
--- a/arch/ia64/include/asm/native/pvchk_inst.h
+++ b/arch/ia64/include/asm/native/pvchk_inst.h
@@ -180,6 +180,11 @@
 	IS_PRED_IN(pred)			\
 	IS_RREG_OUT(reg)			\
 	IS_RREG_CLOB(clob)
+#define MOV_FROM_ITC(pred, pred_clob, reg, clob)	\
+	IS_PRED_IN(pred)				\
+	IS_PRED_CLOB(pred_clob)				\
+	IS_RREG_OUT(reg)				\
+	IS_RREG_CLOB(clob)
 #define MOV_TO_IFA(reg, clob)			\
 	IS_RREG_IN(reg)				\
 	IS_RREG_CLOB(clob)
@@ -246,6 +251,9 @@
 	IS_RREG_CLOB(clob2)
 #define RSM_PSR_DT				\
 	nop 0
+#define RSM_PSR_BE_I(clob0, clob1)		\
+	IS_RREG_CLOB(clob0)			\
+	IS_RREG_CLOB(clob1)
 #define SSM_PSR_DT_AND_SRLZ_I			\
 	nop 0
 #define BSW_0(clob0, clob1, clob2)		\
diff --git a/arch/ia64/include/asm/paravirt.h b/arch/ia64/include/asm/paravirt.h
index 2bf3636473fe..2eb0a981a09a 100644
--- a/arch/ia64/include/asm/paravirt.h
+++ b/arch/ia64/include/asm/paravirt.h
@@ -22,6 +22,56 @@
 #ifndef __ASM_PARAVIRT_H
 #define __ASM_PARAVIRT_H
 
+#ifndef __ASSEMBLY__
+/******************************************************************************
+ * fsys related addresses
+ */
+struct pv_fsys_data {
+	unsigned long *fsyscall_table;
+	void *fsys_bubble_down;
+};
+
+extern struct pv_fsys_data pv_fsys_data;
+
+unsigned long *paravirt_get_fsyscall_table(void);
+char *paravirt_get_fsys_bubble_down(void);
+
+/******************************************************************************
+ * patchlist addresses for gate page
+ */
+enum pv_gate_patchlist {
+	PV_GATE_START_FSYSCALL,
+	PV_GATE_END_FSYSCALL,
+
+	PV_GATE_START_BRL_FSYS_BUBBLE_DOWN,
+	PV_GATE_END_BRL_FSYS_BUBBLE_DOWN,
+
+	PV_GATE_START_VTOP,
+	PV_GATE_END_VTOP,
+
+	PV_GATE_START_MCKINLEY_E9,
+	PV_GATE_END_MCKINLEY_E9,
+};
+
+struct pv_patchdata {
+	unsigned long start_fsyscall_patchlist;
+	unsigned long end_fsyscall_patchlist;
+	unsigned long start_brl_fsys_bubble_down_patchlist;
+	unsigned long end_brl_fsys_bubble_down_patchlist;
+	unsigned long start_vtop_patchlist;
+	unsigned long end_vtop_patchlist;
+	unsigned long start_mckinley_e9_patchlist;
+	unsigned long end_mckinley_e9_patchlist;
+
+	void *gate_section;
+};
+
+extern struct pv_patchdata pv_patchdata;
+
+unsigned long paravirt_get_gate_patchlist(enum pv_gate_patchlist type);
+void *paravirt_get_gate_section(void);
+#endif
+
 #ifdef CONFIG_PARAVIRT_GUEST
 
 #define PARAVIRT_HYPERVISOR_TYPE_DEFAULT	0
@@ -68,6 +118,14 @@ struct pv_init_ops {
 	int (*arch_setup_nomca)(void);
 
 	void (*post_smp_prepare_boot_cpu)(void);
+
+#ifdef ASM_SUPPORTED
+	unsigned long (*patch_bundle)(void *sbundle, void *ebundle,
+				      unsigned long type);
+	unsigned long (*patch_inst)(unsigned long stag, unsigned long etag,
+				    unsigned long type);
+#endif
+	void (*patch_branch)(unsigned long tag, unsigned long type);
 };
 
 extern struct pv_init_ops pv_init_ops;
@@ -210,6 +268,8 @@ struct pv_time_ops {
 	int (*do_steal_accounting)(unsigned long *new_itm);
 
 	void (*clocksource_resume)(void);
+
+	unsigned long long (*sched_clock)(void);
 };
 
 extern struct pv_time_ops pv_time_ops;
@@ -227,6 +287,11 @@ paravirt_do_steal_accounting(unsigned long *new_itm)
 	return pv_time_ops.do_steal_accounting(new_itm);
 }
 
+static inline unsigned long long paravirt_sched_clock(void)
+{
+	return pv_time_ops.sched_clock();
+}
+
 #endif /* !__ASSEMBLY__ */
 
 #else
diff --git a/arch/ia64/include/asm/paravirt_patch.h b/arch/ia64/include/asm/paravirt_patch.h
new file mode 100644
index 000000000000..128ff5db6e67
--- /dev/null
+++ b/arch/ia64/include/asm/paravirt_patch.h
@@ -0,0 +1,143 @@
+/******************************************************************************
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#ifndef __ASM_PARAVIRT_PATCH_H
+#define __ASM_PARAVIRT_PATCH_H
+
+#ifdef __ASSEMBLY__
+
+	.section .paravirt_branches, "a"
+	.previous
+#define PARAVIRT_PATCH_SITE_BR(type)		\
+	{					\
+	[1:] ;					\
+	br.cond.sptk.many 2f ;			\
+	nop.b 0 ;				\
+	nop.b 0;; ;				\
+	} ;					\
+	2:					\
+	.xdata8 ".paravirt_branches", 1b, type
+
+#else
+
+#include <linux/stringify.h>
+#include <asm/intrinsics.h>
+
+/* for binary patch */
+struct paravirt_patch_site_bundle {
+	void		*sbundle;
+	void		*ebundle;
+	unsigned long	type;
+};
+
+/* label means the beginning of new bundle */
+#define paravirt_alt_bundle(instr, privop)				\
+	"\t998:\n"							\
+	"\t" instr "\n"							\
+	"\t999:\n"							\
+	"\t.pushsection .paravirt_bundles, \"a\"\n"			\
+	"\t.popsection\n"						\
+	"\t.xdata8 \".paravirt_bundles\", 998b, 999b, "			\
+	__stringify(privop) "\n"
+
+
+struct paravirt_patch_bundle_elem {
+	const void	*sbundle;
+	const void	*ebundle;
+	unsigned long	type;
+};
+
+
+struct paravirt_patch_site_inst {
+	unsigned long	stag;
+	unsigned long	etag;
+	unsigned long	type;
+};
+
+#define paravirt_alt_inst(instr, privop)				\
+	"\t[998:]\n"							\
+	"\t" instr "\n"							\
+	"\t[999:]\n"							\
+	"\t.pushsection .paravirt_insts, \"a\"\n"			\
+	"\t.popsection\n"						\
+	"\t.xdata8 \".paravirt_insts\", 998b, 999b, "			\
+	__stringify(privop) "\n"
+
+struct paravirt_patch_site_branch {
+	unsigned long	tag;
+	unsigned long	type;
+};
+
+struct paravirt_patch_branch_target {
+	const void	*entry;
+	unsigned long	type;
+};
+
+void
+__paravirt_patch_apply_branch(
+	unsigned long tag, unsigned long type,
+	const struct paravirt_patch_branch_target *entries,
+	unsigned int nr_entries);
+
+void
+paravirt_patch_reloc_br(unsigned long tag, const void *target);
+
+void
+paravirt_patch_reloc_brl(unsigned long tag, const void *target);
+
+
+#if defined(ASM_SUPPORTED) && defined(CONFIG_PARAVIRT)
+unsigned long
+ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type);
+
+unsigned long
+__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
+			      const struct paravirt_patch_bundle_elem *elems,
+			      unsigned long nelems,
+			      const struct paravirt_patch_bundle_elem **found);
+
+void
+paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
+			    const struct paravirt_patch_site_bundle *end);
+
+void
+paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
+			  const struct paravirt_patch_site_inst *end);
+
+void paravirt_patch_apply(void);
+#else
+#define paravirt_patch_apply_bundle(start, end)	do { } while (0)
+#define paravirt_patch_apply_inst(start, end)	do { } while (0)
+#define paravirt_patch_apply()			do { } while (0)
+#endif
+
+#endif /* !__ASSEMBLEY__ */
+
+#endif /* __ASM_PARAVIRT_PATCH_H */
+
+/*
+ * Local variables:
+ * mode: C
+ * c-set-style: "linux"
+ * c-basic-offset: 8
+ * tab-width: 8
+ * indent-tabs-mode: t
+ * End:
+ */
diff --git a/arch/ia64/include/asm/paravirt_privop.h b/arch/ia64/include/asm/paravirt_privop.h
index 33c8e55f5775..3d2951130b5f 100644
--- a/arch/ia64/include/asm/paravirt_privop.h
+++ b/arch/ia64/include/asm/paravirt_privop.h
@@ -33,7 +33,7 @@
  */
 
 struct pv_cpu_ops {
-	void (*fc)(unsigned long addr);
+	void (*fc)(void *addr);
 	unsigned long (*thash)(unsigned long addr);
 	unsigned long (*get_cpuid)(int index);
 	unsigned long (*get_pmd)(int index);
@@ -60,12 +60,18 @@ extern unsigned long ia64_native_getreg_func(int regnum);
 /* Instructions paravirtualized for performance */
 /************************************************/
 
+#ifndef ASM_SUPPORTED
+#define paravirt_ssm_i()	pv_cpu_ops.ssm_i()
+#define paravirt_rsm_i()	pv_cpu_ops.rsm_i()
+#define __paravirt_getreg()	pv_cpu_ops.getreg()
+#endif
+
 /* mask for ia64_native_ssm/rsm() must be constant.("i" constraing).
  * static inline function doesn't satisfy it. */
 #define paravirt_ssm(mask)			\
 	do {					\
 		if ((mask) == IA64_PSR_I)	\
-			pv_cpu_ops.ssm_i();	\
+			paravirt_ssm_i();	\
 		else				\
 			ia64_native_ssm(mask);	\
 	} while (0)
@@ -73,7 +79,7 @@ extern unsigned long ia64_native_getreg_func(int regnum);
 #define paravirt_rsm(mask)			\
 	do {					\
 		if ((mask) == IA64_PSR_I)	\
-			pv_cpu_ops.rsm_i();	\
+			paravirt_rsm_i();	\
 		else				\
 			ia64_native_rsm(mask);	\
 	} while (0)
@@ -86,7 +92,7 @@ extern unsigned long ia64_native_getreg_func(int regnum);
 		if ((reg) == _IA64_REG_IP)			\
 			res = ia64_native_getreg(_IA64_REG_IP); \
 		else						\
-			res = pv_cpu_ops.getreg(reg);		\
+			res = __paravirt_getreg(reg);		\
 		res;						\
 	})
 
@@ -112,6 +118,12 @@ void paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch);
 
 #endif /* CONFIG_PARAVIRT */
 
+#if defined(CONFIG_PARAVIRT) && defined(ASM_SUPPORTED)
+#define paravirt_dv_serialize_data()	ia64_dv_serialize_data()
+#else
+#define paravirt_dv_serialize_data()	/* nothing */
+#endif
+
 /* these routines utilize privilege-sensitive or performance-sensitive
  * privileged instructions so the code must be replaced with
  * paravirtualized versions */
@@ -121,4 +133,349 @@ void paravirt_cpu_asm_init(const struct pv_cpu_asm_switch *cpu_asm_switch);
 	IA64_PARAVIRT_ASM_FUNC(work_processed_syscall)
 #define ia64_leave_kernel		IA64_PARAVIRT_ASM_FUNC(leave_kernel)
 
+
+#if defined(CONFIG_PARAVIRT)
+/******************************************************************************
+ * binary patching infrastructure
+ */
+#define PARAVIRT_PATCH_TYPE_FC				1
+#define PARAVIRT_PATCH_TYPE_THASH			2
+#define PARAVIRT_PATCH_TYPE_GET_CPUID			3
+#define PARAVIRT_PATCH_TYPE_GET_PMD			4
+#define PARAVIRT_PATCH_TYPE_PTCGA			5
+#define PARAVIRT_PATCH_TYPE_GET_RR			6
+#define PARAVIRT_PATCH_TYPE_SET_RR			7
+#define PARAVIRT_PATCH_TYPE_SET_RR0_TO_RR4		8
+#define PARAVIRT_PATCH_TYPE_SSM_I			9
+#define PARAVIRT_PATCH_TYPE_RSM_I			10
+#define PARAVIRT_PATCH_TYPE_GET_PSR_I			11
+#define PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE	12
+
+/* PARAVIRT_PATY_TYPE_[GS]ETREG + _IA64_REG_xxx */
+#define PARAVIRT_PATCH_TYPE_GETREG			0x10000000
+#define PARAVIRT_PATCH_TYPE_SETREG			0x20000000
+
+/*
+ * struct task_struct* (*ia64_switch_to)(void* next_task);
+ * void *ia64_leave_syscall;
+ * void *ia64_work_processed_syscall
+ * void *ia64_leave_kernel;
+ */
+
+#define PARAVIRT_PATCH_TYPE_BR_START			0x30000000
+#define PARAVIRT_PATCH_TYPE_BR_SWITCH_TO		\
+	(PARAVIRT_PATCH_TYPE_BR_START + 0)
+#define PARAVIRT_PATCH_TYPE_BR_LEAVE_SYSCALL		\
+	(PARAVIRT_PATCH_TYPE_BR_START + 1)
+#define PARAVIRT_PATCH_TYPE_BR_WORK_PROCESSED_SYSCALL	\
+	(PARAVIRT_PATCH_TYPE_BR_START + 2)
+#define PARAVIRT_PATCH_TYPE_BR_LEAVE_KERNEL		\
+	(PARAVIRT_PATCH_TYPE_BR_START + 3)
+
+#ifdef ASM_SUPPORTED
+#include <asm/paravirt_patch.h>
+
+/*
+ * pv_cpu_ops calling stub.
+ * normal function call convension can't be written by gcc
+ * inline assembly.
+ *
+ * from the caller's point of view,
+ * the following registers will be clobbered.
+ * r2, r3
+ * r8-r15
+ * r16, r17
+ * b6, b7
+ * p6-p15
+ * ar.ccv
+ *
+ * from the callee's point of view ,
+ * the following registers can be used.
+ * r2, r3: scratch
+ * r8: scratch, input argument0 and return value
+ * r0-r15: scratch, input argument1-5
+ * b6: return pointer
+ * b7: scratch
+ * p6-p15: scratch
+ * ar.ccv: scratch
+ *
+ * other registers must not be changed. especially
+ * b0: rp: preserved. gcc ignores b0 in clobbered register.
+ * r16: saved gp
+ */
+/* 5 bundles */
+#define __PARAVIRT_BR							\
+	";;\n"								\
+	"{ .mlx\n"							\
+	"nop 0\n"							\
+	"movl r2 = %[op_addr]\n"/* get function pointer address */	\
+	";;\n"								\
+	"}\n"								\
+	"1:\n"								\
+	"{ .mii\n"							\
+	"ld8 r2 = [r2]\n"	/* load function descriptor address */	\
+	"mov r17 = ip\n"	/* get ip to calc return address */	\
+	"mov r16 = gp\n"	/* save gp */				\
+	";;\n"								\
+	"}\n"								\
+	"{ .mii\n"							\
+	"ld8 r3 = [r2], 8\n"	/* load entry address */		\
+	"adds r17 =  1f - 1b, r17\n"	/* calculate return address */	\
+	";;\n"								\
+	"mov b7 = r3\n"		/* set entry address */			\
+	"}\n"								\
+	"{ .mib\n"							\
+	"ld8 gp = [r2]\n"	/* load gp value */			\
+	"mov b6 = r17\n"	/* set return address */		\
+	"br.cond.sptk.few b7\n"	/* intrinsics are very short isns */	\
+	"}\n"								\
+	"1:\n"								\
+	"{ .mii\n"							\
+	"mov gp = r16\n"	/* restore gp value */			\
+	"nop 0\n"							\
+	"nop 0\n"							\
+	";;\n"								\
+	"}\n"
+
+#define PARAVIRT_OP(op)				\
+	[op_addr] "i"(&pv_cpu_ops.op)
+
+#define PARAVIRT_TYPE(type)			\
+	PARAVIRT_PATCH_TYPE_ ## type
+
+#define PARAVIRT_REG_CLOBBERS0					\
+	"r2", "r3", /*"r8",*/ "r9", "r10", "r11", "r14",	\
+		"r15", "r16", "r17"
+
+#define PARAVIRT_REG_CLOBBERS1					\
+	"r2","r3", /*"r8",*/ "r9", "r10", "r11", "r14",		\
+		"r15", "r16", "r17"
+
+#define PARAVIRT_REG_CLOBBERS2					\
+	"r2", "r3", /*"r8", "r9",*/ "r10", "r11", "r14",	\
+		"r15", "r16", "r17"
+
+#define PARAVIRT_REG_CLOBBERS5					\
+	"r2", "r3", /*"r8", "r9", "r10", "r11", "r14",*/	\
+		"r15", "r16", "r17"
+
+#define PARAVIRT_BR_CLOBBERS			\
+	"b6", "b7"
+
+#define PARAVIRT_PR_CLOBBERS						\
+	"p6", "p7", "p8", "p9", "p10", "p11", "p12", "p13", "p14", "p15"
+
+#define PARAVIRT_AR_CLOBBERS			\
+	"ar.ccv"
+
+#define PARAVIRT_CLOBBERS0			\
+		PARAVIRT_REG_CLOBBERS0,		\
+		PARAVIRT_BR_CLOBBERS,		\
+		PARAVIRT_PR_CLOBBERS,		\
+		PARAVIRT_AR_CLOBBERS,		\
+		"memory"
+
+#define PARAVIRT_CLOBBERS1			\
+		PARAVIRT_REG_CLOBBERS1,		\
+		PARAVIRT_BR_CLOBBERS,		\
+		PARAVIRT_PR_CLOBBERS,		\
+		PARAVIRT_AR_CLOBBERS,		\
+		"memory"
+
+#define PARAVIRT_CLOBBERS2			\
+		PARAVIRT_REG_CLOBBERS2,		\
+		PARAVIRT_BR_CLOBBERS,		\
+		PARAVIRT_PR_CLOBBERS,		\
+		PARAVIRT_AR_CLOBBERS,		\
+		"memory"
+
+#define PARAVIRT_CLOBBERS5			\
+		PARAVIRT_REG_CLOBBERS5,		\
+		PARAVIRT_BR_CLOBBERS,		\
+		PARAVIRT_PR_CLOBBERS,		\
+		PARAVIRT_AR_CLOBBERS,		\
+		"memory"
+
+#define PARAVIRT_BR0(op, type)					\
+	register unsigned long ia64_clobber asm ("r8");		\
+	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
+					  PARAVIRT_TYPE(type))	\
+		      :	"=r"(ia64_clobber)			\
+		      : PARAVIRT_OP(op)				\
+		      : PARAVIRT_CLOBBERS0)
+
+#define PARAVIRT_BR0_RET(op, type)				\
+	register unsigned long ia64_intri_res asm ("r8");	\
+	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
+					  PARAVIRT_TYPE(type))	\
+		      : "=r"(ia64_intri_res)			\
+		      : PARAVIRT_OP(op)				\
+		      : PARAVIRT_CLOBBERS0)
+
+#define PARAVIRT_BR1(op, type, arg1)				\
+	register unsigned long __##arg1 asm ("r8") = arg1;	\
+	register unsigned long ia64_clobber asm ("r8");		\
+	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
+					  PARAVIRT_TYPE(type))	\
+		      :	"=r"(ia64_clobber)			\
+		      : PARAVIRT_OP(op), "0"(__##arg1)		\
+		      : PARAVIRT_CLOBBERS1)
+
+#define PARAVIRT_BR1_RET(op, type, arg1)			\
+	register unsigned long ia64_intri_res asm ("r8");	\
+	register unsigned long __##arg1 asm ("r8") = arg1;	\
+	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
+					  PARAVIRT_TYPE(type))	\
+		      : "=r"(ia64_intri_res)			\
+		      : PARAVIRT_OP(op), "0"(__##arg1)		\
+		      : PARAVIRT_CLOBBERS1)
+
+#define PARAVIRT_BR1_VOID(op, type, arg1)			\
+	register void *__##arg1 asm ("r8") = arg1;		\
+	register unsigned long ia64_clobber asm ("r8");		\
+	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
+					  PARAVIRT_TYPE(type))	\
+		      :	"=r"(ia64_clobber)			\
+		      : PARAVIRT_OP(op), "0"(__##arg1)		\
+		      : PARAVIRT_CLOBBERS1)
+
+#define PARAVIRT_BR2(op, type, arg1, arg2)				\
+	register unsigned long __##arg1 asm ("r8") = arg1;		\
+	register unsigned long __##arg2 asm ("r9") = arg2;		\
+	register unsigned long ia64_clobber1 asm ("r8");		\
+	register unsigned long ia64_clobber2 asm ("r9");		\
+	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,		\
+					  PARAVIRT_TYPE(type))		\
+		      : "=r"(ia64_clobber1), "=r"(ia64_clobber2)	\
+		      : PARAVIRT_OP(op), "0"(__##arg1), "1"(__##arg2)	\
+		      : PARAVIRT_CLOBBERS2)
+
+
+#define PARAVIRT_DEFINE_CPU_OP0(op, type)		\
+	static inline void				\
+	paravirt_ ## op (void)				\
+	{						\
+		PARAVIRT_BR0(op, type);			\
+	}
+
+#define PARAVIRT_DEFINE_CPU_OP0_RET(op, type)		\
+	static inline unsigned long			\
+	paravirt_ ## op (void)				\
+	{						\
+		PARAVIRT_BR0_RET(op, type);		\
+		return ia64_intri_res;			\
+	}
+
+#define PARAVIRT_DEFINE_CPU_OP1_VOID(op, type)		\
+	static inline void				\
+	paravirt_ ## op (void *arg1)			\
+	{						\
+		PARAVIRT_BR1_VOID(op, type, arg1);	\
+	}
+
+#define PARAVIRT_DEFINE_CPU_OP1(op, type)		\
+	static inline void				\
+	paravirt_ ## op (unsigned long arg1)		\
+	{						\
+		PARAVIRT_BR1(op, type, arg1);		\
+	}
+
+#define PARAVIRT_DEFINE_CPU_OP1_RET(op, type)		\
+	static inline unsigned long			\
+	paravirt_ ## op (unsigned long arg1)		\
+	{						\
+		PARAVIRT_BR1_RET(op, type, arg1);	\
+		return ia64_intri_res;			\
+	}
+
+#define PARAVIRT_DEFINE_CPU_OP2(op, type)		\
+	static inline void				\
+	paravirt_ ## op (unsigned long arg1,		\
+			 unsigned long arg2)		\
+	{						\
+		PARAVIRT_BR2(op, type, arg1, arg2);	\
+	}
+
+
+PARAVIRT_DEFINE_CPU_OP1_VOID(fc, FC);
+PARAVIRT_DEFINE_CPU_OP1_RET(thash, THASH)
+PARAVIRT_DEFINE_CPU_OP1_RET(get_cpuid, GET_CPUID)
+PARAVIRT_DEFINE_CPU_OP1_RET(get_pmd, GET_PMD)
+PARAVIRT_DEFINE_CPU_OP2(ptcga, PTCGA)
+PARAVIRT_DEFINE_CPU_OP1_RET(get_rr, GET_RR)
+PARAVIRT_DEFINE_CPU_OP2(set_rr, SET_RR)
+PARAVIRT_DEFINE_CPU_OP0(ssm_i, SSM_I)
+PARAVIRT_DEFINE_CPU_OP0(rsm_i, RSM_I)
+PARAVIRT_DEFINE_CPU_OP0_RET(get_psr_i, GET_PSR_I)
+PARAVIRT_DEFINE_CPU_OP1(intrin_local_irq_restore, INTRIN_LOCAL_IRQ_RESTORE)
+
+static inline void
+paravirt_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
+			unsigned long val2, unsigned long val3,
+			unsigned long val4)
+{
+	register unsigned long __val0 asm ("r8") = val0;
+	register unsigned long __val1 asm ("r9") = val1;
+	register unsigned long __val2 asm ("r10") = val2;
+	register unsigned long __val3 asm ("r11") = val3;
+	register unsigned long __val4 asm ("r14") = val4;
+
+	register unsigned long ia64_clobber0 asm ("r8");
+	register unsigned long ia64_clobber1 asm ("r9");
+	register unsigned long ia64_clobber2 asm ("r10");
+	register unsigned long ia64_clobber3 asm ("r11");
+	register unsigned long ia64_clobber4 asm ("r14");
+
+	asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,
+					  PARAVIRT_TYPE(SET_RR0_TO_RR4))
+		      : "=r"(ia64_clobber0),
+			"=r"(ia64_clobber1),
+			"=r"(ia64_clobber2),
+			"=r"(ia64_clobber3),
+			"=r"(ia64_clobber4)
+		      : PARAVIRT_OP(set_rr0_to_rr4),
+			"0"(__val0), "1"(__val1), "2"(__val2),
+			"3"(__val3), "4"(__val4)
+		      : PARAVIRT_CLOBBERS5);
+}
+
+/* unsigned long paravirt_getreg(int reg) */
+#define __paravirt_getreg(reg)						\
+	({								\
+		register unsigned long ia64_intri_res asm ("r8");	\
+		register unsigned long __reg asm ("r8") = (reg);	\
+									\
+		BUILD_BUG_ON(!__builtin_constant_p(reg));		\
+		asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
+						  PARAVIRT_TYPE(GETREG) \
+						  + (reg))		\
+			      : "=r"(ia64_intri_res)			\
+			      : PARAVIRT_OP(getreg), "0"(__reg)		\
+			      : PARAVIRT_CLOBBERS1);			\
+									\
+		ia64_intri_res;						\
+	})
+
+/* void paravirt_setreg(int reg, unsigned long val) */
+#define paravirt_setreg(reg, val)					\
+	do {								\
+		register unsigned long __val asm ("r8") = val;		\
+		register unsigned long __reg asm ("r9") = reg;		\
+		register unsigned long ia64_clobber1 asm ("r8");	\
+		register unsigned long ia64_clobber2 asm ("r9");	\
+									\
+		BUILD_BUG_ON(!__builtin_constant_p(reg));		\
+		asm volatile (paravirt_alt_bundle(__PARAVIRT_BR,	\
+						  PARAVIRT_TYPE(SETREG) \
+						  + (reg))		\
+			      : "=r"(ia64_clobber1),			\
+				"=r"(ia64_clobber2)			\
+			      : PARAVIRT_OP(setreg),			\
+				"1"(__reg), "0"(__val)			\
+			      : PARAVIRT_CLOBBERS2);			\
+	} while (0)
+
+#endif /* ASM_SUPPORTED */
+#endif /* CONFIG_PARAVIRT && ASM_SUPPOTED */
+
 #endif /* _ASM_IA64_PARAVIRT_PRIVOP_H */
diff --git a/arch/ia64/include/asm/smp.h b/arch/ia64/include/asm/smp.h
index 21c402365d0e..598408336251 100644
--- a/arch/ia64/include/asm/smp.h
+++ b/arch/ia64/include/asm/smp.h
@@ -126,7 +126,8 @@ extern void identify_siblings (struct cpuinfo_ia64 *);
 extern int is_multithreading_enabled(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 #else /* CONFIG_SMP */
 
diff --git a/arch/ia64/include/asm/spinlock.h b/arch/ia64/include/asm/spinlock.h
index 0229fb95fb38..13ab71576bc7 100644
--- a/arch/ia64/include/asm/spinlock.h
+++ b/arch/ia64/include/asm/spinlock.h
@@ -120,6 +120,38 @@ do {											\
 #define __raw_read_can_lock(rw)		(*(volatile int *)(rw) >= 0)
 #define __raw_write_can_lock(rw)	(*(volatile int *)(rw) == 0)
 
+#ifdef ASM_SUPPORTED
+
+static __always_inline void
+__raw_read_lock_flags(raw_rwlock_t *lock, unsigned long flags)
+{
+	__asm__ __volatile__ (
+		"tbit.nz p6, p0 = %1,%2\n"
+		"br.few 3f\n"
+		"1:\n"
+		"fetchadd4.rel r2 = [%0], -1;;\n"
+		"(p6) ssm psr.i\n"
+		"2:\n"
+		"hint @pause\n"
+		"ld4 r2 = [%0];;\n"
+		"cmp4.lt p7,p0 = r2, r0\n"
+		"(p7) br.cond.spnt.few 2b\n"
+		"(p6) rsm psr.i\n"
+		";;\n"
+		"3:\n"
+		"fetchadd4.acq r2 = [%0], 1;;\n"
+		"cmp4.lt p7,p0 = r2, r0\n"
+		"(p7) br.cond.spnt.few 1b\n"
+		: : "r"(lock), "r"(flags), "i"(IA64_PSR_I_BIT)
+		: "p6", "p7", "r2", "memory");
+}
+
+#define __raw_read_lock(lock) __raw_read_lock_flags(lock, 0)
+
+#else /* !ASM_SUPPORTED */
+
+#define __raw_read_lock_flags(rw, flags) __raw_read_lock(rw)
+
 #define __raw_read_lock(rw)								\
 do {											\
 	raw_rwlock_t *__read_lock_ptr = (rw);						\
@@ -131,6 +163,8 @@ do {											\
 	}										\
 } while (0)
 
+#endif /* !ASM_SUPPORTED */
+
 #define __raw_read_unlock(rw)					\
 do {								\
 	raw_rwlock_t *__read_lock_ptr = (rw);			\
@@ -138,20 +172,33 @@ do {								\
 } while (0)
 
 #ifdef ASM_SUPPORTED
-#define __raw_write_lock(rw)							\
-do {										\
- 	__asm__ __volatile__ (							\
-		"mov ar.ccv = r0\n"						\
-		"dep r29 = -1, r0, 31, 1;;\n"					\
-		"1:\n"								\
-		"ld4 r2 = [%0];;\n"						\
-		"cmp4.eq p0,p7 = r0,r2\n"					\
-		"(p7) br.cond.spnt.few 1b \n"					\
-		"cmpxchg4.acq r2 = [%0], r29, ar.ccv;;\n"			\
-		"cmp4.eq p0,p7 = r0, r2\n"					\
-		"(p7) br.cond.spnt.few 1b;;\n"					\
-		:: "r"(rw) : "ar.ccv", "p7", "r2", "r29", "memory");		\
-} while(0)
+
+static __always_inline void
+__raw_write_lock_flags(raw_rwlock_t *lock, unsigned long flags)
+{
+	__asm__ __volatile__ (
+		"tbit.nz p6, p0 = %1, %2\n"
+		"mov ar.ccv = r0\n"
+		"dep r29 = -1, r0, 31, 1\n"
+		"br.few 3f;;\n"
+		"1:\n"
+		"(p6) ssm psr.i\n"
+		"2:\n"
+		"hint @pause\n"
+		"ld4 r2 = [%0];;\n"
+		"cmp4.eq p0,p7 = r0, r2\n"
+		"(p7) br.cond.spnt.few 2b\n"
+		"(p6) rsm psr.i\n"
+		";;\n"
+		"3:\n"
+		"cmpxchg4.acq r2 = [%0], r29, ar.ccv;;\n"
+		"cmp4.eq p0,p7 = r0, r2\n"
+		"(p7) br.cond.spnt.few 1b;;\n"
+		: : "r"(lock), "r"(flags), "i"(IA64_PSR_I_BIT)
+		: "ar.ccv", "p6", "p7", "r2", "r29", "memory");
+}
+
+#define __raw_write_lock(rw) __raw_write_lock_flags(rw, 0)
 
 #define __raw_write_trylock(rw)							\
 ({										\
@@ -174,6 +221,8 @@ static inline void __raw_write_unlock(raw_rwlock_t *x)
 
 #else /* !ASM_SUPPORTED */
 
+#define __raw_write_lock_flags(l, flags) __raw_write_lock(l)
+
 #define __raw_write_lock(l)								\
 ({											\
 	__u64 ia64_val, ia64_set_val = ia64_dep_mi(-1, 0, 31, 1);			\
diff --git a/arch/ia64/include/asm/timex.h b/arch/ia64/include/asm/timex.h
index 4e03cfe74a0c..86c7db861180 100644
--- a/arch/ia64/include/asm/timex.h
+++ b/arch/ia64/include/asm/timex.h
@@ -40,5 +40,6 @@ get_cycles (void)
 }
 
 extern void ia64_cpu_local_tick (void);
+extern unsigned long long ia64_native_sched_clock (void);
 
 #endif /* _ASM_IA64_TIMEX_H */
diff --git a/arch/ia64/include/asm/topology.h b/arch/ia64/include/asm/topology.h
index f260dcf21515..7b4c8c70b2d1 100644
--- a/arch/ia64/include/asm/topology.h
+++ b/arch/ia64/include/asm/topology.h
@@ -112,11 +112,6 @@ void build_cpu_to_node_map(void);
 
 extern void arch_fix_phys_package_id(int num, u32 slot);
 
-#define pcibus_to_cpumask(bus)	(pcibus_to_node(bus) == -1 ? \
-					CPU_MASK_ALL : \
-					node_to_cpumask(pcibus_to_node(bus)) \
-				)
-
 #define cpumask_of_pcibus(bus)	(pcibus_to_node(bus) == -1 ?		\
 				 cpu_all_mask :				\
 				 cpumask_of_node(pcibus_to_node(bus)))
diff --git a/arch/ia64/include/asm/uv/uv_hub.h b/arch/ia64/include/asm/uv/uv_hub.h
index f607018af4a1..53e9dfacd073 100644
--- a/arch/ia64/include/asm/uv/uv_hub.h
+++ b/arch/ia64/include/asm/uv/uv_hub.h
@@ -305,5 +305,11 @@ static inline int uv_num_possible_blades(void)
 	return 1;
 }
 
+static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
+{
+	/* not currently needed on ia64 */
+}
+
+
 #endif /* __ASM_IA64_UV_HUB__ */
 
diff --git a/arch/ia64/include/asm/uv/uv_mmrs.h b/arch/ia64/include/asm/uv/uv_mmrs.h
index c149ef085437..fe0b8f05e1a8 100644
--- a/arch/ia64/include/asm/uv/uv_mmrs.h
+++ b/arch/ia64/include/asm/uv/uv_mmrs.h
@@ -8,8 +8,8 @@
  * Copyright (C) 2007-2008 Silicon Graphics, Inc. All rights reserved.
  */
 
-#ifndef __ASM_IA64_UV_MMRS__
-#define __ASM_IA64_UV_MMRS__
+#ifndef _ASM_IA64_UV_UV_MMRS_H
+#define _ASM_IA64_UV_UV_MMRS_H
 
 #define UV_MMR_ENABLE		(1UL << 63)
 
@@ -243,6 +243,158 @@ union uvh_event_occurred0_u {
 #define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
 
 /* ========================================================================= */
+/*                         UVH_GR0_TLB_INT0_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL
+
+#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR0_TLB_INT0_CONFIG_DM_SHFT 8
+#define UVH_GR0_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR0_TLB_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_GR0_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR0_TLB_INT0_CONFIG_P_SHFT 13
+#define UVH_GR0_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR0_TLB_INT0_CONFIG_T_SHFT 15
+#define UVH_GR0_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR0_TLB_INT0_CONFIG_M_SHFT 16
+#define UVH_GR0_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr0_tlb_int0_config_u {
+    unsigned long	v;
+    struct uvh_gr0_tlb_int0_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR0_TLB_INT1_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL
+
+#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0
+#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR0_TLB_INT1_CONFIG_DM_SHFT 8
+#define UVH_GR0_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR0_TLB_INT1_CONFIG_STATUS_SHFT 12
+#define UVH_GR0_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR0_TLB_INT1_CONFIG_P_SHFT 13
+#define UVH_GR0_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR0_TLB_INT1_CONFIG_T_SHFT 15
+#define UVH_GR0_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR0_TLB_INT1_CONFIG_M_SHFT 16
+#define UVH_GR0_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr0_tlb_int1_config_u {
+    unsigned long	v;
+    struct uvh_gr0_tlb_int1_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR1_TLB_INT0_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL
+
+#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT 8
+#define UVH_GR1_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR1_TLB_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_GR1_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR1_TLB_INT0_CONFIG_P_SHFT 13
+#define UVH_GR1_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR1_TLB_INT0_CONFIG_T_SHFT 15
+#define UVH_GR1_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR1_TLB_INT0_CONFIG_M_SHFT 16
+#define UVH_GR1_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr1_tlb_int0_config_u {
+    unsigned long	v;
+    struct uvh_gr1_tlb_int0_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR1_TLB_INT1_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL
+
+#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0
+#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT 8
+#define UVH_GR1_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR1_TLB_INT1_CONFIG_STATUS_SHFT 12
+#define UVH_GR1_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR1_TLB_INT1_CONFIG_P_SHFT 13
+#define UVH_GR1_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR1_TLB_INT1_CONFIG_T_SHFT 15
+#define UVH_GR1_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR1_TLB_INT1_CONFIG_M_SHFT 16
+#define UVH_GR1_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr1_tlb_int1_config_u {
+    unsigned long	v;
+    struct uvh_gr1_tlb_int1_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                               UVH_INT_CMPB                                */
 /* ========================================================================= */
 #define UVH_INT_CMPB 0x22080UL
@@ -670,4 +822,4 @@ union uvh_si_alias2_overlay_config_u {
 };
 
 
-#endif /* __ASM_IA64_UV_MMRS__ */
+#endif /* _ASM_IA64_UV_UV_MMRS_H */
diff --git a/arch/ia64/include/asm/xen/hypervisor.h b/arch/ia64/include/asm/xen/hypervisor.h
index 7a804e80fc67..e425227a418e 100644
--- a/arch/ia64/include/asm/xen/hypervisor.h
+++ b/arch/ia64/include/asm/xen/hypervisor.h
@@ -33,9 +33,6 @@
 #ifndef _ASM_IA64_XEN_HYPERVISOR_H
 #define _ASM_IA64_XEN_HYPERVISOR_H
 
-#ifdef CONFIG_XEN
-
-#include <linux/init.h>
 #include <xen/interface/xen.h>
 #include <xen/interface/version.h>	/* to compile feature.c */
 #include <xen/features.h>		/* to comiple xen-netfront.c */
@@ -43,22 +40,32 @@
 
 /* xen_domain_type is set before executing any C code by early_xen_setup */
 enum xen_domain_type {
-	XEN_NATIVE,
-	XEN_PV_DOMAIN,
-	XEN_HVM_DOMAIN,
+	XEN_NATIVE,	/* running on bare hardware */
+	XEN_PV_DOMAIN,	/* running in a PV domain */
+	XEN_HVM_DOMAIN,	/* running in a Xen hvm domain*/
 };
 
+#ifdef CONFIG_XEN
 extern enum xen_domain_type xen_domain_type;
+#else
+#define xen_domain_type		XEN_NATIVE
+#endif
 
 #define xen_domain()		(xen_domain_type != XEN_NATIVE)
-#define xen_pv_domain()		(xen_domain_type == XEN_PV_DOMAIN)
-#define xen_initial_domain()	(xen_pv_domain() && \
+#define xen_pv_domain()		(xen_domain() &&			\
+				 xen_domain_type == XEN_PV_DOMAIN)
+#define xen_hvm_domain()	(xen_domain() &&			\
+				 xen_domain_type == XEN_HVM_DOMAIN)
+
+#ifdef CONFIG_XEN_DOM0
+#define xen_initial_domain()	(xen_pv_domain() &&			\
 				 (xen_start_info->flags & SIF_INITDOMAIN))
-#define xen_hvm_domain()	(xen_domain_type == XEN_HVM_DOMAIN)
+#else
+#define xen_initial_domain()	(0)
+#endif
 
-/* deprecated. remove this */
-#define is_running_on_xen()	(xen_domain_type == XEN_PV_DOMAIN)
 
+#ifdef CONFIG_XEN
 extern struct shared_info *HYPERVISOR_shared_info;
 extern struct start_info *xen_start_info;
 
@@ -74,16 +81,6 @@ void force_evtchn_callback(void);
 
 /* For setup_arch() in arch/ia64/kernel/setup.c */
 void xen_ia64_enable_opt_feature(void);
-
-#else /* CONFIG_XEN */
-
-#define xen_domain()		(0)
-#define xen_pv_domain()		(0)
-#define xen_initial_domain()	(0)
-#define xen_hvm_domain()	(0)
-#define is_running_on_xen()	(0)	/* deprecated. remove this */
 #endif
 
-#define is_initial_xendomain()	(0)	/* deprecated. remove this */
-
 #endif /* _ASM_IA64_XEN_HYPERVISOR_H */
diff --git a/arch/ia64/include/asm/xen/inst.h b/arch/ia64/include/asm/xen/inst.h
index 19c2ae1d878a..c53a47611208 100644
--- a/arch/ia64/include/asm/xen/inst.h
+++ b/arch/ia64/include/asm/xen/inst.h
@@ -33,6 +33,9 @@
 #define __paravirt_work_processed_syscall_target \
 						xen_work_processed_syscall
 
+#define paravirt_fsyscall_table			xen_fsyscall_table
+#define paravirt_fsys_bubble_down		xen_fsys_bubble_down
+
 #define MOV_FROM_IFA(reg)	\
 	movl reg = XSI_IFA;	\
 	;;			\
@@ -110,6 +113,27 @@
 .endm
 #define MOV_FROM_PSR(pred, reg, clob)	__MOV_FROM_PSR pred, reg, clob
 
+/* assuming ar.itc is read with interrupt disabled. */
+#define MOV_FROM_ITC(pred, pred_clob, reg, clob)		\
+(pred)	movl clob = XSI_ITC_OFFSET;				\
+	;;							\
+(pred)	ld8 clob = [clob];					\
+(pred)	mov reg = ar.itc;					\
+	;;							\
+(pred)	add reg = reg, clob;					\
+	;;							\
+(pred)	movl clob = XSI_ITC_LAST;				\
+	;;							\
+(pred)	ld8 clob = [clob];					\
+	;;							\
+(pred)	cmp.geu.unc pred_clob, p0 = clob, reg;			\
+	;;							\
+(pred_clob)	add reg = 1, clob;				\
+	;;							\
+(pred)	movl clob = XSI_ITC_LAST;				\
+	;;							\
+(pred)	st8 [clob] = reg
+
 
 #define MOV_TO_IFA(reg, clob)	\
 	movl clob = XSI_IFA;	\
@@ -362,6 +386,10 @@
 #define RSM_PSR_DT		\
 	XEN_HYPER_RSM_PSR_DT
 
+#define RSM_PSR_BE_I(clob0, clob1)	\
+	RSM_PSR_I(p0, clob0, clob1);	\
+	rum psr.be
+
 #define SSM_PSR_DT_AND_SRLZ_I	\
 	XEN_HYPER_SSM_PSR_DT
 
diff --git a/arch/ia64/include/asm/xen/interface.h b/arch/ia64/include/asm/xen/interface.h
index f00fab40854d..e951e740bdf2 100644
--- a/arch/ia64/include/asm/xen/interface.h
+++ b/arch/ia64/include/asm/xen/interface.h
@@ -209,6 +209,15 @@ struct mapped_regs {
 			unsigned long krs[8];	/* kernel registers */
 			unsigned long tmp[16];	/* temp registers
 						   (e.g. for hyperprivops) */
+
+			/* itc paravirtualization
+			 * vAR.ITC = mAR.ITC + itc_offset
+			 * itc_last is one which was lastly passed to
+			 * the guest OS in order to prevent it from
+			 * going backwords.
+			 */
+			unsigned long itc_offset;
+			unsigned long itc_last;
 		};
 	};
 };
diff --git a/arch/ia64/include/asm/xen/minstate.h b/arch/ia64/include/asm/xen/minstate.h
index 4d92d9bbda7b..c57fa910f2c9 100644
--- a/arch/ia64/include/asm/xen/minstate.h
+++ b/arch/ia64/include/asm/xen/minstate.h
@@ -1,3 +1,12 @@
+
+#ifdef CONFIG_VIRT_CPU_ACCOUNTING
+/* read ar.itc in advance, and use it before leaving bank 0 */
+#define XEN_ACCOUNT_GET_STAMP		\
+	MOV_FROM_ITC(pUStk, p6, r20, r2);
+#else
+#define XEN_ACCOUNT_GET_STAMP
+#endif
+
 /*
  * DO_SAVE_MIN switches to the kernel stacks (if necessary) and saves
  * the minimum state necessary that allows us to turn psr.ic back
@@ -123,7 +132,7 @@
 	;;											\
 .mem.offset 0,0; st8.spill [r16]=r2,16;								\
 .mem.offset 8,0; st8.spill [r17]=r3,16;								\
-	ACCOUNT_GET_STAMP									\
+	XEN_ACCOUNT_GET_STAMP									\
 	adds r2=IA64_PT_REGS_R16_OFFSET,r1;							\
 	;;											\
 	EXTRA;											\
diff --git a/arch/ia64/include/asm/xen/patchlist.h b/arch/ia64/include/asm/xen/patchlist.h
new file mode 100644
index 000000000000..eae944e88846
--- /dev/null
+++ b/arch/ia64/include/asm/xen/patchlist.h
@@ -0,0 +1,38 @@
+/******************************************************************************
+ * arch/ia64/include/asm/xen/patchlist.h
+ *
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#define __paravirt_start_gate_fsyscall_patchlist		\
+	__xen_start_gate_fsyscall_patchlist
+#define __paravirt_end_gate_fsyscall_patchlist			\
+	__xen_end_gate_fsyscall_patchlist
+#define __paravirt_start_gate_brl_fsys_bubble_down_patchlist	\
+	__xen_start_gate_brl_fsys_bubble_down_patchlist
+#define __paravirt_end_gate_brl_fsys_bubble_down_patchlist	\
+	__xen_end_gate_brl_fsys_bubble_down_patchlist
+#define __paravirt_start_gate_vtop_patchlist			\
+	__xen_start_gate_vtop_patchlist
+#define __paravirt_end_gate_vtop_patchlist			\
+	__xen_end_gate_vtop_patchlist
+#define __paravirt_start_gate_mckinley_e9_patchlist		\
+	__xen_start_gate_mckinley_e9_patchlist
+#define __paravirt_end_gate_mckinley_e9_patchlist		\
+	__xen_end_gate_mckinley_e9_patchlist
diff --git a/arch/ia64/include/asm/xen/privop.h b/arch/ia64/include/asm/xen/privop.h
index 71ec7546e100..fb4ec5e0b066 100644
--- a/arch/ia64/include/asm/xen/privop.h
+++ b/arch/ia64/include/asm/xen/privop.h
@@ -55,6 +55,8 @@
 #define XSI_BANK1_R16			(XSI_BASE + XSI_BANK1_R16_OFS)
 #define XSI_BANKNUM			(XSI_BASE + XSI_BANKNUM_OFS)
 #define XSI_IHA				(XSI_BASE + XSI_IHA_OFS)
+#define XSI_ITC_OFFSET			(XSI_BASE + XSI_ITC_OFFSET_OFS)
+#define XSI_ITC_LAST			(XSI_BASE + XSI_ITC_LAST_OFS)
 #endif
 
 #ifndef __ASSEMBLY__
@@ -67,7 +69,7 @@
  *  may have different semantics depending on whether they are executed
  *  at PL0 vs PL!=0.  When paravirtualized, these instructions mustn't
  *  be allowed to execute directly, lest incorrect semantics result. */
-extern void xen_fc(unsigned long addr);
+extern void xen_fc(void *addr);
 extern unsigned long xen_thash(unsigned long addr);
 
 /* Note that "ttag" and "cover" are also privilege-sensitive; "ttag"
@@ -80,8 +82,10 @@ extern unsigned long xen_thash(unsigned long addr);
 extern unsigned long xen_get_cpuid(int index);
 extern unsigned long xen_get_pmd(int index);
 
+#ifndef ASM_SUPPORTED
 extern unsigned long xen_get_eflag(void);	/* see xen_ia64_getreg */
 extern void xen_set_eflag(unsigned long);	/* see xen_ia64_setreg */
+#endif
 
 /************************************************/
 /* Instructions paravirtualized for performance */
@@ -106,6 +110,7 @@ extern void xen_set_eflag(unsigned long);	/* see xen_ia64_setreg */
 #define xen_get_virtual_pend()		\
 	(*(((uint8_t *)XEN_MAPPEDREGS->interrupt_mask_addr) - 1))
 
+#ifndef ASM_SUPPORTED
 /* Although all privileged operations can be left to trap and will
  * be properly handled by Xen, some are frequent enough that we use
  * hyperprivops for performance. */
@@ -123,6 +128,7 @@ extern void xen_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
 			       unsigned long val4);
 extern void xen_set_kr(unsigned long index, unsigned long val);
 extern void xen_ptcga(unsigned long addr, unsigned long size);
+#endif /* !ASM_SUPPORTED */
 
 #endif /* !__ASSEMBLY__ */
 
diff --git a/arch/ia64/kernel/Makefile b/arch/ia64/kernel/Makefile
index dc62df021673..6b7edcab0cb5 100644
--- a/arch/ia64/kernel/Makefile
+++ b/arch/ia64/kernel/Makefile
@@ -9,7 +9,7 @@ endif
 extra-y	:= head.o init_task.o vmlinux.lds
 
 obj-y := acpi.o entry.o efi.o efi_stub.o gate-data.o fsys.o ia64_ksyms.o irq.o irq_ia64.o	\
-	 irq_lsapic.o ivt.o machvec.o pal.o patch.o process.o perfmon.o ptrace.o sal.o		\
+	 irq_lsapic.o ivt.o machvec.o pal.o paravirt_patchlist.o patch.o process.o perfmon.o ptrace.o sal.o		\
 	 salinfo.o setup.o signal.o sys_ia64.o time.o traps.o unaligned.o \
 	 unwind.o mca.o mca_asm.o topology.o dma-mapping.o
 
@@ -41,7 +41,8 @@ obj-$(CONFIG_PCI_MSI)		+= msi_ia64.o
 mca_recovery-y			+= mca_drv.o mca_drv_asm.o
 obj-$(CONFIG_IA64_MC_ERR_INJECT)+= err_inject.o
 
-obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirtentry.o
+obj-$(CONFIG_PARAVIRT)		+= paravirt.o paravirtentry.o \
+				   paravirt_patch.o
 
 obj-$(CONFIG_IA64_ESI)		+= esi.o
 ifneq ($(CONFIG_IA64_ESI),)
@@ -50,35 +51,13 @@ endif
 obj-$(CONFIG_DMAR)		+= pci-dma.o
 obj-$(CONFIG_SWIOTLB)		+= pci-swiotlb.o
 
-# The gate DSO image is built using a special linker script.
-targets += gate.so gate-syms.o
-
-extra-y += gate.so gate-syms.o gate.lds gate.o
-
 # fp_emulate() expects f2-f5,f16-f31 to contain the user-level state.
 CFLAGS_traps.o  += -mfixed-range=f2-f5,f16-f31
 
-CPPFLAGS_gate.lds := -P -C -U$(ARCH)
-
-quiet_cmd_gate = GATE $@
-      cmd_gate = $(CC) -nostdlib $(GATECFLAGS_$(@F)) -Wl,-T,$(filter-out FORCE,$^) -o $@
-
-GATECFLAGS_gate.so = -shared -s -Wl,-soname=linux-gate.so.1 \
-		     $(call ld-option, -Wl$(comma)--hash-style=sysv)
-$(obj)/gate.so: $(obj)/gate.lds $(obj)/gate.o FORCE
-	$(call if_changed,gate)
-
-$(obj)/built-in.o: $(obj)/gate-syms.o
-$(obj)/built-in.o: ld_flags += -R $(obj)/gate-syms.o
-
-GATECFLAGS_gate-syms.o = -r
-$(obj)/gate-syms.o: $(obj)/gate.lds $(obj)/gate.o FORCE
-	$(call if_changed,gate)
-
-# gate-data.o contains the gate DSO image as data in section .data.gate.
-# We must build gate.so before we can assemble it.
-# Note: kbuild does not track this dependency due to usage of .incbin
-$(obj)/gate-data.o: $(obj)/gate.so
+# The gate DSO image is built using a special linker script.
+include $(srctree)/arch/ia64/kernel/Makefile.gate
+# tell compiled for native
+CPPFLAGS_gate.lds += -D__IA64_GATE_PARAVIRTUALIZED_NATIVE
 
 # Calculate NR_IRQ = max(IA64_NATIVE_NR_IRQS, XEN_NR_IRQS, ...) based on config
 define sed-y
@@ -114,9 +93,9 @@ include/asm-ia64/nr-irqs.h: arch/$(SRCARCH)/kernel/nr-irqs.s
 clean-files += $(objtree)/include/asm-ia64/nr-irqs.h
 
 #
-# native ivt.S and entry.S
+# native ivt.S, entry.S and fsys.S
 #
-ASM_PARAVIRT_OBJS = ivt.o entry.o
+ASM_PARAVIRT_OBJS = ivt.o entry.o fsys.o
 define paravirtualized_native
 AFLAGS_$(1) += -D__IA64_ASM_PARAVIRTUALIZED_NATIVE
 AFLAGS_pvchk-sed-$(1) += -D__IA64_ASM_PARAVIRTUALIZED_PVCHECK
diff --git a/arch/ia64/kernel/Makefile.gate b/arch/ia64/kernel/Makefile.gate
new file mode 100644
index 000000000000..1d87f84069b3
--- /dev/null
+++ b/arch/ia64/kernel/Makefile.gate
@@ -0,0 +1,27 @@
+# The gate DSO image is built using a special linker script.
+
+targets += gate.so gate-syms.o
+
+extra-y += gate.so gate-syms.o gate.lds gate.o
+
+CPPFLAGS_gate.lds := -P -C -U$(ARCH)
+
+quiet_cmd_gate = GATE $@
+      cmd_gate = $(CC) -nostdlib $(GATECFLAGS_$(@F)) -Wl,-T,$(filter-out FORCE,$^) -o $@
+
+GATECFLAGS_gate.so = -shared -s -Wl,-soname=linux-gate.so.1 \
+		     $(call ld-option, -Wl$(comma)--hash-style=sysv)
+$(obj)/gate.so: $(obj)/gate.lds $(obj)/gate.o FORCE
+	$(call if_changed,gate)
+
+$(obj)/built-in.o: $(obj)/gate-syms.o
+$(obj)/built-in.o: ld_flags += -R $(obj)/gate-syms.o
+
+GATECFLAGS_gate-syms.o = -r
+$(obj)/gate-syms.o: $(obj)/gate.lds $(obj)/gate.o FORCE
+	$(call if_changed,gate)
+
+# gate-data.o contains the gate DSO image as data in section .data.gate.
+# We must build gate.so before we can assemble it.
+# Note: kbuild does not track this dependency due to usage of .incbin
+$(obj)/gate-data.o: $(obj)/gate.so
diff --git a/arch/ia64/kernel/acpi.c b/arch/ia64/kernel/acpi.c
index bdef2ce38c8b..5510317db37b 100644
--- a/arch/ia64/kernel/acpi.c
+++ b/arch/ia64/kernel/acpi.c
@@ -890,7 +890,7 @@ __init void prefill_possible_map(void)
 		possible, max((possible - available_cpus), 0));
 
 	for (i = 0; i < possible; i++)
-		cpu_set(i, cpu_possible_map);
+		set_cpu_possible(i, true);
 }
 
 int acpi_map_lsapic(acpi_handle handle, int *pcpu)
@@ -928,9 +928,9 @@ int acpi_map_lsapic(acpi_handle handle, int *pcpu)
 	buffer.length = ACPI_ALLOCATE_BUFFER;
 	buffer.pointer = NULL;
 
-	cpus_complement(tmp_map, cpu_present_map);
-	cpu = first_cpu(tmp_map);
-	if (cpu >= NR_CPUS)
+	cpumask_complement(&tmp_map, cpu_present_mask);
+	cpu = cpumask_first(&tmp_map);
+	if (cpu >= nr_cpu_ids)
 		return -EINVAL;
 
 	acpi_map_cpu2node(handle, cpu, physid);
diff --git a/arch/ia64/kernel/asm-offsets.c b/arch/ia64/kernel/asm-offsets.c
index 742dbb1d5a4f..af5650169043 100644
--- a/arch/ia64/kernel/asm-offsets.c
+++ b/arch/ia64/kernel/asm-offsets.c
@@ -316,5 +316,7 @@ void foo(void)
 	DEFINE_MAPPED_REG_OFS(XSI_BANK1_R16_OFS, bank1_regs[0]);
 	DEFINE_MAPPED_REG_OFS(XSI_B0NATS_OFS, vbnat);
 	DEFINE_MAPPED_REG_OFS(XSI_B1NATS_OFS, vnat);
+	DEFINE_MAPPED_REG_OFS(XSI_ITC_OFFSET_OFS, itc_offset);
+	DEFINE_MAPPED_REG_OFS(XSI_ITC_LAST_OFS, itc_last);
 #endif /* CONFIG_XEN */
 }
diff --git a/arch/ia64/kernel/efi.c b/arch/ia64/kernel/efi.c
index efaff15d8cf1..7ef80e8161ce 100644
--- a/arch/ia64/kernel/efi.c
+++ b/arch/ia64/kernel/efi.c
@@ -456,6 +456,7 @@ efi_map_pal_code (void)
 		 GRANULEROUNDDOWN((unsigned long) pal_vaddr),
 		 pte_val(pfn_pte(__pa(pal_vaddr) >> PAGE_SHIFT, PAGE_KERNEL)),
 		 IA64_GRANULE_SHIFT);
+	paravirt_dv_serialize_data();
 	ia64_set_psr(psr);		/* restore psr */
 }
 
diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S
index 7e3382b06d56..8dc69669586a 100644
--- a/arch/ia64/kernel/entry.S
+++ b/arch/ia64/kernel/entry.S
@@ -736,7 +736,7 @@ GLOBAL_ENTRY(__paravirt_leave_syscall)
 __paravirt_work_processed_syscall:
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 	adds r2=PT(LOADRS)+16,r12
-(pUStk)	mov.m r22=ar.itc			// fetch time at leave
+	MOV_FROM_ITC(pUStk, p9, r22, r19)	// fetch time at leave
 	adds r18=TI_FLAGS+IA64_TASK_SIZE,r13
 	;;
 (p6)	ld4 r31=[r18]				// load current_thread_info()->flags
@@ -985,7 +985,7 @@ GLOBAL_ENTRY(__paravirt_leave_kernel)
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 	.pred.rel.mutex pUStk,pKStk
 	MOV_FROM_PSR(pKStk, r22, r29)	// M2 read PSR now that interrupts are disabled
-(pUStk)	mov.m r22=ar.itc	// M  fetch time at leave
+	MOV_FROM_ITC(pUStk, p9, r22, r29)	// M  fetch time at leave
 	nop.i 0
 	;;
 #else
diff --git a/arch/ia64/kernel/fsys.S b/arch/ia64/kernel/fsys.S
index c1625c7e1779..3567d54f8cee 100644
--- a/arch/ia64/kernel/fsys.S
+++ b/arch/ia64/kernel/fsys.S
@@ -25,6 +25,7 @@
 #include <asm/unistd.h>
 
 #include "entry.h"
+#include "paravirt_inst.h"
 
 /*
  * See Documentation/ia64/fsys.txt for details on fsyscalls.
@@ -279,7 +280,7 @@ ENTRY(fsys_gettimeofday)
 (p9)	cmp.eq p13,p0 = 0,r30	// if mmio_ptr, clear p13 jitter control
 	;;
 	.pred.rel.mutex p8,p9
-(p8)	mov r2 = ar.itc		// CPU_TIMER. 36 clocks latency!!!
+	MOV_FROM_ITC(p8, p6, r2, r10)	// CPU_TIMER. 36 clocks latency!!!
 (p9)	ld8 r2 = [r30]		// MMIO_TIMER. Could also have latency issues..
 (p13)	ld8 r25 = [r19]		// get itc_lastcycle value
 	ld8 r9 = [r22],IA64_TIMESPEC_TV_NSEC_OFFSET	// tv_sec
@@ -418,7 +419,7 @@ EX(.fail_efault, ld8 r14=[r33])			// r14 <- *set
 	mov r17=(1 << (SIGKILL - 1)) | (1 << (SIGSTOP - 1))
 	;;
 
-	rsm psr.i				// mask interrupt delivery
+	RSM_PSR_I(p0, r18, r19)			// mask interrupt delivery
 	mov ar.ccv=0
 	andcm r14=r14,r17			// filter out SIGKILL & SIGSTOP
 
@@ -491,7 +492,7 @@ EX(.fail_efault, ld8 r14=[r33])			// r14 <- *set
 #ifdef CONFIG_SMP
 	st4.rel [r31]=r0			// release the lock
 #endif
-	ssm psr.i
+	SSM_PSR_I(p0, p9, r31)
 	;;
 
 	srlz.d					// ensure psr.i is set again
@@ -513,7 +514,7 @@ EX(.fail_efault, (p15) st8 [r34]=r3)
 #ifdef CONFIG_SMP
 	st4.rel [r31]=r0			// release the lock
 #endif
-	ssm psr.i
+	SSM_PSR_I(p0, p9, r17)
 	;;
 	srlz.d
 	br.sptk.many fsys_fallback_syscall	// with signal pending, do the heavy-weight syscall
@@ -521,7 +522,7 @@ EX(.fail_efault, (p15) st8 [r34]=r3)
 #ifdef CONFIG_SMP
 .lock_contention:
 	/* Rather than spinning here, fall back on doing a heavy-weight syscall.  */
-	ssm psr.i
+	SSM_PSR_I(p0, p9, r17)
 	;;
 	srlz.d
 	br.sptk.many fsys_fallback_syscall
@@ -592,17 +593,17 @@ ENTRY(fsys_fallback_syscall)
 	adds r17=-1024,r15
 	movl r14=sys_call_table
 	;;
-	rsm psr.i
+	RSM_PSR_I(p0, r26, r27)
 	shladd r18=r17,3,r14
 	;;
 	ld8 r18=[r18]				// load normal (heavy-weight) syscall entry-point
-	mov r29=psr				// read psr (12 cyc load latency)
+	MOV_FROM_PSR(p0, r29, r26)		// read psr (12 cyc load latency)
 	mov r27=ar.rsc
 	mov r21=ar.fpsr
 	mov r26=ar.pfs
 END(fsys_fallback_syscall)
 	/* FALL THROUGH */
-GLOBAL_ENTRY(fsys_bubble_down)
+GLOBAL_ENTRY(paravirt_fsys_bubble_down)
 	.prologue
 	.altrp b6
 	.body
@@ -640,7 +641,7 @@ GLOBAL_ENTRY(fsys_bubble_down)
 	 *
 	 * PSR.BE : already is turned off in __kernel_syscall_via_epc()
 	 * PSR.AC : don't care (kernel normally turns PSR.AC on)
-	 * PSR.I  : already turned off by the time fsys_bubble_down gets
+	 * PSR.I  : already turned off by the time paravirt_fsys_bubble_down gets
 	 *	    invoked
 	 * PSR.DFL: always 0 (kernel never turns it on)
 	 * PSR.DFH: don't care --- kernel never touches f32-f127 on its own
@@ -650,7 +651,7 @@ GLOBAL_ENTRY(fsys_bubble_down)
 	 * PSR.DB : don't care --- kernel never enables kernel-level
 	 *	    breakpoints
 	 * PSR.TB : must be 0 already; if it wasn't zero on entry to
-	 *          __kernel_syscall_via_epc, the branch to fsys_bubble_down
+	 *          __kernel_syscall_via_epc, the branch to paravirt_fsys_bubble_down
 	 *          will trigger a taken branch; the taken-trap-handler then
 	 *          converts the syscall into a break-based system-call.
 	 */
@@ -683,7 +684,7 @@ GLOBAL_ENTRY(fsys_bubble_down)
 	;;
 	mov ar.rsc=0				// M2   set enforced lazy mode, pl 0, LE, loadrs=0
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	mov.m r30=ar.itc			// M    get cycle for accounting
+	MOV_FROM_ITC(p0, p6, r30, r23)		// M    get cycle for accounting
 #else
 	nop.m 0
 #endif
@@ -734,21 +735,21 @@ GLOBAL_ENTRY(fsys_bubble_down)
 	mov rp=r14				// I0   set the real return addr
 	and r3=_TIF_SYSCALL_TRACEAUDIT,r3	// A
 	;;
-	ssm psr.i				// M2   we're on kernel stacks now, reenable irqs
+	SSM_PSR_I(p0, p6, r22)			// M2   we're on kernel stacks now, reenable irqs
 	cmp.eq p8,p0=r3,r0			// A
 (p10)	br.cond.spnt.many ia64_ret_from_syscall	// B    return if bad call-frame or r15 is a NaT
 
 	nop.m 0
 (p8)	br.call.sptk.many b6=b6			// B    (ignore return address)
 	br.cond.spnt ia64_trace_syscall		// B
-END(fsys_bubble_down)
+END(paravirt_fsys_bubble_down)
 
 	.rodata
 	.align 8
-	.globl fsyscall_table
+	.globl paravirt_fsyscall_table
 
-	data8 fsys_bubble_down
-fsyscall_table:
+	data8 paravirt_fsys_bubble_down
+paravirt_fsyscall_table:
 	data8 fsys_ni_syscall
 	data8 0				// exit			// 1025
 	data8 0				// read
@@ -1033,4 +1034,4 @@ fsyscall_table:
 
 	// fill in zeros for the remaining entries
 	.zero:
-	.space fsyscall_table + 8*NR_syscalls - .zero, 0
+	.space paravirt_fsyscall_table + 8*NR_syscalls - .zero, 0
diff --git a/arch/ia64/kernel/gate.S b/arch/ia64/kernel/gate.S
index 74b1ccce4e84..cf5e0a105e16 100644
--- a/arch/ia64/kernel/gate.S
+++ b/arch/ia64/kernel/gate.S
@@ -13,6 +13,7 @@
 #include <asm/sigcontext.h>
 #include <asm/system.h>
 #include <asm/unistd.h>
+#include "paravirt_inst.h"
 
 /*
  * We can't easily refer to symbols inside the kernel.  To avoid full runtime relocation,
@@ -48,87 +49,6 @@ GLOBAL_ENTRY(__kernel_syscall_via_break)
 }
 END(__kernel_syscall_via_break)
 
-/*
- * On entry:
- *	r11 = saved ar.pfs
- *	r15 = system call #
- *	b0  = saved return address
- *	b6  = return address
- * On exit:
- *	r11 = saved ar.pfs
- *	r15 = system call #
- *	b0  = saved return address
- *	all other "scratch" registers:	undefined
- *	all "preserved" registers:	same as on entry
- */
-
-GLOBAL_ENTRY(__kernel_syscall_via_epc)
-	.prologue
-	.altrp b6
-	.body
-{
-	/*
-	 * Note: the kernel cannot assume that the first two instructions in this
-	 * bundle get executed.  The remaining code must be safe even if
-	 * they do not get executed.
-	 */
-	adds r17=-1024,r15			// A
-	mov r10=0				// A    default to successful syscall execution
-	epc					// B	causes split-issue
-}
-	;;
-	rsm psr.be | psr.i			// M2 (5 cyc to srlz.d)
-	LOAD_FSYSCALL_TABLE(r14)		// X
-	;;
-	mov r16=IA64_KR(CURRENT)		// M2 (12 cyc)
-	shladd r18=r17,3,r14			// A
-	mov r19=NR_syscalls-1			// A
-	;;
-	lfetch [r18]				// M0|1
-	mov r29=psr				// M2 (12 cyc)
-	// If r17 is a NaT, p6 will be zero
-	cmp.geu p6,p7=r19,r17			// A    (sysnr > 0 && sysnr < 1024+NR_syscalls)?
-	;;
-	mov r21=ar.fpsr				// M2 (12 cyc)
-	tnat.nz p10,p9=r15			// I0
-	mov.i r26=ar.pfs			// I0 (would stall anyhow due to srlz.d...)
-	;;
-	srlz.d					// M0 (forces split-issue) ensure PSR.BE==0
-(p6)	ld8 r18=[r18]				// M0|1
-	nop.i 0
-	;;
-	nop.m 0
-(p6)	tbit.z.unc p8,p0=r18,0			// I0 (dual-issues with "mov b7=r18"!)
-	nop.i 0
-	;;
-(p8)	ssm psr.i
-(p6)	mov b7=r18				// I0
-(p8)	br.dptk.many b7				// B
-
-	mov r27=ar.rsc				// M2 (12 cyc)
-/*
- * brl.cond doesn't work as intended because the linker would convert this branch
- * into a branch to a PLT.  Perhaps there will be a way to avoid this with some
- * future version of the linker.  In the meantime, we just use an indirect branch
- * instead.
- */
-#ifdef CONFIG_ITANIUM
-(p6)	add r14=-8,r14				// r14 <- addr of fsys_bubble_down entry
-	;;
-(p6)	ld8 r14=[r14]				// r14 <- fsys_bubble_down
-	;;
-(p6)	mov b7=r14
-(p6)	br.sptk.many b7
-#else
-	BRL_COND_FSYS_BUBBLE_DOWN(p6)
-#endif
-	ssm psr.i
-	mov r10=-1
-(p10)	mov r8=EINVAL
-(p9)	mov r8=ENOSYS
-	FSYS_RETURN
-END(__kernel_syscall_via_epc)
-
 #	define ARG0_OFF		(16 + IA64_SIGFRAME_ARG0_OFFSET)
 #	define ARG1_OFF		(16 + IA64_SIGFRAME_ARG1_OFFSET)
 #	define ARG2_OFF		(16 + IA64_SIGFRAME_ARG2_OFFSET)
@@ -374,3 +294,92 @@ restore_rbs:
 	// invala not necessary as that will happen when returning to user-mode
 	br.cond.sptk back_from_restore_rbs
 END(__kernel_sigtramp)
+
+/*
+ * On entry:
+ *	r11 = saved ar.pfs
+ *	r15 = system call #
+ *	b0  = saved return address
+ *	b6  = return address
+ * On exit:
+ *	r11 = saved ar.pfs
+ *	r15 = system call #
+ *	b0  = saved return address
+ *	all other "scratch" registers:	undefined
+ *	all "preserved" registers:	same as on entry
+ */
+
+GLOBAL_ENTRY(__kernel_syscall_via_epc)
+	.prologue
+	.altrp b6
+	.body
+{
+	/*
+	 * Note: the kernel cannot assume that the first two instructions in this
+	 * bundle get executed.  The remaining code must be safe even if
+	 * they do not get executed.
+	 */
+	adds r17=-1024,r15			// A
+	mov r10=0				// A    default to successful syscall execution
+	epc					// B	causes split-issue
+}
+	;;
+	RSM_PSR_BE_I(r20, r22)			// M2 (5 cyc to srlz.d)
+	LOAD_FSYSCALL_TABLE(r14)		// X
+	;;
+	mov r16=IA64_KR(CURRENT)		// M2 (12 cyc)
+	shladd r18=r17,3,r14			// A
+	mov r19=NR_syscalls-1			// A
+	;;
+	lfetch [r18]				// M0|1
+	MOV_FROM_PSR(p0, r29, r8)		// M2 (12 cyc)
+	// If r17 is a NaT, p6 will be zero
+	cmp.geu p6,p7=r19,r17			// A    (sysnr > 0 && sysnr < 1024+NR_syscalls)?
+	;;
+	mov r21=ar.fpsr				// M2 (12 cyc)
+	tnat.nz p10,p9=r15			// I0
+	mov.i r26=ar.pfs			// I0 (would stall anyhow due to srlz.d...)
+	;;
+	srlz.d					// M0 (forces split-issue) ensure PSR.BE==0
+(p6)	ld8 r18=[r18]				// M0|1
+	nop.i 0
+	;;
+	nop.m 0
+(p6)	tbit.z.unc p8,p0=r18,0			// I0 (dual-issues with "mov b7=r18"!)
+	nop.i 0
+	;;
+	SSM_PSR_I(p8, p14, r25)
+(p6)	mov b7=r18				// I0
+(p8)	br.dptk.many b7				// B
+
+	mov r27=ar.rsc				// M2 (12 cyc)
+/*
+ * brl.cond doesn't work as intended because the linker would convert this branch
+ * into a branch to a PLT.  Perhaps there will be a way to avoid this with some
+ * future version of the linker.  In the meantime, we just use an indirect branch
+ * instead.
+ */
+#ifdef CONFIG_ITANIUM
+(p6)	add r14=-8,r14				// r14 <- addr of fsys_bubble_down entry
+	;;
+(p6)	ld8 r14=[r14]				// r14 <- fsys_bubble_down
+	;;
+(p6)	mov b7=r14
+(p6)	br.sptk.many b7
+#else
+	BRL_COND_FSYS_BUBBLE_DOWN(p6)
+#endif
+	SSM_PSR_I(p0, p14, r10)
+	mov r10=-1
+(p10)	mov r8=EINVAL
+(p9)	mov r8=ENOSYS
+	FSYS_RETURN
+
+#ifdef CONFIG_PARAVIRT
+	/*
+	 * padd to make the size of this symbol constant
+	 * independent of paravirtualization.
+	 */
+	.align PAGE_SIZE / 8
+#endif
+END(__kernel_syscall_via_epc)
diff --git a/arch/ia64/kernel/gate.lds.S b/arch/ia64/kernel/gate.lds.S
index 3cb1abc00e24..88c64ed47c36 100644
--- a/arch/ia64/kernel/gate.lds.S
+++ b/arch/ia64/kernel/gate.lds.S
@@ -7,6 +7,7 @@
 
 
 #include <asm/system.h>
+#include "paravirt_patchlist.h"
 
 SECTIONS
 {
@@ -33,21 +34,21 @@ SECTIONS
 	. = GATE_ADDR + 0x600;
 
 	.data.patch		: {
-		__start_gate_mckinley_e9_patchlist = .;
+		__paravirt_start_gate_mckinley_e9_patchlist = .;
 		*(.data.patch.mckinley_e9)
-		__end_gate_mckinley_e9_patchlist = .;
+		__paravirt_end_gate_mckinley_e9_patchlist = .;
 
-		__start_gate_vtop_patchlist = .;
+		__paravirt_start_gate_vtop_patchlist = .;
 		*(.data.patch.vtop)
-		__end_gate_vtop_patchlist = .;
+		__paravirt_end_gate_vtop_patchlist = .;
 
-		__start_gate_fsyscall_patchlist = .;
+		__paravirt_start_gate_fsyscall_patchlist = .;
 		*(.data.patch.fsyscall_table)
-		__end_gate_fsyscall_patchlist = .;
+		__paravirt_end_gate_fsyscall_patchlist = .;
 
-		__start_gate_brl_fsys_bubble_down_patchlist = .;
+		__paravirt_start_gate_brl_fsys_bubble_down_patchlist = .;
 		*(.data.patch.brl_fsys_bubble_down)
-		__end_gate_brl_fsys_bubble_down_patchlist = .;
+		__paravirt_end_gate_brl_fsys_bubble_down_patchlist = .;
 	}						:readable
 
 	.IA_64.unwind_info	: { *(.IA_64.unwind_info*) }
diff --git a/arch/ia64/kernel/head.S b/arch/ia64/kernel/head.S
index 59301c472800..23f846de62d5 100644
--- a/arch/ia64/kernel/head.S
+++ b/arch/ia64/kernel/head.S
@@ -1050,7 +1050,7 @@ END(ia64_delay_loop)
  * except that the multiplication and the shift are done with 128-bit
  * intermediate precision so that we can produce a full 64-bit result.
  */
-GLOBAL_ENTRY(sched_clock)
+GLOBAL_ENTRY(ia64_native_sched_clock)
 	addl r8=THIS_CPU(cpu_info) + IA64_CPUINFO_NSEC_PER_CYC_OFFSET,r0
 	mov.m r9=ar.itc		// fetch cycle-counter				(35 cyc)
 	;;
@@ -1066,7 +1066,13 @@ GLOBAL_ENTRY(sched_clock)
 	;;
 	shrp r8=r9,r8,IA64_NSEC_PER_CYC_SHIFT
 	br.ret.sptk.many rp
-END(sched_clock)
+END(ia64_native_sched_clock)
+#ifndef CONFIG_PARAVIRT
+	//unsigned long long
+	//sched_clock(void) __attribute__((alias("ia64_native_sched_clock")));
+	.global sched_clock
+sched_clock = ia64_native_sched_clock
+#endif
 
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
 GLOBAL_ENTRY(cycle_to_cputime)
diff --git a/arch/ia64/kernel/ivt.S b/arch/ia64/kernel/ivt.S
index f675d8e33853..ec9a5fdfa1b9 100644
--- a/arch/ia64/kernel/ivt.S
+++ b/arch/ia64/kernel/ivt.S
@@ -804,7 +804,7 @@ ENTRY(break_fault)
 ///////////////////////////////////////////////////////////////////////
 	st1 [r16]=r0				// M2|3 clear current->thread.on_ustack flag
 #ifdef CONFIG_VIRT_CPU_ACCOUNTING
-	mov.m r30=ar.itc			// M    get cycle for accounting
+	MOV_FROM_ITC(p0, p14, r30, r18)		// M    get cycle for accounting
 #else
 	mov b6=r30				// I0   setup syscall handler branch reg early
 #endif
diff --git a/arch/ia64/kernel/mca.c b/arch/ia64/kernel/mca.c
index bab1de2d2f6a..8f33a8840422 100644
--- a/arch/ia64/kernel/mca.c
+++ b/arch/ia64/kernel/mca.c
@@ -1456,9 +1456,9 @@ ia64_mca_cmc_int_caller(int cmc_irq, void *arg)
 
 	ia64_mca_cmc_int_handler(cmc_irq, arg);
 
-	for (++cpuid ; cpuid < NR_CPUS && !cpu_online(cpuid) ; cpuid++);
+	cpuid = cpumask_next(cpuid+1, cpu_online_mask);
 
-	if (cpuid < NR_CPUS) {
+	if (cpuid < nr_cpu_ids) {
 		platform_send_ipi(cpuid, IA64_CMCP_VECTOR, IA64_IPI_DM_INT, 0);
 	} else {
 		/* If no log record, switch out of polling mode */
@@ -1525,7 +1525,7 @@ ia64_mca_cpe_int_caller(int cpe_irq, void *arg)
 
 	ia64_mca_cpe_int_handler(cpe_irq, arg);
 
-	for (++cpuid ; cpuid < NR_CPUS && !cpu_online(cpuid) ; cpuid++);
+	cpuid = cpumask_next(cpuid+1, cpu_online_mask);
 
 	if (cpuid < NR_CPUS) {
 		platform_send_ipi(cpuid, IA64_CPEP_VECTOR, IA64_IPI_DM_INT, 0);
diff --git a/arch/ia64/kernel/module.c b/arch/ia64/kernel/module.c
index aaa7d901521f..da3b0cf495a3 100644
--- a/arch/ia64/kernel/module.c
+++ b/arch/ia64/kernel/module.c
@@ -446,6 +446,14 @@ module_frob_arch_sections (Elf_Ehdr *ehdr, Elf_Shdr *sechdrs, char *secstrings,
 			mod->arch.opd = s;
 		else if (strcmp(".IA_64.unwind", secstrings + s->sh_name) == 0)
 			mod->arch.unwind = s;
+#ifdef CONFIG_PARAVIRT
+		else if (strcmp(".paravirt_bundles",
+				secstrings + s->sh_name) == 0)
+			mod->arch.paravirt_bundles = s;
+		else if (strcmp(".paravirt_insts",
+				secstrings + s->sh_name) == 0)
+			mod->arch.paravirt_insts = s;
+#endif
 
 	if (!mod->arch.core_plt || !mod->arch.init_plt || !mod->arch.got || !mod->arch.opd) {
 		printk(KERN_ERR "%s: sections missing\n", mod->name);
@@ -525,8 +533,7 @@ get_ltoff (struct module *mod, uint64_t value, int *okp)
 			goto found;
 
 	/* Not enough GOT entries? */
-	if (e >= (struct got_entry *) (mod->arch.got->sh_addr + mod->arch.got->sh_size))
-		BUG();
+	BUG_ON(e >= (struct got_entry *) (mod->arch.got->sh_addr + mod->arch.got->sh_size));
 
 	e->val = value;
 	++mod->arch.next_got_entry;
@@ -921,6 +928,30 @@ module_finalize (const Elf_Ehdr *hdr, const Elf_Shdr *sechdrs, struct module *mo
 	DEBUGP("%s: init: entry=%p\n", __func__, mod->init);
 	if (mod->arch.unwind)
 		register_unwind_table(mod);
+#ifdef CONFIG_PARAVIRT
+        if (mod->arch.paravirt_bundles) {
+                struct paravirt_patch_site_bundle *start =
+                        (struct paravirt_patch_site_bundle *)
+                        mod->arch.paravirt_bundles->sh_addr;
+                struct paravirt_patch_site_bundle *end =
+                        (struct paravirt_patch_site_bundle *)
+                        (mod->arch.paravirt_bundles->sh_addr +
+                         mod->arch.paravirt_bundles->sh_size);
+
+                paravirt_patch_apply_bundle(start, end);
+        }
+        if (mod->arch.paravirt_insts) {
+                struct paravirt_patch_site_inst *start =
+                        (struct paravirt_patch_site_inst *)
+                        mod->arch.paravirt_insts->sh_addr;
+                struct paravirt_patch_site_inst *end =
+                        (struct paravirt_patch_site_inst *)
+                        (mod->arch.paravirt_insts->sh_addr +
+                         mod->arch.paravirt_insts->sh_size);
+
+                paravirt_patch_apply_inst(start, end);
+        }
+#endif
 	return 0;
 }
 
diff --git a/arch/ia64/kernel/paravirt.c b/arch/ia64/kernel/paravirt.c
index 9f14c16f6369..a21d7bb9c69c 100644
--- a/arch/ia64/kernel/paravirt.c
+++ b/arch/ia64/kernel/paravirt.c
@@ -46,13 +46,23 @@ struct pv_info pv_info = {
  * initialization hooks.
  */
 
-struct pv_init_ops pv_init_ops;
+static void __init
+ia64_native_patch_branch(unsigned long tag, unsigned long type);
+
+struct pv_init_ops pv_init_ops =
+{
+#ifdef ASM_SUPPORTED
+	.patch_bundle = ia64_native_patch_bundle,
+#endif
+	.patch_branch = ia64_native_patch_branch,
+};
 
 /***************************************************************************
  * pv_cpu_ops
  * intrinsics hooks.
  */
 
+#ifndef ASM_SUPPORTED
 /* ia64_native_xxx are macros so that we have to make them real functions */
 
 #define DEFINE_VOID_FUNC1(name)					\
@@ -60,7 +70,14 @@ struct pv_init_ops pv_init_ops;
 	ia64_native_ ## name ## _func(unsigned long arg)	\
 	{							\
 		ia64_native_ ## name(arg);			\
-	}							\
+	}
+
+#define DEFINE_VOID_FUNC1_VOID(name)				\
+	static void						\
+	ia64_native_ ## name ## _func(void *arg)		\
+	{							\
+		ia64_native_ ## name(arg);			\
+	}
 
 #define DEFINE_VOID_FUNC2(name)					\
 	static void						\
@@ -68,7 +85,7 @@ struct pv_init_ops pv_init_ops;
 				      unsigned long arg1)	\
 	{							\
 		ia64_native_ ## name(arg0, arg1);		\
-	}							\
+	}
 
 #define DEFINE_FUNC0(name)			\
 	static unsigned long			\
@@ -84,7 +101,7 @@ struct pv_init_ops pv_init_ops;
 		return ia64_native_ ## name(arg);	\
 	}						\
 
-DEFINE_VOID_FUNC1(fc);
+DEFINE_VOID_FUNC1_VOID(fc);
 DEFINE_VOID_FUNC1(intrin_local_irq_restore);
 
 DEFINE_VOID_FUNC2(ptcga);
@@ -274,6 +291,266 @@ ia64_native_setreg_func(int regnum, unsigned long val)
 		break;
 	}
 }
+#else
+
+#define __DEFINE_FUNC(name, code)					\
+	extern const char ia64_native_ ## name ## _direct_start[];	\
+	extern const char ia64_native_ ## name ## _direct_end[];	\
+	asm (".align 32\n"						\
+	     ".proc ia64_native_" #name "_func\n"			\
+	     "ia64_native_" #name "_func:\n"				\
+	     "ia64_native_" #name "_direct_start:\n"			\
+	     code							\
+	     "ia64_native_" #name "_direct_end:\n"			\
+	     "br.cond.sptk.many b6\n"					\
+	     ".endp ia64_native_" #name "_func\n")
+
+#define DEFINE_VOID_FUNC0(name, code)				\
+	extern void						\
+	ia64_native_ ## name ## _func(void);			\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_VOID_FUNC1(name, code)				\
+	extern void						\
+	ia64_native_ ## name ## _func(unsigned long arg);	\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_VOID_FUNC1_VOID(name, code)			\
+	extern void						\
+	ia64_native_ ## name ## _func(void *arg);		\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_VOID_FUNC2(name, code)				\
+	extern void						\
+	ia64_native_ ## name ## _func(unsigned long arg0,	\
+				      unsigned long arg1);	\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_FUNC0(name, code)		\
+	extern unsigned long			\
+	ia64_native_ ## name ## _func(void);	\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_FUNC1(name, type, code)			\
+	extern unsigned long				\
+	ia64_native_ ## name ## _func(type arg);	\
+	__DEFINE_FUNC(name, code)
+
+DEFINE_VOID_FUNC1_VOID(fc,
+		       "fc r8\n");
+DEFINE_VOID_FUNC1(intrin_local_irq_restore,
+		  ";;\n"
+		  "     cmp.ne p6, p7 = r8, r0\n"
+		  ";;\n"
+		  "(p6) ssm psr.i\n"
+		  "(p7) rsm psr.i\n"
+		  ";;\n"
+		  "(p6) srlz.d\n");
+
+DEFINE_VOID_FUNC2(ptcga,
+		  "ptc.ga r8, r9\n");
+DEFINE_VOID_FUNC2(set_rr,
+		  "mov rr[r8] = r9\n");
+
+/* ia64_native_getreg(_IA64_REG_PSR) & IA64_PSR_I */
+DEFINE_FUNC0(get_psr_i,
+	     "mov r2 = " __stringify(1 << IA64_PSR_I_BIT) "\n"
+	     "mov r8 = psr\n"
+	     ";;\n"
+	     "and r8 = r2, r8\n");
+
+DEFINE_FUNC1(thash, unsigned long,
+	     "thash r8 = r8\n");
+DEFINE_FUNC1(get_cpuid, int,
+	     "mov r8 = cpuid[r8]\n");
+DEFINE_FUNC1(get_pmd, int,
+	     "mov r8 = pmd[r8]\n");
+DEFINE_FUNC1(get_rr, unsigned long,
+	     "mov r8 = rr[r8]\n");
+
+DEFINE_VOID_FUNC0(ssm_i,
+		  "ssm psr.i\n");
+DEFINE_VOID_FUNC0(rsm_i,
+		  "rsm psr.i\n");
+
+extern void
+ia64_native_set_rr0_to_rr4_func(unsigned long val0, unsigned long val1,
+				unsigned long val2, unsigned long val3,
+				unsigned long val4);
+__DEFINE_FUNC(set_rr0_to_rr4,
+	      "mov rr[r0] = r8\n"
+	      "movl r2 = 0x2000000000000000\n"
+	      ";;\n"
+	      "mov rr[r2] = r9\n"
+	      "shl r3 = r2, 1\n"	/* movl r3 = 0x4000000000000000 */
+	      ";;\n"
+	      "add r2 = r2, r3\n"	/* movl r2 = 0x6000000000000000 */
+	      "mov rr[r3] = r10\n"
+	      ";;\n"
+	      "mov rr[r2] = r11\n"
+	      "shl r3 = r3, 1\n"	/* movl r3 = 0x8000000000000000 */
+	      ";;\n"
+	      "mov rr[r3] = r14\n");
+
+extern unsigned long ia64_native_getreg_func(int regnum);
+asm(".global ia64_native_getreg_func\n");
+#define __DEFINE_GET_REG(id, reg)			\
+	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"	\
+	";;\n"						\
+	"cmp.eq p6, p0 = r2, r8\n"			\
+	";;\n"						\
+	"(p6) mov r8 = " #reg "\n"			\
+	"(p6) br.cond.sptk.many b6\n"			\
+	";;\n"
+#define __DEFINE_GET_AR(id, reg)	__DEFINE_GET_REG(AR_ ## id, ar.reg)
+#define __DEFINE_GET_CR(id, reg)	__DEFINE_GET_REG(CR_ ## id, cr.reg)
+
+__DEFINE_FUNC(getreg,
+	      __DEFINE_GET_REG(GP, gp)
+	      /*__DEFINE_GET_REG(IP, ip)*/ /* returned ip value shouldn't be constant */
+	      __DEFINE_GET_REG(PSR, psr)
+	      __DEFINE_GET_REG(TP, tp)
+	      __DEFINE_GET_REG(SP, sp)
+
+	      __DEFINE_GET_REG(AR_KR0, ar0)
+	      __DEFINE_GET_REG(AR_KR1, ar1)
+	      __DEFINE_GET_REG(AR_KR2, ar2)
+	      __DEFINE_GET_REG(AR_KR3, ar3)
+	      __DEFINE_GET_REG(AR_KR4, ar4)
+	      __DEFINE_GET_REG(AR_KR5, ar5)
+	      __DEFINE_GET_REG(AR_KR6, ar6)
+	      __DEFINE_GET_REG(AR_KR7, ar7)
+	      __DEFINE_GET_AR(RSC, rsc)
+	      __DEFINE_GET_AR(BSP, bsp)
+	      __DEFINE_GET_AR(BSPSTORE, bspstore)
+	      __DEFINE_GET_AR(RNAT, rnat)
+	      __DEFINE_GET_AR(FCR, fcr)
+	      __DEFINE_GET_AR(EFLAG, eflag)
+	      __DEFINE_GET_AR(CSD, csd)
+	      __DEFINE_GET_AR(SSD, ssd)
+	      __DEFINE_GET_REG(AR_CFLAG, ar27)
+	      __DEFINE_GET_AR(FSR, fsr)
+	      __DEFINE_GET_AR(FIR, fir)
+	      __DEFINE_GET_AR(FDR, fdr)
+	      __DEFINE_GET_AR(CCV, ccv)
+	      __DEFINE_GET_AR(UNAT, unat)
+	      __DEFINE_GET_AR(FPSR, fpsr)
+	      __DEFINE_GET_AR(ITC, itc)
+	      __DEFINE_GET_AR(PFS, pfs)
+	      __DEFINE_GET_AR(LC, lc)
+	      __DEFINE_GET_AR(EC, ec)
+
+	      __DEFINE_GET_CR(DCR, dcr)
+	      __DEFINE_GET_CR(ITM, itm)
+	      __DEFINE_GET_CR(IVA, iva)
+	      __DEFINE_GET_CR(PTA, pta)
+	      __DEFINE_GET_CR(IPSR, ipsr)
+	      __DEFINE_GET_CR(ISR, isr)
+	      __DEFINE_GET_CR(IIP, iip)
+	      __DEFINE_GET_CR(IFA, ifa)
+	      __DEFINE_GET_CR(ITIR, itir)
+	      __DEFINE_GET_CR(IIPA, iipa)
+	      __DEFINE_GET_CR(IFS, ifs)
+	      __DEFINE_GET_CR(IIM, iim)
+	      __DEFINE_GET_CR(IHA, iha)
+	      __DEFINE_GET_CR(LID, lid)
+	      __DEFINE_GET_CR(IVR, ivr)
+	      __DEFINE_GET_CR(TPR, tpr)
+	      __DEFINE_GET_CR(EOI, eoi)
+	      __DEFINE_GET_CR(IRR0, irr0)
+	      __DEFINE_GET_CR(IRR1, irr1)
+	      __DEFINE_GET_CR(IRR2, irr2)
+	      __DEFINE_GET_CR(IRR3, irr3)
+	      __DEFINE_GET_CR(ITV, itv)
+	      __DEFINE_GET_CR(PMV, pmv)
+	      __DEFINE_GET_CR(CMCV, cmcv)
+	      __DEFINE_GET_CR(LRR0, lrr0)
+	      __DEFINE_GET_CR(LRR1, lrr1)
+
+	      "mov r8 = -1\n"	/* unsupported case */
+	);
+
+extern void ia64_native_setreg_func(int regnum, unsigned long val);
+asm(".global ia64_native_setreg_func\n");
+#define __DEFINE_SET_REG(id, reg)			\
+	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"	\
+	";;\n"						\
+	"cmp.eq p6, p0 = r2, r9\n"			\
+	";;\n"						\
+	"(p6) mov " #reg " = r8\n"			\
+	"(p6) br.cond.sptk.many b6\n"			\
+	";;\n"
+#define __DEFINE_SET_AR(id, reg)	__DEFINE_SET_REG(AR_ ## id, ar.reg)
+#define __DEFINE_SET_CR(id, reg)	__DEFINE_SET_REG(CR_ ## id, cr.reg)
+__DEFINE_FUNC(setreg,
+	      "mov r2 = " __stringify(_IA64_REG_PSR_L) "\n"
+	      ";;\n"
+	      "cmp.eq p6, p0 = r2, r9\n"
+	      ";;\n"
+	      "(p6) mov psr.l = r8\n"
+#ifdef HAVE_SERIALIZE_DIRECTIVE
+	      ".serialize.data\n"
+#endif
+	      "(p6) br.cond.sptk.many b6\n"
+	      __DEFINE_SET_REG(GP, gp)
+	      __DEFINE_SET_REG(SP, sp)
+
+	      __DEFINE_SET_REG(AR_KR0, ar0)
+	      __DEFINE_SET_REG(AR_KR1, ar1)
+	      __DEFINE_SET_REG(AR_KR2, ar2)
+	      __DEFINE_SET_REG(AR_KR3, ar3)
+	      __DEFINE_SET_REG(AR_KR4, ar4)
+	      __DEFINE_SET_REG(AR_KR5, ar5)
+	      __DEFINE_SET_REG(AR_KR6, ar6)
+	      __DEFINE_SET_REG(AR_KR7, ar7)
+	      __DEFINE_SET_AR(RSC, rsc)
+	      __DEFINE_SET_AR(BSP, bsp)
+	      __DEFINE_SET_AR(BSPSTORE, bspstore)
+	      __DEFINE_SET_AR(RNAT, rnat)
+	      __DEFINE_SET_AR(FCR, fcr)
+	      __DEFINE_SET_AR(EFLAG, eflag)
+	      __DEFINE_SET_AR(CSD, csd)
+	      __DEFINE_SET_AR(SSD, ssd)
+	      __DEFINE_SET_REG(AR_CFLAG, ar27)
+	      __DEFINE_SET_AR(FSR, fsr)
+	      __DEFINE_SET_AR(FIR, fir)
+	      __DEFINE_SET_AR(FDR, fdr)
+	      __DEFINE_SET_AR(CCV, ccv)
+	      __DEFINE_SET_AR(UNAT, unat)
+	      __DEFINE_SET_AR(FPSR, fpsr)
+	      __DEFINE_SET_AR(ITC, itc)
+	      __DEFINE_SET_AR(PFS, pfs)
+	      __DEFINE_SET_AR(LC, lc)
+	      __DEFINE_SET_AR(EC, ec)
+
+	      __DEFINE_SET_CR(DCR, dcr)
+	      __DEFINE_SET_CR(ITM, itm)
+	      __DEFINE_SET_CR(IVA, iva)
+	      __DEFINE_SET_CR(PTA, pta)
+	      __DEFINE_SET_CR(IPSR, ipsr)
+	      __DEFINE_SET_CR(ISR, isr)
+	      __DEFINE_SET_CR(IIP, iip)
+	      __DEFINE_SET_CR(IFA, ifa)
+	      __DEFINE_SET_CR(ITIR, itir)
+	      __DEFINE_SET_CR(IIPA, iipa)
+	      __DEFINE_SET_CR(IFS, ifs)
+	      __DEFINE_SET_CR(IIM, iim)
+	      __DEFINE_SET_CR(IHA, iha)
+	      __DEFINE_SET_CR(LID, lid)
+	      __DEFINE_SET_CR(IVR, ivr)
+	      __DEFINE_SET_CR(TPR, tpr)
+	      __DEFINE_SET_CR(EOI, eoi)
+	      __DEFINE_SET_CR(IRR0, irr0)
+	      __DEFINE_SET_CR(IRR1, irr1)
+	      __DEFINE_SET_CR(IRR2, irr2)
+	      __DEFINE_SET_CR(IRR3, irr3)
+	      __DEFINE_SET_CR(ITV, itv)
+	      __DEFINE_SET_CR(PMV, pmv)
+	      __DEFINE_SET_CR(CMCV, cmcv)
+	      __DEFINE_SET_CR(LRR0, lrr0)
+	      __DEFINE_SET_CR(LRR1, lrr1)
+	);
+#endif
 
 struct pv_cpu_ops pv_cpu_ops = {
 	.fc		= ia64_native_fc_func,
@@ -366,4 +643,258 @@ ia64_native_do_steal_accounting(unsigned long *new_itm)
 
 struct pv_time_ops pv_time_ops = {
 	.do_steal_accounting = ia64_native_do_steal_accounting,
+	.sched_clock = ia64_native_sched_clock,
+};
+
+/***************************************************************************
+ * binary pacthing
+ * pv_init_ops.patch_bundle
+ */
+
+#ifdef ASM_SUPPORTED
+#define IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg)	\
+	__DEFINE_FUNC(get_ ## name,			\
+		      ";;\n"				\
+		      "mov r8 = " #reg "\n"		\
+		      ";;\n")
+
+#define IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg)	\
+	__DEFINE_FUNC(set_ ## name,			\
+		      ";;\n"				\
+		      "mov " #reg " = r8\n"		\
+		      ";;\n")
+
+#define IA64_NATIVE_PATCH_DEFINE_REG(name, reg)		\
+	IA64_NATIVE_PATCH_DEFINE_GET_REG(name, reg);	\
+	IA64_NATIVE_PATCH_DEFINE_SET_REG(name, reg)	\
+
+#define IA64_NATIVE_PATCH_DEFINE_AR(name, reg)			\
+	IA64_NATIVE_PATCH_DEFINE_REG(ar_ ## name, ar.reg)
+
+#define IA64_NATIVE_PATCH_DEFINE_CR(name, reg)			\
+	IA64_NATIVE_PATCH_DEFINE_REG(cr_ ## name, cr.reg)
+
+
+IA64_NATIVE_PATCH_DEFINE_GET_REG(psr, psr);
+IA64_NATIVE_PATCH_DEFINE_GET_REG(tp, tp);
+
+/* IA64_NATIVE_PATCH_DEFINE_SET_REG(psr_l, psr.l); */
+__DEFINE_FUNC(set_psr_l,
+	      ";;\n"
+	      "mov psr.l = r8\n"
+#ifdef HAVE_SERIALIZE_DIRECTIVE
+	      ".serialize.data\n"
+#endif
+	      ";;\n");
+
+IA64_NATIVE_PATCH_DEFINE_REG(gp, gp);
+IA64_NATIVE_PATCH_DEFINE_REG(sp, sp);
+
+IA64_NATIVE_PATCH_DEFINE_REG(kr0, ar0);
+IA64_NATIVE_PATCH_DEFINE_REG(kr1, ar1);
+IA64_NATIVE_PATCH_DEFINE_REG(kr2, ar2);
+IA64_NATIVE_PATCH_DEFINE_REG(kr3, ar3);
+IA64_NATIVE_PATCH_DEFINE_REG(kr4, ar4);
+IA64_NATIVE_PATCH_DEFINE_REG(kr5, ar5);
+IA64_NATIVE_PATCH_DEFINE_REG(kr6, ar6);
+IA64_NATIVE_PATCH_DEFINE_REG(kr7, ar7);
+
+IA64_NATIVE_PATCH_DEFINE_AR(rsc, rsc);
+IA64_NATIVE_PATCH_DEFINE_AR(bsp, bsp);
+IA64_NATIVE_PATCH_DEFINE_AR(bspstore, bspstore);
+IA64_NATIVE_PATCH_DEFINE_AR(rnat, rnat);
+IA64_NATIVE_PATCH_DEFINE_AR(fcr, fcr);
+IA64_NATIVE_PATCH_DEFINE_AR(eflag, eflag);
+IA64_NATIVE_PATCH_DEFINE_AR(csd, csd);
+IA64_NATIVE_PATCH_DEFINE_AR(ssd, ssd);
+IA64_NATIVE_PATCH_DEFINE_REG(ar27, ar27);
+IA64_NATIVE_PATCH_DEFINE_AR(fsr, fsr);
+IA64_NATIVE_PATCH_DEFINE_AR(fir, fir);
+IA64_NATIVE_PATCH_DEFINE_AR(fdr, fdr);
+IA64_NATIVE_PATCH_DEFINE_AR(ccv, ccv);
+IA64_NATIVE_PATCH_DEFINE_AR(unat, unat);
+IA64_NATIVE_PATCH_DEFINE_AR(fpsr, fpsr);
+IA64_NATIVE_PATCH_DEFINE_AR(itc, itc);
+IA64_NATIVE_PATCH_DEFINE_AR(pfs, pfs);
+IA64_NATIVE_PATCH_DEFINE_AR(lc, lc);
+IA64_NATIVE_PATCH_DEFINE_AR(ec, ec);
+
+IA64_NATIVE_PATCH_DEFINE_CR(dcr, dcr);
+IA64_NATIVE_PATCH_DEFINE_CR(itm, itm);
+IA64_NATIVE_PATCH_DEFINE_CR(iva, iva);
+IA64_NATIVE_PATCH_DEFINE_CR(pta, pta);
+IA64_NATIVE_PATCH_DEFINE_CR(ipsr, ipsr);
+IA64_NATIVE_PATCH_DEFINE_CR(isr, isr);
+IA64_NATIVE_PATCH_DEFINE_CR(iip, iip);
+IA64_NATIVE_PATCH_DEFINE_CR(ifa, ifa);
+IA64_NATIVE_PATCH_DEFINE_CR(itir, itir);
+IA64_NATIVE_PATCH_DEFINE_CR(iipa, iipa);
+IA64_NATIVE_PATCH_DEFINE_CR(ifs, ifs);
+IA64_NATIVE_PATCH_DEFINE_CR(iim, iim);
+IA64_NATIVE_PATCH_DEFINE_CR(iha, iha);
+IA64_NATIVE_PATCH_DEFINE_CR(lid, lid);
+IA64_NATIVE_PATCH_DEFINE_CR(ivr, ivr);
+IA64_NATIVE_PATCH_DEFINE_CR(tpr, tpr);
+IA64_NATIVE_PATCH_DEFINE_CR(eoi, eoi);
+IA64_NATIVE_PATCH_DEFINE_CR(irr0, irr0);
+IA64_NATIVE_PATCH_DEFINE_CR(irr1, irr1);
+IA64_NATIVE_PATCH_DEFINE_CR(irr2, irr2);
+IA64_NATIVE_PATCH_DEFINE_CR(irr3, irr3);
+IA64_NATIVE_PATCH_DEFINE_CR(itv, itv);
+IA64_NATIVE_PATCH_DEFINE_CR(pmv, pmv);
+IA64_NATIVE_PATCH_DEFINE_CR(cmcv, cmcv);
+IA64_NATIVE_PATCH_DEFINE_CR(lrr0, lrr0);
+IA64_NATIVE_PATCH_DEFINE_CR(lrr1, lrr1);
+
+static const struct paravirt_patch_bundle_elem ia64_native_patch_bundle_elems[]
+__initdata_or_module =
+{
+#define IA64_NATIVE_PATCH_BUNDLE_ELEM(name, type)		\
+	{							\
+		(void*)ia64_native_ ## name ## _direct_start,	\
+		(void*)ia64_native_ ## name ## _direct_end,	\
+		PARAVIRT_PATCH_TYPE_ ## type,			\
+	}
+
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(fc, FC),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(thash, THASH),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_cpuid, GET_CPUID),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_pmd, GET_PMD),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(ptcga, PTCGA),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_rr, GET_RR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr, SET_RR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(set_rr0_to_rr4, SET_RR0_TO_RR4),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(ssm_i, SSM_I),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(rsm_i, RSM_I),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(get_psr_i, GET_PSR_I),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM(intrin_local_irq_restore,
+				      INTRIN_LOCAL_IRQ_RESTORE),
+
+#define IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg)			\
+	{								\
+		(void*)ia64_native_get_ ## name ## _direct_start,	\
+		(void*)ia64_native_get_ ## name ## _direct_end,		\
+		PARAVIRT_PATCH_TYPE_GETREG + _IA64_REG_ ## reg,		\
+	}
+
+#define IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg)			\
+	{								\
+		(void*)ia64_native_set_ ## name ## _direct_start,	\
+		(void*)ia64_native_set_ ## name ## _direct_end,		\
+		PARAVIRT_PATCH_TYPE_SETREG + _IA64_REG_ ## reg,		\
+	}
+
+#define IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(name, reg)		\
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(name, reg),	\
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(name, reg)		\
+
+#define IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(name, reg)		\
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar_ ## name, AR_ ## reg)
+
+#define IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(name, reg)		\
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(cr_ ## name, CR_ ## reg)
+
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(psr, PSR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_GETREG(tp, TP),
+
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_SETREG(psr_l, PSR_L),
+
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(gp, GP),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(sp, SP),
+
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr0, AR_KR0),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr1, AR_KR1),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr2, AR_KR2),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr3, AR_KR3),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr4, AR_KR4),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr5, AR_KR5),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr6, AR_KR6),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(kr7, AR_KR7),
+
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rsc, RSC),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bsp, BSP),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(bspstore, BSPSTORE),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(rnat, RNAT),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fcr, FCR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(eflag, EFLAG),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(csd, CSD),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ssd, SSD),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_REG(ar27, AR_CFLAG),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fsr, FSR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fir, FIR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fdr, FDR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ccv, CCV),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(unat, UNAT),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(fpsr, FPSR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(itc, ITC),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(pfs, PFS),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(lc, LC),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_AR(ec, EC),
+
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(dcr, DCR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itm, ITM),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iva, IVA),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pta, PTA),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ipsr, IPSR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(isr, ISR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iip, IIP),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifa, IFA),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itir, ITIR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iipa, IIPA),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ifs, IFS),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iim, IIM),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(iha, IHA),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lid, LID),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(ivr, IVR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(tpr, TPR),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(eoi, EOI),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr0, IRR0),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr1, IRR1),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr2, IRR2),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(irr3, IRR3),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(itv, ITV),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(pmv, PMV),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(cmcv, CMCV),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr0, LRR0),
+	IA64_NATIVE_PATCH_BUNDLE_ELEM_CR(lrr1, LRR1),
 };
+
+unsigned long __init_or_module
+ia64_native_patch_bundle(void *sbundle, void *ebundle, unsigned long type)
+{
+	const unsigned long nelems = sizeof(ia64_native_patch_bundle_elems) /
+		sizeof(ia64_native_patch_bundle_elems[0]);
+
+	return __paravirt_patch_apply_bundle(sbundle, ebundle, type,
+					      ia64_native_patch_bundle_elems,
+					      nelems, NULL);
+}
+#endif /* ASM_SUPPOTED */
+
+extern const char ia64_native_switch_to[];
+extern const char ia64_native_leave_syscall[];
+extern const char ia64_native_work_processed_syscall[];
+extern const char ia64_native_leave_kernel[];
+
+const struct paravirt_patch_branch_target ia64_native_branch_target[]
+__initconst = {
+#define PARAVIRT_BR_TARGET(name, type)			\
+	{						\
+		ia64_native_ ## name,			\
+		PARAVIRT_PATCH_TYPE_BR_ ## type,	\
+	}
+	PARAVIRT_BR_TARGET(switch_to, SWITCH_TO),
+	PARAVIRT_BR_TARGET(leave_syscall, LEAVE_SYSCALL),
+	PARAVIRT_BR_TARGET(work_processed_syscall, WORK_PROCESSED_SYSCALL),
+	PARAVIRT_BR_TARGET(leave_kernel, LEAVE_KERNEL),
+};
+
+static void __init
+ia64_native_patch_branch(unsigned long tag, unsigned long type)
+{
+	const unsigned long nelem =
+		sizeof(ia64_native_branch_target) /
+		sizeof(ia64_native_branch_target[0]);
+	__paravirt_patch_apply_branch(tag, type,
+				      ia64_native_branch_target, nelem);
+}
diff --git a/arch/ia64/kernel/paravirt_patch.c b/arch/ia64/kernel/paravirt_patch.c
new file mode 100644
index 000000000000..bfdfef1b1ffd
--- /dev/null
+++ b/arch/ia64/kernel/paravirt_patch.c
@@ -0,0 +1,514 @@
+/******************************************************************************
+ * linux/arch/ia64/xen/paravirt_patch.c
+ *
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <linux/init.h>
+#include <asm/intrinsics.h>
+#include <asm/kprobes.h>
+#include <asm/paravirt.h>
+#include <asm/paravirt_patch.h>
+
+typedef union ia64_inst {
+        struct {
+		unsigned long long qp : 6;
+		unsigned long long : 31;
+		unsigned long long opcode : 4;
+		unsigned long long reserved : 23;
+        } generic;
+        unsigned long long l;
+} ia64_inst_t;
+
+/*
+ * flush_icache_range() can't be used here.
+ * we are here before cpu_init() which initializes
+ * ia64_i_cache_stride_shift. flush_icache_range() uses it.
+ */
+void __init_or_module
+paravirt_flush_i_cache_range(const void *instr, unsigned long size)
+{
+	extern void paravirt_fc_i(const void *addr);
+	unsigned long i;
+
+	for (i = 0; i < size; i += sizeof(bundle_t))
+		paravirt_fc_i(instr + i);
+}
+
+bundle_t* __init_or_module
+paravirt_get_bundle(unsigned long tag)
+{
+	return (bundle_t *)(tag & ~3UL);
+}
+
+unsigned long __init_or_module
+paravirt_get_slot(unsigned long tag)
+{
+	return tag & 3UL;
+}
+
+unsigned long __init_or_module
+paravirt_get_num_inst(unsigned long stag, unsigned long etag)
+{
+	bundle_t *sbundle = paravirt_get_bundle(stag);
+	unsigned long sslot = paravirt_get_slot(stag);
+	bundle_t *ebundle = paravirt_get_bundle(etag);
+	unsigned long eslot = paravirt_get_slot(etag);
+
+	return (ebundle - sbundle) * 3 + eslot - sslot + 1;
+}
+
+unsigned long __init_or_module
+paravirt_get_next_tag(unsigned long tag)
+{
+	unsigned long slot = paravirt_get_slot(tag);
+
+	switch (slot) {
+	case 0:
+	case 1:
+		return tag + 1;
+	case 2: {
+		bundle_t *bundle = paravirt_get_bundle(tag);
+		return (unsigned long)(bundle + 1);
+	}
+	default:
+		BUG();
+	}
+	/* NOTREACHED */
+}
+
+ia64_inst_t __init_or_module
+paravirt_read_slot0(const bundle_t *bundle)
+{
+	ia64_inst_t inst;
+	inst.l = bundle->quad0.slot0;
+	return inst;
+}
+
+ia64_inst_t __init_or_module
+paravirt_read_slot1(const bundle_t *bundle)
+{
+	ia64_inst_t inst;
+	inst.l = bundle->quad0.slot1_p0 |
+		((unsigned long long)bundle->quad1.slot1_p1 << 18UL);
+	return inst;
+}
+
+ia64_inst_t __init_or_module
+paravirt_read_slot2(const bundle_t *bundle)
+{
+	ia64_inst_t inst;
+	inst.l = bundle->quad1.slot2;
+	return inst;
+}
+
+ia64_inst_t __init_or_module
+paravirt_read_inst(unsigned long tag)
+{
+	bundle_t *bundle = paravirt_get_bundle(tag);
+	unsigned long slot = paravirt_get_slot(tag);
+
+	switch (slot) {
+	case 0:
+		return paravirt_read_slot0(bundle);
+	case 1:
+		return paravirt_read_slot1(bundle);
+	case 2:
+		return paravirt_read_slot2(bundle);
+	default:
+		BUG();
+	}
+	/* NOTREACHED */
+}
+
+void __init_or_module
+paravirt_write_slot0(bundle_t *bundle, ia64_inst_t inst)
+{
+	bundle->quad0.slot0 = inst.l;
+}
+
+void __init_or_module
+paravirt_write_slot1(bundle_t *bundle, ia64_inst_t inst)
+{
+	bundle->quad0.slot1_p0 = inst.l;
+	bundle->quad1.slot1_p1 = inst.l >> 18UL;
+}
+
+void __init_or_module
+paravirt_write_slot2(bundle_t *bundle, ia64_inst_t inst)
+{
+	bundle->quad1.slot2 = inst.l;
+}
+
+void __init_or_module
+paravirt_write_inst(unsigned long tag, ia64_inst_t inst)
+{
+	bundle_t *bundle = paravirt_get_bundle(tag);
+	unsigned long slot = paravirt_get_slot(tag);
+
+	switch (slot) {
+	case 0:
+		paravirt_write_slot0(bundle, inst);
+		break;
+	case 1:
+		paravirt_write_slot1(bundle, inst);
+		break;
+	case 2:
+		paravirt_write_slot2(bundle, inst);
+		break;
+	default:
+		BUG();
+		break;
+	}
+	paravirt_flush_i_cache_range(bundle, sizeof(*bundle));
+}
+
+/* for debug */
+void
+paravirt_print_bundle(const bundle_t *bundle)
+{
+	const unsigned long *quad = (const unsigned long *)bundle;
+	ia64_inst_t slot0 = paravirt_read_slot0(bundle);
+	ia64_inst_t slot1 = paravirt_read_slot1(bundle);
+	ia64_inst_t slot2 = paravirt_read_slot2(bundle);
+
+	printk(KERN_DEBUG
+	       "bundle 0x%p 0x%016lx 0x%016lx\n", bundle, quad[0], quad[1]);
+	printk(KERN_DEBUG
+	       "bundle template 0x%x\n",
+	       bundle->quad0.template);
+	printk(KERN_DEBUG
+	       "slot0 0x%lx slot1_p0 0x%lx slot1_p1 0x%lx slot2 0x%lx\n",
+	       (unsigned long)bundle->quad0.slot0,
+	       (unsigned long)bundle->quad0.slot1_p0,
+	       (unsigned long)bundle->quad1.slot1_p1,
+	       (unsigned long)bundle->quad1.slot2);
+	printk(KERN_DEBUG
+	       "slot0 0x%016llx slot1 0x%016llx slot2 0x%016llx\n",
+	       slot0.l, slot1.l, slot2.l);
+}
+
+static int noreplace_paravirt __init_or_module = 0;
+
+static int __init setup_noreplace_paravirt(char *str)
+{
+	noreplace_paravirt = 1;
+	return 1;
+}
+__setup("noreplace-paravirt", setup_noreplace_paravirt);
+
+#ifdef ASM_SUPPORTED
+static void __init_or_module
+fill_nop_bundle(void *sbundle, void *ebundle)
+{
+	extern const char paravirt_nop_bundle[];
+	extern const unsigned long paravirt_nop_bundle_size;
+
+	void *bundle = sbundle;
+
+	BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
+	BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
+
+	while (bundle < ebundle) {
+		memcpy(bundle, paravirt_nop_bundle, paravirt_nop_bundle_size);
+
+		bundle += paravirt_nop_bundle_size;
+	}
+}
+
+/* helper function */
+unsigned long __init_or_module
+__paravirt_patch_apply_bundle(void *sbundle, void *ebundle, unsigned long type,
+			      const struct paravirt_patch_bundle_elem *elems,
+			      unsigned long nelems,
+			      const struct paravirt_patch_bundle_elem **found)
+{
+	unsigned long used = 0;
+	unsigned long i;
+
+	BUG_ON((((unsigned long)sbundle) % sizeof(bundle_t)) != 0);
+	BUG_ON((((unsigned long)ebundle) % sizeof(bundle_t)) != 0);
+
+	found = NULL;
+	for (i = 0; i < nelems; i++) {
+		const struct paravirt_patch_bundle_elem *p = &elems[i];
+		if (p->type == type) {
+			unsigned long need = p->ebundle - p->sbundle;
+			unsigned long room = ebundle - sbundle;
+
+			if (found != NULL)
+				*found = p;
+
+			if (room < need) {
+				/* no room to replace. skip it */
+				printk(KERN_DEBUG
+				       "the space is too small to put "
+				       "bundles. type %ld need %ld room %ld\n",
+				       type, need, room);
+				break;
+			}
+
+			used = need;
+			memcpy(sbundle, p->sbundle, used);
+			break;
+		}
+	}
+
+	return used;
+}
+
+void __init_or_module
+paravirt_patch_apply_bundle(const struct paravirt_patch_site_bundle *start,
+			    const struct paravirt_patch_site_bundle *end)
+{
+	const struct paravirt_patch_site_bundle *p;
+
+	if (noreplace_paravirt)
+		return;
+	if (pv_init_ops.patch_bundle == NULL)
+		return;
+
+	for (p = start; p < end; p++) {
+		unsigned long used;
+
+		used = (*pv_init_ops.patch_bundle)(p->sbundle, p->ebundle,
+						   p->type);
+		if (used == 0)
+			continue;
+
+		fill_nop_bundle(p->sbundle + used, p->ebundle);
+		paravirt_flush_i_cache_range(p->sbundle,
+					     p->ebundle - p->sbundle);
+	}
+	ia64_sync_i();
+	ia64_srlz_i();
+}
+
+/*
+ * nop.i, nop.m, nop.f instruction are same format.
+ * but nop.b has differennt format.
+ * This doesn't support nop.b for now.
+ */
+static void __init_or_module
+fill_nop_inst(unsigned long stag, unsigned long etag)
+{
+	extern const bundle_t paravirt_nop_mfi_inst_bundle[];
+	unsigned long tag;
+	const ia64_inst_t nop_inst =
+		paravirt_read_slot0(paravirt_nop_mfi_inst_bundle);
+
+	for (tag = stag; tag < etag; tag = paravirt_get_next_tag(tag))
+		paravirt_write_inst(tag, nop_inst);
+}
+
+void __init_or_module
+paravirt_patch_apply_inst(const struct paravirt_patch_site_inst *start,
+			  const struct paravirt_patch_site_inst *end)
+{
+	const struct paravirt_patch_site_inst *p;
+
+	if (noreplace_paravirt)
+		return;
+	if (pv_init_ops.patch_inst == NULL)
+		return;
+
+	for (p = start; p < end; p++) {
+		unsigned long tag;
+		bundle_t *sbundle;
+		bundle_t *ebundle;
+
+		tag = (*pv_init_ops.patch_inst)(p->stag, p->etag, p->type);
+		if (tag == p->stag)
+			continue;
+
+		fill_nop_inst(tag, p->etag);
+		sbundle = paravirt_get_bundle(p->stag);
+		ebundle = paravirt_get_bundle(p->etag) + 1;
+		paravirt_flush_i_cache_range(sbundle, (ebundle - sbundle) *
+					     sizeof(bundle_t));
+	}
+	ia64_sync_i();
+	ia64_srlz_i();
+}
+#endif /* ASM_SUPPOTED */
+
+/* brl.cond.sptk.many <target64> X3 */
+typedef union inst_x3_op {
+	ia64_inst_t inst;
+	struct {
+		unsigned long qp: 6;
+		unsigned long btyp: 3;
+		unsigned long unused: 3;
+		unsigned long p: 1;
+		unsigned long imm20b: 20;
+		unsigned long wh: 2;
+		unsigned long d: 1;
+		unsigned long i: 1;
+		unsigned long opcode: 4;
+	};
+	unsigned long l;
+} inst_x3_op_t;
+
+typedef union inst_x3_imm {
+	ia64_inst_t inst;
+	struct {
+		unsigned long unused: 2;
+		unsigned long imm39: 39;
+	};
+	unsigned long l;
+} inst_x3_imm_t;
+
+void __init_or_module
+paravirt_patch_reloc_brl(unsigned long tag, const void *target)
+{
+	unsigned long tag_op = paravirt_get_next_tag(tag);
+	unsigned long tag_imm = tag;
+	bundle_t *bundle = paravirt_get_bundle(tag);
+
+	ia64_inst_t inst_op = paravirt_read_inst(tag_op);
+	ia64_inst_t inst_imm = paravirt_read_inst(tag_imm);
+
+	inst_x3_op_t inst_x3_op = { .l = inst_op.l };
+	inst_x3_imm_t inst_x3_imm = { .l = inst_imm.l };
+
+	unsigned long imm60 =
+		((unsigned long)target - (unsigned long)bundle) >> 4;
+
+	BUG_ON(paravirt_get_slot(tag) != 1); /* MLX */
+	BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
+
+	/* imm60[59] 1bit */
+	inst_x3_op.i = (imm60 >> 59) & 1;
+	/* imm60[19:0] 20bit */
+	inst_x3_op.imm20b = imm60 & ((1UL << 20) - 1);
+	/* imm60[58:20] 39bit */
+	inst_x3_imm.imm39 = (imm60 >> 20) & ((1UL << 39) - 1);
+
+	inst_op.l = inst_x3_op.l;
+	inst_imm.l = inst_x3_imm.l;
+
+	paravirt_write_inst(tag_op, inst_op);
+	paravirt_write_inst(tag_imm, inst_imm);
+}
+
+/* br.cond.sptk.many <target25>	B1 */
+typedef union inst_b1 {
+	ia64_inst_t inst;
+	struct {
+		unsigned long qp: 6;
+		unsigned long btype: 3;
+		unsigned long unused: 3;
+		unsigned long p: 1;
+		unsigned long imm20b: 20;
+		unsigned long wh: 2;
+		unsigned long d: 1;
+		unsigned long s: 1;
+		unsigned long opcode: 4;
+	};
+	unsigned long l;
+} inst_b1_t;
+
+void __init
+paravirt_patch_reloc_br(unsigned long tag, const void *target)
+{
+	bundle_t *bundle = paravirt_get_bundle(tag);
+	ia64_inst_t inst = paravirt_read_inst(tag);
+	unsigned long target25 = (unsigned long)target - (unsigned long)bundle;
+	inst_b1_t inst_b1;
+
+	BUG_ON(((unsigned long)target & (sizeof(bundle_t) - 1)) != 0);
+
+	inst_b1.l = inst.l;
+	if (target25 & (1UL << 63))
+		inst_b1.s = 1;
+	else
+		inst_b1.s = 0;
+
+	inst_b1.imm20b = target25 >> 4;
+	inst.l = inst_b1.l;
+
+	paravirt_write_inst(tag, inst);
+}
+
+void __init
+__paravirt_patch_apply_branch(
+	unsigned long tag, unsigned long type,
+	const struct paravirt_patch_branch_target *entries,
+	unsigned int nr_entries)
+{
+	unsigned int i;
+	for (i = 0; i < nr_entries; i++) {
+		if (entries[i].type == type) {
+			paravirt_patch_reloc_br(tag, entries[i].entry);
+			break;
+		}
+	}
+}
+
+static void __init
+paravirt_patch_apply_branch(const struct paravirt_patch_site_branch *start,
+			    const struct paravirt_patch_site_branch *end)
+{
+	const struct paravirt_patch_site_branch *p;
+
+	if (noreplace_paravirt)
+		return;
+	if (pv_init_ops.patch_branch == NULL)
+		return;
+
+	for (p = start; p < end; p++)
+		(*pv_init_ops.patch_branch)(p->tag, p->type);
+
+	ia64_sync_i();
+	ia64_srlz_i();
+}
+
+void __init
+paravirt_patch_apply(void)
+{
+	extern const char __start_paravirt_bundles[];
+	extern const char __stop_paravirt_bundles[];
+	extern const char __start_paravirt_insts[];
+	extern const char __stop_paravirt_insts[];
+	extern const char __start_paravirt_branches[];
+	extern const char __stop_paravirt_branches[];
+
+	paravirt_patch_apply_bundle((const struct paravirt_patch_site_bundle *)
+				    __start_paravirt_bundles,
+				    (const struct paravirt_patch_site_bundle *)
+				    __stop_paravirt_bundles);
+	paravirt_patch_apply_inst((const struct paravirt_patch_site_inst *)
+				  __start_paravirt_insts,
+				  (const struct paravirt_patch_site_inst *)
+				  __stop_paravirt_insts);
+	paravirt_patch_apply_branch((const struct paravirt_patch_site_branch *)
+				    __start_paravirt_branches,
+				    (const struct paravirt_patch_site_branch *)
+				    __stop_paravirt_branches);
+}
+
+/*
+ * Local variables:
+ * mode: C
+ * c-set-style: "linux"
+ * c-basic-offset: 8
+ * tab-width: 8
+ * indent-tabs-mode: t
+ * End:
+ */
diff --git a/arch/ia64/kernel/paravirt_patchlist.c b/arch/ia64/kernel/paravirt_patchlist.c
new file mode 100644
index 000000000000..b28082a95d45
--- /dev/null
+++ b/arch/ia64/kernel/paravirt_patchlist.c
@@ -0,0 +1,79 @@
+/******************************************************************************
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#include <linux/bug.h>
+#include <asm/paravirt.h>
+
+#define DECLARE(name)						\
+	extern unsigned long					\
+		__ia64_native_start_gate_##name##_patchlist[];	\
+	extern unsigned long					\
+		__ia64_native_end_gate_##name##_patchlist[]
+
+DECLARE(fsyscall);
+DECLARE(brl_fsys_bubble_down);
+DECLARE(vtop);
+DECLARE(mckinley_e9);
+
+extern unsigned long __start_gate_section[];
+
+#define ASSIGN(name)							    \
+	.start_##name##_patchlist =					    \
+		(unsigned long)__ia64_native_start_gate_##name##_patchlist, \
+	.end_##name##_patchlist =					    \
+		(unsigned long)__ia64_native_end_gate_##name##_patchlist
+
+struct pv_patchdata pv_patchdata __initdata = {
+	ASSIGN(fsyscall),
+	ASSIGN(brl_fsys_bubble_down),
+	ASSIGN(vtop),
+	ASSIGN(mckinley_e9),
+
+	.gate_section = (void*)__start_gate_section,
+};
+
+
+unsigned long __init
+paravirt_get_gate_patchlist(enum pv_gate_patchlist type)
+{
+
+#define CASE(NAME, name)					\
+	case PV_GATE_START_##NAME:				\
+		return pv_patchdata.start_##name##_patchlist;	\
+	case PV_GATE_END_##NAME:				\
+		return pv_patchdata.end_##name##_patchlist;	\
+
+	switch (type) {
+		CASE(FSYSCALL, fsyscall);
+		CASE(BRL_FSYS_BUBBLE_DOWN, brl_fsys_bubble_down);
+		CASE(VTOP, vtop);
+		CASE(MCKINLEY_E9, mckinley_e9);
+	default:
+		BUG();
+		break;
+	}
+	return 0;
+}
+
+void * __init
+paravirt_get_gate_section(void)
+{
+	return pv_patchdata.gate_section;
+}
diff --git a/arch/ia64/kernel/paravirt_patchlist.h b/arch/ia64/kernel/paravirt_patchlist.h
new file mode 100644
index 000000000000..0684aa6c6507
--- /dev/null
+++ b/arch/ia64/kernel/paravirt_patchlist.h
@@ -0,0 +1,28 @@
+/******************************************************************************
+ * linux/arch/ia64/xen/paravirt_patchlist.h
+ *
+ * Copyright (c) 2008 Isaku Yamahata <yamahata at valinux co jp>
+ *                    VA Linux Systems Japan K.K.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307  USA
+ *
+ */
+
+#if defined(__IA64_GATE_PARAVIRTUALIZED_XEN)
+#include <asm/xen/patchlist.h>
+#else
+#include <asm/native/patchlist.h>
+#endif
+
diff --git a/arch/ia64/kernel/paravirtentry.S b/arch/ia64/kernel/paravirtentry.S
index 2f42fcb9776a..6158560d7f17 100644
--- a/arch/ia64/kernel/paravirtentry.S
+++ b/arch/ia64/kernel/paravirtentry.S
@@ -20,8 +20,11 @@
  *
  */
 
+#include <linux/init.h>
 #include <asm/asmmacro.h>
 #include <asm/asm-offsets.h>
+#include <asm/paravirt_privop.h>
+#include <asm/paravirt_patch.h>
 #include "entry.h"
 
 #define DATA8(sym, init_value)			\
@@ -32,29 +35,87 @@
 	data8 init_value ;			\
 	.popsection
 
-#define BRANCH(targ, reg, breg)		\
-	movl reg=targ ;			\
-	;;				\
-	ld8 reg=[reg] ;			\
-	;;				\
-	mov breg=reg ;			\
+#define BRANCH(targ, reg, breg, type)					\
+	PARAVIRT_PATCH_SITE_BR(PARAVIRT_PATCH_TYPE_BR_ ## type) ;	\
+	;;								\
+	movl reg=targ ;							\
+	;;								\
+	ld8 reg=[reg] ;							\
+	;;								\
+	mov breg=reg ;							\
 	br.cond.sptk.many breg
 
-#define BRANCH_PROC(sym, reg, breg)				\
-	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ; \
-	GLOBAL_ENTRY(paravirt_ ## sym) ;			\
-		BRANCH(paravirt_ ## sym ## _targ, reg, breg) ;	\
+#define BRANCH_PROC(sym, reg, breg, type)				\
+	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ;		\
+	GLOBAL_ENTRY(paravirt_ ## sym) ;				\
+		BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ;	\
 	END(paravirt_ ## sym)
 
-#define BRANCH_PROC_UNWINFO(sym, reg, breg)			\
-	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ; \
-	GLOBAL_ENTRY(paravirt_ ## sym) ;			\
-		PT_REGS_UNWIND_INFO(0) ;			\
-		BRANCH(paravirt_ ## sym ## _targ, reg, breg) ;	\
+#define BRANCH_PROC_UNWINFO(sym, reg, breg, type)			\
+	DATA8(paravirt_ ## sym ## _targ, ia64_native_ ## sym) ;		\
+	GLOBAL_ENTRY(paravirt_ ## sym) ;				\
+		PT_REGS_UNWIND_INFO(0) ;				\
+		BRANCH(paravirt_ ## sym ## _targ, reg, breg, type) ;	\
 	END(paravirt_ ## sym)
 
 
-BRANCH_PROC(switch_to, r22, b7)
-BRANCH_PROC_UNWINFO(leave_syscall, r22, b7)
-BRANCH_PROC(work_processed_syscall, r2, b7)
-BRANCH_PROC_UNWINFO(leave_kernel, r22, b7)
+BRANCH_PROC(switch_to, r22, b7, SWITCH_TO)
+BRANCH_PROC_UNWINFO(leave_syscall, r22, b7, LEAVE_SYSCALL)
+BRANCH_PROC(work_processed_syscall, r2, b7, WORK_PROCESSED_SYSCALL)
+BRANCH_PROC_UNWINFO(leave_kernel, r22, b7, LEAVE_KERNEL)
+
+
+#ifdef CONFIG_MODULES
+#define __INIT_OR_MODULE	.text
+#define __INITDATA_OR_MODULE	.data
+#else
+#define __INIT_OR_MODULE	__INIT
+#define __INITDATA_OR_MODULE	__INITDATA
+#endif /* CONFIG_MODULES */
+
+	__INIT_OR_MODULE
+	GLOBAL_ENTRY(paravirt_fc_i)
+	fc.i r32
+	br.ret.sptk.many rp
+	END(paravirt_fc_i)
+	__FINIT
+
+	__INIT_OR_MODULE
+	.align 32
+	GLOBAL_ENTRY(paravirt_nop_b_inst_bundle)
+	{
+		nop.b 0
+		nop.b 0
+		nop.b 0
+	}
+	END(paravirt_nop_b_inst_bundle)
+	__FINIT
+
+	/* NOTE: nop.[mfi] has same format */
+	__INIT_OR_MODULE
+	GLOBAL_ENTRY(paravirt_nop_mfi_inst_bundle)
+	{
+		nop.m 0
+		nop.f 0
+		nop.i 0
+	}
+	END(paravirt_nop_mfi_inst_bundle)
+	__FINIT
+
+	__INIT_OR_MODULE
+	GLOBAL_ENTRY(paravirt_nop_bundle)
+paravirt_nop_bundle_start:
+	{
+		nop 0
+		nop 0
+		nop 0
+	}
+paravirt_nop_bundle_end:
+	END(paravirt_nop_bundle)
+	__FINIT
+
+	__INITDATA_OR_MODULE
+	.align 8
+	.global paravirt_nop_bundle_size
+paravirt_nop_bundle_size:
+	data8	paravirt_nop_bundle_end - paravirt_nop_bundle_start
diff --git a/arch/ia64/kernel/patch.c b/arch/ia64/kernel/patch.c
index b83b2c516008..68a1311db806 100644
--- a/arch/ia64/kernel/patch.c
+++ b/arch/ia64/kernel/patch.c
@@ -7,6 +7,7 @@
 #include <linux/init.h>
 #include <linux/string.h>
 
+#include <asm/paravirt.h>
 #include <asm/patch.h>
 #include <asm/processor.h>
 #include <asm/sections.h>
@@ -169,16 +170,35 @@ ia64_patch_mckinley_e9 (unsigned long start, unsigned long end)
 	ia64_srlz_i();
 }
 
+extern unsigned long ia64_native_fsyscall_table[NR_syscalls];
+extern char ia64_native_fsys_bubble_down[];
+struct pv_fsys_data pv_fsys_data __initdata = {
+	.fsyscall_table = (unsigned long *)ia64_native_fsyscall_table,
+	.fsys_bubble_down = (void *)ia64_native_fsys_bubble_down,
+};
+
+unsigned long * __init
+paravirt_get_fsyscall_table(void)
+{
+	return pv_fsys_data.fsyscall_table;
+}
+
+char * __init
+paravirt_get_fsys_bubble_down(void)
+{
+	return pv_fsys_data.fsys_bubble_down;
+}
+
 static void __init
 patch_fsyscall_table (unsigned long start, unsigned long end)
 {
-	extern unsigned long fsyscall_table[NR_syscalls];
+	u64 fsyscall_table = (u64)paravirt_get_fsyscall_table();
 	s32 *offp = (s32 *) start;
 	u64 ip;
 
 	while (offp < (s32 *) end) {
 		ip = (u64) ia64_imva((char *) offp + *offp);
-		ia64_patch_imm64(ip, (u64) fsyscall_table);
+		ia64_patch_imm64(ip, fsyscall_table);
 		ia64_fc((void *) ip);
 		++offp;
 	}
@@ -189,7 +209,7 @@ patch_fsyscall_table (unsigned long start, unsigned long end)
 static void __init
 patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
 {
-	extern char fsys_bubble_down[];
+	u64 fsys_bubble_down = (u64)paravirt_get_fsys_bubble_down();
 	s32 *offp = (s32 *) start;
 	u64 ip;
 
@@ -207,13 +227,13 @@ patch_brl_fsys_bubble_down (unsigned long start, unsigned long end)
 void __init
 ia64_patch_gate (void)
 {
-#	define START(name)	((unsigned long) __start_gate_##name##_patchlist)
-#	define END(name)	((unsigned long)__end_gate_##name##_patchlist)
+#	define START(name)	paravirt_get_gate_patchlist(PV_GATE_START_##name)
+#	define END(name)	paravirt_get_gate_patchlist(PV_GATE_END_##name)
 
-	patch_fsyscall_table(START(fsyscall), END(fsyscall));
-	patch_brl_fsys_bubble_down(START(brl_fsys_bubble_down), END(brl_fsys_bubble_down));
-	ia64_patch_vtop(START(vtop), END(vtop));
-	ia64_patch_mckinley_e9(START(mckinley_e9), END(mckinley_e9));
+	patch_fsyscall_table(START(FSYSCALL), END(FSYSCALL));
+	patch_brl_fsys_bubble_down(START(BRL_FSYS_BUBBLE_DOWN), END(BRL_FSYS_BUBBLE_DOWN));
+	ia64_patch_vtop(START(VTOP), END(VTOP));
+	ia64_patch_mckinley_e9(START(MCKINLEY_E9), END(MCKINLEY_E9));
 }
 
 void ia64_patch_phys_stack_reg(unsigned long val)
@@ -229,7 +249,7 @@ void ia64_patch_phys_stack_reg(unsigned long val)
 	while (offp < end) {
 		ip = (u64) offp + *offp;
 		ia64_patch(ip, mask, imm);
-		ia64_fc(ip);
+		ia64_fc((void *)ip);
 		++offp;
 	}
 	ia64_sync_i();
diff --git a/arch/ia64/kernel/perfmon.c b/arch/ia64/kernel/perfmon.c
index 5c0f408cfd71..8a06dc480594 100644
--- a/arch/ia64/kernel/perfmon.c
+++ b/arch/ia64/kernel/perfmon.c
@@ -5603,7 +5603,7 @@ pfm_interrupt_handler(int irq, void *arg)
  * /proc/perfmon interface, for debug only
  */
 
-#define PFM_PROC_SHOW_HEADER	((void *)NR_CPUS+1)
+#define PFM_PROC_SHOW_HEADER	((void *)nr_cpu_ids+1)
 
 static void *
 pfm_proc_start(struct seq_file *m, loff_t *pos)
@@ -5612,7 +5612,7 @@ pfm_proc_start(struct seq_file *m, loff_t *pos)
 		return PFM_PROC_SHOW_HEADER;
 	}
 
-	while (*pos <= NR_CPUS) {
+	while (*pos <= nr_cpu_ids) {
 		if (cpu_online(*pos - 1)) {
 			return (void *)*pos;
 		}
diff --git a/arch/ia64/kernel/process.c b/arch/ia64/kernel/process.c
index c57162705147..5d7c0e5b9e76 100644
--- a/arch/ia64/kernel/process.c
+++ b/arch/ia64/kernel/process.c
@@ -413,7 +413,7 @@ ia64_load_extra (struct task_struct *task)
  * so there is nothing to worry about.
  */
 int
-copy_thread (int nr, unsigned long clone_flags,
+copy_thread(unsigned long clone_flags,
 	     unsigned long user_stack_base, unsigned long user_stack_size,
 	     struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/ia64/kernel/salinfo.c b/arch/ia64/kernel/salinfo.c
index ecb9eb78d687..7053c55b7649 100644
--- a/arch/ia64/kernel/salinfo.c
+++ b/arch/ia64/kernel/salinfo.c
@@ -317,7 +317,7 @@ retry:
 	}
 
 	n = data->cpu_check;
-	for (i = 0; i < NR_CPUS; i++) {
+	for (i = 0; i < nr_cpu_ids; i++) {
 		if (cpu_isset(n, data->cpu_event)) {
 			if (!cpu_online(n)) {
 				cpu_clear(n, data->cpu_event);
@@ -326,7 +326,7 @@ retry:
 			cpu = n;
 			break;
 		}
-		if (++n == NR_CPUS)
+		if (++n == nr_cpu_ids)
 			n = 0;
 	}
 
@@ -337,7 +337,7 @@ retry:
 
 	/* for next read, start checking at next CPU */
 	data->cpu_check = cpu;
-	if (++data->cpu_check == NR_CPUS)
+	if (++data->cpu_check == nr_cpu_ids)
 		data->cpu_check = 0;
 
 	snprintf(cmd, sizeof(cmd), "read %d\n", cpu);
diff --git a/arch/ia64/kernel/setup.c b/arch/ia64/kernel/setup.c
index 865af27c7737..714066aeda7f 100644
--- a/arch/ia64/kernel/setup.c
+++ b/arch/ia64/kernel/setup.c
@@ -52,6 +52,7 @@
 #include <asm/meminit.h>
 #include <asm/page.h>
 #include <asm/paravirt.h>
+#include <asm/paravirt_patch.h>
 #include <asm/patch.h>
 #include <asm/pgtable.h>
 #include <asm/processor.h>
@@ -537,6 +538,7 @@ setup_arch (char **cmdline_p)
 	paravirt_arch_setup_early();
 
 	ia64_patch_vtop((u64) __start___vtop_patchlist, (u64) __end___vtop_patchlist);
+	paravirt_patch_apply();
 
 	*cmdline_p = __va(ia64_boot_param->command_line);
 	strlcpy(boot_command_line, *cmdline_p, COMMAND_LINE_SIZE);
@@ -730,10 +732,10 @@ static void *
 c_start (struct seq_file *m, loff_t *pos)
 {
 #ifdef CONFIG_SMP
-	while (*pos < NR_CPUS && !cpu_isset(*pos, cpu_online_map))
+	while (*pos < nr_cpu_ids && !cpu_online(*pos))
 		++*pos;
 #endif
-	return *pos < NR_CPUS ? cpu_data(*pos) : NULL;
+	return *pos < nr_cpu_ids ? cpu_data(*pos) : NULL;
 }
 
 static void *
@@ -1016,8 +1018,7 @@ cpu_init (void)
 					| IA64_DCR_DA | IA64_DCR_DD | IA64_DCR_LC));
 	atomic_inc(&init_mm.mm_count);
 	current->active_mm = &init_mm;
-	if (current->mm)
-		BUG();
+	BUG_ON(current->mm);
 
 	ia64_mmu_init(ia64_imva(cpu_data));
 	ia64_mca_cpu_init(ia64_imva(cpu_data));
diff --git a/arch/ia64/kernel/smp.c b/arch/ia64/kernel/smp.c
index da8f020d82c1..2ea4199d9c57 100644
--- a/arch/ia64/kernel/smp.c
+++ b/arch/ia64/kernel/smp.c
@@ -166,11 +166,11 @@ send_IPI_allbutself (int op)
  * Called with preemption disabled.
  */
 static inline void
-send_IPI_mask(cpumask_t mask, int op)
+send_IPI_mask(const struct cpumask *mask, int op)
 {
 	unsigned int cpu;
 
-	for_each_cpu_mask(cpu, mask) {
+	for_each_cpu(cpu, mask) {
 			send_IPI_single(cpu, op);
 	}
 }
@@ -316,7 +316,7 @@ void arch_send_call_function_single_ipi(int cpu)
 	send_IPI_single(cpu, IPI_CALL_FUNC_SINGLE);
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	send_IPI_mask(mask, IPI_CALL_FUNC);
 }
diff --git a/arch/ia64/kernel/smpboot.c b/arch/ia64/kernel/smpboot.c
index 52290547c85b..7700e23034bb 100644
--- a/arch/ia64/kernel/smpboot.c
+++ b/arch/ia64/kernel/smpboot.c
@@ -581,14 +581,14 @@ smp_build_cpu_map (void)
 
 	ia64_cpu_to_sapicid[0] = boot_cpu_id;
 	cpus_clear(cpu_present_map);
-	cpu_set(0, cpu_present_map);
-	cpu_set(0, cpu_possible_map);
+	set_cpu_present(0, true);
+	set_cpu_possible(0, true);
 	for (cpu = 1, i = 0; i < smp_boot_data.cpu_count; i++) {
 		sapicid = smp_boot_data.cpu_phys_id[i];
 		if (sapicid == boot_cpu_id)
 			continue;
-		cpu_set(cpu, cpu_present_map);
-		cpu_set(cpu, cpu_possible_map);
+		set_cpu_present(cpu, true);
+		set_cpu_possible(cpu, true);
 		ia64_cpu_to_sapicid[cpu] = sapicid;
 		cpu++;
 	}
@@ -626,12 +626,9 @@ smp_prepare_cpus (unsigned int max_cpus)
 	 */
 	if (!max_cpus) {
 		printk(KERN_INFO "SMP mode deactivated.\n");
-		cpus_clear(cpu_online_map);
-		cpus_clear(cpu_present_map);
-		cpus_clear(cpu_possible_map);
-		cpu_set(0, cpu_online_map);
-		cpu_set(0, cpu_present_map);
-		cpu_set(0, cpu_possible_map);
+		init_cpu_online(cpumask_of(0));
+		init_cpu_present(cpumask_of(0));
+		init_cpu_possible(cpumask_of(0));
 		return;
 	}
 }
diff --git a/arch/ia64/kernel/time.c b/arch/ia64/kernel/time.c
index d6747bae52d8..641c8b61c4f1 100644
--- a/arch/ia64/kernel/time.c
+++ b/arch/ia64/kernel/time.c
@@ -51,6 +51,15 @@ EXPORT_SYMBOL(last_cli_ip);
 #endif
 
 #ifdef CONFIG_PARAVIRT
+/* We need to define a real function for sched_clock, to override the
+   weak default version */
+unsigned long long sched_clock(void)
+{
+        return paravirt_sched_clock();
+}
+#endif
+
+#ifdef CONFIG_PARAVIRT
 static void
 paravirt_clocksource_resume(void)
 {
diff --git a/arch/ia64/kernel/vmlinux.lds.S b/arch/ia64/kernel/vmlinux.lds.S
index 3765efc5f963..4a95e86b9ac2 100644
--- a/arch/ia64/kernel/vmlinux.lds.S
+++ b/arch/ia64/kernel/vmlinux.lds.S
@@ -169,6 +169,30 @@ SECTIONS
 	  __end___mckinley_e9_bundles = .;
 	}
 
+#if defined(CONFIG_PARAVIRT)
+  . = ALIGN(16);
+  .paravirt_bundles : AT(ADDR(.paravirt_bundles) - LOAD_OFFSET)
+	{
+	  __start_paravirt_bundles = .;
+          *(.paravirt_bundles)
+	  __stop_paravirt_bundles = .;
+	}
+  . = ALIGN(16);
+  .paravirt_insts : AT(ADDR(.paravirt_insts) - LOAD_OFFSET)
+	{
+	  __start_paravirt_insts = .;
+          *(.paravirt_insts)
+	  __stop_paravirt_insts = .;
+	}
+  . = ALIGN(16);
+  .paravirt_branches : AT(ADDR(.paravirt_branches) - LOAD_OFFSET)
+	{
+	  __start_paravirt_branches = .;
+	  *(.paravirt_branches)
+	  __stop_paravirt_branches = .;
+	}
+#endif
+
 #if defined(CONFIG_IA64_GENERIC)
   /* Machine Vector */
   . = ALIGN(16);
@@ -201,6 +225,12 @@ SECTIONS
 	  __start_gate_section = .;
 	  *(.data.gate)
 	  __stop_gate_section = .;
+#ifdef CONFIG_XEN
+	  . = ALIGN(PAGE_SIZE);
+	  __xen_start_gate_section = .;
+	  *(.data.gate.xen)
+	  __xen_stop_gate_section = .;
+#endif
 	}
   . = ALIGN(PAGE_SIZE);		/* make sure the gate page doesn't expose
   				 * kernel data
diff --git a/arch/ia64/kvm/kvm-ia64.c b/arch/ia64/kvm/kvm-ia64.c
index 076b00d1dbff..28af6a731bb8 100644
--- a/arch/ia64/kvm/kvm-ia64.c
+++ b/arch/ia64/kvm/kvm-ia64.c
@@ -70,7 +70,7 @@ static void kvm_flush_icache(unsigned long start, unsigned long len)
 	int l;
 
 	for (l = 0; l < (len + 32); l += 32)
-		ia64_fc(start + l);
+		ia64_fc((void *)(start + l));
 
 	ia64_sync_i();
 	ia64_srlz_i();
diff --git a/arch/ia64/kvm/vcpu.c b/arch/ia64/kvm/vcpu.c
index d4d280505878..a18ee17b9192 100644
--- a/arch/ia64/kvm/vcpu.c
+++ b/arch/ia64/kvm/vcpu.c
@@ -386,7 +386,7 @@ void set_rse_reg(struct kvm_pt_regs *regs, unsigned long r1,
 		else
 			*rnat_addr = (*rnat_addr) & (~nat_mask);
 
-		ia64_setreg(_IA64_REG_AR_BSPSTORE, bspstore);
+		ia64_setreg(_IA64_REG_AR_BSPSTORE, (unsigned long)bspstore);
 		ia64_setreg(_IA64_REG_AR_RNAT, rnat);
 	}
 	local_irq_restore(psr);
diff --git a/arch/ia64/kvm/vtlb.c b/arch/ia64/kvm/vtlb.c
index 38232b37668b..2c2501f13159 100644
--- a/arch/ia64/kvm/vtlb.c
+++ b/arch/ia64/kvm/vtlb.c
@@ -210,6 +210,7 @@ void thash_vhpt_insert(struct kvm_vcpu *v, u64 pte, u64 itir, u64 va, int type)
 		phy_pte  &= ~PAGE_FLAGS_RV_MASK;
 		psr = ia64_clear_ic();
 		ia64_itc(type, va, phy_pte, itir_ps(itir));
+		paravirt_dv_serialize_data();
 		ia64_set_psr(psr);
 	}
 
@@ -456,6 +457,7 @@ void  thash_purge_and_insert(struct kvm_vcpu *v, u64 pte, u64 itir,
 		phy_pte  &= ~PAGE_FLAGS_RV_MASK;
 		psr = ia64_clear_ic();
 		ia64_itc(type, ifa, phy_pte, ps);
+		paravirt_dv_serialize_data();
 		ia64_set_psr(psr);
 	}
 	if (!(pte&VTLB_PTE_IO))
diff --git a/arch/ia64/mm/init.c b/arch/ia64/mm/init.c
index 56e12903973c..c0f3bee69042 100644
--- a/arch/ia64/mm/init.c
+++ b/arch/ia64/mm/init.c
@@ -35,6 +35,7 @@
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include <asm/mca.h>
+#include <asm/paravirt.h>
 
 DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
@@ -259,6 +260,7 @@ put_kernel_page (struct page *page, unsigned long address, pgprot_t pgprot)
 static void __init
 setup_gate (void)
 {
+	void *gate_section;
 	struct page *page;
 
 	/*
@@ -266,10 +268,11 @@ setup_gate (void)
 	 * headers etc. and once execute-only page to enable
 	 * privilege-promotion via "epc":
 	 */
-	page = virt_to_page(ia64_imva(__start_gate_section));
+	gate_section = paravirt_get_gate_section();
+	page = virt_to_page(ia64_imva(gate_section));
 	put_kernel_page(page, GATE_ADDR, PAGE_READONLY);
 #ifdef HAVE_BUGGY_SEGREL
-	page = virt_to_page(ia64_imva(__start_gate_section + PAGE_SIZE));
+	page = virt_to_page(ia64_imva(gate_section + PAGE_SIZE));
 	put_kernel_page(page, GATE_ADDR + PAGE_SIZE, PAGE_GATE);
 #else
 	put_kernel_page(page, GATE_ADDR + PERCPU_PAGE_SIZE, PAGE_GATE);
@@ -633,8 +636,7 @@ mem_init (void)
 #endif
 
 #ifdef CONFIG_FLATMEM
-	if (!mem_map)
-		BUG();
+	BUG_ON(!mem_map);
 	max_mapnr = max_low_pfn;
 #endif
 
@@ -667,8 +669,8 @@ mem_init (void)
 	 * code can tell them apart.
 	 */
 	for (i = 0; i < NR_syscalls; ++i) {
-		extern unsigned long fsyscall_table[NR_syscalls];
 		extern unsigned long sys_call_table[NR_syscalls];
+		unsigned long *fsyscall_table = paravirt_get_fsyscall_table();
 
 		if (!fsyscall_table[i] || nolwsys)
 			fsyscall_table[i] = sys_call_table[i] | 1;
diff --git a/arch/ia64/mm/tlb.c b/arch/ia64/mm/tlb.c
index bd9818a36b47..b9f3d7bbb338 100644
--- a/arch/ia64/mm/tlb.c
+++ b/arch/ia64/mm/tlb.c
@@ -309,7 +309,7 @@ flush_tlb_range (struct vm_area_struct *vma, unsigned long start,
 
 	preempt_disable();
 #ifdef CONFIG_SMP
-	if (mm != current->active_mm || cpus_weight(mm->cpu_vm_mask) != 1) {
+	if (mm != current->active_mm || cpumask_weight(mm_cpumask(mm)) != 1) {
 		platform_global_tlb_purge(mm, start, end, nbits);
 		preempt_enable();
 		return;
diff --git a/arch/ia64/scripts/pvcheck.sed b/arch/ia64/scripts/pvcheck.sed
index ba66ac2e4c60..e59809a3fc01 100644
--- a/arch/ia64/scripts/pvcheck.sed
+++ b/arch/ia64/scripts/pvcheck.sed
@@ -17,6 +17,7 @@ s/mov.*=.*cr\.iip/.warning \"cr.iip should not used directly\"/g
 s/mov.*=.*cr\.ivr/.warning \"cr.ivr should not used directly\"/g
 s/mov.*=[^\.]*psr/.warning \"psr should not used directly\"/g	# avoid ar.fpsr
 s/mov.*=.*ar\.eflags/.warning \"ar.eflags should not used directly\"/g
+s/mov.*=.*ar\.itc.*/.warning \"ar.itc should not used directly\"/g
 s/mov.*cr\.ifa.*=.*/.warning \"cr.ifa should not used directly\"/g
 s/mov.*cr\.itir.*=.*/.warning \"cr.itir should not used directly\"/g
 s/mov.*cr\.iha.*=.*/.warning \"cr.iha should not used directly\"/g
diff --git a/arch/ia64/sn/kernel/io_common.c b/arch/ia64/sn/kernel/io_common.c
index 0d4ffa4da1da..57f280dd9def 100644
--- a/arch/ia64/sn/kernel/io_common.c
+++ b/arch/ia64/sn/kernel/io_common.c
@@ -135,8 +135,7 @@ static s64 sn_device_fixup_war(u64 nasid, u64 widget, int device,
 	}
 
 	war_list = kzalloc(DEV_PER_WIDGET * sizeof(*war_list), GFP_KERNEL);
-	if (!war_list)
-		BUG();
+	BUG_ON(!war_list);
 
 	SAL_CALL_NOLOCK(isrv, SN_SAL_IOIF_GET_WIDGET_DMAFLUSH_LIST,
 			nasid, widget, __pa(war_list), 0, 0, 0 ,0);
@@ -180,23 +179,20 @@ sn_common_hubdev_init(struct hubdev_info *hubdev)
 		sizeof(struct sn_flush_device_kernel *);
 	hubdev->hdi_flush_nasid_list.widget_p =
 		kzalloc(size, GFP_KERNEL);
-	if (!hubdev->hdi_flush_nasid_list.widget_p)
-		BUG();
+	BUG_ON(!hubdev->hdi_flush_nasid_list.widget_p);
 
 	for (widget = 0; widget <= HUB_WIDGET_ID_MAX; widget++) {
 		size = DEV_PER_WIDGET *
 			sizeof(struct sn_flush_device_kernel);
 		sn_flush_device_kernel = kzalloc(size, GFP_KERNEL);
-		if (!sn_flush_device_kernel)
-			BUG();
+		BUG_ON(!sn_flush_device_kernel);
 
 		dev_entry = sn_flush_device_kernel;
 		for (device = 0; device < DEV_PER_WIDGET;
 		     device++, dev_entry++) {
 			size = sizeof(struct sn_flush_device_common);
 			dev_entry->common = kzalloc(size, GFP_KERNEL);
-			if (!dev_entry->common)
-				BUG();
+			BUG_ON(!dev_entry->common);
 			if (sn_prom_feature_available(PRF_DEVICE_FLUSH_LIST))
 				status = sal_get_device_dmaflush_list(
 					     hubdev->hdi_nasid, widget, device,
@@ -326,8 +322,7 @@ sn_common_bus_fixup(struct pci_bus *bus,
 	 */
 	controller->platform_data = kzalloc(sizeof(struct sn_platform_data),
 					    GFP_KERNEL);
-	if (controller->platform_data == NULL)
-		BUG();
+	BUG_ON(controller->platform_data == NULL);
 	sn_platform_data =
 			(struct sn_platform_data *) controller->platform_data;
 	sn_platform_data->provider_soft = provider_soft;
diff --git a/arch/ia64/sn/kernel/io_init.c b/arch/ia64/sn/kernel/io_init.c
index e2eb2da60f96..ee774c366a06 100644
--- a/arch/ia64/sn/kernel/io_init.c
+++ b/arch/ia64/sn/kernel/io_init.c
@@ -128,8 +128,7 @@ sn_legacy_pci_window_fixup(struct pci_controller *controller,
 {
 		controller->window = kcalloc(2, sizeof(struct pci_window),
 					     GFP_KERNEL);
-		if (controller->window == NULL)
-			BUG();
+		BUG_ON(controller->window == NULL);
 		controller->window[0].offset = legacy_io;
 		controller->window[0].resource.name = "legacy_io";
 		controller->window[0].resource.flags = IORESOURCE_IO;
@@ -168,8 +167,7 @@ sn_pci_window_fixup(struct pci_dev *dev, unsigned int count,
 	idx = controller->windows;
 	new_count = controller->windows + count;
 	new_window = kcalloc(new_count, sizeof(struct pci_window), GFP_KERNEL);
-	if (new_window == NULL)
-		BUG();
+	BUG_ON(new_window == NULL);
 	if (controller->window) {
 		memcpy(new_window, controller->window,
 		       sizeof(struct pci_window) * controller->windows);
@@ -222,8 +220,7 @@ sn_io_slot_fixup(struct pci_dev *dev)
 		(u64) __pa(pcidev_info),
 		(u64) __pa(sn_irq_info));
 
-	if (status)
-		BUG(); /* Cannot get platform pci device information */
+	BUG_ON(status); /* Cannot get platform pci device information */
 
 
 	/* Copy over PIO Mapped Addresses */
@@ -307,8 +304,7 @@ sn_pci_controller_fixup(int segment, int busnum, struct pci_bus *bus)
 	prom_bussoft_ptr = __va(prom_bussoft_ptr);
 
 	controller = kzalloc(sizeof(*controller), GFP_KERNEL);
-	if (!controller)
-		BUG();
+	BUG_ON(!controller);
 	controller->segment = segment;
 
 	/*
diff --git a/arch/ia64/sn/kernel/setup.c b/arch/ia64/sn/kernel/setup.c
index 02c5b8a9fb60..e456f062f241 100644
--- a/arch/ia64/sn/kernel/setup.c
+++ b/arch/ia64/sn/kernel/setup.c
@@ -732,8 +732,7 @@ void __init build_cnode_tables(void)
 		kl_config_hdr_t *klgraph_header;
 		nasid = cnodeid_to_nasid(node);
 		klgraph_header = ia64_sn_get_klconfig_addr(nasid);
-		if (klgraph_header == NULL)
-			BUG();
+		BUG_ON(klgraph_header == NULL);
 		brd = NODE_OFFSET_TO_LBOARD(nasid, klgraph_header->ch_board_info);
 		while (brd) {
 			if (board_needs_cnode(brd->brd_type) && physical_node_map[brd->brd_nasid] < 0) {
@@ -750,7 +749,7 @@ nasid_slice_to_cpuid(int nasid, int slice)
 {
 	long cpu;
 
-	for (cpu = 0; cpu < NR_CPUS; cpu++)
+	for (cpu = 0; cpu < nr_cpu_ids; cpu++)
 		if (cpuid_to_nasid(cpu) == nasid &&
 					cpuid_to_slice(cpu) == slice)
 			return cpu;
diff --git a/arch/ia64/sn/kernel/sn2/sn2_smp.c b/arch/ia64/sn/kernel/sn2/sn2_smp.c
index e585f9a2afb9..1176506b2bae 100644
--- a/arch/ia64/sn/kernel/sn2/sn2_smp.c
+++ b/arch/ia64/sn/kernel/sn2/sn2_smp.c
@@ -133,7 +133,7 @@ sn2_ipi_flush_all_tlb(struct mm_struct *mm)
 	unsigned long itc;
 
 	itc = ia64_get_itc();
-	smp_flush_tlb_cpumask(mm->cpu_vm_mask);
+	smp_flush_tlb_cpumask(*mm_cpumask(mm));
 	itc = ia64_get_itc() - itc;
 	__get_cpu_var(ptcstats).shub_ipi_flushes_itc_clocks += itc;
 	__get_cpu_var(ptcstats).shub_ipi_flushes++;
@@ -182,7 +182,7 @@ sn2_global_tlb_purge(struct mm_struct *mm, unsigned long start,
 	nodes_clear(nodes_flushed);
 	i = 0;
 
-	for_each_cpu_mask(cpu, mm->cpu_vm_mask) {
+	for_each_cpu(cpu, mm_cpumask(mm)) {
 		cnode = cpu_to_node(cpu);
 		node_set(cnode, nodes_flushed);
 		lcpu = cpu;
@@ -461,7 +461,7 @@ bool sn_cpu_disable_allowed(int cpu)
 
 static void *sn2_ptc_seq_start(struct seq_file *file, loff_t * offset)
 {
-	if (*offset < NR_CPUS)
+	if (*offset < nr_cpu_ids)
 		return offset;
 	return NULL;
 }
@@ -469,7 +469,7 @@ static void *sn2_ptc_seq_start(struct seq_file *file, loff_t * offset)
 static void *sn2_ptc_seq_next(struct seq_file *file, void *data, loff_t * offset)
 {
 	(*offset)++;
-	if (*offset < NR_CPUS)
+	if (*offset < nr_cpu_ids)
 		return offset;
 	return NULL;
 }
@@ -491,7 +491,7 @@ static int sn2_ptc_seq_show(struct seq_file *file, void *data)
 		seq_printf(file, "# ptctest %d, flushopt %d\n", sn2_ptctest, sn2_flush_opt);
 	}
 
-	if (cpu < NR_CPUS && cpu_online(cpu)) {
+	if (cpu < nr_cpu_ids && cpu_online(cpu)) {
 		stat = &per_cpu(ptcstats, cpu);
 		seq_printf(file, "cpu %d %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld %ld\n", cpu, stat->ptc_l,
 				stat->change_rid, stat->shub_ptc_flushes, stat->nodes_flushed,
@@ -554,7 +554,7 @@ static int __init sn2_ptc_init(void)
 
 	proc_sn2_ptc = proc_create(PTC_BASENAME, 0444,
 				   NULL, &proc_sn2_ptc_operations);
-	if (!&proc_sn2_ptc_operations) {
+	if (!proc_sn2_ptc) {
 		printk(KERN_ERR "unable to create %s proc entry", PTC_BASENAME);
 		return -EINVAL;
 	}
diff --git a/arch/ia64/sn/kernel/sn2/sn_hwperf.c b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
index be339477f906..9e6491cf72bd 100644
--- a/arch/ia64/sn/kernel/sn2/sn_hwperf.c
+++ b/arch/ia64/sn/kernel/sn2/sn_hwperf.c
@@ -275,8 +275,7 @@ static int sn_hwperf_get_nearest_node_objdata(struct sn_hwperf_object_info *objb
 
 	/* get it's interconnect topology */
 	sz = op->ports * sizeof(struct sn_hwperf_port_info);
-	if (sz > sizeof(ptdata))
-		BUG();
+	BUG_ON(sz > sizeof(ptdata));
 	e = ia64_sn_hwperf_op(sn_hwperf_master_nasid,
 			      SN_HWPERF_ENUM_PORTS, nodeobj->id, sz,
 			      (u64)&ptdata, 0, 0, NULL);
@@ -310,8 +309,7 @@ static int sn_hwperf_get_nearest_node_objdata(struct sn_hwperf_object_info *objb
 	if (router && (!found_cpu || !found_mem)) {
 		/* search for a node connected to the same router */
 		sz = router->ports * sizeof(struct sn_hwperf_port_info);
-		if (sz > sizeof(ptdata))
-			BUG();
+		BUG_ON(sz > sizeof(ptdata));
 		e = ia64_sn_hwperf_op(sn_hwperf_master_nasid,
 				      SN_HWPERF_ENUM_PORTS, router->id, sz,
 				      (u64)&ptdata, 0, 0, NULL);
@@ -612,7 +610,7 @@ static int sn_hwperf_op_cpu(struct sn_hwperf_op_info *op_info)
 	op_info->a->arg &= SN_HWPERF_ARG_OBJID_MASK;
 
 	if (cpu != SN_HWPERF_ARG_ANY_CPU) {
-		if (cpu >= NR_CPUS || !cpu_online(cpu)) {
+		if (cpu >= nr_cpu_ids || !cpu_online(cpu)) {
 			r = -EINVAL;
 			goto out;
 		}
diff --git a/arch/ia64/sn/pci/pcibr/pcibr_dma.c b/arch/ia64/sn/pci/pcibr/pcibr_dma.c
index 060df4aa9916..c659ad5613a0 100644
--- a/arch/ia64/sn/pci/pcibr/pcibr_dma.c
+++ b/arch/ia64/sn/pci/pcibr/pcibr_dma.c
@@ -256,9 +256,7 @@ void sn_dma_flush(u64 addr)
 
 	hubinfo = (NODEPDA(nasid_to_cnodeid(nasid)))->pdinfo;
 
-	if (!hubinfo) {
-		BUG();
-	}
+	BUG_ON(!hubinfo);
 
 	flush_nasid_list = &hubinfo->hdi_flush_nasid_list;
 	if (flush_nasid_list->widget_p == NULL)
diff --git a/arch/ia64/xen/Makefile b/arch/ia64/xen/Makefile
index 0ad0224693d9..e6f4a0a74228 100644
--- a/arch/ia64/xen/Makefile
+++ b/arch/ia64/xen/Makefile
@@ -3,14 +3,29 @@
 #
 
 obj-y := hypercall.o xenivt.o xensetup.o xen_pv_ops.o irq_xen.o \
-	 hypervisor.o xencomm.o xcom_hcall.o grant-table.o time.o suspend.o
+	 hypervisor.o xencomm.o xcom_hcall.o grant-table.o time.o suspend.o \
+	 gate-data.o
 
 obj-$(CONFIG_IA64_GENERIC) += machvec.o
 
+# The gate DSO image is built using a special linker script.
+include $(srctree)/arch/ia64/kernel/Makefile.gate
+
+# tell compiled for xen
+CPPFLAGS_gate.lds += -D__IA64_GATE_PARAVIRTUALIZED_XEN
+AFLAGS_gate.o += -D__IA64_ASM_PARAVIRTUALIZED_XEN -D__IA64_GATE_PARAVIRTUALIZED_XEN
+
+# use same file of native.
+$(obj)/gate.o: $(src)/../kernel/gate.S FORCE
+	$(call if_changed_dep,as_o_S)
+$(obj)/gate.lds: $(src)/../kernel/gate.lds.S FORCE
+	$(call if_changed_dep,cpp_lds_S)
+
+
 AFLAGS_xenivt.o += -D__IA64_ASM_PARAVIRTUALIZED_XEN
 
 # xen multi compile
-ASM_PARAVIRT_MULTI_COMPILE_SRCS = ivt.S entry.S
+ASM_PARAVIRT_MULTI_COMPILE_SRCS = ivt.S entry.S fsys.S
 ASM_PARAVIRT_OBJS = $(addprefix xen-,$(ASM_PARAVIRT_MULTI_COMPILE_SRCS:.S=.o))
 obj-y += $(ASM_PARAVIRT_OBJS)
 define paravirtualized_xen
diff --git a/arch/ia64/xen/gate-data.S b/arch/ia64/xen/gate-data.S
new file mode 100644
index 000000000000..7d4830afc91d
--- /dev/null
+++ b/arch/ia64/xen/gate-data.S
@@ -0,0 +1,3 @@
+	.section .data.gate.xen, "aw"
+
+	.incbin "arch/ia64/xen/gate.so"
diff --git a/arch/ia64/xen/hypercall.S b/arch/ia64/xen/hypercall.S
index 45e02bb64a92..e32dae444dd6 100644
--- a/arch/ia64/xen/hypercall.S
+++ b/arch/ia64/xen/hypercall.S
@@ -9,6 +9,7 @@
 #include <asm/intrinsics.h>
 #include <asm/xen/privop.h>
 
+#ifdef __INTEL_COMPILER
 /*
  * Hypercalls without parameter.
  */
@@ -72,6 +73,7 @@ GLOBAL_ENTRY(xen_set_rr0_to_rr4)
 	br.ret.sptk.many rp
 	;;
 END(xen_set_rr0_to_rr4)
+#endif
 
 GLOBAL_ENTRY(xen_send_ipi)
 	mov r14=r32
diff --git a/arch/ia64/xen/time.c b/arch/ia64/xen/time.c
index 68d6204c3f16..fb8332690179 100644
--- a/arch/ia64/xen/time.c
+++ b/arch/ia64/xen/time.c
@@ -175,10 +175,58 @@ static void xen_itc_jitter_data_reset(void)
 	} while (unlikely(ret != lcycle));
 }
 
+/* based on xen_sched_clock() in arch/x86/xen/time.c. */
+/*
+ * This relies on HAVE_UNSTABLE_SCHED_CLOCK. If it can't be defined,
+ * something similar logic should be implemented here.
+ */
+/*
+ * Xen sched_clock implementation.  Returns the number of unstolen
+ * nanoseconds, which is nanoseconds the VCPU spent in RUNNING+BLOCKED
+ * states.
+ */
+static unsigned long long xen_sched_clock(void)
+{
+	struct vcpu_runstate_info runstate;
+
+	unsigned long long now;
+	unsigned long long offset;
+	unsigned long long ret;
+
+	/*
+	 * Ideally sched_clock should be called on a per-cpu basis
+	 * anyway, so preempt should already be disabled, but that's
+	 * not current practice at the moment.
+	 */
+	preempt_disable();
+
+	/*
+	 * both ia64_native_sched_clock() and xen's runstate are
+	 * based on mAR.ITC. So difference of them makes sense.
+	 */
+	now = ia64_native_sched_clock();
+
+	get_runstate_snapshot(&runstate);
+
+	WARN_ON(runstate.state != RUNSTATE_running);
+
+	offset = 0;
+	if (now > runstate.state_entry_time)
+		offset = now - runstate.state_entry_time;
+	ret = runstate.time[RUNSTATE_blocked] +
+		runstate.time[RUNSTATE_running] +
+		offset;
+
+	preempt_enable();
+
+	return ret;
+}
+
 struct pv_time_ops xen_time_ops __initdata = {
 	.init_missing_ticks_accounting	= xen_init_missing_ticks_accounting,
 	.do_steal_accounting		= xen_do_steal_accounting,
 	.clocksource_resume		= xen_itc_jitter_data_reset,
+	.sched_clock			= xen_sched_clock,
 };
 
 /* Called after suspend, to resume time.  */
diff --git a/arch/ia64/xen/xen_pv_ops.c b/arch/ia64/xen/xen_pv_ops.c
index 936cff3c96e0..5e2270a999fa 100644
--- a/arch/ia64/xen/xen_pv_ops.c
+++ b/arch/ia64/xen/xen_pv_ops.c
@@ -24,6 +24,7 @@
 #include <linux/irq.h>
 #include <linux/kernel.h>
 #include <linux/pm.h>
+#include <linux/unistd.h>
 
 #include <asm/xen/hypervisor.h>
 #include <asm/xen/xencomm.h>
@@ -153,6 +154,13 @@ xen_post_smp_prepare_boot_cpu(void)
 	xen_setup_vcpu_info_placement();
 }
 
+#ifdef ASM_SUPPORTED
+static unsigned long __init_or_module
+xen_patch_bundle(void *sbundle, void *ebundle, unsigned long type);
+#endif
+static void __init
+xen_patch_branch(unsigned long tag, unsigned long type);
+
 static const struct pv_init_ops xen_init_ops __initconst = {
 	.banner = xen_banner,
 
@@ -163,6 +171,53 @@ static const struct pv_init_ops xen_init_ops __initconst = {
 	.arch_setup_nomca = xen_arch_setup_nomca,
 
 	.post_smp_prepare_boot_cpu = xen_post_smp_prepare_boot_cpu,
+#ifdef ASM_SUPPORTED
+	.patch_bundle = xen_patch_bundle,
+#endif
+	.patch_branch = xen_patch_branch,
+};
+
+/***************************************************************************
+ * pv_fsys_data
+ * addresses for fsys
+ */
+
+extern unsigned long xen_fsyscall_table[NR_syscalls];
+extern char xen_fsys_bubble_down[];
+struct pv_fsys_data xen_fsys_data __initdata = {
+	.fsyscall_table = (unsigned long *)xen_fsyscall_table,
+	.fsys_bubble_down = (void *)xen_fsys_bubble_down,
+};
+
+/***************************************************************************
+ * pv_patchdata
+ * patchdata addresses
+ */
+
+#define DECLARE(name)							\
+	extern unsigned long __xen_start_gate_##name##_patchlist[];	\
+	extern unsigned long __xen_end_gate_##name##_patchlist[]
+
+DECLARE(fsyscall);
+DECLARE(brl_fsys_bubble_down);
+DECLARE(vtop);
+DECLARE(mckinley_e9);
+
+extern unsigned long __xen_start_gate_section[];
+
+#define ASSIGN(name)							\
+	.start_##name##_patchlist =					\
+		(unsigned long)__xen_start_gate_##name##_patchlist,	\
+	.end_##name##_patchlist =					\
+		(unsigned long)__xen_end_gate_##name##_patchlist
+
+static struct pv_patchdata xen_patchdata __initdata = {
+	ASSIGN(fsyscall),
+	ASSIGN(brl_fsys_bubble_down),
+	ASSIGN(vtop),
+	ASSIGN(mckinley_e9),
+
+	.gate_section = (void*)__xen_start_gate_section,
 };
 
 /***************************************************************************
@@ -170,6 +225,76 @@ static const struct pv_init_ops xen_init_ops __initconst = {
  * intrinsics hooks.
  */
 
+#ifndef ASM_SUPPORTED
+static void
+xen_set_itm_with_offset(unsigned long val)
+{
+	/* ia64_cpu_local_tick() calls this with interrupt enabled. */
+	/* WARN_ON(!irqs_disabled()); */
+	xen_set_itm(val - XEN_MAPPEDREGS->itc_offset);
+}
+
+static unsigned long
+xen_get_itm_with_offset(void)
+{
+	/* unused at this moment */
+	printk(KERN_DEBUG "%s is called.\n", __func__);
+
+	WARN_ON(!irqs_disabled());
+	return ia64_native_getreg(_IA64_REG_CR_ITM) +
+		XEN_MAPPEDREGS->itc_offset;
+}
+
+/* ia64_set_itc() is only called by
+ * cpu_init() with ia64_set_itc(0) and ia64_sync_itc().
+ * So XEN_MAPPEDRESG->itc_offset cal be considered as almost constant.
+ */
+static void
+xen_set_itc(unsigned long val)
+{
+	unsigned long mitc;
+
+	WARN_ON(!irqs_disabled());
+	mitc = ia64_native_getreg(_IA64_REG_AR_ITC);
+	XEN_MAPPEDREGS->itc_offset = val - mitc;
+	XEN_MAPPEDREGS->itc_last = val;
+}
+
+static unsigned long
+xen_get_itc(void)
+{
+	unsigned long res;
+	unsigned long itc_offset;
+	unsigned long itc_last;
+	unsigned long ret_itc_last;
+
+	itc_offset = XEN_MAPPEDREGS->itc_offset;
+	do {
+		itc_last = XEN_MAPPEDREGS->itc_last;
+		res = ia64_native_getreg(_IA64_REG_AR_ITC);
+		res += itc_offset;
+		if (itc_last >= res)
+			res = itc_last + 1;
+		ret_itc_last = cmpxchg(&XEN_MAPPEDREGS->itc_last,
+				       itc_last, res);
+	} while (unlikely(ret_itc_last != itc_last));
+	return res;
+
+#if 0
+	/* ia64_itc_udelay() calls ia64_get_itc() with interrupt enabled.
+	   Should it be paravirtualized instead? */
+	WARN_ON(!irqs_disabled());
+	itc_offset = XEN_MAPPEDREGS->itc_offset;
+	itc_last = XEN_MAPPEDREGS->itc_last;
+	res = ia64_native_getreg(_IA64_REG_AR_ITC);
+	res += itc_offset;
+	if (itc_last >= res)
+		res = itc_last + 1;
+	XEN_MAPPEDREGS->itc_last = res;
+	return res;
+#endif
+}
+
 static void xen_setreg(int regnum, unsigned long val)
 {
 	switch (regnum) {
@@ -181,11 +306,14 @@ static void xen_setreg(int regnum, unsigned long val)
 		xen_set_eflag(val);
 		break;
 #endif
+	case _IA64_REG_AR_ITC:
+		xen_set_itc(val);
+		break;
 	case _IA64_REG_CR_TPR:
 		xen_set_tpr(val);
 		break;
 	case _IA64_REG_CR_ITM:
-		xen_set_itm(val);
+		xen_set_itm_with_offset(val);
 		break;
 	case _IA64_REG_CR_EOI:
 		xen_eoi(val);
@@ -209,6 +337,12 @@ static unsigned long xen_getreg(int regnum)
 		res = xen_get_eflag();
 		break;
 #endif
+	case _IA64_REG_AR_ITC:
+		res = xen_get_itc();
+		break;
+	case _IA64_REG_CR_ITM:
+		res = xen_get_itm_with_offset();
+		break;
 	case _IA64_REG_CR_IVR:
 		res = xen_get_ivr();
 		break;
@@ -259,8 +393,417 @@ xen_intrin_local_irq_restore(unsigned long mask)
 	else
 		xen_rsm_i();
 }
+#else
+#define __DEFINE_FUNC(name, code)					\
+	extern const char xen_ ## name ## _direct_start[];		\
+	extern const char xen_ ## name ## _direct_end[];		\
+	asm (".align 32\n"						\
+	     ".proc xen_" #name "\n"					\
+	     "xen_" #name ":\n"						\
+	     "xen_" #name "_direct_start:\n"				\
+	     code							\
+	     "xen_" #name "_direct_end:\n"				\
+	     "br.cond.sptk.many b6\n"					\
+	     ".endp xen_" #name "\n")
+
+#define DEFINE_VOID_FUNC0(name, code)		\
+	extern void				\
+	xen_ ## name (void);			\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_VOID_FUNC1(name, code)		\
+	extern void				\
+	xen_ ## name (unsigned long arg);	\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_VOID_FUNC1_VOID(name, code)	\
+	extern void				\
+	xen_ ## name (void *arg);		\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_VOID_FUNC2(name, code)		\
+	extern void				\
+	xen_ ## name (unsigned long arg0,	\
+		      unsigned long arg1);	\
+	__DEFINE_FUNC(name, code)
 
-static const struct pv_cpu_ops xen_cpu_ops __initdata = {
+#define DEFINE_FUNC0(name, code)		\
+	extern unsigned long			\
+	xen_ ## name (void);			\
+	__DEFINE_FUNC(name, code)
+
+#define DEFINE_FUNC1(name, type, code)		\
+	extern unsigned long			\
+	xen_ ## name (type arg);		\
+	__DEFINE_FUNC(name, code)
+
+#define XEN_PSR_I_ADDR_ADDR     (XSI_BASE + XSI_PSR_I_ADDR_OFS)
+
+/*
+ * static void xen_set_itm_with_offset(unsigned long val)
+ *        xen_set_itm(val - XEN_MAPPEDREGS->itc_offset);
+ */
+/* 2 bundles */
+DEFINE_VOID_FUNC1(set_itm_with_offset,
+		  "mov r2 = " __stringify(XSI_BASE) " + "
+		  __stringify(XSI_ITC_OFFSET_OFS) "\n"
+		  ";;\n"
+		  "ld8 r3 = [r2]\n"
+		  ";;\n"
+		  "sub r8 = r8, r3\n"
+		  "break " __stringify(HYPERPRIVOP_SET_ITM) "\n");
+
+/*
+ * static unsigned long xen_get_itm_with_offset(void)
+ *    return ia64_native_getreg(_IA64_REG_CR_ITM) + XEN_MAPPEDREGS->itc_offset;
+ */
+/* 2 bundles */
+DEFINE_FUNC0(get_itm_with_offset,
+	     "mov r2 = " __stringify(XSI_BASE) " + "
+	     __stringify(XSI_ITC_OFFSET_OFS) "\n"
+	     ";;\n"
+	     "ld8 r3 = [r2]\n"
+	     "mov r8 = cr.itm\n"
+	     ";;\n"
+	     "add r8 = r8, r2\n");
+
+/*
+ * static void xen_set_itc(unsigned long val)
+ *	unsigned long mitc;
+ *
+ *	WARN_ON(!irqs_disabled());
+ *	mitc = ia64_native_getreg(_IA64_REG_AR_ITC);
+ *	XEN_MAPPEDREGS->itc_offset = val - mitc;
+ *	XEN_MAPPEDREGS->itc_last = val;
+ */
+/* 2 bundles */
+DEFINE_VOID_FUNC1(set_itc,
+		  "mov r2 = " __stringify(XSI_BASE) " + "
+		  __stringify(XSI_ITC_LAST_OFS) "\n"
+		  "mov r3 = ar.itc\n"
+		  ";;\n"
+		  "sub r3 = r8, r3\n"
+		  "st8 [r2] = r8, "
+		  __stringify(XSI_ITC_LAST_OFS) " - "
+		  __stringify(XSI_ITC_OFFSET_OFS) "\n"
+		  ";;\n"
+		  "st8 [r2] = r3\n");
+
+/*
+ * static unsigned long xen_get_itc(void)
+ *	unsigned long res;
+ *	unsigned long itc_offset;
+ *	unsigned long itc_last;
+ *	unsigned long ret_itc_last;
+ *
+ *	itc_offset = XEN_MAPPEDREGS->itc_offset;
+ *	do {
+ *		itc_last = XEN_MAPPEDREGS->itc_last;
+ *		res = ia64_native_getreg(_IA64_REG_AR_ITC);
+ *		res += itc_offset;
+ *		if (itc_last >= res)
+ *			res = itc_last + 1;
+ *		ret_itc_last = cmpxchg(&XEN_MAPPEDREGS->itc_last,
+ *				       itc_last, res);
+ *	} while (unlikely(ret_itc_last != itc_last));
+ *	return res;
+ */
+/* 5 bundles */
+DEFINE_FUNC0(get_itc,
+	     "mov r2 = " __stringify(XSI_BASE) " + "
+	     __stringify(XSI_ITC_OFFSET_OFS) "\n"
+	     ";;\n"
+	     "ld8 r9 = [r2], " __stringify(XSI_ITC_LAST_OFS) " - "
+	     __stringify(XSI_ITC_OFFSET_OFS) "\n"
+					/* r9 = itc_offset */
+					/* r2 = XSI_ITC_OFFSET */
+	     "888:\n"
+	     "mov r8 = ar.itc\n"	/* res = ar.itc */
+	     ";;\n"
+	     "ld8 r3 = [r2]\n"		/* r3 = itc_last */
+	     "add r8 = r8, r9\n"	/* res = ar.itc + itc_offset */
+	     ";;\n"
+	     "cmp.gtu p6, p0 = r3, r8\n"
+	     ";;\n"
+	     "(p6) add r8 = 1, r3\n"	/* if (itc_last > res) itc_last + 1 */
+	     ";;\n"
+	     "mov ar.ccv = r8\n"
+	     ";;\n"
+	     "cmpxchg8.acq r10 = [r2], r8, ar.ccv\n"
+	     ";;\n"
+	     "cmp.ne p6, p0 = r10, r3\n"
+	     "(p6) hint @pause\n"
+	     "(p6) br.cond.spnt 888b\n");
+
+DEFINE_VOID_FUNC1_VOID(fc,
+		       "break " __stringify(HYPERPRIVOP_FC) "\n");
+
+/*
+ * psr_i_addr_addr = XEN_PSR_I_ADDR_ADDR
+ * masked_addr = *psr_i_addr_addr
+ * pending_intr_addr = masked_addr - 1
+ * if (val & IA64_PSR_I) {
+ *   masked = *masked_addr
+ *   *masked_addr = 0:xen_set_virtual_psr_i(1)
+ *   compiler barrier
+ *   if (masked) {
+ *      uint8_t pending = *pending_intr_addr;
+ *      if (pending)
+ *              XEN_HYPER_SSM_I
+ *   }
+ * } else {
+ *   *masked_addr = 1:xen_set_virtual_psr_i(0)
+ * }
+ */
+/* 6 bundles */
+DEFINE_VOID_FUNC1(intrin_local_irq_restore,
+		  /* r8 = input value: 0 or IA64_PSR_I
+		   * p6 =  (flags & IA64_PSR_I)
+		   *    = if clause
+		   * p7 = !(flags & IA64_PSR_I)
+		   *    = else clause
+		   */
+		  "cmp.ne p6, p7 = r8, r0\n"
+		  "mov r9 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
+		  ";;\n"
+		  /* r9 = XEN_PSR_I_ADDR */
+		  "ld8 r9 = [r9]\n"
+		  ";;\n"
+
+		  /* r10 = masked previous value */
+		  "(p6)	ld1.acq r10 = [r9]\n"
+		  ";;\n"
+
+		  /* p8 = !masked interrupt masked previously? */
+		  "(p6)	cmp.ne.unc p8, p0 = r10, r0\n"
+
+		  /* p7 = else clause */
+		  "(p7)	mov r11 = 1\n"
+		  ";;\n"
+		  /* masked = 1 */
+		  "(p7)	st1.rel [r9] = r11\n"
+
+		  /* p6 = if clause */
+		  /* masked = 0
+		   * r9 = masked_addr - 1
+		   *    = pending_intr_addr
+		   */
+		  "(p8)	st1.rel [r9] = r0, -1\n"
+		  ";;\n"
+		  /* r8 = pending_intr */
+		  "(p8)	ld1.acq r11 = [r9]\n"
+		  ";;\n"
+		  /* p9 = interrupt pending? */
+		  "(p8)	cmp.ne.unc p9, p10 = r11, r0\n"
+		  ";;\n"
+		  "(p10) mf\n"
+		  /* issue hypercall to trigger interrupt */
+		  "(p9)	break " __stringify(HYPERPRIVOP_SSM_I) "\n");
+
+DEFINE_VOID_FUNC2(ptcga,
+		  "break " __stringify(HYPERPRIVOP_PTC_GA) "\n");
+DEFINE_VOID_FUNC2(set_rr,
+		  "break " __stringify(HYPERPRIVOP_SET_RR) "\n");
+
+/*
+ * tmp = XEN_MAPPEDREGS->interrupt_mask_addr = XEN_PSR_I_ADDR_ADDR;
+ * tmp = *tmp
+ * tmp = *tmp;
+ * psr_i = tmp? 0: IA64_PSR_I;
+ */
+/* 4 bundles */
+DEFINE_FUNC0(get_psr_i,
+	     "mov r9 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
+	     ";;\n"
+	     "ld8 r9 = [r9]\n"			/* r9 = XEN_PSR_I_ADDR */
+	     "mov r8 = 0\n"			/* psr_i = 0 */
+	     ";;\n"
+	     "ld1.acq r9 = [r9]\n"		/* r9 = XEN_PSR_I */
+	     ";;\n"
+	     "cmp.eq.unc p6, p0 = r9, r0\n"	/* p6 = (XEN_PSR_I != 0) */
+	     ";;\n"
+	     "(p6) mov r8 = " __stringify(1 << IA64_PSR_I_BIT) "\n");
+
+DEFINE_FUNC1(thash, unsigned long,
+	     "break " __stringify(HYPERPRIVOP_THASH) "\n");
+DEFINE_FUNC1(get_cpuid, int,
+	     "break " __stringify(HYPERPRIVOP_GET_CPUID) "\n");
+DEFINE_FUNC1(get_pmd, int,
+	     "break " __stringify(HYPERPRIVOP_GET_PMD) "\n");
+DEFINE_FUNC1(get_rr, unsigned long,
+	     "break " __stringify(HYPERPRIVOP_GET_RR) "\n");
+
+/*
+ * void xen_privop_ssm_i(void)
+ *
+ * int masked = !xen_get_virtual_psr_i();
+ *	// masked = *(*XEN_MAPPEDREGS->interrupt_mask_addr)
+ * xen_set_virtual_psr_i(1)
+ *	// *(*XEN_MAPPEDREGS->interrupt_mask_addr) = 0
+ * // compiler barrier
+ * if (masked) {
+ *	uint8_t* pend_int_addr =
+ *		(uint8_t*)(*XEN_MAPPEDREGS->interrupt_mask_addr) - 1;
+ *	uint8_t pending = *pend_int_addr;
+ *	if (pending)
+ *		XEN_HYPER_SSM_I
+ * }
+ */
+/* 4 bundles */
+DEFINE_VOID_FUNC0(ssm_i,
+		  "mov r8 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
+		  ";;\n"
+		  "ld8 r8 = [r8]\n"		/* r8 = XEN_PSR_I_ADDR */
+		  ";;\n"
+		  "ld1.acq r9 = [r8]\n"		/* r9 = XEN_PSR_I */
+		  ";;\n"
+		  "st1.rel [r8] = r0, -1\n"	/* psr_i = 0. enable interrupt
+						 * r8 = XEN_PSR_I_ADDR - 1
+						 *    = pend_int_addr
+						 */
+		  "cmp.eq.unc p0, p6 = r9, r0\n"/* p6 = !XEN_PSR_I
+						 * previously interrupt
+						 * masked?
+						 */
+		  ";;\n"
+		  "(p6) ld1.acq r8 = [r8]\n"	/* r8 = xen_pend_int */
+		  ";;\n"
+		  "(p6) cmp.eq.unc p6, p7 = r8, r0\n"	/*interrupt pending?*/
+		  ";;\n"
+		  /* issue hypercall to get interrupt */
+		  "(p7) break " __stringify(HYPERPRIVOP_SSM_I) "\n"
+		  ";;\n");
+
+/*
+ * psr_i_addr_addr = XEN_MAPPEDREGS->interrupt_mask_addr
+ *		   = XEN_PSR_I_ADDR_ADDR;
+ * psr_i_addr = *psr_i_addr_addr;
+ * *psr_i_addr = 1;
+ */
+/* 2 bundles */
+DEFINE_VOID_FUNC0(rsm_i,
+		  "mov r8 = " __stringify(XEN_PSR_I_ADDR_ADDR) "\n"
+						/* r8 = XEN_PSR_I_ADDR */
+		  "mov r9 = 1\n"
+		  ";;\n"
+		  "ld8 r8 = [r8]\n"		/* r8 = XEN_PSR_I */
+		  ";;\n"
+		  "st1.rel [r8] = r9\n");	/* XEN_PSR_I = 1 */
+
+extern void
+xen_set_rr0_to_rr4(unsigned long val0, unsigned long val1,
+		   unsigned long val2, unsigned long val3,
+		   unsigned long val4);
+__DEFINE_FUNC(set_rr0_to_rr4,
+	      "break " __stringify(HYPERPRIVOP_SET_RR0_TO_RR4) "\n");
+
+
+extern unsigned long xen_getreg(int regnum);
+#define __DEFINE_GET_REG(id, privop)					\
+	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"			\
+	";;\n"								\
+	"cmp.eq p6, p0 = r2, r8\n"					\
+	";;\n"								\
+	"(p6) break " __stringify(HYPERPRIVOP_GET_ ## privop) "\n"	\
+	"(p6) br.cond.sptk.many b6\n"					\
+	";;\n"
+
+__DEFINE_FUNC(getreg,
+	      __DEFINE_GET_REG(PSR, PSR)
+#ifdef CONFIG_IA32_SUPPORT
+	      __DEFINE_GET_REG(AR_EFLAG, EFLAG)
+#endif
+
+	      /* get_itc */
+	      "mov r2 = " __stringify(_IA64_REG_AR_ITC) "\n"
+	      ";;\n"
+	      "cmp.eq p6, p0 = r2, r8\n"
+	      ";;\n"
+	      "(p6) br.cond.spnt xen_get_itc\n"
+	      ";;\n"
+
+	      /* get itm */
+	      "mov r2 = " __stringify(_IA64_REG_CR_ITM) "\n"
+	      ";;\n"
+	      "cmp.eq p6, p0 = r2, r8\n"
+	      ";;\n"
+	      "(p6) br.cond.spnt xen_get_itm_with_offset\n"
+	      ";;\n"
+
+	      __DEFINE_GET_REG(CR_IVR, IVR)
+	      __DEFINE_GET_REG(CR_TPR, TPR)
+
+	      /* fall back */
+	      "movl r2 = ia64_native_getreg_func\n"
+	      ";;\n"
+	      "mov b7 = r2\n"
+	      ";;\n"
+	      "br.cond.sptk.many b7\n");
+
+extern void xen_setreg(int regnum, unsigned long val);
+#define __DEFINE_SET_REG(id, privop)					\
+	"mov r2 = " __stringify(_IA64_REG_ ## id) "\n"			\
+	";;\n"								\
+	"cmp.eq p6, p0 = r2, r9\n"					\
+	";;\n"								\
+	"(p6) break " __stringify(HYPERPRIVOP_ ## privop) "\n"		\
+	"(p6) br.cond.sptk.many b6\n"					\
+	";;\n"
+
+__DEFINE_FUNC(setreg,
+	      /* kr0 .. kr 7*/
+	      /*
+	       * if (_IA64_REG_AR_KR0 <= regnum &&
+	       *     regnum <= _IA64_REG_AR_KR7) {
+	       *     register __index asm ("r8") = regnum - _IA64_REG_AR_KR0
+	       *     register __val asm ("r9") = val
+	       *    "break HYPERPRIVOP_SET_KR"
+	       * }
+	       */
+	      "mov r17 = r9\n"
+	      "mov r2 = " __stringify(_IA64_REG_AR_KR0) "\n"
+	      ";;\n"
+	      "cmp.ge p6, p0 = r9, r2\n"
+	      "sub r17 = r17, r2\n"
+	      ";;\n"
+	      "(p6) cmp.ge.unc p7, p0 = "
+	      __stringify(_IA64_REG_AR_KR7) " - " __stringify(_IA64_REG_AR_KR0)
+	      ", r17\n"
+	      ";;\n"
+	      "(p7) mov r9 = r8\n"
+	      ";;\n"
+	      "(p7) mov r8 = r17\n"
+	      "(p7) break " __stringify(HYPERPRIVOP_SET_KR) "\n"
+
+	      /* set itm */
+	      "mov r2 = " __stringify(_IA64_REG_CR_ITM) "\n"
+	      ";;\n"
+	      "cmp.eq p6, p0 = r2, r8\n"
+	      ";;\n"
+	      "(p6) br.cond.spnt xen_set_itm_with_offset\n"
+
+	      /* set itc */
+	      "mov r2 = " __stringify(_IA64_REG_AR_ITC) "\n"
+	      ";;\n"
+	      "cmp.eq p6, p0 = r2, r8\n"
+	      ";;\n"
+	      "(p6) br.cond.spnt xen_set_itc\n"
+
+#ifdef CONFIG_IA32_SUPPORT
+	      __DEFINE_SET_REG(AR_EFLAG, SET_EFLAG)
+#endif
+	      __DEFINE_SET_REG(CR_TPR, SET_TPR)
+	      __DEFINE_SET_REG(CR_EOI, EOI)
+
+	      /* fall back */
+	      "movl r2 = ia64_native_setreg_func\n"
+	      ";;\n"
+	      "mov b7 = r2\n"
+	      ";;\n"
+	      "br.cond.sptk.many b7\n");
+#endif
+
+static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.fc		= xen_fc,
 	.thash		= xen_thash,
 	.get_cpuid	= xen_get_cpuid,
@@ -337,7 +880,7 @@ xen_iosapic_write(char __iomem *iosapic, unsigned int reg, u32 val)
 	HYPERVISOR_physdev_op(PHYSDEVOP_apic_write, &apic_op);
 }
 
-static const struct pv_iosapic_ops xen_iosapic_ops __initconst = {
+static struct pv_iosapic_ops xen_iosapic_ops __initdata = {
 	.pcat_compat_init = xen_pcat_compat_init,
 	.__get_irq_chip = xen_iosapic_get_irq_chip,
 
@@ -355,6 +898,8 @@ xen_setup_pv_ops(void)
 	xen_info_init();
 	pv_info = xen_info;
 	pv_init_ops = xen_init_ops;
+	pv_fsys_data = xen_fsys_data;
+	pv_patchdata = xen_patchdata;
 	pv_cpu_ops = xen_cpu_ops;
 	pv_iosapic_ops = xen_iosapic_ops;
 	pv_irq_ops = xen_irq_ops;
@@ -362,3 +907,252 @@ xen_setup_pv_ops(void)
 
 	paravirt_cpu_asm_init(&xen_cpu_asm_switch);
 }
+
+#ifdef ASM_SUPPORTED
+/***************************************************************************
+ * binary pacthing
+ * pv_init_ops.patch_bundle
+ */
+
+#define DEFINE_FUNC_GETREG(name, privop)				\
+	DEFINE_FUNC0(get_ ## name,					\
+		     "break "__stringify(HYPERPRIVOP_GET_ ## privop) "\n")
+
+DEFINE_FUNC_GETREG(psr, PSR);
+DEFINE_FUNC_GETREG(eflag, EFLAG);
+DEFINE_FUNC_GETREG(ivr, IVR);
+DEFINE_FUNC_GETREG(tpr, TPR);
+
+#define DEFINE_FUNC_SET_KR(n)						\
+	DEFINE_VOID_FUNC0(set_kr ## n,					\
+			  ";;\n"					\
+			  "mov r9 = r8\n"				\
+			  "mov r8 = " #n "\n"				\
+			  "break " __stringify(HYPERPRIVOP_SET_KR) "\n")
+
+DEFINE_FUNC_SET_KR(0);
+DEFINE_FUNC_SET_KR(1);
+DEFINE_FUNC_SET_KR(2);
+DEFINE_FUNC_SET_KR(3);
+DEFINE_FUNC_SET_KR(4);
+DEFINE_FUNC_SET_KR(5);
+DEFINE_FUNC_SET_KR(6);
+DEFINE_FUNC_SET_KR(7);
+
+#define __DEFINE_FUNC_SETREG(name, privop)				\
+	DEFINE_VOID_FUNC0(name,						\
+			  "break "__stringify(HYPERPRIVOP_ ## privop) "\n")
+
+#define DEFINE_FUNC_SETREG(name, privop)			\
+	__DEFINE_FUNC_SETREG(set_ ## name, SET_ ## privop)
+
+DEFINE_FUNC_SETREG(eflag, EFLAG);
+DEFINE_FUNC_SETREG(tpr, TPR);
+__DEFINE_FUNC_SETREG(eoi, EOI);
+
+extern const char xen_check_events[];
+extern const char __xen_intrin_local_irq_restore_direct_start[];
+extern const char __xen_intrin_local_irq_restore_direct_end[];
+extern const unsigned long __xen_intrin_local_irq_restore_direct_reloc;
+
+asm (
+	".align 32\n"
+	".proc xen_check_events\n"
+	"xen_check_events:\n"
+	/* masked = 0
+	 * r9 = masked_addr - 1
+	 *    = pending_intr_addr
+	 */
+	"st1.rel [r9] = r0, -1\n"
+	";;\n"
+	/* r8 = pending_intr */
+	"ld1.acq r11 = [r9]\n"
+	";;\n"
+	/* p9 = interrupt pending? */
+	"cmp.ne p9, p10 = r11, r0\n"
+	";;\n"
+	"(p10) mf\n"
+	/* issue hypercall to trigger interrupt */
+	"(p9) break " __stringify(HYPERPRIVOP_SSM_I) "\n"
+	"br.cond.sptk.many b6\n"
+	".endp xen_check_events\n"
+	"\n"
+	".align 32\n"
+	".proc __xen_intrin_local_irq_restore_direct\n"
+	"__xen_intrin_local_irq_restore_direct:\n"
+	"__xen_intrin_local_irq_restore_direct_start:\n"
+	"1:\n"
+	"{\n"
+	"cmp.ne p6, p7 = r8, r0\n"
+	"mov r17 = ip\n" /* get ip to calc return address */
+	"mov r9 = "__stringify(XEN_PSR_I_ADDR_ADDR) "\n"
+	";;\n"
+	"}\n"
+	"{\n"
+	/* r9 = XEN_PSR_I_ADDR */
+	"ld8 r9 = [r9]\n"
+	";;\n"
+	/* r10 = masked previous value */
+	"(p6) ld1.acq r10 = [r9]\n"
+	"adds r17 =  1f - 1b, r17\n" /* calculate return address */
+	";;\n"
+	"}\n"
+	"{\n"
+	/* p8 = !masked interrupt masked previously? */
+	"(p6) cmp.ne.unc p8, p0 = r10, r0\n"
+	"\n"
+	/* p7 = else clause */
+	"(p7) mov r11 = 1\n"
+	";;\n"
+	"(p8) mov b6 = r17\n" /* set return address */
+	"}\n"
+	"{\n"
+	/* masked = 1 */
+	"(p7) st1.rel [r9] = r11\n"
+	"\n"
+	"[99:]\n"
+	"(p8) brl.cond.dptk.few xen_check_events\n"
+	"}\n"
+	/* pv calling stub is 5 bundles. fill nop to adjust return address */
+	"{\n"
+	"nop 0\n"
+	"nop 0\n"
+	"nop 0\n"
+	"}\n"
+	"1:\n"
+	"__xen_intrin_local_irq_restore_direct_end:\n"
+	".endp __xen_intrin_local_irq_restore_direct\n"
+	"\n"
+	".align 8\n"
+	"__xen_intrin_local_irq_restore_direct_reloc:\n"
+	"data8 99b\n"
+);
+
+static struct paravirt_patch_bundle_elem xen_patch_bundle_elems[]
+__initdata_or_module =
+{
+#define XEN_PATCH_BUNDLE_ELEM(name, type)		\
+	{						\
+		(void*)xen_ ## name ## _direct_start,	\
+		(void*)xen_ ## name ## _direct_end,	\
+		PARAVIRT_PATCH_TYPE_ ## type,		\
+	}
+
+	XEN_PATCH_BUNDLE_ELEM(fc, FC),
+	XEN_PATCH_BUNDLE_ELEM(thash, THASH),
+	XEN_PATCH_BUNDLE_ELEM(get_cpuid, GET_CPUID),
+	XEN_PATCH_BUNDLE_ELEM(get_pmd, GET_PMD),
+	XEN_PATCH_BUNDLE_ELEM(ptcga, PTCGA),
+	XEN_PATCH_BUNDLE_ELEM(get_rr, GET_RR),
+	XEN_PATCH_BUNDLE_ELEM(set_rr, SET_RR),
+	XEN_PATCH_BUNDLE_ELEM(set_rr0_to_rr4, SET_RR0_TO_RR4),
+	XEN_PATCH_BUNDLE_ELEM(ssm_i, SSM_I),
+	XEN_PATCH_BUNDLE_ELEM(rsm_i, RSM_I),
+	XEN_PATCH_BUNDLE_ELEM(get_psr_i, GET_PSR_I),
+	{
+		(void*)__xen_intrin_local_irq_restore_direct_start,
+		(void*)__xen_intrin_local_irq_restore_direct_end,
+		PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE,
+	},
+
+#define XEN_PATCH_BUNDLE_ELEM_GETREG(name, reg)			\
+	{							\
+		xen_get_ ## name ## _direct_start,		\
+		xen_get_ ## name ## _direct_end,		\
+		PARAVIRT_PATCH_TYPE_GETREG + _IA64_REG_ ## reg, \
+	}
+
+	XEN_PATCH_BUNDLE_ELEM_GETREG(psr, PSR),
+	XEN_PATCH_BUNDLE_ELEM_GETREG(eflag, AR_EFLAG),
+
+	XEN_PATCH_BUNDLE_ELEM_GETREG(ivr, CR_IVR),
+	XEN_PATCH_BUNDLE_ELEM_GETREG(tpr, CR_TPR),
+
+	XEN_PATCH_BUNDLE_ELEM_GETREG(itc, AR_ITC),
+	XEN_PATCH_BUNDLE_ELEM_GETREG(itm_with_offset, CR_ITM),
+
+
+#define __XEN_PATCH_BUNDLE_ELEM_SETREG(name, reg)		\
+	{							\
+		xen_ ## name ## _direct_start,			\
+		xen_ ## name ## _direct_end,			\
+		PARAVIRT_PATCH_TYPE_SETREG + _IA64_REG_ ## reg, \
+	}
+
+#define XEN_PATCH_BUNDLE_ELEM_SETREG(name, reg)			\
+	__XEN_PATCH_BUNDLE_ELEM_SETREG(set_ ## name, reg)
+
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr0, AR_KR0),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr1, AR_KR1),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr2, AR_KR2),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr3, AR_KR3),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr4, AR_KR4),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr5, AR_KR5),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr6, AR_KR6),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(kr7, AR_KR7),
+
+	XEN_PATCH_BUNDLE_ELEM_SETREG(eflag, AR_EFLAG),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(tpr, CR_TPR),
+	__XEN_PATCH_BUNDLE_ELEM_SETREG(eoi, CR_EOI),
+
+	XEN_PATCH_BUNDLE_ELEM_SETREG(itc, AR_ITC),
+	XEN_PATCH_BUNDLE_ELEM_SETREG(itm_with_offset, CR_ITM),
+};
+
+static unsigned long __init_or_module
+xen_patch_bundle(void *sbundle, void *ebundle, unsigned long type)
+{
+	const unsigned long nelems = sizeof(xen_patch_bundle_elems) /
+		sizeof(xen_patch_bundle_elems[0]);
+	unsigned long used;
+	const struct paravirt_patch_bundle_elem *found;
+
+	used = __paravirt_patch_apply_bundle(sbundle, ebundle, type,
+					     xen_patch_bundle_elems, nelems,
+					     &found);
+
+	if (found == NULL)
+		/* fallback */
+		return ia64_native_patch_bundle(sbundle, ebundle, type);
+	if (used == 0)
+		return used;
+
+	/* relocation */
+	switch (type) {
+	case PARAVIRT_PATCH_TYPE_INTRIN_LOCAL_IRQ_RESTORE: {
+		unsigned long reloc =
+			__xen_intrin_local_irq_restore_direct_reloc;
+		unsigned long reloc_offset = reloc - (unsigned long)
+			__xen_intrin_local_irq_restore_direct_start;
+		unsigned long tag = (unsigned long)sbundle + reloc_offset;
+		paravirt_patch_reloc_brl(tag, xen_check_events);
+		break;
+	}
+	default:
+		/* nothing */
+		break;
+	}
+	return used;
+}
+#endif /* ASM_SUPPOTED */
+
+const struct paravirt_patch_branch_target xen_branch_target[]
+__initconst = {
+#define PARAVIRT_BR_TARGET(name, type)			\
+	{						\
+		&xen_ ## name,				\
+		PARAVIRT_PATCH_TYPE_BR_ ## type,	\
+	}
+	PARAVIRT_BR_TARGET(switch_to, SWITCH_TO),
+	PARAVIRT_BR_TARGET(leave_syscall, LEAVE_SYSCALL),
+	PARAVIRT_BR_TARGET(work_processed_syscall, WORK_PROCESSED_SYSCALL),
+	PARAVIRT_BR_TARGET(leave_kernel, LEAVE_KERNEL),
+};
+
+static void __init
+xen_patch_branch(unsigned long tag, unsigned long type)
+{
+	const unsigned long nelem =
+		sizeof(xen_branch_target) / sizeof(xen_branch_target[0]);
+	__paravirt_patch_apply_branch(tag, type, xen_branch_target, nelem);
+}
diff --git a/arch/m32r/kernel/process.c b/arch/m32r/kernel/process.c
index 7103d91e1a2f..3e876f0baebc 100644
--- a/arch/m32r/kernel/process.c
+++ b/arch/m32r/kernel/process.c
@@ -225,7 +225,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 	return 0; /* Task didn't use the fpu at all. */
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long spu,
+int copy_thread(unsigned long clone_flags, unsigned long spu,
 	unsigned long unused, struct task_struct *tsk, struct pt_regs *regs)
 {
 	struct pt_regs *childregs = task_pt_regs(tsk);
diff --git a/arch/m68k/include/asm/bootinfo.h b/arch/m68k/include/asm/bootinfo.h
index fedf3e326121..fb8a06b9ab6a 100644
--- a/arch/m68k/include/asm/bootinfo.h
+++ b/arch/m68k/include/asm/bootinfo.h
@@ -1,5 +1,378 @@
-#ifdef __uClinux__
-#include "bootinfo_no.h"
-#else
-#include "bootinfo_mm.h"
+/*
+** asm/bootinfo.h -- Definition of the Linux/m68k boot information structure
+**
+** Copyright 1992 by Greg Harp
+**
+** This file is subject to the terms and conditions of the GNU General Public
+** License.  See the file COPYING in the main directory of this archive
+** for more details.
+**
+** Created 09/29/92 by Greg Harp
+**
+** 5/2/94 Roman Hodek:
+**   Added bi_atari part of the machine dependent union bi_un; for now it
+**   contains just a model field to distinguish between TT and Falcon.
+** 26/7/96 Roman Zippel:
+**   Renamed to setup.h; added some useful macros to allow gcc some
+**   optimizations if possible.
+** 5/10/96 Geert Uytterhoeven:
+**   Redesign of the boot information structure; renamed to bootinfo.h again
+** 27/11/96 Geert Uytterhoeven:
+**   Backwards compatibility with bootinfo interface version 1.0
+*/
+
+#ifndef _M68K_BOOTINFO_H
+#define _M68K_BOOTINFO_H
+
+
+    /*
+     *  Bootinfo definitions
+     *
+     *  This is an easily parsable and extendable structure containing all
+     *  information to be passed from the bootstrap to the kernel.
+     *
+     *  This way I hope to keep all future changes back/forewards compatible.
+     *  Thus, keep your fingers crossed...
+     *
+     *  This structure is copied right after the kernel bss by the bootstrap
+     *  routine.
+     */
+
+#ifndef __ASSEMBLY__
+
+struct bi_record {
+    unsigned short tag;			/* tag ID */
+    unsigned short size;		/* size of record (in bytes) */
+    unsigned long data[0];		/* data */
+};
+
+#endif /* __ASSEMBLY__ */
+
+
+    /*
+     *  Tag Definitions
+     *
+     *  Machine independent tags start counting from 0x0000
+     *  Machine dependent tags start counting from 0x8000
+     */
+
+#define BI_LAST			0x0000	/* last record (sentinel) */
+#define BI_MACHTYPE		0x0001	/* machine type (u_long) */
+#define BI_CPUTYPE		0x0002	/* cpu type (u_long) */
+#define BI_FPUTYPE		0x0003	/* fpu type (u_long) */
+#define BI_MMUTYPE		0x0004	/* mmu type (u_long) */
+#define BI_MEMCHUNK		0x0005	/* memory chunk address and size */
+					/* (struct mem_info) */
+#define BI_RAMDISK		0x0006	/* ramdisk address and size */
+					/* (struct mem_info) */
+#define BI_COMMAND_LINE		0x0007	/* kernel command line parameters */
+					/* (string) */
+
+    /*
+     *  Amiga-specific tags
+     */
+
+#define BI_AMIGA_MODEL		0x8000	/* model (u_long) */
+#define BI_AMIGA_AUTOCON	0x8001	/* AutoConfig device */
+					/* (struct ConfigDev) */
+#define BI_AMIGA_CHIP_SIZE	0x8002	/* size of Chip RAM (u_long) */
+#define BI_AMIGA_VBLANK		0x8003	/* VBLANK frequency (u_char) */
+#define BI_AMIGA_PSFREQ		0x8004	/* power supply frequency (u_char) */
+#define BI_AMIGA_ECLOCK		0x8005	/* EClock frequency (u_long) */
+#define BI_AMIGA_CHIPSET	0x8006	/* native chipset present (u_long) */
+#define BI_AMIGA_SERPER		0x8007	/* serial port period (u_short) */
+
+    /*
+     *  Atari-specific tags
+     */
+
+#define BI_ATARI_MCH_COOKIE	0x8000	/* _MCH cookie from TOS (u_long) */
+#define BI_ATARI_MCH_TYPE	0x8001	/* special machine type (u_long) */
+					/* (values are ATARI_MACH_* defines */
+
+/* mch_cookie values (upper word) */
+#define ATARI_MCH_ST		0
+#define ATARI_MCH_STE		1
+#define ATARI_MCH_TT		2
+#define ATARI_MCH_FALCON	3
+
+/* mch_type values */
+#define ATARI_MACH_NORMAL	0	/* no special machine type */
+#define ATARI_MACH_MEDUSA	1	/* Medusa 040 */
+#define ATARI_MACH_HADES	2	/* Hades 040 or 060 */
+#define ATARI_MACH_AB40		3	/* Afterburner040 on Falcon */
+
+    /*
+     *  VME-specific tags
+     */
+
+#define BI_VME_TYPE		0x8000	/* VME sub-architecture (u_long) */
+#define BI_VME_BRDINFO		0x8001	/* VME board information (struct) */
+
+/* BI_VME_TYPE codes */
+#define	VME_TYPE_TP34V		0x0034	/* Tadpole TP34V */
+#define VME_TYPE_MVME147	0x0147	/* Motorola MVME147 */
+#define VME_TYPE_MVME162	0x0162	/* Motorola MVME162 */
+#define VME_TYPE_MVME166	0x0166	/* Motorola MVME166 */
+#define VME_TYPE_MVME167	0x0167	/* Motorola MVME167 */
+#define VME_TYPE_MVME172	0x0172	/* Motorola MVME172 */
+#define VME_TYPE_MVME177	0x0177	/* Motorola MVME177 */
+#define VME_TYPE_BVME4000	0x4000	/* BVM Ltd. BVME4000 */
+#define VME_TYPE_BVME6000	0x6000	/* BVM Ltd. BVME6000 */
+
+/* BI_VME_BRDINFO is a 32 byte struct as returned by the Bug code on
+ * Motorola VME boards.  Contains board number, Bug version, board
+ * configuration options, etc.  See include/asm/mvme16xhw.h for details.
+ */
+
+
+    /*
+     *  Macintosh-specific tags (all u_long)
+     */
+
+#define BI_MAC_MODEL		0x8000	/* Mac Gestalt ID (model type) */
+#define BI_MAC_VADDR		0x8001	/* Mac video base address */
+#define BI_MAC_VDEPTH		0x8002	/* Mac video depth */
+#define BI_MAC_VROW		0x8003	/* Mac video rowbytes */
+#define BI_MAC_VDIM		0x8004	/* Mac video dimensions */
+#define BI_MAC_VLOGICAL		0x8005	/* Mac video logical base */
+#define BI_MAC_SCCBASE		0x8006	/* Mac SCC base address */
+#define BI_MAC_BTIME		0x8007	/* Mac boot time */
+#define BI_MAC_GMTBIAS		0x8008	/* Mac GMT timezone offset */
+#define BI_MAC_MEMSIZE		0x8009	/* Mac RAM size (sanity check) */
+#define BI_MAC_CPUID		0x800a	/* Mac CPU type (sanity check) */
+#define BI_MAC_ROMBASE		0x800b	/* Mac system ROM base address */
+
+    /*
+     *  Macintosh hardware profile data - unused, see macintosh.h for
+     *  resonable type values
+     */
+
+#define BI_MAC_VIA1BASE		0x8010	/* Mac VIA1 base address (always present) */
+#define BI_MAC_VIA2BASE		0x8011	/* Mac VIA2 base address (type varies) */
+#define BI_MAC_VIA2TYPE		0x8012	/* Mac VIA2 type (VIA, RBV, OSS) */
+#define BI_MAC_ADBTYPE		0x8013	/* Mac ADB interface type */
+#define BI_MAC_ASCBASE		0x8014	/* Mac Apple Sound Chip base address */
+#define BI_MAC_SCSI5380		0x8015	/* Mac NCR 5380 SCSI (base address, multi) */
+#define BI_MAC_SCSIDMA		0x8016	/* Mac SCSI DMA (base address) */
+#define BI_MAC_SCSI5396		0x8017	/* Mac NCR 53C96 SCSI (base address, multi) */
+#define BI_MAC_IDETYPE		0x8018	/* Mac IDE interface type */
+#define BI_MAC_IDEBASE		0x8019	/* Mac IDE interface base address */
+#define BI_MAC_NUBUS		0x801a	/* Mac Nubus type (none, regular, pseudo) */
+#define BI_MAC_SLOTMASK		0x801b	/* Mac Nubus slots present */
+#define BI_MAC_SCCTYPE		0x801c	/* Mac SCC serial type (normal, IOP) */
+#define BI_MAC_ETHTYPE		0x801d	/* Mac builtin ethernet type (Sonic, MACE */
+#define BI_MAC_ETHBASE		0x801e	/* Mac builtin ethernet base address */
+#define BI_MAC_PMU		0x801f	/* Mac power management / poweroff hardware */
+#define BI_MAC_IOP_SWIM		0x8020	/* Mac SWIM floppy IOP */
+#define BI_MAC_IOP_ADB		0x8021	/* Mac ADB IOP */
+
+    /*
+     * Mac: compatibility with old booter data format (temporarily)
+     * Fields unused with the new bootinfo can be deleted now; instead of
+     * adding new fields the struct might be splitted into a hardware address
+     * part and a hardware type part
+     */
+
+#ifndef __ASSEMBLY__
+
+struct mac_booter_data
+{
+	unsigned long videoaddr;
+	unsigned long videorow;
+	unsigned long videodepth;
+	unsigned long dimensions;
+	unsigned long args;
+	unsigned long boottime;
+	unsigned long gmtbias;
+	unsigned long bootver;
+	unsigned long videological;
+	unsigned long sccbase;
+	unsigned long id;
+	unsigned long memsize;
+	unsigned long serialmf;
+	unsigned long serialhsk;
+	unsigned long serialgpi;
+	unsigned long printmf;
+	unsigned long printhsk;
+	unsigned long printgpi;
+	unsigned long cpuid;
+	unsigned long rombase;
+	unsigned long adbdelay;
+	unsigned long timedbra;
+};
+
+extern struct mac_booter_data
+	mac_bi_data;
+
 #endif
+
+    /*
+     *  Apollo-specific tags
+     */
+
+#define BI_APOLLO_MODEL         0x8000  /* model (u_long) */
+
+    /*
+     *  HP300-specific tags
+     */
+
+#define BI_HP300_MODEL		0x8000	/* model (u_long) */
+#define BI_HP300_UART_SCODE	0x8001	/* UART select code (u_long) */
+#define BI_HP300_UART_ADDR	0x8002	/* phys. addr of UART (u_long) */
+
+    /*
+     * Stuff for bootinfo interface versioning
+     *
+     * At the start of kernel code, a 'struct bootversion' is located.
+     * bootstrap checks for a matching version of the interface before booting
+     * a kernel, to avoid user confusion if kernel and bootstrap don't work
+     * together :-)
+     *
+     * If incompatible changes are made to the bootinfo interface, the major
+     * number below should be stepped (and the minor reset to 0) for the
+     * appropriate machine. If a change is backward-compatible, the minor
+     * should be stepped. "Backwards-compatible" means that booting will work,
+     * but certain features may not.
+     */
+
+#define BOOTINFOV_MAGIC			0x4249561A	/* 'BIV^Z' */
+#define MK_BI_VERSION(major,minor)	(((major)<<16)+(minor))
+#define BI_VERSION_MAJOR(v)		(((v) >> 16) & 0xffff)
+#define BI_VERSION_MINOR(v)		((v) & 0xffff)
+
+#ifndef __ASSEMBLY__
+
+struct bootversion {
+    unsigned short branch;
+    unsigned long magic;
+    struct {
+	unsigned long machtype;
+	unsigned long version;
+    } machversions[0];
+};
+
+#endif /* __ASSEMBLY__ */
+
+#define AMIGA_BOOTI_VERSION    MK_BI_VERSION( 2, 0 )
+#define ATARI_BOOTI_VERSION    MK_BI_VERSION( 2, 1 )
+#define MAC_BOOTI_VERSION      MK_BI_VERSION( 2, 0 )
+#define MVME147_BOOTI_VERSION  MK_BI_VERSION( 2, 0 )
+#define MVME16x_BOOTI_VERSION  MK_BI_VERSION( 2, 0 )
+#define BVME6000_BOOTI_VERSION MK_BI_VERSION( 2, 0 )
+#define Q40_BOOTI_VERSION      MK_BI_VERSION( 2, 0 )
+#define HP300_BOOTI_VERSION    MK_BI_VERSION( 2, 0 )
+
+#ifdef BOOTINFO_COMPAT_1_0
+
+    /*
+     *  Backwards compatibility with bootinfo interface version 1.0
+     */
+
+#define COMPAT_AMIGA_BOOTI_VERSION    MK_BI_VERSION( 1, 0 )
+#define COMPAT_ATARI_BOOTI_VERSION    MK_BI_VERSION( 1, 0 )
+#define COMPAT_MAC_BOOTI_VERSION      MK_BI_VERSION( 1, 0 )
+
+#include <linux/zorro.h>
+
+#define COMPAT_NUM_AUTO    16
+
+struct compat_bi_Amiga {
+    int model;
+    int num_autocon;
+    struct ConfigDev autocon[COMPAT_NUM_AUTO];
+    unsigned long chip_size;
+    unsigned char vblank;
+    unsigned char psfreq;
+    unsigned long eclock;
+    unsigned long chipset;
+    unsigned long hw_present;
+};
+
+struct compat_bi_Atari {
+    unsigned long hw_present;
+    unsigned long mch_cookie;
+};
+
+#ifndef __ASSEMBLY__
+
+struct compat_bi_Macintosh
+{
+	unsigned long videoaddr;
+	unsigned long videorow;
+	unsigned long videodepth;
+	unsigned long dimensions;
+	unsigned long args;
+	unsigned long boottime;
+	unsigned long gmtbias;
+	unsigned long bootver;
+	unsigned long videological;
+	unsigned long sccbase;
+	unsigned long id;
+	unsigned long memsize;
+	unsigned long serialmf;
+	unsigned long serialhsk;
+	unsigned long serialgpi;
+	unsigned long printmf;
+	unsigned long printhsk;
+	unsigned long printgpi;
+	unsigned long cpuid;
+	unsigned long rombase;
+	unsigned long adbdelay;
+	unsigned long timedbra;
+};
+
+#endif
+
+struct compat_mem_info {
+    unsigned long addr;
+    unsigned long size;
+};
+
+#define COMPAT_NUM_MEMINFO  4
+
+#define COMPAT_CPUB_68020 0
+#define COMPAT_CPUB_68030 1
+#define COMPAT_CPUB_68040 2
+#define COMPAT_CPUB_68060 3
+#define COMPAT_FPUB_68881 5
+#define COMPAT_FPUB_68882 6
+#define COMPAT_FPUB_68040 7
+#define COMPAT_FPUB_68060 8
+
+#define COMPAT_CPU_68020    (1<<COMPAT_CPUB_68020)
+#define COMPAT_CPU_68030    (1<<COMPAT_CPUB_68030)
+#define COMPAT_CPU_68040    (1<<COMPAT_CPUB_68040)
+#define COMPAT_CPU_68060    (1<<COMPAT_CPUB_68060)
+#define COMPAT_CPU_MASK     (31)
+#define COMPAT_FPU_68881    (1<<COMPAT_FPUB_68881)
+#define COMPAT_FPU_68882    (1<<COMPAT_FPUB_68882)
+#define COMPAT_FPU_68040    (1<<COMPAT_FPUB_68040)
+#define COMPAT_FPU_68060    (1<<COMPAT_FPUB_68060)
+#define COMPAT_FPU_MASK     (0xfe0)
+
+#define COMPAT_CL_SIZE      (256)
+
+struct compat_bootinfo {
+    unsigned long machtype;
+    unsigned long cputype;
+    struct compat_mem_info memory[COMPAT_NUM_MEMINFO];
+    int num_memory;
+    unsigned long ramdisk_size;
+    unsigned long ramdisk_addr;
+    char command_line[COMPAT_CL_SIZE];
+    union {
+	struct compat_bi_Amiga     bi_ami;
+	struct compat_bi_Atari     bi_ata;
+	struct compat_bi_Macintosh bi_mac;
+    } bi_un;
+};
+
+#define bi_amiga	bi_un.bi_ami
+#define bi_atari	bi_un.bi_ata
+#define bi_mac		bi_un.bi_mac
+
+#endif /* BOOTINFO_COMPAT_1_0 */
+
+
+#endif /* _M68K_BOOTINFO_H */
diff --git a/arch/m68k/include/asm/bootinfo_mm.h b/arch/m68k/include/asm/bootinfo_mm.h
deleted file mode 100644
index fb8a06b9ab6a..000000000000
--- a/arch/m68k/include/asm/bootinfo_mm.h
+++ /dev/null
@@ -1,378 +0,0 @@
-/*
-** asm/bootinfo.h -- Definition of the Linux/m68k boot information structure
-**
-** Copyright 1992 by Greg Harp
-**
-** This file is subject to the terms and conditions of the GNU General Public
-** License.  See the file COPYING in the main directory of this archive
-** for more details.
-**
-** Created 09/29/92 by Greg Harp
-**
-** 5/2/94 Roman Hodek:
-**   Added bi_atari part of the machine dependent union bi_un; for now it
-**   contains just a model field to distinguish between TT and Falcon.
-** 26/7/96 Roman Zippel:
-**   Renamed to setup.h; added some useful macros to allow gcc some
-**   optimizations if possible.
-** 5/10/96 Geert Uytterhoeven:
-**   Redesign of the boot information structure; renamed to bootinfo.h again
-** 27/11/96 Geert Uytterhoeven:
-**   Backwards compatibility with bootinfo interface version 1.0
-*/
-
-#ifndef _M68K_BOOTINFO_H
-#define _M68K_BOOTINFO_H
-
-
-    /*
-     *  Bootinfo definitions
-     *
-     *  This is an easily parsable and extendable structure containing all
-     *  information to be passed from the bootstrap to the kernel.
-     *
-     *  This way I hope to keep all future changes back/forewards compatible.
-     *  Thus, keep your fingers crossed...
-     *
-     *  This structure is copied right after the kernel bss by the bootstrap
-     *  routine.
-     */
-
-#ifndef __ASSEMBLY__
-
-struct bi_record {
-    unsigned short tag;			/* tag ID */
-    unsigned short size;		/* size of record (in bytes) */
-    unsigned long data[0];		/* data */
-};
-
-#endif /* __ASSEMBLY__ */
-
-
-    /*
-     *  Tag Definitions
-     *
-     *  Machine independent tags start counting from 0x0000
-     *  Machine dependent tags start counting from 0x8000
-     */
-
-#define BI_LAST			0x0000	/* last record (sentinel) */
-#define BI_MACHTYPE		0x0001	/* machine type (u_long) */
-#define BI_CPUTYPE		0x0002	/* cpu type (u_long) */
-#define BI_FPUTYPE		0x0003	/* fpu type (u_long) */
-#define BI_MMUTYPE		0x0004	/* mmu type (u_long) */
-#define BI_MEMCHUNK		0x0005	/* memory chunk address and size */
-					/* (struct mem_info) */
-#define BI_RAMDISK		0x0006	/* ramdisk address and size */
-					/* (struct mem_info) */
-#define BI_COMMAND_LINE		0x0007	/* kernel command line parameters */
-					/* (string) */
-
-    /*
-     *  Amiga-specific tags
-     */
-
-#define BI_AMIGA_MODEL		0x8000	/* model (u_long) */
-#define BI_AMIGA_AUTOCON	0x8001	/* AutoConfig device */
-					/* (struct ConfigDev) */
-#define BI_AMIGA_CHIP_SIZE	0x8002	/* size of Chip RAM (u_long) */
-#define BI_AMIGA_VBLANK		0x8003	/* VBLANK frequency (u_char) */
-#define BI_AMIGA_PSFREQ		0x8004	/* power supply frequency (u_char) */
-#define BI_AMIGA_ECLOCK		0x8005	/* EClock frequency (u_long) */
-#define BI_AMIGA_CHIPSET	0x8006	/* native chipset present (u_long) */
-#define BI_AMIGA_SERPER		0x8007	/* serial port period (u_short) */
-
-    /*
-     *  Atari-specific tags
-     */
-
-#define BI_ATARI_MCH_COOKIE	0x8000	/* _MCH cookie from TOS (u_long) */
-#define BI_ATARI_MCH_TYPE	0x8001	/* special machine type (u_long) */
-					/* (values are ATARI_MACH_* defines */
-
-/* mch_cookie values (upper word) */
-#define ATARI_MCH_ST		0
-#define ATARI_MCH_STE		1
-#define ATARI_MCH_TT		2
-#define ATARI_MCH_FALCON	3
-
-/* mch_type values */
-#define ATARI_MACH_NORMAL	0	/* no special machine type */
-#define ATARI_MACH_MEDUSA	1	/* Medusa 040 */
-#define ATARI_MACH_HADES	2	/* Hades 040 or 060 */
-#define ATARI_MACH_AB40		3	/* Afterburner040 on Falcon */
-
-    /*
-     *  VME-specific tags
-     */
-
-#define BI_VME_TYPE		0x8000	/* VME sub-architecture (u_long) */
-#define BI_VME_BRDINFO		0x8001	/* VME board information (struct) */
-
-/* BI_VME_TYPE codes */
-#define	VME_TYPE_TP34V		0x0034	/* Tadpole TP34V */
-#define VME_TYPE_MVME147	0x0147	/* Motorola MVME147 */
-#define VME_TYPE_MVME162	0x0162	/* Motorola MVME162 */
-#define VME_TYPE_MVME166	0x0166	/* Motorola MVME166 */
-#define VME_TYPE_MVME167	0x0167	/* Motorola MVME167 */
-#define VME_TYPE_MVME172	0x0172	/* Motorola MVME172 */
-#define VME_TYPE_MVME177	0x0177	/* Motorola MVME177 */
-#define VME_TYPE_BVME4000	0x4000	/* BVM Ltd. BVME4000 */
-#define VME_TYPE_BVME6000	0x6000	/* BVM Ltd. BVME6000 */
-
-/* BI_VME_BRDINFO is a 32 byte struct as returned by the Bug code on
- * Motorola VME boards.  Contains board number, Bug version, board
- * configuration options, etc.  See include/asm/mvme16xhw.h for details.
- */
-
-
-    /*
-     *  Macintosh-specific tags (all u_long)
-     */
-
-#define BI_MAC_MODEL		0x8000	/* Mac Gestalt ID (model type) */
-#define BI_MAC_VADDR		0x8001	/* Mac video base address */
-#define BI_MAC_VDEPTH		0x8002	/* Mac video depth */
-#define BI_MAC_VROW		0x8003	/* Mac video rowbytes */
-#define BI_MAC_VDIM		0x8004	/* Mac video dimensions */
-#define BI_MAC_VLOGICAL		0x8005	/* Mac video logical base */
-#define BI_MAC_SCCBASE		0x8006	/* Mac SCC base address */
-#define BI_MAC_BTIME		0x8007	/* Mac boot time */
-#define BI_MAC_GMTBIAS		0x8008	/* Mac GMT timezone offset */
-#define BI_MAC_MEMSIZE		0x8009	/* Mac RAM size (sanity check) */
-#define BI_MAC_CPUID		0x800a	/* Mac CPU type (sanity check) */
-#define BI_MAC_ROMBASE		0x800b	/* Mac system ROM base address */
-
-    /*
-     *  Macintosh hardware profile data - unused, see macintosh.h for
-     *  resonable type values
-     */
-
-#define BI_MAC_VIA1BASE		0x8010	/* Mac VIA1 base address (always present) */
-#define BI_MAC_VIA2BASE		0x8011	/* Mac VIA2 base address (type varies) */
-#define BI_MAC_VIA2TYPE		0x8012	/* Mac VIA2 type (VIA, RBV, OSS) */
-#define BI_MAC_ADBTYPE		0x8013	/* Mac ADB interface type */
-#define BI_MAC_ASCBASE		0x8014	/* Mac Apple Sound Chip base address */
-#define BI_MAC_SCSI5380		0x8015	/* Mac NCR 5380 SCSI (base address, multi) */
-#define BI_MAC_SCSIDMA		0x8016	/* Mac SCSI DMA (base address) */
-#define BI_MAC_SCSI5396		0x8017	/* Mac NCR 53C96 SCSI (base address, multi) */
-#define BI_MAC_IDETYPE		0x8018	/* Mac IDE interface type */
-#define BI_MAC_IDEBASE		0x8019	/* Mac IDE interface base address */
-#define BI_MAC_NUBUS		0x801a	/* Mac Nubus type (none, regular, pseudo) */
-#define BI_MAC_SLOTMASK		0x801b	/* Mac Nubus slots present */
-#define BI_MAC_SCCTYPE		0x801c	/* Mac SCC serial type (normal, IOP) */
-#define BI_MAC_ETHTYPE		0x801d	/* Mac builtin ethernet type (Sonic, MACE */
-#define BI_MAC_ETHBASE		0x801e	/* Mac builtin ethernet base address */
-#define BI_MAC_PMU		0x801f	/* Mac power management / poweroff hardware */
-#define BI_MAC_IOP_SWIM		0x8020	/* Mac SWIM floppy IOP */
-#define BI_MAC_IOP_ADB		0x8021	/* Mac ADB IOP */
-
-    /*
-     * Mac: compatibility with old booter data format (temporarily)
-     * Fields unused with the new bootinfo can be deleted now; instead of
-     * adding new fields the struct might be splitted into a hardware address
-     * part and a hardware type part
-     */
-
-#ifndef __ASSEMBLY__
-
-struct mac_booter_data
-{
-	unsigned long videoaddr;
-	unsigned long videorow;
-	unsigned long videodepth;
-	unsigned long dimensions;
-	unsigned long args;
-	unsigned long boottime;
-	unsigned long gmtbias;
-	unsigned long bootver;
-	unsigned long videological;
-	unsigned long sccbase;
-	unsigned long id;
-	unsigned long memsize;
-	unsigned long serialmf;
-	unsigned long serialhsk;
-	unsigned long serialgpi;
-	unsigned long printmf;
-	unsigned long printhsk;
-	unsigned long printgpi;
-	unsigned long cpuid;
-	unsigned long rombase;
-	unsigned long adbdelay;
-	unsigned long timedbra;
-};
-
-extern struct mac_booter_data
-	mac_bi_data;
-
-#endif
-
-    /*
-     *  Apollo-specific tags
-     */
-
-#define BI_APOLLO_MODEL         0x8000  /* model (u_long) */
-
-    /*
-     *  HP300-specific tags
-     */
-
-#define BI_HP300_MODEL		0x8000	/* model (u_long) */
-#define BI_HP300_UART_SCODE	0x8001	/* UART select code (u_long) */
-#define BI_HP300_UART_ADDR	0x8002	/* phys. addr of UART (u_long) */
-
-    /*
-     * Stuff for bootinfo interface versioning
-     *
-     * At the start of kernel code, a 'struct bootversion' is located.
-     * bootstrap checks for a matching version of the interface before booting
-     * a kernel, to avoid user confusion if kernel and bootstrap don't work
-     * together :-)
-     *
-     * If incompatible changes are made to the bootinfo interface, the major
-     * number below should be stepped (and the minor reset to 0) for the
-     * appropriate machine. If a change is backward-compatible, the minor
-     * should be stepped. "Backwards-compatible" means that booting will work,
-     * but certain features may not.
-     */
-
-#define BOOTINFOV_MAGIC			0x4249561A	/* 'BIV^Z' */
-#define MK_BI_VERSION(major,minor)	(((major)<<16)+(minor))
-#define BI_VERSION_MAJOR(v)		(((v) >> 16) & 0xffff)
-#define BI_VERSION_MINOR(v)		((v) & 0xffff)
-
-#ifndef __ASSEMBLY__
-
-struct bootversion {
-    unsigned short branch;
-    unsigned long magic;
-    struct {
-	unsigned long machtype;
-	unsigned long version;
-    } machversions[0];
-};
-
-#endif /* __ASSEMBLY__ */
-
-#define AMIGA_BOOTI_VERSION    MK_BI_VERSION( 2, 0 )
-#define ATARI_BOOTI_VERSION    MK_BI_VERSION( 2, 1 )
-#define MAC_BOOTI_VERSION      MK_BI_VERSION( 2, 0 )
-#define MVME147_BOOTI_VERSION  MK_BI_VERSION( 2, 0 )
-#define MVME16x_BOOTI_VERSION  MK_BI_VERSION( 2, 0 )
-#define BVME6000_BOOTI_VERSION MK_BI_VERSION( 2, 0 )
-#define Q40_BOOTI_VERSION      MK_BI_VERSION( 2, 0 )
-#define HP300_BOOTI_VERSION    MK_BI_VERSION( 2, 0 )
-
-#ifdef BOOTINFO_COMPAT_1_0
-
-    /*
-     *  Backwards compatibility with bootinfo interface version 1.0
-     */
-
-#define COMPAT_AMIGA_BOOTI_VERSION    MK_BI_VERSION( 1, 0 )
-#define COMPAT_ATARI_BOOTI_VERSION    MK_BI_VERSION( 1, 0 )
-#define COMPAT_MAC_BOOTI_VERSION      MK_BI_VERSION( 1, 0 )
-
-#include <linux/zorro.h>
-
-#define COMPAT_NUM_AUTO    16
-
-struct compat_bi_Amiga {
-    int model;
-    int num_autocon;
-    struct ConfigDev autocon[COMPAT_NUM_AUTO];
-    unsigned long chip_size;
-    unsigned char vblank;
-    unsigned char psfreq;
-    unsigned long eclock;
-    unsigned long chipset;
-    unsigned long hw_present;
-};
-
-struct compat_bi_Atari {
-    unsigned long hw_present;
-    unsigned long mch_cookie;
-};
-
-#ifndef __ASSEMBLY__
-
-struct compat_bi_Macintosh
-{
-	unsigned long videoaddr;
-	unsigned long videorow;
-	unsigned long videodepth;
-	unsigned long dimensions;
-	unsigned long args;
-	unsigned long boottime;
-	unsigned long gmtbias;
-	unsigned long bootver;
-	unsigned long videological;
-	unsigned long sccbase;
-	unsigned long id;
-	unsigned long memsize;
-	unsigned long serialmf;
-	unsigned long serialhsk;
-	unsigned long serialgpi;
-	unsigned long printmf;
-	unsigned long printhsk;
-	unsigned long printgpi;
-	unsigned long cpuid;
-	unsigned long rombase;
-	unsigned long adbdelay;
-	unsigned long timedbra;
-};
-
-#endif
-
-struct compat_mem_info {
-    unsigned long addr;
-    unsigned long size;
-};
-
-#define COMPAT_NUM_MEMINFO  4
-
-#define COMPAT_CPUB_68020 0
-#define COMPAT_CPUB_68030 1
-#define COMPAT_CPUB_68040 2
-#define COMPAT_CPUB_68060 3
-#define COMPAT_FPUB_68881 5
-#define COMPAT_FPUB_68882 6
-#define COMPAT_FPUB_68040 7
-#define COMPAT_FPUB_68060 8
-
-#define COMPAT_CPU_68020    (1<<COMPAT_CPUB_68020)
-#define COMPAT_CPU_68030    (1<<COMPAT_CPUB_68030)
-#define COMPAT_CPU_68040    (1<<COMPAT_CPUB_68040)
-#define COMPAT_CPU_68060    (1<<COMPAT_CPUB_68060)
-#define COMPAT_CPU_MASK     (31)
-#define COMPAT_FPU_68881    (1<<COMPAT_FPUB_68881)
-#define COMPAT_FPU_68882    (1<<COMPAT_FPUB_68882)
-#define COMPAT_FPU_68040    (1<<COMPAT_FPUB_68040)
-#define COMPAT_FPU_68060    (1<<COMPAT_FPUB_68060)
-#define COMPAT_FPU_MASK     (0xfe0)
-
-#define COMPAT_CL_SIZE      (256)
-
-struct compat_bootinfo {
-    unsigned long machtype;
-    unsigned long cputype;
-    struct compat_mem_info memory[COMPAT_NUM_MEMINFO];
-    int num_memory;
-    unsigned long ramdisk_size;
-    unsigned long ramdisk_addr;
-    char command_line[COMPAT_CL_SIZE];
-    union {
-	struct compat_bi_Amiga     bi_ami;
-	struct compat_bi_Atari     bi_ata;
-	struct compat_bi_Macintosh bi_mac;
-    } bi_un;
-};
-
-#define bi_amiga	bi_un.bi_ami
-#define bi_atari	bi_un.bi_ata
-#define bi_mac		bi_un.bi_mac
-
-#endif /* BOOTINFO_COMPAT_1_0 */
-
-
-#endif /* _M68K_BOOTINFO_H */
diff --git a/arch/m68k/include/asm/bootinfo_no.h b/arch/m68k/include/asm/bootinfo_no.h
deleted file mode 100644
index c12e526f5189..000000000000
--- a/arch/m68k/include/asm/bootinfo_no.h
+++ /dev/null
@@ -1,2 +0,0 @@
-
-/* Nothing for m68knommu */
diff --git a/arch/m68k/include/asm/bug.h b/arch/m68k/include/asm/bug.h
index 997e0944ebc1..ef9a2e47352f 100644
--- a/arch/m68k/include/asm/bug.h
+++ b/arch/m68k/include/asm/bug.h
@@ -1,5 +1,30 @@
-#ifdef __uClinux__
-#include "bug_no.h"
+#ifndef _M68K_BUG_H
+#define _M68K_BUG_H
+
+#ifdef CONFIG_MMU
+#ifdef CONFIG_BUG
+#ifdef CONFIG_DEBUG_BUGVERBOSE
+#ifndef CONFIG_SUN3
+#define BUG() do { \
+	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
+	__builtin_trap(); \
+} while (0)
 #else
-#include "bug_mm.h"
+#define BUG() do { \
+	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
+	panic("BUG!"); \
+} while (0)
+#endif
+#else
+#define BUG() do { \
+	__builtin_trap(); \
+} while (0)
+#endif
+
+#define HAVE_ARCH_BUG
+#endif
+#endif /* CONFIG_MMU */
+
+#include <asm-generic/bug.h>
+
 #endif
diff --git a/arch/m68k/include/asm/bug_mm.h b/arch/m68k/include/asm/bug_mm.h
deleted file mode 100644
index e5b528deb8a8..000000000000
--- a/arch/m68k/include/asm/bug_mm.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef _M68K_BUG_H
-#define _M68K_BUG_H
-
-
-#ifdef CONFIG_BUG
-#ifdef CONFIG_DEBUG_BUGVERBOSE
-#ifndef CONFIG_SUN3
-#define BUG() do { \
-	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
-	__builtin_trap(); \
-} while (0)
-#else
-#define BUG() do { \
-	printk("kernel BUG at %s:%d!\n", __FILE__, __LINE__); \
-	panic("BUG!"); \
-} while (0)
-#endif
-#else
-#define BUG() do { \
-	__builtin_trap(); \
-} while (0)
-#endif
-
-#define HAVE_ARCH_BUG
-#endif
-
-#include <asm-generic/bug.h>
-
-#endif
diff --git a/arch/m68k/include/asm/bug_no.h b/arch/m68k/include/asm/bug_no.h
deleted file mode 100644
index 70e7dc0af21a..000000000000
--- a/arch/m68k/include/asm/bug_no.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef _M68KNOMMU_BUG_H
-#define _M68KNOMMU_BUG_H
-#include <asm-generic/bug.h>
-#endif
diff --git a/arch/m68k/include/asm/bugs.h b/arch/m68k/include/asm/bugs.h
index 01f047d784ec..d06207b9ba5a 100644
--- a/arch/m68k/include/asm/bugs.h
+++ b/arch/m68k/include/asm/bugs.h
@@ -1,5 +1,20 @@
-#ifdef __uClinux__
-#include "bugs_no.h"
+/*
+ *  include/asm-m68k/bugs.h
+ *
+ *  Copyright (C) 1994  Linus Torvalds
+ */
+
+/*
+ * This is included by init/main.c to check for architecture-dependent bugs.
+ *
+ * Needs:
+ *	void check_bugs(void);
+ */
+
+#ifdef CONFIG_MMU
+extern void check_bugs(void);	/* in arch/m68k/kernel/setup.c */
 #else
-#include "bugs_mm.h"
+static void check_bugs(void)
+{
+}
 #endif
diff --git a/arch/m68k/include/asm/bugs_mm.h b/arch/m68k/include/asm/bugs_mm.h
deleted file mode 100644
index d01935592410..000000000000
--- a/arch/m68k/include/asm/bugs_mm.h
+++ /dev/null
@@ -1,14 +0,0 @@
-/*
- *  include/asm-m68k/bugs.h
- *
- *  Copyright (C) 1994  Linus Torvalds
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- *	void check_bugs(void);
- */
-
-extern void check_bugs(void);	/* in arch/m68k/kernel/setup.c */
diff --git a/arch/m68k/include/asm/bugs_no.h b/arch/m68k/include/asm/bugs_no.h
deleted file mode 100644
index 5f382dac3a60..000000000000
--- a/arch/m68k/include/asm/bugs_no.h
+++ /dev/null
@@ -1,16 +0,0 @@
-/*
- *  include/asm-m68k/bugs.h
- *
- *  Copyright (C) 1994  Linus Torvalds
- */
-
-/*
- * This is included by init/main.c to check for architecture-dependent bugs.
- *
- * Needs:
- *	void check_bugs(void);
- */
-
-static void check_bugs(void)
-{
-}
diff --git a/arch/m68k/include/asm/cache.h b/arch/m68k/include/asm/cache.h
index 599c29bc8f40..fed3fd30de7e 100644
--- a/arch/m68k/include/asm/cache.h
+++ b/arch/m68k/include/asm/cache.h
@@ -1,5 +1,11 @@
-#ifdef __uClinux__
-#include "cache_no.h"
-#else
-#include "cache_mm.h"
+/*
+ * include/asm-m68k/cache.h
+ */
+#ifndef __ARCH_M68K_CACHE_H
+#define __ARCH_M68K_CACHE_H
+
+/* bytes per L1 cache line */
+#define        L1_CACHE_SHIFT  4
+#define        L1_CACHE_BYTES  (1<< L1_CACHE_SHIFT)
+
 #endif
diff --git a/arch/m68k/include/asm/cache_mm.h b/arch/m68k/include/asm/cache_mm.h
deleted file mode 100644
index fed3fd30de7e..000000000000
--- a/arch/m68k/include/asm/cache_mm.h
+++ /dev/null
@@ -1,11 +0,0 @@
-/*
- * include/asm-m68k/cache.h
- */
-#ifndef __ARCH_M68K_CACHE_H
-#define __ARCH_M68K_CACHE_H
-
-/* bytes per L1 cache line */
-#define        L1_CACHE_SHIFT  4
-#define        L1_CACHE_BYTES  (1<< L1_CACHE_SHIFT)
-
-#endif
diff --git a/arch/m68k/include/asm/cache_no.h b/arch/m68k/include/asm/cache_no.h
deleted file mode 100644
index 24e9eace5f8c..000000000000
--- a/arch/m68k/include/asm/cache_no.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef __ARCH_M68KNOMMU_CACHE_H
-#define __ARCH_M68KNOMMU_CACHE_H
-
-/* bytes per L1 cache line */
-#define        L1_CACHE_BYTES  16	/* this need to be at least 1 */
-
-/* m68k-elf-gcc  2.95.2 doesn't like these */
-
-#define __cacheline_aligned
-#define ____cacheline_aligned
-
-#endif
diff --git a/arch/m68k/include/asm/current.h b/arch/m68k/include/asm/current.h
index 51b056dfaedd..91fcc5358cfe 100644
--- a/arch/m68k/include/asm/current.h
+++ b/arch/m68k/include/asm/current.h
@@ -1,5 +1,28 @@
-#ifdef __uClinux__
-#include "current_no.h"
+#ifndef _M68K_CURRENT_H
+#define _M68K_CURRENT_H
+
+#ifdef CONFIG_MMU
+
+register struct task_struct *current __asm__("%a2");
+
 #else
-#include "current_mm.h"
-#endif
+
+/*
+ *	Rather than dedicate a register (as the m68k source does), we
+ *	just keep a global,  we should probably just change it all to be
+ *	current and lose _current_task.
+ */
+#include <linux/thread_info.h>
+
+struct task_struct;
+
+static inline struct task_struct *get_current(void)
+{
+	return(current_thread_info()->task);
+}
+
+#define	current	get_current()
+
+#endif /* CONFNIG_MMU */
+
+#endif /* !(_M68K_CURRENT_H) */
diff --git a/arch/m68k/include/asm/current_mm.h b/arch/m68k/include/asm/current_mm.h
deleted file mode 100644
index 8de8f8ceda61..000000000000
--- a/arch/m68k/include/asm/current_mm.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _M68K_CURRENT_H
-#define _M68K_CURRENT_H
-
-register struct task_struct *current __asm__("%a2");
-
-#endif /* !(_M68K_CURRENT_H) */
diff --git a/arch/m68k/include/asm/current_no.h b/arch/m68k/include/asm/current_no.h
deleted file mode 100644
index 53ee0f9f7cef..000000000000
--- a/arch/m68k/include/asm/current_no.h
+++ /dev/null
@@ -1,24 +0,0 @@
-#ifndef _M68KNOMMU_CURRENT_H
-#define _M68KNOMMU_CURRENT_H
-/*
- *	current.h
- *	(C) Copyright 2000, Lineo, David McCullough <davidm@uclinux.org>
- *	(C) Copyright 2002, Greg Ungerer (gerg@snapgear.com)
- *
- *	rather than dedicate a register (as the m68k source does), we
- *	just keep a global,  we should probably just change it all to be
- *	current and lose _current_task.
- */
-
-#include <linux/thread_info.h>
-
-struct task_struct;
-
-static inline struct task_struct *get_current(void)
-{
-	return(current_thread_info()->task);
-}
-
-#define	current	get_current()
-
-#endif /* _M68KNOMMU_CURRENT_H */
diff --git a/arch/m68k/include/asm/div64.h b/arch/m68k/include/asm/div64.h
index d211d9f54276..edb66148a71d 100644
--- a/arch/m68k/include/asm/div64.h
+++ b/arch/m68k/include/asm/div64.h
@@ -1,5 +1,34 @@
-#ifdef __uClinux__
-#include "div64_no.h"
+#ifndef _M68K_DIV64_H
+#define _M68K_DIV64_H
+
+#ifdef CONFIG_MMU
+
+#include <linux/types.h>
+
+/* n = n / base; return rem; */
+
+#define do_div(n, base) ({					\
+	union {							\
+		unsigned long n32[2];				\
+		unsigned long long n64;				\
+	} __n;							\
+	unsigned long __rem, __upper;				\
+								\
+	__n.n64 = (n);						\
+	if ((__upper = __n.n32[0])) {				\
+		asm ("divul.l %2,%1:%0"				\
+			: "=d" (__n.n32[0]), "=d" (__upper)	\
+			: "d" (base), "0" (__n.n32[0]));	\
+	}							\
+	asm ("divu.l %2,%1:%0"					\
+		: "=d" (__n.n32[1]), "=d" (__rem)		\
+		: "d" (base), "1" (__upper), "0" (__n.n32[1]));	\
+	(n) = __n.n64;						\
+	__rem;							\
+})
+
 #else
-#include "div64_mm.h"
-#endif
+#include <asm-generic/div64.h>
+#endif /* CONFIG_MMU */
+
+#endif /* _M68K_DIV64_H */
diff --git a/arch/m68k/include/asm/div64_mm.h b/arch/m68k/include/asm/div64_mm.h
deleted file mode 100644
index 8243c931b5c0..000000000000
--- a/arch/m68k/include/asm/div64_mm.h
+++ /dev/null
@@ -1,28 +0,0 @@
-#ifndef _M68K_DIV64_H
-#define _M68K_DIV64_H
-
-#include <linux/types.h>
-
-/* n = n / base; return rem; */
-
-#define do_div(n, base) ({					\
-	union {							\
-		unsigned long n32[2];				\
-		unsigned long long n64;				\
-	} __n;							\
-	unsigned long __rem, __upper;				\
-								\
-	__n.n64 = (n);						\
-	if ((__upper = __n.n32[0])) {				\
-		asm ("divul.l %2,%1:%0"				\
-			: "=d" (__n.n32[0]), "=d" (__upper)	\
-			: "d" (base), "0" (__n.n32[0]));	\
-	}							\
-	asm ("divu.l %2,%1:%0"					\
-		: "=d" (__n.n32[1]), "=d" (__rem)		\
-		: "d" (base), "1" (__upper), "0" (__n.n32[1]));	\
-	(n) = __n.n64;						\
-	__rem;							\
-})
-
-#endif /* _M68K_DIV64_H */
diff --git a/arch/m68k/include/asm/div64_no.h b/arch/m68k/include/asm/div64_no.h
deleted file mode 100644
index 6cd978cefb28..000000000000
--- a/arch/m68k/include/asm/div64_no.h
+++ /dev/null
@@ -1 +0,0 @@
-#include <asm-generic/div64.h>
diff --git a/arch/m68k/include/asm/dma-mapping.h b/arch/m68k/include/asm/dma-mapping.h
index f4a4c7638f89..26f505488c11 100644
--- a/arch/m68k/include/asm/dma-mapping.h
+++ b/arch/m68k/include/asm/dma-mapping.h
@@ -1,5 +1,112 @@
-#ifdef __uClinux__
-#include "dma-mapping_no.h"
+#ifndef _M68K_DMA_MAPPING_H
+#define _M68K_DMA_MAPPING_H
+
+#include <asm/cache.h>
+
+struct scatterlist;
+
+#ifndef CONFIG_MMU_SUN3
+static inline int dma_supported(struct device *dev, u64 mask)
+{
+	return 1;
+}
+
+static inline int dma_set_mask(struct device *dev, u64 mask)
+{
+	return 0;
+}
+
+static inline int dma_get_cache_alignment(void)
+{
+	return 1 << L1_CACHE_SHIFT;
+}
+
+static inline int dma_is_consistent(struct device *dev, dma_addr_t dma_addr)
+{
+	return 0;
+}
+
+extern void *dma_alloc_coherent(struct device *, size_t,
+				dma_addr_t *, gfp_t);
+extern void dma_free_coherent(struct device *, size_t,
+			      void *, dma_addr_t);
+
+static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
+					  dma_addr_t *handle, gfp_t flag)
+{
+	return dma_alloc_coherent(dev, size, handle, flag);
+}
+static inline void dma_free_noncoherent(struct device *dev, size_t size,
+					void *addr, dma_addr_t handle)
+{
+	dma_free_coherent(dev, size, addr, handle);
+}
+static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
+				  enum dma_data_direction dir)
+{
+	/* we use coherent allocation, so not much to do here. */
+}
+
+extern dma_addr_t dma_map_single(struct device *, void *, size_t,
+				 enum dma_data_direction);
+static inline void dma_unmap_single(struct device *dev, dma_addr_t addr,
+				    size_t size, enum dma_data_direction dir)
+{
+}
+
+extern dma_addr_t dma_map_page(struct device *, struct page *,
+			       unsigned long, size_t size,
+			       enum dma_data_direction);
+static inline void dma_unmap_page(struct device *dev, dma_addr_t address,
+				  size_t size, enum dma_data_direction dir)
+{
+}
+
+extern int dma_map_sg(struct device *, struct scatterlist *, int,
+		      enum dma_data_direction);
+static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
+				int nhwentries, enum dma_data_direction dir)
+{
+}
+
+extern void dma_sync_single_for_device(struct device *, dma_addr_t, size_t,
+				       enum dma_data_direction);
+extern void dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
+				   enum dma_data_direction);
+
+static inline void dma_sync_single_range_for_device(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	/* just sync everything for now */
+	dma_sync_single_for_device(dev, dma_handle, offset + size, direction);
+}
+
+static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
+					   size_t size, enum dma_data_direction dir)
+{
+}
+
+static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
+				       int nents, enum dma_data_direction dir)
+{
+}
+
+static inline void dma_sync_single_range_for_cpu(struct device *dev,
+		dma_addr_t dma_handle, unsigned long offset, size_t size,
+		enum dma_data_direction direction)
+{
+	/* just sync everything for now */
+	dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction);
+}
+
+static inline int dma_mapping_error(struct device *dev, dma_addr_t handle)
+{
+	return 0;
+}
+
 #else
-#include "dma-mapping_mm.h"
+#include <asm-generic/dma-mapping-broken.h>
 #endif
+
+#endif  /* _M68K_DMA_MAPPING_H */
diff --git a/arch/m68k/include/asm/dma-mapping_mm.h b/arch/m68k/include/asm/dma-mapping_mm.h
deleted file mode 100644
index 26f505488c11..000000000000
--- a/arch/m68k/include/asm/dma-mapping_mm.h
+++ /dev/null
@@ -1,112 +0,0 @@
-#ifndef _M68K_DMA_MAPPING_H
-#define _M68K_DMA_MAPPING_H
-
-#include <asm/cache.h>
-
-struct scatterlist;
-
-#ifndef CONFIG_MMU_SUN3
-static inline int dma_supported(struct device *dev, u64 mask)
-{
-	return 1;
-}
-
-static inline int dma_set_mask(struct device *dev, u64 mask)
-{
-	return 0;
-}
-
-static inline int dma_get_cache_alignment(void)
-{
-	return 1 << L1_CACHE_SHIFT;
-}
-
-static inline int dma_is_consistent(struct device *dev, dma_addr_t dma_addr)
-{
-	return 0;
-}
-
-extern void *dma_alloc_coherent(struct device *, size_t,
-				dma_addr_t *, gfp_t);
-extern void dma_free_coherent(struct device *, size_t,
-			      void *, dma_addr_t);
-
-static inline void *dma_alloc_noncoherent(struct device *dev, size_t size,
-					  dma_addr_t *handle, gfp_t flag)
-{
-	return dma_alloc_coherent(dev, size, handle, flag);
-}
-static inline void dma_free_noncoherent(struct device *dev, size_t size,
-					void *addr, dma_addr_t handle)
-{
-	dma_free_coherent(dev, size, addr, handle);
-}
-static inline void dma_cache_sync(struct device *dev, void *vaddr, size_t size,
-				  enum dma_data_direction dir)
-{
-	/* we use coherent allocation, so not much to do here. */
-}
-
-extern dma_addr_t dma_map_single(struct device *, void *, size_t,
-				 enum dma_data_direction);
-static inline void dma_unmap_single(struct device *dev, dma_addr_t addr,
-				    size_t size, enum dma_data_direction dir)
-{
-}
-
-extern dma_addr_t dma_map_page(struct device *, struct page *,
-			       unsigned long, size_t size,
-			       enum dma_data_direction);
-static inline void dma_unmap_page(struct device *dev, dma_addr_t address,
-				  size_t size, enum dma_data_direction dir)
-{
-}
-
-extern int dma_map_sg(struct device *, struct scatterlist *, int,
-		      enum dma_data_direction);
-static inline void dma_unmap_sg(struct device *dev, struct scatterlist *sg,
-				int nhwentries, enum dma_data_direction dir)
-{
-}
-
-extern void dma_sync_single_for_device(struct device *, dma_addr_t, size_t,
-				       enum dma_data_direction);
-extern void dma_sync_sg_for_device(struct device *, struct scatterlist *, int,
-				   enum dma_data_direction);
-
-static inline void dma_sync_single_range_for_device(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_device(dev, dma_handle, offset + size, direction);
-}
-
-static inline void dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle,
-					   size_t size, enum dma_data_direction dir)
-{
-}
-
-static inline void dma_sync_sg_for_cpu(struct device *dev, struct scatterlist *sg,
-				       int nents, enum dma_data_direction dir)
-{
-}
-
-static inline void dma_sync_single_range_for_cpu(struct device *dev,
-		dma_addr_t dma_handle, unsigned long offset, size_t size,
-		enum dma_data_direction direction)
-{
-	/* just sync everything for now */
-	dma_sync_single_for_cpu(dev, dma_handle, offset + size, direction);
-}
-
-static inline int dma_mapping_error(struct device *dev, dma_addr_t handle)
-{
-	return 0;
-}
-
-#else
-#include <asm-generic/dma-mapping-broken.h>
-#endif
-
-#endif  /* _M68K_DMA_MAPPING_H */
diff --git a/arch/m68k/include/asm/dma-mapping_no.h b/arch/m68k/include/asm/dma-mapping_no.h
deleted file mode 100644
index 1748f2bca940..000000000000
--- a/arch/m68k/include/asm/dma-mapping_no.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef _M68KNOMMU_DMA_MAPPING_H
-#define _M68KNOMMU_DMA_MAPPING_H
-
-#include <asm-generic/dma-mapping-broken.h>
-
-#endif  /* _M68KNOMMU_DMA_MAPPING_H */
diff --git a/arch/m68k/include/asm/elf.h b/arch/m68k/include/asm/elf.h
index 04ce488bc63f..0b0f49eb876b 100644
--- a/arch/m68k/include/asm/elf.h
+++ b/arch/m68k/include/asm/elf.h
@@ -1,5 +1,119 @@
-#ifdef __uClinux__
-#include "elf_no.h"
+#ifndef __ASMm68k_ELF_H
+#define __ASMm68k_ELF_H
+
+/*
+ * ELF register definitions..
+ */
+
+#include <asm/ptrace.h>
+#include <asm/user.h>
+
+/*
+ * 68k ELF relocation types
+ */
+#define R_68K_NONE	0
+#define R_68K_32	1
+#define R_68K_16	2
+#define R_68K_8		3
+#define R_68K_PC32	4
+#define R_68K_PC16	5
+#define R_68K_PC8	6
+#define R_68K_GOT32	7
+#define R_68K_GOT16	8
+#define R_68K_GOT8	9
+#define R_68K_GOT32O	10
+#define R_68K_GOT16O	11
+#define R_68K_GOT8O	12
+#define R_68K_PLT32	13
+#define R_68K_PLT16	14
+#define R_68K_PLT8	15
+#define R_68K_PLT32O	16
+#define R_68K_PLT16O	17
+#define R_68K_PLT8O	18
+#define R_68K_COPY	19
+#define R_68K_GLOB_DAT	20
+#define R_68K_JMP_SLOT	21
+#define R_68K_RELATIVE	22
+
+typedef unsigned long elf_greg_t;
+
+#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
+typedef elf_greg_t elf_gregset_t[ELF_NGREG];
+
+typedef struct user_m68kfp_struct elf_fpregset_t;
+
+/*
+ * This is used to ensure we don't load something for the wrong architecture.
+ */
+#define elf_check_arch(x) ((x)->e_machine == EM_68K)
+
+/*
+ * These are used to set parameters in the core dumps.
+ */
+#define ELF_CLASS	ELFCLASS32
+#define ELF_DATA	ELFDATA2MSB
+#define ELF_ARCH	EM_68K
+
+/* For SVR4/m68k the function pointer to be registered with `atexit' is
+   passed in %a1.  Although my copy of the ABI has no such statement, it
+   is actually used on ASV.  */
+#define ELF_PLAT_INIT(_r, load_addr)	_r->a1 = 0
+
+#define USE_ELF_CORE_DUMP
+#ifndef CONFIG_SUN3
+#define ELF_EXEC_PAGESIZE	4096
 #else
-#include "elf_mm.h"
+#define ELF_EXEC_PAGESIZE	8192
+#endif
+
+/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
+   use of this is to invoke "./ld.so someprog" to test out a new version of
+   the loader.  We need to make sure that it is out of the way of the program
+   that it will "exec", and that there is sufficient room for the brk.  */
+
+#ifndef CONFIG_SUN3
+#define ELF_ET_DYN_BASE         0xD0000000UL
+#else
+#define ELF_ET_DYN_BASE         0x0D800000UL
+#endif
+
+#define ELF_CORE_COPY_REGS(pr_reg, regs)				\
+	/* Bleech. */							\
+	pr_reg[0] = regs->d1;						\
+	pr_reg[1] = regs->d2;						\
+	pr_reg[2] = regs->d3;						\
+	pr_reg[3] = regs->d4;						\
+	pr_reg[4] = regs->d5;						\
+	pr_reg[7] = regs->a0;						\
+	pr_reg[8] = regs->a1;						\
+	pr_reg[9] = regs->a2;						\
+	pr_reg[14] = regs->d0;						\
+	pr_reg[15] = rdusp();						\
+	pr_reg[16] = regs->orig_d0;					\
+	pr_reg[17] = regs->sr;						\
+	pr_reg[18] = regs->pc;						\
+	pr_reg[19] = (regs->format << 12) | regs->vector;		\
+	{								\
+	  struct switch_stack *sw = ((struct switch_stack *)regs) - 1;	\
+	  pr_reg[5] = sw->d6;						\
+	  pr_reg[6] = sw->d7;						\
+	  pr_reg[10] = sw->a3;						\
+	  pr_reg[11] = sw->a4;						\
+	  pr_reg[12] = sw->a5;						\
+	  pr_reg[13] = sw->a6;						\
+	}
+
+/* This yields a mask that user programs can use to figure out what
+   instruction set this cpu supports.  */
+
+#define ELF_HWCAP	(0)
+
+/* This yields a string that ld.so will use to load implementation
+   specific libraries for optimization.  This is more specific in
+   intent than poking at uname or /proc/cpuinfo.  */
+
+#define ELF_PLATFORM  (NULL)
+
+#define SET_PERSONALITY(ex) set_personality(PER_LINUX)
+
 #endif
diff --git a/arch/m68k/include/asm/elf_mm.h b/arch/m68k/include/asm/elf_mm.h
deleted file mode 100644
index 0b0f49eb876b..000000000000
--- a/arch/m68k/include/asm/elf_mm.h
+++ /dev/null
@@ -1,119 +0,0 @@
-#ifndef __ASMm68k_ELF_H
-#define __ASMm68k_ELF_H
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-#include <asm/user.h>
-
-/*
- * 68k ELF relocation types
- */
-#define R_68K_NONE	0
-#define R_68K_32	1
-#define R_68K_16	2
-#define R_68K_8		3
-#define R_68K_PC32	4
-#define R_68K_PC16	5
-#define R_68K_PC8	6
-#define R_68K_GOT32	7
-#define R_68K_GOT16	8
-#define R_68K_GOT8	9
-#define R_68K_GOT32O	10
-#define R_68K_GOT16O	11
-#define R_68K_GOT8O	12
-#define R_68K_PLT32	13
-#define R_68K_PLT16	14
-#define R_68K_PLT8	15
-#define R_68K_PLT32O	16
-#define R_68K_PLT16O	17
-#define R_68K_PLT8O	18
-#define R_68K_COPY	19
-#define R_68K_GLOB_DAT	20
-#define R_68K_JMP_SLOT	21
-#define R_68K_RELATIVE	22
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_m68kfp_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) ((x)->e_machine == EM_68K)
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS	ELFCLASS32
-#define ELF_DATA	ELFDATA2MSB
-#define ELF_ARCH	EM_68K
-
-/* For SVR4/m68k the function pointer to be registered with `atexit' is
-   passed in %a1.  Although my copy of the ABI has no such statement, it
-   is actually used on ASV.  */
-#define ELF_PLAT_INIT(_r, load_addr)	_r->a1 = 0
-
-#define USE_ELF_CORE_DUMP
-#ifndef CONFIG_SUN3
-#define ELF_EXEC_PAGESIZE	4096
-#else
-#define ELF_EXEC_PAGESIZE	8192
-#endif
-
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#ifndef CONFIG_SUN3
-#define ELF_ET_DYN_BASE         0xD0000000UL
-#else
-#define ELF_ET_DYN_BASE         0x0D800000UL
-#endif
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs)				\
-	/* Bleech. */							\
-	pr_reg[0] = regs->d1;						\
-	pr_reg[1] = regs->d2;						\
-	pr_reg[2] = regs->d3;						\
-	pr_reg[3] = regs->d4;						\
-	pr_reg[4] = regs->d5;						\
-	pr_reg[7] = regs->a0;						\
-	pr_reg[8] = regs->a1;						\
-	pr_reg[9] = regs->a2;						\
-	pr_reg[14] = regs->d0;						\
-	pr_reg[15] = rdusp();						\
-	pr_reg[16] = regs->orig_d0;					\
-	pr_reg[17] = regs->sr;						\
-	pr_reg[18] = regs->pc;						\
-	pr_reg[19] = (regs->format << 12) | regs->vector;		\
-	{								\
-	  struct switch_stack *sw = ((struct switch_stack *)regs) - 1;	\
-	  pr_reg[5] = sw->d6;						\
-	  pr_reg[6] = sw->d7;						\
-	  pr_reg[10] = sw->a3;						\
-	  pr_reg[11] = sw->a4;						\
-	  pr_reg[12] = sw->a5;						\
-	  pr_reg[13] = sw->a6;						\
-	}
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this cpu supports.  */
-
-#define ELF_HWCAP	(0)
-
-/* This yields a string that ld.so will use to load implementation
-   specific libraries for optimization.  This is more specific in
-   intent than poking at uname or /proc/cpuinfo.  */
-
-#define ELF_PLATFORM  (NULL)
-
-#define SET_PERSONALITY(ex) set_personality(PER_LINUX)
-
-#endif
diff --git a/arch/m68k/include/asm/elf_no.h b/arch/m68k/include/asm/elf_no.h
deleted file mode 100644
index b8046837f384..000000000000
--- a/arch/m68k/include/asm/elf_no.h
+++ /dev/null
@@ -1,110 +0,0 @@
-#ifndef __ASMm68k_ELF_H
-#define __ASMm68k_ELF_H
-
-/*
- * ELF register definitions..
- */
-
-#include <asm/ptrace.h>
-#include <asm/user.h>
-
-/*
- * 68k ELF relocation types
- */
-#define R_68K_NONE  0
-#define R_68K_32    1
-#define R_68K_16    2
-#define R_68K_8     3
-#define R_68K_PC32  4
-#define R_68K_PC16  5
-#define R_68K_PC8   6
-#define R_68K_GOT32 7
-#define R_68K_GOT16 8
-#define R_68K_GOT8  9
-#define R_68K_GOT32O    10
-#define R_68K_GOT16O    11
-#define R_68K_GOT8O 12
-#define R_68K_PLT32 13
-#define R_68K_PLT16 14
-#define R_68K_PLT8  15
-#define R_68K_PLT32O    16
-#define R_68K_PLT16O    17
-#define R_68K_PLT8O 18
-#define R_68K_COPY  19
-#define R_68K_GLOB_DAT  20
-#define R_68K_JMP_SLOT  21
-#define R_68K_RELATIVE  22
-
-typedef unsigned long elf_greg_t;
-
-#define ELF_NGREG (sizeof(struct user_regs_struct) / sizeof(elf_greg_t))
-typedef elf_greg_t elf_gregset_t[ELF_NGREG];
-
-typedef struct user_m68kfp_struct elf_fpregset_t;
-
-/*
- * This is used to ensure we don't load something for the wrong architecture.
- */
-#define elf_check_arch(x) ((x)->e_machine == EM_68K)
-
-/*
- * These are used to set parameters in the core dumps.
- */
-#define ELF_CLASS	ELFCLASS32
-#define ELF_DATA	ELFDATA2MSB
-#define ELF_ARCH	EM_68K
-
-/* For SVR4/m68k the function pointer to be registered with `atexit' is
-   passed in %a1.  Although my copy of the ABI has no such statement, it
-   is actually used on ASV.  */
-#define ELF_PLAT_INIT(_r, load_addr)	_r->a1 = 0
-
-#define USE_ELF_CORE_DUMP
-#define ELF_EXEC_PAGESIZE	4096
-
-/* This is the location that an ET_DYN program is loaded if exec'ed.  Typical
-   use of this is to invoke "./ld.so someprog" to test out a new version of
-   the loader.  We need to make sure that it is out of the way of the program
-   that it will "exec", and that there is sufficient room for the brk.  */
-
-#define ELF_ET_DYN_BASE         0xD0000000UL
-
-#define ELF_CORE_COPY_REGS(pr_reg, regs)				\
-	/* Bleech. */							\
-	pr_reg[0] = regs->d1;						\
-	pr_reg[1] = regs->d2;						\
-	pr_reg[2] = regs->d3;						\
-	pr_reg[3] = regs->d4;						\
-	pr_reg[4] = regs->d5;						\
-	pr_reg[7] = regs->a0;						\
-	pr_reg[8] = regs->a1;						\
-	pr_reg[14] = regs->d0;						\
-	pr_reg[15] = rdusp();						\
-	pr_reg[16] = 0 /* regs->orig_d0 */;				\
-	pr_reg[17] = regs->sr;						\
-	pr_reg[18] = regs->pc;						\
-	/* pr_reg[19] = (regs->format << 12) | regs->vector; */		\
-	{								\
-	  struct switch_stack *sw = ((struct switch_stack *)regs) - 1;	\
-	  pr_reg[5] = sw->d6;						\
-	  pr_reg[6] = sw->d7;						\
-	  pr_reg[10] = sw->a3;						\
-	  pr_reg[11] = sw->a4;						\
-	  pr_reg[12] = sw->a5;						\
-	  pr_reg[13] = sw->a6;						\
-	}
-
-/* This yields a mask that user programs can use to figure out what
-   instruction set this cpu supports.  */
-
-#define ELF_HWCAP	(0)
-
-/* This yields a string that ld.so will use to load implementation
-   specific libraries for optimization.  This is more specific in
-   intent than poking at uname or /proc/cpuinfo.  */
-
-#define ELF_PLATFORM  (NULL)
-
-#define SET_PERSONALITY(ex) set_personality(PER_LINUX)
-
-#endif
diff --git a/arch/m68k/include/asm/fb.h b/arch/m68k/include/asm/fb.h
index 97bcaefd2064..be4e4c6797e8 100644
--- a/arch/m68k/include/asm/fb.h
+++ b/arch/m68k/include/asm/fb.h
@@ -1,5 +1,38 @@
-#ifdef __uClinux__
-#include "fb_no.h"
+#ifndef _ASM_FB_H_
+#define _ASM_FB_H_
+
+#include <linux/fb.h>
+#include <linux/fs.h>
+#include <asm/page.h>
+#include <asm/setup.h>
+
+#ifdef CONFIG_MMU
+#ifdef CONFIG_SUN3
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+				unsigned long off)
+{
+	pgprot_val(vma->vm_page_prot) |= SUN3_PAGE_NOCACHE;
+}
 #else
-#include "fb_mm.h"
-#endif
+static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
+				unsigned long off)
+{
+	if (CPU_IS_020_OR_030)
+		pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE030;
+	if (CPU_IS_040_OR_060) {
+		pgprot_val(vma->vm_page_prot) &= _CACHEMASK040;
+		/* Use no-cache mode, serialized */
+		pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE_S;
+	}
+}
+#endif /* CONFIG_SUN3 */
+#else
+#define fb_pgprotect(...) do {} while (0)
+#endif /* CONFIG_MMU */
+
+static inline int fb_is_primary_device(struct fb_info *info)
+{
+	return 0;
+}
+
+#endif /* _ASM_FB_H_ */
diff --git a/arch/m68k/include/asm/fb_mm.h b/arch/m68k/include/asm/fb_mm.h
deleted file mode 100644
index 380b97ae8157..000000000000
--- a/arch/m68k/include/asm/fb_mm.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-
-#include <linux/fb.h>
-#include <linux/fs.h>
-#include <asm/page.h>
-#include <asm/setup.h>
-
-#ifdef CONFIG_SUN3
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-				unsigned long off)
-{
-	pgprot_val(vma->vm_page_prot) |= SUN3_PAGE_NOCACHE;
-}
-#else
-static inline void fb_pgprotect(struct file *file, struct vm_area_struct *vma,
-				unsigned long off)
-{
-	if (CPU_IS_020_OR_030)
-		pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE030;
-	if (CPU_IS_040_OR_060) {
-		pgprot_val(vma->vm_page_prot) &= _CACHEMASK040;
-		/* Use no-cache mode, serialized */
-		pgprot_val(vma->vm_page_prot) |= _PAGE_NOCACHE_S;
-	}
-}
-#endif /* CONFIG_SUN3 */
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/arch/m68k/include/asm/fb_no.h b/arch/m68k/include/asm/fb_no.h
deleted file mode 100644
index c7df38030992..000000000000
--- a/arch/m68k/include/asm/fb_no.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_FB_H_
-#define _ASM_FB_H_
-#include <linux/fb.h>
-
-#define fb_pgprotect(...) do {} while (0)
-
-static inline int fb_is_primary_device(struct fb_info *info)
-{
-	return 0;
-}
-
-#endif /* _ASM_FB_H_ */
diff --git a/arch/m68k/include/asm/fpu.h b/arch/m68k/include/asm/fpu.h
index e19bc5ed9c37..ffb6b8cfc6d5 100644
--- a/arch/m68k/include/asm/fpu.h
+++ b/arch/m68k/include/asm/fpu.h
@@ -1,5 +1,21 @@
-#ifdef __uClinux__
-#include "fpu_no.h"
+#ifndef __M68K_FPU_H
+#define __M68K_FPU_H
+
+
+/*
+ * MAX floating point unit state size (FSAVE/FRESTORE)
+ */
+
+#if defined(CONFIG_M68020) || defined(CONFIG_M68030)
+#define FPSTATESIZE (216)
+#elif defined(CONFIG_M68040)
+#define FPSTATESIZE (96)
+#elif defined(CONFIG_M68KFPU_EMU)
+#define FPSTATESIZE (28)
+#elif defined(CONFIG_M68060)
+#define FPSTATESIZE (12)
 #else
-#include "fpu_mm.h"
+#define FPSTATESIZE (0)
 #endif
+
+#endif /* __M68K_FPU_H */
diff --git a/arch/m68k/include/asm/fpu_mm.h b/arch/m68k/include/asm/fpu_mm.h
deleted file mode 100644
index ffb6b8cfc6d5..000000000000
--- a/arch/m68k/include/asm/fpu_mm.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __M68K_FPU_H
-#define __M68K_FPU_H
-
-
-/*
- * MAX floating point unit state size (FSAVE/FRESTORE)
- */
-
-#if defined(CONFIG_M68020) || defined(CONFIG_M68030)
-#define FPSTATESIZE (216)
-#elif defined(CONFIG_M68040)
-#define FPSTATESIZE (96)
-#elif defined(CONFIG_M68KFPU_EMU)
-#define FPSTATESIZE (28)
-#elif defined(CONFIG_M68060)
-#define FPSTATESIZE (12)
-#else
-#define FPSTATESIZE (0)
-#endif
-
-#endif /* __M68K_FPU_H */
diff --git a/arch/m68k/include/asm/fpu_no.h b/arch/m68k/include/asm/fpu_no.h
deleted file mode 100644
index b16b2e4fca2a..000000000000
--- a/arch/m68k/include/asm/fpu_no.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __M68KNOMMU_FPU_H
-#define __M68KNOMMU_FPU_H
-
-
-/*
- * MAX floating point unit state size (FSAVE/FRESTORE)
- */
-#if defined(CONFIG_M68020) || defined(CONFIG_M68030)
-#define FPSTATESIZE (216/sizeof(unsigned char))
-#elif defined(CONFIG_M68040)
-#define FPSTATESIZE (96/sizeof(unsigned char))
-#elif defined(CONFIG_M68KFPU_EMU)
-#define FPSTATESIZE (28/sizeof(unsigned char))
-#elif defined(CONFIG_M68060)
-#define FPSTATESIZE (12/sizeof(unsigned char))
-#else
-/* Assume no FP unit present then... */
-#define FPSTATESIZE (2) /* dummy size */
-#endif
-
-#endif /* __M68K_FPU_H */
diff --git a/arch/m68k/include/asm/hw_irq.h b/arch/m68k/include/asm/hw_irq.h
index e19526015890..eacef0951fbf 100644
--- a/arch/m68k/include/asm/hw_irq.h
+++ b/arch/m68k/include/asm/hw_irq.h
@@ -1,5 +1,6 @@
-#ifdef __uClinux__
-#include "hw_irq_no.h"
-#else
-#include "hw_irq_mm.h"
+#ifndef __ASM_M68K_HW_IRQ_H
+#define __ASM_M68K_HW_IRQ_H
+
+/* Dummy include. */
+
 #endif
diff --git a/arch/m68k/include/asm/hw_irq_mm.h b/arch/m68k/include/asm/hw_irq_mm.h
deleted file mode 100644
index eacef0951fbf..000000000000
--- a/arch/m68k/include/asm/hw_irq_mm.h
+++ /dev/null
@@ -1,6 +0,0 @@
-#ifndef __ASM_M68K_HW_IRQ_H
-#define __ASM_M68K_HW_IRQ_H
-
-/* Dummy include. */
-
-#endif
diff --git a/arch/m68k/include/asm/hw_irq_no.h b/arch/m68k/include/asm/hw_irq_no.h
deleted file mode 100644
index f3ec9e5ae049..000000000000
--- a/arch/m68k/include/asm/hw_irq_no.h
+++ /dev/null
@@ -1,4 +0,0 @@
-#ifndef __M68KNOMMU_HW_IRQ_H__
-#define __M68KNOMMU_HW_IRQ_H__
-
-#endif /* __M68KNOMMU_HW_IRQ_H__ */
diff --git a/arch/m68k/include/asm/kmap_types.h b/arch/m68k/include/asm/kmap_types.h
index 045d9fd122a2..c843c63d3801 100644
--- a/arch/m68k/include/asm/kmap_types.h
+++ b/arch/m68k/include/asm/kmap_types.h
@@ -1,5 +1,21 @@
-#ifdef __uClinux__
-#include "kmap_types_no.h"
-#else
-#include "kmap_types_mm.h"
-#endif
+#ifndef __ASM_M68K_KMAP_TYPES_H
+#define __ASM_M68K_KMAP_TYPES_H
+
+enum km_type {
+	KM_BOUNCE_READ,
+	KM_SKB_SUNRPC_DATA,
+	KM_SKB_DATA_SOFTIRQ,
+	KM_USER0,
+	KM_USER1,
+	KM_BIO_SRC_IRQ,
+	KM_BIO_DST_IRQ,
+	KM_PTE0,
+	KM_PTE1,
+	KM_IRQ0,
+	KM_IRQ1,
+	KM_SOFTIRQ0,
+	KM_SOFTIRQ1,
+	KM_TYPE_NR
+};
+
+#endif	/* __ASM_M68K_KMAP_TYPES_H */
diff --git a/arch/m68k/include/asm/kmap_types_mm.h b/arch/m68k/include/asm/kmap_types_mm.h
deleted file mode 100644
index c843c63d3801..000000000000
--- a/arch/m68k/include/asm/kmap_types_mm.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __ASM_M68K_KMAP_TYPES_H
-#define __ASM_M68K_KMAP_TYPES_H
-
-enum km_type {
-	KM_BOUNCE_READ,
-	KM_SKB_SUNRPC_DATA,
-	KM_SKB_DATA_SOFTIRQ,
-	KM_USER0,
-	KM_USER1,
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_TYPE_NR
-};
-
-#endif	/* __ASM_M68K_KMAP_TYPES_H */
diff --git a/arch/m68k/include/asm/kmap_types_no.h b/arch/m68k/include/asm/kmap_types_no.h
deleted file mode 100644
index bfb6707575d1..000000000000
--- a/arch/m68k/include/asm/kmap_types_no.h
+++ /dev/null
@@ -1,21 +0,0 @@
-#ifndef __ASM_M68K_KMAP_TYPES_H
-#define __ASM_M68K_KMAP_TYPES_H
-
-enum km_type {
-	KM_BOUNCE_READ,
-	KM_SKB_SUNRPC_DATA,
-	KM_SKB_DATA_SOFTIRQ,
-	KM_USER0,
-	KM_USER1,
-	KM_BIO_SRC_IRQ,
-	KM_BIO_DST_IRQ,
-	KM_PTE0,
-	KM_PTE1,
-	KM_IRQ0,
-	KM_IRQ1,
-	KM_SOFTIRQ0,
-	KM_SOFTIRQ1,
-	KM_TYPE_NR
-};
-
-#endif
diff --git a/arch/m68k/include/asm/m532xsim.h b/arch/m68k/include/asm/m532xsim.h
index 1835fd20a82c..ce603451b55e 100644
--- a/arch/m68k/include/asm/m532xsim.h
+++ b/arch/m68k/include/asm/m532xsim.h
@@ -16,6 +16,7 @@
 #define MCFINT_VECBASE      64
 #define MCFINT_UART0        26          /* Interrupt number for UART0 */
 #define MCFINT_UART1        27          /* Interrupt number for UART1 */
+#define MCFINT_UART2        28          /* Interrupt number for UART2 */
 
 #define MCF_WTM_WCR	MCF_REG16(0xFC098000)
 
diff --git a/arch/m68k/include/asm/mc146818rtc.h b/arch/m68k/include/asm/mc146818rtc.h
index fb90dcf78426..9f70a01f73dc 100644
--- a/arch/m68k/include/asm/mc146818rtc.h
+++ b/arch/m68k/include/asm/mc146818rtc.h
@@ -1,5 +1,26 @@
-#ifdef __uClinux__
-#include "mc146818rtc_no.h"
-#else
-#include "mc146818rtc_mm.h"
-#endif
+/*
+ * Machine dependent access functions for RTC registers.
+ */
+#ifndef _ASM_MC146818RTC_H
+#define _ASM_MC146818RTC_H
+
+
+#ifdef CONFIG_ATARI
+/* RTC in Atari machines */
+
+#include <asm/atarihw.h>
+
+#define RTC_PORT(x)	(TT_RTC_BAS + 2*(x))
+#define RTC_ALWAYS_BCD	0
+
+#define CMOS_READ(addr) ({ \
+atari_outb_p((addr),RTC_PORT(0)); \
+atari_inb_p(RTC_PORT(1)); \
+})
+#define CMOS_WRITE(val, addr) ({ \
+atari_outb_p((addr),RTC_PORT(0)); \
+atari_outb_p((val),RTC_PORT(1)); \
+})
+#endif /* CONFIG_ATARI */
+
+#endif /* _ASM_MC146818RTC_H */
diff --git a/arch/m68k/include/asm/mc146818rtc_mm.h b/arch/m68k/include/asm/mc146818rtc_mm.h
deleted file mode 100644
index 9f70a01f73dc..000000000000
--- a/arch/m68k/include/asm/mc146818rtc_mm.h
+++ /dev/null
@@ -1,26 +0,0 @@
-/*
- * Machine dependent access functions for RTC registers.
- */
-#ifndef _ASM_MC146818RTC_H
-#define _ASM_MC146818RTC_H
-
-
-#ifdef CONFIG_ATARI
-/* RTC in Atari machines */
-
-#include <asm/atarihw.h>
-
-#define RTC_PORT(x)	(TT_RTC_BAS + 2*(x))
-#define RTC_ALWAYS_BCD	0
-
-#define CMOS_READ(addr) ({ \
-atari_outb_p((addr),RTC_PORT(0)); \
-atari_inb_p(RTC_PORT(1)); \
-})
-#define CMOS_WRITE(val, addr) ({ \
-atari_outb_p((addr),RTC_PORT(0)); \
-atari_outb_p((val),RTC_PORT(1)); \
-})
-#endif /* CONFIG_ATARI */
-
-#endif /* _ASM_MC146818RTC_H */
diff --git a/arch/m68k/include/asm/mc146818rtc_no.h b/arch/m68k/include/asm/mc146818rtc_no.h
deleted file mode 100644
index 907a0481a140..000000000000
--- a/arch/m68k/include/asm/mc146818rtc_no.h
+++ /dev/null
@@ -1,9 +0,0 @@
-/*
- * Machine dependent access functions for RTC registers.
- */
-#ifndef _M68KNOMMU_MC146818RTC_H
-#define _M68KNOMMU_MC146818RTC_H
-
-/* empty include file to satisfy the include in genrtc.c/ide-geometry.c */
-
-#endif /* _M68KNOMMU_MC146818RTC_H */
diff --git a/arch/m68k/include/asm/mcfpci.h b/arch/m68k/include/asm/mcfpci.h
deleted file mode 100644
index f1507dd06ec6..000000000000
--- a/arch/m68k/include/asm/mcfpci.h
+++ /dev/null
@@ -1,119 +0,0 @@
-/****************************************************************************/
-
-/*
- *	mcfpci.h -- PCI bridge on ColdFire eval boards.
- *
- *	(C) Copyright 2000, Greg Ungerer (gerg@snapgear.com)
- *	(C) Copyright 2000, Lineo Inc. (www.lineo.com)
- */
-
-/****************************************************************************/
-#ifndef	mcfpci_h
-#define	mcfpci_h
-/****************************************************************************/
-
-
-#ifdef CONFIG_PCI
-
-/*
- *	Address regions in the PCI address space are not mapped into the
- *	normal memory space of the ColdFire. They must be accessed via
- *	handler routines. This is easy for I/O space (inb/outb/etc) but
- *	needs some code changes to support ordinary memory. Interrupts
- *	also need to be vectored through the PCI handler first, then it
- *	will call the actual driver sub-handlers.
- */
-
-/*
- *	Un-define all the standard I/O access routines.
- */
-#undef	inb
-#undef	inw
-#undef	inl
-#undef	inb_p
-#undef	inw_p
-#undef	insb
-#undef	insw
-#undef	insl
-#undef	outb
-#undef	outw
-#undef	outl
-#undef	outb_p
-#undef	outw_p
-#undef	outsb
-#undef	outsw
-#undef	outsl
-
-#undef	request_irq
-#undef	free_irq
-
-#undef	bus_to_virt
-#undef	virt_to_bus
-
-
-/*
- *	Re-direct all I/O memory accesses functions to PCI specific ones.
- */
-#define	inb	pci_inb
-#define	inw	pci_inw
-#define	inl	pci_inl
-#define	inb_p	pci_inb
-#define	inw_p	pci_inw
-#define	insb	pci_insb
-#define	insw	pci_insw
-#define	insl	pci_insl
-
-#define	outb	pci_outb
-#define	outw	pci_outw
-#define	outl	pci_outl
-#define	outb_p	pci_outb
-#define	outw_p	pci_outw
-#define	outsb	pci_outsb
-#define	outsw	pci_outsw
-#define	outsl	pci_outsl
-
-#define	request_irq	pci_request_irq
-#define	free_irq	pci_free_irq
-
-#define	virt_to_bus	pci_virt_to_bus
-#define	bus_to_virt	pci_bus_to_virt
-
-#define	CONFIG_COMEMPCI	1
-
-
-/*
- *	Prototypes of the real PCI functions (defined in bios32.c).
- */
-unsigned char	pci_inb(unsigned int addr);
-unsigned short	pci_inw(unsigned int addr);
-unsigned int	pci_inl(unsigned int addr);
-void		pci_insb(void *addr, void *buf, int len);
-void		pci_insw(void *addr, void *buf, int len);
-void		pci_insl(void *addr, void *buf, int len);
-
-void		pci_outb(unsigned char val, unsigned int addr);
-void		pci_outw(unsigned short val, unsigned int addr);
-void		pci_outl(unsigned int val, unsigned int addr);
-void		pci_outsb(void *addr, void *buf, int len);
-void		pci_outsw(void *addr, void *buf, int len);
-void		pci_outsl(void *addr, void *buf, int len);
-
-int		pci_request_irq(unsigned int irq,
-			void (*handler)(int, void *, struct pt_regs *),
-			unsigned long flags,
-			const char *device,
-			void *dev_id);
-void		pci_free_irq(unsigned int irq, void *dev_id);
-
-void		*pci_bmalloc(int size);
-void		pci_bmfree(void *bmp, int len);
-void		pci_copytoshmem(unsigned long bmp, void *src, int size);
-void		pci_copyfromshmem(void *dst, unsigned long bmp, int size);
-unsigned long	pci_virt_to_bus(volatile void *address);
-void		*pci_bus_to_virt(unsigned long address);
-void		pci_bmcpyto(void *dst, void *src, int len);
-void		pci_bmcpyfrom(void *dst, void *src, int len);
-
-#endif /* CONFIG_PCI */
-/****************************************************************************/
-#endif	/* mcfpci_h */
diff --git a/arch/m68k/include/asm/mmu.h b/arch/m68k/include/asm/mmu.h
index a81d3946675f..8a11a63ee15a 100644
--- a/arch/m68k/include/asm/mmu.h
+++ b/arch/m68k/include/asm/mmu.h
@@ -1,5 +1,13 @@
-#ifdef __uClinux__
-#include "mmu_no.h"
+#ifndef __MMU_H
+#define __MMU_H
+
+#ifdef CONFIG_MMU
+/* Default "unsigned long" context */
+typedef unsigned long mm_context_t;
 #else
-#include "mmu_mm.h"
+typedef struct {
+	unsigned long		end_brk;
+} mm_context_t;
+#endif
+
 #endif
diff --git a/arch/m68k/include/asm/mmu_context.h b/arch/m68k/include/asm/mmu_context.h
index b440928fc6c7..7d4341e55a99 100644
--- a/arch/m68k/include/asm/mmu_context.h
+++ b/arch/m68k/include/asm/mmu_context.h
@@ -1,5 +1,175 @@
-#ifdef __uClinux__
-#include "mmu_context_no.h"
+#ifndef __M68K_MMU_CONTEXT_H
+#define __M68K_MMU_CONTEXT_H
+
+#include <asm-generic/mm_hooks.h>
+
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+}
+
+#ifdef CONFIG_MMU
+#ifndef CONFIG_SUN3
+
+#include <asm/setup.h>
+#include <asm/page.h>
+#include <asm/pgalloc.h>
+
+static inline int init_new_context(struct task_struct *tsk,
+				   struct mm_struct *mm)
+{
+	mm->context = virt_to_phys(mm->pgd);
+	return 0;
+}
+
+#define destroy_context(mm)		do { } while(0)
+
+static inline void switch_mm_0230(struct mm_struct *mm)
+{
+	unsigned long crp[2] = {
+		0x80000000 | _PAGE_TABLE, mm->context
+	};
+	unsigned long tmp;
+
+	asm volatile (".chip 68030");
+
+	/* flush MC68030/MC68020 caches (they are virtually addressed) */
+	asm volatile (
+		"movec %%cacr,%0;"
+		"orw %1,%0; "
+		"movec %0,%%cacr"
+		: "=d" (tmp) : "di" (FLUSH_I_AND_D));
+
+	/* Switch the root pointer. For a 030-only kernel,
+	 * avoid flushing the whole ATC, we only need to
+	 * flush the user entries. The 68851 does this by
+	 * itself. Avoid a runtime check here.
+	 */
+	asm volatile (
+#ifdef CPU_M68030_ONLY
+		"pmovefd %0,%%crp; "
+		"pflush #0,#4"
 #else
-#include "mmu_context_mm.h"
+		"pmove %0,%%crp"
 #endif
+		: : "m" (crp[0]));
+
+	asm volatile (".chip 68k");
+}
+
+static inline void switch_mm_0460(struct mm_struct *mm)
+{
+	asm volatile (".chip 68040");
+
+	/* flush address translation cache (user entries) */
+	asm volatile ("pflushan");
+
+	/* switch the root pointer */
+	asm volatile ("movec %0,%%urp" : : "r" (mm->context));
+
+	if (CPU_IS_060) {
+		unsigned long tmp;
+
+		/* clear user entries in the branch cache */
+		asm volatile (
+			"movec %%cacr,%0; "
+		        "orl %1,%0; "
+		        "movec %0,%%cacr"
+			: "=d" (tmp): "di" (0x00200000));
+	}
+
+	asm volatile (".chip 68k");
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
+{
+	if (prev != next) {
+		if (CPU_IS_020_OR_030)
+			switch_mm_0230(next);
+		else
+			switch_mm_0460(next);
+	}
+}
+
+#define deactivate_mm(tsk,mm)	do { } while (0)
+
+static inline void activate_mm(struct mm_struct *prev_mm,
+			       struct mm_struct *next_mm)
+{
+	next_mm->context = virt_to_phys(next_mm->pgd);
+
+	if (CPU_IS_020_OR_030)
+		switch_mm_0230(next_mm);
+	else
+		switch_mm_0460(next_mm);
+}
+
+#else  /* CONFIG_SUN3 */
+#include <asm/sun3mmu.h>
+#include <linux/sched.h>
+
+extern unsigned long get_free_context(struct mm_struct *mm);
+extern void clear_context(unsigned long context);
+
+/* set the context for a new task to unmapped */
+static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	mm->context = SUN3_INVALID_CONTEXT;
+	return 0;
+}
+
+/* find the context given to this process, and if it hasn't already
+   got one, go get one for it. */
+static inline void get_mmu_context(struct mm_struct *mm)
+{
+	if(mm->context == SUN3_INVALID_CONTEXT)
+		mm->context = get_free_context(mm);
+}
+
+/* flush context if allocated... */
+static inline void destroy_context(struct mm_struct *mm)
+{
+	if(mm->context != SUN3_INVALID_CONTEXT)
+		clear_context(mm->context);
+}
+
+static inline void activate_context(struct mm_struct *mm)
+{
+	get_mmu_context(mm);
+	sun3_put_context(mm->context);
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
+{
+	activate_context(tsk->mm);
+}
+
+#define deactivate_mm(tsk,mm)	do { } while (0)
+
+static inline void activate_mm(struct mm_struct *prev_mm,
+			       struct mm_struct *next_mm)
+{
+	activate_context(next_mm);
+}
+
+#endif
+#else /* !CONFIG_MMU */
+
+static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	return 0;
+}
+
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
+{
+}
+
+#define destroy_context(mm)	do { } while (0)
+#define deactivate_mm(tsk,mm)	do { } while (0)
+
+static inline void activate_mm(struct mm_struct *prev_mm, struct mm_struct *next_mm)
+{
+}
+
+#endif /* CONFIG_MMU */
+#endif /* __M68K_MMU_CONTEXT_H */
diff --git a/arch/m68k/include/asm/mmu_context_mm.h b/arch/m68k/include/asm/mmu_context_mm.h
deleted file mode 100644
index 894dacbcee14..000000000000
--- a/arch/m68k/include/asm/mmu_context_mm.h
+++ /dev/null
@@ -1,154 +0,0 @@
-#ifndef __M68K_MMU_CONTEXT_H
-#define __M68K_MMU_CONTEXT_H
-
-#include <asm-generic/mm_hooks.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-#ifndef CONFIG_SUN3
-
-#include <asm/setup.h>
-#include <asm/page.h>
-#include <asm/pgalloc.h>
-
-static inline int init_new_context(struct task_struct *tsk,
-				   struct mm_struct *mm)
-{
-	mm->context = virt_to_phys(mm->pgd);
-	return 0;
-}
-
-#define destroy_context(mm)		do { } while(0)
-
-static inline void switch_mm_0230(struct mm_struct *mm)
-{
-	unsigned long crp[2] = {
-		0x80000000 | _PAGE_TABLE, mm->context
-	};
-	unsigned long tmp;
-
-	asm volatile (".chip 68030");
-
-	/* flush MC68030/MC68020 caches (they are virtually addressed) */
-	asm volatile (
-		"movec %%cacr,%0;"
-		"orw %1,%0; "
-		"movec %0,%%cacr"
-		: "=d" (tmp) : "di" (FLUSH_I_AND_D));
-
-	/* Switch the root pointer. For a 030-only kernel,
-	 * avoid flushing the whole ATC, we only need to
-	 * flush the user entries. The 68851 does this by
-	 * itself. Avoid a runtime check here.
-	 */
-	asm volatile (
-#ifdef CPU_M68030_ONLY
-		"pmovefd %0,%%crp; "
-		"pflush #0,#4"
-#else
-		"pmove %0,%%crp"
-#endif
-		: : "m" (crp[0]));
-
-	asm volatile (".chip 68k");
-}
-
-static inline void switch_mm_0460(struct mm_struct *mm)
-{
-	asm volatile (".chip 68040");
-
-	/* flush address translation cache (user entries) */
-	asm volatile ("pflushan");
-
-	/* switch the root pointer */
-	asm volatile ("movec %0,%%urp" : : "r" (mm->context));
-
-	if (CPU_IS_060) {
-		unsigned long tmp;
-
-		/* clear user entries in the branch cache */
-		asm volatile (
-			"movec %%cacr,%0; "
-		        "orl %1,%0; "
-		        "movec %0,%%cacr"
-			: "=d" (tmp): "di" (0x00200000));
-	}
-
-	asm volatile (".chip 68k");
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
-{
-	if (prev != next) {
-		if (CPU_IS_020_OR_030)
-			switch_mm_0230(next);
-		else
-			switch_mm_0460(next);
-	}
-}
-
-#define deactivate_mm(tsk,mm)	do { } while (0)
-
-static inline void activate_mm(struct mm_struct *prev_mm,
-			       struct mm_struct *next_mm)
-{
-	next_mm->context = virt_to_phys(next_mm->pgd);
-
-	if (CPU_IS_020_OR_030)
-		switch_mm_0230(next_mm);
-	else
-		switch_mm_0460(next_mm);
-}
-
-#else  /* CONFIG_SUN3 */
-#include <asm/sun3mmu.h>
-#include <linux/sched.h>
-
-extern unsigned long get_free_context(struct mm_struct *mm);
-extern void clear_context(unsigned long context);
-
-/* set the context for a new task to unmapped */
-static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
-	mm->context = SUN3_INVALID_CONTEXT;
-	return 0;
-}
-
-/* find the context given to this process, and if it hasn't already
-   got one, go get one for it. */
-static inline void get_mmu_context(struct mm_struct *mm)
-{
-	if(mm->context == SUN3_INVALID_CONTEXT)
-		mm->context = get_free_context(mm);
-}
-
-/* flush context if allocated... */
-static inline void destroy_context(struct mm_struct *mm)
-{
-	if(mm->context != SUN3_INVALID_CONTEXT)
-		clear_context(mm->context);
-}
-
-static inline void activate_context(struct mm_struct *mm)
-{
-	get_mmu_context(mm);
-	sun3_put_context(mm->context);
-}
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
-{
-	activate_context(tsk->mm);
-}
-
-#define deactivate_mm(tsk,mm)	do { } while (0)
-
-static inline void activate_mm(struct mm_struct *prev_mm,
-			       struct mm_struct *next_mm)
-{
-	activate_context(next_mm);
-}
-
-#endif
-#endif
diff --git a/arch/m68k/include/asm/mmu_context_no.h b/arch/m68k/include/asm/mmu_context_no.h
deleted file mode 100644
index 9ccee4278c97..000000000000
--- a/arch/m68k/include/asm/mmu_context_no.h
+++ /dev/null
@@ -1,33 +0,0 @@
-#ifndef __M68KNOMMU_MMU_CONTEXT_H
-#define __M68KNOMMU_MMU_CONTEXT_H
-
-#include <asm/setup.h>
-#include <asm/page.h>
-#include <asm/pgalloc.h>
-#include <asm-generic/mm_hooks.h>
-
-static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
-{
-}
-
-static inline int
-init_new_context(struct task_struct *tsk, struct mm_struct *mm)
-{
-	// mm->context = virt_to_phys(mm->pgd);
-	return(0);
-}
-
-#define destroy_context(mm)		do { } while(0)
-
-static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next, struct task_struct *tsk)
-{
-}
-
-#define deactivate_mm(tsk,mm)	do { } while (0)
-
-static inline void activate_mm(struct mm_struct *prev_mm,
-			       struct mm_struct *next_mm)
-{
-}
-
-#endif
diff --git a/arch/m68k/include/asm/mmu_mm.h b/arch/m68k/include/asm/mmu_mm.h
deleted file mode 100644
index ccd36d26615a..000000000000
--- a/arch/m68k/include/asm/mmu_mm.h
+++ /dev/null
@@ -1,7 +0,0 @@
-#ifndef __MMU_H
-#define __MMU_H
-
-/* Default "unsigned long" context */
-typedef unsigned long mm_context_t;
-
-#endif
diff --git a/arch/m68k/include/asm/mmu_no.h b/arch/m68k/include/asm/mmu_no.h
deleted file mode 100644
index e2da1e6f09fe..000000000000
--- a/arch/m68k/include/asm/mmu_no.h
+++ /dev/null
@@ -1,10 +0,0 @@
-#ifndef __M68KNOMMU_MMU_H
-#define __M68KNOMMU_MMU_H
-
-/* Copyright (C) 2002, David McCullough <davidm@snapgear.com> */
-
-typedef struct {
-	unsigned long		end_brk;
-} mm_context_t;
-
-#endif /* __M68KNOMMU_MMU_H */
diff --git a/arch/m68k/include/asm/module.h b/arch/m68k/include/asm/module.h
index 79b59d137dd0..5f21e11071bd 100644
--- a/arch/m68k/include/asm/module.h
+++ b/arch/m68k/include/asm/module.h
@@ -1,5 +1,48 @@
-#ifdef __uClinux__
-#include "module_no.h"
+#ifndef _ASM_M68K_MODULE_H
+#define _ASM_M68K_MODULE_H
+
+#ifdef CONFIG_MMU
+
+struct mod_arch_specific {
+	struct m68k_fixup_info *fixup_start, *fixup_end;
+};
+
+#define MODULE_ARCH_INIT {				\
+	.fixup_start		= __start_fixup,	\
+	.fixup_end		= __stop_fixup,		\
+}
+
+
+enum m68k_fixup_type {
+	m68k_fixup_memoffset,
+	m68k_fixup_vnode_shift,
+};
+
+struct m68k_fixup_info {
+	enum m68k_fixup_type type;
+	void *addr;
+};
+
+#define m68k_fixup(type, addr)			\
+	"	.section \".m68k_fixup\",\"aw\"\n"	\
+	"	.long " #type "," #addr "\n"	\
+	"	.previous\n"
+
+extern struct m68k_fixup_info __start_fixup[], __stop_fixup[];
+
+struct module;
+extern void module_fixup(struct module *mod, struct m68k_fixup_info *start,
+			 struct m68k_fixup_info *end);
+
 #else
-#include "module_mm.h"
-#endif
+
+struct mod_arch_specific {
+};
+
+#endif /* CONFIG_MMU */
+
+#define Elf_Shdr Elf32_Shdr
+#define Elf_Sym Elf32_Sym
+#define Elf_Ehdr Elf32_Ehdr
+
+#endif /* _ASM_M68K_MODULE_H */
diff --git a/arch/m68k/include/asm/module_mm.h b/arch/m68k/include/asm/module_mm.h
deleted file mode 100644
index 382d20a6fc18..000000000000
--- a/arch/m68k/include/asm/module_mm.h
+++ /dev/null
@@ -1,39 +0,0 @@
-#ifndef _ASM_M68K_MODULE_H
-#define _ASM_M68K_MODULE_H
-
-struct mod_arch_specific {
-	struct m68k_fixup_info *fixup_start, *fixup_end;
-};
-
-#define MODULE_ARCH_INIT {				\
-	.fixup_start		= __start_fixup,	\
-	.fixup_end		= __stop_fixup,		\
-}
-
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-
-
-enum m68k_fixup_type {
-	m68k_fixup_memoffset,
-	m68k_fixup_vnode_shift,
-};
-
-struct m68k_fixup_info {
-	enum m68k_fixup_type type;
-	void *addr;
-};
-
-#define m68k_fixup(type, addr)			\
-	"	.section \".m68k_fixup\",\"aw\"\n"	\
-	"	.long " #type "," #addr "\n"	\
-	"	.previous\n"
-
-extern struct m68k_fixup_info __start_fixup[], __stop_fixup[];
-
-struct module;
-extern void module_fixup(struct module *mod, struct m68k_fixup_info *start,
-			 struct m68k_fixup_info *end);
-
-#endif /* _ASM_M68K_MODULE_H */
diff --git a/arch/m68k/include/asm/module_no.h b/arch/m68k/include/asm/module_no.h
deleted file mode 100644
index 2e45ab50b232..000000000000
--- a/arch/m68k/include/asm/module_no.h
+++ /dev/null
@@ -1,11 +0,0 @@
-#ifndef ASM_M68KNOMMU_MODULE_H
-#define ASM_M68KNOMMU_MODULE_H
-
-struct mod_arch_specific {
-};
-
-#define Elf_Shdr Elf32_Shdr
-#define Elf_Sym Elf32_Sym
-#define Elf_Ehdr Elf32_Ehdr
-
-#endif /* ASM_M68KNOMMU_MODULE_H */
diff --git a/arch/m68k/include/asm/page_offset.h b/arch/m68k/include/asm/page_offset.h
index 66455c849fbb..1780152d81da 100644
--- a/arch/m68k/include/asm/page_offset.h
+++ b/arch/m68k/include/asm/page_offset.h
@@ -1,5 +1,11 @@
-#ifdef __uClinux__
-#include "page_offset_no.h"
+/* This handles the memory map.. */
+
+#ifdef CONFIG_MMU
+#ifndef CONFIG_SUN3
+#define PAGE_OFFSET_RAW		0x00000000
 #else
-#include "page_offset_mm.h"
+#define PAGE_OFFSET_RAW		0x0E000000
+#endif
+#else
+#define	PAGE_OFFSET_RAW		CONFIG_RAMBASE
 #endif
diff --git a/arch/m68k/include/asm/page_offset_mm.h b/arch/m68k/include/asm/page_offset_mm.h
deleted file mode 100644
index 1cbdb7f30ac2..000000000000
--- a/arch/m68k/include/asm/page_offset_mm.h
+++ /dev/null
@@ -1,8 +0,0 @@
-
-/* This handles the memory map.. */
-#ifndef CONFIG_SUN3
-#define PAGE_OFFSET_RAW		0x00000000
-#else
-#define PAGE_OFFSET_RAW		0x0E000000
-#endif
-
diff --git a/arch/m68k/include/asm/page_offset_no.h b/arch/m68k/include/asm/page_offset_no.h
deleted file mode 100644
index d4e73e0ba646..000000000000
--- a/arch/m68k/include/asm/page_offset_no.h
+++ /dev/null
@@ -1,5 +0,0 @@
-
-
-/* This handles the memory map.. */
-#define	PAGE_OFFSET_RAW		CONFIG_RAMBASE
-
diff --git a/arch/m68k/include/asm/pci.h b/arch/m68k/include/asm/pci.h
index dbea95373080..4ad0aea48ab4 100644
--- a/arch/m68k/include/asm/pci.h
+++ b/arch/m68k/include/asm/pci.h
@@ -1,5 +1,12 @@
-#ifdef __uClinux__
-#include "pci_no.h"
-#else
-#include "pci_mm.h"
-#endif
+#ifndef _ASM_M68K_PCI_H
+#define _ASM_M68K_PCI_H
+
+#include <asm-generic/pci-dma-compat.h>
+
+/* The PCI address space does equal the physical memory
+ * address space.  The networking and block device layers use
+ * this boolean for bounce buffer decisions.
+ */
+#define PCI_DMA_BUS_IS_PHYS	(1)
+
+#endif /* _ASM_M68K_PCI_H */
diff --git a/arch/m68k/include/asm/pci_mm.h b/arch/m68k/include/asm/pci_mm.h
deleted file mode 100644
index 4ad0aea48ab4..000000000000
--- a/arch/m68k/include/asm/pci_mm.h
+++ /dev/null
@@ -1,12 +0,0 @@
-#ifndef _ASM_M68K_PCI_H
-#define _ASM_M68K_PCI_H
-
-#include <asm-generic/pci-dma-compat.h>
-
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
-#endif /* _ASM_M68K_PCI_H */
diff --git a/arch/m68k/include/asm/pci_no.h b/arch/m68k/include/asm/pci_no.h
deleted file mode 100644
index 9abbc03c73ee..000000000000
--- a/arch/m68k/include/asm/pci_no.h
+++ /dev/null
@@ -1,29 +0,0 @@
-#ifndef M68KNOMMU_PCI_H
-#define	M68KNOMMU_PCI_H
-
-#include <asm/pci_mm.h>
-
-#ifdef CONFIG_COMEMPCI
-/*
- *	These are pretty much arbitary with the CoMEM implementation.
- *	We have the whole address space to ourselves.
- */
-#define PCIBIOS_MIN_IO		0x100
-#define PCIBIOS_MIN_MEM		0x00010000
-
-#define pcibios_scan_all_fns(a, b)	0
-
-/*
- * Return whether the given PCI device DMA address mask can
- * be supported properly.  For example, if your device can
- * only drive the low 24-bits during PCI bus mastering, then
- * you would pass 0x00ffffff as the mask to this function.
- */
-static inline int pci_dma_supported(struct pci_dev *hwdev, u64 mask)
-{
-	return 1;
-}
-
-#endif /* CONFIG_COMEMPCI */
-
-#endif /* M68KNOMMU_PCI_H */
diff --git a/arch/m68k/include/asm/pgalloc.h b/arch/m68k/include/asm/pgalloc.h
index 059cb73e78fc..c294aad8a900 100644
--- a/arch/m68k/include/asm/pgalloc.h
+++ b/arch/m68k/include/asm/pgalloc.h
@@ -1,5 +1,19 @@
-#ifdef __uClinux__
-#include "pgalloc_no.h"
+#ifndef M68K_PGALLOC_H
+#define M68K_PGALLOC_H
+
+#include <linux/mm.h>
+#include <linux/highmem.h>
+#include <asm/setup.h>
+
+#ifdef CONFIG_MMU
+#include <asm/virtconvert.h>
+#ifdef CONFIG_SUN3
+#include <asm/sun3_pgalloc.h>
 #else
-#include "pgalloc_mm.h"
+#include <asm/motorola_pgalloc.h>
 #endif
+
+extern void m68k_setup_node(int node);
+#endif
+
+#endif /* M68K_PGALLOC_H */
diff --git a/arch/m68k/include/asm/pgalloc_mm.h b/arch/m68k/include/asm/pgalloc_mm.h
deleted file mode 100644
index 4cb1a57ab763..000000000000
--- a/arch/m68k/include/asm/pgalloc_mm.h
+++ /dev/null
@@ -1,19 +0,0 @@
-
-#ifndef M68K_PGALLOC_H
-#define M68K_PGALLOC_H
-
-#include <linux/mm.h>
-#include <linux/highmem.h>
-#include <asm/setup.h>
-#include <asm/virtconvert.h>
-
-
-#ifdef CONFIG_SUN3
-#include <asm/sun3_pgalloc.h>
-#else
-#include <asm/motorola_pgalloc.h>
-#endif
-
-extern void m68k_setup_node(int node);
-
-#endif /* M68K_PGALLOC_H */
diff --git a/arch/m68k/include/asm/pgalloc_no.h b/arch/m68k/include/asm/pgalloc_no.h
deleted file mode 100644
index d6352f671ec0..000000000000
--- a/arch/m68k/include/asm/pgalloc_no.h
+++ /dev/null
@@ -1,8 +0,0 @@
-#ifndef _M68KNOMMU_PGALLOC_H
-#define _M68KNOMMU_PGALLOC_H
-
-#include <asm/setup.h>
-
-#define check_pgt_cache()	do { } while (0)
-
-#endif /* _M68KNOMMU_PGALLOC_H */
diff --git a/arch/m68k/include/asm/pgtable_no.h b/arch/m68k/include/asm/pgtable_no.h
index 46251016e821..bf86b29fe64a 100644
--- a/arch/m68k/include/asm/pgtable_no.h
+++ b/arch/m68k/include/asm/pgtable_no.h
@@ -67,4 +67,6 @@ extern unsigned int kobjsize(const void *objp);
 
 #include <asm-generic/pgtable.h>
 
+#define check_pgt_cache()	do { } while (0)
+
 #endif /* _M68KNOMMU_PGTABLE_H */
diff --git a/arch/m68k/include/asm/rtc.h b/arch/m68k/include/asm/rtc.h
index 5d3e03859844..a4d08ea122ee 100644
--- a/arch/m68k/include/asm/rtc.h
+++ b/arch/m68k/include/asm/rtc.h
@@ -36,13 +36,16 @@ static inline unsigned int get_rtc_time(struct rtc_time *time)
 	 * RTC has RTC_DAY_OF_WEEK, we ignore it, as it is only updated
 	 * by the RTC when initially set to a non-zero value.
 	 */
-	mach_hwclk(0, time);
+	if (mach_hwclk)
+		mach_hwclk(0, time);
 	return RTC_24H;
 }
 
 static inline int set_rtc_time(struct rtc_time *time)
 {
-	return mach_hwclk(1, time);
+	if (mach_hwclk)
+		return mach_hwclk(1, time);
+	return -EINVAL;
 }
 
 static inline unsigned int get_rtc_ss(void)
diff --git a/arch/m68k/include/asm/scatterlist.h b/arch/m68k/include/asm/scatterlist.h
index b7e528636252..e27ad902b1cf 100644
--- a/arch/m68k/include/asm/scatterlist.h
+++ b/arch/m68k/include/asm/scatterlist.h
@@ -1,5 +1,23 @@
-#ifdef __uClinux__
-#include "scatterlist_no.h"
-#else
-#include "scatterlist_mm.h"
+#ifndef _M68K_SCATTERLIST_H
+#define _M68K_SCATTERLIST_H
+
+#include <linux/types.h>
+
+struct scatterlist {
+#ifdef CONFIG_DEBUG_SG
+	unsigned long sg_magic;
 #endif
+	unsigned long page_link;
+	unsigned int offset;
+	unsigned int length;
+
+	dma_addr_t dma_address;	/* A place to hang host-specific addresses at. */
+};
+
+/* This is bogus and should go away. */
+#define ISA_DMA_THRESHOLD (0x00ffffff)
+
+#define sg_dma_address(sg)	((sg)->dma_address)
+#define sg_dma_len(sg)		((sg)->length)
+
+#endif /* !(_M68K_SCATTERLIST_H) */
diff --git a/arch/m68k/include/asm/scatterlist_mm.h b/arch/m68k/include/asm/scatterlist_mm.h
deleted file mode 100644
index d3a7a0edfeca..000000000000
--- a/arch/m68k/include/asm/scatterlist_mm.h
+++ /dev/null
@@ -1,23 +0,0 @@
-#ifndef _M68K_SCATTERLIST_H
-#define _M68K_SCATTERLIST_H
-
-#include <linux/types.h>
-
-struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
-	unsigned long sg_magic;
-#endif
-	unsigned long page_link;
-	unsigned int offset;
-	unsigned int length;
-
-	__u32 dma_address;	/* A place to hang host-specific addresses at. */
-};
-
-/* This is bogus and should go away. */
-#define ISA_DMA_THRESHOLD (0x00ffffff)
-
-#define sg_dma_address(sg)	((sg)->dma_address)
-#define sg_dma_len(sg)		((sg)->length)
-
-#endif /* !(_M68K_SCATTERLIST_H) */
diff --git a/arch/m68k/include/asm/scatterlist_no.h b/arch/m68k/include/asm/scatterlist_no.h
deleted file mode 100644
index afc4788b0d2c..000000000000
--- a/arch/m68k/include/asm/scatterlist_no.h
+++ /dev/null
@@ -1,22 +0,0 @@
-#ifndef _M68KNOMMU_SCATTERLIST_H
-#define _M68KNOMMU_SCATTERLIST_H
-
-#include <linux/mm.h>
-#include <asm/types.h>
-
-struct scatterlist {
-#ifdef CONFIG_DEBUG_SG
-	unsigned long	sg_magic;
-#endif
-	unsigned long	page_link;
-	unsigned int	offset;
-	dma_addr_t	dma_address;
-	unsigned int	length;
-};
-
-#define sg_dma_address(sg)      ((sg)->dma_address)
-#define sg_dma_len(sg)          ((sg)->length)
-
-#define ISA_DMA_THRESHOLD	(0xffffffff)
-
-#endif /* !(_M68KNOMMU_SCATTERLIST_H) */
diff --git a/arch/m68k/include/asm/segment.h b/arch/m68k/include/asm/segment.h
index 82583bc004bd..ee959219fdfe 100644
--- a/arch/m68k/include/asm/segment.h
+++ b/arch/m68k/include/asm/segment.h
@@ -1,5 +1,63 @@
-#ifdef __uClinux__
-#include "segment_no.h"
+#ifndef _M68K_SEGMENT_H
+#define _M68K_SEGMENT_H
+
+/* define constants */
+/* Address spaces (FC0-FC2) */
+#define USER_DATA     (1)
+#ifndef __USER_DS
+#define __USER_DS     (USER_DATA)
+#endif
+#define USER_PROGRAM  (2)
+#define SUPER_DATA    (5)
+#ifndef __KERNEL_DS
+#define __KERNEL_DS   (SUPER_DATA)
+#endif
+#define SUPER_PROGRAM (6)
+#define CPU_SPACE     (7)
+
+#ifndef __ASSEMBLY__
+
+typedef struct {
+	unsigned long seg;
+} mm_segment_t;
+
+#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
+#define USER_DS		MAKE_MM_SEG(__USER_DS)
+#define KERNEL_DS	MAKE_MM_SEG(__KERNEL_DS)
+
+/*
+ * Get/set the SFC/DFC registers for MOVES instructions
+ */
+
+static inline mm_segment_t get_fs(void)
+{
+#ifdef CONFIG_MMU
+	mm_segment_t _v;
+	__asm__ ("movec %/dfc,%0":"=r" (_v.seg):);
+
+	return _v;
 #else
-#include "segment_mm.h"
+	return USER_DS;
+#endif
+}
+
+static inline mm_segment_t get_ds(void)
+{
+    /* return the supervisor data space code */
+    return KERNEL_DS;
+}
+
+static inline void set_fs(mm_segment_t val)
+{
+#ifdef CONFIG_MMU
+	__asm__ __volatile__ ("movec %0,%/sfc\n\t"
+			      "movec %0,%/dfc\n\t"
+			      : /* no outputs */ : "r" (val.seg) : "memory");
 #endif
+}
+
+#define segment_eq(a,b)	((a).seg == (b).seg)
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* _M68K_SEGMENT_H */
diff --git a/arch/m68k/include/asm/segment_mm.h b/arch/m68k/include/asm/segment_mm.h
deleted file mode 100644
index 7b0b2d3127f9..000000000000
--- a/arch/m68k/include/asm/segment_mm.h
+++ /dev/null
@@ -1,57 +0,0 @@
-#ifndef _M68K_SEGMENT_H
-#define _M68K_SEGMENT_H
-
-/* define constants */
-/* Address spaces (FC0-FC2) */
-#define USER_DATA     (1)
-#ifndef __USER_DS
-#define __USER_DS     (USER_DATA)
-#endif
-#define USER_PROGRAM  (2)
-#define SUPER_DATA    (5)
-#ifndef __KERNEL_DS
-#define __KERNEL_DS   (SUPER_DATA)
-#endif
-#define SUPER_PROGRAM (6)
-#define CPU_SPACE     (7)
-
-#ifndef __ASSEMBLY__
-
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-#define USER_DS		MAKE_MM_SEG(__USER_DS)
-#define KERNEL_DS	MAKE_MM_SEG(__KERNEL_DS)
-
-/*
- * Get/set the SFC/DFC registers for MOVES instructions
- */
-
-static inline mm_segment_t get_fs(void)
-{
-	mm_segment_t _v;
-	__asm__ ("movec %/dfc,%0":"=r" (_v.seg):);
-
-	return _v;
-}
-
-static inline mm_segment_t get_ds(void)
-{
-    /* return the supervisor data space code */
-    return KERNEL_DS;
-}
-
-static inline void set_fs(mm_segment_t val)
-{
-	__asm__ __volatile__ ("movec %0,%/sfc\n\t"
-			      "movec %0,%/dfc\n\t"
-			      : /* no outputs */ : "r" (val.seg) : "memory");
-}
-
-#define segment_eq(a,b)	((a).seg == (b).seg)
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _M68K_SEGMENT_H */
diff --git a/arch/m68k/include/asm/segment_no.h b/arch/m68k/include/asm/segment_no.h
deleted file mode 100644
index 42318ebec7ec..000000000000
--- a/arch/m68k/include/asm/segment_no.h
+++ /dev/null
@@ -1,51 +0,0 @@
-#ifndef _M68K_SEGMENT_H
-#define _M68K_SEGMENT_H
-
-/* define constants */
-/* Address spaces (FC0-FC2) */
-#define USER_DATA     (1)
-#ifndef __USER_DS
-#define __USER_DS     (USER_DATA)
-#endif
-#define USER_PROGRAM  (2)
-#define SUPER_DATA    (5)
-#ifndef __KERNEL_DS
-#define __KERNEL_DS   (SUPER_DATA)
-#endif
-#define SUPER_PROGRAM (6)
-#define CPU_SPACE     (7)
-
-#ifndef __ASSEMBLY__
-
-typedef struct {
-	unsigned long seg;
-} mm_segment_t;
-
-#define MAKE_MM_SEG(s)	((mm_segment_t) { (s) })
-#define USER_DS		MAKE_MM_SEG(__USER_DS)
-#define KERNEL_DS	MAKE_MM_SEG(__KERNEL_DS)
-
-/*
- * Get/set the SFC/DFC registers for MOVES instructions
- */
-
-static inline mm_segment_t get_fs(void)
-{
-    return USER_DS;
-}
-
-static inline mm_segment_t get_ds(void)
-{
-    /* return the supervisor data space code */
-    return KERNEL_DS;
-}
-
-static inline void set_fs(mm_segment_t val)
-{
-}
-
-#define segment_eq(a,b)	((a).seg == (b).seg)
-
-#endif /* __ASSEMBLY__ */
-
-#endif /* _M68K_SEGMENT_H */
diff --git a/arch/m68k/include/asm/timex.h b/arch/m68k/include/asm/timex.h
index 719762980578..b87f2f278f67 100644
--- a/arch/m68k/include/asm/timex.h
+++ b/arch/m68k/include/asm/timex.h
@@ -1,5 +1,18 @@
-#ifdef __uClinux__
-#include "timex_no.h"
-#else
-#include "timex_mm.h"
+/*
+ * linux/include/asm-m68k/timex.h
+ *
+ * m68k architecture timex specifications
+ */
+#ifndef _ASMm68k_TIMEX_H
+#define _ASMm68k_TIMEX_H
+
+#define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
+
+typedef unsigned long cycles_t;
+
+static inline cycles_t get_cycles(void)
+{
+	return 0;
+}
+
 #endif
diff --git a/arch/m68k/include/asm/timex_mm.h b/arch/m68k/include/asm/timex_mm.h
deleted file mode 100644
index b87f2f278f67..000000000000
--- a/arch/m68k/include/asm/timex_mm.h
+++ /dev/null
@@ -1,18 +0,0 @@
-/*
- * linux/include/asm-m68k/timex.h
- *
- * m68k architecture timex specifications
- */
-#ifndef _ASMm68k_TIMEX_H
-#define _ASMm68k_TIMEX_H
-
-#define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
-
-typedef unsigned long cycles_t;
-
-static inline cycles_t get_cycles(void)
-{
-	return 0;
-}
-
-#endif
diff --git a/arch/m68k/include/asm/timex_no.h b/arch/m68k/include/asm/timex_no.h
deleted file mode 100644
index 109050f3fe91..000000000000
--- a/arch/m68k/include/asm/timex_no.h
+++ /dev/null
@@ -1,23 +0,0 @@
-/*
- * linux/include/asm-m68knommu/timex.h
- *
- * m68knommu architecture timex specifications
- */
-#ifndef _ASM_M68KNOMMU_TIMEX_H
-#define _ASM_M68KNOMMU_TIMEX_H
-
-#ifdef CONFIG_COLDFIRE
-#include <asm/coldfire.h>
-#define CLOCK_TICK_RATE	MCF_CLK
-#else
-#define CLOCK_TICK_RATE	1193180 /* Underlying HZ */
-#endif
-
-typedef unsigned long cycles_t;
-
-static inline cycles_t get_cycles(void)
-{
-	return 0;
-}
-
-#endif
diff --git a/arch/m68k/include/asm/tlbflush.h b/arch/m68k/include/asm/tlbflush.h
index b6f93b30951e..a6b4ed4fc90f 100644
--- a/arch/m68k/include/asm/tlbflush.h
+++ b/arch/m68k/include/asm/tlbflush.h
@@ -1,5 +1,267 @@
-#ifdef __uClinux__
-#include "tlbflush_no.h"
+#ifndef _M68K_TLBFLUSH_H
+#define _M68K_TLBFLUSH_H
+
+#ifdef CONFIG_MMU
+#ifndef CONFIG_SUN3
+
+#include <asm/current.h>
+
+static inline void flush_tlb_kernel_page(void *addr)
+{
+	if (CPU_IS_040_OR_060) {
+		mm_segment_t old_fs = get_fs();
+		set_fs(KERNEL_DS);
+		__asm__ __volatile__(".chip 68040\n\t"
+				     "pflush (%0)\n\t"
+				     ".chip 68k"
+				     : : "a" (addr));
+		set_fs(old_fs);
+	} else if (CPU_IS_020_OR_030)
+		__asm__ __volatile__("pflush #4,#4,(%0)" : : "a" (addr));
+}
+
+/*
+ * flush all user-space atc entries.
+ */
+static inline void __flush_tlb(void)
+{
+	if (CPU_IS_040_OR_060)
+		__asm__ __volatile__(".chip 68040\n\t"
+				     "pflushan\n\t"
+				     ".chip 68k");
+	else if (CPU_IS_020_OR_030)
+		__asm__ __volatile__("pflush #0,#4");
+}
+
+static inline void __flush_tlb040_one(unsigned long addr)
+{
+	__asm__ __volatile__(".chip 68040\n\t"
+			     "pflush (%0)\n\t"
+			     ".chip 68k"
+			     : : "a" (addr));
+}
+
+static inline void __flush_tlb_one(unsigned long addr)
+{
+	if (CPU_IS_040_OR_060)
+		__flush_tlb040_one(addr);
+	else if (CPU_IS_020_OR_030)
+		__asm__ __volatile__("pflush #0,#4,(%0)" : : "a" (addr));
+}
+
+#define flush_tlb() __flush_tlb()
+
+/*
+ * flush all atc entries (both kernel and user-space entries).
+ */
+static inline void flush_tlb_all(void)
+{
+	if (CPU_IS_040_OR_060)
+		__asm__ __volatile__(".chip 68040\n\t"
+				     "pflusha\n\t"
+				     ".chip 68k");
+	else if (CPU_IS_020_OR_030)
+		__asm__ __volatile__("pflusha");
+}
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	if (mm == current->active_mm)
+		__flush_tlb();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	if (vma->vm_mm == current->active_mm) {
+		mm_segment_t old_fs = get_fs();
+		set_fs(USER_DS);
+		__flush_tlb_one(addr);
+		set_fs(old_fs);
+	}
+}
+
+static inline void flush_tlb_range(struct vm_area_struct *vma,
+				   unsigned long start, unsigned long end)
+{
+	if (vma->vm_mm == current->active_mm)
+		__flush_tlb();
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	flush_tlb_all();
+}
+
 #else
-#include "tlbflush_mm.h"
+
+
+/* Reserved PMEGs. */
+extern char sun3_reserved_pmeg[SUN3_PMEGS_NUM];
+extern unsigned long pmeg_vaddr[SUN3_PMEGS_NUM];
+extern unsigned char pmeg_alloc[SUN3_PMEGS_NUM];
+extern unsigned char pmeg_ctx[SUN3_PMEGS_NUM];
+
+/* Flush all userspace mappings one by one...  (why no flush command,
+   sun?) */
+static inline void flush_tlb_all(void)
+{
+       unsigned long addr;
+       unsigned char ctx, oldctx;
+
+       oldctx = sun3_get_context();
+       for(addr = 0x00000000; addr < TASK_SIZE; addr += SUN3_PMEG_SIZE) {
+	       for(ctx = 0; ctx < 8; ctx++) {
+		       sun3_put_context(ctx);
+		       sun3_put_segmap(addr, SUN3_INVALID_PMEG);
+	       }
+       }
+
+       sun3_put_context(oldctx);
+       /* erase all of the userspace pmeg maps, we've clobbered them
+	  all anyway */
+       for(addr = 0; addr < SUN3_INVALID_PMEG; addr++) {
+	       if(pmeg_alloc[addr] == 1) {
+		       pmeg_alloc[addr] = 0;
+		       pmeg_ctx[addr] = 0;
+		       pmeg_vaddr[addr] = 0;
+	       }
+       }
+
+}
+
+/* Clear user TLB entries within the context named in mm */
+static inline void flush_tlb_mm (struct mm_struct *mm)
+{
+     unsigned char oldctx;
+     unsigned char seg;
+     unsigned long i;
+
+     oldctx = sun3_get_context();
+     sun3_put_context(mm->context);
+
+     for(i = 0; i < TASK_SIZE; i += SUN3_PMEG_SIZE) {
+	     seg = sun3_get_segmap(i);
+	     if(seg == SUN3_INVALID_PMEG)
+		     continue;
+
+	     sun3_put_segmap(i, SUN3_INVALID_PMEG);
+	     pmeg_alloc[seg] = 0;
+	     pmeg_ctx[seg] = 0;
+	     pmeg_vaddr[seg] = 0;
+     }
+
+     sun3_put_context(oldctx);
+
+}
+
+/* Flush a single TLB page. In this case, we're limited to flushing a
+   single PMEG */
+static inline void flush_tlb_page (struct vm_area_struct *vma,
+				   unsigned long addr)
+{
+	unsigned char oldctx;
+	unsigned char i;
+
+	oldctx = sun3_get_context();
+	sun3_put_context(vma->vm_mm->context);
+	addr &= ~SUN3_PMEG_MASK;
+	if((i = sun3_get_segmap(addr)) != SUN3_INVALID_PMEG)
+	{
+		pmeg_alloc[i] = 0;
+		pmeg_ctx[i] = 0;
+		pmeg_vaddr[i] = 0;
+		sun3_put_segmap (addr,  SUN3_INVALID_PMEG);
+	}
+	sun3_put_context(oldctx);
+
+}
+/* Flush a range of pages from TLB. */
+
+static inline void flush_tlb_range (struct vm_area_struct *vma,
+		      unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	unsigned char seg, oldctx;
+
+	start &= ~SUN3_PMEG_MASK;
+
+	oldctx = sun3_get_context();
+	sun3_put_context(mm->context);
+
+	while(start < end)
+	{
+		if((seg = sun3_get_segmap(start)) == SUN3_INVALID_PMEG)
+		     goto next;
+		if(pmeg_ctx[seg] == mm->context) {
+			pmeg_alloc[seg] = 0;
+			pmeg_ctx[seg] = 0;
+			pmeg_vaddr[seg] = 0;
+		}
+		sun3_put_segmap(start, SUN3_INVALID_PMEG);
+	next:
+		start += SUN3_PMEG_SIZE;
+	}
+}
+
+static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
+{
+	flush_tlb_all();
+}
+
+/* Flush kernel page from TLB. */
+static inline void flush_tlb_kernel_page (unsigned long addr)
+{
+	sun3_put_segmap (addr & ~(SUN3_PMEG_SIZE - 1), SUN3_INVALID_PMEG);
+}
+
 #endif
+
+#else /* !CONFIG_MMU */
+
+/*
+ * flush all user-space atc entries.
+ */
+static inline void __flush_tlb(void)
+{
+	BUG();
+}
+
+static inline void __flush_tlb_one(unsigned long addr)
+{
+	BUG();
+}
+
+#define flush_tlb() __flush_tlb()
+
+/*
+ * flush all atc entries (both kernel and user-space entries).
+ */
+static inline void flush_tlb_all(void)
+{
+	BUG();
+}
+
+static inline void flush_tlb_mm(struct mm_struct *mm)
+{
+	BUG();
+}
+
+static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
+{
+	BUG();
+}
+
+static inline void flush_tlb_range(struct mm_struct *mm,
+				   unsigned long start, unsigned long end)
+{
+	BUG();
+}
+
+static inline void flush_tlb_kernel_page(unsigned long addr)
+{
+	BUG();
+}
+
+#endif /* CONFIG_MMU */
+
+#endif /* _M68K_TLBFLUSH_H */
diff --git a/arch/m68k/include/asm/tlbflush_mm.h b/arch/m68k/include/asm/tlbflush_mm.h
deleted file mode 100644
index acb6bf21a321..000000000000
--- a/arch/m68k/include/asm/tlbflush_mm.h
+++ /dev/null
@@ -1,219 +0,0 @@
-#ifndef _M68K_TLBFLUSH_H
-#define _M68K_TLBFLUSH_H
-
-
-#ifndef CONFIG_SUN3
-
-#include <asm/current.h>
-
-static inline void flush_tlb_kernel_page(void *addr)
-{
-	if (CPU_IS_040_OR_060) {
-		mm_segment_t old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		__asm__ __volatile__(".chip 68040\n\t"
-				     "pflush (%0)\n\t"
-				     ".chip 68k"
-				     : : "a" (addr));
-		set_fs(old_fs);
-	} else if (CPU_IS_020_OR_030)
-		__asm__ __volatile__("pflush #4,#4,(%0)" : : "a" (addr));
-}
-
-/*
- * flush all user-space atc entries.
- */
-static inline void __flush_tlb(void)
-{
-	if (CPU_IS_040_OR_060)
-		__asm__ __volatile__(".chip 68040\n\t"
-				     "pflushan\n\t"
-				     ".chip 68k");
-	else if (CPU_IS_020_OR_030)
-		__asm__ __volatile__("pflush #0,#4");
-}
-
-static inline void __flush_tlb040_one(unsigned long addr)
-{
-	__asm__ __volatile__(".chip 68040\n\t"
-			     "pflush (%0)\n\t"
-			     ".chip 68k"
-			     : : "a" (addr));
-}
-
-static inline void __flush_tlb_one(unsigned long addr)
-{
-	if (CPU_IS_040_OR_060)
-		__flush_tlb040_one(addr);
-	else if (CPU_IS_020_OR_030)
-		__asm__ __volatile__("pflush #0,#4,(%0)" : : "a" (addr));
-}
-
-#define flush_tlb() __flush_tlb()
-
-/*
- * flush all atc entries (both kernel and user-space entries).
- */
-static inline void flush_tlb_all(void)
-{
-	if (CPU_IS_040_OR_060)
-		__asm__ __volatile__(".chip 68040\n\t"
-				     "pflusha\n\t"
-				     ".chip 68k");
-	else if (CPU_IS_020_OR_030)
-		__asm__ __volatile__("pflusha");
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	if (mm == current->active_mm)
-		__flush_tlb();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
-{
-	if (vma->vm_mm == current->active_mm) {
-		mm_segment_t old_fs = get_fs();
-		set_fs(USER_DS);
-		__flush_tlb_one(addr);
-		set_fs(old_fs);
-	}
-}
-
-static inline void flush_tlb_range(struct vm_area_struct *vma,
-				   unsigned long start, unsigned long end)
-{
-	if (vma->vm_mm == current->active_mm)
-		__flush_tlb();
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
-	flush_tlb_all();
-}
-
-#else
-
-
-/* Reserved PMEGs. */
-extern char sun3_reserved_pmeg[SUN3_PMEGS_NUM];
-extern unsigned long pmeg_vaddr[SUN3_PMEGS_NUM];
-extern unsigned char pmeg_alloc[SUN3_PMEGS_NUM];
-extern unsigned char pmeg_ctx[SUN3_PMEGS_NUM];
-
-/* Flush all userspace mappings one by one...  (why no flush command,
-   sun?) */
-static inline void flush_tlb_all(void)
-{
-       unsigned long addr;
-       unsigned char ctx, oldctx;
-
-       oldctx = sun3_get_context();
-       for(addr = 0x00000000; addr < TASK_SIZE; addr += SUN3_PMEG_SIZE) {
-	       for(ctx = 0; ctx < 8; ctx++) {
-		       sun3_put_context(ctx);
-		       sun3_put_segmap(addr, SUN3_INVALID_PMEG);
-	       }
-       }
-
-       sun3_put_context(oldctx);
-       /* erase all of the userspace pmeg maps, we've clobbered them
-	  all anyway */
-       for(addr = 0; addr < SUN3_INVALID_PMEG; addr++) {
-	       if(pmeg_alloc[addr] == 1) {
-		       pmeg_alloc[addr] = 0;
-		       pmeg_ctx[addr] = 0;
-		       pmeg_vaddr[addr] = 0;
-	       }
-       }
-
-}
-
-/* Clear user TLB entries within the context named in mm */
-static inline void flush_tlb_mm (struct mm_struct *mm)
-{
-     unsigned char oldctx;
-     unsigned char seg;
-     unsigned long i;
-
-     oldctx = sun3_get_context();
-     sun3_put_context(mm->context);
-
-     for(i = 0; i < TASK_SIZE; i += SUN3_PMEG_SIZE) {
-	     seg = sun3_get_segmap(i);
-	     if(seg == SUN3_INVALID_PMEG)
-		     continue;
-
-	     sun3_put_segmap(i, SUN3_INVALID_PMEG);
-	     pmeg_alloc[seg] = 0;
-	     pmeg_ctx[seg] = 0;
-	     pmeg_vaddr[seg] = 0;
-     }
-
-     sun3_put_context(oldctx);
-
-}
-
-/* Flush a single TLB page. In this case, we're limited to flushing a
-   single PMEG */
-static inline void flush_tlb_page (struct vm_area_struct *vma,
-				   unsigned long addr)
-{
-	unsigned char oldctx;
-	unsigned char i;
-
-	oldctx = sun3_get_context();
-	sun3_put_context(vma->vm_mm->context);
-	addr &= ~SUN3_PMEG_MASK;
-	if((i = sun3_get_segmap(addr)) != SUN3_INVALID_PMEG)
-	{
-		pmeg_alloc[i] = 0;
-		pmeg_ctx[i] = 0;
-		pmeg_vaddr[i] = 0;
-		sun3_put_segmap (addr,  SUN3_INVALID_PMEG);
-	}
-	sun3_put_context(oldctx);
-
-}
-/* Flush a range of pages from TLB. */
-
-static inline void flush_tlb_range (struct vm_area_struct *vma,
-		      unsigned long start, unsigned long end)
-{
-	struct mm_struct *mm = vma->vm_mm;
-	unsigned char seg, oldctx;
-
-	start &= ~SUN3_PMEG_MASK;
-
-	oldctx = sun3_get_context();
-	sun3_put_context(mm->context);
-
-	while(start < end)
-	{
-		if((seg = sun3_get_segmap(start)) == SUN3_INVALID_PMEG)
-		     goto next;
-		if(pmeg_ctx[seg] == mm->context) {
-			pmeg_alloc[seg] = 0;
-			pmeg_ctx[seg] = 0;
-			pmeg_vaddr[seg] = 0;
-		}
-		sun3_put_segmap(start, SUN3_INVALID_PMEG);
-	next:
-		start += SUN3_PMEG_SIZE;
-	}
-}
-
-static inline void flush_tlb_kernel_range(unsigned long start, unsigned long end)
-{
-	flush_tlb_all();
-}
-
-/* Flush kernel page from TLB. */
-static inline void flush_tlb_kernel_page (unsigned long addr)
-{
-	sun3_put_segmap (addr & ~(SUN3_PMEG_SIZE - 1), SUN3_INVALID_PMEG);
-}
-
-#endif
-
-#endif /* _M68K_TLBFLUSH_H */
diff --git a/arch/m68k/include/asm/tlbflush_no.h b/arch/m68k/include/asm/tlbflush_no.h
deleted file mode 100644
index a470cfb803eb..000000000000
--- a/arch/m68k/include/asm/tlbflush_no.h
+++ /dev/null
@@ -1,55 +0,0 @@
-#ifndef _M68KNOMMU_TLBFLUSH_H
-#define _M68KNOMMU_TLBFLUSH_H
-
-/*
- * Copyright (C) 2000 Lineo, David McCullough <davidm@uclinux.org>
- * Copyright (C) 2000-2002, Greg Ungerer <gerg@snapgear.com>
- */
-
-#include <asm/setup.h>
-
-/*
- * flush all user-space atc entries.
- */
-static inline void __flush_tlb(void)
-{
-	BUG();
-}
-
-static inline void __flush_tlb_one(unsigned long addr)
-{
-	BUG();
-}
-
-#define flush_tlb() __flush_tlb()
-
-/*
- * flush all atc entries (both kernel and user-space entries).
- */
-static inline void flush_tlb_all(void)
-{
-	BUG();
-}
-
-static inline void flush_tlb_mm(struct mm_struct *mm)
-{
-	BUG();
-}
-
-static inline void flush_tlb_page(struct vm_area_struct *vma, unsigned long addr)
-{
-	BUG();
-}
-
-static inline void flush_tlb_range(struct mm_struct *mm,
-				   unsigned long start, unsigned long end)
-{
-	BUG();
-}
-
-static inline void flush_tlb_kernel_page(unsigned long addr)
-{
-	BUG();
-}
-
-#endif /* _M68KNOMMU_TLBFLUSH_H */
diff --git a/arch/m68k/include/asm/ucontext.h b/arch/m68k/include/asm/ucontext.h
index b53cd160c0b3..e4e22669edc0 100644
--- a/arch/m68k/include/asm/ucontext.h
+++ b/arch/m68k/include/asm/ucontext.h
@@ -1,5 +1,30 @@
-#ifdef __uClinux__
-#include "ucontext_no.h"
-#else
-#include "ucontext_mm.h"
+#ifndef _M68K_UCONTEXT_H
+#define _M68K_UCONTEXT_H
+
+typedef int greg_t;
+#define NGREG 18
+typedef greg_t gregset_t[NGREG];
+
+typedef struct fpregset {
+	int f_fpcntl[3];
+	int f_fpregs[8*3];
+} fpregset_t;
+
+struct mcontext {
+	int version;
+	gregset_t gregs;
+	fpregset_t fpregs;
+};
+
+#define MCONTEXT_VERSION 2
+
+struct ucontext {
+	unsigned long	  uc_flags;
+	struct ucontext  *uc_link;
+	stack_t		  uc_stack;
+	struct mcontext	  uc_mcontext;
+	unsigned long	  uc_filler[80];
+	sigset_t	  uc_sigmask;	/* mask last for extensibility */
+};
+
 #endif
diff --git a/arch/m68k/include/asm/ucontext_mm.h b/arch/m68k/include/asm/ucontext_mm.h
deleted file mode 100644
index e4e22669edc0..000000000000
--- a/arch/m68k/include/asm/ucontext_mm.h
+++ /dev/null
@@ -1,30 +0,0 @@
-#ifndef _M68K_UCONTEXT_H
-#define _M68K_UCONTEXT_H
-
-typedef int greg_t;
-#define NGREG 18
-typedef greg_t gregset_t[NGREG];
-
-typedef struct fpregset {
-	int f_fpcntl[3];
-	int f_fpregs[8*3];
-} fpregset_t;
-
-struct mcontext {
-	int version;
-	gregset_t gregs;
-	fpregset_t fpregs;
-};
-
-#define MCONTEXT_VERSION 2
-
-struct ucontext {
-	unsigned long	  uc_flags;
-	struct ucontext  *uc_link;
-	stack_t		  uc_stack;
-	struct mcontext	  uc_mcontext;
-	unsigned long	  uc_filler[80];
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
-#endif
diff --git a/arch/m68k/include/asm/ucontext_no.h b/arch/m68k/include/asm/ucontext_no.h
deleted file mode 100644
index 713a27f901cd..000000000000
--- a/arch/m68k/include/asm/ucontext_no.h
+++ /dev/null
@@ -1,32 +0,0 @@
-#ifndef _M68KNOMMU_UCONTEXT_H
-#define _M68KNOMMU_UCONTEXT_H
-
-typedef int greg_t;
-#define NGREG 18
-typedef greg_t gregset_t[NGREG];
-
-typedef struct fpregset {
-	int f_pcr;
-	int f_psr;
-	int f_fpiaddr;
-	int f_fpregs[8][3];
-} fpregset_t;
-
-struct mcontext {
-	int version;
-	gregset_t gregs;
-	fpregset_t fpregs;
-};
-
-#define MCONTEXT_VERSION 2
-
-struct ucontext {
-	unsigned long	  uc_flags;
-	struct ucontext  *uc_link;
-	stack_t		  uc_stack;
-	struct mcontext	  uc_mcontext;
-	unsigned long	  uc_filler[80];
-	sigset_t	  uc_sigmask;	/* mask last for extensibility */
-};
-
-#endif
diff --git a/arch/m68k/include/asm/unaligned.h b/arch/m68k/include/asm/unaligned.h
index c640bba3bdf4..019caa740c21 100644
--- a/arch/m68k/include/asm/unaligned.h
+++ b/arch/m68k/include/asm/unaligned.h
@@ -1,5 +1,25 @@
-#ifdef __uClinux__
-#include "unaligned_no.h"
+#ifndef _ASM_M68K_UNALIGNED_H
+#define _ASM_M68K_UNALIGNED_H
+
+
+#ifdef CONFIG_COLDFIRE
+#include <linux/unaligned/be_struct.h>
+#include <linux/unaligned/le_byteshift.h>
+#include <linux/unaligned/generic.h>
+
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
+
 #else
-#include "unaligned_mm.h"
+/*
+ * The m68k can do unaligned accesses itself. 
+ */
+#include <linux/unaligned/access_ok.h>
+#include <linux/unaligned/generic.h>
+
+#define get_unaligned	__get_unaligned_be
+#define put_unaligned	__put_unaligned_be
+
 #endif
+
+#endif /* _ASM_M68K_UNALIGNED_H */
diff --git a/arch/m68k/include/asm/unaligned_mm.h b/arch/m68k/include/asm/unaligned_mm.h
deleted file mode 100644
index 77698f2dc33c..000000000000
--- a/arch/m68k/include/asm/unaligned_mm.h
+++ /dev/null
@@ -1,13 +0,0 @@
-#ifndef _ASM_M68K_UNALIGNED_H
-#define _ASM_M68K_UNALIGNED_H
-
-/*
- * The m68k can do unaligned accesses itself.
- */
-#include <linux/unaligned/access_ok.h>
-#include <linux/unaligned/generic.h>
-
-#define get_unaligned	__get_unaligned_be
-#define put_unaligned	__put_unaligned_be
-
-#endif /* _ASM_M68K_UNALIGNED_H */
diff --git a/arch/m68k/include/asm/unaligned_no.h b/arch/m68k/include/asm/unaligned_no.h
deleted file mode 100644
index eb1ea4cb9a59..000000000000
--- a/arch/m68k/include/asm/unaligned_no.h
+++ /dev/null
@@ -1,25 +0,0 @@
-#ifndef _ASM_M68KNOMMU_UNALIGNED_H
-#define _ASM_M68KNOMMU_UNALIGNED_H
-
-
-#ifdef CONFIG_COLDFIRE
-#include <linux/unaligned/be_struct.h>
-#include <linux/unaligned/le_byteshift.h>
-#include <linux/unaligned/generic.h>
-
-#define get_unaligned	__get_unaligned_be
-#define put_unaligned	__put_unaligned_be
-
-#else
-/*
- * The m68k can do unaligned accesses itself. 
- */
-#include <linux/unaligned/access_ok.h>
-#include <linux/unaligned/generic.h>
-
-#define get_unaligned	__get_unaligned_be
-#define put_unaligned	__put_unaligned_be
-
-#endif
-
-#endif /* _ASM_M68KNOMMU_UNALIGNED_H */
diff --git a/arch/m68k/kernel/process.c b/arch/m68k/kernel/process.c
index 632ce016014d..ec37fb56c127 100644
--- a/arch/m68k/kernel/process.c
+++ b/arch/m68k/kernel/process.c
@@ -233,7 +233,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs)
 		       parent_tidptr, child_tidptr);
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		 unsigned long unused,
 		 struct task_struct * p, struct pt_regs * regs)
 {
diff --git a/arch/m68k/kernel/time.c b/arch/m68k/kernel/time.c
index 7db41594d7b6..54d980795fc4 100644
--- a/arch/m68k/kernel/time.c
+++ b/arch/m68k/kernel/time.c
@@ -18,6 +18,7 @@
 #include <linux/string.h>
 #include <linux/mm.h>
 #include <linux/rtc.h>
+#include <linux/platform_device.h>
 
 #include <asm/machdep.h>
 #include <asm/io.h>
@@ -159,3 +160,20 @@ int do_settimeofday(struct timespec *tv)
 }
 
 EXPORT_SYMBOL(do_settimeofday);
+
+
+static int __init rtc_init(void)
+{
+	struct platform_device *pdev;
+
+	if (!mach_hwclk)
+		return -ENODEV;
+
+	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	return 0;
+}
+
+module_init(rtc_init);
diff --git a/arch/m68knommu/Makefile b/arch/m68knommu/Makefile
index fd0fb303d885..ce404bc9ccbd 100644
--- a/arch/m68knommu/Makefile
+++ b/arch/m68knommu/Makefile
@@ -88,18 +88,18 @@ export PLATFORM BOARD MODEL CPUCLASS
 #
 # Some CFLAG additions based on specific CPU type.
 #
-cflags-$(CONFIG_M5206)		:= -m5200
-cflags-$(CONFIG_M5206e)		:= -m5200
-cflags-$(CONFIG_M520x)		:= -m5307
+cflags-$(CONFIG_M5206)		:= $(call cc-option,-mcpu=5206,-m5200)
+cflags-$(CONFIG_M5206e)		:= $(call cc-option,-m5206e,-m5200)
+cflags-$(CONFIG_M520x)		:= $(call cc-option,-mcpu=5208,-m5200)
 cflags-$(CONFIG_M523x)		:= $(call cc-option,-mcpu=523x,-m5307)
-cflags-$(CONFIG_M5249)		:= -m5200
+cflags-$(CONFIG_M5249)		:= $(call cc-option,-mcpu=5249,-m5200)
 cflags-$(CONFIG_M5271)		:= $(call cc-option,-mcpu=5271,-m5307)
-cflags-$(CONFIG_M5272)		:= -m5307
+cflags-$(CONFIG_M5272)		:= $(call cc-option,-mcpu=5271,-m5200)
 cflags-$(CONFIG_M5275)		:= $(call cc-option,-mcpu=5275,-m5307)
 cflags-$(CONFIG_M528x)		:= $(call cc-option,-m528x,-m5307)
-cflags-$(CONFIG_M5307)		:= -m5307
+cflags-$(CONFIG_M5307)		:= $(call cc-option,-m5307,-m5200)
 cflags-$(CONFIG_M532x)		:= $(call cc-option,-mcpu=532x,-m5307)
-cflags-$(CONFIG_M5407)		:= -m5200
+cflags-$(CONFIG_M5407)		:= $(call cc-option,-m5407,-m5200)
 cflags-$(CONFIG_M68328)		:= -m68000
 cflags-$(CONFIG_M68EZ328)	:= -m68000
 cflags-$(CONFIG_M68VZ328)	:= -m68000
diff --git a/arch/m68knommu/kernel/dma.c b/arch/m68knommu/kernel/dma.c
index e10eafc52789..936125806638 100644
--- a/arch/m68knommu/kernel/dma.c
+++ b/arch/m68knommu/kernel/dma.c
@@ -9,10 +9,11 @@
 #include <linux/mm.h>
 #include <linux/string.h>
 #include <linux/device.h>
+#include <linux/dma-mapping.h>
 #include <asm/io.h>
 
 void *dma_alloc_coherent(struct device *dev, size_t size,
-			   dma_addr_t *dma_handle, int gfp)
+			   dma_addr_t *dma_handle, gfp_t gfp)
 {
 	void *ret;
 	/* ignore region specifiers */
@@ -34,3 +35,8 @@ void dma_free_coherent(struct device *dev, size_t size,
 {
 	free_pages((unsigned long)vaddr, get_order(size));
 }
+
+void dma_sync_single_for_cpu(struct device *dev, dma_addr_t handle, size_t size, enum dma_data_direction dir)
+{
+}
+
diff --git a/arch/m68knommu/kernel/irq.c b/arch/m68knommu/kernel/irq.c
index bba1bb48a21f..56e0f4c55a67 100644
--- a/arch/m68knommu/kernel/irq.c
+++ b/arch/m68knommu/kernel/irq.c
@@ -23,7 +23,7 @@ asmlinkage void do_IRQ(int irq, struct pt_regs *regs)
 	struct pt_regs *oldregs = set_irq_regs(regs);
 
 	irq_enter();
-	__do_IRQ(irq);
+	generic_handle_irq(irq);
 	irq_exit();
 
 	set_irq_regs(oldregs);
diff --git a/arch/m68knommu/kernel/process.c b/arch/m68knommu/kernel/process.c
index 3f2d7745f31e..1e96c6eb6312 100644
--- a/arch/m68knommu/kernel/process.c
+++ b/arch/m68knommu/kernel/process.c
@@ -199,7 +199,7 @@ asmlinkage int m68k_clone(struct pt_regs *regs)
         return do_fork(clone_flags, newsp, regs, 0, NULL, NULL);
 }
 
-int copy_thread(int nr, unsigned long clone_flags,
+int copy_thread(unsigned long clone_flags,
 		unsigned long usp, unsigned long topstk,
 		struct task_struct * p, struct pt_regs * regs)
 {
diff --git a/arch/m68knommu/mm/init.c b/arch/m68knommu/mm/init.c
index 3bf249c53e41..7befc0c357e0 100644
--- a/arch/m68knommu/mm/init.c
+++ b/arch/m68knommu/mm/init.c
@@ -111,11 +111,7 @@ void __init paging_init(void)
 	{
 		unsigned long zones_size[MAX_NR_ZONES] = {0, };
 
-		zones_size[ZONE_DMA] = 0 >> PAGE_SHIFT;
-		zones_size[ZONE_NORMAL] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT;
-#ifdef CONFIG_HIGHMEM
-		zones_size[ZONE_HIGHMEM] = 0;
-#endif
+		zones_size[ZONE_DMA] = (end_mem - PAGE_OFFSET) >> PAGE_SHIFT;
 		free_area_init(zones_size);
 	}
 }
diff --git a/arch/m68knommu/platform/5249/config.c b/arch/m68knommu/platform/5249/config.c
index d299f7b8768a..9eab19d01eb1 100644
--- a/arch/m68knommu/platform/5249/config.c
+++ b/arch/m68knommu/platform/5249/config.c
@@ -32,7 +32,8 @@ static struct mcf_platform_uart m5249_uart_platform[] = {
 	{
 		.mapbase 	= MCF_MBAR + MCFUART_BASE2,
 		.irq		= 74,
-	}
+	},
+	{ },
 };
 
 static struct platform_device m5249_uart = {
@@ -50,12 +51,12 @@ static struct platform_device *m5249_devices[] __initdata = {
 static void __init m5249_uart_init_line(int line, int irq)
 {
 	if (line == 0) {
-		writel(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI1, MCF_MBAR + MCFSIM_UART1ICR);
-		writeb(irq, MCFUART_BASE1 + MCFUART_UIVR);
+		writeb(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI1, MCF_MBAR + MCFSIM_UART1ICR);
+		writeb(irq, MCF_MBAR + MCFUART_BASE1 + MCFUART_UIVR);
 		mcf_setimr(mcf_getimr() & ~MCFSIM_IMR_UART1);
 	} else if (line == 1) {
-		writel(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI2, MCF_MBAR + MCFSIM_UART2ICR);
-		writeb(irq, MCFUART_BASE2 + MCFUART_UIVR);
+		writeb(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI2, MCF_MBAR + MCFSIM_UART2ICR);
+		writeb(irq, MCF_MBAR + MCFUART_BASE2 + MCFUART_UIVR);
 		mcf_setimr(mcf_getimr() & ~MCFSIM_IMR_UART2);
 	}
 }
diff --git a/arch/m68knommu/platform/5307/config.c b/arch/m68knommu/platform/5307/config.c
index 724faf05852a..44803bf70a6e 100644
--- a/arch/m68knommu/platform/5307/config.c
+++ b/arch/m68knommu/platform/5307/config.c
@@ -65,12 +65,12 @@ static struct platform_device *m5307_devices[] __initdata = {
 static void __init m5307_uart_init_line(int line, int irq)
 {
 	if (line == 0) {
-		writel(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI1, MCF_MBAR + MCFSIM_UART1ICR);
-		writeb(irq, MCFUART_BASE1 + MCFUART_UIVR);
+		writeb(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI1, MCF_MBAR + MCFSIM_UART1ICR);
+		writeb(irq, MCF_MBAR + MCFUART_BASE1 + MCFUART_UIVR);
 		mcf_setimr(mcf_getimr() & ~MCFSIM_IMR_UART1);
 	} else if (line == 1) {
-		writel(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI2, MCF_MBAR + MCFSIM_UART2ICR);
-		writeb(irq, MCFUART_BASE2 + MCFUART_UIVR);
+		writeb(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI2, MCF_MBAR + MCFSIM_UART2ICR);
+		writeb(irq, MCF_MBAR + MCFUART_BASE2 + MCFUART_UIVR);
 		mcf_setimr(mcf_getimr() & ~MCFSIM_IMR_UART2);
 	}
 }
diff --git a/arch/m68knommu/platform/5407/config.c b/arch/m68knommu/platform/5407/config.c
index 648b8b778211..0ee8c1a200c8 100644
--- a/arch/m68knommu/platform/5407/config.c
+++ b/arch/m68knommu/platform/5407/config.c
@@ -56,12 +56,12 @@ static struct platform_device *m5407_devices[] __initdata = {
 static void __init m5407_uart_init_line(int line, int irq)
 {
 	if (line == 0) {
-		writel(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI1, MCF_MBAR + MCFSIM_UART1ICR);
-		writeb(irq, MCFUART_BASE1 + MCFUART_UIVR);
+		writeb(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI1, MCF_MBAR + MCFSIM_UART1ICR);
+		writeb(irq, MCF_MBAR + MCFUART_BASE1 + MCFUART_UIVR);
 		mcf_setimr(mcf_getimr() & ~MCFSIM_IMR_UART1);
 	} else if (line == 1) {
-		writel(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI2, MCF_MBAR + MCFSIM_UART2ICR);
-		writeb(irq, MCFUART_BASE2 + MCFUART_UIVR);
+		writeb(MCFSIM_ICR_LEVEL6 | MCFSIM_ICR_PRI2, MCF_MBAR + MCFSIM_UART2ICR);
+		writeb(irq, MCF_MBAR + MCFUART_BASE2 + MCFUART_UIVR);
 		mcf_setimr(mcf_getimr() & ~MCFSIM_IMR_UART2);
 	}
 }
diff --git a/arch/m68knommu/platform/coldfire/Makefile b/arch/m68knommu/platform/coldfire/Makefile
index 4f416a91a829..1bcb9372353f 100644
--- a/arch/m68knommu/platform/coldfire/Makefile
+++ b/arch/m68knommu/platform/coldfire/Makefile
@@ -14,7 +14,7 @@
 
 asflags-$(CONFIG_FULLDEBUG) := -DDEBUGGER_COMPATIBLE_CACHE=1
 
-obj-$(CONFIG_COLDFIRE)	+= dma.o entry.o vectors.o
+obj-$(CONFIG_COLDFIRE)	+= clk.o dma.o entry.o vectors.o
 obj-$(CONFIG_M5206)	+= timers.o
 obj-$(CONFIG_M5206e)	+= timers.o
 obj-$(CONFIG_M520x)	+= pit.o
diff --git a/arch/m68knommu/platform/coldfire/clk.c b/arch/m68knommu/platform/coldfire/clk.c
new file mode 100644
index 000000000000..7cdbf445b28f
--- /dev/null
+++ b/arch/m68knommu/platform/coldfire/clk.c
@@ -0,0 +1,40 @@
+/***************************************************************************/
+
+/*
+ *	clk.c -- general ColdFire CPU kernel clk handling
+ *
+ *	Copyright (C) 2009, Greg Ungerer (gerg@snapgear.com)
+ */
+
+/***************************************************************************/
+
+#include <linux/kernel.h>
+#include <linux/clk.h>
+#include <asm/coldfire.h>
+
+/***************************************************************************/
+
+struct clk *clk_get(struct device *dev, const char *id)
+{
+	return NULL;
+}
+
+int clk_enable(struct clk *clk)
+{
+	return 0;
+}
+
+void clk_disable(struct clk *clk)
+{
+}
+
+void clk_put(struct clk *clk)
+{
+}
+
+unsigned long clk_get_rate(struct clk *clk)
+{
+	return MCF_CLK;
+}
+
+/***************************************************************************/
diff --git a/arch/mips/Kconfig b/arch/mips/Kconfig
index dc787190430a..998e5db8cc0f 100644
--- a/arch/mips/Kconfig
+++ b/arch/mips/Kconfig
@@ -134,7 +134,7 @@ config MACH_JAZZ
 	help
 	 This a family of machines based on the MIPS R4030 chipset which was
 	 used by several vendors to build RISC/os and Windows NT workstations.
-	 Members include the Acer PICA, MIPS Magnum 4000, MIPS Millenium and
+	 Members include the Acer PICA, MIPS Magnum 4000, MIPS Millennium and
 	 Olivetti M700-10 workstations.
 
 config LASAT
diff --git a/arch/mips/include/asm/spinlock.h b/arch/mips/include/asm/spinlock.h
index 10e82441b496..5b60a09a0f08 100644
--- a/arch/mips/include/asm/spinlock.h
+++ b/arch/mips/include/asm/spinlock.h
@@ -480,6 +480,8 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
 	return ret;
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
 
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
diff --git a/arch/mips/include/asm/unistd.h b/arch/mips/include/asm/unistd.h
index a73e1531e151..40005010827c 100644
--- a/arch/mips/include/asm/unistd.h
+++ b/arch/mips/include/asm/unistd.h
@@ -350,16 +350,18 @@
 #define __NR_dup3			(__NR_Linux + 327)
 #define __NR_pipe2			(__NR_Linux + 328)
 #define __NR_inotify_init1		(__NR_Linux + 329)
+#define __NR_preadv			(__NR_Linux + 330)
+#define __NR_pwritev			(__NR_Linux + 331)
 
 /*
  * Offset of the last Linux o32 flavoured syscall
  */
-#define __NR_Linux_syscalls		329
+#define __NR_Linux_syscalls		331
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI32 */
 
 #define __NR_O32_Linux			4000
-#define __NR_O32_Linux_syscalls		329
+#define __NR_O32_Linux_syscalls		331
 
 #if _MIPS_SIM == _MIPS_SIM_ABI64
 
@@ -656,16 +658,18 @@
 #define __NR_dup3			(__NR_Linux + 286)
 #define __NR_pipe2			(__NR_Linux + 287)
 #define __NR_inotify_init1		(__NR_Linux + 288)
+#define __NR_preadv			(__NR_Linux + 289)
+#define __NR_pwritev			(__NR_Linux + 290)
 
 /*
  * Offset of the last Linux 64-bit flavoured syscall
  */
-#define __NR_Linux_syscalls		288
+#define __NR_Linux_syscalls		290
 
 #endif /* _MIPS_SIM == _MIPS_SIM_ABI64 */
 
 #define __NR_64_Linux			5000
-#define __NR_64_Linux_syscalls		288
+#define __NR_64_Linux_syscalls		290
 
 #if _MIPS_SIM == _MIPS_SIM_NABI32
 
@@ -966,16 +970,18 @@
 #define __NR_dup3			(__NR_Linux + 290)
 #define __NR_pipe2			(__NR_Linux + 291)
 #define __NR_inotify_init1		(__NR_Linux + 292)
+#define __NR_preadv			(__NR_Linux + 293)
+#define __NR_pwritev			(__NR_Linux + 294)
 
 /*
  * Offset of the last N32 flavoured syscall
  */
-#define __NR_Linux_syscalls		292
+#define __NR_Linux_syscalls		294
 
 #endif /* _MIPS_SIM == _MIPS_SIM_NABI32 */
 
 #define __NR_N32_Linux			6000
-#define __NR_N32_Linux_syscalls		292
+#define __NR_N32_Linux_syscalls		294
 
 #ifdef __KERNEL__
 
diff --git a/arch/mips/kernel/process.c b/arch/mips/kernel/process.c
index ca2e4026ad20..1eaaa450e20c 100644
--- a/arch/mips/kernel/process.c
+++ b/arch/mips/kernel/process.c
@@ -99,7 +99,7 @@ void flush_thread(void)
 {
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 	unsigned long unused, struct task_struct *p, struct pt_regs *regs)
 {
 	struct thread_info *ti = task_thread_info(p);
diff --git a/arch/mips/kernel/scall32-o32.S b/arch/mips/kernel/scall32-o32.S
index 9ab70c3b5be6..0b31b9bda048 100644
--- a/arch/mips/kernel/scall32-o32.S
+++ b/arch/mips/kernel/scall32-o32.S
@@ -650,6 +650,8 @@ einval:	li	v0, -ENOSYS
 	sys	sys_dup3		3
 	sys	sys_pipe2		2
 	sys	sys_inotify_init1	1
+	sys	sys_preadv		6	/* 4330 */
+	sys	sys_pwritev		6
 	.endm
 
 	/* We pre-compute the number of _instruction_ bytes needed to
diff --git a/arch/mips/kernel/scall64-64.S b/arch/mips/kernel/scall64-64.S
index 9b4698667154..c647fd6e722f 100644
--- a/arch/mips/kernel/scall64-64.S
+++ b/arch/mips/kernel/scall64-64.S
@@ -487,4 +487,6 @@ sys_call_table:
 	PTR	sys_dup3
 	PTR	sys_pipe2
 	PTR	sys_inotify_init1
+	PTR	sys_preadv
+	PTR	sys_pwritev			/* 5390 */
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/kernel/scall64-n32.S b/arch/mips/kernel/scall64-n32.S
index f61d6b0e5731..c2c16ef9218f 100644
--- a/arch/mips/kernel/scall64-n32.S
+++ b/arch/mips/kernel/scall64-n32.S
@@ -413,4 +413,6 @@ EXPORT(sysn32_call_table)
 	PTR	sys_dup3			/* 5290 */
 	PTR	sys_pipe2
 	PTR	sys_inotify_init1
+	PTR	sys_preadv
+	PTR	sys_pwritev
 	.size	sysn32_call_table,.-sysn32_call_table
diff --git a/arch/mips/kernel/scall64-o32.S b/arch/mips/kernel/scall64-o32.S
index 60997f1f69d4..002fac27021e 100644
--- a/arch/mips/kernel/scall64-o32.S
+++ b/arch/mips/kernel/scall64-o32.S
@@ -533,4 +533,6 @@ sys_call_table:
 	PTR	sys_dup3
 	PTR	sys_pipe2
 	PTR	sys_inotify_init1
+	PTR	compat_sys_preadv		/* 4330 */
+	PTR	compat_sys_pwritev
 	.size	sys_call_table,.-sys_call_table
diff --git a/arch/mips/sgi-ip27/ip27-smp.c b/arch/mips/sgi-ip27/ip27-smp.c
index 5b47d6b65275..cbcd7eb83bd1 100644
--- a/arch/mips/sgi-ip27/ip27-smp.c
+++ b/arch/mips/sgi-ip27/ip27-smp.c
@@ -221,7 +221,7 @@ static void __init ip27_smp_setup(void)
 	 * Assumption to be fixed: we're always booted on logical / physical
 	 * processor 0.  While we're always running on logical processor 0
 	 * this still means this is physical processor zero; it might for
-	 * example be disabled in the firwware.
+	 * example be disabled in the firmware.
 	 */
 	alloc_cpupda(0, 0);
 }
diff --git a/arch/mn10300/kernel/process.c b/arch/mn10300/kernel/process.c
index b28c9a60445b..234cf344cdce 100644
--- a/arch/mn10300/kernel/process.c
+++ b/arch/mn10300/kernel/process.c
@@ -193,7 +193,7 @@ void prepare_to_copy(struct task_struct *tsk)
  * set up the kernel stack for a new thread and copy arch-specific thread
  * control information
  */
-int copy_thread(int nr, unsigned long clone_flags,
+int copy_thread(unsigned long clone_flags,
 		unsigned long c_usp, unsigned long ustk_size,
 		struct task_struct *p, struct pt_regs *kregs)
 {
diff --git a/arch/parisc/Kconfig b/arch/parisc/Kconfig
index aacf11d33723..9038f39d9d73 100644
--- a/arch/parisc/Kconfig
+++ b/arch/parisc/Kconfig
@@ -9,9 +9,13 @@ config PARISC
 	def_bool y
 	select HAVE_IDE
 	select HAVE_OPROFILE
+	select HAVE_FUNCTION_TRACER if 64BIT
+	select HAVE_FUNCTION_GRAPH_TRACER if 64BIT
+	select HAVE_FUNCTION_TRACE_MCOUNT_TEST if 64BIT
 	select RTC_CLASS
-	select RTC_DRV_PARISC
+	select RTC_DRV_GENERIC
 	select INIT_ALL_POSSIBLE
+	select BUG
 	help
 	  The PA-RISC microprocessor is designed by Hewlett-Packard and used
 	  in many of their workstations & servers (HP9000 700 and 800 series,
@@ -75,6 +79,9 @@ config GENERIC_HARDIRQS
 config GENERIC_IRQ_PROBE
 	def_bool y
 
+config HAVE_LATENCYTOP_SUPPORT
+        def_bool y
+
 config IRQ_PER_CPU
 	bool
 	default y
@@ -83,6 +90,9 @@ config IRQ_PER_CPU
 config PM
 	bool
 
+config STACKTRACE_SUPPORT
+	def_bool y
+
 config ISA_DMA_API
 	bool
 
diff --git a/arch/parisc/Makefile b/arch/parisc/Makefile
index 0d428278356d..da6f66901c92 100644
--- a/arch/parisc/Makefile
+++ b/arch/parisc/Makefile
@@ -56,7 +56,9 @@ cflags-y	+= -mdisable-fpregs
 
 # Without this, "ld -r" results in .text sections that are too big
 # (> 0x40000) for branches to reach stubs.
-cflags-y	+= -ffunction-sections
+ifndef CONFIG_FUNCTION_TRACER
+  cflags-y	+= -ffunction-sections
+endif
 
 # select which processor to optimise for
 cflags-$(CONFIG_PA7100)		+= -march=1.1 -mschedule=7100
diff --git a/arch/parisc/include/asm/atomic.h b/arch/parisc/include/asm/atomic.h
index edbfe25c5fc1..ada3e5364d82 100644
--- a/arch/parisc/include/asm/atomic.h
+++ b/arch/parisc/include/asm/atomic.h
@@ -25,7 +25,7 @@
  * Since "a" is usually an address, use one spinlock per cacheline.
  */
 #  define ATOMIC_HASH_SIZE 4
-#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) a)/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
+#  define ATOMIC_HASH(a) (&(__atomic_hash[ (((unsigned long) (a))/L1_CACHE_BYTES) & (ATOMIC_HASH_SIZE-1) ]))
 
 extern raw_spinlock_t __atomic_hash[ATOMIC_HASH_SIZE] __lock_aligned;
 
@@ -222,13 +222,13 @@ static __inline__ int atomic_add_unless(atomic_t *v, int a, int u)
 
 #define atomic_inc_not_zero(v) atomic_add_unless((v), 1, 0)
 
-#define atomic_add(i,v)	((void)(__atomic_add_return( ((int)i),(v))))
-#define atomic_sub(i,v)	((void)(__atomic_add_return(-((int)i),(v))))
+#define atomic_add(i,v)	((void)(__atomic_add_return( ((int)(i)),(v))))
+#define atomic_sub(i,v)	((void)(__atomic_add_return(-((int)(i)),(v))))
 #define atomic_inc(v)	((void)(__atomic_add_return(   1,(v))))
 #define atomic_dec(v)	((void)(__atomic_add_return(  -1,(v))))
 
-#define atomic_add_return(i,v)	(__atomic_add_return( ((int)i),(v)))
-#define atomic_sub_return(i,v)	(__atomic_add_return(-((int)i),(v)))
+#define atomic_add_return(i,v)	(__atomic_add_return( ((int)(i)),(v)))
+#define atomic_sub_return(i,v)	(__atomic_add_return(-((int)(i)),(v)))
 #define atomic_inc_return(v)	(__atomic_add_return(   1,(v)))
 #define atomic_dec_return(v)	(__atomic_add_return(  -1,(v)))
 
@@ -289,13 +289,13 @@ atomic64_read(const atomic64_t *v)
 	return v->counter;
 }
 
-#define atomic64_add(i,v)	((void)(__atomic64_add_return( ((s64)i),(v))))
-#define atomic64_sub(i,v)	((void)(__atomic64_add_return(-((s64)i),(v))))
+#define atomic64_add(i,v)	((void)(__atomic64_add_return( ((s64)(i)),(v))))
+#define atomic64_sub(i,v)	((void)(__atomic64_add_return(-((s64)(i)),(v))))
 #define atomic64_inc(v)		((void)(__atomic64_add_return(   1,(v))))
 #define atomic64_dec(v)		((void)(__atomic64_add_return(  -1,(v))))
 
-#define atomic64_add_return(i,v)	(__atomic64_add_return( ((s64)i),(v)))
-#define atomic64_sub_return(i,v)	(__atomic64_add_return(-((s64)i),(v)))
+#define atomic64_add_return(i,v)	(__atomic64_add_return( ((s64)(i)),(v)))
+#define atomic64_sub_return(i,v)	(__atomic64_add_return(-((s64)(i)),(v)))
 #define atomic64_inc_return(v)		(__atomic64_add_return(   1,(v)))
 #define atomic64_dec_return(v)		(__atomic64_add_return(  -1,(v)))
 
diff --git a/arch/parisc/include/asm/cacheflush.h b/arch/parisc/include/asm/cacheflush.h
index b7ca6dc7fddc..724395143f26 100644
--- a/arch/parisc/include/asm/cacheflush.h
+++ b/arch/parisc/include/asm/cacheflush.h
@@ -97,6 +97,9 @@ void mark_rodata_ro(void);
 
 #ifdef CONFIG_PA8X00
 /* Only pa8800, pa8900 needs this */
+
+#include <asm/kmap_types.h>
+
 #define ARCH_HAS_KMAP
 
 void kunmap_parisc(void *addr);
diff --git a/arch/parisc/include/asm/elf.h b/arch/parisc/include/asm/elf.h
index 7fa675799e6d..9c802eb4be84 100644
--- a/arch/parisc/include/asm/elf.h
+++ b/arch/parisc/include/asm/elf.h
@@ -168,6 +168,16 @@ typedef struct elf64_fdesc {
 	__u64	gp;
 } Elf64_Fdesc;
 
+#ifdef __KERNEL__
+
+#ifdef CONFIG_64BIT
+#define Elf_Fdesc	Elf64_Fdesc
+#else
+#define Elf_Fdesc	Elf32_Fdesc
+#endif /*CONFIG_64BIT*/
+
+#endif /*__KERNEL__*/
+
 /* Legal values for p_type field of Elf32_Phdr/Elf64_Phdr.  */
 
 #define PT_HP_TLS		(PT_LOOS + 0x0)
diff --git a/arch/parisc/include/asm/ftrace.h b/arch/parisc/include/asm/ftrace.h
index 40a8c178f10d..2fa05dd6aeee 100644
--- a/arch/parisc/include/asm/ftrace.h
+++ b/arch/parisc/include/asm/ftrace.h
@@ -1 +1,25 @@
-/* empty */
+#ifndef _ASM_PARISC_FTRACE_H
+#define _ASM_PARISC_FTRACE_H
+
+#ifndef __ASSEMBLY__
+extern void mcount(void);
+
+/*
+ * Stack of return addresses for functions of a thread.
+ * Used in struct thread_info
+ */
+struct ftrace_ret_stack {
+	unsigned long ret;
+	unsigned long func;
+	unsigned long long calltime;
+};
+
+/*
+ * Primary handler of a function return.
+ * It relays on ftrace_return_to_handler.
+ * Defined in entry.S
+ */
+extern void return_to_handler(void);
+#endif /* __ASSEMBLY__ */
+
+#endif /* _ASM_PARISC_FTRACE_H */
diff --git a/arch/parisc/include/asm/page.h b/arch/parisc/include/asm/page.h
index c3941f09a878..7bc5125d7d4c 100644
--- a/arch/parisc/include/asm/page.h
+++ b/arch/parisc/include/asm/page.h
@@ -36,16 +36,7 @@ void clear_user_page(void *page, unsigned long vaddr, struct page *pg);
  */
 #define STRICT_MM_TYPECHECKS
 #ifdef STRICT_MM_TYPECHECKS
-typedef struct { unsigned long pte;
-#if !defined(CONFIG_64BIT)
-                 unsigned long future_flags;
- /* XXX: it's possible to remove future_flags and change BITS_PER_PTE_ENTRY
-	 to 2, but then strangely the identical 32bit kernel boots on a
-	 c3000(pa20), but not any longer on a 715(pa11).
-	 Still investigating... HelgeD.
-  */
-#endif
-} pte_t; /* either 32 or 64bit */
+typedef struct { unsigned long pte; } pte_t; /* either 32 or 64bit */
 
 /* NOTE: even on 64 bits, these entries are __u32 because we allocate
  * the pmd and pgd in ZONE_DMA (i.e. under 4GB) */
@@ -111,7 +102,7 @@ extern int npmem_ranges;
 #define BITS_PER_PMD_ENTRY	2
 #define BITS_PER_PGD_ENTRY	2
 #else
-#define BITS_PER_PTE_ENTRY	3
+#define BITS_PER_PTE_ENTRY	2
 #define BITS_PER_PMD_ENTRY	2
 #define BITS_PER_PGD_ENTRY	BITS_PER_PMD_ENTRY
 #endif
diff --git a/arch/parisc/include/asm/pdc.h b/arch/parisc/include/asm/pdc.h
index 430f1aeea0b8..4ca510b3c6f8 100644
--- a/arch/parisc/include/asm/pdc.h
+++ b/arch/parisc/include/asm/pdc.h
@@ -49,6 +49,8 @@
 #define PDC_MODEL_CPU_ID	6	/* returns cpu-id (only newer machines!) */
 #define PDC_MODEL_CAPABILITIES	7	/* returns OS32/OS64-flags	*/
 /* Values for PDC_MODEL_CAPABILITIES non-equivalent virtual aliasing support */
+#define  PDC_MODEL_OS64			(1 << 0)
+#define  PDC_MODEL_OS32			(1 << 1)
 #define  PDC_MODEL_IOPDIR_FDC		(1 << 2)
 #define  PDC_MODEL_NVA_MASK		(3 << 4)
 #define  PDC_MODEL_NVA_SUPPORTED	(0 << 4)
@@ -341,6 +343,8 @@
 
 #ifdef __KERNEL__
 
+#include <asm/page.h> /* for __PAGE_OFFSET */
+
 extern int pdc_type;
 
 /* Values for pdc_type */
diff --git a/arch/parisc/include/asm/pgtable.h b/arch/parisc/include/asm/pgtable.h
index 470a4b88124d..a27d2e200fb2 100644
--- a/arch/parisc/include/asm/pgtable.h
+++ b/arch/parisc/include/asm/pgtable.h
@@ -50,11 +50,7 @@
 	printk("%s:%d: bad pgd %08lx.\n", __FILE__, __LINE__, (unsigned long)pgd_val(e))
 
 /* This is the size of the initially mapped kernel memory */
-#ifdef CONFIG_64BIT
 #define KERNEL_INITIAL_ORDER	24	/* 0 to 1<<24 = 16MB */
-#else
-#define KERNEL_INITIAL_ORDER	23	/* 0 to 1<<23 = 8MB */
-#endif
 #define KERNEL_INITIAL_SIZE	(1 << KERNEL_INITIAL_ORDER)
 
 #if defined(CONFIG_64BIT) && defined(CONFIG_PARISC_PAGE_SIZE_4KB)
@@ -91,16 +87,25 @@
 
 /* Definitions for 1st level */
 #define PGDIR_SHIFT	(PMD_SHIFT + BITS_PER_PMD)
+#if (PGDIR_SHIFT + PAGE_SHIFT + PGD_ORDER - BITS_PER_PGD_ENTRY) > BITS_PER_LONG
+#define BITS_PER_PGD	(BITS_PER_LONG - PGDIR_SHIFT)
+#else
 #define BITS_PER_PGD	(PAGE_SHIFT + PGD_ORDER - BITS_PER_PGD_ENTRY)
+#endif
 #define PGDIR_SIZE	(1UL << PGDIR_SHIFT)
 #define PGDIR_MASK	(~(PGDIR_SIZE-1))
 #define PTRS_PER_PGD    (1UL << BITS_PER_PGD)
 #define USER_PTRS_PER_PGD       PTRS_PER_PGD
 
+#ifdef CONFIG_64BIT
 #define MAX_ADDRBITS	(PGDIR_SHIFT + BITS_PER_PGD)
 #define MAX_ADDRESS	(1UL << MAX_ADDRBITS)
-
 #define SPACEID_SHIFT	(MAX_ADDRBITS - 32)
+#else
+#define MAX_ADDRBITS	(BITS_PER_LONG)
+#define MAX_ADDRESS	(1UL << MAX_ADDRBITS)
+#define SPACEID_SHIFT	0
+#endif
 
 /* This calculates the number of initial pages we need for the initial
  * page tables */
diff --git a/arch/parisc/include/asm/smp.h b/arch/parisc/include/asm/smp.h
index 6ef4b7867b1b..21eb45a52629 100644
--- a/arch/parisc/include/asm/smp.h
+++ b/arch/parisc/include/asm/smp.h
@@ -29,7 +29,8 @@ extern void smp_send_reschedule(int cpu);
 extern void smp_send_all_nop(void);
 
 extern void arch_send_call_function_single_ipi(int cpu);
-extern void arch_send_call_function_ipi(cpumask_t mask);
+extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
+#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
 
 #endif /* !ASSEMBLY */
 
diff --git a/arch/parisc/include/asm/spinlock.h b/arch/parisc/include/asm/spinlock.h
index f3d2090a18dc..fae03e136fa8 100644
--- a/arch/parisc/include/asm/spinlock.h
+++ b/arch/parisc/include/asm/spinlock.h
@@ -187,6 +187,9 @@ static __inline__ int __raw_write_can_lock(raw_rwlock_t *rw)
 	return !rw->counter;
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
diff --git a/arch/parisc/kernel/Makefile b/arch/parisc/kernel/Makefile
index 016d3fc4111c..67db0722e6ca 100644
--- a/arch/parisc/kernel/Makefile
+++ b/arch/parisc/kernel/Makefile
@@ -11,10 +11,25 @@ obj-y	     	:= cache.o pacache.o setup.o traps.o time.o irq.o \
 		   process.o processor.o pdc_cons.o pdc_chassis.o unwind.o \
 		   topology.o
 
+ifdef CONFIG_FUNCTION_TRACER
+# Do not profile debug and lowlevel utilities
+CFLAGS_REMOVE_ftrace.o = -pg
+CFLAGS_REMOVE_cache.o = -pg
+CFLAGS_REMOVE_irq.o = -pg
+CFLAGS_REMOVE_pacache.o = -pg
+CFLAGS_REMOVE_perf.o = -pg
+CFLAGS_REMOVE_traps.o = -pg
+CFLAGS_REMOVE_unaligned.o = -pg
+CFLAGS_REMOVE_unwind.o = -pg
+endif
+
 obj-$(CONFIG_SMP)	+= smp.o
 obj-$(CONFIG_PA11)	+= pci-dma.o
 obj-$(CONFIG_PCI)	+= pci.o
 obj-$(CONFIG_MODULES)	+= module.o
 obj-$(CONFIG_64BIT)	+= binfmt_elf32.o sys_parisc32.o signal32.o
+obj-$(CONFIG_STACKTRACE)+= stacktrace.o
 # only supported for PCX-W/U in 64-bit mode at the moment
 obj-$(CONFIG_64BIT)	+= perf.o perf_asm.o
+obj-$(CONFIG_FUNCTION_TRACER)		+= ftrace.o
+obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o
diff --git a/arch/parisc/kernel/entry.S b/arch/parisc/kernel/entry.S
index 0db9fdcb7709..ae3e70cd1e14 100644
--- a/arch/parisc/kernel/entry.S
+++ b/arch/parisc/kernel/entry.S
@@ -505,6 +505,18 @@
 	STREG		\pte,0(\ptep)
 	.endm
 
+	/* bitshift difference between a PFN (based on kernel's PAGE_SIZE)
+	 * to a CPU TLB 4k PFN (4k => 12 bits to shift) */
+	#define PAGE_ADD_SHIFT  (PAGE_SHIFT-12)
+
+	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
+	.macro		convert_for_tlb_insert20 pte
+	extrd,u		\pte,(63-ASM_PFN_PTE_SHIFT)+(63-58)+PAGE_ADD_SHIFT,\
+				64-PAGE_SHIFT-PAGE_ADD_SHIFT,\pte
+	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,\
+				(63-58)+PAGE_ADD_SHIFT,\pte
+	.endm
+
 	/* Convert the pte and prot to tlb insertion values.  How
 	 * this happens is quite subtle, read below */
 	.macro		make_insert_tlb	spc,pte,prot
@@ -544,8 +556,7 @@
 	depi		1,12,1,\prot
 
 	/* Drop prot bits and convert to page addr for iitlbt and idtlbt */
-	extrd,u		\pte,(63-ASM_PFN_PTE_SHIFT)+(63-58),64-PAGE_SHIFT,\pte
-	depdi		_PAGE_SIZE_ENCODING_DEFAULT,63,63-58,\pte
+	convert_for_tlb_insert20 \pte
 	.endm
 
 	/* Identical macro to make_insert_tlb above, except it
@@ -563,8 +574,8 @@
 
 	/* Get rid of prot bits and convert to page addr for iitlba */
 
-	depi		_PAGE_SIZE_ENCODING_DEFAULT,31,ASM_PFN_PTE_SHIFT,\pte
-	extru		\pte,24,25,\pte
+	depi		0,31,ASM_PFN_PTE_SHIFT,\pte
+	SHRREG		\pte,(ASM_PFN_PTE_SHIFT-(31-26)),\pte
 	.endm
 
 	/* This is for ILP32 PA2.0 only.  The TLB insertion needs
@@ -1244,10 +1255,9 @@ nadtlb_check_flush_20w:
 	depdi,z         7,7,3,prot
 	depdi           1,10,1,prot
 
-	/* Get rid of prot bits and convert to page addr for idtlbt */
+	/* Drop prot bits from pte and convert to page addr for idtlbt */
+	convert_for_tlb_insert20 pte
 
-	depdi		0,63,12,pte
-	extrd,u         pte,56,52,pte
 	idtlbt          pte,prot
 
 	rfir
@@ -1337,8 +1347,8 @@ nadtlb_check_flush_11:
 
 	/* Get rid of prot bits and convert to page addr for idtlba */
 
-	depi		0,31,12,pte
-	extru		pte,24,25,pte
+	depi		0,31,ASM_PFN_PTE_SHIFT,pte
+	SHRREG		pte,(ASM_PFN_PTE_SHIFT-(31-26)),pte
 
 	mfsp		%sr1,t0  /* Save sr1 so we can use it in tlb inserts */
 	mtsp		spc,%sr1
@@ -1403,10 +1413,9 @@ nadtlb_check_flush_20:
 	depdi,z         7,7,3,prot
 	depdi           1,10,1,prot
 
-	/* Get rid of prot bits and convert to page addr for idtlbt */
+	/* Drop prot bits from pte and convert to page addr for idtlbt */
+	convert_for_tlb_insert20 pte
 
-	depdi		0,63,12,pte
-	extrd,u         pte,56,32,pte
 	idtlbt          pte,prot
 
 	rfir
@@ -2176,6 +2185,33 @@ syscall_do_resched:
 ENDPROC(syscall_exit)
 
 
+#ifdef CONFIG_FUNCTION_TRACER
+	.import ftrace_function_trampoline,code
+ENTRY(_mcount)
+	copy	%r3, %arg2
+	b	ftrace_function_trampoline
+	nop
+ENDPROC(_mcount)
+
+ENTRY(return_to_handler)
+	load32	return_trampoline, %rp
+	copy	%ret0, %arg0
+	copy	%ret1, %arg1
+	b	ftrace_return_to_handler
+	nop
+return_trampoline:
+	copy	%ret0, %rp
+	copy	%r23, %ret0
+	copy	%r24, %ret1
+
+.globl ftrace_stub
+ftrace_stub:
+	bv	%r0(%rp)
+	nop
+ENDPROC(return_to_handler)
+#endif	/* CONFIG_FUNCTION_TRACER */
+
+
 get_register:
 	/*
 	 * get_register is used by the non access tlb miss handlers to
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index f6d241238a78..4c247e02d9b1 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -527,7 +527,11 @@ int pdc_model_capabilities(unsigned long *capabilities)
         pdc_result[0] = 0; /* preset zero (call may not be implemented!) */
         retval = mem_pdc_call(PDC_MODEL, PDC_MODEL_CAPABILITIES, __pa(pdc_result), 0);
         convert_to_wide(pdc_result);
-        *capabilities = pdc_result[0];
+        if (retval == PDC_OK) {
+                *capabilities = pdc_result[0];
+        } else {
+                *capabilities = PDC_MODEL_OS32;
+        }
         spin_unlock_irqrestore(&pdc_lock, flags);
 
         return retval;
diff --git a/arch/parisc/kernel/ftrace.c b/arch/parisc/kernel/ftrace.c
new file mode 100644
index 000000000000..9877372ffdba
--- /dev/null
+++ b/arch/parisc/kernel/ftrace.c
@@ -0,0 +1,185 @@
+/*
+ * Code for tracing calls in Linux kernel.
+ * Copyright (C) 2009 Helge Deller <deller@gmx.de>
+ *
+ * based on code for x86 which is:
+ * Copyright (C) 2007-2008 Steven Rostedt <srostedt@redhat.com>
+ *
+ * future possible enhancements:
+ * 	- add CONFIG_DYNAMIC_FTRACE
+ *	- add CONFIG_STACK_TRACER
+ */
+
+#include <linux/init.h>
+#include <linux/ftrace.h>
+
+#include <asm/sections.h>
+#include <asm/ftrace.h>
+
+
+
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+
+/* Add a function return address to the trace stack on thread info.*/
+static int push_return_trace(unsigned long ret, unsigned long long time,
+				unsigned long func, int *depth)
+{
+	int index;
+
+	if (!current->ret_stack)
+		return -EBUSY;
+
+	/* The return trace stack is full */
+	if (current->curr_ret_stack == FTRACE_RETFUNC_DEPTH - 1) {
+		atomic_inc(&current->trace_overrun);
+		return -EBUSY;
+	}
+
+	index = ++current->curr_ret_stack;
+	barrier();
+	current->ret_stack[index].ret = ret;
+	current->ret_stack[index].func = func;
+	current->ret_stack[index].calltime = time;
+	*depth = index;
+
+	return 0;
+}
+
+/* Retrieve a function return address to the trace stack on thread info.*/
+static void pop_return_trace(struct ftrace_graph_ret *trace, unsigned long *ret)
+{
+	int index;
+
+	index = current->curr_ret_stack;
+
+	if (unlikely(index < 0)) {
+		ftrace_graph_stop();
+		WARN_ON(1);
+		/* Might as well panic, otherwise we have no where to go */
+		*ret = (unsigned long)
+			dereference_function_descriptor(&panic);
+		return;
+	}
+
+	*ret = current->ret_stack[index].ret;
+	trace->func = current->ret_stack[index].func;
+	trace->calltime = current->ret_stack[index].calltime;
+	trace->overrun = atomic_read(&current->trace_overrun);
+	trace->depth = index;
+	barrier();
+	current->curr_ret_stack--;
+
+}
+
+/*
+ * Send the trace to the ring-buffer.
+ * @return the original return address.
+ */
+unsigned long ftrace_return_to_handler(unsigned long retval0,
+				       unsigned long retval1)
+{
+	struct ftrace_graph_ret trace;
+	unsigned long ret;
+
+	pop_return_trace(&trace, &ret);
+	trace.rettime = cpu_clock(raw_smp_processor_id());
+	ftrace_graph_return(&trace);
+
+	if (unlikely(!ret)) {
+		ftrace_graph_stop();
+		WARN_ON(1);
+		/* Might as well panic. What else to do? */
+		ret = (unsigned long)
+			dereference_function_descriptor(&panic);
+	}
+
+	/* HACK: we hand over the old functions' return values
+	   in %r23 and %r24. Assembly in entry.S will take care
+	   and move those to their final registers %ret0 and %ret1 */
+	asm( "copy %0, %%r23 \n\t"
+	     "copy %1, %%r24 \n" : : "r" (retval0), "r" (retval1) );
+
+	return ret;
+}
+
+/*
+ * Hook the return address and push it in the stack of return addrs
+ * in current thread info.
+ */
+void prepare_ftrace_return(unsigned long *parent, unsigned long self_addr)
+{
+	unsigned long old;
+	unsigned long long calltime;
+	struct ftrace_graph_ent trace;
+
+	if (unlikely(atomic_read(&current->tracing_graph_pause)))
+		return;
+
+	old = *parent;
+	*parent = (unsigned long)
+		  dereference_function_descriptor(&return_to_handler);
+
+	if (unlikely(!__kernel_text_address(old))) {
+		ftrace_graph_stop();
+		*parent = old;
+		WARN_ON(1);
+		return;
+	}
+
+	calltime = cpu_clock(raw_smp_processor_id());
+
+	if (push_return_trace(old, calltime,
+				self_addr, &trace.depth) == -EBUSY) {
+		*parent = old;
+		return;
+	}
+
+	trace.func = self_addr;
+
+	/* Only trace if the calling function expects to */
+	if (!ftrace_graph_entry(&trace)) {
+		current->curr_ret_stack--;
+		*parent = old;
+	}
+}
+
+#endif /* CONFIG_FUNCTION_GRAPH_TRACER */
+
+
+void ftrace_function_trampoline(unsigned long parent,
+				unsigned long self_addr,
+				unsigned long org_sp_gr3)
+{
+	extern ftrace_func_t ftrace_trace_function;
+
+	if (function_trace_stop)
+		return;
+
+	if (ftrace_trace_function != ftrace_stub) {
+		ftrace_trace_function(parent, self_addr);
+		return;
+	}
+#ifdef CONFIG_FUNCTION_GRAPH_TRACER
+	if (ftrace_graph_entry && ftrace_graph_return) {
+		unsigned long sp;
+		unsigned long *parent_rp;
+
+                asm volatile ("copy %%r30, %0" : "=r"(sp));
+		/* sanity check: is stack pointer which we got from
+		   assembler function in entry.S in a reasonable
+		   range compared to current stack pointer? */
+		if ((sp - org_sp_gr3) > 0x400)
+			return;
+
+		/* calculate pointer to %rp in stack */
+		parent_rp = (unsigned long *) org_sp_gr3 - 0x10;
+		/* sanity check: parent_rp should hold parent */
+		if (*parent_rp != parent)
+			return;
+		
+		prepare_ftrace_return(parent_rp, self_addr);
+		return;
+	}
+#endif
+}
+
diff --git a/arch/parisc/kernel/irq.c b/arch/parisc/kernel/irq.c
index 1c740f5cbd63..4ea4229d765c 100644
--- a/arch/parisc/kernel/irq.c
+++ b/arch/parisc/kernel/irq.c
@@ -311,12 +311,12 @@ unsigned long txn_alloc_addr(unsigned int virt_irq)
 	next_cpu++; /* assign to "next" CPU we want this bugger on */
 
 	/* validate entry */
-	while ((next_cpu < NR_CPUS) &&
+	while ((next_cpu < nr_cpu_ids) &&
 		(!per_cpu(cpu_data, next_cpu).txn_addr ||
 		 !cpu_online(next_cpu)))
 		next_cpu++;
 
-	if (next_cpu >= NR_CPUS) 
+	if (next_cpu >= nr_cpu_ids) 
 		next_cpu = 0;	/* nothing else, assign monarch */
 
 	return txn_affinity_addr(virt_irq, next_cpu);
diff --git a/arch/parisc/kernel/module.c b/arch/parisc/kernel/module.c
index 9013243cecca..ecd1c5024447 100644
--- a/arch/parisc/kernel/module.c
+++ b/arch/parisc/kernel/module.c
@@ -61,9 +61,7 @@
 #include <linux/string.h>
 #include <linux/kernel.h>
 #include <linux/bug.h>
-#include <linux/uaccess.h>
 
-#include <asm/sections.h>
 #include <asm/unwind.h>
 
 #if 0
@@ -115,8 +113,6 @@ struct got_entry {
 	Elf32_Addr addr;
 };
 
-#define Elf_Fdesc	Elf32_Fdesc
-
 struct stub_entry {
 	Elf32_Word insns[2]; /* each stub entry has two insns */
 };
@@ -125,8 +121,6 @@ struct got_entry {
 	Elf64_Addr addr;
 };
 
-#define Elf_Fdesc	Elf64_Fdesc
-
 struct stub_entry {
 	Elf64_Word insns[4]; /* each stub entry has four insns */
 };
@@ -916,15 +910,3 @@ void module_arch_cleanup(struct module *mod)
 	deregister_unwind_table(mod);
 	module_bug_cleanup(mod);
 }
-
-#ifdef CONFIG_64BIT
-void *dereference_function_descriptor(void *ptr)
-{
-	Elf64_Fdesc *desc = ptr;
-	void *p;
-
-	if (!probe_kernel_address(&desc->addr, p))
-		ptr = p;
-	return ptr;
-}
-#endif
diff --git a/arch/parisc/kernel/parisc_ksyms.c b/arch/parisc/kernel/parisc_ksyms.c
index 0eecfbbc59cd..df653663d3db 100644
--- a/arch/parisc/kernel/parisc_ksyms.c
+++ b/arch/parisc/kernel/parisc_ksyms.c
@@ -153,5 +153,10 @@ EXPORT_SYMBOL(node_data);
 EXPORT_SYMBOL(pfnnid_map);
 #endif
 
+#ifdef CONFIG_FUNCTION_TRACER
+extern void _mcount(void);
+EXPORT_SYMBOL(_mcount);
+#endif
+
 /* from pacache.S -- needed for copy_page */
 EXPORT_SYMBOL(copy_user_page_asm);
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index b80e02a4d81d..6f69101f90bb 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -46,14 +46,15 @@
 #include <linux/stddef.h>
 #include <linux/unistd.h>
 #include <linux/kallsyms.h>
+#include <linux/uaccess.h>
 
 #include <asm/io.h>
 #include <asm/asm-offsets.h>
 #include <asm/pdc.h>
 #include <asm/pdc_chassis.h>
 #include <asm/pgalloc.h>
-#include <asm/uaccess.h>
 #include <asm/unwind.h>
+#include <asm/sections.h>
 
 /*
  * The idle thread. There's no useful work to be
@@ -231,8 +232,8 @@ sys_clone(unsigned long clone_flags, unsigned long usp,
 	   
 	   However, these last 3 args are only examined
 	   if the proper flags are set. */
-	int __user *child_tidptr;
-	int __user *parent_tidptr;
+	int __user *parent_tidptr = (int __user *)regs->gr[24];
+	int __user *child_tidptr  = (int __user *)regs->gr[22];
 
 	/* usp must be word aligned.  This also prevents users from
 	 * passing in the value 1 (which is the signal for a special
@@ -243,16 +244,6 @@ sys_clone(unsigned long clone_flags, unsigned long usp,
 	if (usp == 0)
 	  usp = regs->gr[30];
 
-	if (clone_flags & CLONE_PARENT_SETTID)
-	  parent_tidptr = (int __user *)regs->gr[24];
-	else
-	  parent_tidptr = NULL;
-	
-	if (clone_flags & (CLONE_CHILD_SETTID | CLONE_CHILD_CLEARTID))
-	  child_tidptr = (int __user *)regs->gr[22];
-	else
-	  child_tidptr = NULL;
-
 	return do_fork(clone_flags, usp, regs, 0, parent_tidptr, child_tidptr);
 }
 
@@ -263,7 +254,7 @@ sys_vfork(struct pt_regs *regs)
 }
 
 int
-copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+copy_thread(unsigned long clone_flags, unsigned long usp,
 	    unsigned long unused,	/* in ia64 this is "user_stack_size" */
 	    struct task_struct * p, struct pt_regs * pregs)
 {
@@ -400,3 +391,15 @@ get_wchan(struct task_struct *p)
 	} while (count++ < 16);
 	return 0;
 }
+
+#ifdef CONFIG_64BIT
+void *dereference_function_descriptor(void *ptr)
+{
+	Elf64_Fdesc *desc = ptr;
+	void *p;
+
+	if (!probe_kernel_address(&desc->addr, p))
+		ptr = p;
+	return ptr;
+}
+#endif
diff --git a/arch/parisc/kernel/processor.c b/arch/parisc/kernel/processor.c
index ecb609342feb..e09d0f7fb6b0 100644
--- a/arch/parisc/kernel/processor.c
+++ b/arch/parisc/kernel/processor.c
@@ -100,8 +100,8 @@ static int __cpuinit processor_probe(struct parisc_device *dev)
 	struct cpuinfo_parisc *p;
 
 #ifdef CONFIG_SMP
-	if (num_online_cpus() >= NR_CPUS) {
-		printk(KERN_INFO "num_online_cpus() >= NR_CPUS\n");
+	if (num_online_cpus() >= nr_cpu_ids) {
+		printk(KERN_INFO "num_online_cpus() >= nr_cpu_ids\n");
 		return 1;
 	}
 #else
@@ -214,7 +214,7 @@ static int __cpuinit processor_probe(struct parisc_device *dev)
 	 */
 #ifdef CONFIG_SMP
 	if (cpuid) {
-		cpu_set(cpuid, cpu_present_map);
+		set_cpu_present(cpuid, true);
 		cpu_up(cpuid);
 	}
 #endif
@@ -364,6 +364,13 @@ show_cpuinfo (struct seq_file *m, void *v)
 				 boot_cpu_data.cpu_hz / 1000000,
 				 boot_cpu_data.cpu_hz % 1000000  );
 
+		seq_printf(m, "capabilities\t:");
+		if (boot_cpu_data.pdc.capabilities & PDC_MODEL_OS32)
+			seq_printf(m, " os32");
+		if (boot_cpu_data.pdc.capabilities & PDC_MODEL_OS64)
+			seq_printf(m, " os64");
+		seq_printf(m, "\n");
+
 		seq_printf(m, "model\t\t: %s\n"
 				"model name\t: %s\n",
 				 boot_cpu_data.pdc.sys_model_name,
diff --git a/arch/parisc/kernel/smp.c b/arch/parisc/kernel/smp.c
index 9995d7ed5819..1fd0f0cec037 100644
--- a/arch/parisc/kernel/smp.c
+++ b/arch/parisc/kernel/smp.c
@@ -31,6 +31,7 @@
 #include <linux/err.h>
 #include <linux/delay.h>
 #include <linux/bitops.h>
+#include <linux/ftrace.h>
 
 #include <asm/system.h>
 #include <asm/atomic.h>
@@ -113,14 +114,14 @@ halt_processor(void)
 {
 	/* REVISIT : redirect I/O Interrupts to another CPU? */
 	/* REVISIT : does PM *know* this CPU isn't available? */
-	cpu_clear(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), false);
 	local_irq_disable();
 	for (;;)
 		;
 }
 
 
-irqreturn_t
+irqreturn_t __irq_entry
 ipi_interrupt(int irq, void *dev_id) 
 {
 	int this_cpu = smp_processor_id();
@@ -214,11 +215,11 @@ ipi_send(int cpu, enum ipi_message_type op)
 }
 
 static void
-send_IPI_mask(cpumask_t mask, enum ipi_message_type op)
+send_IPI_mask(const struct cpumask *mask, enum ipi_message_type op)
 {
 	int cpu;
 
-	for_each_cpu_mask(cpu, mask)
+	for_each_cpu(cpu, mask)
 		ipi_send(cpu, op);
 }
 
@@ -257,7 +258,7 @@ smp_send_all_nop(void)
 	send_IPI_allbutself(IPI_NOP);
 }
 
-void arch_send_call_function_ipi(cpumask_t mask)
+void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
 	send_IPI_mask(mask, IPI_CALL_FUNC);
 }
@@ -296,13 +297,14 @@ smp_cpu_init(int cpunum)
 	mb();
 
 	/* Well, support 2.4 linux scheme as well. */
-	if (cpu_test_and_set(cpunum, cpu_online_map))
+	if (cpu_isset(cpunum, cpu_online_map))
 	{
 		extern void machine_halt(void); /* arch/parisc.../process.c */
 
 		printk(KERN_CRIT "CPU#%d already initialized!\n", cpunum);
 		machine_halt();
 	}  
+	set_cpu_online(cpunum, true);
 
 	/* Initialise the idle task for this CPU */
 	atomic_inc(&init_mm.mm_count);
@@ -424,8 +426,8 @@ void __init smp_prepare_boot_cpu(void)
 	/* Setup BSP mappings */
 	printk(KERN_INFO "SMP: bootstrap CPU ID is %d\n", bootstrap_processor);
 
-	cpu_set(bootstrap_processor, cpu_online_map);
-	cpu_set(bootstrap_processor, cpu_present_map);
+	set_cpu_online(bootstrap_processor, true);
+	set_cpu_present(bootstrap_processor, true);
 }
 
 
@@ -436,8 +438,7 @@ void __init smp_prepare_boot_cpu(void)
 */
 void __init smp_prepare_cpus(unsigned int max_cpus)
 {
-	cpus_clear(cpu_present_map);
-	cpu_set(0, cpu_present_map);
+	init_cpu_present(cpumask_of(0));
 
 	parisc_max_cpus = max_cpus;
 	if (!max_cpus)
diff --git a/arch/parisc/kernel/stacktrace.c b/arch/parisc/kernel/stacktrace.c
new file mode 100644
index 000000000000..2fe914c5f533
--- /dev/null
+++ b/arch/parisc/kernel/stacktrace.c
@@ -0,0 +1,63 @@
+/*
+ * Stack trace management functions
+ *
+ *  Copyright (C) 2009 Helge Deller <deller@gmx.de>
+ *  based on arch/x86/kernel/stacktrace.c by Ingo Molnar <mingo@redhat.com>
+ *  and parisc unwind functions by Randolph Chung <tausq@debian.org>
+ *
+ *  TODO: Userspace stacktrace (CONFIG_USER_STACKTRACE_SUPPORT)
+ */
+#include <linux/module.h>
+#include <linux/stacktrace.h>
+
+#include <asm/unwind.h>
+
+static void dump_trace(struct task_struct *task, struct stack_trace *trace)
+{
+	struct unwind_frame_info info;
+
+	/* initialize unwind info */
+	if (task == current) {
+		unsigned long sp;
+		struct pt_regs r;
+HERE:
+		asm volatile ("copy %%r30, %0" : "=r"(sp));
+		memset(&r, 0, sizeof(struct pt_regs));
+		r.iaoq[0] = (unsigned long)&&HERE;
+		r.gr[2] = (unsigned long)__builtin_return_address(0);
+		r.gr[30] = sp;
+		unwind_frame_init(&info, task, &r);
+	} else {
+		unwind_frame_init_from_blocked_task(&info, task);
+	}
+
+	/* unwind stack and save entries in stack_trace struct */
+	trace->nr_entries = 0;
+	while (trace->nr_entries < trace->max_entries) {
+		if (unwind_once(&info) < 0 || info.ip == 0)
+			break;
+
+		if (__kernel_text_address(info.ip))
+			trace->entries[trace->nr_entries++] = info.ip;
+	}
+}
+
+
+/*
+ * Save stack-backtrace addresses into a stack_trace buffer.
+ */
+void save_stack_trace(struct stack_trace *trace)
+{
+	dump_trace(current, trace);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+EXPORT_SYMBOL_GPL(save_stack_trace);
+
+void save_stack_trace_tsk(struct task_struct *tsk, struct stack_trace *trace)
+{
+	dump_trace(tsk, trace);
+	if (trace->nr_entries < trace->max_entries)
+		trace->entries[trace->nr_entries++] = ULONG_MAX;
+}
+EXPORT_SYMBOL_GPL(save_stack_trace_tsk);
diff --git a/arch/parisc/kernel/syscall.S b/arch/parisc/kernel/syscall.S
index 69b6eebc466e..59fc1a43ec3e 100644
--- a/arch/parisc/kernel/syscall.S
+++ b/arch/parisc/kernel/syscall.S
@@ -365,17 +365,51 @@ tracesys_sigexit:
 
 
 	/*********************************************************
-		Light-weight-syscall code
+		32/64-bit Light-Weight-Syscall ABI
 
-		r20 - lws number
-		r26,r25,r24,r23,r22 - Input registers
-		r28 - Function return register
-		r21 - Error code.
+		* - Indicates a hint for userspace inline asm
+		implementations.
 
-		Scracth: Any of the above that aren't being
-		currently used, including r1. 
+		Syscall number (caller-saves)
+	        - %r20
+	        * In asm clobber.
 
-		Return pointer: r31 (Not usable)
+		Argument registers (caller-saves)
+	        - %r26, %r25, %r24, %r23, %r22
+	        * In asm input.
+
+		Return registers (caller-saves)
+	        - %r28 (return), %r21 (errno)
+	        * In asm output.
+
+		Caller-saves registers
+	        - %r1, %r27, %r29
+	        - %r2 (return pointer)
+	        - %r31 (ble link register)
+	        * In asm clobber.
+
+		Callee-saves registers
+	        - %r3-%r18
+	        - %r30 (stack pointer)
+	        * Not in asm clobber.
+
+		If userspace is 32-bit:
+		Callee-saves registers
+	        - %r19 (32-bit PIC register)
+
+		Differences from 32-bit calling convention:
+		- Syscall number in %r20
+		- Additional argument register %r22 (arg4)
+		- Callee-saves %r19.
+
+		If userspace is 64-bit:
+		Callee-saves registers
+		- %r27 (64-bit PIC register)
+
+		Differences from 64-bit calling convention:
+		- Syscall number in %r20
+		- Additional argument register %r22 (arg4)
+		- Callee-saves %r27.
 
 		Error codes returned by entry path:
 
@@ -473,7 +507,8 @@ lws_compare_and_swap64:
 	b,n	lws_compare_and_swap
 #else
 	/* If we are not a 64-bit kernel, then we don't
-	 * implement having 64-bit input registers
+	 * have 64-bit input registers, and calling
+	 * the 64-bit LWS CAS returns ENOSYS.
 	 */
 	b,n	lws_exit_nosys
 #endif
@@ -635,12 +670,15 @@ END(sys_call_table64)
 	/*
 		All light-weight-syscall atomic operations 
 		will use this set of locks 
+
+		NOTE: The lws_lock_start symbol must be
+		at least 16-byte aligned for safe use
+		with ldcw.
 	*/
 	.section .data
 	.align	PAGE_SIZE
 ENTRY(lws_lock_start)
 	/* lws locks */
-	.align 16
 	.rept 16
 	/* Keep locks aligned at 16-bytes */
 	.word 1
diff --git a/arch/parisc/kernel/time.c b/arch/parisc/kernel/time.c
index e75cae6072c5..d4dd05674c62 100644
--- a/arch/parisc/kernel/time.c
+++ b/arch/parisc/kernel/time.c
@@ -24,6 +24,7 @@
 #include <linux/profile.h>
 #include <linux/clocksource.h>
 #include <linux/platform_device.h>
+#include <linux/ftrace.h>
 
 #include <asm/uaccess.h>
 #include <asm/io.h>
@@ -53,7 +54,7 @@ static unsigned long clocktick __read_mostly;	/* timer cycles per tick */
  * held off for an arbitrarily long period of time by interrupts being
  * disabled, so we may miss one or more ticks.
  */
-irqreturn_t timer_interrupt(int irq, void *dev_id)
+irqreturn_t __irq_entry timer_interrupt(int irq, void *dev_id)
 {
 	unsigned long now;
 	unsigned long next_tick;
@@ -216,14 +217,14 @@ void __init start_cpu_itimer(void)
 	per_cpu(cpu_data, cpu).it_value = next_tick;
 }
 
-static struct platform_device rtc_parisc_dev = {
-	.name = "rtc-parisc",
+static struct platform_device rtc_generic_dev = {
+	.name = "rtc-generic",
 	.id = -1,
 };
 
 static int __init rtc_init(void)
 {
-	if (platform_device_register(&rtc_parisc_dev) < 0)
+	if (platform_device_register(&rtc_generic_dev) < 0)
 		printk(KERN_ERR "unable to register rtc device...\n");
 
 	/* not necessarily an error */
diff --git a/arch/parisc/kernel/traps.c b/arch/parisc/kernel/traps.c
index ba658d2086f7..c32f5d6d778e 100644
--- a/arch/parisc/kernel/traps.c
+++ b/arch/parisc/kernel/traps.c
@@ -247,6 +247,8 @@ void die_if_kernel(char *str, struct pt_regs *regs, long err)
 
 	oops_in_progress = 1;
 
+	oops_enter();
+
 	/* Amuse the user in a SPARC fashion */
 	if (err) printk(
 KERN_CRIT "      _______________________________ \n"
@@ -293,6 +295,7 @@ KERN_CRIT "                     ||     ||\n");
 		panic("Fatal exception");
 	}
 
+	oops_exit();
 	do_exit(SIGSEGV);
 }
 
@@ -494,7 +497,7 @@ void parisc_terminate(char *msg, struct pt_regs *regs, int code, unsigned long o
 	panic(msg);
 }
 
-void handle_interruption(int code, struct pt_regs *regs)
+void notrace handle_interruption(int code, struct pt_regs *regs)
 {
 	unsigned long fault_address = 0;
 	unsigned long fault_space = 0;
diff --git a/arch/parisc/kernel/vmlinux.lds.S b/arch/parisc/kernel/vmlinux.lds.S
index 1a3b6ccd3620..fd2cc4fd2b65 100644
--- a/arch/parisc/kernel/vmlinux.lds.S
+++ b/arch/parisc/kernel/vmlinux.lds.S
@@ -54,6 +54,8 @@ SECTIONS
 		TEXT_TEXT
 		SCHED_TEXT
 		LOCK_TEXT
+		KPROBES_TEXT
+		IRQENTRY_TEXT
 		*(.text.do_softirq)
 		*(.text.sys_exit)
 		*(.text.do_sigaltstack)
diff --git a/arch/parisc/mm/init.c b/arch/parisc/mm/init.c
index 9d704d9831d1..4356ceb1e366 100644
--- a/arch/parisc/mm/init.c
+++ b/arch/parisc/mm/init.c
@@ -456,6 +456,13 @@ void __init mem_init(void)
 {
 	int codesize, reservedpages, datasize, initsize;
 
+	/* Do sanity checks on page table constants */
+	BUILD_BUG_ON(PTE_ENTRY_SIZE != sizeof(pte_t));
+	BUILD_BUG_ON(PMD_ENTRY_SIZE != sizeof(pmd_t));
+	BUILD_BUG_ON(PGD_ENTRY_SIZE != sizeof(pgd_t));
+	BUILD_BUG_ON(PAGE_SHIFT + BITS_PER_PTE + BITS_PER_PMD + BITS_PER_PGD
+			> BITS_PER_LONG);
+
 	high_memory = __va((max_pfn << PAGE_SHIFT));
 
 #ifndef CONFIG_DISCONTIGMEM
diff --git a/arch/powerpc/Kconfig b/arch/powerpc/Kconfig
index 45192dce65c4..9e08d8a69fdf 100644
--- a/arch/powerpc/Kconfig
+++ b/arch/powerpc/Kconfig
@@ -346,7 +346,7 @@ config PHYP_DUMP
 	help
 	  Hypervisor-assisted dump is meant to be a kdump replacement
 	  offering robustness and speed not possible without system
-	  hypervisor assistence.
+	  hypervisor assistance.
 
 	  If unsure, say "N"
 
diff --git a/arch/powerpc/Kconfig.debug b/arch/powerpc/Kconfig.debug
index 6aa0b5e087cd..a1098e23221f 100644
--- a/arch/powerpc/Kconfig.debug
+++ b/arch/powerpc/Kconfig.debug
@@ -27,16 +27,6 @@ config DEBUG_STACK_USAGE
 
 	  This option will slow down process creation somewhat.
 
-config DEBUG_PAGEALLOC
-        bool "Debug page memory allocations"
-        depends on DEBUG_KERNEL && !HIBERNATION
-	depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC
-        help
-          Unmap pages from the kernel linear mapping after free_pages().
-          This results in a large slowdown, but helps to find certain types
-          of memory corruptions.
-
-
 config HCALL_STATS
 	bool "Hypervisor call instrumentation"
 	depends on PPC_PSERIES && DEBUG_FS
diff --git a/arch/powerpc/include/asm/mmzone.h b/arch/powerpc/include/asm/mmzone.h
index 19f299b7e256..35acac90c8ca 100644
--- a/arch/powerpc/include/asm/mmzone.h
+++ b/arch/powerpc/include/asm/mmzone.h
@@ -8,6 +8,7 @@
 #define _ASM_MMZONE_H_
 #ifdef __KERNEL__
 
+#include <linux/cpumask.h>
 
 /*
  * generic non-linear memory support:
diff --git a/arch/powerpc/include/asm/ps3.h b/arch/powerpc/include/asm/ps3.h
index 67f1812698d2..cdb6fd814de8 100644
--- a/arch/powerpc/include/asm/ps3.h
+++ b/arch/powerpc/include/asm/ps3.h
@@ -50,6 +50,9 @@ enum ps3_param_av_multi_out {
 
 enum ps3_param_av_multi_out ps3_os_area_get_av_multi_out(void);
 
+extern u64 ps3_os_area_get_rtc_diff(void);
+extern void ps3_os_area_set_rtc_diff(u64 rtc_diff);
+
 /* dma routines */
 
 enum ps3_dma_page_size {
diff --git a/arch/powerpc/include/asm/spinlock.h b/arch/powerpc/include/asm/spinlock.h
index 36864364e601..c3b193121f81 100644
--- a/arch/powerpc/include/asm/spinlock.h
+++ b/arch/powerpc/include/asm/spinlock.h
@@ -287,6 +287,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 	rw->lock = 0;
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)	__spin_yield(lock)
 #define _raw_read_relax(lock)	__rw_yield(lock)
 #define _raw_write_relax(lock)	__rw_yield(lock)
diff --git a/arch/powerpc/kernel/process.c b/arch/powerpc/kernel/process.c
index eac064948780..7b44a33f03c2 100644
--- a/arch/powerpc/kernel/process.c
+++ b/arch/powerpc/kernel/process.c
@@ -598,7 +598,7 @@ void prepare_to_copy(struct task_struct *tsk)
 /*
  * Copy a thread..
  */
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long unused, struct task_struct *p,
 		struct pt_regs *regs)
 {
diff --git a/arch/powerpc/kernel/time.c b/arch/powerpc/kernel/time.c
index c9564031a2a9..926ea864e34f 100644
--- a/arch/powerpc/kernel/time.c
+++ b/arch/powerpc/kernel/time.c
@@ -1127,3 +1127,19 @@ void div128_by_32(u64 dividend_high, u64 dividend_low,
 	dr->result_low  = ((u64)y << 32) + z;
 
 }
+
+static int __init rtc_init(void)
+{
+	struct platform_device *pdev;
+
+	if (!ppc_md.get_rtc_time)
+		return -ENODEV;
+
+	pdev = platform_device_register_simple("rtc-generic", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	return 0;
+}
+
+module_init(rtc_init);
diff --git a/arch/powerpc/kernel/vio.c b/arch/powerpc/kernel/vio.c
index d3694498f3af..819e59f6f7c7 100644
--- a/arch/powerpc/kernel/vio.c
+++ b/arch/powerpc/kernel/vio.c
@@ -482,7 +482,7 @@ static void vio_cmo_balance(struct work_struct *work)
 	cmo->excess.size = cmo->entitled - cmo->reserve.size;
 	cmo->excess.free = cmo->excess.size - need;
 
-	cancel_delayed_work(container_of(work, struct delayed_work, work));
+	cancel_delayed_work(to_delayed_work(work));
 	spin_unlock_irqrestore(&vio_cmo.lock, flags);
 }
 
diff --git a/arch/powerpc/platforms/Kconfig b/arch/powerpc/platforms/Kconfig
index ffa2a9fd53d0..e3e87078d03f 100644
--- a/arch/powerpc/platforms/Kconfig
+++ b/arch/powerpc/platforms/Kconfig
@@ -293,7 +293,7 @@ config CPM
 config OF_RTC
 	bool
 	help
-	  Uses information from the OF or flattened device tree to instatiate
+	  Uses information from the OF or flattened device tree to instantiate
 	  platform devices for direct mapped RTC chips like the DS1742 or DS1743.
 
 source "arch/powerpc/sysdev/bestcomm/Kconfig"
diff --git a/arch/powerpc/platforms/cell/spufs/inode.c b/arch/powerpc/platforms/cell/spufs/inode.c
index 64f068540d0d..706eb5c7e2ee 100644
--- a/arch/powerpc/platforms/cell/spufs/inode.c
+++ b/arch/powerpc/platforms/cell/spufs/inode.c
@@ -635,7 +635,7 @@ long spufs_create(struct nameidata *nd, unsigned int flags, mode_t mode,
 	if (dentry->d_inode)
 		goto out_dput;
 
-	mode &= ~current->fs->umask;
+	mode &= ~current_umask();
 
 	if (flags & SPU_CREATE_GANG)
 		ret = spufs_create_gang(nd->path.dentry->d_inode,
diff --git a/arch/powerpc/platforms/ps3/os-area.c b/arch/powerpc/platforms/ps3/os-area.c
index e1c83c23b435..86e392b1b049 100644
--- a/arch/powerpc/platforms/ps3/os-area.c
+++ b/arch/powerpc/platforms/ps3/os-area.c
@@ -808,6 +808,7 @@ u64 ps3_os_area_get_rtc_diff(void)
 {
 	return saved_params.rtc_diff;
 }
+EXPORT_SYMBOL(ps3_os_area_get_rtc_diff);
 
 /**
  * ps3_os_area_set_rtc_diff - Set the rtc diff value.
@@ -823,6 +824,7 @@ void ps3_os_area_set_rtc_diff(u64 rtc_diff)
 		os_area_queue_work();
 	}
 }
+EXPORT_SYMBOL(ps3_os_area_set_rtc_diff);
 
 /**
  * ps3_os_area_get_av_multi_out - Returns the default video mode.
diff --git a/arch/powerpc/platforms/ps3/platform.h b/arch/powerpc/platforms/ps3/platform.h
index 235c13ebacd9..136aa0637d9c 100644
--- a/arch/powerpc/platforms/ps3/platform.h
+++ b/arch/powerpc/platforms/ps3/platform.h
@@ -64,8 +64,6 @@ int ps3_set_rtc_time(struct rtc_time *time);
 
 void __init ps3_os_area_save_params(void);
 void __init ps3_os_area_init(void);
-u64 ps3_os_area_get_rtc_diff(void);
-void ps3_os_area_set_rtc_diff(u64 rtc_diff);
 
 /* spu */
 
diff --git a/arch/powerpc/platforms/ps3/setup.c b/arch/powerpc/platforms/ps3/setup.c
index 3331ccbb8d38..66181821322a 100644
--- a/arch/powerpc/platforms/ps3/setup.c
+++ b/arch/powerpc/platforms/ps3/setup.c
@@ -270,8 +270,6 @@ define_machine(ps3) {
 	.init_IRQ			= ps3_init_IRQ,
 	.panic				= ps3_panic,
 	.get_boot_time			= ps3_get_boot_time,
-	.set_rtc_time			= ps3_set_rtc_time,
-	.get_rtc_time			= ps3_get_rtc_time,
 	.set_dabr			= ps3_set_dabr,
 	.calibrate_decr			= ps3_calibrate_decr,
 	.progress			= ps3_progress,
diff --git a/arch/powerpc/platforms/ps3/time.c b/arch/powerpc/platforms/ps3/time.c
index d0daf7d6d3b2..b178a1e66c91 100644
--- a/arch/powerpc/platforms/ps3/time.c
+++ b/arch/powerpc/platforms/ps3/time.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/platform_device.h>
 
 #include <asm/rtc.h>
 #include <asm/lv1call.h>
@@ -74,23 +75,20 @@ static u64 read_rtc(void)
 	return rtc_val;
 }
 
-int ps3_set_rtc_time(struct rtc_time *tm)
+unsigned long __init ps3_get_boot_time(void)
 {
-	u64 now = mktime(tm->tm_year + 1900, tm->tm_mon + 1, tm->tm_mday,
-		tm->tm_hour, tm->tm_min, tm->tm_sec);
-
-	ps3_os_area_set_rtc_diff(now - read_rtc());
-	return 0;
+	return read_rtc() + ps3_os_area_get_rtc_diff();
 }
 
-void ps3_get_rtc_time(struct rtc_time *tm)
+static int __init ps3_rtc_init(void)
 {
-	to_tm(read_rtc() + ps3_os_area_get_rtc_diff(), tm);
-	tm->tm_year -= 1900;
-	tm->tm_mon -= 1;
-}
+	struct platform_device *pdev;
 
-unsigned long __init ps3_get_boot_time(void)
-{
-	return read_rtc() + ps3_os_area_get_rtc_diff();
+	pdev = platform_device_register_simple("rtc-ps3", -1, NULL, 0);
+	if (IS_ERR(pdev))
+		return PTR_ERR(pdev);
+
+	return 0;
 }
+
+module_init(ps3_rtc_init);
diff --git a/arch/powerpc/sysdev/bestcomm/Kconfig b/arch/powerpc/sysdev/bestcomm/Kconfig
index 0b192a1c429d..29e427085efb 100644
--- a/arch/powerpc/sysdev/bestcomm/Kconfig
+++ b/arch/powerpc/sysdev/bestcomm/Kconfig
@@ -9,8 +9,8 @@ config PPC_BESTCOMM
 	select PPC_LIB_RHEAP
 	help
 	  BestComm is the name of the communication coprocessor found
-	  on the Freescale MPC5200 family of processor. It's usage is
-	  optionnal for some drivers (like ATA), but required for
+	  on the Freescale MPC5200 family of processor.  Its usage is
+	  optional for some drivers (like ATA), but required for
 	  others (like FEC).
 
 	  If you want to use drivers that require DMA operations,
diff --git a/arch/s390/Kconfig.debug b/arch/s390/Kconfig.debug
index 7e297a3cde34..2283933a9a93 100644
--- a/arch/s390/Kconfig.debug
+++ b/arch/s390/Kconfig.debug
@@ -6,13 +6,4 @@ config TRACE_IRQFLAGS_SUPPORT
 
 source "lib/Kconfig.debug"
 
-config DEBUG_PAGEALLOC
-	bool "Debug page memory allocations"
-	depends on DEBUG_KERNEL
-	depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	help
-	  Unmap pages from the kernel linear mapping after free_pages().
-	  This results in a slowdown, but helps to find certain types of
-	  memory corruptions.
-
 endmenu
diff --git a/arch/s390/include/asm/smp.h b/arch/s390/include/asm/smp.h
index 2009158a4502..72137bc907ac 100644
--- a/arch/s390/include/asm/smp.h
+++ b/arch/s390/include/asm/smp.h
@@ -92,12 +92,6 @@ extern void arch_send_call_function_ipi(cpumask_t mask);
 #endif
 
 #ifndef CONFIG_SMP
-static inline void smp_send_stop(void)
-{
-	/* Disable all interrupts/machine checks */
-	__load_psw_mask(psw_kernel_bits & ~PSW_MASK_MCHECK);
-}
-
 #define hard_smp_processor_id()		0
 #define smp_cpu_not_running(cpu)	1
 #endif
diff --git a/arch/s390/include/asm/spinlock.h b/arch/s390/include/asm/spinlock.h
index df84ae96915f..f3861b09ebb0 100644
--- a/arch/s390/include/asm/spinlock.h
+++ b/arch/s390/include/asm/spinlock.h
@@ -172,6 +172,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
 	return _raw_write_trylock_retry(rw);
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
 
diff --git a/arch/s390/kernel/process.c b/arch/s390/kernel/process.c
index b48e961a38f6..a3acd8e60aff 100644
--- a/arch/s390/kernel/process.c
+++ b/arch/s390/kernel/process.c
@@ -160,7 +160,7 @@ void release_thread(struct task_struct *dead_task)
 {
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long new_stackp,
+int copy_thread(unsigned long clone_flags, unsigned long new_stackp,
 		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/sh/Kconfig b/arch/sh/Kconfig
index 8d50d527c595..2d52b515c241 100644
--- a/arch/sh/Kconfig
+++ b/arch/sh/Kconfig
@@ -640,10 +640,10 @@ config GUSA_RB
 	depends on GUSA && CPU_SH3 || (CPU_SH4 && !CPU_SH4A)
 	help
 	  Enabling this option will allow the kernel to implement some
-	  atomic operations using a software implemention of load-locked/
+	  atomic operations using a software implementation of load-locked/
 	  store-conditional (LLSC). On machines which do not have hardware
 	  LLSC, this should be more efficient than the other alternative of
-	  disabling insterrupts around the atomic sequence.
+	  disabling interrupts around the atomic sequence.
 
 endmenu
 
diff --git a/arch/sh/include/asm/spinlock.h b/arch/sh/include/asm/spinlock.h
index e793181d64da..60283565f89b 100644
--- a/arch/sh/include/asm/spinlock.h
+++ b/arch/sh/include/asm/spinlock.h
@@ -216,6 +216,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *rw)
 	return (oldval > (RW_LOCK_BIAS - 1));
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
diff --git a/arch/sh/kernel/process_32.c b/arch/sh/kernel/process_32.c
index ddafbbbab2ab..694bc15f84fd 100644
--- a/arch/sh/kernel/process_32.c
+++ b/arch/sh/kernel/process_32.c
@@ -170,7 +170,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 
 asmlinkage void ret_from_fork(void);
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/sh/kernel/process_64.c b/arch/sh/kernel/process_64.c
index c90c7e5e5fee..96be839040f8 100644
--- a/arch/sh/kernel/process_64.c
+++ b/arch/sh/kernel/process_64.c
@@ -425,7 +425,7 @@ int dump_fpu(struct pt_regs *regs, elf_fpregset_t *fpu)
 
 asmlinkage void ret_from_fork(void);
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/sparc/Kconfig.debug b/arch/sparc/Kconfig.debug
index d001b42041a5..90d5fe223a74 100644
--- a/arch/sparc/Kconfig.debug
+++ b/arch/sparc/Kconfig.debug
@@ -22,15 +22,6 @@ config DEBUG_DCFLUSH
 config STACK_DEBUG
 	bool "Stack Overflow Detection Support"
 
-config DEBUG_PAGEALLOC
-	bool "Debug page memory allocations"
-	depends on DEBUG_KERNEL && !HIBERNATION
-	depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	help
-	  Unmap pages from the kernel linear mapping after free_pages().
-	  This results in a large slowdown, but helps to find certain types
-	  of memory corruptions.
-
 config MCOUNT
 	bool
 	depends on SPARC64
diff --git a/arch/sparc/include/asm/mmzone.h b/arch/sparc/include/asm/mmzone.h
index ebf5986c12ed..e8c648741ed4 100644
--- a/arch/sparc/include/asm/mmzone.h
+++ b/arch/sparc/include/asm/mmzone.h
@@ -3,6 +3,8 @@
 
 #ifdef CONFIG_NEED_MULTIPLE_NODES
 
+#include <linux/cpumask.h>
+
 extern struct pglist_data *node_data[];
 
 #define NODE_DATA(nid)		(node_data[nid])
diff --git a/arch/sparc/include/asm/spinlock_32.h b/arch/sparc/include/asm/spinlock_32.h
index bf2d532593e3..46f91ab66a50 100644
--- a/arch/sparc/include/asm/spinlock_32.h
+++ b/arch/sparc/include/asm/spinlock_32.h
@@ -177,6 +177,8 @@ static inline int __read_trylock(raw_rwlock_t *rw)
 #define __raw_write_unlock(rw)	do { (rw)->lock = 0; } while(0)
 
 #define __raw_spin_lock_flags(lock, flags) __raw_spin_lock(lock)
+#define __raw_read_lock_flags(rw, flags)   __raw_read_lock(rw)
+#define __raw_write_lock_flags(rw, flags)  __raw_write_lock(rw)
 
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
diff --git a/arch/sparc/include/asm/spinlock_64.h b/arch/sparc/include/asm/spinlock_64.h
index c4d274d330e9..f6b2b92ad8d2 100644
--- a/arch/sparc/include/asm/spinlock_64.h
+++ b/arch/sparc/include/asm/spinlock_64.h
@@ -211,9 +211,11 @@ static int inline __write_trylock(raw_rwlock_t *lock)
 }
 
 #define __raw_read_lock(p)	__read_lock(p)
+#define __raw_read_lock_flags(p, f) __read_lock(p)
 #define __raw_read_trylock(p)	__read_trylock(p)
 #define __raw_read_unlock(p)	__read_unlock(p)
 #define __raw_write_lock(p)	__write_lock(p)
+#define __raw_write_lock_flags(p, f) __write_lock(p)
 #define __raw_write_unlock(p)	__write_unlock(p)
 #define __raw_write_trylock(p)	__write_trylock(p)
 
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index a46c3a21e26d..3a1b7bf03cff 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -686,7 +686,7 @@ tlb_fixup_done:
 	 * point.
 	 *
 	 * There used to be enormous complexity wrt. transferring
-	 * over from the firwmare's trap table to the Linux kernel's.
+	 * over from the firmware's trap table to the Linux kernel's.
 	 * For example, there was a chicken & egg problem wrt. building
 	 * the OBP page tables, yet needing to be on the Linux kernel
 	 * trap table (to translate PAGE_OFFSET addresses) in order to
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index f4bee35a1b46..2830b415e214 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -455,7 +455,7 @@ asmlinkage int sparc_do_fork(unsigned long clone_flags,
  */
 extern void ret_from_fork(void);
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index a73954b87f0a..4041f94e7724 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -561,7 +561,7 @@ asmlinkage long sparc_do_fork(unsigned long clone_flags,
  * Parent -->  %o0 == childs  pid, %o1 == 0
  * Child  -->  %o0 == parents pid, %o1 == 1
  */
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long unused,
 		struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/um/drivers/net_kern.c b/arch/um/drivers/net_kern.c
index 434224e2229f..434ba121e3c5 100644
--- a/arch/um/drivers/net_kern.c
+++ b/arch/um/drivers/net_kern.c
@@ -757,7 +757,7 @@ static int uml_inetaddr_event(struct notifier_block *this, unsigned long event,
 	void (*proc)(unsigned char *, unsigned char *, void *);
 	unsigned char addr_buf[4], netmask_buf[4];
 
-	if (dev->open != uml_net_open)
+	if (dev->netdev_ops->ndo_open != uml_net_open)
 		return NOTIFY_DONE;
 
 	lp = netdev_priv(dev);
diff --git a/arch/um/drivers/ubd_kern.c b/arch/um/drivers/ubd_kern.c
index d42f826a8ab9..f934225fd8ef 100644
--- a/arch/um/drivers/ubd_kern.c
+++ b/arch/um/drivers/ubd_kern.c
@@ -22,6 +22,7 @@
 #include "linux/kernel.h"
 #include "linux/module.h"
 #include "linux/blkdev.h"
+#include "linux/ata.h"
 #include "linux/hdreg.h"
 #include "linux/init.h"
 #include "linux/cdrom.h"
@@ -1308,16 +1309,15 @@ static int ubd_ioctl(struct block_device *bdev, fmode_t mode,
 		     unsigned int cmd, unsigned long arg)
 {
 	struct ubd *ubd_dev = bdev->bd_disk->private_data;
-	struct hd_driveid ubd_id = {
-		.cyls		= 0,
-		.heads		= 128,
-		.sectors	= 32,
-	};
+	u16 ubd_id[ATA_ID_WORDS];
 
 	switch (cmd) {
 		struct cdrom_volctrl volume;
 	case HDIO_GET_IDENTITY:
-		ubd_id.cyls = ubd_dev->size / (128 * 32 * 512);
+		memset(&ubd_id, 0, ATA_ID_WORDS * 2);
+		ubd_id[ATA_ID_CYLS]	= ubd_dev->size / (128 * 32 * 512);
+		ubd_id[ATA_ID_HEADS]	= 128;
+		ubd_id[ATA_ID_SECTORS]	= 32;
 		if(copy_to_user((char __user *) arg, (char *) &ubd_id,
 				 sizeof(ubd_id)))
 			return -EFAULT;
diff --git a/arch/um/kernel/process.c b/arch/um/kernel/process.c
index a1c6d07cac3e..4a28a1568d85 100644
--- a/arch/um/kernel/process.c
+++ b/arch/um/kernel/process.c
@@ -179,7 +179,7 @@ void fork_handler(void)
 	userspace(&current->thread.regs.regs);
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long stack_top, struct task_struct * p,
 		struct pt_regs *regs)
 {
diff --git a/arch/um/kernel/syscall.c b/arch/um/kernel/syscall.c
index c4df705b8359..a4625c7b2bf9 100644
--- a/arch/um/kernel/syscall.c
+++ b/arch/um/kernel/syscall.c
@@ -127,7 +127,8 @@ int kernel_execve(const char *filename, char *const argv[], char *const envp[])
 
 	fs = get_fs();
 	set_fs(KERNEL_DS);
-	ret = um_execve(filename, argv, envp);
+	ret = um_execve((char *)filename, (char __user *__user *)argv,
+			(char __user *__user *) envp);
 	set_fs(fs);
 
 	return ret;
diff --git a/arch/um/sys-i386/sys_call_table.S b/arch/um/sys-i386/sys_call_table.S
index 00e5f5203eea..c6260dd6ebb9 100644
--- a/arch/um/sys-i386/sys_call_table.S
+++ b/arch/um/sys-i386/sys_call_table.S
@@ -9,6 +9,17 @@
 
 #define old_mmap old_mmap_i386
 
+#define ptregs_fork sys_fork
+#define ptregs_execve sys_execve
+#define ptregs_iopl sys_iopl
+#define ptregs_vm86old sys_vm86old
+#define ptregs_sigreturn sys_sigreturn
+#define ptregs_clone sys_clone
+#define ptregs_vm86 sys_vm86
+#define ptregs_rt_sigreturn sys_rt_sigreturn
+#define ptregs_sigaltstack sys_sigaltstack
+#define ptregs_vfork sys_vfork
+
 .section .rodata,"a"
 
 #include "../../x86/kernel/syscall_table_32.S"
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 0885245e6808..5b2196ab8168 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -1146,7 +1146,7 @@ config NODES_SHIFT
 	depends on NEED_MULTIPLE_NODES
 	---help---
 	  Specify the maximum number of NUMA Nodes available on the target
-	  system.  Increases memory reserved to accomodate various tables.
+	  system.  Increases memory reserved to accommodate various tables.
 
 config HAVE_ARCH_BOOTMEM
 	def_bool y
@@ -1324,7 +1324,7 @@ config MTRR_SANITIZER
 	  add writeback entries.
 
 	  Can be disabled with disable_mtrr_cleanup on the kernel command line.
-	  The largest mtrr entry size for a continous block can be set with
+	  The largest mtrr entry size for a continuous block can be set with
 	  mtrr_chunk_size.
 
 	  If unsure, say Y.
@@ -1839,8 +1839,8 @@ config PCI_MMCONFIG
 
 config DMAR
 	bool "Support for DMA Remapping Devices (EXPERIMENTAL)"
-	depends on X86_64 && PCI_MSI && ACPI && EXPERIMENTAL
-	---help---
+	depends on PCI_MSI && ACPI && EXPERIMENTAL
+	help
 	  DMA remapping (DMAR) devices support enables independent address
 	  translations for Direct Memory Access (DMA) from devices.
 	  These DMA remapping devices are reported via ACPI tables
diff --git a/arch/x86/Kconfig.debug b/arch/x86/Kconfig.debug
index a345cb5447a8..d8359e73317f 100644
--- a/arch/x86/Kconfig.debug
+++ b/arch/x86/Kconfig.debug
@@ -72,15 +72,6 @@ config DEBUG_STACK_USAGE
 
 	  This option will slow down process creation somewhat.
 
-config DEBUG_PAGEALLOC
-	bool "Debug page memory allocations"
-	depends on DEBUG_KERNEL
-	depends on ARCH_SUPPORTS_DEBUG_PAGEALLOC
-	---help---
-	  Unmap pages from the kernel linear mapping after free_pages().
-	  This results in a large slowdown, but helps to find certain types
-	  of memory corruptions.
-
 config DEBUG_PER_CPU_MAPS
 	bool "Debug access to per_cpu maps"
 	depends on DEBUG_KERNEL
diff --git a/arch/x86/boot/Makefile b/arch/x86/boot/Makefile
index fb737ce5888d..6633b6e7505a 100644
--- a/arch/x86/boot/Makefile
+++ b/arch/x86/boot/Makefile
@@ -57,6 +57,7 @@ $(obj)/cpustr.h: $(obj)/mkcpustr FORCE
 # How to compile the 16-bit code.  Note we always compile for -march=i386,
 # that way we can complain to the user if the CPU is insufficient.
 KBUILD_CFLAGS	:= $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
+		   -DDISABLE_BRANCH_PROFILING \
 		   -Wall -Wstrict-prototypes \
 		   -march=i386 -mregparm=3 \
 		   -include $(srctree)/$(src)/code16gcc.h \
@@ -66,7 +67,7 @@ KBUILD_CFLAGS	:= $(LINUXINCLUDE) -g -Os -D_SETUP -D__KERNEL__ \
 			$(call cc-option, -fno-unit-at-a-time)) \
 		   $(call cc-option, -fno-stack-protector) \
 		   $(call cc-option, -mpreferred-stack-boundary=2)
-KBUILD_CFLAGS +=   $(call cc-option,-m32)
+KBUILD_CFLAGS	+= $(call cc-option, -m32)
 KBUILD_AFLAGS	:= $(KBUILD_CFLAGS) -D__ASSEMBLY__
 
 $(obj)/bzImage: asflags-y  := $(SVGA_MODE)
diff --git a/arch/x86/boot/compressed/Makefile b/arch/x86/boot/compressed/Makefile
index 3ca4c194b8e5..65551c9f8571 100644
--- a/arch/x86/boot/compressed/Makefile
+++ b/arch/x86/boot/compressed/Makefile
@@ -8,6 +8,7 @@ targets := vmlinux vmlinux.bin vmlinux.bin.gz vmlinux.bin.bz2 vmlinux.bin.lzma h
 
 KBUILD_CFLAGS := -m$(BITS) -D__KERNEL__ $(LINUX_INCLUDE) -O2
 KBUILD_CFLAGS += -fno-strict-aliasing -fPIC
+KBUILD_CFLAGS += -DDISABLE_BRANCH_PROFILING
 cflags-$(CONFIG_X86_64) := -mcmodel=small
 KBUILD_CFLAGS += $(cflags-y)
 KBUILD_CFLAGS += $(call cc-option,-ffreestanding)
diff --git a/arch/x86/boot/memory.c b/arch/x86/boot/memory.c
index 8c3c25f35578..5054c2ddd1a0 100644
--- a/arch/x86/boot/memory.c
+++ b/arch/x86/boot/memory.c
@@ -2,6 +2,7 @@
  *
  *   Copyright (C) 1991, 1992 Linus Torvalds
  *   Copyright 2007 rPath, Inc. - All Rights Reserved
+ *   Copyright 2009 Intel Corporation; author H. Peter Anvin
  *
  *   This file is part of the Linux kernel, and is made available under
  *   the terms of the GNU General Public License version 2.
@@ -16,24 +17,38 @@
 
 #define SMAP	0x534d4150	/* ASCII "SMAP" */
 
+struct e820_ext_entry {
+	struct e820entry std;
+	u32 ext_flags;
+} __attribute__((packed));
+
 static int detect_memory_e820(void)
 {
 	int count = 0;
 	u32 next = 0;
-	u32 size, id;
+	u32 size, id, edi;
 	u8 err;
 	struct e820entry *desc = boot_params.e820_map;
+	static struct e820_ext_entry buf; /* static so it is zeroed */
+
+	/*
+	 * Set this here so that if the BIOS doesn't change this field
+	 * but still doesn't change %ecx, we're still okay...
+	 */
+	buf.ext_flags = 1;
 
 	do {
-		size = sizeof(struct e820entry);
+		size = sizeof buf;
 
-		/* Important: %edx is clobbered by some BIOSes,
-		   so it must be either used for the error output
-		   or explicitly marked clobbered. */
-		asm("int $0x15; setc %0"
+		/* Important: %edx and %esi are clobbered by some BIOSes,
+		   so they must be either used for the error output
+		   or explicitly marked clobbered.  Given that, assume there
+		   is something out there clobbering %ebp and %edi, too. */
+		asm("pushl %%ebp; int $0x15; popl %%ebp; setc %0"
 		    : "=d" (err), "+b" (next), "=a" (id), "+c" (size),
-		      "=m" (*desc)
-		    : "D" (desc), "d" (SMAP), "a" (0xe820));
+		      "=D" (edi), "+m" (buf)
+		    : "D" (&buf), "d" (SMAP), "a" (0xe820)
+		    : "esi");
 
 		/* BIOSes which terminate the chain with CF = 1 as opposed
 		   to %ebx = 0 don't always report the SMAP signature on
@@ -51,8 +66,14 @@ static int detect_memory_e820(void)
 			break;
 		}
 
+		/* ACPI 3.0 added the extended flags support.  If bit 0
+		   in the extended flags is zero, we're supposed to simply
+		   ignore the entry -- a backwards incompatible change! */
+		if (size > 20 && !(buf.ext_flags & 1))
+			continue;
+
+		*desc++ = buf.std;
 		count++;
-		desc++;
 	} while (next && count < ARRAY_SIZE(boot_params.e820_map));
 
 	return boot_params.e820_entries = count;
diff --git a/arch/x86/ia32/ia32entry.S b/arch/x86/ia32/ia32entry.S
index db0c803170ab..a505202086e8 100644
--- a/arch/x86/ia32/ia32entry.S
+++ b/arch/x86/ia32/ia32entry.S
@@ -828,4 +828,6 @@ ia32_sys_call_table:
 	.quad sys_dup3			/* 330 */
 	.quad sys_pipe2
 	.quad sys_inotify_init1
+	.quad compat_sys_preadv
+	.quad compat_sys_pwritev
 ia32_syscall_end:
diff --git a/arch/x86/include/asm/cpumask.h b/arch/x86/include/asm/cpumask.h
index a7f3c75f8ad7..61c852fa346b 100644
--- a/arch/x86/include/asm/cpumask.h
+++ b/arch/x86/include/asm/cpumask.h
@@ -3,8 +3,6 @@
 #ifndef __ASSEMBLY__
 #include <linux/cpumask.h>
 
-#ifdef CONFIG_X86_64
-
 extern cpumask_var_t cpu_callin_mask;
 extern cpumask_var_t cpu_callout_mask;
 extern cpumask_var_t cpu_initialized_mask;
@@ -12,21 +10,5 @@ extern cpumask_var_t cpu_sibling_setup_mask;
 
 extern void setup_cpu_local_masks(void);
 
-#else /* CONFIG_X86_32 */
-
-extern cpumask_t cpu_callin_map;
-extern cpumask_t cpu_callout_map;
-extern cpumask_t cpu_initialized;
-extern cpumask_t cpu_sibling_setup_map;
-
-#define cpu_callin_mask		((struct cpumask *)&cpu_callin_map)
-#define cpu_callout_mask	((struct cpumask *)&cpu_callout_map)
-#define cpu_initialized_mask	((struct cpumask *)&cpu_initialized)
-#define cpu_sibling_setup_mask	((struct cpumask *)&cpu_sibling_setup_map)
-
-static inline void setup_cpu_local_masks(void) { }
-
-#endif /* CONFIG_X86_32 */
-
 #endif /* __ASSEMBLY__ */
 #endif /* _ASM_X86_CPUMASK_H */
diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h
index a0301bfeb954..b51a1e8b0baf 100644
--- a/arch/x86/include/asm/pci.h
+++ b/arch/x86/include/asm/pci.h
@@ -89,12 +89,40 @@ extern void pci_iommu_alloc(void);
 /* MSI arch hook */
 #define arch_setup_msi_irqs arch_setup_msi_irqs
 
-#endif  /* __KERNEL__ */
+#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
+
+#if defined(CONFIG_X86_64) || defined(CONFIG_DMA_API_DEBUG)
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       \
+	        dma_addr_t ADDR_NAME;
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)         \
+	        __u32 LEN_NAME;
+#define pci_unmap_addr(PTR, ADDR_NAME)                  \
+	        ((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)         \
+	        (((PTR)->ADDR_NAME) = (VAL))
+#define pci_unmap_len(PTR, LEN_NAME)                    \
+	        ((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL)           \
+	        (((PTR)->LEN_NAME) = (VAL))
 
-#ifdef CONFIG_X86_32
-# include "pci_32.h"
 #else
-# include "pci_64.h"
+
+#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)       dma_addr_t ADDR_NAME[0];
+#define DECLARE_PCI_UNMAP_LEN(LEN_NAME) unsigned LEN_NAME[0];
+#define pci_unmap_addr(PTR, ADDR_NAME)  sizeof((PTR)->ADDR_NAME)
+#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
+	        do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
+#define pci_unmap_len(PTR, LEN_NAME)            sizeof((PTR)->LEN_NAME)
+#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
+	        do { break; } while (pci_unmap_len(PTR, LEN_NAME))
+
+#endif
+
+#endif  /* __KERNEL__ */
+
+#ifdef CONFIG_X86_64
+#include "pci_64.h"
 #endif
 
 /* implement the pci_ DMA API in terms of the generic device dma_ one */
@@ -112,11 +140,6 @@ static inline int __pcibus_to_node(const struct pci_bus *bus)
 	return sd->node;
 }
 
-static inline cpumask_t __pcibus_to_cpumask(struct pci_bus *bus)
-{
-	return node_to_cpumask(__pcibus_to_node(bus));
-}
-
 static inline const struct cpumask *
 cpumask_of_pcibus(const struct pci_bus *bus)
 {
diff --git a/arch/x86/include/asm/pci_32.h b/arch/x86/include/asm/pci_32.h
deleted file mode 100644
index 6f1213a6ef4f..000000000000
--- a/arch/x86/include/asm/pci_32.h
+++ /dev/null
@@ -1,34 +0,0 @@
-#ifndef _ASM_X86_PCI_32_H
-#define _ASM_X86_PCI_32_H
-
-
-#ifdef __KERNEL__
-
-
-/* Dynamic DMA mapping stuff.
- * i386 has everything mapped statically.
- */
-
-struct pci_dev;
-
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions.
- */
-#define PCI_DMA_BUS_IS_PHYS	(1)
-
-/* pci_unmap_{page,single} is a nop so... */
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	dma_addr_t ADDR_NAME[0];
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)	unsigned LEN_NAME[0];
-#define pci_unmap_addr(PTR, ADDR_NAME)	sizeof((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL) \
-	do { break; } while (pci_unmap_addr(PTR, ADDR_NAME))
-#define pci_unmap_len(PTR, LEN_NAME)		sizeof((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL) \
-	do { break; } while (pci_unmap_len(PTR, LEN_NAME))
-
-
-#endif /* __KERNEL__ */
-
-
-#endif /* _ASM_X86_PCI_32_H */
diff --git a/arch/x86/include/asm/pci_64.h b/arch/x86/include/asm/pci_64.h
index 4da207982777..ae5e40f67daf 100644
--- a/arch/x86/include/asm/pci_64.h
+++ b/arch/x86/include/asm/pci_64.h
@@ -24,28 +24,6 @@ extern int (*pci_config_write)(int seg, int bus, int dev, int fn,
 
 extern void dma32_reserve_bootmem(void);
 
-/* The PCI address space does equal the physical memory
- * address space.  The networking and block device layers use
- * this boolean for bounce buffer decisions
- *
- * On AMD64 it mostly equals, but we set it to zero if a hardware
- * IOMMU (gart) of sotware IOMMU (swiotlb) is available.
- */
-#define PCI_DMA_BUS_IS_PHYS (dma_ops->is_phys)
-
-#define DECLARE_PCI_UNMAP_ADDR(ADDR_NAME)	\
-	dma_addr_t ADDR_NAME;
-#define DECLARE_PCI_UNMAP_LEN(LEN_NAME)		\
-	__u32 LEN_NAME;
-#define pci_unmap_addr(PTR, ADDR_NAME)			\
-	((PTR)->ADDR_NAME)
-#define pci_unmap_addr_set(PTR, ADDR_NAME, VAL)		\
-	(((PTR)->ADDR_NAME) = (VAL))
-#define pci_unmap_len(PTR, LEN_NAME)			\
-	((PTR)->LEN_NAME)
-#define pci_unmap_len_set(PTR, LEN_NAME, VAL)		\
-	(((PTR)->LEN_NAME) = (VAL))
-
 #endif /* __KERNEL__ */
 
 #endif /* _ASM_X86_PCI_64_H */
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index ae85a8d66a30..34c52370f2fe 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -94,7 +94,7 @@ struct cpuinfo_x86 {
 	unsigned long		loops_per_jiffy;
 #ifdef CONFIG_SMP
 	/* cpus sharing the last level cache: */
-	cpumask_t		llc_shared_map;
+	cpumask_var_t		llc_shared_map;
 #endif
 	/* cpuid returned max cores value: */
 	u16			 x86_max_cores;
@@ -736,6 +736,7 @@ static inline void __sti_mwait(unsigned long eax, unsigned long ecx)
 extern void mwait_idle_with_hints(unsigned long eax, unsigned long ecx);
 
 extern void select_idle_routine(const struct cpuinfo_x86 *c);
+extern void init_c1e_mask(void);
 
 extern unsigned long		boot_option_idle_override;
 extern unsigned long		idle_halt;
diff --git a/arch/x86/include/asm/smp.h b/arch/x86/include/asm/smp.h
index 47d0e21f2b9e..19e0d88b966d 100644
--- a/arch/x86/include/asm/smp.h
+++ b/arch/x86/include/asm/smp.h
@@ -21,19 +21,19 @@
 extern int smp_num_siblings;
 extern unsigned int num_processors;
 
-DECLARE_PER_CPU(cpumask_t, cpu_sibling_map);
-DECLARE_PER_CPU(cpumask_t, cpu_core_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_sibling_map);
+DECLARE_PER_CPU(cpumask_var_t, cpu_core_map);
 DECLARE_PER_CPU(u16, cpu_llc_id);
 DECLARE_PER_CPU(int, cpu_number);
 
 static inline struct cpumask *cpu_sibling_mask(int cpu)
 {
-	return &per_cpu(cpu_sibling_map, cpu);
+	return per_cpu(cpu_sibling_map, cpu);
 }
 
 static inline struct cpumask *cpu_core_mask(int cpu)
 {
-	return &per_cpu(cpu_core_map, cpu);
+	return per_cpu(cpu_core_map, cpu);
 }
 
 DECLARE_EARLY_PER_CPU(u16, x86_cpu_to_apicid);
@@ -121,9 +121,10 @@ static inline void arch_send_call_function_single_ipi(int cpu)
 	smp_ops.send_call_func_single_ipi(cpu);
 }
 
-static inline void arch_send_call_function_ipi(cpumask_t mask)
+#define arch_send_call_function_ipi_mask arch_send_call_function_ipi_mask
+static inline void arch_send_call_function_ipi_mask(const struct cpumask *mask)
 {
-	smp_ops.send_call_func_ipi(&mask);
+	smp_ops.send_call_func_ipi(mask);
 }
 
 void cpu_disable_common(void);
diff --git a/arch/x86/include/asm/spinlock.h b/arch/x86/include/asm/spinlock.h
index 3a5696656680..e5e6caffec87 100644
--- a/arch/x86/include/asm/spinlock.h
+++ b/arch/x86/include/asm/spinlock.h
@@ -295,6 +295,9 @@ static inline void __raw_write_unlock(raw_rwlock_t *rw)
 		     : "+m" (rw->lock) : "i" (RW_LOCK_BIAS) : "memory");
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index 744299c0b774..892b119dba6f 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -44,9 +44,6 @@
 
 #ifdef CONFIG_X86_32
 
-/* Mappings between node number and cpus on that node. */
-extern cpumask_t node_to_cpumask_map[];
-
 /* Mappings between logical cpu number and node number */
 extern int cpu_to_node_map[];
 
@@ -57,30 +54,8 @@ static inline int cpu_to_node(int cpu)
 }
 #define early_cpu_to_node(cpu)	cpu_to_node(cpu)
 
-/* Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used.  The
- * cpumask_of_node function should be used whenever possible.
- */
-static inline cpumask_t node_to_cpumask(int node)
-{
-	return node_to_cpumask_map[node];
-}
-
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline const struct cpumask *cpumask_of_node(int node)
-{
-	return &node_to_cpumask_map[node];
-}
-
-static inline void setup_node_to_cpumask_map(void) { }
-
 #else /* CONFIG_X86_64 */
 
-/* Mappings between node number and cpus on that node. */
-extern cpumask_t *node_to_cpumask_map;
-
 /* Mappings between logical cpu number and node number */
 DECLARE_EARLY_PER_CPU(int, x86_cpu_to_node_map);
 
@@ -91,8 +66,6 @@ DECLARE_PER_CPU(int, node_number);
 #ifdef CONFIG_DEBUG_PER_CPU_MAPS
 extern int cpu_to_node(int cpu);
 extern int early_cpu_to_node(int cpu);
-extern const cpumask_t *cpumask_of_node(int node);
-extern cpumask_t node_to_cpumask(int node);
 
 #else	/* !CONFIG_DEBUG_PER_CPU_MAPS */
 
@@ -108,42 +81,32 @@ static inline int early_cpu_to_node(int cpu)
 	return early_per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
-static inline const cpumask_t *cpumask_of_node(int node)
-{
-	return &node_to_cpumask_map[node];
-}
+#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+
+#endif /* CONFIG_X86_64 */
 
-/* Returns a bitmask of CPUs on Node 'node'. */
-static inline cpumask_t node_to_cpumask(int node)
+/* Mappings between node number and cpus on that node. */
+extern cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+extern const struct cpumask *cpumask_of_node(int node);
+#else
+/* Returns a pointer to the cpumask of CPUs on Node 'node'. */
+static inline const struct cpumask *cpumask_of_node(int node)
 {
 	return node_to_cpumask_map[node];
 }
-
-#endif /* !CONFIG_DEBUG_PER_CPU_MAPS */
+#endif
 
 extern void setup_node_to_cpumask_map(void);
 
 /*
- * Replace default node_to_cpumask_ptr with optimized version
- * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
- */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = cpumask_of_node(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = cpumask_of_node(node)
-
-#endif /* CONFIG_X86_64 */
-
-/*
  * Returns the number of the node containing Node 'node'. This
  * architecture is flat, so it is a pretty simple function!
  */
 #define parent_node(node) (node)
 
 #define pcibus_to_node(bus) __pcibus_to_node(bus)
-#define pcibus_to_cpumask(bus) __pcibus_to_cpumask(bus)
 
 #ifdef CONFIG_X86_32
 extern unsigned long node_start_pfn[];
@@ -209,40 +172,24 @@ static inline int early_cpu_to_node(int cpu)
 	return 0;
 }
 
-static inline const cpumask_t *cpumask_of_node(int node)
-{
-	return &cpu_online_map;
-}
-static inline cpumask_t node_to_cpumask(int node)
+static inline const struct cpumask *cpumask_of_node(int node)
 {
-	return cpu_online_map;
+	return cpu_online_mask;
 }
 
 static inline void setup_node_to_cpumask_map(void) { }
 
-/*
- * Replace default node_to_cpumask_ptr with optimized version
- * Deprecated: use "const struct cpumask *mask = cpumask_of_node(node)"
- */
-#define node_to_cpumask_ptr(v, node)		\
-		const cpumask_t *v = cpumask_of_node(node)
-
-#define node_to_cpumask_ptr_next(v, node)	\
-			   v = cpumask_of_node(node)
 #endif
 
 #include <asm-generic/topology.h>
 
-extern cpumask_t cpu_coregroup_map(int cpu);
 extern const struct cpumask *cpu_coregroup_mask(int cpu);
 
 #ifdef ENABLE_TOPO_DEFINES
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).phys_proc_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).cpu_core_id)
-#define topology_core_siblings(cpu)		(per_cpu(cpu_core_map, cpu))
-#define topology_thread_siblings(cpu)		(per_cpu(cpu_sibling_map, cpu))
-#define topology_core_cpumask(cpu)		(&per_cpu(cpu_core_map, cpu))
-#define topology_thread_cpumask(cpu)		(&per_cpu(cpu_sibling_map, cpu))
+#define topology_core_cpumask(cpu)		(per_cpu(cpu_core_map, cpu))
+#define topology_thread_cpumask(cpu)		(per_cpu(cpu_sibling_map, cpu))
 
 /* indicates that pointers to the topology cpumask_t maps are valid */
 #define arch_provides_topology_pointers		yes
@@ -256,7 +203,7 @@ struct pci_bus;
 void set_pci_bus_resources_arch_default(struct pci_bus *b);
 
 #ifdef CONFIG_SMP
-#define mc_capable()	(cpus_weight(per_cpu(cpu_core_map, 0)) != nr_cpu_ids)
+#define mc_capable()	(cpumask_weight(cpu_core_mask(0)) != nr_cpu_ids)
 #define smt_capable()			(smp_num_siblings > 1)
 #endif
 
diff --git a/arch/x86/include/asm/unistd_32.h b/arch/x86/include/asm/unistd_32.h
index f2bba78430a4..6e72d74cf8dc 100644
--- a/arch/x86/include/asm/unistd_32.h
+++ b/arch/x86/include/asm/unistd_32.h
@@ -338,6 +338,8 @@
 #define __NR_dup3		330
 #define __NR_pipe2		331
 #define __NR_inotify_init1	332
+#define __NR_preadv		333
+#define __NR_pwritev		334
 
 #ifdef __KERNEL__
 
diff --git a/arch/x86/include/asm/unistd_64.h b/arch/x86/include/asm/unistd_64.h
index d2e415e6666f..f81829462325 100644
--- a/arch/x86/include/asm/unistd_64.h
+++ b/arch/x86/include/asm/unistd_64.h
@@ -653,6 +653,10 @@ __SYSCALL(__NR_dup3, sys_dup3)
 __SYSCALL(__NR_pipe2, sys_pipe2)
 #define __NR_inotify_init1			294
 __SYSCALL(__NR_inotify_init1, sys_inotify_init1)
+#define __NR_preadv				295
+__SYSCALL(__NR_preadv, sys_preadv)
+#define __NR_pwritev				296
+__SYSCALL(__NR_pwritev, sys_pwritev)
 
 
 #ifndef __NO_STUBS
diff --git a/arch/x86/include/asm/uv/uv_hub.h b/arch/x86/include/asm/uv/uv_hub.h
index 9f4dfba33b28..d3a98ea1062e 100644
--- a/arch/x86/include/asm/uv/uv_hub.h
+++ b/arch/x86/include/asm/uv/uv_hub.h
@@ -11,11 +11,13 @@
 #ifndef _ASM_X86_UV_UV_HUB_H
 #define _ASM_X86_UV_UV_HUB_H
 
+#ifdef CONFIG_X86_64
 #include <linux/numa.h>
 #include <linux/percpu.h>
 #include <linux/timer.h>
 #include <asm/types.h>
 #include <asm/percpu.h>
+#include <asm/uv/uv_mmrs.h>
 
 
 /*
@@ -397,6 +399,7 @@ static inline void uv_set_scir_bits(unsigned char value)
 		uv_write_local_mmr8(uv_hub_info->scir.offset, value);
 	}
 }
+
 static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 {
 	if (uv_cpu_hub_info(cpu)->scir.state != value) {
@@ -405,4 +408,15 @@ static inline void uv_set_cpu_scir_bits(int cpu, unsigned char value)
 	}
 }
 
+static inline void uv_hub_send_ipi(int pnode, int apicid, int vector)
+{
+	unsigned long val;
+
+	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
+			((apicid & 0x3f) << UVH_IPI_INT_APIC_ID_SHFT) |
+			(vector << UVH_IPI_INT_VECTOR_SHFT);
+	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
+}
+
+#endif /* CONFIG_X86_64 */
 #endif /* _ASM_X86_UV_UV_HUB_H */
diff --git a/arch/x86/include/asm/uv/uv_mmrs.h b/arch/x86/include/asm/uv/uv_mmrs.h
index dd627793a234..db68ac8a5ac2 100644
--- a/arch/x86/include/asm/uv/uv_mmrs.h
+++ b/arch/x86/include/asm/uv/uv_mmrs.h
@@ -1,3 +1,4 @@
+
 /*
  * This file is subject to the terms and conditions of the GNU General Public
  * License.  See the file "COPYING" in the main directory of this archive
@@ -243,6 +244,158 @@ union uvh_event_occurred0_u {
 #define UVH_EVENT_OCCURRED0_ALIAS_32 0x005f0
 
 /* ========================================================================= */
+/*                         UVH_GR0_TLB_INT0_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR0_TLB_INT0_CONFIG 0x61b00UL
+
+#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_GR0_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR0_TLB_INT0_CONFIG_DM_SHFT 8
+#define UVH_GR0_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR0_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR0_TLB_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_GR0_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR0_TLB_INT0_CONFIG_P_SHFT 13
+#define UVH_GR0_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR0_TLB_INT0_CONFIG_T_SHFT 15
+#define UVH_GR0_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR0_TLB_INT0_CONFIG_M_SHFT 16
+#define UVH_GR0_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR0_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr0_tlb_int0_config_u {
+    unsigned long	v;
+    struct uvh_gr0_tlb_int0_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR0_TLB_INT1_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR0_TLB_INT1_CONFIG 0x61b40UL
+
+#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_SHFT 0
+#define UVH_GR0_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR0_TLB_INT1_CONFIG_DM_SHFT 8
+#define UVH_GR0_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR0_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR0_TLB_INT1_CONFIG_STATUS_SHFT 12
+#define UVH_GR0_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR0_TLB_INT1_CONFIG_P_SHFT 13
+#define UVH_GR0_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR0_TLB_INT1_CONFIG_T_SHFT 15
+#define UVH_GR0_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR0_TLB_INT1_CONFIG_M_SHFT 16
+#define UVH_GR0_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR0_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr0_tlb_int1_config_u {
+    unsigned long	v;
+    struct uvh_gr0_tlb_int1_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR1_TLB_INT0_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR1_TLB_INT0_CONFIG 0x61f00UL
+
+#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_SHFT 0
+#define UVH_GR1_TLB_INT0_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR1_TLB_INT0_CONFIG_DM_SHFT 8
+#define UVH_GR1_TLB_INT0_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR1_TLB_INT0_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR1_TLB_INT0_CONFIG_STATUS_SHFT 12
+#define UVH_GR1_TLB_INT0_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR1_TLB_INT0_CONFIG_P_SHFT 13
+#define UVH_GR1_TLB_INT0_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR1_TLB_INT0_CONFIG_T_SHFT 15
+#define UVH_GR1_TLB_INT0_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR1_TLB_INT0_CONFIG_M_SHFT 16
+#define UVH_GR1_TLB_INT0_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR1_TLB_INT0_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr1_tlb_int0_config_u {
+    unsigned long	v;
+    struct uvh_gr1_tlb_int0_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
+/*                         UVH_GR1_TLB_INT1_CONFIG                           */
+/* ========================================================================= */
+#define UVH_GR1_TLB_INT1_CONFIG 0x61f40UL
+
+#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_SHFT 0
+#define UVH_GR1_TLB_INT1_CONFIG_VECTOR_MASK 0x00000000000000ffUL
+#define UVH_GR1_TLB_INT1_CONFIG_DM_SHFT 8
+#define UVH_GR1_TLB_INT1_CONFIG_DM_MASK 0x0000000000000700UL
+#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_SHFT 11
+#define UVH_GR1_TLB_INT1_CONFIG_DESTMODE_MASK 0x0000000000000800UL
+#define UVH_GR1_TLB_INT1_CONFIG_STATUS_SHFT 12
+#define UVH_GR1_TLB_INT1_CONFIG_STATUS_MASK 0x0000000000001000UL
+#define UVH_GR1_TLB_INT1_CONFIG_P_SHFT 13
+#define UVH_GR1_TLB_INT1_CONFIG_P_MASK 0x0000000000002000UL
+#define UVH_GR1_TLB_INT1_CONFIG_T_SHFT 15
+#define UVH_GR1_TLB_INT1_CONFIG_T_MASK 0x0000000000008000UL
+#define UVH_GR1_TLB_INT1_CONFIG_M_SHFT 16
+#define UVH_GR1_TLB_INT1_CONFIG_M_MASK 0x0000000000010000UL
+#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_SHFT 32
+#define UVH_GR1_TLB_INT1_CONFIG_APIC_ID_MASK 0xffffffff00000000UL
+
+union uvh_gr1_tlb_int1_config_u {
+    unsigned long	v;
+    struct uvh_gr1_tlb_int1_config_s {
+	unsigned long	vector_  :  8;  /* RW */
+	unsigned long	dm       :  3;  /* RW */
+	unsigned long	destmode :  1;  /* RW */
+	unsigned long	status   :  1;  /* RO */
+	unsigned long	p        :  1;  /* RO */
+	unsigned long	rsvd_14  :  1;  /*    */
+	unsigned long	t        :  1;  /* RO */
+	unsigned long	m        :  1;  /* RW */
+	unsigned long	rsvd_17_31: 15;  /*    */
+	unsigned long	apic_id  : 32;  /* RW */
+    } s;
+};
+
+/* ========================================================================= */
 /*                               UVH_INT_CMPB                                */
 /* ========================================================================= */
 #define UVH_INT_CMPB 0x22080UL
diff --git a/arch/x86/kernel/amd_iommu.c b/arch/x86/kernel/amd_iommu.c
index c5962fe3796f..a97db99dad52 100644
--- a/arch/x86/kernel/amd_iommu.c
+++ b/arch/x86/kernel/amd_iommu.c
@@ -1928,6 +1928,12 @@ static phys_addr_t amd_iommu_iova_to_phys(struct iommu_domain *dom,
 	return paddr;
 }
 
+static int amd_iommu_domain_has_cap(struct iommu_domain *domain,
+				    unsigned long cap)
+{
+	return 0;
+}
+
 static struct iommu_ops amd_iommu_ops = {
 	.domain_init = amd_iommu_domain_init,
 	.domain_destroy = amd_iommu_domain_destroy,
@@ -1936,5 +1942,6 @@ static struct iommu_ops amd_iommu_ops = {
 	.map = amd_iommu_map_range,
 	.unmap = amd_iommu_unmap_range,
 	.iova_to_phys = amd_iommu_iova_to_phys,
+	.domain_has_cap = amd_iommu_domain_has_cap,
 };
 
diff --git a/arch/x86/kernel/apic/bigsmp_32.c b/arch/x86/kernel/apic/bigsmp_32.c
index d806ecaa948f..676cdac385c0 100644
--- a/arch/x86/kernel/apic/bigsmp_32.c
+++ b/arch/x86/kernel/apic/bigsmp_32.c
@@ -26,12 +26,12 @@ static int bigsmp_apic_id_registered(void)
 	return 1;
 }
 
-static const cpumask_t *bigsmp_target_cpus(void)
+static const struct cpumask *bigsmp_target_cpus(void)
 {
 #ifdef CONFIG_SMP
-	return &cpu_online_map;
+	return cpu_online_mask;
 #else
-	return &cpumask_of_cpu(0);
+	return cpumask_of(0);
 #endif
 }
 
@@ -118,9 +118,9 @@ static int bigsmp_check_phys_apicid_present(int boot_cpu_physical_apicid)
 }
 
 /* As we are using single CPU as destination, pick only one CPU here */
-static unsigned int bigsmp_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int bigsmp_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
-	return bigsmp_cpu_to_logical_apicid(first_cpu(*cpumask));
+	return bigsmp_cpu_to_logical_apicid(cpumask_first(cpumask));
 }
 
 static unsigned int bigsmp_cpu_mask_to_apicid_and(const struct cpumask *cpumask,
@@ -188,10 +188,10 @@ static const struct dmi_system_id bigsmp_dmi_table[] = {
 	{ } /* NULL entry stops DMI scanning */
 };
 
-static void bigsmp_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void bigsmp_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
-	cpus_clear(*retmask);
-	cpu_set(cpu, *retmask);
+	cpumask_clear(retmask);
+	cpumask_set_cpu(cpu, retmask);
 }
 
 static int probe_bigsmp(void)
diff --git a/arch/x86/kernel/apic/es7000_32.c b/arch/x86/kernel/apic/es7000_32.c
index 19588f2770ee..1c11b819f245 100644
--- a/arch/x86/kernel/apic/es7000_32.c
+++ b/arch/x86/kernel/apic/es7000_32.c
@@ -410,7 +410,7 @@ static void es7000_enable_apic_mode(void)
 		WARN(1, "Command failed, status = %x\n", mip_status);
 }
 
-static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void es7000_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -420,7 +420,8 @@ static void es7000_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 
@@ -455,14 +456,14 @@ static int es7000_apic_id_registered(void)
 	return 1;
 }
 
-static const cpumask_t *target_cpus_cluster(void)
+static const struct cpumask *target_cpus_cluster(void)
 {
-	return &CPU_MASK_ALL;
+	return cpu_all_mask;
 }
 
-static const cpumask_t *es7000_target_cpus(void)
+static const struct cpumask *es7000_target_cpus(void)
 {
-	return &cpumask_of_cpu(smp_processor_id());
+	return cpumask_of(smp_processor_id());
 }
 
 static unsigned long
@@ -517,7 +518,7 @@ static void es7000_setup_apic_routing(void)
 	  "Enabling APIC mode:  %s. Using %d I/O APICs, target cpus %lx\n",
 		(apic_version[apic] == 0x14) ?
 			"Physical Cluster" : "Logical Cluster",
-		nr_ioapics, cpus_addr(*es7000_target_cpus())[0]);
+		nr_ioapics, cpumask_bits(es7000_target_cpus())[0]);
 }
 
 static int es7000_apicid_to_node(int logical_apicid)
@@ -572,7 +573,7 @@ static int es7000_check_phys_apicid_present(int cpu_physical_apicid)
 	return 1;
 }
 
-static unsigned int es7000_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int es7000_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	unsigned int round = 0;
 	int cpu, uninitialized_var(apicid);
diff --git a/arch/x86/kernel/apic/nmi.c b/arch/x86/kernel/apic/nmi.c
index bdfad80c3cf1..d6bd62407152 100644
--- a/arch/x86/kernel/apic/nmi.c
+++ b/arch/x86/kernel/apic/nmi.c
@@ -39,7 +39,7 @@
 int unknown_nmi_panic;
 int nmi_watchdog_enabled;
 
-static cpumask_t backtrace_mask = CPU_MASK_NONE;
+static cpumask_var_t backtrace_mask;
 
 /* nmi_active:
  * >0: the lapic NMI watchdog is active, but can be disabled
@@ -138,6 +138,7 @@ int __init check_nmi_watchdog(void)
 	if (!prev_nmi_count)
 		goto error;
 
+	alloc_cpumask_var(&backtrace_mask, GFP_KERNEL);
 	printk(KERN_INFO "Testing NMI watchdog ... ");
 
 #ifdef CONFIG_SMP
@@ -413,14 +414,14 @@ nmi_watchdog_tick(struct pt_regs *regs, unsigned reason)
 		touched = 1;
 	}
 
-	if (cpu_isset(cpu, backtrace_mask)) {
+	if (cpumask_test_cpu(cpu, backtrace_mask)) {
 		static DEFINE_SPINLOCK(lock);	/* Serialise the printks */
 
 		spin_lock(&lock);
 		printk(KERN_WARNING "NMI backtrace for cpu %d\n", cpu);
 		dump_stack();
 		spin_unlock(&lock);
-		cpu_clear(cpu, backtrace_mask);
+		cpumask_clear_cpu(cpu, backtrace_mask);
 	}
 
 	/* Could check oops_in_progress here too, but it's safer not to */
@@ -554,10 +555,10 @@ void __trigger_all_cpu_backtrace(void)
 {
 	int i;
 
-	backtrace_mask = cpu_online_map;
+	cpumask_copy(backtrace_mask, cpu_online_mask);
 	/* Wait for up to 10 seconds for all CPUs to do the backtrace */
 	for (i = 0; i < 10 * 1000; i++) {
-		if (cpus_empty(backtrace_mask))
+		if (cpumask_empty(backtrace_mask))
 			break;
 		mdelay(1);
 	}
diff --git a/arch/x86/kernel/apic/numaq_32.c b/arch/x86/kernel/apic/numaq_32.c
index ba2fc6465534..533e59c6fc82 100644
--- a/arch/x86/kernel/apic/numaq_32.c
+++ b/arch/x86/kernel/apic/numaq_32.c
@@ -334,9 +334,9 @@ static inline void numaq_smp_callin_clear_local_apic(void)
 	clear_local_APIC();
 }
 
-static inline const cpumask_t *numaq_target_cpus(void)
+static inline const struct cpumask *numaq_target_cpus(void)
 {
-	return &CPU_MASK_ALL;
+	return cpu_all_mask;
 }
 
 static inline unsigned long
@@ -427,7 +427,7 @@ static inline int numaq_check_phys_apicid_present(int boot_cpu_physical_apicid)
  * We use physical apicids here, not logical, so just return the default
  * physical broadcast to stop people from breaking us
  */
-static inline unsigned int numaq_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int numaq_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	return 0x0F;
 }
@@ -462,7 +462,7 @@ static int probe_numaq(void)
 	return found_numaq;
 }
 
-static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void numaq_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -472,7 +472,8 @@ static void numaq_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 static void numaq_setup_portio_remap(void)
diff --git a/arch/x86/kernel/apic/probe_32.c b/arch/x86/kernel/apic/probe_32.c
index 141c99a1c264..01eda2ac65e4 100644
--- a/arch/x86/kernel/apic/probe_32.c
+++ b/arch/x86/kernel/apic/probe_32.c
@@ -83,7 +83,8 @@ static void default_vector_allocation_domain(int cpu, struct cpumask *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t) { { [0] = APIC_ALL_CPUS } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 /* should be called last. */
diff --git a/arch/x86/kernel/apic/summit_32.c b/arch/x86/kernel/apic/summit_32.c
index aac52fa873ff..9cfe1f415d81 100644
--- a/arch/x86/kernel/apic/summit_32.c
+++ b/arch/x86/kernel/apic/summit_32.c
@@ -53,23 +53,19 @@ static unsigned summit_get_apic_id(unsigned long x)
 	return (x >> 24) & 0xFF;
 }
 
-static inline void summit_send_IPI_mask(const cpumask_t *mask, int vector)
+static inline void summit_send_IPI_mask(const struct cpumask *mask, int vector)
 {
 	default_send_IPI_mask_sequence_logical(mask, vector);
 }
 
 static void summit_send_IPI_allbutself(int vector)
 {
-	cpumask_t mask = cpu_online_map;
-	cpu_clear(smp_processor_id(), mask);
-
-	if (!cpus_empty(mask))
-		summit_send_IPI_mask(&mask, vector);
+	default_send_IPI_mask_allbutself_logical(cpu_online_mask, vector);
 }
 
 static void summit_send_IPI_all(int vector)
 {
-	summit_send_IPI_mask(&cpu_online_map, vector);
+	summit_send_IPI_mask(cpu_online_mask, vector);
 }
 
 #include <asm/tsc.h>
@@ -186,13 +182,13 @@ static inline int is_WPEG(struct rio_detail *rio){
 
 #define SUMMIT_APIC_DFR_VALUE	(APIC_DFR_CLUSTER)
 
-static const cpumask_t *summit_target_cpus(void)
+static const struct cpumask *summit_target_cpus(void)
 {
 	/* CPU_MASK_ALL (0xff) has undefined behaviour with
 	 * dest_LowestPrio mode logical clustered apic interrupt routing
 	 * Just start on cpu 0.  IRQ balancing will spread load
 	 */
-	return &cpumask_of_cpu(0);
+	return cpumask_of(0);
 }
 
 static unsigned long summit_check_apicid_used(physid_mask_t bitmap, int apicid)
@@ -289,7 +285,7 @@ static int summit_check_phys_apicid_present(int boot_cpu_physical_apicid)
 	return 1;
 }
 
-static unsigned int summit_cpu_mask_to_apicid(const cpumask_t *cpumask)
+static unsigned int summit_cpu_mask_to_apicid(const struct cpumask *cpumask)
 {
 	unsigned int round = 0;
 	int cpu, apicid = 0;
@@ -346,7 +342,7 @@ static int probe_summit(void)
 	return 0;
 }
 
-static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask)
+static void summit_vector_allocation_domain(int cpu, struct cpumask *retmask)
 {
 	/* Careful. Some cpus do not strictly honor the set of cpus
 	 * specified in the interrupt destination when using lowest
@@ -356,7 +352,8 @@ static void summit_vector_allocation_domain(int cpu, cpumask_t *retmask)
 	 * deliver interrupts to the wrong hyperthread when only one
 	 * hyperthread was specified in the interrupt desitination.
 	 */
-	*retmask = (cpumask_t){ { [0] = APIC_ALL_CPUS, } };
+	cpumask_clear(retmask);
+	cpumask_bits(retmask)[0] = APIC_ALL_CPUS;
 }
 
 #ifdef CONFIG_X86_SUMMIT_NUMA
diff --git a/arch/x86/kernel/apic/x2apic_uv_x.c b/arch/x86/kernel/apic/x2apic_uv_x.c
index 1bd6da1f8fad..1248318436e8 100644
--- a/arch/x86/kernel/apic/x2apic_uv_x.c
+++ b/arch/x86/kernel/apic/x2apic_uv_x.c
@@ -118,17 +118,12 @@ static int uv_wakeup_secondary(int phys_apicid, unsigned long start_rip)
 
 static void uv_send_IPI_one(int cpu, int vector)
 {
-	unsigned long val, apicid;
+	unsigned long apicid;
 	int pnode;
 
 	apicid = per_cpu(x86_cpu_to_apicid, cpu);
 	pnode = uv_apicid_to_pnode(apicid);
-
-	val = (1UL << UVH_IPI_INT_SEND_SHFT) |
-	      (apicid << UVH_IPI_INT_APIC_ID_SHFT) |
-	      (vector << UVH_IPI_INT_VECTOR_SHFT);
-
-	uv_write_global_mmr64(pnode, UVH_IPI_INT, val);
+	uv_hub_send_ipi(pnode, apicid, vector);
 }
 
 static void uv_send_IPI_mask(const struct cpumask *mask, int vector)
diff --git a/arch/x86/kernel/apm_32.c b/arch/x86/kernel/apm_32.c
index ac7783a67432..49e0939bac42 100644
--- a/arch/x86/kernel/apm_32.c
+++ b/arch/x86/kernel/apm_32.c
@@ -466,7 +466,7 @@ static const lookup_t error_table[] = {
  *	@err: APM BIOS return code
  *
  *	Write a meaningful log entry to the kernel log in the event of
- *	an APM error.
+ *	an APM error.  Note that this also handles (negative) kernel errors.
  */
 
 static void apm_error(char *str, int err)
@@ -478,43 +478,14 @@ static void apm_error(char *str, int err)
 			break;
 	if (i < ERROR_COUNT)
 		printk(KERN_NOTICE "apm: %s: %s\n", str, error_table[i].msg);
+	else if (err < 0)
+		printk(KERN_NOTICE "apm: %s: linux error code %i\n", str, err);
 	else
 		printk(KERN_NOTICE "apm: %s: unknown error code %#2.2x\n",
 		       str, err);
 }
 
 /*
- * Lock APM functionality to physical CPU 0
- */
-
-#ifdef CONFIG_SMP
-
-static cpumask_t apm_save_cpus(void)
-{
-	cpumask_t x = current->cpus_allowed;
-	/* Some bioses don't like being called from CPU != 0 */
-	set_cpus_allowed(current, cpumask_of_cpu(0));
-	BUG_ON(smp_processor_id() != 0);
-	return x;
-}
-
-static inline void apm_restore_cpus(cpumask_t mask)
-{
-	set_cpus_allowed(current, mask);
-}
-
-#else
-
-/*
- *	No CPU lockdown needed on a uniprocessor
- */
-
-#define apm_save_cpus()		(current->cpus_allowed)
-#define apm_restore_cpus(x)	(void)(x)
-
-#endif
-
-/*
  * These are the actual BIOS calls.  Depending on APM_ZERO_SEGS and
  * apm_info.allow_ints, we are being really paranoid here!  Not only
  * are interrupts disabled, but all the segment registers (except SS)
@@ -568,16 +539,23 @@ static inline void apm_irq_restore(unsigned long flags)
 #	define APM_DO_RESTORE_SEGS
 #endif
 
+struct apm_bios_call {
+	u32 func;
+	/* In and out */
+	u32 ebx;
+	u32 ecx;
+	/* Out only */
+	u32 eax;
+	u32 edx;
+	u32 esi;
+
+	/* Error: -ENOMEM, or bits 8-15 of eax */
+	int err;
+};
+
 /**
- *	apm_bios_call	-	Make an APM BIOS 32bit call
- *	@func: APM function to execute
- *	@ebx_in: EBX register for call entry
- *	@ecx_in: ECX register for call entry
- *	@eax: EAX register return
- *	@ebx: EBX register return
- *	@ecx: ECX register return
- *	@edx: EDX register return
- *	@esi: ESI register return
+ *	__apm_bios_call - Make an APM BIOS 32bit call
+ *	@_call: pointer to struct apm_bios_call.
  *
  *	Make an APM call using the 32bit protected mode interface. The
  *	caller is responsible for knowing if APM BIOS is configured and
@@ -586,80 +564,142 @@ static inline void apm_irq_restore(unsigned long flags)
  *	flag is loaded into AL.  If there is an error, then the error
  *	code is returned in AH (bits 8-15 of eax) and this function
  *	returns non-zero.
+ *
+ *	Note: this makes the call on the current CPU.
  */
-
-static u8 apm_bios_call(u32 func, u32 ebx_in, u32 ecx_in,
-	u32 *eax, u32 *ebx, u32 *ecx, u32 *edx, u32 *esi)
+static long __apm_bios_call(void *_call)
 {
 	APM_DECL_SEGS
 	unsigned long		flags;
-	cpumask_t		cpus;
 	int			cpu;
 	struct desc_struct	save_desc_40;
 	struct desc_struct	*gdt;
-
-	cpus = apm_save_cpus();
+	struct apm_bios_call	*call = _call;
 
 	cpu = get_cpu();
+	BUG_ON(cpu != 0);
 	gdt = get_cpu_gdt_table(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
 	APM_DO_SAVE_SEGS;
-	apm_bios_call_asm(func, ebx_in, ecx_in, eax, ebx, ecx, edx, esi);
+	apm_bios_call_asm(call->func, call->ebx, call->ecx,
+			  &call->eax, &call->ebx, &call->ecx, &call->edx,
+			  &call->esi);
 	APM_DO_RESTORE_SEGS;
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
-	apm_restore_cpus(cpus);
 
-	return *eax & 0xff;
+	return call->eax & 0xff;
+}
+
+/* Run __apm_bios_call or __apm_bios_call_simple on CPU 0 */
+static int on_cpu0(long (*fn)(void *), struct apm_bios_call *call)
+{
+	int ret;
+
+	/* Don't bother with work_on_cpu in the common case, so we don't
+	 * have to worry about OOM or overhead. */
+	if (get_cpu() == 0) {
+		ret = fn(call);
+		put_cpu();
+	} else {
+		put_cpu();
+		ret = work_on_cpu(0, fn, call);
+	}
+
+	/* work_on_cpu can fail with -ENOMEM */
+	if (ret < 0)
+		call->err = ret;
+	else
+		call->err = (call->eax >> 8) & 0xff;
+
+	return ret;
 }
 
 /**
- *	apm_bios_call_simple	-	make a simple APM BIOS 32bit call
- *	@func: APM function to invoke
- *	@ebx_in: EBX register value for BIOS call
- *	@ecx_in: ECX register value for BIOS call
- *	@eax: EAX register on return from the BIOS call
+ *	apm_bios_call	-	Make an APM BIOS 32bit call (on CPU 0)
+ *	@call: the apm_bios_call registers.
+ *
+ *	If there is an error, it is returned in @call.err.
+ */
+static int apm_bios_call(struct apm_bios_call *call)
+{
+	return on_cpu0(__apm_bios_call, call);
+}
+
+/**
+ *	__apm_bios_call_simple - Make an APM BIOS 32bit call (on CPU 0)
+ *	@_call: pointer to struct apm_bios_call.
  *
  *	Make a BIOS call that returns one value only, or just status.
  *	If there is an error, then the error code is returned in AH
- *	(bits 8-15 of eax) and this function returns non-zero. This is
- *	used for simpler BIOS operations. This call may hold interrupts
- *	off for a long time on some laptops.
+ *	(bits 8-15 of eax) and this function returns non-zero (it can
+ *	also return -ENOMEM). This is used for simpler BIOS operations.
+ *	This call may hold interrupts off for a long time on some laptops.
+ *
+ *	Note: this makes the call on the current CPU.
  */
-
-static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
+static long __apm_bios_call_simple(void *_call)
 {
 	u8			error;
 	APM_DECL_SEGS
 	unsigned long		flags;
-	cpumask_t		cpus;
 	int			cpu;
 	struct desc_struct	save_desc_40;
 	struct desc_struct	*gdt;
-
-	cpus = apm_save_cpus();
+	struct apm_bios_call	*call = _call;
 
 	cpu = get_cpu();
+	BUG_ON(cpu != 0);
 	gdt = get_cpu_gdt_table(cpu);
 	save_desc_40 = gdt[0x40 / 8];
 	gdt[0x40 / 8] = bad_bios_desc;
 
 	apm_irq_save(flags);
 	APM_DO_SAVE_SEGS;
-	error = apm_bios_call_simple_asm(func, ebx_in, ecx_in, eax);
+	error = apm_bios_call_simple_asm(call->func, call->ebx, call->ecx,
+					 &call->eax);
 	APM_DO_RESTORE_SEGS;
 	apm_irq_restore(flags);
 	gdt[0x40 / 8] = save_desc_40;
 	put_cpu();
-	apm_restore_cpus(cpus);
 	return error;
 }
 
 /**
+ *	apm_bios_call_simple	-	make a simple APM BIOS 32bit call
+ *	@func: APM function to invoke
+ *	@ebx_in: EBX register value for BIOS call
+ *	@ecx_in: ECX register value for BIOS call
+ *	@eax: EAX register on return from the BIOS call
+ *	@err: bits
+ *
+ *	Make a BIOS call that returns one value only, or just status.
+ *	If there is an error, then the error code is returned in @err
+ *	and this function returns non-zero. This is used for simpler
+ *	BIOS operations.  This call may hold interrupts off for a long
+ *	time on some laptops.
+ */
+static int apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax,
+				int *err)
+{
+	struct apm_bios_call call;
+	int ret;
+
+	call.func = func;
+	call.ebx = ebx_in;
+	call.ecx = ecx_in;
+
+	ret = on_cpu0(__apm_bios_call_simple, &call);
+	*eax = call.eax;
+	*err = call.err;
+	return ret;
+}
+
+/**
  *	apm_driver_version	-	APM driver version
  *	@val:	loaded with the APM version on return
  *
@@ -678,9 +718,10 @@ static u8 apm_bios_call_simple(u32 func, u32 ebx_in, u32 ecx_in, u32 *eax)
 static int apm_driver_version(u_short *val)
 {
 	u32 eax;
+	int err;
 
-	if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax))
-		return (eax >> 8) & 0xff;
+	if (apm_bios_call_simple(APM_FUNC_VERSION, 0, *val, &eax, &err))
+		return err;
 	*val = eax;
 	return APM_SUCCESS;
 }
@@ -701,22 +742,21 @@ static int apm_driver_version(u_short *val)
  *	that APM 1.2 is in use. If no messges are pending the value 0x80
  *	is returned (No power management events pending).
  */
-
 static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
 {
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 dummy;
+	struct apm_bios_call call;
 
-	if (apm_bios_call(APM_FUNC_GET_EVENT, 0, 0, &eax, &ebx, &ecx,
-			  &dummy, &dummy))
-		return (eax >> 8) & 0xff;
-	*event = ebx;
+	call.func = APM_FUNC_GET_EVENT;
+	call.ebx = call.ecx = 0;
+
+	if (apm_bios_call(&call))
+		return call.err;
+
+	*event = call.ebx;
 	if (apm_info.connection_version < 0x0102)
 		*info = ~0; /* indicate info not valid */
 	else
-		*info = ecx;
+		*info = call.ecx;
 	return APM_SUCCESS;
 }
 
@@ -737,9 +777,10 @@ static int apm_get_event(apm_event_t *event, apm_eventinfo_t *info)
 static int set_power_state(u_short what, u_short state)
 {
 	u32 eax;
+	int err;
 
-	if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax))
-		return (eax >> 8) & 0xff;
+	if (apm_bios_call_simple(APM_FUNC_SET_STATE, what, state, &eax, &err))
+		return err;
 	return APM_SUCCESS;
 }
 
@@ -770,6 +811,7 @@ static int apm_do_idle(void)
 	u8 ret = 0;
 	int idled = 0;
 	int polling;
+	int err;
 
 	polling = !!(current_thread_info()->status & TS_POLLING);
 	if (polling) {
@@ -782,7 +824,7 @@ static int apm_do_idle(void)
 	}
 	if (!need_resched()) {
 		idled = 1;
-		ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax);
+		ret = apm_bios_call_simple(APM_FUNC_IDLE, 0, 0, &eax, &err);
 	}
 	if (polling)
 		current_thread_info()->status |= TS_POLLING;
@@ -797,8 +839,7 @@ static int apm_do_idle(void)
 		 * Only report the failure the first 5 times.
 		 */
 		if (++t < 5) {
-			printk(KERN_DEBUG "apm_do_idle failed (%d)\n",
-			       (eax >> 8) & 0xff);
+			printk(KERN_DEBUG "apm_do_idle failed (%d)\n", err);
 			t = jiffies;
 		}
 		return -1;
@@ -816,9 +857,10 @@ static int apm_do_idle(void)
 static void apm_do_busy(void)
 {
 	u32 dummy;
+	int err;
 
 	if (clock_slowed || ALWAYS_CALL_BUSY) {
-		(void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy);
+		(void)apm_bios_call_simple(APM_FUNC_BUSY, 0, 0, &dummy, &err);
 		clock_slowed = 0;
 	}
 }
@@ -937,7 +979,7 @@ static void apm_power_off(void)
 
 	/* Some bioses don't like being called from CPU != 0 */
 	if (apm_info.realmode_power_off) {
-		(void)apm_save_cpus();
+		set_cpus_allowed_ptr(current, cpumask_of(0));
 		machine_real_restart(po_bios_call, sizeof(po_bios_call));
 	} else {
 		(void)set_system_power_state(APM_STATE_OFF);
@@ -956,12 +998,13 @@ static void apm_power_off(void)
 static int apm_enable_power_management(int enable)
 {
 	u32 eax;
+	int err;
 
 	if ((enable == 0) && (apm_info.bios.flags & APM_BIOS_DISENGAGED))
 		return APM_NOT_ENGAGED;
 	if (apm_bios_call_simple(APM_FUNC_ENABLE_PM, APM_DEVICE_BALL,
-				 enable, &eax))
-		return (eax >> 8) & 0xff;
+				 enable, &eax, &err))
+		return err;
 	if (enable)
 		apm_info.bios.flags &= ~APM_BIOS_DISABLED;
 	else
@@ -986,24 +1029,23 @@ static int apm_enable_power_management(int enable)
 
 static int apm_get_power_status(u_short *status, u_short *bat, u_short *life)
 {
-	u32 eax;
-	u32 ebx;
-	u32 ecx;
-	u32 edx;
-	u32 dummy;
+	struct apm_bios_call call;
+
+	call.func = APM_FUNC_GET_STATUS;
+	call.ebx = APM_DEVICE_ALL;
+	call.ecx = 0;
 
 	if (apm_info.get_power_status_broken)
 		return APM_32_UNSUPPORTED;
-	if (apm_bios_call(APM_FUNC_GET_STATUS, APM_DEVICE_ALL, 0,
-			  &eax, &ebx, &ecx, &edx, &dummy))
-		return (eax >> 8) & 0xff;
-	*status = ebx;
-	*bat = ecx;
+	if (apm_bios_call(&call))
+		return call.err;
+	*status = call.ebx;
+	*bat = call.ecx;
 	if (apm_info.get_power_status_swabinminutes) {
-		*life = swab16((u16)edx);
+		*life = swab16((u16)call.edx);
 		*life |= 0x8000;
 	} else
-		*life = edx;
+		*life = call.edx;
 	return APM_SUCCESS;
 }
 
@@ -1048,12 +1090,14 @@ static int apm_get_battery_status(u_short which, u_short *status,
 static int apm_engage_power_management(u_short device, int enable)
 {
 	u32 eax;
+	int err;
 
 	if ((enable == 0) && (device == APM_DEVICE_ALL)
 	    && (apm_info.bios.flags & APM_BIOS_DISABLED))
 		return APM_DISABLED;
-	if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable, &eax))
-		return (eax >> 8) & 0xff;
+	if (apm_bios_call_simple(APM_FUNC_ENGAGE_PM, device, enable,
+				 &eax, &err))
+		return err;
 	if (device == APM_DEVICE_ALL) {
 		if (enable)
 			apm_info.bios.flags &= ~APM_BIOS_DISENGAGED;
@@ -1689,16 +1733,14 @@ static int apm(void *unused)
 	char 		*power_stat;
 	char 		*bat_stat;
 
-#ifdef CONFIG_SMP
 	/* 2002/08/01 - WT
 	 * This is to avoid random crashes at boot time during initialization
 	 * on SMP systems in case of "apm=power-off" mode. Seen on ASUS A7M266D.
 	 * Some bioses don't like being called from CPU != 0.
 	 * Method suggested by Ingo Molnar.
 	 */
-	set_cpus_allowed(current, cpumask_of_cpu(0));
+	set_cpus_allowed_ptr(current, cpumask_of(0));
 	BUG_ON(smp_processor_id() != 0);
-#endif
 
 	if (apm_info.connection_version == 0) {
 		apm_info.connection_version = apm_info.bios.version;
diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c
index e2962cc1e27b..c4f667896c28 100644
--- a/arch/x86/kernel/cpu/common.c
+++ b/arch/x86/kernel/cpu/common.c
@@ -41,8 +41,6 @@
 
 #include "cpu.h"
 
-#ifdef CONFIG_X86_64
-
 /* all of these masks are initialized in setup_cpu_local_masks() */
 cpumask_var_t cpu_initialized_mask;
 cpumask_var_t cpu_callout_mask;
@@ -60,16 +58,6 @@ void __init setup_cpu_local_masks(void)
 	alloc_bootmem_cpumask_var(&cpu_sibling_setup_mask);
 }
 
-#else /* CONFIG_X86_32 */
-
-cpumask_t cpu_sibling_setup_map;
-cpumask_t cpu_callout_map;
-cpumask_t cpu_initialized;
-cpumask_t cpu_callin_map;
-
-#endif /* CONFIG_X86_32 */
-
-
 static const struct cpu_dev *this_cpu __cpuinitdata;
 
 DEFINE_PER_CPU_PAGE_ALIGNED(struct gdt_page, gdt_page) = { .gdt = {
@@ -859,6 +847,7 @@ static void vgetcpu_set_mode(void)
 void __init identify_boot_cpu(void)
 {
 	identify_cpu(&boot_cpu_data);
+	init_c1e_mask();
 #ifdef CONFIG_X86_32
 	sysenter_setup();
 	enable_sep_cpu();
diff --git a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
index 41ed94915f97..6ac55bd341ae 100644
--- a/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
+++ b/arch/x86/kernel/cpu/cpufreq/p4-clockmod.c
@@ -211,7 +211,7 @@ static int cpufreq_p4_cpu_init(struct cpufreq_policy *policy)
 	unsigned int i;
 
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	/* Errata workaround */
diff --git a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
index a15ac94e0b9b..4709ead2db52 100644
--- a/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
+++ b/arch/x86/kernel/cpu/cpufreq/powernow-k8.c
@@ -54,7 +54,10 @@ static DEFINE_PER_CPU(struct powernow_k8_data *, powernow_data);
 static int cpu_family = CPU_OPTERON;
 
 #ifndef CONFIG_SMP
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+static inline const struct cpumask *cpu_core_mask(int cpu)
+{
+	return cpumask_of(0);
+}
 #endif
 
 /* Return a frequency in MHz, given an input fid */
@@ -699,7 +702,7 @@ static int fill_powernow_table(struct powernow_k8_data *data,
 
 	dprintk("cfid 0x%x, cvid 0x%x\n", data->currfid, data->currvid);
 	data->powernow_table = powernow_table;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 
 	for (j = 0; j < data->numps; j++)
@@ -862,7 +865,7 @@ static int powernow_k8_cpu_init_acpi(struct powernow_k8_data *data)
 
 	/* fill in data */
 	data->numps = data->acpi_data.state_count;
-	if (first_cpu(per_cpu(cpu_core_map, data->cpu)) == data->cpu)
+	if (cpumask_first(cpu_core_mask(data->cpu)) == data->cpu)
 		print_basics(data);
 	powernow_k8_acpi_pst_values(data, 0);
 
@@ -1300,7 +1303,7 @@ static int __cpuinit powernowk8_cpu_init(struct cpufreq_policy *pol)
 	if (cpu_family == CPU_HW_PSTATE)
 		cpumask_copy(pol->cpus, cpumask_of(pol->cpu));
 	else
-		cpumask_copy(pol->cpus, &per_cpu(cpu_core_map, pol->cpu));
+		cpumask_copy(pol->cpus, cpu_core_mask(pol->cpu));
 	data->available_cores = pol->cpus;
 
 	if (cpu_family == CPU_HW_PSTATE)
@@ -1365,7 +1368,7 @@ static unsigned int powernowk8_get(unsigned int cpu)
 	unsigned int khz = 0;
 	unsigned int first;
 
-	first = first_cpu(per_cpu(cpu_core_map, cpu));
+	first = cpumask_first(cpu_core_mask(cpu));
 	data = per_cpu(powernow_data, first);
 
 	if (!data)
diff --git a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
index 8bbb11adb315..016c1a4fa3fc 100644
--- a/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
+++ b/arch/x86/kernel/cpu/cpufreq/speedstep-ich.c
@@ -321,7 +321,7 @@ static int speedstep_cpu_init(struct cpufreq_policy *policy)
 
 	/* only run on CPU to be set, or on its sibling */
 #ifdef CONFIG_SMP
-	cpumask_copy(policy->cpus, &per_cpu(cpu_sibling_map, policy->cpu));
+	cpumask_copy(policy->cpus, cpu_sibling_mask(policy->cpu));
 #endif
 
 	cpus_allowed = current->cpus_allowed;
diff --git a/arch/x86/kernel/cpu/intel_cacheinfo.c b/arch/x86/kernel/cpu/intel_cacheinfo.c
index c471eb1a389c..483eda96e102 100644
--- a/arch/x86/kernel/cpu/intel_cacheinfo.c
+++ b/arch/x86/kernel/cpu/intel_cacheinfo.c
@@ -159,7 +159,7 @@ struct _cpuid4_info_regs {
 	unsigned long can_disable;
 };
 
-#ifdef CONFIG_PCI
+#if defined(CONFIG_PCI) && defined(CONFIG_SYSFS)
 static struct pci_device_id k8_nb_id[] = {
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1103) },
 	{ PCI_DEVICE(PCI_VENDOR_ID_AMD, 0x1203) },
@@ -324,15 +324,6 @@ __cpuinit cpuid4_cache_lookup_regs(int index,
 	return 0;
 }
 
-static int
-__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
-{
-	struct _cpuid4_info_regs *leaf_regs =
-		(struct _cpuid4_info_regs *)this_leaf;
-
-	return cpuid4_cache_lookup_regs(index, leaf_regs);
-}
-
 static int __cpuinit find_num_cache_leaves(void)
 {
 	unsigned int		eax, ebx, ecx, edx;
@@ -508,6 +499,8 @@ unsigned int __cpuinit init_intel_cacheinfo(struct cpuinfo_x86 *c)
 	return l2;
 }
 
+#ifdef CONFIG_SYSFS
+
 /* pointer to _cpuid4_info array (for each cache leaf) */
 static DEFINE_PER_CPU(struct _cpuid4_info *, cpuid4_info);
 #define CPUID4_INFO_IDX(x, y)	(&((per_cpu(cpuid4_info, x))[y]))
@@ -571,6 +564,15 @@ static void __cpuinit free_cache_attributes(unsigned int cpu)
 	per_cpu(cpuid4_info, cpu) = NULL;
 }
 
+static int
+__cpuinit cpuid4_cache_lookup(int index, struct _cpuid4_info *this_leaf)
+{
+	struct _cpuid4_info_regs *leaf_regs =
+		(struct _cpuid4_info_regs *)this_leaf;
+
+	return cpuid4_cache_lookup_regs(index, leaf_regs);
+}
+
 static void __cpuinit get_cpu_leaves(void *_retval)
 {
 	int j, *retval = _retval, cpu = smp_processor_id();
@@ -612,8 +614,6 @@ static int __cpuinit detect_cache_attributes(unsigned int cpu)
 	return retval;
 }
 
-#ifdef CONFIG_SYSFS
-
 #include <linux/kobject.h>
 #include <linux/sysfs.h>
 
diff --git a/arch/x86/kernel/cpu/mcheck/mce_64.c b/arch/x86/kernel/cpu/mcheck/mce_64.c
index ca14604611ec..863f89568b1a 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_64.c
@@ -990,7 +990,7 @@ static struct sysdev_attribute *mce_attributes[] = {
 	NULL
 };
 
-static cpumask_t mce_device_initialized = CPU_MASK_NONE;
+static cpumask_var_t mce_device_initialized;
 
 /* Per cpu sysdev init.  All of the cpus still share the same ctl bank */
 static __cpuinit int mce_create_device(unsigned int cpu)
@@ -1021,7 +1021,7 @@ static __cpuinit int mce_create_device(unsigned int cpu)
 		if (err)
 			goto error2;
 	}
-	cpu_set(cpu, mce_device_initialized);
+	cpumask_set_cpu(cpu, mce_device_initialized);
 
 	return 0;
 error2:
@@ -1043,7 +1043,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 {
 	int i;
 
-	if (!cpu_isset(cpu, mce_device_initialized))
+	if (!cpumask_test_cpu(cpu, mce_device_initialized))
 		return;
 
 	for (i = 0; mce_attributes[i]; i++)
@@ -1053,7 +1053,7 @@ static __cpuinit void mce_remove_device(unsigned int cpu)
 		sysdev_remove_file(&per_cpu(device_mce, cpu),
 			&bank_attrs[i]);
 	sysdev_unregister(&per_cpu(device_mce,cpu));
-	cpu_clear(cpu, mce_device_initialized);
+	cpumask_clear_cpu(cpu, mce_device_initialized);
 }
 
 /* Make sure there are no machine checks on offlined CPUs. */
@@ -1162,6 +1162,8 @@ static __init int mce_init_device(void)
 	if (!mce_available(&boot_cpu_data))
 		return -EIO;
 
+	alloc_cpumask_var(&mce_device_initialized, GFP_KERNEL);
+
 	err = mce_init_banks();
 	if (err)
 		return err;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
index 7d01be868870..56dde9c4bc96 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_amd_64.c
@@ -485,7 +485,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 
 #ifdef CONFIG_SMP
 	if (cpu_data(cpu).cpu_core_id && shared_bank[bank]) {	/* symlink */
-		i = cpumask_first(&per_cpu(cpu_core_map, cpu));
+		i = cpumask_first(cpu_core_mask(cpu));
 
 		/* first core not up yet */
 		if (cpu_data(i).cpu_core_id)
@@ -505,7 +505,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 		if (err)
 			goto out;
 
-		cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+		cpumask_copy(b->cpus, cpu_core_mask(cpu));
 		per_cpu(threshold_banks, cpu)[bank] = b;
 		goto out;
 	}
@@ -529,7 +529,7 @@ static __cpuinit int threshold_create_bank(unsigned int cpu, unsigned int bank)
 #ifndef CONFIG_SMP
 	cpumask_setall(b->cpus);
 #else
-	cpumask_copy(b->cpus, &per_cpu(cpu_core_map, cpu));
+	cpumask_copy(b->cpus, cpu_core_mask(cpu));
 #endif
 
 	per_cpu(threshold_banks, cpu)[bank] = b;
diff --git a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
index 57df3d383470..d6b72df89d69 100644
--- a/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
+++ b/arch/x86/kernel/cpu/mcheck/mce_intel_64.c
@@ -249,7 +249,7 @@ void cmci_rediscover(int dying)
 	for_each_online_cpu (cpu) {
 		if (cpu == dying)
 			continue;
-		if (set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu)))
+		if (set_cpus_allowed_ptr(current, cpumask_of(cpu)))
 			continue;
 		/* Recheck banks in case CPUs don't all have the same */
 		if (cmci_supported(&banks))
diff --git a/arch/x86/kernel/cpu/mtrr/generic.c b/arch/x86/kernel/cpu/mtrr/generic.c
index 37f28fc7cf95..0b776c09aff3 100644
--- a/arch/x86/kernel/cpu/mtrr/generic.c
+++ b/arch/x86/kernel/cpu/mtrr/generic.c
@@ -462,9 +462,6 @@ static void generic_get_mtrr(unsigned int reg, unsigned long *base,
 	*base = base_hi << (32 - PAGE_SHIFT) | base_lo >> PAGE_SHIFT;
 	*type = base_lo & 0xff;
 
-	printk(KERN_DEBUG "  get_mtrr: cpu%d reg%02d base=%010lx size=%010lx %s\n",
-			cpu, reg, *base, *size,
-			mtrr_attrib_to_str(*type & 0xff));
 out_put_cpu:
 	put_cpu();
 }
diff --git a/arch/x86/kernel/cpu/proc.c b/arch/x86/kernel/cpu/proc.c
index d67e0e48bc2d..f93047fed791 100644
--- a/arch/x86/kernel/cpu/proc.c
+++ b/arch/x86/kernel/cpu/proc.c
@@ -14,7 +14,7 @@ static void show_cpuinfo_core(struct seq_file *m, struct cpuinfo_x86 *c,
 	if (c->x86_max_cores * smp_num_siblings > 1) {
 		seq_printf(m, "physical id\t: %d\n", c->phys_proc_id);
 		seq_printf(m, "siblings\t: %d\n",
-			   cpus_weight(per_cpu(cpu_core_map, cpu)));
+			   cpumask_weight(cpu_sibling_mask(cpu)));
 		seq_printf(m, "core id\t\t: %d\n", c->cpu_core_id);
 		seq_printf(m, "cpu cores\t: %d\n", c->booted_cores);
 		seq_printf(m, "apicid\t\t: %d\n", c->apicid);
@@ -143,9 +143,9 @@ static int show_cpuinfo(struct seq_file *m, void *v)
 static void *c_start(struct seq_file *m, loff_t *pos)
 {
 	if (*pos == 0)	/* just in case, cpu 0 is not the first */
-		*pos = first_cpu(cpu_online_map);
+		*pos = cpumask_first(cpu_online_mask);
 	else
-		*pos = next_cpu_nr(*pos - 1, cpu_online_map);
+		*pos = cpumask_next(*pos - 1, cpu_online_mask);
 	if ((*pos) < nr_cpu_ids)
 		return &cpu_data(*pos);
 	return NULL;
diff --git a/arch/x86/kernel/microcode_amd.c b/arch/x86/kernel/microcode_amd.c
index c25fdb382292..453b5795a5c6 100644
--- a/arch/x86/kernel/microcode_amd.c
+++ b/arch/x86/kernel/microcode_amd.c
@@ -12,31 +12,30 @@
  *
  *  Licensed under the terms of the GNU General Public
  *  License version 2. See file COPYING for details.
-*/
-
+ */
+#include <linux/platform_device.h>
 #include <linux/capability.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
-#include <linux/cpumask.h>
-#include <linux/module.h>
-#include <linux/slab.h>
-#include <linux/vmalloc.h>
 #include <linux/miscdevice.h>
+#include <linux/firmware.h>
 #include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
+#include <linux/cpumask.h>
+#include <linux/pci_ids.h>
+#include <linux/uaccess.h>
+#include <linux/vmalloc.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/firmware.h>
-#include <linux/platform_device.h>
 #include <linux/pci.h>
-#include <linux/pci_ids.h>
-#include <linux/uaccess.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 
-#include <asm/msr.h>
-#include <asm/processor.h>
 #include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
 
 MODULE_DESCRIPTION("AMD Microcode Update Driver");
 MODULE_AUTHOR("Peter Oruba");
@@ -72,8 +71,8 @@ struct microcode_header_amd {
 } __attribute__((packed));
 
 struct microcode_amd {
-	struct microcode_header_amd hdr;
-	unsigned int mpb[0];
+	struct microcode_header_amd	hdr;
+	unsigned int			mpb[0];
 };
 
 #define UCODE_MAX_SIZE			2048
@@ -184,8 +183,8 @@ static int get_ucode_data(void *to, const u8 *from, size_t n)
 	return 0;
 }
 
-static void *get_next_ucode(const u8 *buf, unsigned int size,
-			    unsigned int *mc_size)
+static void *
+get_next_ucode(const u8 *buf, unsigned int size, unsigned int *mc_size)
 {
 	unsigned int total_size;
 	u8 section_hdr[UCODE_CONTAINER_SECTION_HDR];
@@ -223,7 +222,6 @@ static void *get_next_ucode(const u8 *buf, unsigned int size,
 	return mc;
 }
 
-
 static int install_equiv_cpu_table(const u8 *buf)
 {
 	u8 *container_hdr[UCODE_CONTAINER_HEADER_SIZE];
@@ -372,4 +370,3 @@ struct microcode_ops * __init init_amd_microcode(void)
 {
 	return &microcode_amd_ops;
 }
-
diff --git a/arch/x86/kernel/microcode_core.c b/arch/x86/kernel/microcode_core.c
index c9b721ba968c..a0f3851ef310 100644
--- a/arch/x86/kernel/microcode_core.c
+++ b/arch/x86/kernel/microcode_core.c
@@ -70,67 +70,78 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
+#include <linux/platform_device.h>
 #include <linux/capability.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/miscdevice.h>
+#include <linux/firmware.h>
 #include <linux/smp_lock.h>
+#include <linux/spinlock.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
-#include <linux/slab.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
-#include <linux/miscdevice.h>
-#include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/firmware.h>
-#include <linux/platform_device.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 
-#include <asm/msr.h>
-#include <asm/uaccess.h>
-#include <asm/processor.h>
 #include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
 
 MODULE_DESCRIPTION("Microcode Update Driver");
 MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
 MODULE_LICENSE("GPL");
 
-#define MICROCODE_VERSION 	"2.00"
+#define MICROCODE_VERSION	"2.00"
 
-static struct microcode_ops *microcode_ops;
+static struct microcode_ops	*microcode_ops;
 
 /* no concurrent ->write()s are allowed on /dev/cpu/microcode */
 static DEFINE_MUTEX(microcode_mutex);
 
-struct ucode_cpu_info ucode_cpu_info[NR_CPUS];
+struct ucode_cpu_info		ucode_cpu_info[NR_CPUS];
 EXPORT_SYMBOL_GPL(ucode_cpu_info);
 
 #ifdef CONFIG_MICROCODE_OLD_INTERFACE
+struct update_for_cpu {
+	const void __user	*buf;
+	size_t			size;
+};
+
+static long update_for_cpu(void *_ufc)
+{
+	struct update_for_cpu *ufc = _ufc;
+	int error;
+
+	error = microcode_ops->request_microcode_user(smp_processor_id(),
+						      ufc->buf, ufc->size);
+	if (error < 0)
+		return error;
+	if (!error)
+		microcode_ops->apply_microcode(smp_processor_id());
+	return error;
+}
+
 static int do_microcode_update(const void __user *buf, size_t size)
 {
-	cpumask_t old;
 	int error = 0;
 	int cpu;
-
-	old = current->cpus_allowed;
+	struct update_for_cpu ufc = { .buf = buf, .size = size };
 
 	for_each_online_cpu(cpu) {
 		struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
 
 		if (!uci->valid)
 			continue;
-
-		set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-		error = microcode_ops->request_microcode_user(cpu, buf, size);
+		error = work_on_cpu(cpu, update_for_cpu, &ufc);
 		if (error < 0)
-			goto out;
-		if (!error)
-			microcode_ops->apply_microcode(cpu);
+			break;
 	}
-out:
-	set_cpus_allowed_ptr(current, &old);
 	return error;
 }
 
@@ -198,18 +209,33 @@ static void microcode_dev_exit(void)
 
 MODULE_ALIAS_MISCDEV(MICROCODE_MINOR);
 #else
-#define microcode_dev_init() 0
-#define microcode_dev_exit() do { } while (0)
+#define microcode_dev_init()	0
+#define microcode_dev_exit()	do { } while (0)
 #endif
 
 /* fake device for request_firmware */
-static struct platform_device *microcode_pdev;
+static struct platform_device	*microcode_pdev;
+
+static long reload_for_cpu(void *unused)
+{
+	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
+	int err = 0;
+
+	mutex_lock(&microcode_mutex);
+	if (uci->valid) {
+		err = microcode_ops->request_microcode_fw(smp_processor_id(),
+							  &microcode_pdev->dev);
+		if (!err)
+			microcode_ops->apply_microcode(smp_processor_id());
+	}
+	mutex_unlock(&microcode_mutex);
+	return err;
+}
 
 static ssize_t reload_store(struct sys_device *dev,
 			    struct sysdev_attribute *attr,
 			    const char *buf, size_t sz)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + dev->id;
 	char *end;
 	unsigned long val = simple_strtoul(buf, &end, 0);
 	int err = 0;
@@ -218,21 +244,9 @@ static ssize_t reload_store(struct sys_device *dev,
 	if (end == buf)
 		return -EINVAL;
 	if (val == 1) {
-		cpumask_t old = current->cpus_allowed;
-
 		get_online_cpus();
-		if (cpu_online(cpu)) {
-			set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-			mutex_lock(&microcode_mutex);
-			if (uci->valid) {
-				err = microcode_ops->request_microcode_fw(cpu,
-						&microcode_pdev->dev);
-				if (!err)
-					microcode_ops->apply_microcode(cpu);
-			}
-			mutex_unlock(&microcode_mutex);
-			set_cpus_allowed_ptr(current, &old);
-		}
+		if (cpu_online(cpu))
+			err = work_on_cpu(cpu, reload_for_cpu, NULL);
 		put_online_cpus();
 	}
 	if (err)
@@ -268,8 +282,8 @@ static struct attribute *mc_default_attrs[] = {
 };
 
 static struct attribute_group mc_attr_group = {
-	.attrs = mc_default_attrs,
-	.name = "microcode",
+	.attrs		= mc_default_attrs,
+	.name		= "microcode",
 };
 
 static void __microcode_fini_cpu(int cpu)
@@ -328,9 +342,9 @@ static int microcode_resume_cpu(int cpu)
 	return 0;
 }
 
-static void microcode_update_cpu(int cpu)
+static long microcode_update_cpu(void *unused)
 {
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
+	struct ucode_cpu_info *uci = ucode_cpu_info + smp_processor_id();
 	int err = 0;
 
 	/*
@@ -338,30 +352,27 @@ static void microcode_update_cpu(int cpu)
 	 * otherwise just request a firmware:
 	 */
 	if (uci->valid) {
-		err = microcode_resume_cpu(cpu);
-	} else {	
-		collect_cpu_info(cpu);
+		err = microcode_resume_cpu(smp_processor_id());
+	} else {
+		collect_cpu_info(smp_processor_id());
 		if (uci->valid && system_state == SYSTEM_RUNNING)
-			err = microcode_ops->request_microcode_fw(cpu,
+			err = microcode_ops->request_microcode_fw(
+					smp_processor_id(),
 					&microcode_pdev->dev);
 	}
 	if (!err)
-		microcode_ops->apply_microcode(cpu);
+		microcode_ops->apply_microcode(smp_processor_id());
+	return err;
 }
 
-static void microcode_init_cpu(int cpu)
+static int microcode_init_cpu(int cpu)
 {
-	cpumask_t old = current->cpus_allowed;
-
-	set_cpus_allowed_ptr(current, &cpumask_of_cpu(cpu));
-	/* We should bind the task to the CPU */
-	BUG_ON(raw_smp_processor_id() != cpu);
-
+	int err;
 	mutex_lock(&microcode_mutex);
-	microcode_update_cpu(cpu);
+	err = work_on_cpu(cpu, microcode_update_cpu, NULL);
 	mutex_unlock(&microcode_mutex);
 
-	set_cpus_allowed_ptr(current, &old);
+	return err;
 }
 
 static int mc_sysdev_add(struct sys_device *sys_dev)
@@ -379,8 +390,11 @@ static int mc_sysdev_add(struct sys_device *sys_dev)
 	if (err)
 		return err;
 
-	microcode_init_cpu(cpu);
-	return 0;
+	err = microcode_init_cpu(cpu);
+	if (err)
+		sysfs_remove_group(&sys_dev->kobj, &mc_attr_group);
+
+	return err;
 }
 
 static int mc_sysdev_remove(struct sys_device *sys_dev)
@@ -404,14 +418,14 @@ static int mc_sysdev_resume(struct sys_device *dev)
 		return 0;
 
 	/* only CPU 0 will apply ucode here */
-	microcode_update_cpu(0);
+	microcode_update_cpu(NULL);
 	return 0;
 }
 
 static struct sysdev_driver mc_sysdev_driver = {
-	.add = mc_sysdev_add,
-	.remove = mc_sysdev_remove,
-	.resume = mc_sysdev_resume,
+	.add		= mc_sysdev_add,
+	.remove		= mc_sysdev_remove,
+	.resume		= mc_sysdev_resume,
 };
 
 static __cpuinit int
@@ -424,7 +438,9 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 	switch (action) {
 	case CPU_ONLINE:
 	case CPU_ONLINE_FROZEN:
-		microcode_init_cpu(cpu);
+		if (microcode_init_cpu(cpu))
+			printk(KERN_ERR "microcode: failed to init CPU%d\n",
+			       cpu);
 	case CPU_DOWN_FAILED:
 	case CPU_DOWN_FAILED_FROZEN:
 		pr_debug("microcode: CPU%d added\n", cpu);
@@ -448,7 +464,7 @@ mc_cpu_callback(struct notifier_block *nb, unsigned long action, void *hcpu)
 }
 
 static struct notifier_block __refdata mc_cpu_notifier = {
-	.notifier_call = mc_cpu_callback,
+	.notifier_call	= mc_cpu_callback,
 };
 
 static int __init microcode_init(void)
diff --git a/arch/x86/kernel/microcode_intel.c b/arch/x86/kernel/microcode_intel.c
index 5e9f4fc51385..149b9ec7c1ab 100644
--- a/arch/x86/kernel/microcode_intel.c
+++ b/arch/x86/kernel/microcode_intel.c
@@ -70,28 +70,28 @@
  *		Fix sigmatch() macro to handle old CPUs with pf == 0.
  *		Thanks to Stuart Swales for pointing out this bug.
  */
+#include <linux/platform_device.h>
 #include <linux/capability.h>
-#include <linux/kernel.h>
-#include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/miscdevice.h>
+#include <linux/firmware.h>
 #include <linux/smp_lock.h>
+#include <linux/spinlock.h>
 #include <linux/cpumask.h>
-#include <linux/module.h>
-#include <linux/slab.h>
+#include <linux/uaccess.h>
 #include <linux/vmalloc.h>
-#include <linux/miscdevice.h>
-#include <linux/spinlock.h>
-#include <linux/mm.h>
-#include <linux/fs.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
 #include <linux/mutex.h>
+#include <linux/sched.h>
+#include <linux/init.h>
+#include <linux/slab.h>
 #include <linux/cpu.h>
-#include <linux/firmware.h>
-#include <linux/platform_device.h>
-#include <linux/uaccess.h>
+#include <linux/fs.h>
+#include <linux/mm.h>
 
-#include <asm/msr.h>
-#include <asm/processor.h>
 #include <asm/microcode.h>
+#include <asm/processor.h>
+#include <asm/msr.h>
 
 MODULE_DESCRIPTION("Microcode Update Driver");
 MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
@@ -129,12 +129,13 @@ struct extended_sigtable {
 	struct extended_signature sigs[0];
 };
 
-#define DEFAULT_UCODE_DATASIZE 	(2000)
+#define DEFAULT_UCODE_DATASIZE	(2000)
 #define MC_HEADER_SIZE		(sizeof(struct microcode_header_intel))
 #define DEFAULT_UCODE_TOTALSIZE (DEFAULT_UCODE_DATASIZE + MC_HEADER_SIZE)
 #define EXT_HEADER_SIZE		(sizeof(struct extended_sigtable))
 #define EXT_SIGNATURE_SIZE	(sizeof(struct extended_signature))
 #define DWSIZE			(sizeof(u32))
+
 #define get_totalsize(mc) \
 	(((struct microcode_intel *)mc)->hdr.totalsize ? \
 	 ((struct microcode_intel *)mc)->hdr.totalsize : \
@@ -197,30 +198,31 @@ static inline int update_match_cpu(struct cpu_signature *csig, int sig, int pf)
 }
 
 static inline int
-update_match_revision(struct microcode_header_intel *mc_header,	int rev)
+update_match_revision(struct microcode_header_intel *mc_header, int rev)
 {
 	return (mc_header->rev <= rev) ? 0 : 1;
 }
 
 static int microcode_sanity_check(void *mc)
 {
+	unsigned long total_size, data_size, ext_table_size;
 	struct microcode_header_intel *mc_header = mc;
 	struct extended_sigtable *ext_header = NULL;
-	struct extended_signature *ext_sig;
-	unsigned long total_size, data_size, ext_table_size;
 	int sum, orig_sum, ext_sigcount = 0, i;
+	struct extended_signature *ext_sig;
 
 	total_size = get_totalsize(mc_header);
 	data_size = get_datasize(mc_header);
+
 	if (data_size + MC_HEADER_SIZE > total_size) {
 		printk(KERN_ERR "microcode: error! "
-			"Bad data size in microcode data file\n");
+				"Bad data size in microcode data file\n");
 		return -EINVAL;
 	}
 
 	if (mc_header->ldrver != 1 || mc_header->hdrver != 1) {
 		printk(KERN_ERR "microcode: error! "
-			"Unknown microcode update format\n");
+				"Unknown microcode update format\n");
 		return -EINVAL;
 	}
 	ext_table_size = total_size - (MC_HEADER_SIZE + data_size);
@@ -318,11 +320,15 @@ get_matching_microcode(struct cpu_signature *cpu_sig, void *mc, int rev)
 
 static void apply_microcode(int cpu)
 {
+	struct microcode_intel *mc_intel;
+	struct ucode_cpu_info *uci;
 	unsigned long flags;
 	unsigned int val[2];
-	int cpu_num = raw_smp_processor_id();
-	struct ucode_cpu_info *uci = ucode_cpu_info + cpu;
-	struct microcode_intel *mc_intel = uci->mc;
+	int cpu_num;
+
+	cpu_num = raw_smp_processor_id();
+	uci = ucode_cpu_info + cpu;
+	mc_intel = uci->mc;
 
 	/* We should bind the task to the CPU */
 	BUG_ON(cpu_num != cpu);
@@ -348,15 +354,17 @@ static void apply_microcode(int cpu)
 	spin_unlock_irqrestore(&microcode_update_lock, flags);
 	if (val[1] != mc_intel->hdr.rev) {
 		printk(KERN_ERR "microcode: CPU%d update from revision "
-			"0x%x to 0x%x failed\n", cpu_num, uci->cpu_sig.rev, val[1]);
+				"0x%x to 0x%x failed\n",
+			cpu_num, uci->cpu_sig.rev, val[1]);
 		return;
 	}
 	printk(KERN_INFO "microcode: CPU%d updated from revision "
-	       "0x%x to 0x%x, date = %04x-%02x-%02x \n",
+			 "0x%x to 0x%x, date = %04x-%02x-%02x \n",
 		cpu_num, uci->cpu_sig.rev, val[1],
 		mc_intel->hdr.date & 0xffff,
 		mc_intel->hdr.date >> 24,
 		(mc_intel->hdr.date >> 16) & 0xff);
+
 	uci->cpu_sig.rev = val[1];
 }
 
@@ -404,18 +412,23 @@ static int generic_load_microcode(int cpu, void *data, size_t size,
 		leftover  -= mc_size;
 	}
 
-	if (new_mc) {
-		if (!leftover) {
-			if (uci->mc)
-				vfree(uci->mc);
-			uci->mc = (struct microcode_intel *)new_mc;
-			pr_debug("microcode: CPU%d found a matching microcode update with"
-				 " version 0x%x (current=0x%x)\n",
-				cpu, new_rev, uci->cpu_sig.rev);
-		} else
-			vfree(new_mc);
+	if (!new_mc)
+		goto out;
+
+	if (leftover) {
+		vfree(new_mc);
+		goto out;
 	}
 
+	if (uci->mc)
+		vfree(uci->mc);
+	uci->mc = (struct microcode_intel *)new_mc;
+
+	pr_debug("microcode: CPU%d found a matching microcode update with"
+		 " version 0x%x (current=0x%x)\n",
+			cpu, new_rev, uci->cpu_sig.rev);
+
+ out:
 	return (int)leftover;
 }
 
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 62fc75b67e45..ca989158e847 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -328,7 +328,7 @@ void stop_this_cpu(void *dummy)
 	/*
 	 * Remove this CPU:
 	 */
-	cpu_clear(smp_processor_id(), cpu_online_map);
+	set_cpu_online(smp_processor_id(), false);
 	disable_local_APIC();
 
 	for (;;) {
@@ -478,12 +478,13 @@ static int __cpuinit check_c1e_idle(const struct cpuinfo_x86 *c)
 	return 1;
 }
 
-static cpumask_t c1e_mask = CPU_MASK_NONE;
+static cpumask_var_t c1e_mask;
 static int c1e_detected;
 
 void c1e_remove_cpu(int cpu)
 {
-	cpu_clear(cpu, c1e_mask);
+	if (c1e_mask != NULL)
+		cpumask_clear_cpu(cpu, c1e_mask);
 }
 
 /*
@@ -512,8 +513,8 @@ static void c1e_idle(void)
 	if (c1e_detected) {
 		int cpu = smp_processor_id();
 
-		if (!cpu_isset(cpu, c1e_mask)) {
-			cpu_set(cpu, c1e_mask);
+		if (!cpumask_test_cpu(cpu, c1e_mask)) {
+			cpumask_set_cpu(cpu, c1e_mask);
 			/*
 			 * Force broadcast so ACPI can not interfere. Needs
 			 * to run with interrupts enabled as it uses
@@ -565,6 +566,15 @@ void __cpuinit select_idle_routine(const struct cpuinfo_x86 *c)
 		pm_idle = default_idle;
 }
 
+void __init init_c1e_mask(void)
+{
+	/* If we're using c1e_idle, we need to allocate c1e_mask. */
+	if (pm_idle == c1e_idle) {
+		alloc_cpumask_var(&c1e_mask, GFP_KERNEL);
+		cpumask_clear(c1e_mask);
+	}
+}
+
 static int __init idle_setup(char *str)
 {
 	if (!str)
diff --git a/arch/x86/kernel/process_32.c b/arch/x86/kernel/process_32.c
index 14014d766cad..76f8f84043a2 100644
--- a/arch/x86/kernel/process_32.c
+++ b/arch/x86/kernel/process_32.c
@@ -245,7 +245,7 @@ void prepare_to_copy(struct task_struct *tsk)
 	unlazy_fpu(tsk);
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 	unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c
index abb7e6a7f0c6..b751a41392b1 100644
--- a/arch/x86/kernel/process_64.c
+++ b/arch/x86/kernel/process_64.c
@@ -278,7 +278,7 @@ void prepare_to_copy(struct task_struct *tsk)
 	unlazy_fpu(tsk);
 }
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long sp,
+int copy_thread(unsigned long clone_flags, unsigned long sp,
 		unsigned long unused,
 	struct task_struct *p, struct pt_regs *regs)
 {
diff --git a/arch/x86/kernel/ptrace.c b/arch/x86/kernel/ptrace.c
index 5c6e46320db1..fe9345c967de 100644
--- a/arch/x86/kernel/ptrace.c
+++ b/arch/x86/kernel/ptrace.c
@@ -1462,6 +1462,6 @@ asmregparm void syscall_trace_leave(struct pt_regs *regs)
 	 * system call instruction.
 	 */
 	if (test_thread_flag(TIF_SINGLESTEP) &&
-	    tracehook_consider_fatal_signal(current, SIGTRAP, SIG_DFL))
+	    tracehook_consider_fatal_signal(current, SIGTRAP))
 		send_sigtrap(current, regs, 0, TRAP_BRKPT);
 }
diff --git a/arch/x86/kernel/setup_percpu.c b/arch/x86/kernel/setup_percpu.c
index 400331b50a53..3a97a4cf1872 100644
--- a/arch/x86/kernel/setup_percpu.c
+++ b/arch/x86/kernel/setup_percpu.c
@@ -153,7 +153,6 @@ static struct page * __init pcpur_get_page(unsigned int cpu, int pageno)
 static ssize_t __init setup_pcpu_remap(size_t static_size)
 {
 	static struct vm_struct vm;
-	pg_data_t *last;
 	size_t ptrs_size, dyn_size;
 	unsigned int cpu;
 	ssize_t ret;
@@ -162,22 +161,9 @@ static ssize_t __init setup_pcpu_remap(size_t static_size)
 	 * If large page isn't supported, there's no benefit in doing
 	 * this.  Also, on non-NUMA, embedding is better.
 	 */
-	if (!cpu_has_pse || pcpu_need_numa())
+	if (!cpu_has_pse || !pcpu_need_numa())
 		return -EINVAL;
 
-	last = NULL;
-	for_each_possible_cpu(cpu) {
-		int node = early_cpu_to_node(cpu);
-
-		if (node_online(node) && NODE_DATA(node) &&
-		    last && last != NODE_DATA(node))
-			goto proceed;
-
-		last = NODE_DATA(node);
-	}
-	return -EINVAL;
-
-proceed:
 	/*
 	 * Currently supports only single page.  Supporting multiple
 	 * pages won't be too difficult if it ever becomes necessary.
diff --git a/arch/x86/kernel/signal.c b/arch/x86/kernel/signal.c
index dfcc74ab0ab6..14425166b8e3 100644
--- a/arch/x86/kernel/signal.c
+++ b/arch/x86/kernel/signal.c
@@ -221,7 +221,7 @@ get_sigframe(struct k_sigaction *ka, struct pt_regs *regs, size_t frame_size,
 	if (!onsigstack) {
 		/* This is the X/Open sanctioned signal stack switching.  */
 		if (ka->sa.sa_flags & SA_ONSTACK) {
-			if (sas_ss_flags(sp) == 0)
+			if (current->sas_ss_size)
 				sp = current->sas_ss_sp + current->sas_ss_size;
 		} else {
 #ifdef CONFIG_X86_32
diff --git a/arch/x86/kernel/smpboot.c b/arch/x86/kernel/smpboot.c
index ef7d10170c30..58d24ef917d8 100644
--- a/arch/x86/kernel/smpboot.c
+++ b/arch/x86/kernel/smpboot.c
@@ -101,11 +101,11 @@ EXPORT_SYMBOL(smp_num_siblings);
 DEFINE_PER_CPU(u16, cpu_llc_id) = BAD_APICID;
 
 /* representing HT siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_sibling_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_sibling_map);
 EXPORT_PER_CPU_SYMBOL(cpu_sibling_map);
 
 /* representing HT and core siblings of each logical CPU */
-DEFINE_PER_CPU(cpumask_t, cpu_core_map);
+DEFINE_PER_CPU(cpumask_var_t, cpu_core_map);
 EXPORT_PER_CPU_SYMBOL(cpu_core_map);
 
 /* Per CPU bogomips and other parameters */
@@ -115,11 +115,6 @@ EXPORT_PER_CPU_SYMBOL(cpu_info);
 atomic_t init_deasserted;
 
 #if defined(CONFIG_NUMA) && defined(CONFIG_X86_32)
-
-/* which logical CPUs are on which nodes */
-cpumask_t node_to_cpumask_map[MAX_NUMNODES] __read_mostly =
-				{ [0 ... MAX_NUMNODES-1] = CPU_MASK_NONE };
-EXPORT_SYMBOL(node_to_cpumask_map);
 /* which node each logical CPU is on */
 int cpu_to_node_map[NR_CPUS] __read_mostly = { [0 ... NR_CPUS-1] = 0 };
 EXPORT_SYMBOL(cpu_to_node_map);
@@ -128,7 +123,7 @@ EXPORT_SYMBOL(cpu_to_node_map);
 static void map_cpu_to_node(int cpu, int node)
 {
 	printk(KERN_INFO "Mapping cpu %d to node %d\n", cpu, node);
-	cpumask_set_cpu(cpu, &node_to_cpumask_map[node]);
+	cpumask_set_cpu(cpu, node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = node;
 }
 
@@ -139,7 +134,7 @@ static void unmap_cpu_to_node(int cpu)
 
 	printk(KERN_INFO "Unmapping cpu %d from all nodes\n", cpu);
 	for (node = 0; node < MAX_NUMNODES; node++)
-		cpumask_clear_cpu(cpu, &node_to_cpumask_map[node]);
+		cpumask_clear_cpu(cpu, node_to_cpumask_map[node]);
 	cpu_to_node_map[cpu] = 0;
 }
 #else /* !(CONFIG_NUMA && CONFIG_X86_32) */
@@ -301,7 +296,7 @@ notrace static void __cpuinit start_secondary(void *unused)
 	__flush_tlb_all();
 #endif
 
-	/* This must be done before setting cpu_online_map */
+	/* This must be done before setting cpu_online_mask */
 	set_cpu_sibling_map(raw_smp_processor_id());
 	wmb();
 
@@ -334,6 +329,23 @@ notrace static void __cpuinit start_secondary(void *unused)
 	cpu_idle();
 }
 
+#ifdef CONFIG_CPUMASK_OFFSTACK
+/* In this case, llc_shared_map is a pointer to a cpumask. */
+static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
+				    const struct cpuinfo_x86 *src)
+{
+	struct cpumask *llc = dst->llc_shared_map;
+	*dst = *src;
+	dst->llc_shared_map = llc;
+}
+#else
+static inline void copy_cpuinfo_x86(struct cpuinfo_x86 *dst,
+				    const struct cpuinfo_x86 *src)
+{
+	*dst = *src;
+}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
+
 /*
  * The bootstrap kernel entry code has set these up. Save them for
  * a given CPU
@@ -343,7 +355,7 @@ void __cpuinit smp_store_cpu_info(int id)
 {
 	struct cpuinfo_x86 *c = &cpu_data(id);
 
-	*c = boot_cpu_data;
+	copy_cpuinfo_x86(c, &boot_cpu_data);
 	c->cpu_index = id;
 	if (id != 0)
 		identify_secondary_cpu(c);
@@ -367,15 +379,15 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 				cpumask_set_cpu(cpu, cpu_sibling_mask(i));
 				cpumask_set_cpu(i, cpu_core_mask(cpu));
 				cpumask_set_cpu(cpu, cpu_core_mask(i));
-				cpumask_set_cpu(i, &c->llc_shared_map);
-				cpumask_set_cpu(cpu, &o->llc_shared_map);
+				cpumask_set_cpu(i, c->llc_shared_map);
+				cpumask_set_cpu(cpu, o->llc_shared_map);
 			}
 		}
 	} else {
 		cpumask_set_cpu(cpu, cpu_sibling_mask(cpu));
 	}
 
-	cpumask_set_cpu(cpu, &c->llc_shared_map);
+	cpumask_set_cpu(cpu, c->llc_shared_map);
 
 	if (current_cpu_data.x86_max_cores == 1) {
 		cpumask_copy(cpu_core_mask(cpu), cpu_sibling_mask(cpu));
@@ -386,8 +398,8 @@ void __cpuinit set_cpu_sibling_map(int cpu)
 	for_each_cpu(i, cpu_sibling_setup_mask) {
 		if (per_cpu(cpu_llc_id, cpu) != BAD_APICID &&
 		    per_cpu(cpu_llc_id, cpu) == per_cpu(cpu_llc_id, i)) {
-			cpumask_set_cpu(i, &c->llc_shared_map);
-			cpumask_set_cpu(cpu, &cpu_data(i).llc_shared_map);
+			cpumask_set_cpu(i, c->llc_shared_map);
+			cpumask_set_cpu(cpu, cpu_data(i).llc_shared_map);
 		}
 		if (c->phys_proc_id == cpu_data(i).phys_proc_id) {
 			cpumask_set_cpu(i, cpu_core_mask(cpu));
@@ -425,12 +437,7 @@ const struct cpumask *cpu_coregroup_mask(int cpu)
 	if (sched_mc_power_savings || sched_smt_power_savings)
 		return cpu_core_mask(cpu);
 	else
-		return &c->llc_shared_map;
-}
-
-cpumask_t cpu_coregroup_map(int cpu)
-{
-	return *cpu_coregroup_mask(cpu);
+		return c->llc_shared_map;
 }
 
 static void impress_friends(void)
@@ -897,9 +904,8 @@ int __cpuinit native_cpu_up(unsigned int cpu)
  */
 static __init void disable_smp(void)
 {
-	/* use the read/write pointers to the present and possible maps */
-	cpumask_copy(&cpu_present_map, cpumask_of(0));
-	cpumask_copy(&cpu_possible_map, cpumask_of(0));
+	init_cpu_present(cpumask_of(0));
+	init_cpu_possible(cpumask_of(0));
 	smpboot_clear_io_apic_irqs();
 
 	if (smp_found_config)
@@ -1031,6 +1037,8 @@ static void __init smp_cpu_index_default(void)
  */
 void __init native_smp_prepare_cpus(unsigned int max_cpus)
 {
+	unsigned int i;
+
 	preempt_disable();
 	smp_cpu_index_default();
 	current_cpu_data = boot_cpu_data;
@@ -1044,6 +1052,14 @@ void __init native_smp_prepare_cpus(unsigned int max_cpus)
 	boot_cpu_logical_apicid = logical_smp_processor_id();
 #endif
 	current_thread_info()->cpu = 0;  /* needed? */
+	for_each_possible_cpu(i) {
+		alloc_cpumask_var(&per_cpu(cpu_sibling_map, i), GFP_KERNEL);
+		alloc_cpumask_var(&per_cpu(cpu_core_map, i), GFP_KERNEL);
+		alloc_cpumask_var(&cpu_data(i).llc_shared_map, GFP_KERNEL);
+		cpumask_clear(per_cpu(cpu_core_map, i));
+		cpumask_clear(per_cpu(cpu_sibling_map, i));
+		cpumask_clear(cpu_data(i).llc_shared_map);
+	}
 	set_cpu_sibling_map(0);
 
 	enable_IR_x2apic();
@@ -1132,11 +1148,11 @@ early_param("possible_cpus", _setup_possible_cpus);
 
 
 /*
- * cpu_possible_map should be static, it cannot change as cpu's
+ * cpu_possible_mask should be static, it cannot change as cpu's
  * are onlined, or offlined. The reason is per-cpu data-structures
  * are allocated by some modules at init time, and dont expect to
  * do this dynamically on cpu arrival/departure.
- * cpu_present_map on the other hand can change dynamically.
+ * cpu_present_mask on the other hand can change dynamically.
  * In case when cpu_hotplug is not compiled, then we resort to current
  * behaviour, which is cpu_possible == cpu_present.
  * - Ashok Raj
diff --git a/arch/x86/kernel/syscall_table_32.S b/arch/x86/kernel/syscall_table_32.S
index 3bdb64829b82..ff5c8736b491 100644
--- a/arch/x86/kernel/syscall_table_32.S
+++ b/arch/x86/kernel/syscall_table_32.S
@@ -332,3 +332,5 @@ ENTRY(sys_call_table)
 	.long sys_dup3			/* 330 */
 	.long sys_pipe2
 	.long sys_inotify_init1
+	.long sys_preadv
+	.long sys_pwritev
diff --git a/arch/x86/kernel/tlb_uv.c b/arch/x86/kernel/tlb_uv.c
index 79c073247284..deb5ebb32c3b 100644
--- a/arch/x86/kernel/tlb_uv.c
+++ b/arch/x86/kernel/tlb_uv.c
@@ -275,6 +275,8 @@ const struct cpumask *uv_flush_send_and_wait(int cpu, int this_blade,
 	return NULL;
 }
 
+static DEFINE_PER_CPU(cpumask_var_t, uv_flush_tlb_mask);
+
 /**
  * uv_flush_tlb_others - globally purge translation cache of a virtual
  * address or all TLB's
@@ -304,8 +306,7 @@ const struct cpumask *uv_flush_tlb_others(const struct cpumask *cpumask,
 					  struct mm_struct *mm,
 					  unsigned long va, unsigned int cpu)
 {
-	static DEFINE_PER_CPU(cpumask_t, flush_tlb_mask);
-	struct cpumask *flush_mask = &__get_cpu_var(flush_tlb_mask);
+	struct cpumask *flush_mask = __get_cpu_var(uv_flush_tlb_mask);
 	int i;
 	int bit;
 	int blade;
@@ -755,6 +756,10 @@ static int __init uv_bau_init(void)
 	if (!is_uv_system())
 		return 0;
 
+	for_each_possible_cpu(cur_cpu)
+		alloc_cpumask_var_node(&per_cpu(uv_flush_tlb_mask, cur_cpu),
+				       GFP_KERNEL, cpu_to_node(cur_cpu));
+
 	uv_bau_retry_limit = 1;
 	uv_nshift = uv_hub_info->n_val;
 	uv_mmask = (1UL << uv_hub_info->n_val) - 1;
diff --git a/arch/x86/mm/Makefile b/arch/x86/mm/Makefile
index 08537747cb58..fdd30d08ab52 100644
--- a/arch/x86/mm/Makefile
+++ b/arch/x86/mm/Makefile
@@ -14,7 +14,7 @@ obj-$(CONFIG_MMIOTRACE)		+= mmiotrace.o
 mmiotrace-y			:= kmmio.o pf_in.o mmio-mod.o
 obj-$(CONFIG_MMIOTRACE_TEST)	+= testmmiotrace.o
 
-obj-$(CONFIG_NUMA)		+= numa_$(BITS).o
+obj-$(CONFIG_NUMA)		+= numa.o numa_$(BITS).o
 obj-$(CONFIG_K8_NUMA)		+= k8topology_64.o
 obj-$(CONFIG_ACPI_NUMA)		+= srat_$(BITS).o
 
diff --git a/arch/x86/mm/highmem_32.c b/arch/x86/mm/highmem_32.c
index 5bc5d1688c1c..8126e8d1a2a4 100644
--- a/arch/x86/mm/highmem_32.c
+++ b/arch/x86/mm/highmem_32.c
@@ -40,7 +40,6 @@ void *kmap_atomic_prot(struct page *page, enum km_type type, pgprot_t prot)
 
 	debug_kmap_atomic(type);
 
-	debug_kmap_atomic(type);
 	idx = type + KM_TYPE_NR*smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	BUG_ON(!pte_none(*(kmap_pte-idx)));
diff --git a/arch/x86/mm/iomap_32.c b/arch/x86/mm/iomap_32.c
index bff0c9032f8c..8056545e2d39 100644
--- a/arch/x86/mm/iomap_32.c
+++ b/arch/x86/mm/iomap_32.c
@@ -23,7 +23,7 @@
 
 int is_io_mapping_possible(resource_size_t base, unsigned long size)
 {
-#ifndef CONFIG_X86_PAE
+#if !defined(CONFIG_X86_PAE) && defined(CONFIG_PHYS_ADDR_T_64BIT)
 	/* There is no way to map greater than 1 << 32 address without PAE */
 	if (base + size > 0x100000000ULL)
 		return 0;
@@ -39,6 +39,7 @@ void *kmap_atomic_prot_pfn(unsigned long pfn, enum km_type type, pgprot_t prot)
 
 	pagefault_disable();
 
+	debug_kmap_atomic(type);
 	idx = type + KM_TYPE_NR * smp_processor_id();
 	vaddr = __fix_to_virt(FIX_KMAP_BEGIN + idx);
 	set_pte(kmap_pte - idx, pfn_pte(pfn, prot));
@@ -72,7 +73,6 @@ iounmap_atomic(void *kvaddr, enum km_type type)
 	unsigned long vaddr = (unsigned long) kvaddr & PAGE_MASK;
 	enum fixed_addresses idx = type + KM_TYPE_NR*smp_processor_id();
 
-	debug_kmap_atomic(type);
 	/*
 	 * Force other mappings to Oops if they'll try to access this pte
 	 * without first remap it.  Keeping stale mappings around is a bad idea
diff --git a/arch/x86/mm/mmio-mod.c b/arch/x86/mm/mmio-mod.c
index 2c4baa88f2cb..c9342ed8b402 100644
--- a/arch/x86/mm/mmio-mod.c
+++ b/arch/x86/mm/mmio-mod.c
@@ -378,27 +378,34 @@ static void clear_trace_list(void)
 }
 
 #ifdef CONFIG_HOTPLUG_CPU
-static cpumask_t downed_cpus;
+static cpumask_var_t downed_cpus;
 
 static void enter_uniprocessor(void)
 {
 	int cpu;
 	int err;
 
+	if (downed_cpus == NULL &&
+	    !alloc_cpumask_var(&downed_cpus, GFP_KERNEL)) {
+		pr_notice(NAME "Failed to allocate mask\n");
+		goto out;
+	}
+
 	get_online_cpus();
-	downed_cpus = cpu_online_map;
-	cpu_clear(first_cpu(cpu_online_map), downed_cpus);
+	cpumask_copy(downed_cpus, cpu_online_mask);
+	cpumask_clear_cpu(cpumask_first(cpu_online_mask), downed_cpus);
 	if (num_online_cpus() > 1)
 		pr_notice(NAME "Disabling non-boot CPUs...\n");
 	put_online_cpus();
 
-	for_each_cpu_mask(cpu, downed_cpus) {
+	for_each_cpu(cpu, downed_cpus) {
 		err = cpu_down(cpu);
 		if (!err)
 			pr_info(NAME "CPU%d is down.\n", cpu);
 		else
 			pr_err(NAME "Error taking CPU%d down: %d\n", cpu, err);
 	}
+out:
 	if (num_online_cpus() > 1)
 		pr_warning(NAME "multiple CPUs still online, "
 						"may miss events.\n");
@@ -411,10 +418,10 @@ static void __ref leave_uniprocessor(void)
 	int cpu;
 	int err;
 
-	if (cpus_weight(downed_cpus) == 0)
+	if (downed_cpus == NULL || cpumask_weight(downed_cpus) == 0)
 		return;
 	pr_notice(NAME "Re-enabling CPUs...\n");
-	for_each_cpu_mask(cpu, downed_cpus) {
+	for_each_cpu(cpu, downed_cpus) {
 		err = cpu_up(cpu);
 		if (!err)
 			pr_info(NAME "enabled CPU%d.\n", cpu);
diff --git a/arch/x86/mm/numa.c b/arch/x86/mm/numa.c
new file mode 100644
index 000000000000..550df481accd
--- /dev/null
+++ b/arch/x86/mm/numa.c
@@ -0,0 +1,67 @@
+/* Common code for 32 and 64-bit NUMA */
+#include <linux/topology.h>
+#include <linux/module.h>
+#include <linux/bootmem.h>
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+# define DBG(x...) printk(KERN_DEBUG x)
+#else
+# define DBG(x...)
+#endif
+
+/*
+ * Which logical CPUs are on which nodes
+ */
+cpumask_var_t node_to_cpumask_map[MAX_NUMNODES];
+EXPORT_SYMBOL(node_to_cpumask_map);
+
+/*
+ * Allocate node_to_cpumask_map based on number of available nodes
+ * Requires node_possible_map to be valid.
+ *
+ * Note: node_to_cpumask() is not valid until after this is done.
+ * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
+ */
+void __init setup_node_to_cpumask_map(void)
+{
+	unsigned int node, num = 0;
+
+	/* setup nr_node_ids if not done yet */
+	if (nr_node_ids == MAX_NUMNODES) {
+		for_each_node_mask(node, node_possible_map)
+			num = node;
+		nr_node_ids = num + 1;
+	}
+
+	/* allocate the map */
+	for (node = 0; node < nr_node_ids; node++)
+		alloc_bootmem_cpumask_var(&node_to_cpumask_map[node]);
+
+	/* cpumask_of_node() will now work */
+	pr_debug("Node to cpumask map for %d nodes\n", nr_node_ids);
+}
+
+#ifdef CONFIG_DEBUG_PER_CPU_MAPS
+/*
+ * Returns a pointer to the bitmask of CPUs on Node 'node'.
+ */
+const struct cpumask *cpumask_of_node(int node)
+{
+	if (node >= nr_node_ids) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
+			node, nr_node_ids);
+		dump_stack();
+		return cpu_none_mask;
+	}
+	if (node_to_cpumask_map[node] == NULL) {
+		printk(KERN_WARNING
+			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
+			node);
+		dump_stack();
+		return cpu_online_mask;
+	}
+	return node_to_cpumask_map[node];
+}
+EXPORT_SYMBOL(cpumask_of_node);
+#endif
diff --git a/arch/x86/mm/numa_64.c b/arch/x86/mm/numa_64.c
index 64c9cf043cdd..d73aaa892371 100644
--- a/arch/x86/mm/numa_64.c
+++ b/arch/x86/mm/numa_64.c
@@ -20,12 +20,6 @@
 #include <asm/acpi.h>
 #include <asm/k8.h>
 
-#ifdef CONFIG_DEBUG_PER_CPU_MAPS
-# define DBG(x...) printk(KERN_DEBUG x)
-#else
-# define DBG(x...)
-#endif
-
 struct pglist_data *node_data[MAX_NUMNODES] __read_mostly;
 EXPORT_SYMBOL(node_data);
 
@@ -49,12 +43,6 @@ DEFINE_EARLY_PER_CPU(int, x86_cpu_to_node_map, NUMA_NO_NODE);
 EXPORT_EARLY_PER_CPU_SYMBOL(x86_cpu_to_node_map);
 
 /*
- * Which logical CPUs are on which nodes
- */
-cpumask_t *node_to_cpumask_map;
-EXPORT_SYMBOL(node_to_cpumask_map);
-
-/*
  * Given a shift value, try to populate memnodemap[]
  * Returns :
  * 1 if OK
@@ -661,36 +649,6 @@ void __init init_cpu_to_node(void)
 #endif
 
 
-/*
- * Allocate node_to_cpumask_map based on number of available nodes
- * Requires node_possible_map to be valid.
- *
- * Note: node_to_cpumask() is not valid until after this is done.
- * (Use CONFIG_DEBUG_PER_CPU_MAPS to check this.)
- */
-void __init setup_node_to_cpumask_map(void)
-{
-	unsigned int node, num = 0;
-	cpumask_t *map;
-
-	/* setup nr_node_ids if not done yet */
-	if (nr_node_ids == MAX_NUMNODES) {
-		for_each_node_mask(node, node_possible_map)
-			num = node;
-		nr_node_ids = num + 1;
-	}
-
-	/* allocate the map */
-	map = alloc_bootmem_low(nr_node_ids * sizeof(cpumask_t));
-	DBG("node_to_cpumask_map at %p for %d nodes\n", map, nr_node_ids);
-
-	pr_debug("Node to cpumask map at %p for %d nodes\n",
-		 map, nr_node_ids);
-
-	/* node_to_cpumask() will now work */
-	node_to_cpumask_map = map;
-}
-
 void __cpuinit numa_set_node(int cpu, int node)
 {
 	int *cpu_to_node_map = early_per_cpu_ptr(x86_cpu_to_node_map);
@@ -723,12 +681,12 @@ void __cpuinit numa_clear_node(int cpu)
 
 void __cpuinit numa_add_cpu(int cpu)
 {
-	cpu_set(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+	cpumask_set_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
 
 void __cpuinit numa_remove_cpu(int cpu)
 {
-	cpu_clear(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
+	cpumask_clear_cpu(cpu, node_to_cpumask_map[early_cpu_to_node(cpu)]);
 }
 
 #else /* CONFIG_DEBUG_PER_CPU_MAPS */
@@ -739,20 +697,20 @@ void __cpuinit numa_remove_cpu(int cpu)
 static void __cpuinit numa_set_cpumask(int cpu, int enable)
 {
 	int node = early_cpu_to_node(cpu);
-	cpumask_t *mask;
+	struct cpumask *mask;
 	char buf[64];
 
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_ERR "node_to_cpumask_map NULL\n");
+	mask = node_to_cpumask_map[node];
+	if (mask == NULL) {
+		printk(KERN_ERR "node_to_cpumask_map[%i] NULL\n", node);
 		dump_stack();
 		return;
 	}
 
-	mask = &node_to_cpumask_map[node];
 	if (enable)
-		cpu_set(cpu, *mask);
+		cpumask_set_cpu(cpu, mask);
 	else
-		cpu_clear(cpu, *mask);
+		cpumask_clear_cpu(cpu, mask);
 
 	cpulist_scnprintf(buf, sizeof(buf), mask);
 	printk(KERN_DEBUG "%s cpu %d node %d: mask now %s\n",
@@ -799,59 +757,6 @@ int early_cpu_to_node(int cpu)
 	return per_cpu(x86_cpu_to_node_map, cpu);
 }
 
-
-/* empty cpumask */
-static const cpumask_t cpu_mask_none;
-
-/*
- * Returns a pointer to the bitmask of CPUs on Node 'node'.
- */
-const cpumask_t *cpumask_of_node(int node)
-{
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"cpumask_of_node(%d): no node_to_cpumask_map!\n",
-			node);
-		dump_stack();
-		return (const cpumask_t *)&cpu_online_map;
-	}
-	if (node >= nr_node_ids) {
-		printk(KERN_WARNING
-			"cpumask_of_node(%d): node > nr_node_ids(%d)\n",
-			node, nr_node_ids);
-		dump_stack();
-		return &cpu_mask_none;
-	}
-	return &node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(cpumask_of_node);
-
-/*
- * Returns a bitmask of CPUs on Node 'node'.
- *
- * Side note: this function creates the returned cpumask on the stack
- * so with a high NR_CPUS count, excessive stack space is used.  The
- * node_to_cpumask_ptr function should be used whenever possible.
- */
-cpumask_t node_to_cpumask(int node)
-{
-	if (node_to_cpumask_map == NULL) {
-		printk(KERN_WARNING
-			"node_to_cpumask(%d): no node_to_cpumask_map!\n", node);
-		dump_stack();
-		return cpu_online_map;
-	}
-	if (node >= nr_node_ids) {
-		printk(KERN_WARNING
-			"node_to_cpumask(%d): node > nr_node_ids(%d)\n",
-			node, nr_node_ids);
-		dump_stack();
-		return cpu_mask_none;
-	}
-	return node_to_cpumask_map[node];
-}
-EXPORT_SYMBOL(node_to_cpumask);
-
 /*
  * --------- end of debug versions of the numa functions ---------
  */
diff --git a/arch/x86/oprofile/op_model_p4.c b/arch/x86/oprofile/op_model_p4.c
index 4c4a51c90bc2..819b131fd752 100644
--- a/arch/x86/oprofile/op_model_p4.c
+++ b/arch/x86/oprofile/op_model_p4.c
@@ -380,7 +380,7 @@ static unsigned int get_stagger(void)
 {
 #ifdef CONFIG_SMP
 	int cpu = smp_processor_id();
-	return (cpu != first_cpu(per_cpu(cpu_sibling_map, cpu)));
+	return cpu != cpumask_first(__get_cpu_var(cpu_sibling_map));
 #endif
 	return 0;
 }
diff --git a/arch/x86/pci/i386.c b/arch/x86/pci/i386.c
index f234a37bd428..f1817f71e009 100644
--- a/arch/x86/pci/i386.c
+++ b/arch/x86/pci/i386.c
@@ -258,24 +258,7 @@ void pcibios_set_master(struct pci_dev *dev)
 	pci_write_config_byte(dev, PCI_LATENCY_TIMER, lat);
 }
 
-static void pci_unmap_page_range(struct vm_area_struct *vma)
-{
-	u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT;
-	free_memtype(addr, addr + vma->vm_end - vma->vm_start);
-}
-
-static void pci_track_mmap_page_range(struct vm_area_struct *vma)
-{
-	u64 addr = (u64)vma->vm_pgoff << PAGE_SHIFT;
-	unsigned long flags = pgprot_val(vma->vm_page_prot)
-						& _PAGE_CACHE_MASK;
-
-	reserve_memtype(addr, addr + vma->vm_end - vma->vm_start, flags, NULL);
-}
-
 static struct vm_operations_struct pci_mmap_ops = {
-	.open  = pci_track_mmap_page_range,
-	.close = pci_unmap_page_range,
 	.access = generic_access_phys,
 };
 
@@ -283,11 +266,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 			enum pci_mmap_state mmap_state, int write_combine)
 {
 	unsigned long prot;
-	u64 addr = vma->vm_pgoff << PAGE_SHIFT;
-	unsigned long len = vma->vm_end - vma->vm_start;
-	unsigned long flags;
-	unsigned long new_flags;
-	int retval;
 
 	/* I/O space cannot be accessed via normal processor loads and
 	 * stores on this platform.
@@ -308,30 +286,6 @@ int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,
 
 	vma->vm_page_prot = __pgprot(prot);
 
-	flags = pgprot_val(vma->vm_page_prot) & _PAGE_CACHE_MASK;
-	retval = reserve_memtype(addr, addr + len, flags, &new_flags);
-	if (retval)
-		return retval;
-
-	if (flags != new_flags) {
-		if (!is_new_memtype_allowed(flags, new_flags)) {
-			free_memtype(addr, addr+len);
-			return -EINVAL;
-		}
-		flags = new_flags;
-		vma->vm_page_prot = __pgprot(
-			(pgprot_val(vma->vm_page_prot) & ~_PAGE_CACHE_MASK) |
-			flags);
-	}
-
-	if (((vma->vm_pgoff < max_low_pfn_mapped) ||
-	     (vma->vm_pgoff >= (1UL<<(32 - PAGE_SHIFT)) &&
-	      vma->vm_pgoff < max_pfn_mapped)) &&
-	    ioremap_change_attr((unsigned long)__va(addr), len, flags)) {
-		free_memtype(addr, addr + len);
-		return -EINVAL;
-	}
-
 	if (io_remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff,
 			       vma->vm_end - vma->vm_start,
 			       vma->vm_page_prot))
diff --git a/arch/x86/power/Makefile b/arch/x86/power/Makefile
index 9ff4d5b55ad1..58b32db33125 100644
--- a/arch/x86/power/Makefile
+++ b/arch/x86/power/Makefile
@@ -1,2 +1,7 @@
+# __restore_processor_state() restores %gs after S3 resume and so should not
+# itself be stack-protected
+nostackp := $(call cc-option, -fno-stack-protector)
+CFLAGS_cpu_$(BITS).o	:= $(nostackp)
+
 obj-$(CONFIG_PM_SLEEP)		+= cpu_$(BITS).o
 obj-$(CONFIG_HIBERNATION)	+= hibernate_$(BITS).o hibernate_asm_$(BITS).o
diff --git a/arch/x86/xen/smp.c b/arch/x86/xen/smp.c
index 8d470562ffc9..585a6e330837 100644
--- a/arch/x86/xen/smp.c
+++ b/arch/x86/xen/smp.c
@@ -158,7 +158,7 @@ static void __init xen_fill_possible_map(void)
 		rc = HYPERVISOR_vcpu_op(VCPUOP_is_up, i, NULL);
 		if (rc >= 0) {
 			num_processors++;
-			cpu_set(i, cpu_possible_map);
+			set_cpu_possible(i, true);
 		}
 	}
 }
@@ -197,7 +197,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 	while ((num_possible_cpus() > 1) && (num_possible_cpus() > max_cpus)) {
 		for (cpu = nr_cpu_ids - 1; !cpu_possible(cpu); cpu--)
 			continue;
-		cpu_clear(cpu, cpu_possible_map);
+		set_cpu_possible(cpu, false);
 	}
 
 	for_each_possible_cpu (cpu) {
@@ -210,7 +210,7 @@ static void __init xen_smp_prepare_cpus(unsigned int max_cpus)
 		if (IS_ERR(idle))
 			panic("failed fork for CPU %d", cpu);
 
-		cpu_set(cpu, cpu_present_map);
+		set_cpu_present(cpu, true);
 	}
 }
 
diff --git a/arch/xtensa/Kconfig b/arch/xtensa/Kconfig
index 981200830432..fa6dc4dd3b19 100644
--- a/arch/xtensa/Kconfig
+++ b/arch/xtensa/Kconfig
@@ -4,16 +4,13 @@
 mainmenu "Linux/Xtensa Kernel Configuration"
 
 config FRAME_POINTER
-	bool
-	default n
+	def_bool n
 
 config ZONE_DMA
-	bool
-	default y
+	def_bool y
 
 config XTENSA
-	bool
-	default y
+	def_bool y
 	select HAVE_IDE
 	help
 	  Xtensa processors are 32-bit RISC machines designed by Tensilica
@@ -24,28 +21,25 @@ config XTENSA
 	  a home page at <http://xtensa.sourceforge.net/>.
 
 config RWSEM_XCHGADD_ALGORITHM
-	bool
-	default y
+	def_bool y
 
 config GENERIC_FIND_NEXT_BIT
-	bool
-	default y
+	def_bool y
 
 config GENERIC_HWEIGHT
-	bool
-	default y
+	def_bool y
 
 config GENERIC_HARDIRQS
-	bool
-	default y
+	def_bool y
+
+config GENERIC_GPIO
+	def_bool y
 
 config ARCH_HAS_ILOG2_U32
-	bool
-	default n
+	def_bool n
 
 config ARCH_HAS_ILOG2_U64
-	bool
-	default n
+	def_bool n
 
 config NO_IOPORT
 	def_bool y
@@ -54,9 +48,18 @@ config HZ
 	int
 	default 100
 
+config GENERIC_TIME
+	def_bool y
+
 source "init/Kconfig"
 source "kernel/Kconfig.freezer"
 
+config MMU
+	def_bool n
+
+config VARIANT_IRQ_SWITCH
+	def_bool n
+
 menu "Processor type and features"
 
 choice
@@ -65,38 +68,41 @@ choice
 
 config XTENSA_VARIANT_FSF
 	bool "fsf - default (not generic) configuration"
+	select MMU
 
 config XTENSA_VARIANT_DC232B
 	bool "dc232b - Diamond 232L Standard Core Rev.B (LE)"
+	select MMU
 	help
-	This variant refers to Tensilica's Diamond 232L Standard core Rev.B (LE).
-endchoice
+	  This variant refers to Tensilica's Diamond 232L Standard core Rev.B (LE).
 
-config MMU
-	bool
-	default y
+config XTENSA_VARIANT_S6000
+	bool "s6000 - Stretch software configurable processor"
+	select VARIANT_IRQ_SWITCH
+	select ARCH_REQUIRE_GPIOLIB
+endchoice
 
 config XTENSA_UNALIGNED_USER
 	bool "Unaligned memory access in use space"
-	---help---
-	   The Xtensa architecture currently does not handle unaligned
-	   memory accesses in hardware but through an exception handler.
-	   Per default, unaligned memory accesses are disabled in user space.
+	help
+	  The Xtensa architecture currently does not handle unaligned
+	  memory accesses in hardware but through an exception handler.
+	  Per default, unaligned memory accesses are disabled in user space.
 
-	   Say Y here to enable unaligned memory access in user space.
+	  Say Y here to enable unaligned memory access in user space.
 
 config PREEMPT
 	bool "Preemptible Kernel"
-	---help---
-           This option reduces the latency of the kernel when reacting to
-           real-time or interactive events by allowing a low priority process to
-           be preempted even if it is in kernel mode executing a system call.
-           Unfortunately the kernel code has some race conditions if both
-           CONFIG_SMP and CONFIG_PREEMPT are enabled, so this option is
-           currently disabled if you are building an SMP kernel.
+	help
+          This option reduces the latency of the kernel when reacting to
+          real-time or interactive events by allowing a low priority process to
+          be preempted even if it is in kernel mode executing a system call.
+          Unfortunately the kernel code has some race conditions if both
+          CONFIG_SMP and CONFIG_PREEMPT are enabled, so this option is
+          currently disabled if you are building an SMP kernel.
 
-           Say Y here if you are building a kernel for a desktop, embedded
-           or real-time system.  Say N if you are unsure.
+          Say Y here if you are building a kernel for a desktop, embedded
+          or real-time system.  Say N if you are unsure.
 
 config MATH_EMULATION
 	bool "Math emulation"
@@ -105,6 +111,32 @@ config MATH_EMULATION
 
 endmenu
 
+config XTENSA_CALIBRATE_CCOUNT
+	def_bool n
+	help
+	  On some platforms (XT2000, for example), the CPU clock rate can
+	  vary.  The frequency can be determined, however, by measuring
+	  against a well known, fixed frequency, such as an UART oscillator.
+
+config SERIAL_CONSOLE
+	def_bool n
+
+config XTENSA_ISS_NETWORK
+	def_bool n
+
+menu "Bus options"
+
+config PCI
+	bool "PCI support"
+	default y
+	help
+	  Find out whether you have a PCI motherboard. PCI is the name of a
+	  bus system, i.e. the way the CPU talks to the other stuff inside
+	  your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or
+	  VESA. If you have PCI, say Y, otherwise N.
+
+source "drivers/pci/Kconfig"
+
 menu "Platform options"
 
 choice
@@ -113,33 +145,35 @@ choice
 
 config XTENSA_PLATFORM_ISS
 	bool "ISS"
+	select XTENSA_CALIBRATE_CCOUNT
+	select SERIAL_CONSOLE
+	select XTENSA_ISS_NETWORK
 	help
 	  ISS is an acronym for Tensilica's Instruction Set Simulator.
 
 config XTENSA_PLATFORM_XT2000
 	bool "XT2000"
+	select XTENSA_CALIBRATE_CCOUNT
+	select PCI
 	help
 	  XT2000 is the name of Tensilica's feature-rich emulation platform.
 	  This hardware is capable of running a full Linux distribution.
 
-endchoice
+config XTENSA_PLATFORM_S6105
+	bool "S6105"
+	select SERIAL_CONSOLE
 
+endchoice
 
-config XTENSA_CALIBRATE_CCOUNT
-	bool "Auto calibration of the CPU clock rate"
-	---help---
-	  On some platforms (XT2000, for example), the CPU clock rate can
-	  vary.  The frequency can be determined, however, by measuring
-	  against a well known, fixed frequency, such as an UART oscillator.
 
 config XTENSA_CPU_CLOCK
 	int "CPU clock rate [MHz]"
 	depends on !XTENSA_CALIBRATE_CCOUNT
-	default "16"
+	default 16
 
 config GENERIC_CALIBRATE_DELAY
 	bool "Auto calibration of the BogoMIPS value"
-	---help---
+	help
 	  The BogoMIPS value can easily be derived from the CPU frequency.
 
 config CMDLINE_BOOL
@@ -156,52 +190,27 @@ config CMDLINE
 	  time by entering them here. As a minimum, you should specify the
 	  memory size and the root device (e.g., mem=64M root=/dev/nfs).
 
-config SERIAL_CONSOLE
-	bool
-	depends on XTENSA_PLATFORM_ISS
-	default y
-
-config XTENSA_ISS_NETWORK
-	bool
-	depends on XTENSA_PLATFORM_ISS
-	default y
-
 source "mm/Kconfig"
 
 endmenu
 
-menu "Bus options"
-
-config PCI
-	bool "PCI support" if !XTENSA_PLATFORM_ISS
-	depends on !XTENSA_PLATFORM_ISS
-	default y
+config HOTPLUG
+	bool "Support for hot-pluggable devices"
 	help
-	  Find out whether you have a PCI motherboard. PCI is the name of a
-	  bus system, i.e. the way the CPU talks to the other stuff inside
-	  your box. Other bus systems are ISA, EISA, MicroChannel (MCA) or
-	  VESA. If you have PCI, say Y, otherwise N.
+	  Say Y here if you want to plug devices into your computer while
+	  the system is running, and be able to use them quickly.  In many
+	  cases, the devices can likewise be unplugged at any time too.
 
-source "drivers/pci/Kconfig"
+	  One well known example of this is PCMCIA- or PC-cards, credit-card
+	  size devices such as network cards, modems or hard drives which are
+	  plugged into slots found on all modern laptop computers.  Another
+	  example, used on modern desktops as well as laptops, is USB.
 
-config HOTPLUG
-
-	bool "Support for hot-pluggable devices"
-	---help---
-	Say Y here if you want to plug devices into your computer while
-	the system is running, and be able to use them quickly.  In many
-	cases, the devices can likewise be unplugged at any time too.
-
-	One well known example of this is PCMCIA- or PC-cards, credit-card
-	size devices such as network cards, modems or hard drives which are
-	plugged into slots found on all modern laptop computers.  Another
-	example, used on modern desktops as well as laptops, is USB.
-
-	Enable HOTPLUG and build a modular kernel.  Get agent software
-	(from <http://linux-hotplug.sourceforge.net/>) and install it.
-	Then your kernel will automatically call out to a user mode "policy
-	agent" (/sbin/hotplug) to load modules and set up software needed
-	to use devices as you hotplug them.
+	  Enable HOTPLUG and build a modular kernel.  Get agent software
+	  (from <http://linux-hotplug.sourceforge.net/>) and install it.
+	  Then your kernel will automatically call out to a user mode "policy
+	  agent" (/sbin/hotplug) to load modules and set up software needed
+	  to use devices as you hotplug them.
 
 source "drivers/pcmcia/Kconfig"
 
@@ -213,9 +222,8 @@ menu "Executable file formats"
 
 # only elf supported
 config KCORE_ELF
-        bool
+	def_bool y
         depends on PROC_FS
-        default y
         help
           If you enabled support for /proc file system then the file
           /proc/kcore will contain the kernel core image in ELF format. This
@@ -240,7 +248,7 @@ source "fs/Kconfig"
 menu "Xtensa initrd options"
 	depends on BLK_DEV_INITRD
 
-	config EMBEDDED_RAMDISK
+config EMBEDDED_RAMDISK
 	bool "Embed root filesystem ramdisk into the kernel"
 
 config EMBEDDED_RAMDISK_IMAGE
diff --git a/arch/xtensa/Makefile b/arch/xtensa/Makefile
index 1da55fe4beff..4caffac3ca2e 100644
--- a/arch/xtensa/Makefile
+++ b/arch/xtensa/Makefile
@@ -15,6 +15,7 @@
 
 variant-$(CONFIG_XTENSA_VARIANT_FSF)		:= fsf
 variant-$(CONFIG_XTENSA_VARIANT_DC232B)		:= dc232b
+variant-$(CONFIG_XTENSA_VARIANT_S6000)		:= s6000
 variant-$(CONFIG_XTENSA_VARIANT_LINUX_CUSTOM)	:= custom
 
 VARIANT = $(variant-y)
@@ -24,6 +25,7 @@ export VARIANT
 
 platform-$(CONFIG_XTENSA_PLATFORM_XT2000)	:= xt2000
 platform-$(CONFIG_XTENSA_PLATFORM_ISS)		:= iss
+platform-$(CONFIG_XTENSA_PLATFORM_S6105)	:= s6105
 
 PLATFORM = $(platform-y)
 export PLATFORM
@@ -62,20 +64,23 @@ ifneq ($(VARIANT),)
   endif
 endif
 
-#
+# Only build variant and/or platform if it includes a Makefile
+
+buildvar := $(shell test -a $(srctree)/arch/xtensa/variants/$(VARIANT)/Makefile && echo arch/xtensa/variants/$(VARIANT)/)
+buildplf := $(shell test -a $(srctree)/arch/xtensa/platforms/$(PLATFORM)/Makefile && echo arch/xtensa/platforms/$(PLATFORM)/)
+
+# Find libgcc.a
 
 LIBGCC := $(shell $(CC) $(KBUILD_CFLAGS) -print-libgcc-file-name)
 
 head-y		:= arch/xtensa/kernel/head.o
 core-y		+= arch/xtensa/kernel/ arch/xtensa/mm/
-ifneq ($(PLATFORM),)
-core-y		+= arch/xtensa/platforms/$(PLATFORM)/
-endif
+core-y		+= $(buildvar) $(buildplf)
+
 libs-y		+= arch/xtensa/lib/ $(LIBGCC)
 
 boot		:= arch/xtensa/boot
 
-
 all: zImage
 
 bzImage : zImage
diff --git a/arch/xtensa/configs/s6105_defconfig b/arch/xtensa/configs/s6105_defconfig
new file mode 100644
index 000000000000..6e1deff41590
--- /dev/null
+++ b/arch/xtensa/configs/s6105_defconfig
@@ -0,0 +1,530 @@
+#
+# Automatically generated make config: don't edit
+# Linux kernel version: 2.6.29-rc7-s6
+# Tue Mar 10 11:09:26 2009
+#
+# CONFIG_FRAME_POINTER is not set
+CONFIG_ZONE_DMA=y
+CONFIG_XTENSA=y
+CONFIG_RWSEM_XCHGADD_ALGORITHM=y
+CONFIG_GENERIC_FIND_NEXT_BIT=y
+CONFIG_GENERIC_HWEIGHT=y
+CONFIG_GENERIC_HARDIRQS=y
+CONFIG_GENERIC_GPIO=y
+# CONFIG_ARCH_HAS_ILOG2_U32 is not set
+# CONFIG_ARCH_HAS_ILOG2_U64 is not set
+CONFIG_NO_IOPORT=y
+CONFIG_HZ=100
+CONFIG_GENERIC_TIME=y
+CONFIG_DEFCONFIG_LIST="/lib/modules/$UNAME_RELEASE/.config"
+
+#
+# General setup
+#
+CONFIG_EXPERIMENTAL=y
+CONFIG_BROKEN_ON_SMP=y
+CONFIG_LOCK_KERNEL=y
+CONFIG_INIT_ENV_ARG_LIMIT=32
+CONFIG_LOCALVERSION=""
+CONFIG_LOCALVERSION_AUTO=y
+CONFIG_SYSVIPC=y
+CONFIG_SYSVIPC_SYSCTL=y
+# CONFIG_POSIX_MQUEUE is not set
+# CONFIG_BSD_PROCESS_ACCT is not set
+# CONFIG_TASKSTATS is not set
+# CONFIG_AUDIT is not set
+
+#
+# RCU Subsystem
+#
+# CONFIG_CLASSIC_RCU is not set
+# CONFIG_TREE_RCU is not set
+CONFIG_PREEMPT_RCU=y
+# CONFIG_RCU_TRACE is not set
+# CONFIG_TREE_RCU_TRACE is not set
+# CONFIG_PREEMPT_RCU_TRACE is not set
+CONFIG_IKCONFIG=y
+CONFIG_IKCONFIG_PROC=y
+CONFIG_LOG_BUF_SHIFT=16
+# CONFIG_GROUP_SCHED is not set
+# CONFIG_CGROUPS is not set
+# CONFIG_SYSFS_DEPRECATED_V2 is not set
+# CONFIG_RELAY is not set
+# CONFIG_NAMESPACES is not set
+CONFIG_BLK_DEV_INITRD=y
+CONFIG_INITRAMFS_SOURCE=""
+CONFIG_CC_OPTIMIZE_FOR_SIZE=y
+CONFIG_SYSCTL=y
+CONFIG_EMBEDDED=y
+CONFIG_SYSCTL_SYSCALL=y
+CONFIG_KALLSYMS=y
+# CONFIG_KALLSYMS_ALL is not set
+# CONFIG_KALLSYMS_EXTRA_PASS is not set
+# CONFIG_HOTPLUG is not set
+CONFIG_PRINTK=y
+CONFIG_BUG=y
+CONFIG_ELF_CORE=y
+# CONFIG_COMPAT_BRK is not set
+CONFIG_BASE_FULL=y
+CONFIG_FUTEX=y
+CONFIG_ANON_INODES=y
+CONFIG_EPOLL=y
+CONFIG_SIGNALFD=y
+CONFIG_TIMERFD=y
+CONFIG_EVENTFD=y
+CONFIG_AIO=y
+CONFIG_VM_EVENT_COUNTERS=y
+CONFIG_SLAB=y
+# CONFIG_SLUB is not set
+# CONFIG_SLOB is not set
+# CONFIG_PROFILING is not set
+# CONFIG_HAVE_GENERIC_DMA_COHERENT is not set
+CONFIG_SLABINFO=y
+CONFIG_RT_MUTEXES=y
+CONFIG_BASE_SMALL=0
+# CONFIG_MODULES is not set
+CONFIG_BLOCK=y
+# CONFIG_LBD is not set
+# CONFIG_BLK_DEV_IO_TRACE is not set
+# CONFIG_BLK_DEV_BSG is not set
+# CONFIG_BLK_DEV_INTEGRITY is not set
+
+#
+# IO Schedulers
+#
+CONFIG_IOSCHED_NOOP=y
+# CONFIG_IOSCHED_AS is not set
+# CONFIG_IOSCHED_DEADLINE is not set
+CONFIG_IOSCHED_CFQ=y
+# CONFIG_DEFAULT_AS is not set
+# CONFIG_DEFAULT_DEADLINE is not set
+CONFIG_DEFAULT_CFQ=y
+# CONFIG_DEFAULT_NOOP is not set
+CONFIG_DEFAULT_IOSCHED="cfq"
+# CONFIG_FREEZER is not set
+# CONFIG_MMU is not set
+CONFIG_VARIANT_IRQ_SWITCH=y
+
+#
+# Processor type and features
+#
+# CONFIG_XTENSA_VARIANT_FSF is not set
+# CONFIG_XTENSA_VARIANT_DC232B is not set
+CONFIG_XTENSA_VARIANT_S6000=y
+# CONFIG_XTENSA_UNALIGNED_USER is not set
+CONFIG_PREEMPT=y
+# CONFIG_MATH_EMULATION is not set
+# CONFIG_HIGHMEM is not set
+# CONFIG_XTENSA_CALIBRATE_CCOUNT is not set
+CONFIG_SERIAL_CONSOLE=y
+# CONFIG_XTENSA_ISS_NETWORK is not set
+
+#
+# Bus options
+#
+# CONFIG_PCI is not set
+# CONFIG_ARCH_SUPPORTS_MSI is not set
+
+#
+# Platform options
+#
+# CONFIG_XTENSA_PLATFORM_ISS is not set
+# CONFIG_XTENSA_PLATFORM_XT2000 is not set
+CONFIG_XTENSA_PLATFORM_S6105=y
+CONFIG_XTENSA_CPU_CLOCK=300
+CONFIG_GENERIC_CALIBRATE_DELAY=y
+CONFIG_CMDLINE_BOOL=y
+CONFIG_CMDLINE="console=ttyS1,38400 debug bootmem_debug loglevel=7"
+CONFIG_SELECT_MEMORY_MODEL=y
+CONFIG_FLATMEM_MANUAL=y
+# CONFIG_DISCONTIGMEM_MANUAL is not set
+# CONFIG_SPARSEMEM_MANUAL is not set
+CONFIG_FLATMEM=y
+CONFIG_FLAT_NODE_MEM_MAP=y
+CONFIG_PAGEFLAGS_EXTENDED=y
+CONFIG_SPLIT_PTLOCK_CPUS=4
+# CONFIG_PHYS_ADDR_T_64BIT is not set
+CONFIG_ZONE_DMA_FLAG=1
+CONFIG_VIRT_TO_BUS=y
+
+#
+# Executable file formats
+#
+CONFIG_KCORE_ELF=y
+CONFIG_BINFMT_FLAT=y
+# CONFIG_BINFMT_ZFLAT is not set
+# CONFIG_BINFMT_SHARED_FLAT is not set
+# CONFIG_HAVE_AOUT is not set
+# CONFIG_BINFMT_MISC is not set
+CONFIG_NET=y
+
+#
+# Networking options
+#
+CONFIG_COMPAT_NET_DEV_OPS=y
+CONFIG_PACKET=y
+# CONFIG_PACKET_MMAP is not set
+CONFIG_UNIX=y
+# CONFIG_NET_KEY is not set
+CONFIG_INET=y
+# CONFIG_IP_MULTICAST is not set
+# CONFIG_IP_ADVANCED_ROUTER is not set
+CONFIG_IP_FIB_HASH=y
+# CONFIG_IP_PNP is not set
+# CONFIG_NET_IPIP is not set
+# CONFIG_NET_IPGRE is not set
+# CONFIG_ARPD is not set
+# CONFIG_SYN_COOKIES is not set
+# CONFIG_INET_AH is not set
+# CONFIG_INET_ESP is not set
+# CONFIG_INET_IPCOMP is not set
+# CONFIG_INET_XFRM_TUNNEL is not set
+# CONFIG_INET_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_TRANSPORT is not set
+# CONFIG_INET_XFRM_MODE_TUNNEL is not set
+# CONFIG_INET_XFRM_MODE_BEET is not set
+# CONFIG_INET_LRO is not set
+# CONFIG_INET_DIAG is not set
+# CONFIG_TCP_CONG_ADVANCED is not set
+CONFIG_TCP_CONG_CUBIC=y
+CONFIG_DEFAULT_TCP_CONG="cubic"
+# CONFIG_TCP_MD5SIG is not set
+# CONFIG_IPV6 is not set
+# CONFIG_NETWORK_SECMARK is not set
+# CONFIG_NETFILTER is not set
+# CONFIG_IP_DCCP is not set
+# CONFIG_IP_SCTP is not set
+# CONFIG_TIPC is not set
+# CONFIG_ATM is not set
+# CONFIG_BRIDGE is not set
+# CONFIG_NET_DSA is not set
+# CONFIG_VLAN_8021Q is not set
+# CONFIG_DECNET is not set
+# CONFIG_LLC2 is not set
+# CONFIG_IPX is not set
+# CONFIG_ATALK is not set
+# CONFIG_X25 is not set
+# CONFIG_LAPB is not set
+# CONFIG_ECONET is not set
+# CONFIG_WAN_ROUTER is not set
+# CONFIG_NET_SCHED is not set
+# CONFIG_DCB is not set
+
+#
+# Network testing
+#
+# CONFIG_NET_PKTGEN is not set
+# CONFIG_HAMRADIO is not set
+# CONFIG_CAN is not set
+# CONFIG_IRDA is not set
+# CONFIG_BT is not set
+# CONFIG_AF_RXRPC is not set
+# CONFIG_PHONET is not set
+# CONFIG_WIRELESS is not set
+# CONFIG_WIMAX is not set
+# CONFIG_RFKILL is not set
+# CONFIG_NET_9P is not set
+
+#
+# Device Drivers
+#
+
+#
+# Generic Driver Options
+#
+CONFIG_STANDALONE=y
+CONFIG_PREVENT_FIRMWARE_BUILD=y
+# CONFIG_DEBUG_DRIVER is not set
+# CONFIG_DEBUG_DEVRES is not set
+# CONFIG_SYS_HYPERVISOR is not set
+# CONFIG_CONNECTOR is not set
+# CONFIG_MTD is not set
+# CONFIG_PARPORT is not set
+CONFIG_BLK_DEV=y
+# CONFIG_BLK_DEV_COW_COMMON is not set
+# CONFIG_BLK_DEV_LOOP is not set
+# CONFIG_BLK_DEV_NBD is not set
+CONFIG_BLK_DEV_RAM=y
+CONFIG_BLK_DEV_RAM_COUNT=16
+CONFIG_BLK_DEV_RAM_SIZE=4096
+# CONFIG_BLK_DEV_XIP is not set
+# CONFIG_CDROM_PKTCDVD is not set
+# CONFIG_ATA_OVER_ETH is not set
+# CONFIG_BLK_DEV_HD is not set
+# CONFIG_MISC_DEVICES is not set
+CONFIG_HAVE_IDE=y
+# CONFIG_IDE is not set
+
+#
+# SCSI device support
+#
+# CONFIG_RAID_ATTRS is not set
+# CONFIG_SCSI is not set
+# CONFIG_SCSI_DMA is not set
+# CONFIG_SCSI_NETLINK is not set
+# CONFIG_ATA is not set
+# CONFIG_MD is not set
+# CONFIG_NETDEVICES is not set
+# CONFIG_ISDN is not set
+# CONFIG_PHONE is not set
+
+#
+# Input device support
+#
+# CONFIG_INPUT is not set
+
+#
+# Hardware I/O ports
+#
+# CONFIG_SERIO is not set
+# CONFIG_GAMEPORT is not set
+
+#
+# Character devices
+#
+# CONFIG_VT is not set
+# CONFIG_DEVKMEM is not set
+# CONFIG_SERIAL_NONSTANDARD is not set
+
+#
+# Serial drivers
+#
+CONFIG_SERIAL_8250=y
+CONFIG_SERIAL_8250_CONSOLE=y
+CONFIG_SERIAL_8250_NR_UARTS=2
+CONFIG_SERIAL_8250_RUNTIME_UARTS=2
+# CONFIG_SERIAL_8250_EXTENDED is not set
+
+#
+# Non-8250 serial port support
+#
+CONFIG_SERIAL_CORE=y
+CONFIG_SERIAL_CORE_CONSOLE=y
+CONFIG_UNIX98_PTYS=y
+# CONFIG_DEVPTS_MULTIPLE_INSTANCES is not set
+# CONFIG_LEGACY_PTYS is not set
+# CONFIG_IPMI_HANDLER is not set
+# CONFIG_HW_RANDOM is not set
+# CONFIG_RTC is not set
+# CONFIG_GEN_RTC is not set
+# CONFIG_R3964 is not set
+# CONFIG_RAW_DRIVER is not set
+# CONFIG_TCG_TPM is not set
+# CONFIG_I2C is not set
+# CONFIG_SPI is not set
+CONFIG_ARCH_REQUIRE_GPIOLIB=y
+CONFIG_GPIOLIB=y
+# CONFIG_DEBUG_GPIO is not set
+# CONFIG_GPIO_SYSFS is not set
+
+#
+# Memory mapped GPIO expanders:
+#
+
+#
+# I2C GPIO expanders:
+#
+
+#
+# PCI GPIO expanders:
+#
+
+#
+# SPI GPIO expanders:
+#
+# CONFIG_W1 is not set
+# CONFIG_POWER_SUPPLY is not set
+# CONFIG_HWMON is not set
+# CONFIG_THERMAL is not set
+# CONFIG_THERMAL_HWMON is not set
+# CONFIG_WATCHDOG is not set
+CONFIG_SSB_POSSIBLE=y
+
+#
+# Sonics Silicon Backplane
+#
+# CONFIG_SSB is not set
+
+#
+# Multifunction device drivers
+#
+# CONFIG_MFD_CORE is not set
+# CONFIG_MFD_SM501 is not set
+# CONFIG_HTC_PASIC3 is not set
+# CONFIG_MFD_TMIO is not set
+# CONFIG_REGULATOR is not set
+
+#
+# Multimedia devices
+#
+
+#
+# Multimedia core support
+#
+# CONFIG_VIDEO_DEV is not set
+# CONFIG_DVB_CORE is not set
+# CONFIG_VIDEO_MEDIA is not set
+
+#
+# Multimedia drivers
+#
+# CONFIG_DAB is not set
+
+#
+# Graphics support
+#
+# CONFIG_VGASTATE is not set
+# CONFIG_VIDEO_OUTPUT_CONTROL is not set
+# CONFIG_FB is not set
+# CONFIG_BACKLIGHT_LCD_SUPPORT is not set
+
+#
+# Display device support
+#
+# CONFIG_DISPLAY_SUPPORT is not set
+# CONFIG_SOUND is not set
+# CONFIG_USB_SUPPORT is not set
+# CONFIG_MMC is not set
+# CONFIG_MEMSTICK is not set
+# CONFIG_NEW_LEDS is not set
+# CONFIG_ACCESSIBILITY is not set
+# CONFIG_RTC_CLASS is not set
+# CONFIG_DMADEVICES is not set
+# CONFIG_UIO is not set
+# CONFIG_STAGING is not set
+
+#
+# File systems
+#
+# CONFIG_EXT2_FS is not set
+# CONFIG_EXT3_FS is not set
+# CONFIG_EXT4_FS is not set
+# CONFIG_REISERFS_FS is not set
+# CONFIG_JFS_FS is not set
+# CONFIG_FS_POSIX_ACL is not set
+CONFIG_FILE_LOCKING=y
+# CONFIG_XFS_FS is not set
+# CONFIG_OCFS2_FS is not set
+# CONFIG_BTRFS_FS is not set
+# CONFIG_DNOTIFY is not set
+# CONFIG_INOTIFY is not set
+# CONFIG_QUOTA is not set
+# CONFIG_AUTOFS_FS is not set
+# CONFIG_AUTOFS4_FS is not set
+# CONFIG_FUSE_FS is not set
+
+#
+# CD-ROM/DVD Filesystems
+#
+# CONFIG_ISO9660_FS is not set
+# CONFIG_UDF_FS is not set
+
+#
+# DOS/FAT/NT Filesystems
+#
+# CONFIG_MSDOS_FS is not set
+# CONFIG_VFAT_FS is not set
+# CONFIG_NTFS_FS is not set
+
+#
+# Pseudo filesystems
+#
+CONFIG_PROC_FS=y
+CONFIG_PROC_SYSCTL=y
+CONFIG_SYSFS=y
+# CONFIG_TMPFS is not set
+# CONFIG_HUGETLB_PAGE is not set
+# CONFIG_CONFIGFS_FS is not set
+# CONFIG_MISC_FILESYSTEMS is not set
+# CONFIG_NETWORK_FILESYSTEMS is not set
+
+#
+# Partition Types
+#
+# CONFIG_PARTITION_ADVANCED is not set
+CONFIG_MSDOS_PARTITION=y
+# CONFIG_NLS is not set
+# CONFIG_DLM is not set
+
+#
+# Xtensa initrd options
+#
+# CONFIG_EMBEDDED_RAMDISK is not set
+
+#
+# Kernel hacking
+#
+CONFIG_PRINTK_TIME=y
+# CONFIG_ENABLE_WARN_DEPRECATED is not set
+# CONFIG_ENABLE_MUST_CHECK is not set
+CONFIG_FRAME_WARN=1024
+# CONFIG_MAGIC_SYSRQ is not set
+# CONFIG_UNUSED_SYMBOLS is not set
+# CONFIG_DEBUG_FS is not set
+# CONFIG_HEADERS_CHECK is not set
+CONFIG_DEBUG_KERNEL=y
+CONFIG_DEBUG_SHIRQ=y
+CONFIG_DETECT_SOFTLOCKUP=y
+# CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC is not set
+CONFIG_BOOTPARAM_SOFTLOCKUP_PANIC_VALUE=0
+# CONFIG_SCHED_DEBUG is not set
+# CONFIG_SCHEDSTATS is not set
+# CONFIG_TIMER_STATS is not set
+# CONFIG_DEBUG_OBJECTS is not set
+# CONFIG_DEBUG_SLAB is not set
+# CONFIG_DEBUG_RT_MUTEXES is not set
+# CONFIG_RT_MUTEX_TESTER is not set
+CONFIG_DEBUG_SPINLOCK=y
+CONFIG_DEBUG_MUTEXES=y
+CONFIG_DEBUG_SPINLOCK_SLEEP=y
+# CONFIG_DEBUG_LOCKING_API_SELFTESTS is not set
+# CONFIG_DEBUG_KOBJECT is not set
+# CONFIG_DEBUG_INFO is not set
+# CONFIG_DEBUG_VM is not set
+CONFIG_DEBUG_NOMMU_REGIONS=y
+# CONFIG_DEBUG_WRITECOUNT is not set
+# CONFIG_DEBUG_MEMORY_INIT is not set
+# CONFIG_DEBUG_LIST is not set
+# CONFIG_DEBUG_SG is not set
+# CONFIG_DEBUG_NOTIFIERS is not set
+# CONFIG_BOOT_PRINTK_DELAY is not set
+# CONFIG_RCU_TORTURE_TEST is not set
+# CONFIG_BACKTRACE_SELF_TEST is not set
+# CONFIG_DEBUG_BLOCK_EXT_DEVT is not set
+# CONFIG_FAULT_INJECTION is not set
+# CONFIG_SYSCTL_SYSCALL_CHECK is not set
+
+#
+# Tracers
+#
+# CONFIG_PREEMPT_TRACER is not set
+# CONFIG_SCHED_TRACER is not set
+# CONFIG_CONTEXT_SWITCH_TRACER is not set
+# CONFIG_BOOT_TRACER is not set
+# CONFIG_TRACE_BRANCH_PROFILING is not set
+# CONFIG_DYNAMIC_PRINTK_DEBUG is not set
+# CONFIG_SAMPLES is not set
+
+#
+# Security options
+#
+# CONFIG_KEYS is not set
+# CONFIG_SECURITY is not set
+# CONFIG_SECURITYFS is not set
+# CONFIG_SECURITY_FILE_CAPABILITIES is not set
+# CONFIG_CRYPTO is not set
+
+#
+# Library routines
+#
+CONFIG_GENERIC_FIND_LAST_BIT=y
+# CONFIG_CRC_CCITT is not set
+# CONFIG_CRC16 is not set
+# CONFIG_CRC_T10DIF is not set
+# CONFIG_CRC_ITU_T is not set
+# CONFIG_CRC32 is not set
+# CONFIG_CRC7 is not set
+# CONFIG_LIBCRC32C is not set
+CONFIG_PLIST=y
+CONFIG_HAS_IOMEM=y
+CONFIG_HAS_DMA=y
diff --git a/arch/xtensa/include/asm/cacheflush.h b/arch/xtensa/include/asm/cacheflush.h
index 94c4c53a099e..8fc1c0c8de07 100644
--- a/arch/xtensa/include/asm/cacheflush.h
+++ b/arch/xtensa/include/asm/cacheflush.h
@@ -65,13 +65,17 @@ extern void __flush_invalidate_dcache_range(unsigned long, unsigned long);
 # define __flush_invalidate_dcache_range(p,s)	__invalidate_dcache_range(p,s)
 #endif
 
-#if (DCACHE_WAY_SIZE > PAGE_SIZE)
+#if defined(CONFIG_MMU) && (DCACHE_WAY_SIZE > PAGE_SIZE)
 extern void __flush_invalidate_dcache_page_alias(unsigned long, unsigned long);
+#else
+static inline void __flush_invalidate_dcache_page_alias(unsigned long virt,
+							unsigned long phys) { }
 #endif
-#if (ICACHE_WAY_SIZE > PAGE_SIZE)
+#if defined(CONFIG_MMU) && (ICACHE_WAY_SIZE > PAGE_SIZE)
 extern void __invalidate_icache_page_alias(unsigned long, unsigned long);
 #else
-# define __invalidate_icache_page_alias(v,p)	do { } while(0)
+static inline void __invalidate_icache_page_alias(unsigned long virt,
+						unsigned long phys) { }
 #endif
 
 /*
diff --git a/arch/xtensa/include/asm/dma.h b/arch/xtensa/include/asm/dma.h
index e30f3abf48f0..137ca3945b07 100644
--- a/arch/xtensa/include/asm/dma.h
+++ b/arch/xtensa/include/asm/dma.h
@@ -44,8 +44,9 @@
  *	the value desired).
  */
 
+#ifndef MAX_DMA_ADDRESS
 #define MAX_DMA_ADDRESS		(PAGE_OFFSET + XCHAL_KIO_SIZE - 1)
-
+#endif
 
 /* Reserve and release a DMA channel */
 extern int request_dma(unsigned int dmanr, const char * device_id);
diff --git a/arch/xtensa/include/asm/flat.h b/arch/xtensa/include/asm/flat.h
new file mode 100644
index 000000000000..94c44abf15e4
--- /dev/null
+++ b/arch/xtensa/include/asm/flat.h
@@ -0,0 +1,12 @@
+#ifndef __ASM_XTENSA_FLAT_H
+#define __ASM_XTENSA_FLAT_H
+
+#define flat_argvp_envp_on_stack()			0
+#define flat_old_ram_flag(flags)			(flags)
+#define flat_reloc_valid(reloc, size)			((reloc) <= (size))
+#define flat_get_addr_from_rp(rp, relval, flags, p)	get_unaligned(rp)
+#define flat_put_addr_at_rp(rp, val, relval	)	put_unaligned(val, rp)
+#define flat_get_relocate_addr(rel)			(rel)
+#define flat_set_persistent(relval, p)			0
+
+#endif /* __ASM_XTENSA_FLAT_H */
diff --git a/arch/xtensa/include/asm/gpio.h b/arch/xtensa/include/asm/gpio.h
new file mode 100644
index 000000000000..0763b0763960
--- /dev/null
+++ b/arch/xtensa/include/asm/gpio.h
@@ -0,0 +1,56 @@
+/*
+ * Generic GPIO API implementation for xtensa.
+ *
+ * Stolen from x86, which is derived from the generic GPIO API for powerpc:
+ *
+ * Copyright (c) 2007-2008  MontaVista Software, Inc.
+ *
+ * Author: Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef _ASM_XTENSA_GPIO_H
+#define _ASM_XTENSA_GPIO_H
+
+#include <asm-generic/gpio.h>
+
+#ifdef CONFIG_GPIOLIB
+
+/*
+ * Just call gpiolib.
+ */
+static inline int gpio_get_value(unsigned int gpio)
+{
+	return __gpio_get_value(gpio);
+}
+
+static inline void gpio_set_value(unsigned int gpio, int value)
+{
+	__gpio_set_value(gpio, value);
+}
+
+static inline int gpio_cansleep(unsigned int gpio)
+{
+	return __gpio_cansleep(gpio);
+}
+
+/*
+ * Not implemented, yet.
+ */
+static inline int gpio_to_irq(unsigned int gpio)
+{
+	return -ENOSYS;
+}
+
+static inline int irq_to_gpio(unsigned int irq)
+{
+	return -EINVAL;
+}
+
+#endif /* CONFIG_GPIOLIB */
+
+#endif /* _ASM_XTENSA_GPIO_H */
diff --git a/arch/xtensa/include/asm/io.h b/arch/xtensa/include/asm/io.h
index 07b7299dab20..d04cd3a625fa 100644
--- a/arch/xtensa/include/asm/io.h
+++ b/arch/xtensa/include/asm/io.h
@@ -69,21 +69,28 @@ static inline void * phys_to_virt(unsigned long address)
 
 static inline void *ioremap(unsigned long offset, unsigned long size)
 {
+#ifdef CONFIG_MMU
 	if (offset >= XCHAL_KIO_PADDR
 	    && offset < XCHAL_KIO_PADDR + XCHAL_KIO_SIZE)
 		return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_BYPASS_VADDR);
-
 	else
 		BUG();
+#else
+	return (void *)offset;
+#endif
 }
 
 static inline void *ioremap_nocache(unsigned long offset, unsigned long size)
 {
+#ifdef CONFIG_MMU
 	if (offset >= XCHAL_KIO_PADDR
 	    && offset < XCHAL_KIO_PADDR + XCHAL_KIO_SIZE)
 		return (void*)(offset-XCHAL_KIO_PADDR+XCHAL_KIO_CACHED_VADDR);
 	else
 		BUG();
+#else
+	return (void *)offset;
+#endif
 }
 
 static inline void iounmap(void *addr)
diff --git a/arch/xtensa/include/asm/irq.h b/arch/xtensa/include/asm/irq.h
index 1620d1e0e695..dfac82dc52ad 100644
--- a/arch/xtensa/include/asm/irq.h
+++ b/arch/xtensa/include/asm/irq.h
@@ -14,6 +14,13 @@
 #include <platform/hardware.h>
 #include <variant/core.h>
 
+#ifdef CONFIG_VARIANT_IRQ_SWITCH
+#include <variant/irq.h>
+#else
+static inline void variant_irq_enable(unsigned int irq) { }
+static inline void variant_irq_disable(unsigned int irq) { }
+#endif
+
 #ifndef PLATFORM_NR_IRQS
 # define PLATFORM_NR_IRQS 0
 #endif
diff --git a/arch/xtensa/include/asm/mmu.h b/arch/xtensa/include/asm/mmu.h
index 44c5bb04c55c..04890d6e2335 100644
--- a/arch/xtensa/include/asm/mmu.h
+++ b/arch/xtensa/include/asm/mmu.h
@@ -11,7 +11,12 @@
 #ifndef _XTENSA_MMU_H
 #define _XTENSA_MMU_H
 
+#ifndef CONFIG_MMU
+#include <asm/nommu.h>
+#else
+
 /* Default "unsigned long" context */
 typedef unsigned long mm_context_t;
 
+#endif /* CONFIG_MMU */
 #endif	/* _XTENSA_MMU_H */
diff --git a/arch/xtensa/include/asm/mmu_context.h b/arch/xtensa/include/asm/mmu_context.h
index c0fd8e5b4513..dbd8731a876a 100644
--- a/arch/xtensa/include/asm/mmu_context.h
+++ b/arch/xtensa/include/asm/mmu_context.h
@@ -13,16 +13,20 @@
 #ifndef _XTENSA_MMU_CONTEXT_H
 #define _XTENSA_MMU_CONTEXT_H
 
+#ifndef CONFIG_MMU
+#include <asm/nommu_context.h>
+#else
+
 #include <linux/stringify.h>
 #include <linux/sched.h>
 
+#include <variant/core.h>
+
 #include <asm/pgtable.h>
 #include <asm/cacheflush.h>
 #include <asm/tlbflush.h>
 #include <asm-generic/mm_hooks.h>
 
-#define XCHAL_MMU_ASID_BITS	8
-
 #if (XCHAL_HAVE_TLBS != 1)
 # error "Linux must have an MMU!"
 #endif
@@ -133,4 +137,5 @@ static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
 
 }
 
+#endif /* CONFIG_MMU */
 #endif /* _XTENSA_MMU_CONTEXT_H */
diff --git a/arch/xtensa/include/asm/nommu.h b/arch/xtensa/include/asm/nommu.h
new file mode 100644
index 000000000000..dce2c438c5ba
--- /dev/null
+++ b/arch/xtensa/include/asm/nommu.h
@@ -0,0 +1,3 @@
+typedef struct {
+	unsigned long end_brk;
+} mm_context_t;
diff --git a/arch/xtensa/include/asm/nommu_context.h b/arch/xtensa/include/asm/nommu_context.h
new file mode 100644
index 000000000000..599e7a2e729d
--- /dev/null
+++ b/arch/xtensa/include/asm/nommu_context.h
@@ -0,0 +1,25 @@
+static inline void enter_lazy_tlb(struct mm_struct *mm, struct task_struct *tsk)
+{
+}
+
+static inline int init_new_context(struct task_struct *tsk, struct mm_struct *mm)
+{
+	return 0;
+}
+
+static inline void destroy_context(struct mm_struct *mm)
+{
+}
+
+static inline void activate_mm(struct mm_struct *prev, struct mm_struct *next)
+{
+}
+
+static inline void switch_mm(struct mm_struct *prev, struct mm_struct *next,
+				struct task_struct *tsk)
+{
+}
+
+static inline void deactivate_mm(struct task_struct *tsk, struct mm_struct *mm)
+{
+}
diff --git a/arch/xtensa/include/asm/page.h b/arch/xtensa/include/asm/page.h
index 11f7dc2dbec7..17e0c5383b10 100644
--- a/arch/xtensa/include/asm/page.h
+++ b/arch/xtensa/include/asm/page.h
@@ -14,6 +14,7 @@
 #include <asm/processor.h>
 #include <asm/types.h>
 #include <asm/cache.h>
+#include <platform/hardware.h>
 
 /*
  * Fixed TLB translations in the processor.
@@ -32,8 +33,14 @@
 #define PAGE_SIZE		(__XTENSA_UL_CONST(1) << PAGE_SHIFT)
 #define PAGE_MASK		(~(PAGE_SIZE-1))
 
+#ifdef CONFIG_MMU
 #define PAGE_OFFSET		XCHAL_KSEG_CACHED_VADDR
 #define MAX_MEM_PFN		XCHAL_KSEG_SIZE
+#else
+#define PAGE_OFFSET		0
+#define MAX_MEM_PFN		(PLATFORM_DEFAULT_MEM_START + PLATFORM_DEFAULT_MEM_SIZE)
+#endif
+
 #define PGTABLE_START		0x80000000
 
 /*
@@ -150,9 +157,11 @@ extern void copy_user_page(void*, void*, unsigned long, struct page*);
  * addresses.
  */
 
+#define ARCH_PFN_OFFSET		(PLATFORM_DEFAULT_MEM_START >> PAGE_SHIFT)
+
 #define __pa(x)			((unsigned long) (x) - PAGE_OFFSET)
 #define __va(x)			((void *)((unsigned long) (x) + PAGE_OFFSET))
-#define pfn_valid(pfn)		((unsigned long)pfn < max_mapnr)
+#define pfn_valid(pfn)		((pfn) >= ARCH_PFN_OFFSET && ((pfn) - ARCH_PFN_OFFSET) < max_mapnr)
 #ifdef CONFIG_DISCONTIGMEM
 # error CONFIG_DISCONTIGMEM not supported
 #endif
@@ -162,8 +171,9 @@ extern void copy_user_page(void*, void*, unsigned long, struct page*);
 #define virt_addr_valid(kaddr)	pfn_valid(__pa(kaddr) >> PAGE_SHIFT)
 #define page_to_phys(page)	(page_to_pfn(page) << PAGE_SHIFT)
 
+#ifdef CONFIG_MMU
 #define WANT_PAGE_VIRTUAL
-
+#endif
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/arch/xtensa/include/asm/pgtable.h b/arch/xtensa/include/asm/pgtable.h
index 8014d96b21f1..a138770c358e 100644
--- a/arch/xtensa/include/asm/pgtable.h
+++ b/arch/xtensa/include/asm/pgtable.h
@@ -183,7 +183,15 @@ extern unsigned long empty_zero_page[1024];
 
 #define ZERO_PAGE(vaddr) (virt_to_page(empty_zero_page))
 
+#ifdef CONFIG_MMU
 extern pgd_t swapper_pg_dir[PAGE_SIZE/sizeof(pgd_t)];
+extern void paging_init(void);
+extern void pgtable_cache_init(void);
+#else
+# define swapper_pg_dir NULL
+static inline void paging_init(void) { }
+static inline void pgtable_cache_init(void) { }
+#endif
 
 /*
  * The pmd contains the kernel virtual address of the pte page.
@@ -383,8 +391,6 @@ ptep_set_wrprotect(struct mm_struct *mm, unsigned long addr, pte_t *ptep)
 
 #else
 
-extern void paging_init(void);
-
 #define kern_addr_valid(addr)	(1)
 
 extern  void update_mmu_cache(struct vm_area_struct * vma,
@@ -398,9 +404,6 @@ extern  void update_mmu_cache(struct vm_area_struct * vma,
 #define io_remap_pfn_range(vma,from,pfn,size,prot) \
                 remap_pfn_range(vma, from, pfn, size, prot)
 
-
-extern void pgtable_cache_init(void);
-
 typedef pte_t *pte_addr_t;
 
 #endif /* !defined (__ASSEMBLY__) */
diff --git a/arch/xtensa/include/asm/platform.h b/arch/xtensa/include/asm/platform.h
index e3d5a48ad495..7d936e58e9be 100644
--- a/arch/xtensa/include/asm/platform.h
+++ b/arch/xtensa/include/asm/platform.h
@@ -74,16 +74,5 @@ extern int platform_pcibios_fixup (void);
  */
 extern void platform_calibrate_ccount (void);
 
-/*
- * platform_get_rtc_time returns RTC seconds (returns 0 for no error)
- */
-extern int platform_get_rtc_time(time_t*);
-
-/*
- * platform_set_rtc_time set RTC seconds (returns 0 for no error)
- */
-extern int platform_set_rtc_time(time_t);
-
-
 #endif	/* _XTENSA_PLATFORM_H */
 
diff --git a/arch/xtensa/include/asm/processor.h b/arch/xtensa/include/asm/processor.h
index 07387d3b99f4..0ea4937c0b61 100644
--- a/arch/xtensa/include/asm/processor.h
+++ b/arch/xtensa/include/asm/processor.h
@@ -13,6 +13,7 @@
 
 #include <variant/core.h>
 #include <asm/coprocessor.h>
+#include <platform/hardware.h>
 
 #include <linux/compiler.h>
 #include <asm/ptrace.h>
@@ -25,6 +26,8 @@
 # error Linux requires the Xtensa Windowed Registers Option.
 #endif
 
+#define ARCH_SLAB_MINALIGN	XCHAL_DATA_WIDTH
+
 /*
  * User space process size: 1 GB.
  * Windowed call ABI requires caller and callee to be located within the same
@@ -33,7 +36,12 @@
  * the 1 GB requirement applies to the stack as well.
  */
 
+#ifdef CONFIG_MMU
 #define TASK_SIZE	__XTENSA_UL_CONST(0x40000000)
+#else
+#define TASK_SIZE	(PLATFORM_DEFAULT_MEM_START + PLATFORM_DEFAULT_MEM_SIZE)
+#endif
+
 #define STACK_TOP	TASK_SIZE
 #define STACK_TOP_MAX	STACK_TOP
 
diff --git a/arch/xtensa/kernel/entry.S b/arch/xtensa/kernel/entry.S
index a51d36a27389..80d24c485fd3 100644
--- a/arch/xtensa/kernel/entry.S
+++ b/arch/xtensa/kernel/entry.S
@@ -1463,6 +1463,7 @@ ENTRY(_spill_registers)
 	callx0	a0		# should not return
 1:	j	1b
 
+#ifdef CONFIG_MMU
 /*
  * We should never get here. Bail out!
  */
@@ -1775,7 +1776,7 @@ ENTRY(fast_store_prohibited)
 	bbsi.l	a2, PS_UM_BIT, 1f
 	j	_kernel_exception
 1:	j	_user_exception
-
+#endif /* CONFIG_MMU */
 
 /*
  * System Calls.
diff --git a/arch/xtensa/kernel/head.S b/arch/xtensa/kernel/head.S
index 67e69139520b..0817f9db836e 100644
--- a/arch/xtensa/kernel/head.S
+++ b/arch/xtensa/kernel/head.S
@@ -53,7 +53,7 @@ _start:	_j	2f
 2:	l32r	a0, 1b
 	jx	a0
 
-	.text
+	.section .init.text, "ax"
 	.align 4
 _startup:
 
@@ -235,8 +235,9 @@ should_never_return:
  */
 	
 .section ".bss.page_aligned", "w"
+#ifdef CONFIG_MMU
 ENTRY(swapper_pg_dir)
 	.fill	PAGE_SIZE, 1, 0
+#endif
 ENTRY(empty_zero_page)
 	.fill	PAGE_SIZE, 1, 0
-
diff --git a/arch/xtensa/kernel/irq.c b/arch/xtensa/kernel/irq.c
index f3b66fba5b8f..a36c85edd045 100644
--- a/arch/xtensa/kernel/irq.c
+++ b/arch/xtensa/kernel/irq.c
@@ -132,6 +132,18 @@ static void xtensa_irq_unmask(unsigned int irq)
 	set_sr (cached_irq_mask, INTENABLE);
 }
 
+static void xtensa_irq_enable(unsigned int irq)
+{
+	variant_irq_enable(irq);
+	xtensa_irq_unmask(irq);
+}
+
+static void xtensa_irq_disable(unsigned int irq)
+{
+	xtensa_irq_mask(irq);
+	variant_irq_disable(irq);
+}
+
 static void xtensa_irq_ack(unsigned int irq)
 {
 	set_sr(1 << irq, INTCLEAR);
@@ -146,6 +158,8 @@ static int xtensa_irq_retrigger(unsigned int irq)
 
 static struct irq_chip xtensa_irq_chip = {
 	.name		= "xtensa",
+	.enable		= xtensa_irq_enable,
+	.disable	= xtensa_irq_disable,
 	.mask		= xtensa_irq_mask,
 	.unmask		= xtensa_irq_unmask,
 	.ack		= xtensa_irq_ack,
diff --git a/arch/xtensa/kernel/platform.c b/arch/xtensa/kernel/platform.c
index 69675f216062..1b91a97f1d84 100644
--- a/arch/xtensa/kernel/platform.c
+++ b/arch/xtensa/kernel/platform.c
@@ -36,8 +36,6 @@ _F(void, power_off, (void), { while(1); });
 _F(void, idle, (void), { __asm__ __volatile__ ("waiti 0" ::: "memory"); });
 _F(void, heartbeat, (void), { });
 _F(int,  pcibios_fixup, (void), { return 0; });
-_F(int, get_rtc_time, (time_t* t), { return 0; });
-_F(int, set_rtc_time, (time_t t), { return 0; });
 
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
 _F(void, calibrate_ccount, (void),
diff --git a/arch/xtensa/kernel/process.c b/arch/xtensa/kernel/process.c
index 9185597eb6a0..031f36685710 100644
--- a/arch/xtensa/kernel/process.c
+++ b/arch/xtensa/kernel/process.c
@@ -172,7 +172,7 @@ void prepare_to_copy(struct task_struct *tsk)
  *       childregs.
  */
 
-int copy_thread(int nr, unsigned long clone_flags, unsigned long usp,
+int copy_thread(unsigned long clone_flags, unsigned long usp,
 		unsigned long unused,
                 struct task_struct * p, struct pt_regs * regs)
 {
diff --git a/arch/xtensa/kernel/setup.c b/arch/xtensa/kernel/setup.c
index 4ec1633c2941..1e5a034fe011 100644
--- a/arch/xtensa/kernel/setup.c
+++ b/arch/xtensa/kernel/setup.c
@@ -84,7 +84,13 @@ sysmem_info_t __initdata sysmem;
 int initrd_is_mapped;
 #endif
 
+#ifdef CONFIG_MMU
 extern void init_mmu(void);
+#else
+static inline void init_mmu(void) { }
+#endif
+
+extern void zones_init(void);
 
 /*
  * Boot parameter parsing.
@@ -286,6 +292,7 @@ void __init setup_arch(char **cmdline_p)
 
 
 	paging_init();
+	zones_init();
 
 #ifdef CONFIG_VT
 # if defined(CONFIG_VGA_CONSOLE)
diff --git a/arch/xtensa/kernel/time.c b/arch/xtensa/kernel/time.c
index 8df1e842f6d4..8848120d291b 100644
--- a/arch/xtensa/kernel/time.c
+++ b/arch/xtensa/kernel/time.c
@@ -14,7 +14,7 @@
 
 #include <linux/errno.h>
 #include <linux/time.h>
-#include <linux/timex.h>
+#include <linux/clocksource.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
 #include <linux/init.h>
@@ -25,27 +25,31 @@
 #include <asm/timex.h>
 #include <asm/platform.h>
 
-
-DEFINE_SPINLOCK(rtc_lock);
-EXPORT_SYMBOL(rtc_lock);
-
-
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
 unsigned long ccount_per_jiffy;		/* per 1/HZ */
 unsigned long nsec_per_ccount;		/* nsec per ccount increment */
 #endif
 
-static long last_rtc_update = 0;
-
-/*
- * Scheduler clock - returns current tim in nanosec units.
- */
-
-unsigned long long sched_clock(void)
+static cycle_t ccount_read(void)
 {
-	return (unsigned long long)jiffies * (1000000000 / HZ);
+	return (cycle_t)get_ccount();
 }
 
+static struct clocksource ccount_clocksource = {
+	.name = "ccount",
+	.rating = 200,
+	.read = ccount_read,
+	.mask = CLOCKSOURCE_MASK(32),
+	/*
+	 * With a shift of 22 the lower limit of the cpu clock is
+	 * 1MHz, where NSEC_PER_CCOUNT is 1000 or a bit less than
+	 * 2^10: Since we have 32 bits and the multiplicator can
+	 * already take up as much as 10 bits, this leaves us with
+	 * remaining upper 22 bits.
+	 */
+	.shift = 22,
+};
+
 static irqreturn_t timer_interrupt(int irq, void *dev_id);
 static struct irqaction timer_irqaction = {
 	.handler =	timer_interrupt,
@@ -55,11 +59,11 @@ static struct irqaction timer_irqaction = {
 
 void __init time_init(void)
 {
-	time_t sec_o, sec_n = 0;
+	xtime.tv_nsec = 0;
+	xtime.tv_sec = read_persistent_clock();
 
-	/* The platform must provide a function to calibrate the processor
-	 * speed for the CALIBRATE.
-	 */
+	set_normalized_timespec(&wall_to_monotonic,
+		-xtime.tv_sec, -xtime.tv_nsec);
 
 #ifdef CONFIG_XTENSA_CALIBRATE_CCOUNT
 	printk("Calibrating CPU frequency ");
@@ -67,19 +71,10 @@ void __init time_init(void)
 	printk("%d.%02d MHz\n", (int)ccount_per_jiffy/(1000000/HZ),
 			(int)(ccount_per_jiffy/(10000/HZ))%100);
 #endif
-
-	/* Set time from RTC (if provided) */
-
-	if (platform_get_rtc_time(&sec_o) == 0)
-		while (platform_get_rtc_time(&sec_n))
-			if (sec_o != sec_n)
-				break;
-
-	xtime.tv_nsec = 0;
-	last_rtc_update = xtime.tv_sec = sec_n;
-
-	set_normalized_timespec(&wall_to_monotonic,
-		-xtime.tv_sec, -xtime.tv_nsec);
+	ccount_clocksource.mult =
+		clocksource_hz2mult(CCOUNT_PER_JIFFY * HZ,
+				ccount_clocksource.shift);
+	clocksource_register(&ccount_clocksource);
 
 	/* Initialize the linux timer interrupt. */
 
@@ -87,69 +82,6 @@ void __init time_init(void)
 	set_linux_timer(get_ccount() + CCOUNT_PER_JIFFY);
 }
 
-
-int do_settimeofday(struct timespec *tv)
-{
-	time_t wtm_sec, sec = tv->tv_sec;
-	long wtm_nsec, nsec = tv->tv_nsec;
-	unsigned long delta;
-
-	if ((unsigned long)tv->tv_nsec >= NSEC_PER_SEC)
-		return -EINVAL;
-
-	write_seqlock_irq(&xtime_lock);
-
-	/* This is revolting. We need to set "xtime" correctly. However, the
-	 * value in this location is the value at the most recent update of
-	 * wall time.  Discover what correction gettimeofday() would have
-	 * made, and then undo it!
-	 */
-
-	delta = CCOUNT_PER_JIFFY;
-	delta += get_ccount() - get_linux_timer();
-	nsec -= delta * NSEC_PER_CCOUNT;
-
-	wtm_sec  = wall_to_monotonic.tv_sec + (xtime.tv_sec - sec);
-	wtm_nsec = wall_to_monotonic.tv_nsec + (xtime.tv_nsec - nsec);
-
-	set_normalized_timespec(&xtime, sec, nsec);
-	set_normalized_timespec(&wall_to_monotonic, wtm_sec, wtm_nsec);
-
-	ntp_clear();
-	write_sequnlock_irq(&xtime_lock);
-	return 0;
-}
-
-EXPORT_SYMBOL(do_settimeofday);
-
-
-void do_gettimeofday(struct timeval *tv)
-{
-	unsigned long flags;
-	unsigned long volatile sec, usec, delta, seq;
-
-	do {
-		seq = read_seqbegin_irqsave(&xtime_lock, flags);
-
-		sec = xtime.tv_sec;
-		usec = (xtime.tv_nsec / NSEC_PER_USEC);
-
-		delta = get_linux_timer() - get_ccount();
-
-	} while (read_seqretry_irqrestore(&xtime_lock, seq, flags));
-
-	usec += (((unsigned long) CCOUNT_PER_JIFFY - delta)
-		 * (unsigned long) NSEC_PER_CCOUNT) / NSEC_PER_USEC;
-
-	for (; usec >= 1000000; sec++, usec -= 1000000)
-		;
-
-	tv->tv_sec = sec;
-	tv->tv_usec = usec;
-}
-
-EXPORT_SYMBOL(do_gettimeofday);
-
 /*
  * The timer interrupt is called HZ times per second.
  */
@@ -178,16 +110,6 @@ again:
 		next += CCOUNT_PER_JIFFY;
 		set_linux_timer(next);
 
-		if (ntp_synced() &&
-		    xtime.tv_sec - last_rtc_update >= 659 &&
-		    abs((xtime.tv_nsec/1000)-(1000000-1000000/HZ))<5000000/HZ) {
-
-			if (platform_set_rtc_time(xtime.tv_sec+1) == 0)
-				last_rtc_update = xtime.tv_sec+1;
-			else
-				/* Do it again in 60 s */
-				last_rtc_update += 60;
-		}
 		write_sequnlock(&xtime_lock);
 	}
 
@@ -213,4 +135,3 @@ void __cpuinit calibrate_delay(void)
 	       (loops_per_jiffy/(10000/HZ)) % 100);
 }
 #endif
-
diff --git a/arch/xtensa/kernel/traps.c b/arch/xtensa/kernel/traps.c
index c44f830b6c7a..9f0b71189e94 100644
--- a/arch/xtensa/kernel/traps.c
+++ b/arch/xtensa/kernel/traps.c
@@ -104,6 +104,7 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = {
 #endif
 { EXCCAUSE_UNALIGNED,		KRNL,	   fast_unaligned },
 #endif
+#ifdef CONFIG_MMU
 { EXCCAUSE_ITLB_MISS,		0,	   do_page_fault },
 { EXCCAUSE_ITLB_MISS,		USER|KRNL, fast_second_level_miss},
 { EXCCAUSE_ITLB_MULTIHIT,		0,	   do_multihit },
@@ -118,6 +119,7 @@ static dispatch_init_table_t __initdata dispatch_init_table[] = {
 { EXCCAUSE_STORE_CACHE_ATTRIBUTE,	USER|KRNL, fast_store_prohibited },
 { EXCCAUSE_STORE_CACHE_ATTRIBUTE,	0,	   do_page_fault },
 { EXCCAUSE_LOAD_CACHE_ATTRIBUTE,	0,	   do_page_fault },
+#endif /* CONFIG_MMU */
 /* XCCHAL_EXCCAUSE_FLOATING_POINT unhandled */
 #if XTENSA_HAVE_COPROCESSOR(0)
 COPROCESSOR(0),
@@ -372,11 +374,10 @@ void show_trace(struct task_struct *task, unsigned long *sp)
 	unsigned long a0, a1, pc;
 	unsigned long sp_start, sp_end;
 
-	a1 = (unsigned long)sp;
-
-	if (a1 == 0)
-		__asm__ __volatile__ ("mov %0, a1\n" : "=a"(a1));
-
+	if (sp)
+		a1 = (unsigned long)sp;
+	else
+		a1 = task->thread.sp;
 
 	sp_start = a1 & ~(THREAD_SIZE-1);
 	sp_end = sp_start + THREAD_SIZE;
@@ -418,9 +419,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 	int i = 0;
 	unsigned long *stack;
 
-	if (sp == 0)
-		__asm__ __volatile__ ("mov %0, a1\n" : "=a"(sp));
-
+	if (!sp)
+		sp = (unsigned long *)task->thread.sp;
  	stack = sp;
 
 	printk("\nStack: ");
diff --git a/arch/xtensa/kernel/vectors.S b/arch/xtensa/kernel/vectors.S
index eb2d7bb69ee0..74a7518faf16 100644
--- a/arch/xtensa/kernel/vectors.S
+++ b/arch/xtensa/kernel/vectors.S
@@ -309,6 +309,7 @@ ENTRY(_DoubleExceptionVector)
 	 * All other exceptions are unexpected and thus unrecoverable!
 	 */
 
+#ifdef CONFIG_MMU
 	.extern fast_second_level_miss_double_kernel
 
 .Lksp:	/* a0: a0, a1: a1, a2: a2, a3: trashed, depc: depc, excsave: a3 */
@@ -319,6 +320,9 @@ ENTRY(_DoubleExceptionVector)
 	bnez	a3, .Lunrecoverable
 1:	movi	a3, fast_second_level_miss_double_kernel
 	jx	a3
+#else
+.equ	.Lksp,	.Lunrecoverable
+#endif
 
 	/* Critical! We can't handle this situation. PANIC! */
 
diff --git a/arch/xtensa/kernel/vmlinux.lds.S b/arch/xtensa/kernel/vmlinux.lds.S
index d506774f4b05..c1be9a4a740c 100644
--- a/arch/xtensa/kernel/vmlinux.lds.S
+++ b/arch/xtensa/kernel/vmlinux.lds.S
@@ -17,6 +17,7 @@
 #include <asm-generic/vmlinux.lds.h>
 
 #include <variant/core.h>
+#include <platform/hardware.h>
 OUTPUT_ARCH(xtensa)
 ENTRY(_start)
 
@@ -26,7 +27,9 @@ jiffies = jiffies_64 + 4;
 jiffies = jiffies_64;
 #endif
 
+#ifndef KERNELOFFSET
 #define KERNELOFFSET 0xd0001000
+#endif
 
 /* Note: In the following macros, it would be nice to specify only the
    vector name and section kind and construct "sym" and "section" using
diff --git a/arch/xtensa/mm/Makefile b/arch/xtensa/mm/Makefile
index 64e304a2f884..f0b646d2f843 100644
--- a/arch/xtensa/mm/Makefile
+++ b/arch/xtensa/mm/Makefile
@@ -2,4 +2,5 @@
 # Makefile for the Linux/Xtensa-specific parts of the memory manager.
 #
 
-obj-y	 := init.o fault.o tlb.o misc.o cache.o
+obj-y			:= init.o cache.o misc.o
+obj-$(CONFIG_MMU)	+= fault.o mmu.o tlb.o
diff --git a/arch/xtensa/mm/init.c b/arch/xtensa/mm/init.c
index 34163cfaaffc..427e14fa43c5 100644
--- a/arch/xtensa/mm/init.c
+++ b/arch/xtensa/mm/init.c
@@ -24,15 +24,8 @@
 #include <linux/mm.h>
 #include <linux/slab.h>
 
-#include <asm/pgtable.h>
 #include <asm/bootparam.h>
-#include <asm/mmu_context.h>
-#include <asm/tlb.h>
 #include <asm/page.h>
-#include <asm/pgalloc.h>
-
-
-DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
 
 /* References to section boundaries */
 
@@ -130,7 +123,8 @@ void __init bootmem_init(void)
 
 	/* Find an area to use for the bootmem bitmap. */
 
-	bootmap_size = bootmem_bootmap_pages(max_low_pfn) << PAGE_SHIFT;
+	bootmap_size = bootmem_bootmap_pages(max_low_pfn - min_low_pfn);
+	bootmap_size <<= PAGE_SHIFT;
 	bootmap_start = ~0;
 
 	for (i=0; i<sysmem.nr_banks; i++)
@@ -145,8 +139,9 @@ void __init bootmem_init(void)
 	/* Reserve the bootmem bitmap area */
 
 	mem_reserve(bootmap_start, bootmap_start + bootmap_size, 1);
-	bootmap_size = init_bootmem_node(NODE_DATA(0), min_low_pfn,
+	bootmap_size = init_bootmem_node(NODE_DATA(0),
 					 bootmap_start >> PAGE_SHIFT,
+					 min_low_pfn,
 					 max_low_pfn);
 
 	/* Add all remaining memory pieces into the bootmem map */
@@ -158,14 +153,14 @@ void __init bootmem_init(void)
 }
 
 
-void __init paging_init(void)
+void __init zones_init(void)
 {
 	unsigned long zones_size[MAX_NR_ZONES];
 	int i;
 
 	/* All pages are DMA-able, so we put them all in the DMA zone. */
 
-	zones_size[ZONE_DMA] = max_low_pfn;
+	zones_size[ZONE_DMA] = max_low_pfn - ARCH_PFN_OFFSET;
 	for (i = 1; i < MAX_NR_ZONES; i++)
 		zones_size[i] = 0;
 
@@ -173,40 +168,7 @@ void __init paging_init(void)
 	zones_size[ZONE_HIGHMEM] = max_pfn - max_low_pfn;
 #endif
 
-	/* Initialize the kernel's page tables. */
-
-	memset(swapper_pg_dir, 0, PAGE_SIZE);
-
-	free_area_init(zones_size);
-}
-
-/*
- * Flush the mmu and reset associated register to default values.
- */
-
-void __init init_mmu (void)
-{
-	/* Writing zeros to the <t>TLBCFG special registers ensure
-	 * that valid values exist in the register.  For existing
-	 * PGSZID<w> fields, zero selects the first element of the
-	 * page-size array.  For nonexistent PGSZID<w> fields, zero is
-	 * the best value to write.  Also, when changing PGSZID<w>
-	 * fields, the corresponding TLB must be flushed.
-	 */
-	set_itlbcfg_register (0);
-	set_dtlbcfg_register (0);
-	flush_tlb_all ();
-
-	/* Set rasid register to a known value. */
-
-	set_rasid_register (ASID_USER_FIRST);
-
-	/* Set PTEVADDR special register to the start of the page
-	 * table, which is in kernel mappable space (ie. not
-	 * statically mapped).  This register's value is undefined on
-	 * reset.
-	 */
-	set_ptevaddr_register (PGTABLE_START);
+	free_area_init_node(0, zones_size, ARCH_PFN_OFFSET, NULL);
 }
 
 /*
@@ -218,8 +180,8 @@ void __init mem_init(void)
 	unsigned long codesize, reservedpages, datasize, initsize;
 	unsigned long highmemsize, tmp, ram;
 
-	max_mapnr = num_physpages = max_low_pfn;
-	high_memory = (void *) __va(max_mapnr << PAGE_SHIFT);
+	max_mapnr = num_physpages = max_low_pfn - ARCH_PFN_OFFSET;
+	high_memory = (void *) __va(max_low_pfn << PAGE_SHIFT);
 	highmemsize = 0;
 
 #ifdef CONFIG_HIGHMEM
@@ -229,7 +191,7 @@ void __init mem_init(void)
 	totalram_pages += free_all_bootmem();
 
 	reservedpages = ram = 0;
-	for (tmp = 0; tmp < max_low_pfn; tmp++) {
+	for (tmp = 0; tmp < max_mapnr; tmp++) {
 		ram++;
 		if (PageReserved(mem_map+tmp))
 			reservedpages++;
@@ -279,23 +241,3 @@ void free_initmem(void)
 	printk("Freeing unused kernel memory: %dk freed\n",
 	       (&__init_end - &__init_begin) >> 10);
 }
-
-struct kmem_cache *pgtable_cache __read_mostly;
-
-static void pgd_ctor(void* addr)
-{
-	pte_t* ptep = (pte_t*)addr;
-	int i;
-
-	for (i = 0; i < 1024; i++, ptep++)
-		pte_clear(NULL, 0, ptep);
-
-}
-
-void __init pgtable_cache_init(void)
-{
-	pgtable_cache = kmem_cache_create("pgd",
-			PAGE_SIZE, PAGE_SIZE,
-			SLAB_HWCACHE_ALIGN,
-			pgd_ctor);
-}
diff --git a/arch/xtensa/mm/misc.S b/arch/xtensa/mm/misc.S
index c885664211d1..b048406d8756 100644
--- a/arch/xtensa/mm/misc.S
+++ b/arch/xtensa/mm/misc.S
@@ -84,6 +84,7 @@ ENTRY(copy_page)
 
 	retw
 
+#ifdef CONFIG_MMU
 /*
  * If we have to deal with cache aliasing, we use temporary memory mappings
  * to ensure that the source and destination pages have the same color as
@@ -311,6 +312,7 @@ ENTRY(__invalidate_icache_page_alias)
 /* End of special treatment in tlb miss exception */
 
 ENTRY(__tlbtemp_mapping_end)
+#endif /* CONFIG_MMU
 
 /*
  * void __invalidate_icache_page(ulong start)
diff --git a/arch/xtensa/mm/mmu.c b/arch/xtensa/mm/mmu.c
new file mode 100644
index 000000000000..4bb91a970f1f
--- /dev/null
+++ b/arch/xtensa/mm/mmu.c
@@ -0,0 +1,70 @@
+/*
+ * xtensa mmu stuff
+ *
+ * Extracted from init.c
+ */
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/string.h>
+#include <linux/slab.h>
+#include <linux/cache.h>
+
+#include <asm/tlb.h>
+#include <asm/tlbflush.h>
+#include <asm/mmu_context.h>
+#include <asm/page.h>
+
+DEFINE_PER_CPU(struct mmu_gather, mmu_gathers);
+
+void __init paging_init(void)
+{
+	memset(swapper_pg_dir, 0, PAGE_SIZE);
+}
+
+/*
+ * Flush the mmu and reset associated register to default values.
+ */
+void __init init_mmu(void)
+{
+	/* Writing zeros to the <t>TLBCFG special registers ensure
+	 * that valid values exist in the register.  For existing
+	 * PGSZID<w> fields, zero selects the first element of the
+	 * page-size array.  For nonexistent PGSZID<w> fields, zero is
+	 * the best value to write.  Also, when changing PGSZID<w>
+	 * fields, the corresponding TLB must be flushed.
+	 */
+	set_itlbcfg_register(0);
+	set_dtlbcfg_register(0);
+	flush_tlb_all();
+
+	/* Set rasid register to a known value. */
+
+	set_rasid_register(ASID_USER_FIRST);
+
+	/* Set PTEVADDR special register to the start of the page
+	 * table, which is in kernel mappable space (ie. not
+	 * statically mapped).  This register's value is undefined on
+	 * reset.
+	 */
+	set_ptevaddr_register(PGTABLE_START);
+}
+
+struct kmem_cache *pgtable_cache __read_mostly;
+
+static void pgd_ctor(void *addr)
+{
+	pte_t *ptep = (pte_t *)addr;
+	int i;
+
+	for (i = 0; i < 1024; i++, ptep++)
+		pte_clear(NULL, 0, ptep);
+
+}
+
+void __init pgtable_cache_init(void)
+{
+	pgtable_cache = kmem_cache_create("pgd",
+			PAGE_SIZE, PAGE_SIZE,
+			SLAB_HWCACHE_ALIGN,
+			pgd_ctor);
+}
diff --git a/arch/xtensa/platforms/s6105/Makefile b/arch/xtensa/platforms/s6105/Makefile
new file mode 100644
index 000000000000..0be6194bcb72
--- /dev/null
+++ b/arch/xtensa/platforms/s6105/Makefile
@@ -0,0 +1,3 @@
+# Makefile for the Stretch S6105 eval board
+
+obj-y		:= setup.o device.o
diff --git a/arch/xtensa/platforms/s6105/device.c b/arch/xtensa/platforms/s6105/device.c
new file mode 100644
index 000000000000..78b08be5a92d
--- /dev/null
+++ b/arch/xtensa/platforms/s6105/device.c
@@ -0,0 +1,67 @@
+/*
+ * s6105 platform devices
+ *
+ * Copyright (c) 2009 emlix GmbH
+ */
+
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/platform_device.h>
+#include <linux/serial.h>
+#include <linux/serial_8250.h>
+
+#include <variant/hardware.h>
+
+#define UART_INTNUM		4
+
+static const signed char uart_irq_mappings[] = {
+	S6_INTC_UART(0),
+	S6_INTC_UART(1),
+	-1,
+};
+
+const signed char *platform_irq_mappings[NR_IRQS] = {
+	[UART_INTNUM] = uart_irq_mappings,
+};
+
+static struct plat_serial8250_port serial_platform_data[] = {
+	{
+		.membase = (void *)S6_REG_UART + 0x0000,
+		.mapbase = S6_REG_UART + 0x0000,
+		.irq = UART_INTNUM,
+		.uartclk = S6_SCLK,
+		.regshift = 2,
+		.iotype = SERIAL_IO_MEM,
+		.flags = ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST,
+	},
+	{
+		.membase = (void *)S6_REG_UART + 0x1000,
+		.mapbase = S6_REG_UART + 0x1000,
+		.irq = UART_INTNUM,
+		.uartclk = S6_SCLK,
+		.regshift = 2,
+		.iotype = SERIAL_IO_MEM,
+		.flags = ASYNC_BOOT_AUTOCONF | ASYNC_SKIP_TEST,
+	},
+	{ },
+};
+
+static struct platform_device platform_devices[] = {
+	{
+		.name = "serial8250",
+		.id = PLAT8250_DEV_PLATFORM,
+		.dev = {
+			.platform_data = serial_platform_data,
+		},
+	},
+};
+
+static int __init device_init(void)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(platform_devices); i++)
+		platform_device_register(&platform_devices[i]);
+	return 0;
+}
+arch_initcall_sync(device_init);
diff --git a/arch/xtensa/platforms/s6105/include/platform/gpio.h b/arch/xtensa/platforms/s6105/include/platform/gpio.h
new file mode 100644
index 000000000000..fa11aa4b61e9
--- /dev/null
+++ b/arch/xtensa/platforms/s6105/include/platform/gpio.h
@@ -0,0 +1,27 @@
+#ifndef __ASM_XTENSA_S6105_GPIO_H
+#define __ASM_XTENSA_S6105_GPIO_H
+
+#define GPIO_BP_TEMP_ALARM	0
+#define GPIO_PB_RESET_IN	1
+#define GPIO_EXP_IRQ		2
+#define GPIO_TRIGGER_IRQ	3
+#define GPIO_RTC_IRQ		4
+#define GPIO_PHY_IRQ		5
+#define GPIO_IMAGER_RESET	6
+#define GPIO_SD_IRQ		7
+#define GPIO_MINI_BOOT_INH	8
+#define GPIO_BOARD_RESET	9
+#define GPIO_EXP_PRESENT	10
+#define GPIO_LED1_NGREEN	12
+#define GPIO_LED1_RED		13
+#define GPIO_LED0_NGREEN	14
+#define GPIO_LED0_NRED		15
+#define GPIO_SPI_CS0		16
+#define GPIO_SPI_CS1		17
+#define GPIO_SPI_CS3		19
+#define GPIO_SPI_CS4		20
+#define GPIO_SD_WP		21
+#define GPIO_BP_RESET		22
+#define GPIO_ALARM_OUT		23
+
+#endif /* __ASM_XTENSA_S6105_GPIO_H */
diff --git a/arch/xtensa/platforms/s6105/include/platform/hardware.h b/arch/xtensa/platforms/s6105/include/platform/hardware.h
new file mode 100644
index 000000000000..d628efac7089
--- /dev/null
+++ b/arch/xtensa/platforms/s6105/include/platform/hardware.h
@@ -0,0 +1,11 @@
+#ifndef __XTENSA_S6105_HARDWARE_H
+#define __XTENSA_S6105_HARDWARE_H
+
+#define PLATFORM_DEFAULT_MEM_START	0x40000000
+#define PLATFORM_DEFAULT_MEM_SIZE	0x08000000
+
+#define MAX_DMA_ADDRESS			0
+
+#define KERNELOFFSET			(PLATFORM_DEFAULT_MEM_START + 0x1000)
+
+#endif /* __XTENSA_S6105_HARDWARE_H */
diff --git a/arch/xtensa/platforms/s6105/include/platform/serial.h b/arch/xtensa/platforms/s6105/include/platform/serial.h
new file mode 100644
index 000000000000..c8a771e5981b
--- /dev/null
+++ b/arch/xtensa/platforms/s6105/include/platform/serial.h
@@ -0,0 +1,8 @@
+#ifndef __ASM_XTENSA_S6105_SERIAL_H
+#define __ASM_XTENSA_S6105_SERIAL_H
+
+#include <variant/hardware.h>
+
+#define BASE_BAUD (S6_SCLK / 16)
+
+#endif /* __ASM_XTENSA_S6105_SERIAL_H */
diff --git a/arch/xtensa/platforms/s6105/setup.c b/arch/xtensa/platforms/s6105/setup.c
new file mode 100644
index 000000000000..ae041d5027a2
--- /dev/null
+++ b/arch/xtensa/platforms/s6105/setup.c
@@ -0,0 +1,61 @@
+/*
+ * s6105 control routines
+ *
+ * Copyright (c) 2009 emlix GmbH
+ */
+#include <linux/irq.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+
+#include <asm/bootparam.h>
+
+#include <variant/hardware.h>
+#include <platform/gpio.h>
+
+void platform_halt(void)
+{
+	local_irq_disable();
+	while (1)
+		;
+}
+
+void platform_power_off(void)
+{
+	platform_halt();
+}
+
+void platform_restart(void)
+{
+	platform_halt();
+}
+
+void __init platform_setup(char **cmdline)
+{
+	unsigned long reg;
+
+	reg = readl(S6_REG_GREG1 + S6_GREG1_CLKGATE);
+	reg &= ~(1 << S6_GREG1_BLOCK_SB);
+	writel(reg, S6_REG_GREG1 + S6_GREG1_CLKGATE);
+
+	reg = readl(S6_REG_GREG1 + S6_GREG1_BLOCKENA);
+	reg |= 1 << S6_GREG1_BLOCK_SB;
+	writel(reg, S6_REG_GREG1 + S6_GREG1_BLOCKENA);
+
+	printk(KERN_NOTICE "S6105 on Stretch S6000 - "
+		"Copyright (C) 2009 emlix GmbH <info@emlix.com>\n");
+}
+
+void __init platform_init(bp_tag_t *first)
+{
+	gpio_request(GPIO_LED1_NGREEN, "led1_green");
+	gpio_request(GPIO_LED1_RED, "led1_red");
+	gpio_direction_output(GPIO_LED1_NGREEN, 1);
+}
+
+void platform_heartbeat(void)
+{
+	static unsigned int c;
+
+	if (!(++c & 0x4F))
+		gpio_direction_output(GPIO_LED1_RED, !(c & 0x10));
+}
diff --git a/arch/xtensa/platforms/xt2000/include/platform/hardware.h b/arch/xtensa/platforms/xt2000/include/platform/hardware.h
index 41459ad07766..886ef156ded3 100644
--- a/arch/xtensa/platforms/xt2000/include/platform/hardware.h
+++ b/arch/xtensa/platforms/xt2000/include/platform/hardware.h
@@ -16,7 +16,6 @@
 #define _XTENSA_XT2000_HARDWARE_H
 
 #include <variant/core.h>
-#include <asm/io.h>
 
 /* 
  * Memory configuration.
diff --git a/arch/xtensa/variants/s6000/Makefile b/arch/xtensa/variants/s6000/Makefile
new file mode 100644
index 000000000000..03b3975468bd
--- /dev/null
+++ b/arch/xtensa/variants/s6000/Makefile
@@ -0,0 +1,3 @@
+# s6000 Makefile
+
+obj-y		+= irq.o gpio.o
diff --git a/arch/xtensa/variants/s6000/gpio.c b/arch/xtensa/variants/s6000/gpio.c
new file mode 100644
index 000000000000..33a8d952934c
--- /dev/null
+++ b/arch/xtensa/variants/s6000/gpio.c
@@ -0,0 +1,71 @@
+/*
+ * s6000 gpio driver
+ *
+ * Copyright (c) 2009 emlix GmbH
+ * Authors:	Oskar Schirmer <os@emlix.com>
+ *		Johannes Weiner <jw@emlix.com>
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/gpio.h>
+
+#include <variant/hardware.h>
+
+#define S6_GPIO_DATA		0x000
+#define S6_GPIO_IS		0x404
+#define S6_GPIO_IBE		0x408
+#define S6_GPIO_IEV		0x40C
+#define S6_GPIO_IE		0x410
+#define S6_GPIO_RIS		0x414
+#define S6_GPIO_MIS		0x418
+#define S6_GPIO_IC		0x41C
+#define S6_GPIO_AFSEL		0x420
+#define S6_GPIO_DIR		0x800
+#define S6_GPIO_BANK(nr)	((nr) * 0x1000)
+#define S6_GPIO_MASK(nr)	(4 << (nr))
+#define S6_GPIO_OFFSET(nr) \
+		(S6_GPIO_BANK((nr) >> 3) + S6_GPIO_MASK((nr) & 7))
+
+static int direction_input(struct gpio_chip *chip, unsigned int off)
+{
+	writeb(0, S6_REG_GPIO + S6_GPIO_DIR + S6_GPIO_OFFSET(off));
+	return 0;
+}
+
+static int get(struct gpio_chip *chip, unsigned int off)
+{
+	return readb(S6_REG_GPIO + S6_GPIO_DATA + S6_GPIO_OFFSET(off));
+}
+
+static int direction_output(struct gpio_chip *chip, unsigned int off, int val)
+{
+	unsigned rel = S6_GPIO_OFFSET(off);
+	writeb(~0, S6_REG_GPIO + S6_GPIO_DIR + rel);
+	writeb(val ? ~0 : 0, S6_REG_GPIO + S6_GPIO_DATA + rel);
+	return 0;
+}
+
+static void set(struct gpio_chip *chip, unsigned int off, int val)
+{
+	writeb(val ? ~0 : 0, S6_REG_GPIO + S6_GPIO_DATA + S6_GPIO_OFFSET(off));
+}
+
+static struct gpio_chip gpiochip = {
+	.owner = THIS_MODULE,
+	.direction_input = direction_input,
+	.get = get,
+	.direction_output = direction_output,
+	.set = set,
+	.base = 0,
+	.ngpio = 24,
+	.can_sleep = 0, /* no blocking io needed */
+	.exported = 0, /* no exporting to userspace */
+};
+
+static int gpio_init(void)
+{
+	return gpiochip_add(&gpiochip);
+}
+device_initcall(gpio_init);
diff --git a/arch/xtensa/variants/s6000/include/variant/core.h b/arch/xtensa/variants/s6000/include/variant/core.h
new file mode 100644
index 000000000000..af007953027e
--- /dev/null
+++ b/arch/xtensa/variants/s6000/include/variant/core.h
@@ -0,0 +1,431 @@
+/*
+ * Xtensa processor core configuration information.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1999-2008 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_CORE_CONFIGURATION_H
+#define _XTENSA_CORE_CONFIGURATION_H
+
+
+/****************************************************************************
+	    Parameters Useful for Any Code, USER or PRIVILEGED
+ ****************************************************************************/
+
+/*
+ *  Note:  Macros of the form XCHAL_HAVE_*** have a value of 1 if the option is
+ *  configured, and a value of 0 otherwise.  These macros are always defined.
+ */
+
+
+/*----------------------------------------------------------------------
+				ISA
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_BE			0	/* big-endian byte ordering */
+#define XCHAL_HAVE_WINDOWED		1	/* windowed registers option */
+#define XCHAL_NUM_AREGS			64	/* num of physical addr regs */
+#define XCHAL_NUM_AREGS_LOG2		6	/* log2(XCHAL_NUM_AREGS) */
+#define XCHAL_MAX_INSTRUCTION_SIZE	8	/* max instr bytes (3..8) */
+#define XCHAL_HAVE_DEBUG		1	/* debug option */
+#define XCHAL_HAVE_DENSITY		1	/* 16-bit instructions */
+#define XCHAL_HAVE_LOOPS		1	/* zero-overhead loops */
+#define XCHAL_HAVE_NSA			1	/* NSA/NSAU instructions */
+#define XCHAL_HAVE_MINMAX		1	/* MIN/MAX instructions */
+#define XCHAL_HAVE_SEXT			1	/* SEXT instruction */
+#define XCHAL_HAVE_CLAMPS		1	/* CLAMPS instruction */
+#define XCHAL_HAVE_MUL16		1	/* MUL16S/MUL16U instructions */
+#define XCHAL_HAVE_MUL32		1	/* MULL instruction */
+#define XCHAL_HAVE_MUL32_HIGH		1	/* MULUH/MULSH instructions */
+#define XCHAL_HAVE_DIV32		0	/* QUOS/QUOU/REMS/REMU instructions */
+#define XCHAL_HAVE_L32R			1	/* L32R instruction */
+#define XCHAL_HAVE_ABSOLUTE_LITERALS	1	/* non-PC-rel (extended) L32R */
+#define XCHAL_HAVE_CONST16		0	/* CONST16 instruction */
+#define XCHAL_HAVE_ADDX			1	/* ADDX#/SUBX# instructions */
+#define XCHAL_HAVE_WIDE_BRANCHES	0	/* B*.W18 or B*.W15 instr's */
+#define XCHAL_HAVE_PREDICTED_BRANCHES	0	/* B[EQ/EQZ/NE/NEZ]T instr's */
+#define XCHAL_HAVE_CALL4AND12		1	/* (obsolete option) */
+#define XCHAL_HAVE_ABS			1	/* ABS instruction */
+/*#define XCHAL_HAVE_POPC		0*/	/* POPC instruction */
+/*#define XCHAL_HAVE_CRC		0*/	/* CRC instruction */
+#define XCHAL_HAVE_RELEASE_SYNC		0	/* L32AI/S32RI instructions */
+#define XCHAL_HAVE_S32C1I		0	/* S32C1I instruction */
+#define XCHAL_HAVE_SPECULATION		0	/* speculation */
+#define XCHAL_HAVE_FULL_RESET		0	/* all regs/state reset */
+#define XCHAL_NUM_CONTEXTS		1	/* */
+#define XCHAL_NUM_MISC_REGS		4	/* num of scratch regs (0..4) */
+#define XCHAL_HAVE_TAP_MASTER		0	/* JTAG TAP control instr's */
+#define XCHAL_HAVE_PRID			0	/* processor ID register */
+#define XCHAL_HAVE_THREADPTR		0	/* THREADPTR register */
+#define XCHAL_HAVE_BOOLEANS		1	/* boolean registers */
+#define XCHAL_HAVE_CP			1	/* CPENABLE reg (coprocessor) */
+#define XCHAL_CP_MAXCFG			8	/* max allowed cp id plus one */
+#define XCHAL_HAVE_MAC16		0	/* MAC16 package */
+#define XCHAL_HAVE_VECTORFPU2005	0	/* vector floating-point pkg */
+#define XCHAL_HAVE_FP			1	/* floating point pkg */
+#define XCHAL_HAVE_VECTRA1		0	/* Vectra I  pkg */
+#define XCHAL_HAVE_VECTRALX		0	/* Vectra LX pkg */
+#define XCHAL_HAVE_HIFI2		0	/* HiFi2 Audio Engine pkg */
+
+
+/*----------------------------------------------------------------------
+				MISC
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_NUM_WRITEBUFFER_ENTRIES	8	/* size of write buffer */
+#define XCHAL_INST_FETCH_WIDTH		8	/* instr-fetch width in bytes */
+#define XCHAL_DATA_WIDTH		16	/* data width in bytes */
+/*  In T1050, applies to selected core load and store instructions (see ISA): */
+#define XCHAL_UNALIGNED_LOAD_EXCEPTION	1	/* unaligned loads cause exc. */
+#define XCHAL_UNALIGNED_STORE_EXCEPTION	1	/* unaligned stores cause exc.*/
+
+#define XCHAL_SW_VERSION		701001	/* sw version of this header */
+
+#define XCHAL_CORE_ID			"stretch_bali"	/* alphanum core name
+						   (CoreID) set in the Xtensa
+						   Processor Generator */
+
+#define XCHAL_BUILD_UNIQUE_ID		0x000104B9	/* 22-bit sw build ID */
+
+/*
+ *  These definitions describe the hardware targeted by this software.
+ */
+#define XCHAL_HW_CONFIGID0		0xC2F3F9FE	/* ConfigID hi 32 bits*/
+#define XCHAL_HW_CONFIGID1		0x054104B9	/* ConfigID lo 32 bits*/
+#define XCHAL_HW_VERSION_NAME		"LX1.0.2"	/* full version name */
+#define XCHAL_HW_VERSION_MAJOR		2100	/* major ver# of targeted hw */
+#define XCHAL_HW_VERSION_MINOR		2	/* minor ver# of targeted hw */
+#define XCHAL_HW_VERSION		210002	/* major*100+minor */
+#define XCHAL_HW_REL_LX1		1
+#define XCHAL_HW_REL_LX1_0		1
+#define XCHAL_HW_REL_LX1_0_2		1
+#define XCHAL_HW_CONFIGID_RELIABLE	1
+/*  If software targets a *range* of hardware versions, these are the bounds: */
+#define XCHAL_HW_MIN_VERSION_MAJOR	2100	/* major v of earliest tgt hw */
+#define XCHAL_HW_MIN_VERSION_MINOR	2	/* minor v of earliest tgt hw */
+#define XCHAL_HW_MIN_VERSION		210002	/* earliest targeted hw */
+#define XCHAL_HW_MAX_VERSION_MAJOR	2100	/* major v of latest tgt hw */
+#define XCHAL_HW_MAX_VERSION_MINOR	2	/* minor v of latest tgt hw */
+#define XCHAL_HW_MAX_VERSION		210002	/* latest targeted hw */
+
+
+/*----------------------------------------------------------------------
+				CACHE
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_ICACHE_LINESIZE		16	/* I-cache line size in bytes */
+#define XCHAL_DCACHE_LINESIZE		16	/* D-cache line size in bytes */
+#define XCHAL_ICACHE_LINEWIDTH		4	/* log2(I line size in bytes) */
+#define XCHAL_DCACHE_LINEWIDTH		4	/* log2(D line size in bytes) */
+
+#define XCHAL_ICACHE_SIZE		32768	/* I-cache size in bytes or 0 */
+#define XCHAL_DCACHE_SIZE		32768	/* D-cache size in bytes or 0 */
+
+#define XCHAL_DCACHE_IS_WRITEBACK	1	/* writeback feature */
+
+
+
+
+/****************************************************************************
+    Parameters Useful for PRIVILEGED (Supervisory or Non-Virtualized) Code
+ ****************************************************************************/
+
+
+#ifndef XTENSA_HAL_NON_PRIVILEGED_ONLY
+
+/*----------------------------------------------------------------------
+				CACHE
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_PIF			1	/* any outbound PIF present */
+
+/*  If present, cache size in bytes == (ways * 2^(linewidth + setwidth)).  */
+
+/*  Number of cache sets in log2(lines per way):  */
+#define XCHAL_ICACHE_SETWIDTH		9
+#define XCHAL_DCACHE_SETWIDTH		10
+
+/*  Cache set associativity (number of ways):  */
+#define XCHAL_ICACHE_WAYS		4
+#define XCHAL_DCACHE_WAYS		2
+
+/*  Cache features:  */
+#define XCHAL_ICACHE_LINE_LOCKABLE	1
+#define XCHAL_DCACHE_LINE_LOCKABLE	0
+#define XCHAL_ICACHE_ECC_PARITY		0
+#define XCHAL_DCACHE_ECC_PARITY		0
+
+/*  Number of encoded cache attr bits (see <xtensa/hal.h> for decoded bits):  */
+#define XCHAL_CA_BITS			4
+
+
+/*----------------------------------------------------------------------
+			INTERNAL I/D RAM/ROMs and XLMI
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_NUM_INSTROM		0	/* number of core instr. ROMs */
+#define XCHAL_NUM_INSTRAM		0	/* number of core instr. RAMs */
+#define XCHAL_NUM_DATAROM		0	/* number of core data ROMs */
+#define XCHAL_NUM_DATARAM		1	/* number of core data RAMs */
+#define XCHAL_NUM_URAM			0	/* number of core unified RAMs*/
+#define XCHAL_NUM_XLMI			1	/* number of core XLMI ports */
+
+/*  Data RAM 0:  */
+#define XCHAL_DATARAM0_VADDR		0x3FFF0000
+#define XCHAL_DATARAM0_PADDR		0x3FFF0000
+#define XCHAL_DATARAM0_SIZE		65536
+#define XCHAL_DATARAM0_ECC_PARITY	0
+
+/*  XLMI Port 0:  */
+#define XCHAL_XLMI0_VADDR		0x37F80000
+#define XCHAL_XLMI0_PADDR		0x37F80000
+#define XCHAL_XLMI0_SIZE		262144
+#define XCHAL_XLMI0_ECC_PARITY	0
+
+
+/*----------------------------------------------------------------------
+			INTERRUPTS and TIMERS
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_INTERRUPTS		1	/* interrupt option */
+#define XCHAL_HAVE_HIGHPRI_INTERRUPTS	1	/* med/high-pri. interrupts */
+#define XCHAL_HAVE_NMI			1	/* non-maskable interrupt */
+#define XCHAL_HAVE_CCOUNT		1	/* CCOUNT reg. (timer option) */
+#define XCHAL_NUM_TIMERS		3	/* number of CCOMPAREn regs */
+#define XCHAL_NUM_INTERRUPTS		27	/* number of interrupts */
+#define XCHAL_NUM_INTERRUPTS_LOG2	5	/* ceil(log2(NUM_INTERRUPTS)) */
+#define XCHAL_NUM_EXTINTERRUPTS		20	/* num of external interrupts */
+#define XCHAL_NUM_INTLEVELS		4	/* number of interrupt levels
+						   (not including level zero) */
+#define XCHAL_EXCM_LEVEL		1	/* level masked by PS.EXCM */
+	/* (always 1 in XEA1; levels 2 .. EXCM_LEVEL are "medium priority") */
+
+/*  Masks of interrupts at each interrupt level:  */
+#define XCHAL_INTLEVEL1_MASK		0x01F07FFF
+#define XCHAL_INTLEVEL2_MASK		0x02018000
+#define XCHAL_INTLEVEL3_MASK		0x04060000
+#define XCHAL_INTLEVEL4_MASK		0x00000000
+#define XCHAL_INTLEVEL5_MASK		0x00080000
+#define XCHAL_INTLEVEL6_MASK		0x00000000
+#define XCHAL_INTLEVEL7_MASK		0x00000000
+
+/*  Masks of interrupts at each range 1..n of interrupt levels:  */
+#define XCHAL_INTLEVEL1_ANDBELOW_MASK	0x01F07FFF
+#define XCHAL_INTLEVEL2_ANDBELOW_MASK	0x03F1FFFF
+#define XCHAL_INTLEVEL3_ANDBELOW_MASK	0x07F7FFFF
+#define XCHAL_INTLEVEL4_ANDBELOW_MASK	0x07F7FFFF
+#define XCHAL_INTLEVEL5_ANDBELOW_MASK	0x07FFFFFF
+#define XCHAL_INTLEVEL6_ANDBELOW_MASK	0x07FFFFFF
+#define XCHAL_INTLEVEL7_ANDBELOW_MASK	0x07FFFFFF
+
+/*  Level of each interrupt:  */
+#define XCHAL_INT0_LEVEL		1
+#define XCHAL_INT1_LEVEL		1
+#define XCHAL_INT2_LEVEL		1
+#define XCHAL_INT3_LEVEL		1
+#define XCHAL_INT4_LEVEL		1
+#define XCHAL_INT5_LEVEL		1
+#define XCHAL_INT6_LEVEL		1
+#define XCHAL_INT7_LEVEL		1
+#define XCHAL_INT8_LEVEL		1
+#define XCHAL_INT9_LEVEL		1
+#define XCHAL_INT10_LEVEL		1
+#define XCHAL_INT11_LEVEL		1
+#define XCHAL_INT12_LEVEL		1
+#define XCHAL_INT13_LEVEL		1
+#define XCHAL_INT14_LEVEL		1
+#define XCHAL_INT15_LEVEL		2
+#define XCHAL_INT16_LEVEL		2
+#define XCHAL_INT17_LEVEL		3
+#define XCHAL_INT18_LEVEL		3
+#define XCHAL_INT19_LEVEL		5
+#define XCHAL_INT20_LEVEL		1
+#define XCHAL_INT21_LEVEL		1
+#define XCHAL_INT22_LEVEL		1
+#define XCHAL_INT23_LEVEL		1
+#define XCHAL_INT24_LEVEL		1
+#define XCHAL_INT25_LEVEL		2
+#define XCHAL_INT26_LEVEL		3
+#define XCHAL_DEBUGLEVEL		4	/* debug interrupt level */
+#define XCHAL_HAVE_DEBUG_EXTERN_INT	1	/* OCD external db interrupt */
+#define XCHAL_NMILEVEL			5	/* NMI "level" (for use with
+						   EXCSAVE/EPS/EPC_n, RFI n) */
+
+/*  Type of each interrupt:  */
+#define XCHAL_INT0_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT1_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT2_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT3_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT4_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT5_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT6_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT7_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT8_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT9_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT10_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT11_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT12_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT13_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT14_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT15_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT16_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT17_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT18_TYPE 	XTHAL_INTTYPE_EXTERN_LEVEL
+#define XCHAL_INT19_TYPE 	XTHAL_INTTYPE_NMI
+#define XCHAL_INT20_TYPE 	XTHAL_INTTYPE_SOFTWARE
+#define XCHAL_INT21_TYPE 	XTHAL_INTTYPE_SOFTWARE
+#define XCHAL_INT22_TYPE 	XTHAL_INTTYPE_SOFTWARE
+#define XCHAL_INT23_TYPE 	XTHAL_INTTYPE_SOFTWARE
+#define XCHAL_INT24_TYPE 	XTHAL_INTTYPE_TIMER
+#define XCHAL_INT25_TYPE 	XTHAL_INTTYPE_TIMER
+#define XCHAL_INT26_TYPE 	XTHAL_INTTYPE_TIMER
+
+/*  Masks of interrupts for each type of interrupt:  */
+#define XCHAL_INTTYPE_MASK_UNCONFIGURED	0xF8000000
+#define XCHAL_INTTYPE_MASK_SOFTWARE	0x00F00000
+#define XCHAL_INTTYPE_MASK_EXTERN_EDGE	0x00000000
+#define XCHAL_INTTYPE_MASK_EXTERN_LEVEL	0x0007FFFF
+#define XCHAL_INTTYPE_MASK_TIMER	0x07000000
+#define XCHAL_INTTYPE_MASK_NMI		0x00080000
+#define XCHAL_INTTYPE_MASK_WRITE_ERROR	0x00000000
+
+/*  Interrupt numbers assigned to specific interrupt sources:  */
+#define XCHAL_TIMER0_INTERRUPT		24	/* CCOMPARE0 */
+#define XCHAL_TIMER1_INTERRUPT		25	/* CCOMPARE1 */
+#define XCHAL_TIMER2_INTERRUPT		26	/* CCOMPARE2 */
+#define XCHAL_TIMER3_INTERRUPT		XTHAL_TIMER_UNCONFIGURED
+#define XCHAL_NMI_INTERRUPT		19	/* non-maskable interrupt */
+
+/*  Interrupt numbers for levels at which only one interrupt is configured:  */
+#define XCHAL_INTLEVEL5_NUM		19
+/*  (There are many interrupts each at level(s) 1, 2, 3.)  */
+
+
+/*
+ *  External interrupt vectors/levels.
+ *  These macros describe how Xtensa processor interrupt numbers
+ *  (as numbered internally, eg. in INTERRUPT and INTENABLE registers)
+ *  map to external BInterrupt<n> pins, for those interrupts
+ *  configured as external (level-triggered, edge-triggered, or NMI).
+ *  See the Xtensa processor databook for more details.
+ */
+
+/*  Core interrupt numbers mapped to each EXTERNAL interrupt number:  */
+#define XCHAL_EXTINT0_NUM		0	/* (intlevel 1) */
+#define XCHAL_EXTINT1_NUM		1	/* (intlevel 1) */
+#define XCHAL_EXTINT2_NUM		2	/* (intlevel 1) */
+#define XCHAL_EXTINT3_NUM		3	/* (intlevel 1) */
+#define XCHAL_EXTINT4_NUM		4	/* (intlevel 1) */
+#define XCHAL_EXTINT5_NUM		5	/* (intlevel 1) */
+#define XCHAL_EXTINT6_NUM		6	/* (intlevel 1) */
+#define XCHAL_EXTINT7_NUM		7	/* (intlevel 1) */
+#define XCHAL_EXTINT8_NUM		8	/* (intlevel 1) */
+#define XCHAL_EXTINT9_NUM		9	/* (intlevel 1) */
+#define XCHAL_EXTINT10_NUM		10	/* (intlevel 1) */
+#define XCHAL_EXTINT11_NUM		11	/* (intlevel 1) */
+#define XCHAL_EXTINT12_NUM		12	/* (intlevel 1) */
+#define XCHAL_EXTINT13_NUM		13	/* (intlevel 1) */
+#define XCHAL_EXTINT14_NUM		14	/* (intlevel 1) */
+#define XCHAL_EXTINT15_NUM		15	/* (intlevel 2) */
+#define XCHAL_EXTINT16_NUM		16	/* (intlevel 2) */
+#define XCHAL_EXTINT17_NUM		17	/* (intlevel 3) */
+#define XCHAL_EXTINT18_NUM		18	/* (intlevel 3) */
+#define XCHAL_EXTINT19_NUM		19	/* (intlevel 5) */
+
+
+/*----------------------------------------------------------------------
+			EXCEPTIONS and VECTORS
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_XEA_VERSION		2	/* Xtensa Exception Architecture
+						   number: 1 == XEA1 (old)
+							   2 == XEA2 (new)
+							   0 == XEAX (extern) */
+#define XCHAL_HAVE_XEA1			0	/* Exception Architecture 1 */
+#define XCHAL_HAVE_XEA2			1	/* Exception Architecture 2 */
+#define XCHAL_HAVE_XEAX			0	/* External Exception Arch. */
+#define XCHAL_HAVE_EXCEPTIONS		1	/* exception option */
+#define XCHAL_HAVE_MEM_ECC_PARITY	0	/* local memory ECC/parity */
+#define XCHAL_HAVE_VECTOR_SELECT	0	/* relocatable vectors */
+#define XCHAL_HAVE_VECBASE		0	/* relocatable vectors */
+
+#define XCHAL_RESET_VECOFS		0x00000000
+#define XCHAL_RESET_VECTOR_VADDR	0x3FFE03D0
+#define XCHAL_RESET_VECTOR_PADDR	0x3FFE03D0
+#define XCHAL_USER_VECOFS		0x00000000
+#define XCHAL_USER_VECTOR_VADDR		0x40000220
+#define XCHAL_USER_VECTOR_PADDR		0x40000220
+#define XCHAL_KERNEL_VECOFS		0x00000000
+#define XCHAL_KERNEL_VECTOR_VADDR	0x40000200
+#define XCHAL_KERNEL_VECTOR_PADDR	0x40000200
+#define XCHAL_DOUBLEEXC_VECOFS		0x00000000
+#define XCHAL_DOUBLEEXC_VECTOR_VADDR	0x400002A0
+#define XCHAL_DOUBLEEXC_VECTOR_PADDR	0x400002A0
+#define XCHAL_WINDOW_OF4_VECOFS		0x00000000
+#define XCHAL_WINDOW_UF4_VECOFS		0x00000040
+#define XCHAL_WINDOW_OF8_VECOFS		0x00000080
+#define XCHAL_WINDOW_UF8_VECOFS		0x000000C0
+#define XCHAL_WINDOW_OF12_VECOFS	0x00000100
+#define XCHAL_WINDOW_UF12_VECOFS	0x00000140
+#define XCHAL_WINDOW_VECTORS_VADDR	0x40000000
+#define XCHAL_WINDOW_VECTORS_PADDR	0x40000000
+#define XCHAL_INTLEVEL2_VECOFS		0x00000000
+#define XCHAL_INTLEVEL2_VECTOR_VADDR	0x40000240
+#define XCHAL_INTLEVEL2_VECTOR_PADDR	0x40000240
+#define XCHAL_INTLEVEL3_VECOFS		0x00000000
+#define XCHAL_INTLEVEL3_VECTOR_VADDR	0x40000260
+#define XCHAL_INTLEVEL3_VECTOR_PADDR	0x40000260
+#define XCHAL_INTLEVEL4_VECOFS		0x00000000
+#define XCHAL_INTLEVEL4_VECTOR_VADDR	0x40000390
+#define XCHAL_INTLEVEL4_VECTOR_PADDR	0x40000390
+#define XCHAL_DEBUG_VECOFS		XCHAL_INTLEVEL4_VECOFS
+#define XCHAL_DEBUG_VECTOR_VADDR	XCHAL_INTLEVEL4_VECTOR_VADDR
+#define XCHAL_DEBUG_VECTOR_PADDR	XCHAL_INTLEVEL4_VECTOR_PADDR
+#define XCHAL_NMI_VECOFS		0x00000000
+#define XCHAL_NMI_VECTOR_VADDR		0x400003B0
+#define XCHAL_NMI_VECTOR_PADDR		0x400003B0
+#define XCHAL_INTLEVEL5_VECOFS		XCHAL_NMI_VECOFS
+#define XCHAL_INTLEVEL5_VECTOR_VADDR	XCHAL_NMI_VECTOR_VADDR
+#define XCHAL_INTLEVEL5_VECTOR_PADDR	XCHAL_NMI_VECTOR_PADDR
+
+
+/*----------------------------------------------------------------------
+				DEBUG
+  ----------------------------------------------------------------------*/
+
+#define XCHAL_HAVE_OCD			1	/* OnChipDebug option */
+#define XCHAL_NUM_IBREAK		2	/* number of IBREAKn regs */
+#define XCHAL_NUM_DBREAK		2	/* number of DBREAKn regs */
+#define XCHAL_HAVE_OCD_DIR_ARRAY	1	/* faster OCD option */
+
+
+/*----------------------------------------------------------------------
+				MMU
+  ----------------------------------------------------------------------*/
+
+/*  See core-matmap.h header file for more details.  */
+
+#define XCHAL_HAVE_TLBS			1	/* inverse of HAVE_CACHEATTR */
+#define XCHAL_HAVE_SPANNING_WAY		1	/* one way maps I+D 4GB vaddr */
+#define XCHAL_HAVE_IDENTITY_MAP		1	/* vaddr == paddr always */
+#define XCHAL_HAVE_CACHEATTR		0	/* CACHEATTR register present */
+#define XCHAL_HAVE_MIMIC_CACHEATTR	1	/* region protection */
+#define XCHAL_HAVE_XLT_CACHEATTR	0	/* region prot. w/translation */
+#define XCHAL_HAVE_PTP_MMU		0	/* full MMU (with page table
+						   [autorefill] and protection)
+						   usable for an MMU-based OS */
+/*  If none of the above last 4 are set, it's a custom TLB configuration.  */
+
+#define XCHAL_MMU_ASID_BITS		0	/* number of bits in ASIDs */
+#define XCHAL_MMU_RINGS			1	/* number of rings (1..4) */
+#define XCHAL_MMU_RING_BITS		0	/* num of bits in RING field */
+
+#endif /* !XTENSA_HAL_NON_PRIVILEGED_ONLY */
+
+
+#endif /* _XTENSA_CORE_CONFIGURATION_H */
+
diff --git a/arch/xtensa/variants/s6000/include/variant/hardware.h b/arch/xtensa/variants/s6000/include/variant/hardware.h
new file mode 100644
index 000000000000..5d9ba098d84a
--- /dev/null
+++ b/arch/xtensa/variants/s6000/include/variant/hardware.h
@@ -0,0 +1,259 @@
+#ifndef __XTENSA_S6000_HARDWARE_H
+#define __XTENSA_S6000_HARDWARE_H
+
+#define S6_SCLK			1843200
+
+#define S6_MEM_REG              0x20000000
+#define S6_MEM_EFI              0x33F00000
+#define S6_MEM_PCIE_DATARAM1    0x34000000
+#define S6_MEM_XLMI             0x37F80000
+#define S6_MEM_PIF_DATARAM1     0x37FFC000
+#define S6_MEM_GMAC             0x38000000
+#define S6_MEM_I2S              0x3A000000
+#define S6_MEM_EGIB             0x3C000000
+#define S6_MEM_PCIE_CFG         0x3E000000
+#define S6_MEM_PIF_DATARAM      0x3FFE0000
+#define S6_MEM_XLMI_DATARAM     0x3FFF0000
+#define S6_MEM_DDR              0x40000000
+#define S6_MEM_PCIE_APER        0xC0000000
+#define S6_MEM_AUX              0xF0000000
+
+/* Device addresses */
+
+#define S6_REG_SCB              S6_MEM_REG
+#define S6_REG_NB               (S6_REG_SCB + 0x10000)
+#define S6_REG_LMSDMA           (S6_REG_SCB + 0x20000)
+#define S6_REG_NI               (S6_REG_SCB + 0x30000)
+#define S6_REG_NIDMA            (S6_REG_SCB + 0x40000)
+#define S6_REG_NS               (S6_REG_SCB + 0x50000)
+#define S6_REG_DDR              (S6_REG_SCB + 0x60000)
+#define S6_REG_GREG1            (S6_REG_SCB + 0x70000)
+#define S6_REG_DP               (S6_REG_SCB + 0x80000)
+#define S6_REG_DPDMA            (S6_REG_SCB + 0x90000)
+#define S6_REG_EGIB             (S6_REG_SCB + 0xA0000)
+#define S6_REG_PCIE             (S6_REG_SCB + 0xB0000)
+#define S6_REG_I2S              (S6_REG_SCB + 0xC0000)
+#define S6_REG_GMAC             (S6_REG_SCB + 0xD0000)
+#define S6_REG_HIFDMA           (S6_REG_SCB + 0xE0000)
+#define S6_REG_GREG2            (S6_REG_SCB + 0xF0000)
+
+#define S6_REG_APB              S6_REG_SCB
+#define S6_REG_UART             (S6_REG_APB + 0x0000)
+#define S6_REG_INTC             (S6_REG_APB + 0x2000)
+#define S6_REG_SPI              (S6_REG_APB + 0x3000)
+#define S6_REG_I2C              (S6_REG_APB + 0x4000)
+#define S6_REG_GPIO             (S6_REG_APB + 0x8000)
+
+/* Global register block */
+
+#define S6_GREG1_PLL_LOCKCLEAR	0x000
+#define S6_GREG1_PLL_LOCK_SYS		0
+#define S6_GREG1_PLL_LOCK_IO		1
+#define S6_GREG1_PLL_LOCK_AIM		2
+#define S6_GREG1_PLL_LOCK_DP0		3
+#define S6_GREG1_PLL_LOCK_DP2		4
+#define S6_GREG1_PLL_LOCK_DDR		5
+#define S6_GREG1_PLL_LOCKSTAT	0x004
+#define S6_GREG1_PLL_LOCKSTAT_CURLOCK	0
+#define S6_GREG1_PLL_LOCKSTAT_EVERUNLCK	8
+#define S6_GREG1_PLLSEL		0x010
+#define S6_GREG1_PLLSEL_AIM		0
+#define S6_GREG1_PLLSEL_AIM_DDR2		0
+#define S6_GREG1_PLLSEL_AIM_300MHZ		1
+#define S6_GREG1_PLLSEL_AIM_240MHZ		2
+#define S6_GREG1_PLLSEL_AIM_200MHZ		3
+#define S6_GREG1_PLLSEL_AIM_150MHZ		4
+#define S6_GREG1_PLLSEL_AIM_120MHZ		5
+#define S6_GREG1_PLLSEL_AIM_40MHZ		6
+#define S6_GREG1_PLLSEL_AIM_PLLAIMREF		7
+#define S6_GREG1_PLLSEL_AIM_MASK		7
+#define S6_GREG1_PLLSEL_DDR		8
+#define S6_GREG1_PLLSEL_DDR_HS			0
+#define S6_GREG1_PLLSEL_DDR_333MHZ		1
+#define S6_GREG1_PLLSEL_DDR_250MHZ		2
+#define S6_GREG1_PLLSEL_DDR_200MHZ		3
+#define S6_GREG1_PLLSEL_DDR_167MHZ		4
+#define S6_GREG1_PLLSEL_DDR_100MHZ		5
+#define S6_GREG1_PLLSEL_DDR_33MHZ		6
+#define S6_GREG1_PLLSEL_DDR_PLLIOREF		7
+#define S6_GREG1_PLLSEL_DDR_MASK		7
+#define S6_GREG1_PLLSEL_GMAC		16
+#define S6_GREG1_PLLSEL_GMAC_125MHZ		0
+#define S6_GREG1_PLLSEL_GMAC_25MHZ		1
+#define S6_GREG1_PLLSEL_GMAC_2500KHZ		2
+#define S6_GREG1_PLLSEL_GMAC_EXTERN		3
+#define S6_GREG1_PLLSEL_GMAC_MASK		3
+#define S6_GREG1_PLLSEL_GMII		18
+#define S6_GREG1_PLLSEL_GMII_111MHZ		0
+#define S6_GREG1_PLLSEL_GMII_IOREF		1
+#define S6_GREG1_PLLSEL_GMII_NONE		2
+#define S6_GREG1_PLLSEL_GMII_125MHZ		3
+#define S6_GREG1_PLLSEL_GMII_MASK		3
+#define S6_GREG1_SYSUNLOCKCNT	0x020
+#define S6_GREG1_IOUNLOCKCNT	0x024
+#define S6_GREG1_AIMUNLOCKCNT	0x028
+#define S6_GREG1_DP0UNLOCKCNT	0x02C
+#define S6_GREG1_DP2UNLOCKCNT	0x030
+#define S6_GREG1_DDRUNLOCKCNT	0x034
+#define S6_GREG1_CLKBAL0	0x040
+#define S6_GREG1_CLKBAL0_LSGB		0
+#define S6_GREG1_CLKBAL0_LSPX		8
+#define S6_GREG1_CLKBAL0_MEMDO		16
+#define S6_GREG1_CLKBAL0_HSXT1		24
+#define S6_GREG1_CLKBAL1	0x044
+#define S6_GREG1_CLKBAL1_HSISEF		0
+#define S6_GREG1_CLKBAL1_HSNI		8
+#define S6_GREG1_CLKBAL1_HSNS		16
+#define S6_GREG1_CLKBAL1_HSISEFCFG	24
+#define S6_GREG1_CLKBAL2	0x048
+#define S6_GREG1_CLKBAL2_LSNB		0
+#define S6_GREG1_CLKBAL2_LSSB		8
+#define S6_GREG1_CLKBAL2_LSREST		24
+#define S6_GREG1_CLKBAL3	0x04C
+#define S6_GREG1_CLKBAL3_ISEFXAD	0
+#define S6_GREG1_CLKBAL3_ISEFLMS	8
+#define S6_GREG1_CLKBAL3_ISEFISEF	16
+#define S6_GREG1_CLKBAL3_DDRDD		24
+#define S6_GREG1_CLKBAL4	0x050
+#define S6_GREG1_CLKBAL4_DDRDP		0
+#define S6_GREG1_CLKBAL4_DDRDO		8
+#define S6_GREG1_CLKBAL4_DDRNB		16
+#define S6_GREG1_CLKBAL4_DDRLMS		24
+#define S6_GREG1_BLOCKENA	0x100
+#define S6_GREG1_BLOCK_DDR		0
+#define S6_GREG1_BLOCK_DP		1
+#define S6_GREG1_BLOCK_NSNI		2
+#define S6_GREG1_BLOCK_PCIE		3
+#define S6_GREG1_BLOCK_GMAC		4
+#define S6_GREG1_BLOCK_I2S		5
+#define S6_GREG1_BLOCK_EGIB		6
+#define S6_GREG1_BLOCK_SB		7
+#define S6_GREG1_BLOCK_XT1		8
+#define S6_GREG1_CLKGATE	0x104
+#define S6_GREG1_BGATE_AIMNORTH		9
+#define S6_GREG1_BGATE_AIMEAST		10
+#define S6_GREG1_BGATE_AIMWEST		11
+#define S6_GREG1_BGATE_AIMSOUTH		12
+#define S6_GREG1_CHIPRES	0x108
+#define S6_GREG1_CHIPRES_SOFTRES	0
+#define S6_GREG1_CHIPRES_LOSTLOCK	1
+#define S6_GREG1_RESETCAUSE	0x10C
+#define S6_GREG1_RESETCAUSE_RESETN	0
+#define S6_GREG1_RESETCAUSE_GLOBAL	1
+#define S6_GREG1_RESETCAUSE_WDOGTIMER	2
+#define S6_GREG1_RESETCAUSE_SWCHIP	3
+#define S6_GREG1_RESETCAUSE_PLLSYSLOSS	4
+#define S6_GREG1_RESETCAUSE_PCIE	5
+#define S6_GREG1_RESETCAUSE_CREATEDGLOB	6
+#define S6_GREG1_REFCLOCKCNT	0x110
+#define S6_GREG1_RESETTIMER	0x114
+#define S6_GREG1_NMITIMER	0x118
+#define S6_GREG1_GLOBAL_TIMER	0x11C
+#define S6_GREG1_TIMER0		0x180
+#define S6_GREG1_TIMER1		0x184
+#define S6_GREG1_UARTCLOCKSEL	0x204
+#define S6_GREG1_CHIPVERSPACKG	0x208
+#define S6_GREG1_CHIPVERSPACKG_CHIPVID	0
+#define S6_GREG1_CHIPVERSPACKG_PACKSEL	8
+#define S6_GREG1_ONDIETERMCTRL	0x20C
+#define S6_GREG1_ONDIETERMCTRL_WEST	0
+#define S6_GREG1_ONDIETERMCTRL_NORTH	2
+#define S6_GREG1_ONDIETERMCTRL_EAST	4
+#define S6_GREG1_ONDIETERMCTRL_SOUTH	6
+#define S6_GREG1_ONDIETERMCTRL_NONE		0
+#define S6_GREG1_ONDIETERMCTRL_75OHM		2
+#define S6_GREG1_ONDIETERMCTRL_MASK		3
+#define S6_GREG1_BOOT_CFG0	0x210
+#define S6_GREG1_BOOT_CFG0_AIMSTRONG	1
+#define S6_GREG1_BOOT_CFG0_MINIBOOTDL	2
+#define S6_GREG1_BOOT_CFG0_OCDGPIO8SET	5
+#define S6_GREG1_BOOT_CFG0_OCDGPIOENA	6
+#define S6_GREG1_BOOT_CFG0_DOWNSTREAM	7
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV	8
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_300MHZ	1
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_240MHZ	2
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_200MHZ	3
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_150MHZ	4
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_120MHZ	5
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_40MHZ	6
+#define S6_GREG1_BOOT_CFG0_PLLSYSDIV_MASK	7
+#define S6_GREG1_BOOT_CFG0_BALHSLMS	12
+#define S6_GREG1_BOOT_CFG0_BALHSNB	18
+#define S6_GREG1_BOOT_CFG0_BALHSXAD	24
+#define S6_GREG1_BOOT_CFG1	0x214
+#define S6_GREG1_BOOT_CFG1_PCIE1LANE	1
+#define S6_GREG1_BOOT_CFG1_MPLLPRESCALE	2
+#define S6_GREG1_BOOT_CFG1_MPLLNCY	4
+#define S6_GREG1_BOOT_CFG1_MPLLNCY5	9
+#define S6_GREG1_BOOT_CFG1_BALHSREST	14
+#define S6_GREG1_BOOT_CFG1_BALHSPSMEMS	20
+#define S6_GREG1_BOOT_CFG1_BALLSGI	26
+#define S6_GREG1_BOOT_CFG2	0x218
+#define S6_GREG1_BOOT_CFG2_PEID		0
+#define S6_GREG1_BOOT_CFG3	0x21C
+#define S6_GREG1_DRAMBUSYHOLDOF	0x220
+#define S6_GREG1_DRAMBUSYHOLDOF_XT0	0
+#define S6_GREG1_DRAMBUSYHOLDOF_XT1	4
+#define S6_GREG1_DRAMBUSYHOLDOF_XT_MASK		7
+#define S6_GREG1_PCIEBAR1SIZE	0x224
+#define S6_GREG1_PCIEBAR2SIZE	0x228
+#define S6_GREG1_PCIEVENDOR	0x22C
+#define S6_GREG1_PCIEDEVICE	0x230
+#define S6_GREG1_PCIEREV	0x234
+#define S6_GREG1_PCIECLASS	0x238
+#define S6_GREG1_XT1DCACHEMISS	0x240
+#define S6_GREG1_XT1ICACHEMISS	0x244
+#define S6_GREG1_HWSEMAPHORE(n)	(0x400 + 4 * (n))
+#define S6_GREG1_HWSEMAPHORE_NB		16
+
+/* peripheral interrupt numbers */
+
+#define S6_INTC_GPIO(n)			(n)		/* 0..3 */
+#define S6_INTC_I2C			4
+#define S6_INTC_SPI			5
+#define S6_INTC_NB_ERR			6
+#define S6_INTC_DMA_LMSERR		7
+#define S6_INTC_DMA_LMSLOWWMRK(n)	(8 + (n))	/* 0..11 */
+#define S6_INTC_DMA_LMSPENDCNT(n)	(20 + (n))	/* 0..11 */
+#define S6_INTC_DMA HOSTLOWWMRK(n)	(32 + (n))	/* 0..6 */
+#define S6_INTC_DMA_HOSTPENDCNT(n)	(39 + (n))	/* 0..6 */
+#define S6_INTC_DMA_HOSTERR		46
+#define S6_INTC_UART(n)			(47 + (n))	/* 0..1 */
+#define S6_INTC_XAD			49
+#define S6_INTC_NI_ERR			50
+#define S6_INTC_NI_INFIFOFULL		51
+#define S6_INTC_DMA_NIERR		52
+#define S6_INTC_DMA_NILOWWMRK(n)	(53 + (n))	/* 0..3 */
+#define S6_INTC_DMA_NIPENDCNT(n)	(57 + (n))	/* 0..3 */
+#define S6_INTC_DDR			61
+#define S6_INTC_NS_ERR			62
+#define S6_INTC_EFI_CFGERR		63
+#define S6_INTC_EFI_ISEFTEST		64
+#define S6_INTC_EFI_WRITEERR		65
+#define S6_INTC_NMI_TIMER		66
+#define S6_INTC_PLLLOCK_SYS		67
+#define S6_INTC_PLLLOCK_IO		68
+#define S6_INTC_PLLLOCK_AIM		69
+#define S6_INTC_PLLLOCK_DP0		70
+#define S6_INTC_PLLLOCK_DP2		71
+#define S6_INTC_I2S_ERR			72
+#define S6_INTC_GMAC_STAT		73
+#define S6_INTC_GMAC_ERR		74
+#define S6_INTC_GIB_ERR			75
+#define S6_INTC_PCIE_ERR		76
+#define S6_INTC_PCIE_MSI(n)		(77 + (n))	/* 0..3 */
+#define S6_INTC_PCIE_INTA		81
+#define S6_INTC_PCIE_INTB		82
+#define S6_INTC_PCIE_INTC		83
+#define S6_INTC_PCIE_INTD		84
+#define S6_INTC_SW(n)			(85 + (n))	/* 0..9 */
+#define S6_INTC_SW_ENABLE(n)		(85 + 256 + (n))
+#define S6_INTC_DMA_DP_ERR		95
+#define S6_INTC_DMA_DPLOWWMRK(n)	(96 + (n))	/* 0..3 */
+#define S6_INTC_DMA_DPPENDCNT(n)	(100 + (n))	/* 0..3 */
+#define S6_INTC_DMA_DPTERMCNT(n)	(104 + (n))	/* 0..3 */
+#define S6_INTC_TIMER0			108
+#define S6_INTC_TIMER1			109
+#define S6_INTC_DMA_HOSTTERMCNT(n)	(110 + (n))	/* 0..6 */
+
+#endif /* __XTENSA_S6000_HARDWARE_H */
diff --git a/arch/xtensa/variants/s6000/include/variant/irq.h b/arch/xtensa/variants/s6000/include/variant/irq.h
new file mode 100644
index 000000000000..fa031cb0acc4
--- /dev/null
+++ b/arch/xtensa/variants/s6000/include/variant/irq.h
@@ -0,0 +1,9 @@
+#ifndef __XTENSA_S6000_IRQ_H
+#define __XTENSA_S6000_IRQ_H
+
+#define NO_IRQ		(-1)
+
+extern void variant_irq_enable(unsigned int irq);
+extern void variant_irq_disable(unsigned int irq);
+
+#endif /* __XTENSA_S6000_IRQ_H */
diff --git a/arch/xtensa/variants/s6000/include/variant/tie-asm.h b/arch/xtensa/variants/s6000/include/variant/tie-asm.h
new file mode 100644
index 000000000000..f02d0a3a2e20
--- /dev/null
+++ b/arch/xtensa/variants/s6000/include/variant/tie-asm.h
@@ -0,0 +1,304 @@
+/*
+ * This header file contains assembly-language definitions (assembly
+ * macros, etc.) for this specific Xtensa processor's TIE extensions
+ * and options.  It is customized to this Xtensa processor configuration.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1999-2008 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_CORE_TIE_ASM_H
+#define _XTENSA_CORE_TIE_ASM_H
+
+/*  Selection parameter values for save-area save/restore macros:  */
+/*  Option vs. TIE:  */
+#define XTHAL_SAS_TIE	0x0001	/* custom extension or coprocessor */
+#define XTHAL_SAS_OPT	0x0002	/* optional (and not a coprocessor) */
+/*  Whether used automatically by compiler:  */
+#define XTHAL_SAS_NOCC	0x0004	/* not used by compiler w/o special opts/code */
+#define XTHAL_SAS_CC	0x0008	/* used by compiler without special opts/code */
+/*  ABI handling across function calls:  */
+#define XTHAL_SAS_CALR	0x0010	/* caller-saved */
+#define XTHAL_SAS_CALE	0x0020	/* callee-saved */
+#define XTHAL_SAS_GLOB	0x0040	/* global across function calls (in thread) */
+/*  Misc  */
+#define XTHAL_SAS_ALL	0xFFFF	/* include all default NCP contents */
+
+
+
+/* Macro to save all non-coprocessor (extra) custom TIE and optional state
+ * (not including zero-overhead loop registers).
+ * Save area ptr (clobbered):  ptr  (16 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_NCP_NUM_ATMPS needed)
+ */
+	.macro xchal_ncp_store  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start	\continue, \ofs
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-4, 4, 4
+	rsr	\at1, BR		// boolean option
+	s32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 4
+	.endif
+	.endm	// xchal_ncp_store
+
+/* Macro to save all non-coprocessor (extra) custom TIE and optional state
+ * (not including zero-overhead loop registers).
+ * Save area ptr (clobbered):  ptr  (16 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_NCP_NUM_ATMPS needed)
+ */
+	.macro xchal_ncp_load  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start	\continue, \ofs
+	.ifeq (XTHAL_SAS_OPT | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 1024-4, 4, 4
+	l32i	\at1, \ptr, .Lxchal_ofs_ + 0
+	wsr	\at1, BR		// boolean option
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 4
+	.endif
+	.endm	// xchal_ncp_load
+
+
+
+#define XCHAL_NCP_NUM_ATMPS	1
+
+
+
+/* Macro to save the state of TIE coprocessor FPU.
+ * Save area ptr (clobbered):  ptr  (16 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_CP0_NUM_ATMPS needed)
+ */
+#define xchal_cp_FPU_store	xchal_cp0_store
+/* #define xchal_cp_FPU_store_a2	xchal_cp0_store a2 a3 a4 a5 a6 */
+	.macro	xchal_cp0_store  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start \continue, \ofs
+	.ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 0, 1, 16
+	rur232	\at1		// FCR
+	s32i	\at1, \ptr, 0
+	rur233	\at1		// FSR
+	s32i	\at1, \ptr, 4
+	SSI f0, \ptr,  8
+	SSI f1, \ptr,  12
+	SSI f2, \ptr,  16
+	SSI f3, \ptr,  20
+	SSI f4, \ptr,  24
+	SSI f5, \ptr,  28
+	SSI f6, \ptr,  32
+	SSI f7, \ptr,  36
+	SSI f8, \ptr,  40
+	SSI f9, \ptr,  44
+	SSI f10, \ptr,  48
+	SSI f11, \ptr,  52
+	SSI f12, \ptr,  56
+	SSI f13, \ptr,  60
+	SSI f14, \ptr,  64
+	SSI f15, \ptr,  68
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 72
+	.endif
+	.endm	// xchal_cp0_store
+
+/* Macro to restore the state of TIE coprocessor FPU.
+ * Save area ptr (clobbered):  ptr  (16 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_CP0_NUM_ATMPS needed)
+ */
+#define xchal_cp_FPU_load	xchal_cp0_load
+/* #define xchal_cp_FPU_load_a2	xchal_cp0_load a2 a3 a4 a5 a6 */
+	.macro	xchal_cp0_load  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start \continue, \ofs
+	.ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 0, 1, 16
+	l32i	\at1, \ptr, 0
+	wur232	\at1		// FCR
+	l32i	\at1, \ptr, 4
+	wur233	\at1		// FSR
+	LSI f0, \ptr,  8
+	LSI f1, \ptr,  12
+	LSI f2, \ptr,  16
+	LSI f3, \ptr,  20
+	LSI f4, \ptr,  24
+	LSI f5, \ptr,  28
+	LSI f6, \ptr,  32
+	LSI f7, \ptr,  36
+	LSI f8, \ptr,  40
+	LSI f9, \ptr,  44
+	LSI f10, \ptr,  48
+	LSI f11, \ptr,  52
+	LSI f12, \ptr,  56
+	LSI f13, \ptr,  60
+	LSI f14, \ptr,  64
+	LSI f15, \ptr,  68
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 72
+	.endif
+	.endm	// xchal_cp0_load
+
+#define XCHAL_CP0_NUM_ATMPS	1
+
+/* Macro to save the state of TIE coprocessor XAD.
+ * Save area ptr (clobbered):  ptr  (16 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_CP6_NUM_ATMPS needed)
+ */
+#define xchal_cp_XAD_store	xchal_cp6_store
+/* #define xchal_cp_XAD_store_a2	xchal_cp6_store a2 a3 a4 a5 a6 */
+	.macro	xchal_cp6_store  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start \continue, \ofs
+	.ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 0, 1, 16
+	rur0	\at1		// LDCBHI
+	s32i	\at1, \ptr, 0
+	rur1	\at1		// LDCBLO
+	s32i	\at1, \ptr, 4
+	rur2	\at1		// STCBHI
+	s32i	\at1, \ptr, 8
+	rur3	\at1		// STCBLO
+	s32i	\at1, \ptr, 12
+	rur8	\at1		// LDBRBASE
+	s32i	\at1, \ptr, 16
+	rur9	\at1		// LDBROFF
+	s32i	\at1, \ptr, 20
+	rur10	\at1		// LDBRINC
+	s32i	\at1, \ptr, 24
+	rur11	\at1		// STBRBASE
+	s32i	\at1, \ptr, 28
+	rur12	\at1		// STBROFF
+	s32i	\at1, \ptr, 32
+	rur13	\at1		// STBRINC
+	s32i	\at1, \ptr, 36
+	rur24	\at1		// SCRATCH0
+	s32i	\at1, \ptr, 40
+	rur25	\at1		// SCRATCH1
+	s32i	\at1, \ptr, 44
+	rur26	\at1		// SCRATCH2
+	s32i	\at1, \ptr, 48
+	rur27	\at1		// SCRATCH3
+	s32i	\at1, \ptr, 52
+	WRAS128I wra0, \ptr,  64
+	WRAS128I wra1, \ptr,  80
+	WRAS128I wra2, \ptr,  96
+	WRAS128I wra3, \ptr,  112
+	WRAS128I wra4, \ptr,  128
+	WRAS128I wra5, \ptr,  144
+	WRAS128I wra6, \ptr,  160
+	WRAS128I wra7, \ptr,  176
+	WRAS128I wra8, \ptr,  192
+	WRAS128I wra9, \ptr,  208
+	WRAS128I wra10, \ptr,  224
+	WRAS128I wra11, \ptr,  240
+	WRAS128I wra12, \ptr,  256
+	WRAS128I wra13, \ptr,  272
+	WRAS128I wra14, \ptr,  288
+	WRAS128I wra15, \ptr,  304
+	WRBS128I wrb0, \ptr,  320
+	WRBS128I wrb1, \ptr,  336
+	WRBS128I wrb2, \ptr,  352
+	WRBS128I wrb3, \ptr,  368
+	WRBS128I wrb4, \ptr,  384
+	WRBS128I wrb5, \ptr,  400
+	WRBS128I wrb6, \ptr,  416
+	WRBS128I wrb7, \ptr,  432
+	WRBS128I wrb8, \ptr,  448
+	WRBS128I wrb9, \ptr,  464
+	WRBS128I wrb10, \ptr,  480
+	WRBS128I wrb11, \ptr,  496
+	WRBS128I wrb12, \ptr,  512
+	WRBS128I wrb13, \ptr,  528
+	WRBS128I wrb14, \ptr,  544
+	WRBS128I wrb15, \ptr,  560
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 576
+	.endif
+	.endm	// xchal_cp6_store
+
+/* Macro to restore the state of TIE coprocessor XAD.
+ * Save area ptr (clobbered):  ptr  (16 byte aligned)
+ * Scratch regs  (clobbered):  at1..at4  (only first XCHAL_CP6_NUM_ATMPS needed)
+ */
+#define xchal_cp_XAD_load	xchal_cp6_load
+/* #define xchal_cp_XAD_load_a2	xchal_cp6_load a2 a3 a4 a5 a6 */
+	.macro	xchal_cp6_load  ptr at1 at2 at3 at4  continue=0 ofs=-1 select=XTHAL_SAS_ALL
+	xchal_sa_start \continue, \ofs
+	.ifeq (XTHAL_SAS_TIE | XTHAL_SAS_NOCC | XTHAL_SAS_CALR) & ~\select
+	xchal_sa_align	\ptr, 0, 0, 1, 16
+	l32i	\at1, \ptr, 0
+	wur0	\at1		// LDCBHI
+	l32i	\at1, \ptr, 4
+	wur1	\at1		// LDCBLO
+	l32i	\at1, \ptr, 8
+	wur2	\at1		// STCBHI
+	l32i	\at1, \ptr, 12
+	wur3	\at1		// STCBLO
+	l32i	\at1, \ptr, 16
+	wur8	\at1		// LDBRBASE
+	l32i	\at1, \ptr, 20
+	wur9	\at1		// LDBROFF
+	l32i	\at1, \ptr, 24
+	wur10	\at1		// LDBRINC
+	l32i	\at1, \ptr, 28
+	wur11	\at1		// STBRBASE
+	l32i	\at1, \ptr, 32
+	wur12	\at1		// STBROFF
+	l32i	\at1, \ptr, 36
+	wur13	\at1		// STBRINC
+	l32i	\at1, \ptr, 40
+	wur24	\at1		// SCRATCH0
+	l32i	\at1, \ptr, 44
+	wur25	\at1		// SCRATCH1
+	l32i	\at1, \ptr, 48
+	wur26	\at1		// SCRATCH2
+	l32i	\at1, \ptr, 52
+	wur27	\at1		// SCRATCH3
+	WRBL128I wrb0, \ptr,  320
+	WRBL128I wrb1, \ptr,  336
+	WRBL128I wrb2, \ptr,  352
+	WRBL128I wrb3, \ptr,  368
+	WRBL128I wrb4, \ptr,  384
+	WRBL128I wrb5, \ptr,  400
+	WRBL128I wrb6, \ptr,  416
+	WRBL128I wrb7, \ptr,  432
+	WRBL128I wrb8, \ptr,  448
+	WRBL128I wrb9, \ptr,  464
+	WRBL128I wrb10, \ptr,  480
+	WRBL128I wrb11, \ptr,  496
+	WRBL128I wrb12, \ptr,  512
+	WRBL128I wrb13, \ptr,  528
+	WRBL128I wrb14, \ptr,  544
+	WRBL128I wrb15, \ptr,  560
+	WRAL128I wra0, \ptr,  64
+	WRAL128I wra1, \ptr,  80
+	WRAL128I wra2, \ptr,  96
+	WRAL128I wra3, \ptr,  112
+	WRAL128I wra4, \ptr,  128
+	WRAL128I wra5, \ptr,  144
+	WRAL128I wra6, \ptr,  160
+	WRAL128I wra7, \ptr,  176
+	WRAL128I wra8, \ptr,  192
+	WRAL128I wra9, \ptr,  208
+	WRAL128I wra10, \ptr,  224
+	WRAL128I wra11, \ptr,  240
+	WRAL128I wra12, \ptr,  256
+	WRAL128I wra13, \ptr,  272
+	WRAL128I wra14, \ptr,  288
+	WRAL128I wra15, \ptr,  304
+	.set	.Lxchal_ofs_, .Lxchal_ofs_ + 576
+	.endif
+	.endm	// xchal_cp6_load
+
+#define XCHAL_CP6_NUM_ATMPS	1
+#define XCHAL_SA_NUM_ATMPS	1
+
+	/*  Empty macros for unconfigured coprocessors:  */
+	.macro xchal_cp1_store	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp1_load	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp2_store	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp2_load	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp3_store	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp3_load	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp4_store	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp4_load	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp5_store	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp5_load	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp7_store	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+	.macro xchal_cp7_load	p a b c d continue=0 ofs=-1 select=-1 ; .endm
+
+#endif /*_XTENSA_CORE_TIE_ASM_H*/
+
diff --git a/arch/xtensa/variants/s6000/include/variant/tie.h b/arch/xtensa/variants/s6000/include/variant/tie.h
new file mode 100644
index 000000000000..be7ea843d5df
--- /dev/null
+++ b/arch/xtensa/variants/s6000/include/variant/tie.h
@@ -0,0 +1,191 @@
+/*
+ * This header file describes this specific Xtensa processor's TIE extensions
+ * that extend basic Xtensa core functionality.  It is customized to this
+ * Xtensa processor configuration.
+ *
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (C) 1999-2008 Tensilica Inc.
+ */
+
+#ifndef _XTENSA_CORE_TIE_H
+#define _XTENSA_CORE_TIE_H
+
+#define XCHAL_CP_NUM			2	/* number of coprocessors */
+#define XCHAL_CP_MAX			7	/* max CP ID + 1 (0 if none) */
+#define XCHAL_CP_MASK			0x41	/* bitmask of all CPs by ID */
+#define XCHAL_CP_PORT_MASK		0x00	/* bitmask of only port CPs */
+
+/*  Basic parameters of each coprocessor:  */
+#define XCHAL_CP0_NAME			"FPU"
+#define XCHAL_CP0_IDENT			FPU
+#define XCHAL_CP0_SA_SIZE		72	/* size of state save area */
+#define XCHAL_CP0_SA_ALIGN		4	/* min alignment of save area */
+#define XCHAL_CP_ID_FPU			0	/* coprocessor ID (0..7) */
+#define XCHAL_CP6_NAME			"XAD"
+#define XCHAL_CP6_IDENT			XAD
+#define XCHAL_CP6_SA_SIZE		576	/* size of state save area */
+#define XCHAL_CP6_SA_ALIGN		16	/* min alignment of save area */
+#define XCHAL_CP_ID_XAD			6	/* coprocessor ID (0..7) */
+
+/*  Filler info for unassigned coprocessors, to simplify arrays etc:  */
+#define XCHAL_CP1_SA_SIZE		0
+#define XCHAL_CP1_SA_ALIGN		1
+#define XCHAL_CP2_SA_SIZE		0
+#define XCHAL_CP2_SA_ALIGN		1
+#define XCHAL_CP3_SA_SIZE		0
+#define XCHAL_CP3_SA_ALIGN		1
+#define XCHAL_CP4_SA_SIZE		0
+#define XCHAL_CP4_SA_ALIGN		1
+#define XCHAL_CP5_SA_SIZE		0
+#define XCHAL_CP5_SA_ALIGN		1
+#define XCHAL_CP7_SA_SIZE		0
+#define XCHAL_CP7_SA_ALIGN		1
+
+/*  Save area for non-coprocessor optional and custom (TIE) state:  */
+#define XCHAL_NCP_SA_SIZE		4
+#define XCHAL_NCP_SA_ALIGN		4
+
+/*  Total save area for optional and custom state (NCP + CPn):  */
+#define XCHAL_TOTAL_SA_SIZE		672	/* with 16-byte align padding */
+#define XCHAL_TOTAL_SA_ALIGN		16	/* actual minimum alignment */
+
+/*
+ * Detailed contents of save areas.
+ * NOTE:  caller must define the XCHAL_SA_REG macro (not defined here)
+ * before expanding the XCHAL_xxx_SA_LIST() macros.
+ *
+ * XCHAL_SA_REG(s,ccused,abikind,kind,opt,name,galign,align,asize,
+ *		dbnum,base,regnum,bitsz,gapsz,reset,x...)
+ *
+ *	s = passed from XCHAL_*_LIST(s), eg. to select how to expand
+ *	ccused = set if used by compiler without special options or code
+ *	abikind = 0 (caller-saved), 1 (callee-saved), or 2 (thread-global)
+ *	kind = 0 (special reg), 1 (TIE user reg), or 2 (TIE regfile reg)
+ *	opt = 0 (custom TIE extension or coprocessor), or 1 (optional reg)
+ *	name = lowercase reg name (no quotes)
+ *	galign = group byte alignment (power of 2) (galign >= align)
+ *	align = register byte alignment (power of 2)
+ *	asize = allocated size in bytes (asize*8 == bitsz + gapsz + padsz)
+ *	  (not including any pad bytes required to galign this or next reg)
+ *	dbnum = unique target number f/debug (see <xtensa-libdb-macros.h>)
+ *	base = reg shortname w/o index (or sr=special, ur=TIE user reg)
+ *	regnum = reg index in regfile, or special/TIE-user reg number
+ *	bitsz = number of significant bits (regfile width, or ur/sr mask bits)
+ *	gapsz = intervening bits, if bitsz bits not stored contiguously
+ *	(padsz = pad bits at end [TIE regfile] or at msbits [ur,sr] of asize)
+ *	reset = register reset value (or 0 if undefined at reset)
+ *	x = reserved for future use (0 until then)
+ *
+ *  To filter out certain registers, e.g. to expand only the non-global
+ *  registers used by the compiler, you can do something like this:
+ *
+ *  #define XCHAL_SA_REG(s,ccused,p...)	SELCC##ccused(p)
+ *  #define SELCC0(p...)
+ *  #define SELCC1(abikind,p...)	SELAK##abikind(p)
+ *  #define SELAK0(p...)		REG(p)
+ *  #define SELAK1(p...)		REG(p)
+ *  #define SELAK2(p...)
+ *  #define REG(kind,tie,name,galn,aln,asz,csz,dbnum,base,rnum,bsz,rst,x...) \
+ *		...what you want to expand...
+ */
+
+#define XCHAL_NCP_SA_NUM	1
+#define XCHAL_NCP_SA_LIST(s)	\
+ XCHAL_SA_REG(s,0,0,0,1,             br, 4, 4, 4,0x0204,  sr,4  , 16,0,0,0)
+
+#define XCHAL_CP0_SA_NUM	18
+#define XCHAL_CP0_SA_LIST(s)	\
+ XCHAL_SA_REG(s,0,0,1,0,            fcr, 4, 4, 4,0x03E8,  ur,232, 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,            fsr, 4, 4, 4,0x03E9,  ur,233, 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f0, 4, 4, 4,0x0030,   f,0  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f1, 4, 4, 4,0x0031,   f,1  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f2, 4, 4, 4,0x0032,   f,2  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f3, 4, 4, 4,0x0033,   f,3  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f4, 4, 4, 4,0x0034,   f,4  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f5, 4, 4, 4,0x0035,   f,5  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f6, 4, 4, 4,0x0036,   f,6  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f7, 4, 4, 4,0x0037,   f,7  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f8, 4, 4, 4,0x0038,   f,8  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,             f9, 4, 4, 4,0x0039,   f,9  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,            f10, 4, 4, 4,0x003A,   f,10 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,            f11, 4, 4, 4,0x003B,   f,11 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,            f12, 4, 4, 4,0x003C,   f,12 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,            f13, 4, 4, 4,0x003D,   f,13 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,            f14, 4, 4, 4,0x003E,   f,14 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,            f15, 4, 4, 4,0x003F,   f,15 , 32,0,0,0)
+
+#define XCHAL_CP1_SA_NUM	0
+#define XCHAL_CP1_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP2_SA_NUM	0
+#define XCHAL_CP2_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP3_SA_NUM	0
+#define XCHAL_CP3_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP4_SA_NUM	0
+#define XCHAL_CP4_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP5_SA_NUM	0
+#define XCHAL_CP5_SA_LIST(s)	/* empty */
+
+#define XCHAL_CP6_SA_NUM	46
+#define XCHAL_CP6_SA_LIST(s)	\
+ XCHAL_SA_REG(s,0,0,1,0,         ldcbhi,16, 4, 4,0x0300,  ur,0  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,         ldcblo, 4, 4, 4,0x0301,  ur,1  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,         stcbhi, 4, 4, 4,0x0302,  ur,2  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,         stcblo, 4, 4, 4,0x0303,  ur,3  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,       ldbrbase, 4, 4, 4,0x0308,  ur,8  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,        ldbroff, 4, 4, 4,0x0309,  ur,9  , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,        ldbrinc, 4, 4, 4,0x030A,  ur,10 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,       stbrbase, 4, 4, 4,0x030B,  ur,11 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,        stbroff, 4, 4, 4,0x030C,  ur,12 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,        stbrinc, 4, 4, 4,0x030D,  ur,13 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,       scratch0, 4, 4, 4,0x0318,  ur,24 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,       scratch1, 4, 4, 4,0x0319,  ur,25 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,       scratch2, 4, 4, 4,0x031A,  ur,26 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,1,0,       scratch3, 4, 4, 4,0x031B,  ur,27 , 32,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra0,16,16,16,0x1010, wra,0  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra1,16,16,16,0x1011, wra,1  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra2,16,16,16,0x1012, wra,2  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra3,16,16,16,0x1013, wra,3  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra4,16,16,16,0x1014, wra,4  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra5,16,16,16,0x1015, wra,5  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra6,16,16,16,0x1016, wra,6  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra7,16,16,16,0x1017, wra,7  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra8,16,16,16,0x1018, wra,8  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wra9,16,16,16,0x1019, wra,9  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wra10,16,16,16,0x101A, wra,10 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wra11,16,16,16,0x101B, wra,11 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wra12,16,16,16,0x101C, wra,12 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wra13,16,16,16,0x101D, wra,13 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wra14,16,16,16,0x101E, wra,14 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wra15,16,16,16,0x101F, wra,15 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb0,16,16,16,0x1020, wrb,0  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb1,16,16,16,0x1021, wrb,1  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb2,16,16,16,0x1022, wrb,2  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb3,16,16,16,0x1023, wrb,3  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb4,16,16,16,0x1024, wrb,4  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb5,16,16,16,0x1025, wrb,5  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb6,16,16,16,0x1026, wrb,6  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb7,16,16,16,0x1027, wrb,7  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb8,16,16,16,0x1028, wrb,8  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,           wrb9,16,16,16,0x1029, wrb,9  ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wrb10,16,16,16,0x102A, wrb,10 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wrb11,16,16,16,0x102B, wrb,11 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wrb12,16,16,16,0x102C, wrb,12 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wrb13,16,16,16,0x102D, wrb,13 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wrb14,16,16,16,0x102E, wrb,14 ,128,0,0,0) \
+ XCHAL_SA_REG(s,0,0,2,0,          wrb15,16,16,16,0x102F, wrb,15 ,128,0,0,0)
+
+#define XCHAL_CP7_SA_NUM	0
+#define XCHAL_CP7_SA_LIST(s)	/* empty */
+
+/* Byte length of instruction from its first nibble (op0 field), per FLIX.  */
+#define XCHAL_OP0_FORMAT_LENGTHS	3,3,3,3,3,3,3,3,2,2,2,2,2,2,8,8
+
+#endif /*_XTENSA_CORE_TIE_H*/
+
diff --git a/arch/xtensa/variants/s6000/irq.c b/arch/xtensa/variants/s6000/irq.c
new file mode 100644
index 000000000000..6651e3285fcf
--- /dev/null
+++ b/arch/xtensa/variants/s6000/irq.c
@@ -0,0 +1,74 @@
+/*
+ * s6000 irq crossbar
+ *
+ * Copyright (c) 2009 emlix GmbH
+ * Authors:	Johannes Weiner <jw@emlix.com>
+ *		Oskar Schirmer <os@emlix.com>
+ */
+#include <linux/io.h>
+#include <asm/irq.h>
+#include <variant/hardware.h>
+
+/* S6_REG_INTC */
+#define INTC_STATUS	0x000
+#define INTC_RAW	0x010
+#define INTC_STATUS_AG	0x100
+#define INTC_CFG(n)	(0x200 + 4 * (n))
+
+/*
+ * The s6000 has a crossbar that multiplexes interrupt output lines
+ * from the peripherals to input lines on the xtensa core.
+ *
+ * We leave the mapping decisions to the platform as it depends on the
+ * actually connected peripherals which distribution makes sense.
+ */
+extern const signed char *platform_irq_mappings[NR_IRQS];
+
+static unsigned long scp_to_intc_enable[] = {
+#define	TO_INTC_ENABLE(n)	(((n) << 1) + 1)
+	TO_INTC_ENABLE(0),
+	TO_INTC_ENABLE(1),
+	TO_INTC_ENABLE(2),
+	TO_INTC_ENABLE(3),
+	TO_INTC_ENABLE(4),
+	TO_INTC_ENABLE(5),
+	TO_INTC_ENABLE(6),
+	TO_INTC_ENABLE(7),
+	TO_INTC_ENABLE(8),
+	TO_INTC_ENABLE(9),
+	TO_INTC_ENABLE(10),
+	TO_INTC_ENABLE(11),
+	TO_INTC_ENABLE(12),
+	-1,
+	-1,
+	TO_INTC_ENABLE(13),
+	-1,
+	TO_INTC_ENABLE(14),
+	-1,
+	TO_INTC_ENABLE(15),
+#undef	TO_INTC_ENABLE
+};
+
+static void irq_set(unsigned int irq, int enable)
+{
+	unsigned long en;
+	const signed char *m = platform_irq_mappings[irq];
+
+	if (!m)
+		return;
+	en = enable ? scp_to_intc_enable[irq] : 0;
+	while (*m >= 0) {
+		writel(en, S6_REG_INTC + INTC_CFG(*m));
+		m++;
+	}
+}
+
+void variant_irq_enable(unsigned int irq)
+{
+	irq_set(irq, 1);
+}
+
+void variant_irq_disable(unsigned int irq)
+{
+	irq_set(irq, 0);
+}
diff --git a/block/blk-softirq.c b/block/blk-softirq.c
index ce0efc6b26dc..ee9c21602228 100644
--- a/block/blk-softirq.c
+++ b/block/blk-softirq.c
@@ -64,7 +64,7 @@ static int raise_blk_irq(int cpu, struct request *rq)
 		data->info = rq;
 		data->flags = 0;
 
-		__smp_call_function_single(cpu, data);
+		__smp_call_function_single(cpu, data, 0);
 		return 0;
 	}
 
diff --git a/block/blk.h b/block/blk.h
index 0dce92c37496..3ee94358b43d 100644
--- a/block/blk.h
+++ b/block/blk.h
@@ -102,7 +102,7 @@ static inline int blk_cpu_to_group(int cpu)
 	const struct cpumask *mask = cpu_coregroup_mask(cpu);
 	return cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	return first_cpu(per_cpu(cpu_sibling_map, cpu));
+	return cpumask_first(topology_thread_cpumask(cpu));
 #else
 	return cpu;
 #endif
diff --git a/crypto/async_tx/async_tx.c b/crypto/async_tx/async_tx.c
index f21147f3626a..06eb6cc09fef 100644
--- a/crypto/async_tx/async_tx.c
+++ b/crypto/async_tx/async_tx.c
@@ -30,7 +30,7 @@
 #ifdef CONFIG_DMA_ENGINE
 static int __init async_tx_init(void)
 {
-	dmaengine_get();
+	async_dmaengine_get();
 
 	printk(KERN_INFO "async_tx: api initialized (async)\n");
 
@@ -39,7 +39,7 @@ static int __init async_tx_init(void)
 
 static void __exit async_tx_exit(void)
 {
-	dmaengine_put();
+	async_dmaengine_put();
 }
 
 /**
@@ -56,7 +56,7 @@ __async_tx_find_channel(struct dma_async_tx_descriptor *depend_tx,
 	if (depend_tx &&
 	    dma_has_cap(tx_type, depend_tx->chan->device->cap_mask))
 		return depend_tx->chan;
-	return dma_find_channel(tx_type);
+	return async_dma_find_channel(tx_type);
 }
 EXPORT_SYMBOL_GPL(__async_tx_find_channel);
 #else
diff --git a/crypto/async_tx/async_xor.c b/crypto/async_tx/async_xor.c
index 595b78672b36..95fe2c8d6c51 100644
--- a/crypto/async_tx/async_xor.c
+++ b/crypto/async_tx/async_xor.c
@@ -30,11 +30,8 @@
 #include <linux/raid/xor.h>
 #include <linux/async_tx.h>
 
-/* do_async_xor - dma map the pages and perform the xor with an engine.
- * 	This routine is marked __always_inline so it can be compiled away
- * 	when CONFIG_DMA_ENGINE=n
- */
-static __always_inline struct dma_async_tx_descriptor *
+/* do_async_xor - dma map the pages and perform the xor with an engine */
+static __async_inline struct dma_async_tx_descriptor *
 do_async_xor(struct dma_chan *chan, struct page *dest, struct page **src_list,
 	     unsigned int offset, int src_cnt, size_t len,
 	     enum async_tx_flags flags,
diff --git a/crypto/shash.c b/crypto/shash.c
index 7a659733f94a..2ccc8b0076ce 100644
--- a/crypto/shash.c
+++ b/crypto/shash.c
@@ -77,6 +77,9 @@ static int shash_update_unaligned(struct shash_desc *desc, const u8 *data,
 	u8 buf[shash_align_buffer_size(unaligned_len, alignmask)]
 		__attribute__ ((aligned));
 
+	if (unaligned_len > len)
+		unaligned_len = len;
+
 	memcpy(buf, data, unaligned_len);
 
 	return shash->update(desc, buf, unaligned_len) ?:
diff --git a/crypto/xor.c b/crypto/xor.c
index b2e6db075e49..996b6ee57d9e 100644
--- a/crypto/xor.c
+++ b/crypto/xor.c
@@ -18,8 +18,8 @@
 
 #define BH_TRACE 0
 #include <linux/module.h>
-#include <linux/raid/md.h>
 #include <linux/raid/xor.h>
+#include <linux/jiffies.h>
 #include <asm/xor.h>
 
 /* The xor routines to use.  */
diff --git a/drivers/acpi/thermal.c b/drivers/acpi/thermal.c
index c11f9aeca706..1ba9d61ea69a 100644
--- a/drivers/acpi/thermal.c
+++ b/drivers/acpi/thermal.c
@@ -367,7 +367,7 @@ static int acpi_thermal_trips_update(struct acpi_thermal *tz, int flag)
 		/*
 		 * Treat freezing temperatures as invalid as well; some
 		 * BIOSes return really low values and cause reboots at startup.
-		 * Below zero (Celcius) values clearly aren't right for sure..
+		 * Below zero (Celsius) values clearly aren't right for sure..
 		 * ... so lets discard those as invalid.
 		 */
 		if (ACPI_FAILURE(status) ||
diff --git a/drivers/ata/Kconfig b/drivers/ata/Kconfig
index 0bcf26464670..9120717c0701 100644
--- a/drivers/ata/Kconfig
+++ b/drivers/ata/Kconfig
@@ -86,7 +86,7 @@ config ATA_SFF
 
 	  For users with exclusively modern controllers like AHCI,
 	  Silicon Image 3124, or Marvell 6440, you may choose to
-	  disable this uneeded SFF support.
+	  disable this unneeded SFF support.
 
 	  If unsure, say Y.
 
diff --git a/drivers/base/iommu.c b/drivers/base/iommu.c
index c2d1eed90376..9f0e672f4be8 100644
--- a/drivers/base/iommu.c
+++ b/drivers/base/iommu.c
@@ -98,3 +98,10 @@ phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
 	return iommu_ops->iova_to_phys(domain, iova);
 }
 EXPORT_SYMBOL_GPL(iommu_iova_to_phys);
+
+int iommu_domain_has_cap(struct iommu_domain *domain,
+			 unsigned long cap)
+{
+	return iommu_ops->domain_has_cap(domain, cap);
+}
+EXPORT_SYMBOL_GPL(iommu_domain_has_cap);
diff --git a/drivers/base/node.c b/drivers/base/node.c
index f8f578a71b25..40b809742a1c 100644
--- a/drivers/base/node.c
+++ b/drivers/base/node.c
@@ -24,7 +24,7 @@ static struct sysdev_class node_class = {
 static ssize_t node_read_cpumap(struct sys_device *dev, int type, char *buf)
 {
 	struct node *node_dev = to_node(dev);
-	node_to_cpumask_ptr(mask, node_dev->sysdev.id);
+	const struct cpumask *mask = cpumask_of_node(node_dev->sysdev.id);
 	int len;
 
 	/* 2008/04/07: buf currently PAGE_SIZE, need 9 chars per 32 bits. */
diff --git a/drivers/base/sys.c b/drivers/base/sys.c
index 76ce75bad91e..3236b434b964 100644
--- a/drivers/base/sys.c
+++ b/drivers/base/sys.c
@@ -300,7 +300,7 @@ void sysdev_unregister(struct sys_device *sysdev)
  *	and the class driver.
  *
  *	Note: The list is iterated in reverse order, so that we shut down
- *	child devices before we shut down thier parents. The list ordering
+ *	child devices before we shut down their parents. The list ordering
  *	is guaranteed by virtue of the fact that child devices are registered
  *	after their parents.
  */
diff --git a/drivers/block/aoe/aoecmd.c b/drivers/block/aoe/aoecmd.c
index 45c5a33daf49..31693bc24444 100644
--- a/drivers/block/aoe/aoecmd.c
+++ b/drivers/block/aoe/aoecmd.c
@@ -4,6 +4,7 @@
  * Filesystem request handling methods
  */
 
+#include <linux/ata.h>
 #include <linux/hdreg.h>
 #include <linux/blkdev.h>
 #include <linux/skbuff.h>
@@ -267,7 +268,7 @@ aoecmd_ata_rw(struct aoedev *d)
 		writebit = 0;
 	}
 
-	ah->cmdstat = WIN_READ | writebit | extbit;
+	ah->cmdstat = ATA_CMD_PIO_READ | writebit | extbit;
 
 	/* mark all tracking fields and load out */
 	buf->nframesout += 1;
@@ -362,10 +363,10 @@ resend(struct aoedev *d, struct aoetgt *t, struct frame *f)
 	switch (ah->cmdstat) {
 	default:
 		break;
-	case WIN_READ:
-	case WIN_READ_EXT:
-	case WIN_WRITE:
-	case WIN_WRITE_EXT:
+	case ATA_CMD_PIO_READ:
+	case ATA_CMD_PIO_READ_EXT:
+	case ATA_CMD_PIO_WRITE:
+	case ATA_CMD_PIO_WRITE_EXT:
 		put_lba(ah, f->lba);
 
 		n = f->bcnt;
@@ -812,8 +813,8 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 			d->htgt = NULL;
 		n = ahout->scnt << 9;
 		switch (ahout->cmdstat) {
-		case WIN_READ:
-		case WIN_READ_EXT:
+		case ATA_CMD_PIO_READ:
+		case ATA_CMD_PIO_READ_EXT:
 			if (skb->len - sizeof *hin - sizeof *ahin < n) {
 				printk(KERN_ERR
 					"aoe: %s.  skb->len=%d need=%ld\n",
@@ -823,8 +824,8 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 				return;
 			}
 			memcpy(f->bufaddr, ahin+1, n);
-		case WIN_WRITE:
-		case WIN_WRITE_EXT:
+		case ATA_CMD_PIO_WRITE:
+		case ATA_CMD_PIO_WRITE_EXT:
 			ifp = getif(t, skb->dev);
 			if (ifp) {
 				ifp->lost = 0;
@@ -838,7 +839,7 @@ aoecmd_ata_rsp(struct sk_buff *skb)
 				goto xmit;
 			}
 			break;
-		case WIN_IDENTIFY:
+		case ATA_CMD_ID_ATA:
 			if (skb->len - sizeof *hin - sizeof *ahin < 512) {
 				printk(KERN_INFO
 					"aoe: runt data size in ataid.  skb->len=%d\n",
@@ -914,7 +915,7 @@ aoecmd_ata_id(struct aoedev *d)
 
 	/* set up ata header */
 	ah->scnt = 1;
-	ah->cmdstat = WIN_IDENTIFY;
+	ah->cmdstat = ATA_CMD_ID_ATA;
 	ah->lba3 = 0xa0;
 
 	skb->dev = t->ifp->nd;
diff --git a/drivers/block/floppy.c b/drivers/block/floppy.c
index c2c95e614506..1300df6f1642 100644
--- a/drivers/block/floppy.c
+++ b/drivers/block/floppy.c
@@ -177,6 +177,7 @@ static int print_unex = 1;
 #include <linux/interrupt.h>
 #include <linux/init.h>
 #include <linux/platform_device.h>
+#include <linux/mod_devicetable.h>
 #include <linux/buffer_head.h>	/* for invalidate_buffers() */
 #include <linux/mutex.h>
 
@@ -4597,6 +4598,13 @@ MODULE_AUTHOR("Alain L. Knaff");
 MODULE_SUPPORTED_DEVICE("fd");
 MODULE_LICENSE("GPL");
 
+/* This doesn't actually get used other than for module information */
+static const struct pnp_device_id floppy_pnpids[] = {
+	{ "PNP0700", 0 },
+	{ }
+};
+MODULE_DEVICE_TABLE(pnp, floppy_pnpids);
+
 #else
 
 __setup("floppy=", floppy_setup);
diff --git a/drivers/block/hd.c b/drivers/block/hd.c
index 482c0c4b964f..3c11f062a18c 100644
--- a/drivers/block/hd.c
+++ b/drivers/block/hd.c
@@ -42,6 +42,8 @@
 #include <linux/ata.h>
 #include <linux/hdreg.h>
 
+#define HD_IRQ 14
+
 #define REALLY_SLOW_IO
 #include <asm/system.h>
 #include <asm/io.h>
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index 8299e2d3b611..4d6de4f15ccb 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -4,7 +4,7 @@
  * Note that you can not swap over this thing, yet. Seems to work but
  * deadlocks sometimes - you can not swap over TCP in general.
  * 
- * Copyright 1997-2000 Pavel Machek <pavel@ucw.cz>
+ * Copyright 1997-2000, 2008 Pavel Machek <pavel@suse.cz>
  * Parts copyright 2001 Steven Whitehouse <steve@chygwyn.com>
  *
  * This file is released under GPLv2 or later.
@@ -276,7 +276,7 @@ static int nbd_send_req(struct nbd_device *lo, struct request *req)
 	return 0;
 
 error_out:
-	return 1;
+	return -EIO;
 }
 
 static struct request *nbd_find_request(struct nbd_device *lo,
@@ -467,9 +467,7 @@ static void nbd_handle_req(struct nbd_device *lo, struct request *req)
 		mutex_unlock(&lo->tx_lock);
 		printk(KERN_ERR "%s: Attempted send on closed socket\n",
 		       lo->disk->disk_name);
-		req->errors++;
-		nbd_end_request(req);
-		return;
+		goto error_out;
 	}
 
 	lo->active_req = req;
@@ -531,7 +529,7 @@ static int nbd_thread(void *data)
  *   { printk( "Warning: Ignoring result!\n"); nbd_end_request( req ); }
  */
 
-static void do_nbd_request(struct request_queue * q)
+static void do_nbd_request(struct request_queue *q)
 {
 	struct request *req;
 	
@@ -568,27 +566,17 @@ static void do_nbd_request(struct request_queue * q)
 	}
 }
 
-static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
-		     unsigned int cmd, unsigned long arg)
-{
-	struct nbd_device *lo = bdev->bd_disk->private_data;
-	struct file *file;
-	int error;
-	struct request sreq ;
-	struct task_struct *thread;
-
-	if (!capable(CAP_SYS_ADMIN))
-		return -EPERM;
-
-	BUG_ON(lo->magic != LO_MAGIC);
-
-	/* Anyone capable of this syscall can do *real bad* things */
-	dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n",
-			lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);
+/* Must be called with tx_lock held */
 
+static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *lo,
+		       unsigned int cmd, unsigned long arg)
+{
 	switch (cmd) {
-	case NBD_DISCONNECT:
+	case NBD_DISCONNECT: {
+		struct request sreq;
+
 	        printk(KERN_INFO "%s: NBD_DISCONNECT\n", lo->disk->disk_name);
+
 		blk_rq_init(NULL, &sreq);
 		sreq.cmd_type = REQ_TYPE_SPECIAL;
 		nbd_cmd(&sreq) = NBD_CMD_DISC;
@@ -599,29 +587,29 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 		 */
 		sreq.sector = 0;
 		sreq.nr_sectors = 0;
-                if (!lo->sock)
+		if (!lo->sock)
 			return -EINVAL;
-		mutex_lock(&lo->tx_lock);
-                nbd_send_req(lo, &sreq);
-		mutex_unlock(&lo->tx_lock);
+		nbd_send_req(lo, &sreq);
                 return 0;
+	}
  
-	case NBD_CLEAR_SOCK:
-		error = 0;
-		mutex_lock(&lo->tx_lock);
+	case NBD_CLEAR_SOCK: {
+		struct file *file;
+
 		lo->sock = NULL;
-		mutex_unlock(&lo->tx_lock);
 		file = lo->file;
 		lo->file = NULL;
 		nbd_clear_que(lo);
 		BUG_ON(!list_empty(&lo->queue_head));
 		if (file)
 			fput(file);
-		return error;
-	case NBD_SET_SOCK:
+		return 0;
+	}
+
+	case NBD_SET_SOCK: {
+		struct file *file;
 		if (lo->file)
 			return -EBUSY;
-		error = -EINVAL;
 		file = fget(arg);
 		if (file) {
 			struct inode *inode = file->f_path.dentry->d_inode;
@@ -630,12 +618,14 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 				lo->sock = SOCKET_I(inode);
 				if (max_part > 0)
 					bdev->bd_invalidated = 1;
-				error = 0;
+				return 0;
 			} else {
 				fput(file);
 			}
 		}
-		return error;
+		return -EINVAL;
+	}
+
 	case NBD_SET_BLKSIZE:
 		lo->blksize = arg;
 		lo->bytesize &= ~(lo->blksize-1);
@@ -643,35 +633,50 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 		set_blocksize(bdev, lo->blksize);
 		set_capacity(lo->disk, lo->bytesize >> 9);
 		return 0;
+
 	case NBD_SET_SIZE:
 		lo->bytesize = arg & ~(lo->blksize-1);
 		bdev->bd_inode->i_size = lo->bytesize;
 		set_blocksize(bdev, lo->blksize);
 		set_capacity(lo->disk, lo->bytesize >> 9);
 		return 0;
+
 	case NBD_SET_TIMEOUT:
 		lo->xmit_timeout = arg * HZ;
 		return 0;
+
 	case NBD_SET_SIZE_BLOCKS:
 		lo->bytesize = ((u64) arg) * lo->blksize;
 		bdev->bd_inode->i_size = lo->bytesize;
 		set_blocksize(bdev, lo->blksize);
 		set_capacity(lo->disk, lo->bytesize >> 9);
 		return 0;
-	case NBD_DO_IT:
+
+	case NBD_DO_IT: {
+		struct task_struct *thread;
+		struct file *file;
+		int error;
+
 		if (lo->pid)
 			return -EBUSY;
 		if (!lo->file)
 			return -EINVAL;
+
+		mutex_unlock(&lo->tx_lock);
+
 		thread = kthread_create(nbd_thread, lo, lo->disk->disk_name);
-		if (IS_ERR(thread))
+		if (IS_ERR(thread)) {
+			mutex_lock(&lo->tx_lock);
 			return PTR_ERR(thread);
+		}
 		wake_up_process(thread);
 		error = nbd_do_it(lo);
 		kthread_stop(thread);
+
+		mutex_lock(&lo->tx_lock);
 		if (error)
 			return error;
-		sock_shutdown(lo, 1);
+		sock_shutdown(lo, 0);
 		file = lo->file;
 		lo->file = NULL;
 		nbd_clear_que(lo);
@@ -684,6 +689,8 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 		if (max_part > 0)
 			ioctl_by_bdev(bdev, BLKRRPART, 0);
 		return lo->harderror;
+	}
+
 	case NBD_CLEAR_QUE:
 		/*
 		 * This is for compatibility only.  The queue is always cleared
@@ -691,6 +698,7 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 		 */
 		BUG_ON(!lo->sock && !list_empty(&lo->queue_head));
 		return 0;
+
 	case NBD_PRINT_DEBUG:
 		printk(KERN_INFO "%s: next = %p, prev = %p, head = %p\n",
 			bdev->bd_disk->disk_name,
@@ -698,7 +706,29 @@ static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
 			&lo->queue_head);
 		return 0;
 	}
-	return -EINVAL;
+	return -ENOTTY;
+}
+
+static int nbd_ioctl(struct block_device *bdev, fmode_t mode,
+		     unsigned int cmd, unsigned long arg)
+{
+	struct nbd_device *lo = bdev->bd_disk->private_data;
+	int error;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	BUG_ON(lo->magic != LO_MAGIC);
+
+	/* Anyone capable of this syscall can do *real bad* things */
+	dprintk(DBG_IOCTL, "%s: nbd_ioctl cmd=%s(0x%x) arg=%lu\n",
+			lo->disk->disk_name, ioctl_cmd_to_ascii(cmd), cmd, arg);
+
+	mutex_lock(&lo->tx_lock);
+	error = __nbd_ioctl(bdev, lo, cmd, arg);
+	mutex_unlock(&lo->tx_lock);
+
+	return error;
 }
 
 static struct block_device_operations nbd_fops =
diff --git a/drivers/block/xsysace.c b/drivers/block/xsysace.c
index 119be3442f28..6cccdc3f5220 100644
--- a/drivers/block/xsysace.c
+++ b/drivers/block/xsysace.c
@@ -89,6 +89,7 @@
 #include <linux/delay.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
+#include <linux/ata.h>
 #include <linux/hdreg.h>
 #include <linux/platform_device.h>
 #if defined(CONFIG_OF)
@@ -208,7 +209,7 @@ struct ace_device {
 	struct gendisk *gd;
 
 	/* Inserted CF card parameters */
-	struct hd_driveid cf_id;
+	u16 cf_id[ATA_ID_WORDS];
 };
 
 static int ace_major;
@@ -402,21 +403,14 @@ static void ace_dump_regs(struct ace_device *ace)
 		 ace_in32(ace, ACE_CFGLBA), ace_in(ace, ACE_FATSTAT));
 }
 
-void ace_fix_driveid(struct hd_driveid *id)
+void ace_fix_driveid(u16 *id)
 {
 #if defined(__BIG_ENDIAN)
-	u16 *buf = (void *)id;
 	int i;
 
 	/* All half words have wrong byte order; swap the bytes */
-	for (i = 0; i < sizeof(struct hd_driveid); i += 2, buf++)
-		*buf = le16_to_cpu(*buf);
-
-	/* Some of the data values are 32bit; swap the half words  */
-	id->lba_capacity = ((id->lba_capacity >> 16) & 0x0000FFFF) |
-	    ((id->lba_capacity << 16) & 0xFFFF0000);
-	id->spg = ((id->spg >> 16) & 0x0000FFFF) |
-	    ((id->spg << 16) & 0xFFFF0000);
+	for (i = 0; i < ATA_ID_WORDS; i++, id++)
+		*id = le16_to_cpu(*id);
 #endif
 }
 
@@ -614,7 +608,7 @@ static void ace_fsm_dostate(struct ace_device *ace)
 		break;
 
 	case ACE_FSM_STATE_IDENTIFY_COMPLETE:
-		ace_fix_driveid(&ace->cf_id);
+		ace_fix_driveid(&ace->cf_id[0]);
 		ace_dump_mem(&ace->cf_id, 512);	/* Debug: Dump out disk ID */
 
 		if (ace->data_result) {
@@ -627,9 +621,10 @@ static void ace_fsm_dostate(struct ace_device *ace)
 			ace->media_change = 0;
 
 			/* Record disk parameters */
-			set_capacity(ace->gd, ace->cf_id.lba_capacity);
+			set_capacity(ace->gd,
+				ata_id_u32(&ace->cf_id, ATA_ID_LBA_CAPACITY));
 			dev_info(ace->dev, "capacity: %i sectors\n",
-				 ace->cf_id.lba_capacity);
+				ata_id_u32(&ace->cf_id, ATA_ID_LBA_CAPACITY));
 		}
 
 		/* We're done, drop to IDLE state and notify waiters */
@@ -928,12 +923,13 @@ static int ace_release(struct gendisk *disk, fmode_t mode)
 static int ace_getgeo(struct block_device *bdev, struct hd_geometry *geo)
 {
 	struct ace_device *ace = bdev->bd_disk->private_data;
+	u16 *cf_id = &ace->cf_id[0];
 
 	dev_dbg(ace->dev, "ace_getgeo()\n");
 
-	geo->heads = ace->cf_id.heads;
-	geo->sectors = ace->cf_id.sectors;
-	geo->cylinders = ace->cf_id.cyls;
+	geo->heads	= cf_id[ATA_ID_HEADS];
+	geo->sectors	= cf_id[ATA_ID_SECTORS];
+	geo->cylinders	= cf_id[ATA_ID_CYLS];
 
 	return 0;
 }
diff --git a/drivers/char/bsr.c b/drivers/char/bsr.c
index f6094ae0ef33..140ea10ecb88 100644
--- a/drivers/char/bsr.c
+++ b/drivers/char/bsr.c
@@ -140,7 +140,7 @@ static int bsr_open(struct inode * inode, struct file * filp)
 	return 0;
 }
 
-const static struct file_operations bsr_fops = {
+static const struct file_operations bsr_fops = {
 	.owner = THIS_MODULE,
 	.mmap  = bsr_mmap,
 	.open  = bsr_open,
diff --git a/drivers/char/hpet.c b/drivers/char/hpet.c
index 32b8bbf5003e..50dfa3bc71ce 100644
--- a/drivers/char/hpet.c
+++ b/drivers/char/hpet.c
@@ -713,7 +713,7 @@ static struct ctl_table_header *sysctl_header;
  */
 #define	TICK_CALIBRATE	(1000UL)
 
-static unsigned long hpet_calibrate(struct hpets *hpetp)
+static unsigned long __hpet_calibrate(struct hpets *hpetp)
 {
 	struct hpet_timer __iomem *timer = NULL;
 	unsigned long t, m, count, i, flags, start;
@@ -750,6 +750,26 @@ static unsigned long hpet_calibrate(struct hpets *hpetp)
 	return (m - start) / i;
 }
 
+static unsigned long hpet_calibrate(struct hpets *hpetp)
+{
+	unsigned long ret = -1;
+	unsigned long tmp;
+
+	/*
+	 * Try to calibrate until return value becomes stable small value.
+	 * If SMI interruption occurs in calibration loop, the return value
+	 * will be big. This avoids its impact.
+	 */
+	for ( ; ; ) {
+		tmp = __hpet_calibrate(hpetp);
+		if (ret <= tmp)
+			break;
+		ret = tmp;
+	}
+
+	return ret;
+}
+
 int hpet_alloc(struct hpet_data *hdp)
 {
 	u64 cap, mcfg;
diff --git a/drivers/char/hw_random/timeriomem-rng.c b/drivers/char/hw_random/timeriomem-rng.c
index 10ad41be5897..dcd352ad0e7f 100644
--- a/drivers/char/hw_random/timeriomem-rng.c
+++ b/drivers/char/hw_random/timeriomem-rng.c
@@ -90,10 +90,30 @@ static struct hwrng timeriomem_rng_ops = {
 
 static int __init timeriomem_rng_probe(struct platform_device *pdev)
 {
+	struct resource *res, *mem;
 	int ret;
 
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+
+	if (!res)
+		return -ENOENT;
+
+	mem = request_mem_region(res->start, res->end - res->start + 1,
+				 pdev->name);
+	if (mem == NULL)
+		return -EBUSY;
+
+	dev_set_drvdata(&pdev->dev, mem);
+
 	timeriomem_rng_data = pdev->dev.platform_data;
 
+	timeriomem_rng_data->address = ioremap(res->start,
+						res->end - res->start + 1);
+	if (!timeriomem_rng_data->address) {
+		ret = -ENOMEM;
+		goto err_ioremap;
+	}
+
 	if (timeriomem_rng_data->period != 0
 		&& usecs_to_jiffies(timeriomem_rng_data->period) > 0) {
 		timeriomem_rng_timer.expires = jiffies;
@@ -104,23 +124,34 @@ static int __init timeriomem_rng_probe(struct platform_device *pdev)
 	timeriomem_rng_data->present = 1;
 
 	ret = hwrng_register(&timeriomem_rng_ops);
-	if (ret) {
-		dev_err(&pdev->dev, "problem registering\n");
-		return ret;
-	}
+	if (ret)
+		goto err_register;
 
 	dev_info(&pdev->dev, "32bits from 0x%p @ %dus\n",
 			timeriomem_rng_data->address,
 			timeriomem_rng_data->period);
 
 	return 0;
+
+err_register:
+	dev_err(&pdev->dev, "problem registering\n");
+	iounmap(timeriomem_rng_data->address);
+err_ioremap:
+	release_resource(mem);
+
+	return ret;
 }
 
 static int __devexit timeriomem_rng_remove(struct platform_device *pdev)
 {
+	struct resource *mem = dev_get_drvdata(&pdev->dev);
+
 	del_timer_sync(&timeriomem_rng_timer);
 	hwrng_unregister(&timeriomem_rng_ops);
 
+	iounmap(timeriomem_rng_data->address);
+	release_resource(mem);
+
 	return 0;
 }
 
diff --git a/drivers/char/random.c b/drivers/char/random.c
index 7c43ae782b26..f824ef8a9273 100644
--- a/drivers/char/random.c
+++ b/drivers/char/random.c
@@ -1488,7 +1488,8 @@ static void rekey_seq_generator(struct work_struct *work)
 	keyptr->count = (ip_cnt & COUNT_MASK) << HASH_BITS;
 	smp_wmb();
 	ip_cnt++;
-	schedule_delayed_work(&rekey_work, REKEY_INTERVAL);
+	schedule_delayed_work(&rekey_work,
+			      round_jiffies_relative(REKEY_INTERVAL));
 }
 
 static inline struct keydata *get_keyptr(void)
diff --git a/drivers/char/synclink_gt.c b/drivers/char/synclink_gt.c
index 6ec6e13d47d7..5e256494686a 100644
--- a/drivers/char/synclink_gt.c
+++ b/drivers/char/synclink_gt.c
@@ -298,6 +298,7 @@ struct slgt_info {
 
 	unsigned int rbuf_fill_level;
 	unsigned int if_mode;
+	unsigned int base_clock;
 
 	/* device status */
 
@@ -1156,22 +1157,26 @@ static long set_params32(struct slgt_info *info, struct MGSL_PARAMS32 __user *ne
 		return -EFAULT;
 
 	spin_lock(&info->lock);
-	info->params.mode            = tmp_params.mode;
-	info->params.loopback        = tmp_params.loopback;
-	info->params.flags           = tmp_params.flags;
-	info->params.encoding        = tmp_params.encoding;
-	info->params.clock_speed     = tmp_params.clock_speed;
-	info->params.addr_filter     = tmp_params.addr_filter;
-	info->params.crc_type        = tmp_params.crc_type;
-	info->params.preamble_length = tmp_params.preamble_length;
-	info->params.preamble        = tmp_params.preamble;
-	info->params.data_rate       = tmp_params.data_rate;
-	info->params.data_bits       = tmp_params.data_bits;
-	info->params.stop_bits       = tmp_params.stop_bits;
-	info->params.parity          = tmp_params.parity;
+	if (tmp_params.mode == MGSL_MODE_BASE_CLOCK) {
+		info->base_clock = tmp_params.clock_speed;
+	} else {
+		info->params.mode            = tmp_params.mode;
+		info->params.loopback        = tmp_params.loopback;
+		info->params.flags           = tmp_params.flags;
+		info->params.encoding        = tmp_params.encoding;
+		info->params.clock_speed     = tmp_params.clock_speed;
+		info->params.addr_filter     = tmp_params.addr_filter;
+		info->params.crc_type        = tmp_params.crc_type;
+		info->params.preamble_length = tmp_params.preamble_length;
+		info->params.preamble        = tmp_params.preamble;
+		info->params.data_rate       = tmp_params.data_rate;
+		info->params.data_bits       = tmp_params.data_bits;
+		info->params.stop_bits       = tmp_params.stop_bits;
+		info->params.parity          = tmp_params.parity;
+	}
 	spin_unlock(&info->lock);
 
- 	change_params(info);
+	program_hw(info);
 
 	return 0;
 }
@@ -2559,10 +2564,13 @@ static int set_params(struct slgt_info *info, MGSL_PARAMS __user *new_params)
 		return -EFAULT;
 
 	spin_lock_irqsave(&info->lock, flags);
-	memcpy(&info->params, &tmp_params, sizeof(MGSL_PARAMS));
+	if (tmp_params.mode == MGSL_MODE_BASE_CLOCK)
+		info->base_clock = tmp_params.clock_speed;
+	else
+		memcpy(&info->params, &tmp_params, sizeof(MGSL_PARAMS));
 	spin_unlock_irqrestore(&info->lock, flags);
 
- 	change_params(info);
+	program_hw(info);
 
 	return 0;
 }
@@ -3432,6 +3440,7 @@ static struct slgt_info *alloc_dev(int adapter_num, int port_num, struct pci_dev
 		info->magic = MGSL_MAGIC;
 		INIT_WORK(&info->task, bh_handler);
 		info->max_frame_size = 4096;
+		info->base_clock = 14745600;
 		info->rbuf_fill_level = DMABUFSIZE;
 		info->port.close_delay = 5*HZ/10;
 		info->port.closing_wait = 30*HZ;
@@ -3779,7 +3788,7 @@ static void enable_loopback(struct slgt_info *info)
 static void set_rate(struct slgt_info *info, u32 rate)
 {
 	unsigned int div;
-	static unsigned int osc = 14745600;
+	unsigned int osc = info->base_clock;
 
 	/* div = osc/rate - 1
 	 *
@@ -4083,18 +4092,27 @@ static void async_mode(struct slgt_info *info)
 	 * 06  CTS      IRQ enable
 	 * 05  DCD      IRQ enable
 	 * 04  RI       IRQ enable
-	 * 03  reserved, must be zero
+	 * 03  0=16x sampling, 1=8x sampling
 	 * 02  1=txd->rxd internal loopback enable
 	 * 01  reserved, must be zero
 	 * 00  1=master IRQ enable
 	 */
 	val = BIT15 + BIT14 + BIT0;
+	/* JCR[8] : 1 = x8 async mode feature available */
+	if ((rd_reg32(info, JCR) & BIT8) && info->params.data_rate &&
+	    ((info->base_clock < (info->params.data_rate * 16)) ||
+	     (info->base_clock % (info->params.data_rate * 16)))) {
+		/* use 8x sampling */
+		val |= BIT3;
+		set_rate(info, info->params.data_rate * 8);
+	} else {
+		/* use 16x sampling */
+		set_rate(info, info->params.data_rate * 16);
+	}
 	wr_reg16(info, SCR, val);
 
 	slgt_irq_on(info, IRQ_RXBREAK | IRQ_RXOVER);
 
-	set_rate(info, info->params.data_rate * 16);
-
 	if (info->params.loopback)
 		enable_loopback(info);
 }
diff --git a/drivers/char/tty_audit.c b/drivers/char/tty_audit.c
index 34ab6d798f81..55ba6f142883 100644
--- a/drivers/char/tty_audit.c
+++ b/drivers/char/tty_audit.c
@@ -10,8 +10,6 @@
  */
 
 #include <linux/audit.h>
-#include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/tty.h>
 
 struct tty_audit_buf {
diff --git a/drivers/char/tty_io.c b/drivers/char/tty_io.c
index 33dac94922a7..66b99a2049e3 100644
--- a/drivers/char/tty_io.c
+++ b/drivers/char/tty_io.c
@@ -1758,7 +1758,7 @@ static int __tty_open(struct inode *inode, struct file *filp)
 	struct tty_driver *driver;
 	int index;
 	dev_t device = inode->i_rdev;
-	unsigned short saved_flags = filp->f_flags;
+	unsigned saved_flags = filp->f_flags;
 
 	nonseekable_open(inode, filp);
 
@@ -2681,7 +2681,7 @@ void __do_SAK(struct tty_struct *tty)
 	/* Kill the entire session */
 	do_each_pid_task(session, PIDTYPE_SID, p) {
 		printk(KERN_NOTICE "SAK: killed process %d"
-			" (%s): task_session_nr(p)==tty->session\n",
+			" (%s): task_session(p)==tty->session\n",
 			task_pid_nr(p), p->comm);
 		send_sig(SIGKILL, p, 1);
 	} while_each_pid_task(session, PIDTYPE_SID, p);
@@ -2691,7 +2691,7 @@ void __do_SAK(struct tty_struct *tty)
 	do_each_thread(g, p) {
 		if (p->signal->tty == tty) {
 			printk(KERN_NOTICE "SAK: killed process %d"
-			    " (%s): task_session_nr(p)==tty->session\n",
+			    " (%s): task_session(p)==tty->session\n",
 			    task_pid_nr(p), p->comm);
 			send_sig(SIGKILL, p, 1);
 			continue;
diff --git a/drivers/char/tty_ldisc.c b/drivers/char/tty_ldisc.c
index 7a84b406a952..f78f5b0127a8 100644
--- a/drivers/char/tty_ldisc.c
+++ b/drivers/char/tty_ldisc.c
@@ -10,7 +10,6 @@
 #include <linux/tty_flip.h>
 #include <linux/devpts_fs.h>
 #include <linux/file.h>
-#include <linux/fdtable.h>
 #include <linux/console.h>
 #include <linux/timer.h>
 #include <linux/ctype.h>
diff --git a/drivers/crypto/hifn_795x.c b/drivers/crypto/hifn_795x.c
index 0c79fe7f1567..4d85402a9e4a 100644
--- a/drivers/crypto/hifn_795x.c
+++ b/drivers/crypto/hifn_795x.c
@@ -1882,7 +1882,7 @@ static void hifn_clear_rings(struct hifn_device *dev, int error)
 
 static void hifn_work(struct work_struct *work)
 {
-	struct delayed_work *dw = container_of(work, struct delayed_work, work);
+	struct delayed_work *dw = to_delayed_work(work);
 	struct hifn_device *dev = container_of(dw, struct hifn_device, work);
 	unsigned long flags;
 	int reset = 0;
diff --git a/drivers/crypto/ixp4xx_crypto.c b/drivers/crypto/ixp4xx_crypto.c
index d9e751be8c5f..af9761ccf9f1 100644
--- a/drivers/crypto/ixp4xx_crypto.c
+++ b/drivers/crypto/ixp4xx_crypto.c
@@ -101,6 +101,7 @@ struct buffer_desc {
 	u32 phys_addr;
 	u32 __reserved[4];
 	struct buffer_desc *next;
+	enum dma_data_direction dir;
 };
 
 struct crypt_ctl {
@@ -132,14 +133,10 @@ struct crypt_ctl {
 struct ablk_ctx {
 	struct buffer_desc *src;
 	struct buffer_desc *dst;
-	unsigned src_nents;
-	unsigned dst_nents;
 };
 
 struct aead_ctx {
 	struct buffer_desc *buffer;
-	unsigned short assoc_nents;
-	unsigned short src_nents;
 	struct scatterlist ivlist;
 	/* used when the hmac is not on one sg entry */
 	u8 *hmac_virt;
@@ -312,7 +309,7 @@ static struct crypt_ctl *get_crypt_desc_emerg(void)
 	}
 }
 
-static void free_buf_chain(struct buffer_desc *buf, u32 phys)
+static void free_buf_chain(struct device *dev, struct buffer_desc *buf,u32 phys)
 {
 	while (buf) {
 		struct buffer_desc *buf1;
@@ -320,6 +317,7 @@ static void free_buf_chain(struct buffer_desc *buf, u32 phys)
 
 		buf1 = buf->next;
 		phys1 = buf->phys_next;
+		dma_unmap_single(dev, buf->phys_next, buf->buf_len, buf->dir);
 		dma_pool_free(buffer_pool, buf, phys);
 		buf = buf1;
 		phys = phys1;
@@ -348,7 +346,6 @@ static void one_packet(dma_addr_t phys)
 	struct crypt_ctl *crypt;
 	struct ixp_ctx *ctx;
 	int failed;
-	enum dma_data_direction src_direction = DMA_BIDIRECTIONAL;
 
 	failed = phys & 0x1 ? -EBADMSG : 0;
 	phys &= ~0x3;
@@ -358,13 +355,8 @@ static void one_packet(dma_addr_t phys)
 	case CTL_FLAG_PERFORM_AEAD: {
 		struct aead_request *req = crypt->data.aead_req;
 		struct aead_ctx *req_ctx = aead_request_ctx(req);
-		dma_unmap_sg(dev, req->assoc, req_ctx->assoc_nents,
-				DMA_TO_DEVICE);
-		dma_unmap_sg(dev, &req_ctx->ivlist, 1, DMA_BIDIRECTIONAL);
-		dma_unmap_sg(dev, req->src, req_ctx->src_nents,
-				DMA_BIDIRECTIONAL);
 
-		free_buf_chain(req_ctx->buffer, crypt->src_buf);
+		free_buf_chain(dev, req_ctx->buffer, crypt->src_buf);
 		if (req_ctx->hmac_virt) {
 			finish_scattered_hmac(crypt);
 		}
@@ -374,16 +366,11 @@ static void one_packet(dma_addr_t phys)
 	case CTL_FLAG_PERFORM_ABLK: {
 		struct ablkcipher_request *req = crypt->data.ablk_req;
 		struct ablk_ctx *req_ctx = ablkcipher_request_ctx(req);
-		int nents;
+
 		if (req_ctx->dst) {
-			nents = req_ctx->dst_nents;
-			dma_unmap_sg(dev, req->dst, nents, DMA_FROM_DEVICE);
-			free_buf_chain(req_ctx->dst, crypt->dst_buf);
-			src_direction = DMA_TO_DEVICE;
+			free_buf_chain(dev, req_ctx->dst, crypt->dst_buf);
 		}
-		nents = req_ctx->src_nents;
-		dma_unmap_sg(dev, req->src, nents, src_direction);
-		free_buf_chain(req_ctx->src, crypt->src_buf);
+		free_buf_chain(dev, req_ctx->src, crypt->src_buf);
 		req->base.complete(&req->base, failed);
 		break;
 	}
@@ -750,56 +737,35 @@ static int setup_cipher(struct crypto_tfm *tfm, int encrypt,
 	return 0;
 }
 
-static int count_sg(struct scatterlist *sg, int nbytes)
+static struct buffer_desc *chainup_buffers(struct device *dev,
+		struct scatterlist *sg,	unsigned nbytes,
+		struct buffer_desc *buf, gfp_t flags,
+		enum dma_data_direction dir)
 {
-	int i;
-	for (i = 0; nbytes > 0; i++, sg = sg_next(sg))
-		nbytes -= sg->length;
-	return i;
-}
-
-static struct buffer_desc *chainup_buffers(struct scatterlist *sg,
-			unsigned nbytes, struct buffer_desc *buf, gfp_t flags)
-{
-	int nents = 0;
-
-	while (nbytes > 0) {
+	for (;nbytes > 0; sg = scatterwalk_sg_next(sg)) {
+		unsigned len = min(nbytes, sg->length);
 		struct buffer_desc *next_buf;
 		u32 next_buf_phys;
-		unsigned len = min(nbytes, sg_dma_len(sg));
+		void *ptr;
 
-		nents++;
 		nbytes -= len;
-		if (!buf->phys_addr) {
-			buf->phys_addr = sg_dma_address(sg);
-			buf->buf_len = len;
-			buf->next = NULL;
-			buf->phys_next = 0;
-			goto next;
-		}
-		/* Two consecutive chunks on one page may be handled by the old
-		 * buffer descriptor, increased by the length of the new one
-		 */
-		if (sg_dma_address(sg) == buf->phys_addr + buf->buf_len) {
-			buf->buf_len += len;
-			goto next;
-		}
+		ptr = page_address(sg_page(sg)) + sg->offset;
 		next_buf = dma_pool_alloc(buffer_pool, flags, &next_buf_phys);
-		if (!next_buf)
-			return NULL;
+		if (!next_buf) {
+			buf = NULL;
+			break;
+		}
+		sg_dma_address(sg) = dma_map_single(dev, ptr, len, dir);
 		buf->next = next_buf;
 		buf->phys_next = next_buf_phys;
-
 		buf = next_buf;
-		buf->next = NULL;
-		buf->phys_next = 0;
+
 		buf->phys_addr = sg_dma_address(sg);
 		buf->buf_len = len;
-next:
-		if (nbytes > 0) {
-			sg = sg_next(sg);
-		}
+		buf->dir = dir;
 	}
+	buf->next = NULL;
+	buf->phys_next = 0;
 	return buf;
 }
 
@@ -860,12 +826,12 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt)
 	struct crypto_ablkcipher *tfm = crypto_ablkcipher_reqtfm(req);
 	struct ixp_ctx *ctx = crypto_ablkcipher_ctx(tfm);
 	unsigned ivsize = crypto_ablkcipher_ivsize(tfm);
-	int ret = -ENOMEM;
 	struct ix_sa_dir *dir;
 	struct crypt_ctl *crypt;
-	unsigned int nbytes = req->nbytes, nents;
+	unsigned int nbytes = req->nbytes;
 	enum dma_data_direction src_direction = DMA_BIDIRECTIONAL;
 	struct ablk_ctx *req_ctx = ablkcipher_request_ctx(req);
+	struct buffer_desc src_hook;
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
 				GFP_KERNEL : GFP_ATOMIC;
 
@@ -878,7 +844,7 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt)
 
 	crypt = get_crypt_desc();
 	if (!crypt)
-		return ret;
+		return -ENOMEM;
 
 	crypt->data.ablk_req = req;
 	crypt->crypto_ctx = dir->npe_ctx_phys;
@@ -891,53 +857,41 @@ static int ablk_perform(struct ablkcipher_request *req, int encrypt)
 	BUG_ON(ivsize && !req->info);
 	memcpy(crypt->iv, req->info, ivsize);
 	if (req->src != req->dst) {
+		struct buffer_desc dst_hook;
 		crypt->mode |= NPE_OP_NOT_IN_PLACE;
-		nents = count_sg(req->dst, nbytes);
 		/* This was never tested by Intel
 		 * for more than one dst buffer, I think. */
-		BUG_ON(nents != 1);
-		req_ctx->dst_nents = nents;
-		dma_map_sg(dev, req->dst, nents, DMA_FROM_DEVICE);
-		req_ctx->dst = dma_pool_alloc(buffer_pool, flags,&crypt->dst_buf);
-		if (!req_ctx->dst)
-			goto unmap_sg_dest;
-		req_ctx->dst->phys_addr = 0;
-		if (!chainup_buffers(req->dst, nbytes, req_ctx->dst, flags))
+		BUG_ON(req->dst->length < nbytes);
+		req_ctx->dst = NULL;
+		if (!chainup_buffers(dev, req->dst, nbytes, &dst_hook,
+					flags, DMA_FROM_DEVICE))
 			goto free_buf_dest;
 		src_direction = DMA_TO_DEVICE;
+		req_ctx->dst = dst_hook.next;
+		crypt->dst_buf = dst_hook.phys_next;
 	} else {
 		req_ctx->dst = NULL;
-		req_ctx->dst_nents = 0;
 	}
-	nents = count_sg(req->src, nbytes);
-	req_ctx->src_nents = nents;
-	dma_map_sg(dev, req->src, nents, src_direction);
-
-	req_ctx->src = dma_pool_alloc(buffer_pool, flags, &crypt->src_buf);
-	if (!req_ctx->src)
-		goto unmap_sg_src;
-	req_ctx->src->phys_addr = 0;
-	if (!chainup_buffers(req->src, nbytes, req_ctx->src, flags))
+	req_ctx->src = NULL;
+	if (!chainup_buffers(dev, req->src, nbytes, &src_hook,
+				flags, src_direction))
 		goto free_buf_src;
 
+	req_ctx->src = src_hook.next;
+	crypt->src_buf = src_hook.phys_next;
 	crypt->ctl_flags |= CTL_FLAG_PERFORM_ABLK;
 	qmgr_put_entry(SEND_QID, crypt_virt2phys(crypt));
 	BUG_ON(qmgr_stat_overflow(SEND_QID));
 	return -EINPROGRESS;
 
 free_buf_src:
-	free_buf_chain(req_ctx->src, crypt->src_buf);
-unmap_sg_src:
-	dma_unmap_sg(dev, req->src, req_ctx->src_nents, src_direction);
+	free_buf_chain(dev, req_ctx->src, crypt->src_buf);
 free_buf_dest:
 	if (req->src != req->dst) {
-		free_buf_chain(req_ctx->dst, crypt->dst_buf);
-unmap_sg_dest:
-		dma_unmap_sg(dev, req->src, req_ctx->dst_nents,
-			DMA_FROM_DEVICE);
+		free_buf_chain(dev, req_ctx->dst, crypt->dst_buf);
 	}
 	crypt->ctl_flags = CTL_FLAG_UNUSED;
-	return ret;
+	return -ENOMEM;
 }
 
 static int ablk_encrypt(struct ablkcipher_request *req)
@@ -985,7 +939,7 @@ static int hmac_inconsistent(struct scatterlist *sg, unsigned start,
 			break;
 
 		offset += sg->length;
-		sg = sg_next(sg);
+		sg = scatterwalk_sg_next(sg);
 	}
 	return (start + nbytes > offset + sg->length);
 }
@@ -997,11 +951,10 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	struct ixp_ctx *ctx = crypto_aead_ctx(tfm);
 	unsigned ivsize = crypto_aead_ivsize(tfm);
 	unsigned authsize = crypto_aead_authsize(tfm);
-	int ret = -ENOMEM;
 	struct ix_sa_dir *dir;
 	struct crypt_ctl *crypt;
-	unsigned int cryptlen, nents;
-	struct buffer_desc *buf;
+	unsigned int cryptlen;
+	struct buffer_desc *buf, src_hook;
 	struct aead_ctx *req_ctx = aead_request_ctx(req);
 	gfp_t flags = req->base.flags & CRYPTO_TFM_REQ_MAY_SLEEP ?
 				GFP_KERNEL : GFP_ATOMIC;
@@ -1022,7 +975,7 @@ static int aead_perform(struct aead_request *req, int encrypt,
 	}
 	crypt = get_crypt_desc();
 	if (!crypt)
-		return ret;
+		return -ENOMEM;
 
 	crypt->data.aead_req = req;
 	crypt->crypto_ctx = dir->npe_ctx_phys;
@@ -1041,31 +994,27 @@ static int aead_perform(struct aead_request *req, int encrypt,
 		BUG(); /* -ENOTSUP because of my lazyness */
 	}
 
-	req_ctx->buffer = dma_pool_alloc(buffer_pool, flags, &crypt->src_buf);
-	if (!req_ctx->buffer)
-		goto out;
-	req_ctx->buffer->phys_addr = 0;
 	/* ASSOC data */
-	nents = count_sg(req->assoc, req->assoclen);
-	req_ctx->assoc_nents = nents;
-	dma_map_sg(dev, req->assoc, nents, DMA_TO_DEVICE);
-	buf = chainup_buffers(req->assoc, req->assoclen, req_ctx->buffer,flags);
+	buf = chainup_buffers(dev, req->assoc, req->assoclen, &src_hook,
+		flags, DMA_TO_DEVICE);
+	req_ctx->buffer = src_hook.next;
+	crypt->src_buf = src_hook.phys_next;
 	if (!buf)
-		goto unmap_sg_assoc;
+		goto out;
 	/* IV */
 	sg_init_table(&req_ctx->ivlist, 1);
 	sg_set_buf(&req_ctx->ivlist, iv, ivsize);
-	dma_map_sg(dev, &req_ctx->ivlist, 1, DMA_BIDIRECTIONAL);
-	buf = chainup_buffers(&req_ctx->ivlist, ivsize, buf, flags);
+	buf = chainup_buffers(dev, &req_ctx->ivlist, ivsize, buf, flags,
+			DMA_BIDIRECTIONAL);
 	if (!buf)
-		goto unmap_sg_iv;
+		goto free_chain;
 	if (unlikely(hmac_inconsistent(req->src, cryptlen, authsize))) {
 		/* The 12 hmac bytes are scattered,
 		 * we need to copy them into a safe buffer */
 		req_ctx->hmac_virt = dma_pool_alloc(buffer_pool, flags,
 				&crypt->icv_rev_aes);
 		if (unlikely(!req_ctx->hmac_virt))
-			goto unmap_sg_iv;
+			goto free_chain;
 		if (!encrypt) {
 			scatterwalk_map_and_copy(req_ctx->hmac_virt,
 				req->src, cryptlen, authsize, 0);
@@ -1075,33 +1024,28 @@ static int aead_perform(struct aead_request *req, int encrypt,
 		req_ctx->hmac_virt = NULL;
 	}
 	/* Crypt */
-	nents = count_sg(req->src, cryptlen + authsize);
-	req_ctx->src_nents = nents;
-	dma_map_sg(dev, req->src, nents, DMA_BIDIRECTIONAL);
-	buf = chainup_buffers(req->src, cryptlen + authsize, buf, flags);
+	buf = chainup_buffers(dev, req->src, cryptlen + authsize, buf, flags,
+			DMA_BIDIRECTIONAL);
 	if (!buf)
-		goto unmap_sg_src;
+		goto free_hmac_virt;
 	if (!req_ctx->hmac_virt) {
 		crypt->icv_rev_aes = buf->phys_addr + buf->buf_len - authsize;
 	}
+
 	crypt->ctl_flags |= CTL_FLAG_PERFORM_AEAD;
 	qmgr_put_entry(SEND_QID, crypt_virt2phys(crypt));
 	BUG_ON(qmgr_stat_overflow(SEND_QID));
 	return -EINPROGRESS;
-unmap_sg_src:
-	dma_unmap_sg(dev, req->src, req_ctx->src_nents, DMA_BIDIRECTIONAL);
+free_hmac_virt:
 	if (req_ctx->hmac_virt) {
 		dma_pool_free(buffer_pool, req_ctx->hmac_virt,
 				crypt->icv_rev_aes);
 	}
-unmap_sg_iv:
-	dma_unmap_sg(dev, &req_ctx->ivlist, 1, DMA_BIDIRECTIONAL);
-unmap_sg_assoc:
-	dma_unmap_sg(dev, req->assoc, req_ctx->assoc_nents, DMA_TO_DEVICE);
-	free_buf_chain(req_ctx->buffer, crypt->src_buf);
+free_chain:
+	free_buf_chain(dev, req_ctx->buffer, crypt->src_buf);
 out:
 	crypt->ctl_flags = CTL_FLAG_UNUSED;
-	return ret;
+	return -ENOMEM;
 }
 
 static int aead_setup(struct crypto_aead *tfm, unsigned int authsize)
diff --git a/drivers/dma/Kconfig b/drivers/dma/Kconfig
index 48ea59e79672..3b3c01b6f1ee 100644
--- a/drivers/dma/Kconfig
+++ b/drivers/dma/Kconfig
@@ -98,6 +98,17 @@ config NET_DMA
 	  Say Y here if you enabled INTEL_IOATDMA or FSL_DMA, otherwise
 	  say N.
 
+config ASYNC_TX_DMA
+	bool "Async_tx: Offload support for the async_tx api"
+	depends on DMA_ENGINE
+	help
+	  This allows the async_tx api to take advantage of offload engines for
+	  memcpy, memset, xor, and raid6 p+q operations.  If your platform has
+	  a dma engine that can perform raid operations and you have enabled
+	  MD_RAID456 say Y.
+
+	  If unsure, say N.
+
 config DMATEST
 	tristate "DMA Test client"
 	depends on DMA_ENGINE
diff --git a/drivers/dma/dmaengine.c b/drivers/dma/dmaengine.c
index 280a9d263eb3..92438e9dacc3 100644
--- a/drivers/dma/dmaengine.c
+++ b/drivers/dma/dmaengine.c
@@ -507,6 +507,7 @@ struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, v
 			 * published in the general-purpose allocator
 			 */
 			dma_cap_set(DMA_PRIVATE, device->cap_mask);
+			device->privatecnt++;
 			err = dma_chan_get(chan);
 
 			if (err == -ENODEV) {
@@ -518,6 +519,8 @@ struct dma_chan *__dma_request_channel(dma_cap_mask_t *mask, dma_filter_fn fn, v
 				       dma_chan_name(chan), err);
 			else
 				break;
+			if (--device->privatecnt == 0)
+				dma_cap_clear(DMA_PRIVATE, device->cap_mask);
 			chan->private = NULL;
 			chan = NULL;
 		}
@@ -537,6 +540,9 @@ void dma_release_channel(struct dma_chan *chan)
 	WARN_ONCE(chan->client_count != 1,
 		  "chan reference count %d != 1\n", chan->client_count);
 	dma_chan_put(chan);
+	/* drop PRIVATE cap enabled by __dma_request_channel() */
+	if (--chan->device->privatecnt == 0)
+		dma_cap_clear(DMA_PRIVATE, chan->device->cap_mask);
 	chan->private = NULL;
 	mutex_unlock(&dma_list_mutex);
 }
@@ -602,6 +608,24 @@ void dmaengine_put(void)
 }
 EXPORT_SYMBOL(dmaengine_put);
 
+static int get_dma_id(struct dma_device *device)
+{
+	int rc;
+
+ idr_retry:
+	if (!idr_pre_get(&dma_idr, GFP_KERNEL))
+		return -ENOMEM;
+	mutex_lock(&dma_list_mutex);
+	rc = idr_get_new(&dma_idr, NULL, &device->dev_id);
+	mutex_unlock(&dma_list_mutex);
+	if (rc == -EAGAIN)
+		goto idr_retry;
+	else if (rc != 0)
+		return rc;
+
+	return 0;
+}
+
 /**
  * dma_async_device_register - registers DMA devices found
  * @device: &dma_device
@@ -640,27 +664,25 @@ int dma_async_device_register(struct dma_device *device)
 	idr_ref = kmalloc(sizeof(*idr_ref), GFP_KERNEL);
 	if (!idr_ref)
 		return -ENOMEM;
-	atomic_set(idr_ref, 0);
- idr_retry:
-	if (!idr_pre_get(&dma_idr, GFP_KERNEL))
-		return -ENOMEM;
-	mutex_lock(&dma_list_mutex);
-	rc = idr_get_new(&dma_idr, NULL, &device->dev_id);
-	mutex_unlock(&dma_list_mutex);
-	if (rc == -EAGAIN)
-		goto idr_retry;
-	else if (rc != 0)
+	rc = get_dma_id(device);
+	if (rc != 0) {
+		kfree(idr_ref);
 		return rc;
+	}
+
+	atomic_set(idr_ref, 0);
 
 	/* represent channels in sysfs. Probably want devs too */
 	list_for_each_entry(chan, &device->channels, device_node) {
+		rc = -ENOMEM;
 		chan->local = alloc_percpu(typeof(*chan->local));
 		if (chan->local == NULL)
-			continue;
+			goto err_out;
 		chan->dev = kzalloc(sizeof(*chan->dev), GFP_KERNEL);
 		if (chan->dev == NULL) {
 			free_percpu(chan->local);
-			continue;
+			chan->local = NULL;
+			goto err_out;
 		}
 
 		chan->chan_id = chancnt++;
@@ -677,6 +699,8 @@ int dma_async_device_register(struct dma_device *device)
 		if (rc) {
 			free_percpu(chan->local);
 			chan->local = NULL;
+			kfree(chan->dev);
+			atomic_dec(idr_ref);
 			goto err_out;
 		}
 		chan->client_count = 0;
@@ -701,12 +725,23 @@ int dma_async_device_register(struct dma_device *device)
 			}
 		}
 	list_add_tail_rcu(&device->global_node, &dma_device_list);
+	if (dma_has_cap(DMA_PRIVATE, device->cap_mask))
+		device->privatecnt++;	/* Always private */
 	dma_channel_rebalance();
 	mutex_unlock(&dma_list_mutex);
 
 	return 0;
 
 err_out:
+	/* if we never registered a channel just release the idr */
+	if (atomic_read(idr_ref) == 0) {
+		mutex_lock(&dma_list_mutex);
+		idr_remove(&dma_idr, device->dev_id);
+		mutex_unlock(&dma_list_mutex);
+		kfree(idr_ref);
+		return rc;
+	}
+
 	list_for_each_entry(chan, &device->channels, device_node) {
 		if (chan->local == NULL)
 			continue;
@@ -893,6 +928,7 @@ void dma_async_tx_descriptor_init(struct dma_async_tx_descriptor *tx,
 {
 	tx->chan = chan;
 	spin_lock_init(&tx->lock);
+	INIT_LIST_HEAD(&tx->tx_list);
 }
 EXPORT_SYMBOL(dma_async_tx_descriptor_init);
 
diff --git a/drivers/dma/dmatest.c b/drivers/dma/dmatest.c
index e190d8b30700..a27c0fb1bc11 100644
--- a/drivers/dma/dmatest.c
+++ b/drivers/dma/dmatest.c
@@ -38,6 +38,11 @@ module_param(max_channels, uint, S_IRUGO);
 MODULE_PARM_DESC(max_channels,
 		"Maximum number of channels to use (default: all)");
 
+static unsigned int xor_sources = 3;
+module_param(xor_sources, uint, S_IRUGO);
+MODULE_PARM_DESC(xor_sources,
+		"Number of xor source buffers (default: 3)");
+
 /*
  * Initialization patterns. All bytes in the source buffer has bit 7
  * set, all bytes in the destination buffer has bit 7 cleared.
@@ -59,8 +64,9 @@ struct dmatest_thread {
 	struct list_head	node;
 	struct task_struct	*task;
 	struct dma_chan		*chan;
-	u8			*srcbuf;
-	u8			*dstbuf;
+	u8			**srcs;
+	u8			**dsts;
+	enum dma_transaction_type type;
 };
 
 struct dmatest_chan {
@@ -98,30 +104,37 @@ static unsigned long dmatest_random(void)
 	return buf;
 }
 
-static void dmatest_init_srcbuf(u8 *buf, unsigned int start, unsigned int len)
+static void dmatest_init_srcs(u8 **bufs, unsigned int start, unsigned int len)
 {
 	unsigned int i;
-
-	for (i = 0; i < start; i++)
-		buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK);
-	for ( ; i < start + len; i++)
-		buf[i] = PATTERN_SRC | PATTERN_COPY
-			| (~i & PATTERN_COUNT_MASK);;
-	for ( ; i < test_buf_size; i++)
-		buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK);
+	u8 *buf;
+
+	for (; (buf = *bufs); bufs++) {
+		for (i = 0; i < start; i++)
+			buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK);
+		for ( ; i < start + len; i++)
+			buf[i] = PATTERN_SRC | PATTERN_COPY
+				| (~i & PATTERN_COUNT_MASK);;
+		for ( ; i < test_buf_size; i++)
+			buf[i] = PATTERN_SRC | (~i & PATTERN_COUNT_MASK);
+		buf++;
+	}
 }
 
-static void dmatest_init_dstbuf(u8 *buf, unsigned int start, unsigned int len)
+static void dmatest_init_dsts(u8 **bufs, unsigned int start, unsigned int len)
 {
 	unsigned int i;
-
-	for (i = 0; i < start; i++)
-		buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK);
-	for ( ; i < start + len; i++)
-		buf[i] = PATTERN_DST | PATTERN_OVERWRITE
-			| (~i & PATTERN_COUNT_MASK);
-	for ( ; i < test_buf_size; i++)
-		buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK);
+	u8 *buf;
+
+	for (; (buf = *bufs); bufs++) {
+		for (i = 0; i < start; i++)
+			buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK);
+		for ( ; i < start + len; i++)
+			buf[i] = PATTERN_DST | PATTERN_OVERWRITE
+				| (~i & PATTERN_COUNT_MASK);
+		for ( ; i < test_buf_size; i++)
+			buf[i] = PATTERN_DST | (~i & PATTERN_COUNT_MASK);
+	}
 }
 
 static void dmatest_mismatch(u8 actual, u8 pattern, unsigned int index,
@@ -150,23 +163,30 @@ static void dmatest_mismatch(u8 actual, u8 pattern, unsigned int index,
 				thread_name, index, expected, actual);
 }
 
-static unsigned int dmatest_verify(u8 *buf, unsigned int start,
+static unsigned int dmatest_verify(u8 **bufs, unsigned int start,
 		unsigned int end, unsigned int counter, u8 pattern,
 		bool is_srcbuf)
 {
 	unsigned int i;
 	unsigned int error_count = 0;
 	u8 actual;
-
-	for (i = start; i < end; i++) {
-		actual = buf[i];
-		if (actual != (pattern | (~counter & PATTERN_COUNT_MASK))) {
-			if (error_count < 32)
-				dmatest_mismatch(actual, pattern, i, counter,
-						is_srcbuf);
-			error_count++;
+	u8 expected;
+	u8 *buf;
+	unsigned int counter_orig = counter;
+
+	for (; (buf = *bufs); bufs++) {
+		counter = counter_orig;
+		for (i = start; i < end; i++) {
+			actual = buf[i];
+			expected = pattern | (~counter & PATTERN_COUNT_MASK);
+			if (actual != expected) {
+				if (error_count < 32)
+					dmatest_mismatch(actual, pattern, i,
+							 counter, is_srcbuf);
+				error_count++;
+			}
+			counter++;
 		}
-		counter++;
 	}
 
 	if (error_count > 32)
@@ -176,12 +196,17 @@ static unsigned int dmatest_verify(u8 *buf, unsigned int start,
 	return error_count;
 }
 
+static void dmatest_callback(void *completion)
+{
+	complete(completion);
+}
+
 /*
  * This function repeatedly tests DMA transfers of various lengths and
- * offsets until it is told to exit by kthread_stop(). There may be
- * multiple threads running this function in parallel for a single
- * channel, and there may be multiple channels being tested in
- * parallel.
+ * offsets for a given operation type until it is told to exit by
+ * kthread_stop(). There may be multiple threads running this function
+ * in parallel for a single channel, and there may be multiple channels
+ * being tested in parallel.
  *
  * Before each test, the source and destination buffer is initialized
  * with a known pattern. This pattern is different depending on
@@ -201,25 +226,57 @@ static int dmatest_func(void *data)
 	unsigned int		total_tests = 0;
 	dma_cookie_t		cookie;
 	enum dma_status		status;
+	enum dma_ctrl_flags 	flags;
 	int			ret;
+	int			src_cnt;
+	int			dst_cnt;
+	int			i;
 
 	thread_name = current->comm;
 
 	ret = -ENOMEM;
-	thread->srcbuf = kmalloc(test_buf_size, GFP_KERNEL);
-	if (!thread->srcbuf)
-		goto err_srcbuf;
-	thread->dstbuf = kmalloc(test_buf_size, GFP_KERNEL);
-	if (!thread->dstbuf)
-		goto err_dstbuf;
 
 	smp_rmb();
 	chan = thread->chan;
+	if (thread->type == DMA_MEMCPY)
+		src_cnt = dst_cnt = 1;
+	else if (thread->type == DMA_XOR) {
+		src_cnt = xor_sources | 1; /* force odd to ensure dst = src */
+		dst_cnt = 1;
+	} else
+		goto err_srcs;
+
+	thread->srcs = kcalloc(src_cnt+1, sizeof(u8 *), GFP_KERNEL);
+	if (!thread->srcs)
+		goto err_srcs;
+	for (i = 0; i < src_cnt; i++) {
+		thread->srcs[i] = kmalloc(test_buf_size, GFP_KERNEL);
+		if (!thread->srcs[i])
+			goto err_srcbuf;
+	}
+	thread->srcs[i] = NULL;
+
+	thread->dsts = kcalloc(dst_cnt+1, sizeof(u8 *), GFP_KERNEL);
+	if (!thread->dsts)
+		goto err_dsts;
+	for (i = 0; i < dst_cnt; i++) {
+		thread->dsts[i] = kmalloc(test_buf_size, GFP_KERNEL);
+		if (!thread->dsts[i])
+			goto err_dstbuf;
+	}
+	thread->dsts[i] = NULL;
+
+	set_user_nice(current, 10);
+
+	flags = DMA_CTRL_ACK | DMA_COMPL_SKIP_DEST_UNMAP | DMA_PREP_INTERRUPT;
 
 	while (!kthread_should_stop()) {
 		struct dma_device *dev = chan->device;
-		struct dma_async_tx_descriptor *tx;
-		dma_addr_t dma_src, dma_dest;
+		struct dma_async_tx_descriptor *tx = NULL;
+		dma_addr_t dma_srcs[src_cnt];
+		dma_addr_t dma_dsts[dst_cnt];
+		struct completion cmp;
+		unsigned long tmo = msecs_to_jiffies(3000);
 
 		total_tests++;
 
@@ -227,22 +284,41 @@ static int dmatest_func(void *data)
 		src_off = dmatest_random() % (test_buf_size - len + 1);
 		dst_off = dmatest_random() % (test_buf_size - len + 1);
 
-		dmatest_init_srcbuf(thread->srcbuf, src_off, len);
-		dmatest_init_dstbuf(thread->dstbuf, dst_off, len);
+		dmatest_init_srcs(thread->srcs, src_off, len);
+		dmatest_init_dsts(thread->dsts, dst_off, len);
 
-		dma_src = dma_map_single(dev->dev, thread->srcbuf + src_off,
-				len, DMA_TO_DEVICE);
+		for (i = 0; i < src_cnt; i++) {
+			u8 *buf = thread->srcs[i] + src_off;
+
+			dma_srcs[i] = dma_map_single(dev->dev, buf, len,
+						     DMA_TO_DEVICE);
+		}
 		/* map with DMA_BIDIRECTIONAL to force writeback/invalidate */
-		dma_dest = dma_map_single(dev->dev, thread->dstbuf,
-				test_buf_size, DMA_BIDIRECTIONAL);
+		for (i = 0; i < dst_cnt; i++) {
+			dma_dsts[i] = dma_map_single(dev->dev, thread->dsts[i],
+						     test_buf_size,
+						     DMA_BIDIRECTIONAL);
+		}
+
+		if (thread->type == DMA_MEMCPY)
+			tx = dev->device_prep_dma_memcpy(chan,
+							 dma_dsts[0] + dst_off,
+							 dma_srcs[0], len,
+							 flags);
+		else if (thread->type == DMA_XOR)
+			tx = dev->device_prep_dma_xor(chan,
+						      dma_dsts[0] + dst_off,
+						      dma_srcs, xor_sources,
+						      len, flags);
 
-		tx = dev->device_prep_dma_memcpy(chan, dma_dest + dst_off,
-				dma_src, len,
-				DMA_CTRL_ACK | DMA_COMPL_SKIP_DEST_UNMAP);
 		if (!tx) {
-			dma_unmap_single(dev->dev, dma_src, len, DMA_TO_DEVICE);
-			dma_unmap_single(dev->dev, dma_dest,
-					test_buf_size, DMA_BIDIRECTIONAL);
+			for (i = 0; i < src_cnt; i++)
+				dma_unmap_single(dev->dev, dma_srcs[i], len,
+						 DMA_TO_DEVICE);
+			for (i = 0; i < dst_cnt; i++)
+				dma_unmap_single(dev->dev, dma_dsts[i],
+						 test_buf_size,
+						 DMA_BIDIRECTIONAL);
 			pr_warning("%s: #%u: prep error with src_off=0x%x "
 					"dst_off=0x%x len=0x%x\n",
 					thread_name, total_tests - 1,
@@ -251,7 +327,10 @@ static int dmatest_func(void *data)
 			failed_tests++;
 			continue;
 		}
-		tx->callback = NULL;
+
+		init_completion(&cmp);
+		tx->callback = dmatest_callback;
+		tx->callback_param = &cmp;
 		cookie = tx->tx_submit(tx);
 
 		if (dma_submit_error(cookie)) {
@@ -263,44 +342,50 @@ static int dmatest_func(void *data)
 			failed_tests++;
 			continue;
 		}
-		dma_async_memcpy_issue_pending(chan);
+		dma_async_issue_pending(chan);
 
-		do {
-			msleep(1);
-			status = dma_async_memcpy_complete(
-					chan, cookie, NULL, NULL);
-		} while (status == DMA_IN_PROGRESS);
+		tmo = wait_for_completion_timeout(&cmp, tmo);
+		status = dma_async_is_tx_complete(chan, cookie, NULL, NULL);
 
-		if (status == DMA_ERROR) {
-			pr_warning("%s: #%u: error during copy\n",
-					thread_name, total_tests - 1);
+		if (tmo == 0) {
+			pr_warning("%s: #%u: test timed out\n",
+				   thread_name, total_tests - 1);
+			failed_tests++;
+			continue;
+		} else if (status != DMA_SUCCESS) {
+			pr_warning("%s: #%u: got completion callback,"
+				   " but status is \'%s\'\n",
+				   thread_name, total_tests - 1,
+				   status == DMA_ERROR ? "error" : "in progress");
 			failed_tests++;
 			continue;
 		}
+
 		/* Unmap by myself (see DMA_COMPL_SKIP_DEST_UNMAP above) */
-		dma_unmap_single(dev->dev, dma_dest,
-				test_buf_size, DMA_BIDIRECTIONAL);
+		for (i = 0; i < dst_cnt; i++)
+			dma_unmap_single(dev->dev, dma_dsts[i], test_buf_size,
+					 DMA_BIDIRECTIONAL);
 
 		error_count = 0;
 
 		pr_debug("%s: verifying source buffer...\n", thread_name);
-		error_count += dmatest_verify(thread->srcbuf, 0, src_off,
+		error_count += dmatest_verify(thread->srcs, 0, src_off,
 				0, PATTERN_SRC, true);
-		error_count += dmatest_verify(thread->srcbuf, src_off,
+		error_count += dmatest_verify(thread->srcs, src_off,
 				src_off + len, src_off,
 				PATTERN_SRC | PATTERN_COPY, true);
-		error_count += dmatest_verify(thread->srcbuf, src_off + len,
+		error_count += dmatest_verify(thread->srcs, src_off + len,
 				test_buf_size, src_off + len,
 				PATTERN_SRC, true);
 
 		pr_debug("%s: verifying dest buffer...\n",
 				thread->task->comm);
-		error_count += dmatest_verify(thread->dstbuf, 0, dst_off,
+		error_count += dmatest_verify(thread->dsts, 0, dst_off,
 				0, PATTERN_DST, false);
-		error_count += dmatest_verify(thread->dstbuf, dst_off,
+		error_count += dmatest_verify(thread->dsts, dst_off,
 				dst_off + len, src_off,
 				PATTERN_SRC | PATTERN_COPY, false);
-		error_count += dmatest_verify(thread->dstbuf, dst_off + len,
+		error_count += dmatest_verify(thread->dsts, dst_off + len,
 				test_buf_size, dst_off + len,
 				PATTERN_DST, false);
 
@@ -319,10 +404,16 @@ static int dmatest_func(void *data)
 	}
 
 	ret = 0;
-	kfree(thread->dstbuf);
+	for (i = 0; thread->dsts[i]; i++)
+		kfree(thread->dsts[i]);
 err_dstbuf:
-	kfree(thread->srcbuf);
+	kfree(thread->dsts);
+err_dsts:
+	for (i = 0; thread->srcs[i]; i++)
+		kfree(thread->srcs[i]);
 err_srcbuf:
+	kfree(thread->srcs);
+err_srcs:
 	pr_notice("%s: terminating after %u tests, %u failures (status %d)\n",
 			thread_name, total_tests, failed_tests, ret);
 	return ret;
@@ -344,35 +435,36 @@ static void dmatest_cleanup_channel(struct dmatest_chan *dtc)
 	kfree(dtc);
 }
 
-static int dmatest_add_channel(struct dma_chan *chan)
+static int dmatest_add_threads(struct dmatest_chan *dtc, enum dma_transaction_type type)
 {
-	struct dmatest_chan	*dtc;
-	struct dmatest_thread	*thread;
-	unsigned int		i;
-
-	dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL);
-	if (!dtc) {
-		pr_warning("dmatest: No memory for %s\n", dma_chan_name(chan));
-		return -ENOMEM;
-	}
+	struct dmatest_thread *thread;
+	struct dma_chan *chan = dtc->chan;
+	char *op;
+	unsigned int i;
 
-	dtc->chan = chan;
-	INIT_LIST_HEAD(&dtc->threads);
+	if (type == DMA_MEMCPY)
+		op = "copy";
+	else if (type == DMA_XOR)
+		op = "xor";
+	else
+		return -EINVAL;
 
 	for (i = 0; i < threads_per_chan; i++) {
 		thread = kzalloc(sizeof(struct dmatest_thread), GFP_KERNEL);
 		if (!thread) {
-			pr_warning("dmatest: No memory for %s-test%u\n",
-				   dma_chan_name(chan), i);
+			pr_warning("dmatest: No memory for %s-%s%u\n",
+				   dma_chan_name(chan), op, i);
+
 			break;
 		}
 		thread->chan = dtc->chan;
+		thread->type = type;
 		smp_wmb();
-		thread->task = kthread_run(dmatest_func, thread, "%s-test%u",
-				dma_chan_name(chan), i);
+		thread->task = kthread_run(dmatest_func, thread, "%s-%s%u",
+				dma_chan_name(chan), op, i);
 		if (IS_ERR(thread->task)) {
-			pr_warning("dmatest: Failed to run thread %s-test%u\n",
-					dma_chan_name(chan), i);
+			pr_warning("dmatest: Failed to run thread %s-%s%u\n",
+					dma_chan_name(chan), op, i);
 			kfree(thread);
 			break;
 		}
@@ -382,7 +474,36 @@ static int dmatest_add_channel(struct dma_chan *chan)
 		list_add_tail(&thread->node, &dtc->threads);
 	}
 
-	pr_info("dmatest: Started %u threads using %s\n", i, dma_chan_name(chan));
+	return i;
+}
+
+static int dmatest_add_channel(struct dma_chan *chan)
+{
+	struct dmatest_chan	*dtc;
+	struct dma_device	*dma_dev = chan->device;
+	unsigned int		thread_count = 0;
+	unsigned int		cnt;
+
+	dtc = kmalloc(sizeof(struct dmatest_chan), GFP_KERNEL);
+	if (!dtc) {
+		pr_warning("dmatest: No memory for %s\n", dma_chan_name(chan));
+		return -ENOMEM;
+	}
+
+	dtc->chan = chan;
+	INIT_LIST_HEAD(&dtc->threads);
+
+	if (dma_has_cap(DMA_MEMCPY, dma_dev->cap_mask)) {
+		cnt = dmatest_add_threads(dtc, DMA_MEMCPY);
+		thread_count += cnt > 0 ?: 0;
+	}
+	if (dma_has_cap(DMA_XOR, dma_dev->cap_mask)) {
+		cnt = dmatest_add_threads(dtc, DMA_XOR);
+		thread_count += cnt > 0 ?: 0;
+	}
+
+	pr_info("dmatest: Started %u threads using %s\n",
+		thread_count, dma_chan_name(chan));
 
 	list_add_tail(&dtc->node, &dmatest_channels);
 	nr_channels++;
diff --git a/drivers/dma/dw_dmac.c b/drivers/dma/dw_dmac.c
index 20ad3d26bec2..98c9a847bf51 100644
--- a/drivers/dma/dw_dmac.c
+++ b/drivers/dma/dw_dmac.c
@@ -363,6 +363,82 @@ static void dwc_handle_error(struct dw_dma *dw, struct dw_dma_chan *dwc)
 	dwc_descriptor_complete(dwc, bad_desc);
 }
 
+/* --------------------- Cyclic DMA API extensions -------------------- */
+
+inline dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	return channel_readl(dwc, SAR);
+}
+EXPORT_SYMBOL(dw_dma_get_src_addr);
+
+inline dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan)
+{
+	struct dw_dma_chan *dwc = to_dw_dma_chan(chan);
+	return channel_readl(dwc, DAR);
+}
+EXPORT_SYMBOL(dw_dma_get_dst_addr);
+
+/* called with dwc->lock held and all DMAC interrupts disabled */
+static void dwc_handle_cyclic(struct dw_dma *dw, struct dw_dma_chan *dwc,
+		u32 status_block, u32 status_err, u32 status_xfer)
+{
+	if (status_block & dwc->mask) {
+		void (*callback)(void *param);
+		void *callback_param;
+
+		dev_vdbg(chan2dev(&dwc->chan), "new cyclic period llp 0x%08x\n",
+				channel_readl(dwc, LLP));
+		dma_writel(dw, CLEAR.BLOCK, dwc->mask);
+
+		callback = dwc->cdesc->period_callback;
+		callback_param = dwc->cdesc->period_callback_param;
+		if (callback) {
+			spin_unlock(&dwc->lock);
+			callback(callback_param);
+			spin_lock(&dwc->lock);
+		}
+	}
+
+	/*
+	 * Error and transfer complete are highly unlikely, and will most
+	 * likely be due to a configuration error by the user.
+	 */
+	if (unlikely(status_err & dwc->mask) ||
+			unlikely(status_xfer & dwc->mask)) {
+		int i;
+
+		dev_err(chan2dev(&dwc->chan), "cyclic DMA unexpected %s "
+				"interrupt, stopping DMA transfer\n",
+				status_xfer ? "xfer" : "error");
+		dev_err(chan2dev(&dwc->chan),
+			"  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
+			channel_readl(dwc, SAR),
+			channel_readl(dwc, DAR),
+			channel_readl(dwc, LLP),
+			channel_readl(dwc, CTL_HI),
+			channel_readl(dwc, CTL_LO));
+
+		channel_clear_bit(dw, CH_EN, dwc->mask);
+		while (dma_readl(dw, CH_EN) & dwc->mask)
+			cpu_relax();
+
+		/* make sure DMA does not restart by loading a new list */
+		channel_writel(dwc, LLP, 0);
+		channel_writel(dwc, CTL_LO, 0);
+		channel_writel(dwc, CTL_HI, 0);
+
+		dma_writel(dw, CLEAR.BLOCK, dwc->mask);
+		dma_writel(dw, CLEAR.ERROR, dwc->mask);
+		dma_writel(dw, CLEAR.XFER, dwc->mask);
+
+		for (i = 0; i < dwc->cdesc->periods; i++)
+			dwc_dump_lli(dwc, &dwc->cdesc->desc[i]->lli);
+	}
+}
+
+/* ------------------------------------------------------------------------- */
+
 static void dw_dma_tasklet(unsigned long data)
 {
 	struct dw_dma *dw = (struct dw_dma *)data;
@@ -382,7 +458,10 @@ static void dw_dma_tasklet(unsigned long data)
 	for (i = 0; i < dw->dma.chancnt; i++) {
 		dwc = &dw->chan[i];
 		spin_lock(&dwc->lock);
-		if (status_err & (1 << i))
+		if (test_bit(DW_DMA_IS_CYCLIC, &dwc->flags))
+			dwc_handle_cyclic(dw, dwc, status_block, status_err,
+					status_xfer);
+		else if (status_err & (1 << i))
 			dwc_handle_error(dw, dwc);
 		else if ((status_block | status_xfer) & (1 << i))
 			dwc_scan_descriptors(dw, dwc);
@@ -826,7 +905,6 @@ static int dwc_alloc_chan_resources(struct dma_chan *chan)
 		dma_async_tx_descriptor_init(&desc->txd, chan);
 		desc->txd.tx_submit = dwc_tx_submit;
 		desc->txd.flags = DMA_CTRL_ACK;
-		INIT_LIST_HEAD(&desc->txd.tx_list);
 		desc->txd.phys = dma_map_single(chan2parent(chan), &desc->lli,
 				sizeof(desc->lli), DMA_TO_DEVICE);
 		dwc_desc_put(dwc, desc);
@@ -884,6 +962,257 @@ static void dwc_free_chan_resources(struct dma_chan *chan)
 	dev_vdbg(chan2dev(chan), "free_chan_resources done\n");
 }
 
+/* --------------------- Cyclic DMA API extensions -------------------- */
+
+/**
+ * dw_dma_cyclic_start - start the cyclic DMA transfer
+ * @chan: the DMA channel to start
+ *
+ * Must be called with soft interrupts disabled. Returns zero on success or
+ * -errno on failure.
+ */
+int dw_dma_cyclic_start(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
+
+	if (!test_bit(DW_DMA_IS_CYCLIC, &dwc->flags)) {
+		dev_err(chan2dev(&dwc->chan), "missing prep for cyclic DMA\n");
+		return -ENODEV;
+	}
+
+	spin_lock(&dwc->lock);
+
+	/* assert channel is idle */
+	if (dma_readl(dw, CH_EN) & dwc->mask) {
+		dev_err(chan2dev(&dwc->chan),
+			"BUG: Attempted to start non-idle channel\n");
+		dev_err(chan2dev(&dwc->chan),
+			"  SAR: 0x%x DAR: 0x%x LLP: 0x%x CTL: 0x%x:%08x\n",
+			channel_readl(dwc, SAR),
+			channel_readl(dwc, DAR),
+			channel_readl(dwc, LLP),
+			channel_readl(dwc, CTL_HI),
+			channel_readl(dwc, CTL_LO));
+		spin_unlock(&dwc->lock);
+		return -EBUSY;
+	}
+
+	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
+	dma_writel(dw, CLEAR.ERROR, dwc->mask);
+	dma_writel(dw, CLEAR.XFER, dwc->mask);
+
+	/* setup DMAC channel registers */
+	channel_writel(dwc, LLP, dwc->cdesc->desc[0]->txd.phys);
+	channel_writel(dwc, CTL_LO, DWC_CTLL_LLP_D_EN | DWC_CTLL_LLP_S_EN);
+	channel_writel(dwc, CTL_HI, 0);
+
+	channel_set_bit(dw, CH_EN, dwc->mask);
+
+	spin_unlock(&dwc->lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(dw_dma_cyclic_start);
+
+/**
+ * dw_dma_cyclic_stop - stop the cyclic DMA transfer
+ * @chan: the DMA channel to stop
+ *
+ * Must be called with soft interrupts disabled.
+ */
+void dw_dma_cyclic_stop(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
+
+	spin_lock(&dwc->lock);
+
+	channel_clear_bit(dw, CH_EN, dwc->mask);
+	while (dma_readl(dw, CH_EN) & dwc->mask)
+		cpu_relax();
+
+	spin_unlock(&dwc->lock);
+}
+EXPORT_SYMBOL(dw_dma_cyclic_stop);
+
+/**
+ * dw_dma_cyclic_prep - prepare the cyclic DMA transfer
+ * @chan: the DMA channel to prepare
+ * @buf_addr: physical DMA address where the buffer starts
+ * @buf_len: total number of bytes for the entire buffer
+ * @period_len: number of bytes for each period
+ * @direction: transfer direction, to or from device
+ *
+ * Must be called before trying to start the transfer. Returns a valid struct
+ * dw_cyclic_desc if successful or an ERR_PTR(-errno) if not successful.
+ */
+struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
+		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
+		enum dma_data_direction direction)
+{
+	struct dw_dma_chan		*dwc = to_dw_dma_chan(chan);
+	struct dw_cyclic_desc		*cdesc;
+	struct dw_cyclic_desc		*retval = NULL;
+	struct dw_desc			*desc;
+	struct dw_desc			*last = NULL;
+	struct dw_dma_slave		*dws = chan->private;
+	unsigned long			was_cyclic;
+	unsigned int			reg_width;
+	unsigned int			periods;
+	unsigned int			i;
+
+	spin_lock_bh(&dwc->lock);
+	if (!list_empty(&dwc->queue) || !list_empty(&dwc->active_list)) {
+		spin_unlock_bh(&dwc->lock);
+		dev_dbg(chan2dev(&dwc->chan),
+				"queue and/or active list are not empty\n");
+		return ERR_PTR(-EBUSY);
+	}
+
+	was_cyclic = test_and_set_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
+	spin_unlock_bh(&dwc->lock);
+	if (was_cyclic) {
+		dev_dbg(chan2dev(&dwc->chan),
+				"channel already prepared for cyclic DMA\n");
+		return ERR_PTR(-EBUSY);
+	}
+
+	retval = ERR_PTR(-EINVAL);
+	reg_width = dws->reg_width;
+	periods = buf_len / period_len;
+
+	/* Check for too big/unaligned periods and unaligned DMA buffer. */
+	if (period_len > (DWC_MAX_COUNT << reg_width))
+		goto out_err;
+	if (unlikely(period_len & ((1 << reg_width) - 1)))
+		goto out_err;
+	if (unlikely(buf_addr & ((1 << reg_width) - 1)))
+		goto out_err;
+	if (unlikely(!(direction & (DMA_TO_DEVICE | DMA_FROM_DEVICE))))
+		goto out_err;
+
+	retval = ERR_PTR(-ENOMEM);
+
+	if (periods > NR_DESCS_PER_CHANNEL)
+		goto out_err;
+
+	cdesc = kzalloc(sizeof(struct dw_cyclic_desc), GFP_KERNEL);
+	if (!cdesc)
+		goto out_err;
+
+	cdesc->desc = kzalloc(sizeof(struct dw_desc *) * periods, GFP_KERNEL);
+	if (!cdesc->desc)
+		goto out_err_alloc;
+
+	for (i = 0; i < periods; i++) {
+		desc = dwc_desc_get(dwc);
+		if (!desc)
+			goto out_err_desc_get;
+
+		switch (direction) {
+		case DMA_TO_DEVICE:
+			desc->lli.dar = dws->tx_reg;
+			desc->lli.sar = buf_addr + (period_len * i);
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO
+					| DWC_CTLL_DST_WIDTH(reg_width)
+					| DWC_CTLL_SRC_WIDTH(reg_width)
+					| DWC_CTLL_DST_FIX
+					| DWC_CTLL_SRC_INC
+					| DWC_CTLL_FC_M2P
+					| DWC_CTLL_INT_EN);
+			break;
+		case DMA_FROM_DEVICE:
+			desc->lli.dar = buf_addr + (period_len * i);
+			desc->lli.sar = dws->rx_reg;
+			desc->lli.ctllo = (DWC_DEFAULT_CTLLO
+					| DWC_CTLL_SRC_WIDTH(reg_width)
+					| DWC_CTLL_DST_WIDTH(reg_width)
+					| DWC_CTLL_DST_INC
+					| DWC_CTLL_SRC_FIX
+					| DWC_CTLL_FC_P2M
+					| DWC_CTLL_INT_EN);
+			break;
+		default:
+			break;
+		}
+
+		desc->lli.ctlhi = (period_len >> reg_width);
+		cdesc->desc[i] = desc;
+
+		if (last) {
+			last->lli.llp = desc->txd.phys;
+			dma_sync_single_for_device(chan2parent(chan),
+					last->txd.phys, sizeof(last->lli),
+					DMA_TO_DEVICE);
+		}
+
+		last = desc;
+	}
+
+	/* lets make a cyclic list */
+	last->lli.llp = cdesc->desc[0]->txd.phys;
+	dma_sync_single_for_device(chan2parent(chan), last->txd.phys,
+			sizeof(last->lli), DMA_TO_DEVICE);
+
+	dev_dbg(chan2dev(&dwc->chan), "cyclic prepared buf 0x%08x len %zu "
+			"period %zu periods %d\n", buf_addr, buf_len,
+			period_len, periods);
+
+	cdesc->periods = periods;
+	dwc->cdesc = cdesc;
+
+	return cdesc;
+
+out_err_desc_get:
+	while (i--)
+		dwc_desc_put(dwc, cdesc->desc[i]);
+out_err_alloc:
+	kfree(cdesc);
+out_err:
+	clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
+	return (struct dw_cyclic_desc *)retval;
+}
+EXPORT_SYMBOL(dw_dma_cyclic_prep);
+
+/**
+ * dw_dma_cyclic_free - free a prepared cyclic DMA transfer
+ * @chan: the DMA channel to free
+ */
+void dw_dma_cyclic_free(struct dma_chan *chan)
+{
+	struct dw_dma_chan	*dwc = to_dw_dma_chan(chan);
+	struct dw_dma		*dw = to_dw_dma(dwc->chan.device);
+	struct dw_cyclic_desc	*cdesc = dwc->cdesc;
+	int			i;
+
+	dev_dbg(chan2dev(&dwc->chan), "cyclic free\n");
+
+	if (!cdesc)
+		return;
+
+	spin_lock_bh(&dwc->lock);
+
+	channel_clear_bit(dw, CH_EN, dwc->mask);
+	while (dma_readl(dw, CH_EN) & dwc->mask)
+		cpu_relax();
+
+	dma_writel(dw, CLEAR.BLOCK, dwc->mask);
+	dma_writel(dw, CLEAR.ERROR, dwc->mask);
+	dma_writel(dw, CLEAR.XFER, dwc->mask);
+
+	spin_unlock_bh(&dwc->lock);
+
+	for (i = 0; i < cdesc->periods; i++)
+		dwc_desc_put(dwc, cdesc->desc[i]);
+
+	kfree(cdesc->desc);
+	kfree(cdesc);
+
+	clear_bit(DW_DMA_IS_CYCLIC, &dwc->flags);
+}
+EXPORT_SYMBOL(dw_dma_cyclic_free);
+
 /*----------------------------------------------------------------------*/
 
 static void dw_dma_off(struct dw_dma *dw)
diff --git a/drivers/dma/dw_dmac_regs.h b/drivers/dma/dw_dmac_regs.h
index b252b202c5cf..13a580767031 100644
--- a/drivers/dma/dw_dmac_regs.h
+++ b/drivers/dma/dw_dmac_regs.h
@@ -126,6 +126,10 @@ struct dw_dma_regs {
 
 #define DW_REGLEN		0x400
 
+enum dw_dmac_flags {
+	DW_DMA_IS_CYCLIC = 0,
+};
+
 struct dw_dma_chan {
 	struct dma_chan		chan;
 	void __iomem		*ch_regs;
@@ -134,10 +138,12 @@ struct dw_dma_chan {
 	spinlock_t		lock;
 
 	/* these other elements are all protected by lock */
+	unsigned long		flags;
 	dma_cookie_t		completed;
 	struct list_head	active_list;
 	struct list_head	queue;
 	struct list_head	free_list;
+	struct dw_cyclic_desc	*cdesc;
 
 	unsigned int		descs_allocated;
 };
@@ -158,7 +164,6 @@ static inline struct dw_dma_chan *to_dw_dma_chan(struct dma_chan *chan)
 	return container_of(chan, struct dw_dma_chan, chan);
 }
 
-
 struct dw_dma {
 	struct dma_device	dma;
 	void __iomem		*regs;
diff --git a/drivers/dma/fsldma.c b/drivers/dma/fsldma.c
index 86d6da47f558..da8a8ed9e411 100644
--- a/drivers/dma/fsldma.c
+++ b/drivers/dma/fsldma.c
@@ -354,7 +354,6 @@ static struct fsl_desc_sw *fsl_dma_alloc_descriptor(
 		dma_async_tx_descriptor_init(&desc_sw->async_tx,
 						&fsl_chan->common);
 		desc_sw->async_tx.tx_submit = fsl_dma_tx_submit;
-		INIT_LIST_HEAD(&desc_sw->async_tx.tx_list);
 		desc_sw->async_tx.phys = pdesc;
 	}
 
diff --git a/drivers/dma/ioat_dma.c b/drivers/dma/ioat_dma.c
index 5905cd36bcd2..e4fc33c1c32f 100644
--- a/drivers/dma/ioat_dma.c
+++ b/drivers/dma/ioat_dma.c
@@ -693,7 +693,6 @@ static struct ioat_desc_sw *ioat_dma_alloc_descriptor(
 		desc_sw->async_tx.tx_submit = ioat2_tx_submit;
 		break;
 	}
-	INIT_LIST_HEAD(&desc_sw->async_tx.tx_list);
 
 	desc_sw->hw = desc;
 	desc_sw->async_tx.phys = phys;
diff --git a/drivers/dma/iop-adma.c b/drivers/dma/iop-adma.c
index 16adbe61cfb2..2f052265122f 100644
--- a/drivers/dma/iop-adma.c
+++ b/drivers/dma/iop-adma.c
@@ -498,7 +498,6 @@ static int iop_adma_alloc_chan_resources(struct dma_chan *chan)
 		slot->async_tx.tx_submit = iop_adma_tx_submit;
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
-		INIT_LIST_HEAD(&slot->async_tx.tx_list);
 		hw_desc = (char *) iop_chan->device->dma_desc_pool;
 		slot->async_tx.phys =
 			(dma_addr_t) &hw_desc[idx * IOP_ADMA_SLOT_SIZE];
diff --git a/drivers/dma/ipu/ipu_idmac.c b/drivers/dma/ipu/ipu_idmac.c
index da781d107895..e202a6ce5573 100644
--- a/drivers/dma/ipu/ipu_idmac.c
+++ b/drivers/dma/ipu/ipu_idmac.c
@@ -28,6 +28,9 @@
 #define FS_VF_IN_VALID	0x00000002
 #define FS_ENC_IN_VALID	0x00000001
 
+static int ipu_disable_channel(struct idmac *idmac, struct idmac_channel *ichan,
+			       bool wait_for_stop);
+
 /*
  * There can be only one, we could allocate it dynamically, but then we'd have
  * to add an extra parameter to some functions, and use something as ugly as
@@ -107,7 +110,7 @@ static uint32_t bytes_per_pixel(enum pixel_fmt fmt)
 	}
 }
 
-/* Enable / disable direct write to memory by the Camera Sensor Interface */
+/* Enable direct write to memory by the Camera Sensor Interface */
 static void ipu_ic_enable_task(struct ipu *ipu, enum ipu_channel channel)
 {
 	uint32_t ic_conf, mask;
@@ -126,6 +129,7 @@ static void ipu_ic_enable_task(struct ipu *ipu, enum ipu_channel channel)
 	idmac_write_icreg(ipu, ic_conf, IC_CONF);
 }
 
+/* Called under spin_lock_irqsave(&ipu_data.lock) */
 static void ipu_ic_disable_task(struct ipu *ipu, enum ipu_channel channel)
 {
 	uint32_t ic_conf, mask;
@@ -422,7 +426,7 @@ static void ipu_ch_param_set_size(union chan_param_mem *params,
 		break;
 	default:
 		dev_err(ipu_data.dev,
-			"mxc ipu: unimplemented pixel format %d\n", pixel_fmt);
+			"mx3 ipu: unimplemented pixel format %d\n", pixel_fmt);
 		break;
 	}
 
@@ -433,20 +437,20 @@ static void ipu_ch_param_set_burst_size(union chan_param_mem *params,
 					uint16_t burst_pixels)
 {
 	params->pp.npb = burst_pixels - 1;
-};
+}
 
 static void ipu_ch_param_set_buffer(union chan_param_mem *params,
 				    dma_addr_t buf0, dma_addr_t buf1)
 {
 	params->pp.eba0 = buf0;
 	params->pp.eba1 = buf1;
-};
+}
 
 static void ipu_ch_param_set_rotation(union chan_param_mem *params,
 				      enum ipu_rotate_mode rotate)
 {
 	params->pp.bam = rotate;
-};
+}
 
 static void ipu_write_param_mem(uint32_t addr, uint32_t *data,
 				uint32_t num_words)
@@ -571,7 +575,7 @@ static uint32_t dma_param_addr(uint32_t dma_ch)
 {
 	/* Channel Parameter Memory */
 	return 0x10000 | (dma_ch << 4);
-};
+}
 
 static void ipu_channel_set_priority(struct ipu *ipu, enum ipu_channel channel,
 				     bool prio)
@@ -611,7 +615,8 @@ static uint32_t ipu_channel_conf_mask(enum ipu_channel channel)
 
 /**
  * ipu_enable_channel() - enable an IPU channel.
- * @channel:	channel ID.
+ * @idmac:	IPU DMAC context.
+ * @ichan:	IDMAC channel.
  * @return:	0 on success or negative error code on failure.
  */
 static int ipu_enable_channel(struct idmac *idmac, struct idmac_channel *ichan)
@@ -649,7 +654,7 @@ static int ipu_enable_channel(struct idmac *idmac, struct idmac_channel *ichan)
 
 /**
  * ipu_init_channel_buffer() - initialize a buffer for logical IPU channel.
- * @channel:	channel ID.
+ * @ichan:	IDMAC channel.
  * @pixel_fmt:	pixel format of buffer. Pixel format is a FOURCC ASCII code.
  * @width:	width of buffer in pixels.
  * @height:	height of buffer in pixels.
@@ -687,7 +692,7 @@ static int ipu_init_channel_buffer(struct idmac_channel *ichan,
 	}
 
 	/* IC channel's stride must be a multiple of 8 pixels */
-	if ((channel <= 13) && (stride % 8)) {
+	if ((channel <= IDMAC_IC_13) && (stride % 8)) {
 		dev_err(ipu->dev, "Stride must be 8 pixel multiple\n");
 		return -EINVAL;
 	}
@@ -752,7 +757,7 @@ static void ipu_select_buffer(enum ipu_channel channel, int buffer_n)
 
 /**
  * ipu_update_channel_buffer() - update physical address of a channel buffer.
- * @channel:	channel ID.
+ * @ichan:	IDMAC channel.
  * @buffer_n:	buffer number to update.
  *		0 or 1 are the only valid values.
  * @phyaddr:	buffer physical address.
@@ -760,9 +765,10 @@ static void ipu_select_buffer(enum ipu_channel channel, int buffer_n)
  *              function will fail if the buffer is set to ready.
  */
 /* Called under spin_lock(_irqsave)(&ichan->lock) */
-static int ipu_update_channel_buffer(enum ipu_channel channel,
+static int ipu_update_channel_buffer(struct idmac_channel *ichan,
 				     int buffer_n, dma_addr_t phyaddr)
 {
+	enum ipu_channel channel = ichan->dma_chan.chan_id;
 	uint32_t reg;
 	unsigned long flags;
 
@@ -771,8 +777,8 @@ static int ipu_update_channel_buffer(enum ipu_channel channel,
 	if (buffer_n == 0) {
 		reg = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF0_RDY);
 		if (reg & (1UL << channel)) {
-			spin_unlock_irqrestore(&ipu_data.lock, flags);
-			return -EACCES;
+			ipu_ic_disable_task(&ipu_data, channel);
+			ichan->status = IPU_CHANNEL_READY;
 		}
 
 		/* 44.3.3.1.9 - Row Number 1 (WORD1, offset 0) */
@@ -782,8 +788,8 @@ static int ipu_update_channel_buffer(enum ipu_channel channel,
 	} else {
 		reg = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF1_RDY);
 		if (reg & (1UL << channel)) {
-			spin_unlock_irqrestore(&ipu_data.lock, flags);
-			return -EACCES;
+			ipu_ic_disable_task(&ipu_data, channel);
+			ichan->status = IPU_CHANNEL_READY;
 		}
 
 		/* Check if double-buffering is already enabled */
@@ -805,6 +811,39 @@ static int ipu_update_channel_buffer(enum ipu_channel channel,
 }
 
 /* Called under spin_lock_irqsave(&ichan->lock) */
+static int ipu_submit_buffer(struct idmac_channel *ichan,
+	struct idmac_tx_desc *desc, struct scatterlist *sg, int buf_idx)
+{
+	unsigned int chan_id = ichan->dma_chan.chan_id;
+	struct device *dev = &ichan->dma_chan.dev->device;
+	int ret;
+
+	if (async_tx_test_ack(&desc->txd))
+		return -EINTR;
+
+	/*
+	 * On first invocation this shouldn't be necessary, the call to
+	 * ipu_init_channel_buffer() above will set addresses for us, so we
+	 * could make it conditional on status >= IPU_CHANNEL_ENABLED, but
+	 * doing it again shouldn't hurt either.
+	 */
+	ret = ipu_update_channel_buffer(ichan, buf_idx,
+					sg_dma_address(sg));
+
+	if (ret < 0) {
+		dev_err(dev, "Updating sg %p on channel 0x%x buffer %d failed!\n",
+			sg, chan_id, buf_idx);
+		return ret;
+	}
+
+	ipu_select_buffer(chan_id, buf_idx);
+	dev_dbg(dev, "Updated sg %p on channel 0x%x buffer %d\n",
+		sg, chan_id, buf_idx);
+
+	return 0;
+}
+
+/* Called under spin_lock_irqsave(&ichan->lock) */
 static int ipu_submit_channel_buffers(struct idmac_channel *ichan,
 				      struct idmac_tx_desc *desc)
 {
@@ -815,20 +854,10 @@ static int ipu_submit_channel_buffers(struct idmac_channel *ichan,
 		if (!ichan->sg[i]) {
 			ichan->sg[i] = sg;
 
-			/*
-			 * On first invocation this shouldn't be necessary, the
-			 * call to ipu_init_channel_buffer() above will set
-			 * addresses for us, so we could make it conditional
-			 * on status >= IPU_CHANNEL_ENABLED, but doing it again
-			 * shouldn't hurt either.
-			 */
-			ret = ipu_update_channel_buffer(ichan->dma_chan.chan_id, i,
-							sg_dma_address(sg));
+			ret = ipu_submit_buffer(ichan, desc, sg, i);
 			if (ret < 0)
 				return ret;
 
-			ipu_select_buffer(ichan->dma_chan.chan_id, i);
-
 			sg = sg_next(sg);
 		}
 	}
@@ -842,19 +871,22 @@ static dma_cookie_t idmac_tx_submit(struct dma_async_tx_descriptor *tx)
 	struct idmac_channel *ichan = to_idmac_chan(tx->chan);
 	struct idmac *idmac = to_idmac(tx->chan->device);
 	struct ipu *ipu = to_ipu(idmac);
+	struct device *dev = &ichan->dma_chan.dev->device;
 	dma_cookie_t cookie;
 	unsigned long flags;
+	int ret;
 
 	/* Sanity check */
 	if (!list_empty(&desc->list)) {
 		/* The descriptor doesn't belong to client */
-		dev_err(&ichan->dma_chan.dev->device,
-			"Descriptor %p not prepared!\n", tx);
+		dev_err(dev, "Descriptor %p not prepared!\n", tx);
 		return -EBUSY;
 	}
 
 	mutex_lock(&ichan->chan_mutex);
 
+	async_tx_clear_ack(tx);
+
 	if (ichan->status < IPU_CHANNEL_READY) {
 		struct idmac_video_param *video = &ichan->params.video;
 		/*
@@ -878,16 +910,7 @@ static dma_cookie_t idmac_tx_submit(struct dma_async_tx_descriptor *tx)
 			goto out;
 	}
 
-	/* ipu->lock can be taken under ichan->lock, but not v.v. */
-	spin_lock_irqsave(&ichan->lock, flags);
-
-	/* submit_buffers() atomically verifies and fills empty sg slots */
-	cookie = ipu_submit_channel_buffers(ichan, desc);
-
-	spin_unlock_irqrestore(&ichan->lock, flags);
-
-	if (cookie < 0)
-		goto out;
+	dev_dbg(dev, "Submitting sg %p\n", &desc->sg[0]);
 
 	cookie = ichan->dma_chan.cookie;
 
@@ -897,24 +920,40 @@ static dma_cookie_t idmac_tx_submit(struct dma_async_tx_descriptor *tx)
 	/* from dmaengine.h: "last cookie value returned to client" */
 	ichan->dma_chan.cookie = cookie;
 	tx->cookie = cookie;
+
+	/* ipu->lock can be taken under ichan->lock, but not v.v. */
 	spin_lock_irqsave(&ichan->lock, flags);
+
 	list_add_tail(&desc->list, &ichan->queue);
+	/* submit_buffers() atomically verifies and fills empty sg slots */
+	ret = ipu_submit_channel_buffers(ichan, desc);
+
 	spin_unlock_irqrestore(&ichan->lock, flags);
 
+	if (ret < 0) {
+		cookie = ret;
+		goto dequeue;
+	}
+
 	if (ichan->status < IPU_CHANNEL_ENABLED) {
-		int ret = ipu_enable_channel(idmac, ichan);
+		ret = ipu_enable_channel(idmac, ichan);
 		if (ret < 0) {
 			cookie = ret;
-			spin_lock_irqsave(&ichan->lock, flags);
-			list_del_init(&desc->list);
-			spin_unlock_irqrestore(&ichan->lock, flags);
-			tx->cookie = cookie;
-			ichan->dma_chan.cookie = cookie;
+			goto dequeue;
 		}
 	}
 
 	dump_idmac_reg(ipu);
 
+dequeue:
+	if (cookie < 0) {
+		spin_lock_irqsave(&ichan->lock, flags);
+		list_del_init(&desc->list);
+		spin_unlock_irqrestore(&ichan->lock, flags);
+		tx->cookie = cookie;
+		ichan->dma_chan.cookie = cookie;
+	}
+
 out:
 	mutex_unlock(&ichan->chan_mutex);
 
@@ -944,8 +983,6 @@ static int idmac_desc_alloc(struct idmac_channel *ichan, int n)
 		memset(txd, 0, sizeof(*txd));
 		dma_async_tx_descriptor_init(txd, &ichan->dma_chan);
 		txd->tx_submit		= idmac_tx_submit;
-		txd->chan		= &ichan->dma_chan;
-		INIT_LIST_HEAD(&txd->tx_list);
 
 		list_add(&desc->list, &ichan->free_list);
 
@@ -1161,6 +1198,24 @@ static int ipu_disable_channel(struct idmac *idmac, struct idmac_channel *ichan,
 	return 0;
 }
 
+static struct scatterlist *idmac_sg_next(struct idmac_channel *ichan,
+	struct idmac_tx_desc **desc, struct scatterlist *sg)
+{
+	struct scatterlist *sgnew = sg ? sg_next(sg) : NULL;
+
+	if (sgnew)
+		/* next sg-element in this list */
+		return sgnew;
+
+	if ((*desc)->list.next == &ichan->queue)
+		/* No more descriptors on the queue */
+		return NULL;
+
+	/* Fetch next descriptor */
+	*desc = list_entry((*desc)->list.next, struct idmac_tx_desc, list);
+	return (*desc)->sg;
+}
+
 /*
  * We have several possibilities here:
  * current BUF		next BUF
@@ -1176,23 +1231,46 @@ static int ipu_disable_channel(struct idmac *idmac, struct idmac_channel *ichan,
 static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 {
 	struct idmac_channel *ichan = dev_id;
+	struct device *dev = &ichan->dma_chan.dev->device;
 	unsigned int chan_id = ichan->dma_chan.chan_id;
 	struct scatterlist **sg, *sgnext, *sgnew = NULL;
 	/* Next transfer descriptor */
-	struct idmac_tx_desc *desc = NULL, *descnew;
+	struct idmac_tx_desc *desc, *descnew;
 	dma_async_tx_callback callback;
 	void *callback_param;
 	bool done = false;
-	u32	ready0 = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF0_RDY),
-		ready1 = idmac_read_ipureg(&ipu_data, IPU_CHA_BUF1_RDY),
-		curbuf = idmac_read_ipureg(&ipu_data, IPU_CHA_CUR_BUF);
+	u32 ready0, ready1, curbuf, err;
+	unsigned long flags;
 
 	/* IDMAC has cleared the respective BUFx_RDY bit, we manage the buffer */
 
-	pr_debug("IDMAC irq %d\n", irq);
+	dev_dbg(dev, "IDMAC irq %d, buf %d\n", irq, ichan->active_buffer);
+
+	spin_lock_irqsave(&ipu_data.lock, flags);
+
+	ready0	= idmac_read_ipureg(&ipu_data, IPU_CHA_BUF0_RDY);
+	ready1	= idmac_read_ipureg(&ipu_data, IPU_CHA_BUF1_RDY);
+	curbuf	= idmac_read_ipureg(&ipu_data, IPU_CHA_CUR_BUF);
+	err	= idmac_read_ipureg(&ipu_data, IPU_INT_STAT_4);
+
+	if (err & (1 << chan_id)) {
+		idmac_write_ipureg(&ipu_data, 1 << chan_id, IPU_INT_STAT_4);
+		spin_unlock_irqrestore(&ipu_data.lock, flags);
+		/*
+		 * Doing this
+		 * ichan->sg[0] = ichan->sg[1] = NULL;
+		 * you can force channel re-enable on the next tx_submit(), but
+		 * this is dirty - think about descriptors with multiple
+		 * sg elements.
+		 */
+		dev_warn(dev, "NFB4EOF on channel %d, ready %x, %x, cur %x\n",
+			 chan_id, ready0, ready1, curbuf);
+		return IRQ_HANDLED;
+	}
+	spin_unlock_irqrestore(&ipu_data.lock, flags);
+
 	/* Other interrupts do not interfere with this channel */
 	spin_lock(&ichan->lock);
-
 	if (unlikely(chan_id != IDMAC_SDC_0 && chan_id != IDMAC_SDC_1 &&
 		     ((curbuf >> chan_id) & 1) == ichan->active_buffer)) {
 		int i = 100;
@@ -1207,19 +1285,23 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 
 		if (!i) {
 			spin_unlock(&ichan->lock);
-			dev_dbg(ichan->dma_chan.device->dev,
+			dev_dbg(dev,
 				"IRQ on active buffer on channel %x, active "
 				"%d, ready %x, %x, current %x!\n", chan_id,
 				ichan->active_buffer, ready0, ready1, curbuf);
 			return IRQ_NONE;
-		}
+		} else
+			dev_dbg(dev,
+				"Buffer deactivated on channel %x, active "
+				"%d, ready %x, %x, current %x, rest %d!\n", chan_id,
+				ichan->active_buffer, ready0, ready1, curbuf, i);
 	}
 
 	if (unlikely((ichan->active_buffer && (ready1 >> chan_id) & 1) ||
 		     (!ichan->active_buffer && (ready0 >> chan_id) & 1)
 		     )) {
 		spin_unlock(&ichan->lock);
-		dev_dbg(ichan->dma_chan.device->dev,
+		dev_dbg(dev,
 			"IRQ with active buffer still ready on channel %x, "
 			"active %d, ready %x, %x!\n", chan_id,
 			ichan->active_buffer, ready0, ready1);
@@ -1227,8 +1309,9 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 	}
 
 	if (unlikely(list_empty(&ichan->queue))) {
+		ichan->sg[ichan->active_buffer] = NULL;
 		spin_unlock(&ichan->lock);
-		dev_err(ichan->dma_chan.device->dev,
+		dev_err(dev,
 			"IRQ without queued buffers on channel %x, active %d, "
 			"ready %x, %x!\n", chan_id,
 			ichan->active_buffer, ready0, ready1);
@@ -1243,40 +1326,44 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 	sg = &ichan->sg[ichan->active_buffer];
 	sgnext = ichan->sg[!ichan->active_buffer];
 
+	if (!*sg) {
+		spin_unlock(&ichan->lock);
+		return IRQ_HANDLED;
+	}
+
+	desc = list_entry(ichan->queue.next, struct idmac_tx_desc, list);
+	descnew = desc;
+
+	dev_dbg(dev, "IDMAC irq %d, dma 0x%08x, next dma 0x%08x, current %d, curbuf 0x%08x\n",
+		irq, sg_dma_address(*sg), sgnext ? sg_dma_address(sgnext) : 0, ichan->active_buffer, curbuf);
+
+	/* Find the descriptor of sgnext */
+	sgnew = idmac_sg_next(ichan, &descnew, *sg);
+	if (sgnext != sgnew)
+		dev_err(dev, "Submitted buffer %p, next buffer %p\n", sgnext, sgnew);
+
 	/*
 	 * if sgnext == NULL sg must be the last element in a scatterlist and
 	 * queue must be empty
 	 */
 	if (unlikely(!sgnext)) {
-		if (unlikely(sg_next(*sg))) {
-			dev_err(ichan->dma_chan.device->dev,
-				"Broken buffer-update locking on channel %x!\n",
-				chan_id);
-			/* We'll let the user catch up */
+		if (!WARN_ON(sg_next(*sg)))
+			dev_dbg(dev, "Underrun on channel %x\n", chan_id);
+		ichan->sg[!ichan->active_buffer] = sgnew;
+
+		if (unlikely(sgnew)) {
+			ipu_submit_buffer(ichan, descnew, sgnew, !ichan->active_buffer);
 		} else {
-			/* Underrun */
+			spin_lock_irqsave(&ipu_data.lock, flags);
 			ipu_ic_disable_task(&ipu_data, chan_id);
-			dev_dbg(ichan->dma_chan.device->dev,
-				"Underrun on channel %x\n", chan_id);
+			spin_unlock_irqrestore(&ipu_data.lock, flags);
 			ichan->status = IPU_CHANNEL_READY;
 			/* Continue to check for complete descriptor */
 		}
 	}
 
-	desc = list_entry(ichan->queue.next, struct idmac_tx_desc, list);
-
-	/* First calculate and submit the next sg element */
-	if (likely(sgnext))
-		sgnew = sg_next(sgnext);
-
-	if (unlikely(!sgnew)) {
-		/* Start a new scatterlist, if any queued */
-		if (likely(desc->list.next != &ichan->queue)) {
-			descnew = list_entry(desc->list.next,
-					     struct idmac_tx_desc, list);
-			sgnew = &descnew->sg[0];
-		}
-	}
+	/* Calculate and submit the next sg element */
+	sgnew = idmac_sg_next(ichan, &descnew, sgnew);
 
 	if (unlikely(!sg_next(*sg)) || !sgnext) {
 		/*
@@ -1289,17 +1376,13 @@ static irqreturn_t idmac_interrupt(int irq, void *dev_id)
 
 	*sg = sgnew;
 
-	if (likely(sgnew)) {
-		int ret;
-
-		ret = ipu_update_channel_buffer(chan_id, ichan->active_buffer,
-						sg_dma_address(*sg));
-		if (ret < 0)
-			dev_err(ichan->dma_chan.device->dev,
-				"Failed to update buffer on channel %x buffer %d!\n",
-				chan_id, ichan->active_buffer);
-		else
-			ipu_select_buffer(chan_id, ichan->active_buffer);
+	if (likely(sgnew) &&
+	    ipu_submit_buffer(ichan, descnew, sgnew, ichan->active_buffer) < 0) {
+		callback = desc->txd.callback;
+		callback_param = desc->txd.callback_param;
+		spin_unlock(&ichan->lock);
+		callback(callback_param);
+		spin_lock(&ichan->lock);
 	}
 
 	/* Flip the active buffer - even if update above failed */
@@ -1327,13 +1410,20 @@ static void ipu_gc_tasklet(unsigned long arg)
 		struct idmac_channel *ichan = ipu->channel + i;
 		struct idmac_tx_desc *desc;
 		unsigned long flags;
-		int j;
+		struct scatterlist *sg;
+		int j, k;
 
 		for (j = 0; j < ichan->n_tx_desc; j++) {
 			desc = ichan->desc + j;
 			spin_lock_irqsave(&ichan->lock, flags);
 			if (async_tx_test_ack(&desc->txd)) {
 				list_move(&desc->list, &ichan->free_list);
+				for_each_sg(desc->sg, sg, desc->sg_len, k) {
+					if (ichan->sg[0] == sg)
+						ichan->sg[0] = NULL;
+					else if (ichan->sg[1] == sg)
+						ichan->sg[1] = NULL;
+				}
 				async_tx_clear_ack(&desc->txd);
 			}
 			spin_unlock_irqrestore(&ichan->lock, flags);
@@ -1341,13 +1431,7 @@ static void ipu_gc_tasklet(unsigned long arg)
 	}
 }
 
-/*
- * At the time .device_alloc_chan_resources() method is called, we cannot know,
- * whether the client will accept the channel. Thus we must only check, if we
- * can satisfy client's request but the only real criterion to verify, whether
- * the client has accepted our offer is the client_count. That's why we have to
- * perform the rest of our allocation tasks on the first call to this function.
- */
+/* Allocate and initialise a transfer descriptor. */
 static struct dma_async_tx_descriptor *idmac_prep_slave_sg(struct dma_chan *chan,
 		struct scatterlist *sgl, unsigned int sg_len,
 		enum dma_data_direction direction, unsigned long tx_flags)
@@ -1358,8 +1442,8 @@ static struct dma_async_tx_descriptor *idmac_prep_slave_sg(struct dma_chan *chan
 	unsigned long flags;
 
 	/* We only can handle these three channels so far */
-	if (ichan->dma_chan.chan_id != IDMAC_SDC_0 && ichan->dma_chan.chan_id != IDMAC_SDC_1 &&
-	    ichan->dma_chan.chan_id != IDMAC_IC_7)
+	if (chan->chan_id != IDMAC_SDC_0 && chan->chan_id != IDMAC_SDC_1 &&
+	    chan->chan_id != IDMAC_IC_7)
 		return NULL;
 
 	if (direction != DMA_FROM_DEVICE && direction != DMA_TO_DEVICE) {
@@ -1400,7 +1484,7 @@ static void idmac_issue_pending(struct dma_chan *chan)
 
 	/* This is not always needed, but doesn't hurt either */
 	spin_lock_irqsave(&ipu->lock, flags);
-	ipu_select_buffer(ichan->dma_chan.chan_id, ichan->active_buffer);
+	ipu_select_buffer(chan->chan_id, ichan->active_buffer);
 	spin_unlock_irqrestore(&ipu->lock, flags);
 
 	/*
@@ -1432,8 +1516,7 @@ static void __idmac_terminate_all(struct dma_chan *chan)
 			struct idmac_tx_desc *desc = ichan->desc + i;
 			if (list_empty(&desc->list))
 				/* Descriptor was prepared, but not submitted */
-				list_add(&desc->list,
-					 &ichan->free_list);
+				list_add(&desc->list, &ichan->free_list);
 
 			async_tx_clear_ack(&desc->txd);
 		}
@@ -1458,6 +1541,28 @@ static void idmac_terminate_all(struct dma_chan *chan)
 	mutex_unlock(&ichan->chan_mutex);
 }
 
+#ifdef DEBUG
+static irqreturn_t ic_sof_irq(int irq, void *dev_id)
+{
+	struct idmac_channel *ichan = dev_id;
+	printk(KERN_DEBUG "Got SOF IRQ %d on Channel %d\n",
+	       irq, ichan->dma_chan.chan_id);
+	disable_irq(irq);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t ic_eof_irq(int irq, void *dev_id)
+{
+	struct idmac_channel *ichan = dev_id;
+	printk(KERN_DEBUG "Got EOF IRQ %d on Channel %d\n",
+	       irq, ichan->dma_chan.chan_id);
+	disable_irq(irq);
+	return IRQ_HANDLED;
+}
+
+static int ic_sof = -EINVAL, ic_eof = -EINVAL;
+#endif
+
 static int idmac_alloc_chan_resources(struct dma_chan *chan)
 {
 	struct idmac_channel *ichan = to_idmac_chan(chan);
@@ -1471,31 +1576,49 @@ static int idmac_alloc_chan_resources(struct dma_chan *chan)
 	chan->cookie		= 1;
 	ichan->completed	= -ENXIO;
 
-	ret = ipu_irq_map(ichan->dma_chan.chan_id);
+	ret = ipu_irq_map(chan->chan_id);
 	if (ret < 0)
 		goto eimap;
 
 	ichan->eof_irq = ret;
+
+	/*
+	 * Important to first disable the channel, because maybe someone
+	 * used it before us, e.g., the bootloader
+	 */
+	ipu_disable_channel(idmac, ichan, true);
+
+	ret = ipu_init_channel(idmac, ichan);
+	if (ret < 0)
+		goto eichan;
+
 	ret = request_irq(ichan->eof_irq, idmac_interrupt, 0,
 			  ichan->eof_name, ichan);
 	if (ret < 0)
 		goto erirq;
 
-	ret = ipu_init_channel(idmac, ichan);
-	if (ret < 0)
-		goto eichan;
+#ifdef DEBUG
+	if (chan->chan_id == IDMAC_IC_7) {
+		ic_sof = ipu_irq_map(69);
+		if (ic_sof > 0)
+			request_irq(ic_sof, ic_sof_irq, 0, "IC SOF", ichan);
+		ic_eof = ipu_irq_map(70);
+		if (ic_eof > 0)
+			request_irq(ic_eof, ic_eof_irq, 0, "IC EOF", ichan);
+	}
+#endif
 
 	ichan->status = IPU_CHANNEL_INITIALIZED;
 
-	dev_dbg(&ichan->dma_chan.dev->device, "Found channel 0x%x, irq %d\n",
-		ichan->dma_chan.chan_id, ichan->eof_irq);
+	dev_dbg(&chan->dev->device, "Found channel 0x%x, irq %d\n",
+		chan->chan_id, ichan->eof_irq);
 
 	return ret;
 
-eichan:
-	free_irq(ichan->eof_irq, ichan);
 erirq:
-	ipu_irq_unmap(ichan->dma_chan.chan_id);
+	ipu_uninit_channel(idmac, ichan);
+eichan:
+	ipu_irq_unmap(chan->chan_id);
 eimap:
 	return ret;
 }
@@ -1510,8 +1633,22 @@ static void idmac_free_chan_resources(struct dma_chan *chan)
 	__idmac_terminate_all(chan);
 
 	if (ichan->status > IPU_CHANNEL_FREE) {
+#ifdef DEBUG
+		if (chan->chan_id == IDMAC_IC_7) {
+			if (ic_sof > 0) {
+				free_irq(ic_sof, ichan);
+				ipu_irq_unmap(69);
+				ic_sof = -EINVAL;
+			}
+			if (ic_eof > 0) {
+				free_irq(ic_eof, ichan);
+				ipu_irq_unmap(70);
+				ic_eof = -EINVAL;
+			}
+		}
+#endif
 		free_irq(ichan->eof_irq, ichan);
-		ipu_irq_unmap(ichan->dma_chan.chan_id);
+		ipu_irq_unmap(chan->chan_id);
 	}
 
 	ichan->status = IPU_CHANNEL_FREE;
@@ -1573,7 +1710,7 @@ static int __init ipu_idmac_init(struct ipu *ipu)
 		dma_chan->device	= &idmac->dma;
 		dma_chan->cookie	= 1;
 		dma_chan->chan_id	= i;
-		list_add_tail(&ichan->dma_chan.device_node, &dma->channels);
+		list_add_tail(&dma_chan->device_node, &dma->channels);
 	}
 
 	idmac_write_icreg(ipu, 0x00000070, IDMAC_CONF);
@@ -1581,7 +1718,7 @@ static int __init ipu_idmac_init(struct ipu *ipu)
 	return dma_async_device_register(&idmac->dma);
 }
 
-static void ipu_idmac_exit(struct ipu *ipu)
+static void __exit ipu_idmac_exit(struct ipu *ipu)
 {
 	int i;
 	struct idmac *idmac = &ipu->idmac;
@@ -1600,7 +1737,7 @@ static void ipu_idmac_exit(struct ipu *ipu)
  * IPU common probe / remove
  */
 
-static int ipu_probe(struct platform_device *pdev)
+static int __init ipu_probe(struct platform_device *pdev)
 {
 	struct ipu_platform_data *pdata = pdev->dev.platform_data;
 	struct resource *mem_ipu, *mem_ic;
@@ -1700,7 +1837,7 @@ err_noirq:
 	return ret;
 }
 
-static int ipu_remove(struct platform_device *pdev)
+static int __exit ipu_remove(struct platform_device *pdev)
 {
 	struct ipu *ipu = platform_get_drvdata(pdev);
 
@@ -1725,7 +1862,7 @@ static struct platform_driver ipu_platform_driver = {
 		.name	= "ipu-core",
 		.owner	= THIS_MODULE,
 	},
-	.remove		= ipu_remove,
+	.remove		= __exit_p(ipu_remove),
 };
 
 static int __init ipu_init(void)
diff --git a/drivers/dma/ipu/ipu_irq.c b/drivers/dma/ipu/ipu_irq.c
index 83f532cc767f..dd8ebc75b667 100644
--- a/drivers/dma/ipu/ipu_irq.c
+++ b/drivers/dma/ipu/ipu_irq.c
@@ -352,7 +352,7 @@ static struct irq_chip ipu_irq_chip = {
 };
 
 /* Install the IRQ handler */
-int ipu_irq_attach_irq(struct ipu *ipu, struct platform_device *dev)
+int __init ipu_irq_attach_irq(struct ipu *ipu, struct platform_device *dev)
 {
 	struct ipu_platform_data *pdata = dev->dev.platform_data;
 	unsigned int irq, irq_base, i;
diff --git a/drivers/dma/mv_xor.c b/drivers/dma/mv_xor.c
index cb7f26fb9f18..ddab94f51224 100644
--- a/drivers/dma/mv_xor.c
+++ b/drivers/dma/mv_xor.c
@@ -632,7 +632,6 @@ static int mv_xor_alloc_chan_resources(struct dma_chan *chan)
 		slot->async_tx.tx_submit = mv_xor_tx_submit;
 		INIT_LIST_HEAD(&slot->chain_node);
 		INIT_LIST_HEAD(&slot->slot_node);
-		INIT_LIST_HEAD(&slot->async_tx.tx_list);
 		hw_desc = (char *) mv_chan->device->dma_desc_pool;
 		slot->async_tx.phys =
 			(dma_addr_t) &hw_desc[idx * MV_XOR_SLOT_SIZE];
diff --git a/drivers/edac/Kconfig b/drivers/edac/Kconfig
index eee47fd16d79..e5f5c5a8ba6c 100644
--- a/drivers/edac/Kconfig
+++ b/drivers/edac/Kconfig
@@ -1,13 +1,12 @@
 #
 #	EDAC Kconfig
-#	Copyright (c) 2003 Linux Networx
+#	Copyright (c) 2008 Doug Thompson www.softwarebitmaker.com
 #	Licensed and distributed under the GPL
 #
 
 menuconfig EDAC
-	bool "EDAC - error detection and reporting (EXPERIMENTAL)"
+	bool "EDAC - error detection and reporting"
 	depends on HAS_IOMEM
-	depends on EXPERIMENTAL
 	depends on X86 || PPC
 	help
 	  EDAC is designed to report errors in the core system.
@@ -40,6 +39,14 @@ config EDAC_DEBUG
 	  there're four debug levels (x=0,1,2,3 from low to high).
 	  Usually you should select 'N'.
 
+config EDAC_DEBUG_VERBOSE
+	bool "More verbose debugging"
+	depends on EDAC_DEBUG
+	help
+	  This option makes debugging information more verbose.
+	  Source file name and line number where debugging message
+	  printed will be added to debugging message.
+
 config EDAC_MM_EDAC
 	tristate "Main Memory EDAC (Error Detection And Correction) reporting"
 	default y
@@ -174,4 +181,27 @@ config EDAC_CELL
 	  Cell Broadband Engine internal memory controller
 	  on platform without a hypervisor
 
+config EDAC_PPC4XX
+	tristate "PPC4xx IBM DDR2 Memory Controller"
+	depends on EDAC_MM_EDAC && 4xx
+	help
+	  This enables support for EDAC on the ECC memory used
+	  with the IBM DDR2 memory controller found in various
+	  PowerPC 4xx embedded processors such as the 405EX[r],
+	  440SP, 440SPe, 460EX, 460GT and 460SX.
+
+config EDAC_AMD8131
+	tristate "AMD8131 HyperTransport PCI-X Tunnel"
+	depends on EDAC_MM_EDAC && PCI
+	help
+	  Support for error detection and correction on the
+	  AMD8131 HyperTransport PCI-X Tunnel chip.
+
+config EDAC_AMD8111
+	tristate "AMD8111 HyperTransport I/O Hub"
+	depends on EDAC_MM_EDAC && PCI
+	help
+	  Support for error detection and correction on the
+	  AMD8111 HyperTransport I/O Hub chip.
+
 endif # EDAC
diff --git a/drivers/edac/Makefile b/drivers/edac/Makefile
index b75196927de3..a5fdcf02f591 100644
--- a/drivers/edac/Makefile
+++ b/drivers/edac/Makefile
@@ -34,4 +34,4 @@ obj-$(CONFIG_EDAC_PASEMI)		+= pasemi_edac.o
 obj-$(CONFIG_EDAC_MPC85XX)		+= mpc85xx_edac.o
 obj-$(CONFIG_EDAC_MV64X60)		+= mv64x60_edac.o
 obj-$(CONFIG_EDAC_CELL)			+= cell_edac.o
-
+obj-$(CONFIG_EDAC_PPC4XX)		+= ppc4xx_edac.o
diff --git a/drivers/edac/amd8111_edac.c b/drivers/edac/amd8111_edac.c
new file mode 100644
index 000000000000..614692181120
--- /dev/null
+++ b/drivers/edac/amd8111_edac.c
@@ -0,0 +1,595 @@
+/*
+ * amd8111_edac.c, AMD8111 Hyper Transport chip EDAC kernel module
+ *
+ * Copyright (c) 2008 Wind River Systems, Inc.
+ *
+ * Authors:	Cao Qingtao <qingtao.cao@windriver.com>
+ * 		Benjamin Walsh <benjamin.walsh@windriver.com>
+ * 		Hu Yongqi <yongqi.hu@windriver.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/bitops.h>
+#include <linux/edac.h>
+#include <linux/pci_ids.h>
+#include <asm/io.h>
+
+#include "edac_core.h"
+#include "edac_module.h"
+#include "amd8111_edac.h"
+
+#define AMD8111_EDAC_REVISION	" Ver: 1.0.0 " __DATE__
+#define AMD8111_EDAC_MOD_STR	"amd8111_edac"
+
+#define PCI_DEVICE_ID_AMD_8111_PCI	0x7460
+static int edac_dev_idx;
+
+enum amd8111_edac_devs {
+	LPC_BRIDGE = 0,
+};
+
+enum amd8111_edac_pcis {
+	PCI_BRIDGE = 0,
+};
+
+/* Wrapper functions for accessing PCI configuration space */
+static int edac_pci_read_dword(struct pci_dev *dev, int reg, u32 *val32)
+{
+	int ret;
+
+	ret = pci_read_config_dword(dev, reg, val32);
+	if (ret != 0)
+		printk(KERN_ERR AMD8111_EDAC_MOD_STR
+			" PCI Access Read Error at 0x%x\n", reg);
+
+	return ret;
+}
+
+static void edac_pci_read_byte(struct pci_dev *dev, int reg, u8 *val8)
+{
+	int ret;
+
+	ret = pci_read_config_byte(dev, reg, val8);
+	if (ret != 0)
+		printk(KERN_ERR AMD8111_EDAC_MOD_STR
+			" PCI Access Read Error at 0x%x\n", reg);
+}
+
+static void edac_pci_write_dword(struct pci_dev *dev, int reg, u32 val32)
+{
+	int ret;
+
+	ret = pci_write_config_dword(dev, reg, val32);
+	if (ret != 0)
+		printk(KERN_ERR AMD8111_EDAC_MOD_STR
+			" PCI Access Write Error at 0x%x\n", reg);
+}
+
+static void edac_pci_write_byte(struct pci_dev *dev, int reg, u8 val8)
+{
+	int ret;
+
+	ret = pci_write_config_byte(dev, reg, val8);
+	if (ret != 0)
+		printk(KERN_ERR AMD8111_EDAC_MOD_STR
+			" PCI Access Write Error at 0x%x\n", reg);
+}
+
+/*
+ * device-specific methods for amd8111 PCI Bridge Controller
+ *
+ * Error Reporting and Handling for amd8111 chipset could be found
+ * in its datasheet 3.1.2 section, P37
+ */
+static void amd8111_pci_bridge_init(struct amd8111_pci_info *pci_info)
+{
+	u32 val32;
+	struct pci_dev *dev = pci_info->dev;
+
+	/* First clear error detection flags on the host interface */
+
+	/* Clear SSE/SMA/STA flags in the global status register*/
+	edac_pci_read_dword(dev, REG_PCI_STSCMD, &val32);
+	if (val32 & PCI_STSCMD_CLEAR_MASK)
+		edac_pci_write_dword(dev, REG_PCI_STSCMD, val32);
+
+	/* Clear CRC and Link Fail flags in HT Link Control reg */
+	edac_pci_read_dword(dev, REG_HT_LINK, &val32);
+	if (val32 & HT_LINK_CLEAR_MASK)
+		edac_pci_write_dword(dev, REG_HT_LINK, val32);
+
+	/* Second clear all fault on the secondary interface */
+
+	/* Clear error flags in the memory-base limit reg. */
+	edac_pci_read_dword(dev, REG_MEM_LIM, &val32);
+	if (val32 & MEM_LIMIT_CLEAR_MASK)
+		edac_pci_write_dword(dev, REG_MEM_LIM, val32);
+
+	/* Clear Discard Timer Expired flag in Interrupt/Bridge Control reg */
+	edac_pci_read_dword(dev, REG_PCI_INTBRG_CTRL, &val32);
+	if (val32 & PCI_INTBRG_CTRL_CLEAR_MASK)
+		edac_pci_write_dword(dev, REG_PCI_INTBRG_CTRL, val32);
+
+	/* Last enable error detections */
+	if (edac_op_state == EDAC_OPSTATE_POLL) {
+		/* Enable System Error reporting in global status register */
+		edac_pci_read_dword(dev, REG_PCI_STSCMD, &val32);
+		val32 |= PCI_STSCMD_SERREN;
+		edac_pci_write_dword(dev, REG_PCI_STSCMD, val32);
+
+		/* Enable CRC Sync flood packets to HyperTransport Link */
+		edac_pci_read_dword(dev, REG_HT_LINK, &val32);
+		val32 |= HT_LINK_CRCFEN;
+		edac_pci_write_dword(dev, REG_HT_LINK, val32);
+
+		/* Enable SSE reporting etc in Interrupt control reg */
+		edac_pci_read_dword(dev, REG_PCI_INTBRG_CTRL, &val32);
+		val32 |= PCI_INTBRG_CTRL_POLL_MASK;
+		edac_pci_write_dword(dev, REG_PCI_INTBRG_CTRL, val32);
+	}
+}
+
+static void amd8111_pci_bridge_exit(struct amd8111_pci_info *pci_info)
+{
+	u32 val32;
+	struct pci_dev *dev = pci_info->dev;
+
+	if (edac_op_state == EDAC_OPSTATE_POLL) {
+		/* Disable System Error reporting */
+		edac_pci_read_dword(dev, REG_PCI_STSCMD, &val32);
+		val32 &= ~PCI_STSCMD_SERREN;
+		edac_pci_write_dword(dev, REG_PCI_STSCMD, val32);
+
+		/* Disable CRC flood packets */
+		edac_pci_read_dword(dev, REG_HT_LINK, &val32);
+		val32 &= ~HT_LINK_CRCFEN;
+		edac_pci_write_dword(dev, REG_HT_LINK, val32);
+
+		/* Disable DTSERREN/MARSP/SERREN in Interrupt Control reg */
+		edac_pci_read_dword(dev, REG_PCI_INTBRG_CTRL, &val32);
+		val32 &= ~PCI_INTBRG_CTRL_POLL_MASK;
+		edac_pci_write_dword(dev, REG_PCI_INTBRG_CTRL, val32);
+	}
+}
+
+static void amd8111_pci_bridge_check(struct edac_pci_ctl_info *edac_dev)
+{
+	struct amd8111_pci_info *pci_info = edac_dev->pvt_info;
+	struct pci_dev *dev = pci_info->dev;
+	u32 val32;
+
+	/* Check out PCI Bridge Status and Command Register */
+	edac_pci_read_dword(dev, REG_PCI_STSCMD, &val32);
+	if (val32 & PCI_STSCMD_CLEAR_MASK) {
+		printk(KERN_INFO "Error(s) in PCI bridge status and command"
+			"register on device %s\n", pci_info->ctl_name);
+		printk(KERN_INFO "SSE: %d, RMA: %d, RTA: %d\n",
+			(val32 & PCI_STSCMD_SSE) != 0,
+			(val32 & PCI_STSCMD_RMA) != 0,
+			(val32 & PCI_STSCMD_RTA) != 0);
+
+		val32 |= PCI_STSCMD_CLEAR_MASK;
+		edac_pci_write_dword(dev, REG_PCI_STSCMD, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+
+	/* Check out HyperTransport Link Control Register */
+	edac_pci_read_dword(dev, REG_HT_LINK, &val32);
+	if (val32 & HT_LINK_LKFAIL) {
+		printk(KERN_INFO "Error(s) in hypertransport link control"
+			"register on device %s\n", pci_info->ctl_name);
+		printk(KERN_INFO "LKFAIL: %d\n",
+			(val32 & HT_LINK_LKFAIL) != 0);
+
+		val32 |= HT_LINK_LKFAIL;
+		edac_pci_write_dword(dev, REG_HT_LINK, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+
+	/* Check out PCI Interrupt and Bridge Control Register */
+	edac_pci_read_dword(dev, REG_PCI_INTBRG_CTRL, &val32);
+	if (val32 & PCI_INTBRG_CTRL_DTSTAT) {
+		printk(KERN_INFO "Error(s) in PCI interrupt and bridge control"
+			"register on device %s\n", pci_info->ctl_name);
+		printk(KERN_INFO "DTSTAT: %d\n",
+			(val32 & PCI_INTBRG_CTRL_DTSTAT) != 0);
+
+		val32 |= PCI_INTBRG_CTRL_DTSTAT;
+		edac_pci_write_dword(dev, REG_PCI_INTBRG_CTRL, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+
+	/* Check out PCI Bridge Memory Base-Limit Register */
+	edac_pci_read_dword(dev, REG_MEM_LIM, &val32);
+	if (val32 & MEM_LIMIT_CLEAR_MASK) {
+		printk(KERN_INFO
+			"Error(s) in mem limit register on %s device\n",
+			pci_info->ctl_name);
+		printk(KERN_INFO "DPE: %d, RSE: %d, RMA: %d\n"
+			"RTA: %d, STA: %d, MDPE: %d\n",
+			(val32 & MEM_LIMIT_DPE)  != 0,
+			(val32 & MEM_LIMIT_RSE)  != 0,
+			(val32 & MEM_LIMIT_RMA)  != 0,
+			(val32 & MEM_LIMIT_RTA)  != 0,
+			(val32 & MEM_LIMIT_STA)  != 0,
+			(val32 & MEM_LIMIT_MDPE) != 0);
+
+		val32 |= MEM_LIMIT_CLEAR_MASK;
+		edac_pci_write_dword(dev, REG_MEM_LIM, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+}
+
+static struct resource *legacy_io_res;
+static int at_compat_reg_broken;
+#define LEGACY_NR_PORTS	1
+
+/* device-specific methods for amd8111 LPC Bridge device */
+static void amd8111_lpc_bridge_init(struct amd8111_dev_info *dev_info)
+{
+	u8 val8;
+	struct pci_dev *dev = dev_info->dev;
+
+	/* First clear REG_AT_COMPAT[SERR, IOCHK] if necessary */
+	legacy_io_res = request_region(REG_AT_COMPAT, LEGACY_NR_PORTS,
+					AMD8111_EDAC_MOD_STR);
+	if (!legacy_io_res)
+		printk(KERN_INFO "%s: failed to request legacy I/O region "
+			"start %d, len %d\n", __func__,
+			REG_AT_COMPAT, LEGACY_NR_PORTS);
+	else {
+		val8 = __do_inb(REG_AT_COMPAT);
+		if (val8 == 0xff) { /* buggy port */
+			printk(KERN_INFO "%s: port %d is buggy, not supported"
+				" by hardware?\n", __func__, REG_AT_COMPAT);
+			at_compat_reg_broken = 1;
+			release_region(REG_AT_COMPAT, LEGACY_NR_PORTS);
+			legacy_io_res = NULL;
+		} else {
+			u8 out8 = 0;
+			if (val8 & AT_COMPAT_SERR)
+				out8 = AT_COMPAT_CLRSERR;
+			if (val8 & AT_COMPAT_IOCHK)
+				out8 |= AT_COMPAT_CLRIOCHK;
+			if (out8 > 0)
+				__do_outb(out8, REG_AT_COMPAT);
+		}
+	}
+
+	/* Second clear error flags on LPC bridge */
+	edac_pci_read_byte(dev, REG_IO_CTRL_1, &val8);
+	if (val8 & IO_CTRL_1_CLEAR_MASK)
+		edac_pci_write_byte(dev, REG_IO_CTRL_1, val8);
+}
+
+static void amd8111_lpc_bridge_exit(struct amd8111_dev_info *dev_info)
+{
+	if (legacy_io_res)
+		release_region(REG_AT_COMPAT, LEGACY_NR_PORTS);
+}
+
+static void amd8111_lpc_bridge_check(struct edac_device_ctl_info *edac_dev)
+{
+	struct amd8111_dev_info *dev_info = edac_dev->pvt_info;
+	struct pci_dev *dev = dev_info->dev;
+	u8 val8;
+
+	edac_pci_read_byte(dev, REG_IO_CTRL_1, &val8);
+	if (val8 & IO_CTRL_1_CLEAR_MASK) {
+		printk(KERN_INFO
+			"Error(s) in IO control register on %s device\n",
+			dev_info->ctl_name);
+		printk(KERN_INFO "LPC ERR: %d, PW2LPC: %d\n",
+			(val8 & IO_CTRL_1_LPC_ERR) != 0,
+			(val8 & IO_CTRL_1_PW2LPC) != 0);
+
+		val8 |= IO_CTRL_1_CLEAR_MASK;
+		edac_pci_write_byte(dev, REG_IO_CTRL_1, val8);
+
+		edac_device_handle_ue(edac_dev, 0, 0, edac_dev->ctl_name);
+	}
+
+	if (at_compat_reg_broken == 0) {
+		u8 out8 = 0;
+		val8 = __do_inb(REG_AT_COMPAT);
+		if (val8 & AT_COMPAT_SERR)
+			out8 = AT_COMPAT_CLRSERR;
+		if (val8 & AT_COMPAT_IOCHK)
+			out8 |= AT_COMPAT_CLRIOCHK;
+		if (out8 > 0) {
+			__do_outb(out8, REG_AT_COMPAT);
+			edac_device_handle_ue(edac_dev, 0, 0,
+						edac_dev->ctl_name);
+		}
+	}
+}
+
+/* General devices represented by edac_device_ctl_info */
+static struct amd8111_dev_info amd8111_devices[] = {
+	[LPC_BRIDGE] = {
+		.err_dev = PCI_DEVICE_ID_AMD_8111_LPC,
+		.ctl_name = "lpc",
+		.init = amd8111_lpc_bridge_init,
+		.exit = amd8111_lpc_bridge_exit,
+		.check = amd8111_lpc_bridge_check,
+	},
+	{0},
+};
+
+/* PCI controllers represented by edac_pci_ctl_info */
+static struct amd8111_pci_info amd8111_pcis[] = {
+	[PCI_BRIDGE] = {
+		.err_dev = PCI_DEVICE_ID_AMD_8111_PCI,
+		.ctl_name = "AMD8111_PCI_Controller",
+		.init = amd8111_pci_bridge_init,
+		.exit = amd8111_pci_bridge_exit,
+		.check = amd8111_pci_bridge_check,
+	},
+	{0},
+};
+
+static int amd8111_dev_probe(struct pci_dev *dev,
+				const struct pci_device_id *id)
+{
+	struct amd8111_dev_info *dev_info = &amd8111_devices[id->driver_data];
+
+	dev_info->dev = pci_get_device(PCI_VENDOR_ID_AMD,
+					dev_info->err_dev, NULL);
+
+	if (!dev_info->dev) {
+		printk(KERN_ERR "EDAC device not found:"
+			"vendor %x, device %x, name %s\n",
+			PCI_VENDOR_ID_AMD, dev_info->err_dev,
+			dev_info->ctl_name);
+		return -ENODEV;
+	}
+
+	if (pci_enable_device(dev_info->dev)) {
+		pci_dev_put(dev_info->dev);
+		printk(KERN_ERR "failed to enable:"
+			"vendor %x, device %x, name %s\n",
+			PCI_VENDOR_ID_AMD, dev_info->err_dev,
+			dev_info->ctl_name);
+		return -ENODEV;
+	}
+
+	/*
+	 * we do not allocate extra private structure for
+	 * edac_device_ctl_info, but make use of existing
+	 * one instead.
+	*/
+	dev_info->edac_idx = edac_dev_idx++;
+	dev_info->edac_dev =
+		edac_device_alloc_ctl_info(0, dev_info->ctl_name, 1,
+					   NULL, 0, 0,
+					   NULL, 0, dev_info->edac_idx);
+	if (!dev_info->edac_dev)
+		return -ENOMEM;
+
+	dev_info->edac_dev->pvt_info = dev_info;
+	dev_info->edac_dev->dev = &dev_info->dev->dev;
+	dev_info->edac_dev->mod_name = AMD8111_EDAC_MOD_STR;
+	dev_info->edac_dev->ctl_name = dev_info->ctl_name;
+	dev_info->edac_dev->dev_name = dev_info->dev->dev.bus_id;
+
+	if (edac_op_state == EDAC_OPSTATE_POLL)
+		dev_info->edac_dev->edac_check = dev_info->check;
+
+	if (dev_info->init)
+		dev_info->init(dev_info);
+
+	if (edac_device_add_device(dev_info->edac_dev) > 0) {
+		printk(KERN_ERR "failed to add edac_dev for %s\n",
+			dev_info->ctl_name);
+		edac_device_free_ctl_info(dev_info->edac_dev);
+		return -ENODEV;
+	}
+
+	printk(KERN_INFO "added one edac_dev on AMD8111 "
+		"vendor %x, device %x, name %s\n",
+		PCI_VENDOR_ID_AMD, dev_info->err_dev,
+		dev_info->ctl_name);
+
+	return 0;
+}
+
+static void amd8111_dev_remove(struct pci_dev *dev)
+{
+	struct amd8111_dev_info *dev_info;
+
+	for (dev_info = amd8111_devices; dev_info->err_dev; dev_info++)
+		if (dev_info->dev->device == dev->device)
+			break;
+
+	if (!dev_info->err_dev)	/* should never happen */
+		return;
+
+	if (dev_info->edac_dev) {
+		edac_device_del_device(dev_info->edac_dev->dev);
+		edac_device_free_ctl_info(dev_info->edac_dev);
+	}
+
+	if (dev_info->exit)
+		dev_info->exit(dev_info);
+
+	pci_dev_put(dev_info->dev);
+}
+
+static int amd8111_pci_probe(struct pci_dev *dev,
+				const struct pci_device_id *id)
+{
+	struct amd8111_pci_info *pci_info = &amd8111_pcis[id->driver_data];
+
+	pci_info->dev = pci_get_device(PCI_VENDOR_ID_AMD,
+					pci_info->err_dev, NULL);
+
+	if (!pci_info->dev) {
+		printk(KERN_ERR "EDAC device not found:"
+			"vendor %x, device %x, name %s\n",
+			PCI_VENDOR_ID_AMD, pci_info->err_dev,
+			pci_info->ctl_name);
+		return -ENODEV;
+	}
+
+	if (pci_enable_device(pci_info->dev)) {
+		pci_dev_put(pci_info->dev);
+		printk(KERN_ERR "failed to enable:"
+			"vendor %x, device %x, name %s\n",
+			PCI_VENDOR_ID_AMD, pci_info->err_dev,
+			pci_info->ctl_name);
+		return -ENODEV;
+	}
+
+	/*
+	 * we do not allocate extra private structure for
+	 * edac_pci_ctl_info, but make use of existing
+	 * one instead.
+	*/
+	pci_info->edac_idx = edac_pci_alloc_index();
+	pci_info->edac_dev = edac_pci_alloc_ctl_info(0, pci_info->ctl_name);
+	if (!pci_info->edac_dev)
+		return -ENOMEM;
+
+	pci_info->edac_dev->pvt_info = pci_info;
+	pci_info->edac_dev->dev = &pci_info->dev->dev;
+	pci_info->edac_dev->mod_name = AMD8111_EDAC_MOD_STR;
+	pci_info->edac_dev->ctl_name = pci_info->ctl_name;
+	pci_info->edac_dev->dev_name = pci_info->dev->dev.bus_id;
+
+	if (edac_op_state == EDAC_OPSTATE_POLL)
+		pci_info->edac_dev->edac_check = pci_info->check;
+
+	if (pci_info->init)
+		pci_info->init(pci_info);
+
+	if (edac_pci_add_device(pci_info->edac_dev, pci_info->edac_idx) > 0) {
+		printk(KERN_ERR "failed to add edac_pci for %s\n",
+			pci_info->ctl_name);
+		edac_pci_free_ctl_info(pci_info->edac_dev);
+		return -ENODEV;
+	}
+
+	printk(KERN_INFO "added one edac_pci on AMD8111 "
+		"vendor %x, device %x, name %s\n",
+		PCI_VENDOR_ID_AMD, pci_info->err_dev,
+		pci_info->ctl_name);
+
+	return 0;
+}
+
+static void amd8111_pci_remove(struct pci_dev *dev)
+{
+	struct amd8111_pci_info *pci_info;
+
+	for (pci_info = amd8111_pcis; pci_info->err_dev; pci_info++)
+		if (pci_info->dev->device == dev->device)
+			break;
+
+	if (!pci_info->err_dev)	/* should never happen */
+		return;
+
+	if (pci_info->edac_dev) {
+		edac_pci_del_device(pci_info->edac_dev->dev);
+		edac_pci_free_ctl_info(pci_info->edac_dev);
+	}
+
+	if (pci_info->exit)
+		pci_info->exit(pci_info);
+
+	pci_dev_put(pci_info->dev);
+}
+
+/* PCI Device ID talbe for general EDAC device */
+static const struct pci_device_id amd8111_edac_dev_tbl[] = {
+	{
+	PCI_VEND_DEV(AMD, 8111_LPC),
+	.subvendor = PCI_ANY_ID,
+	.subdevice = PCI_ANY_ID,
+	.class = 0,
+	.class_mask = 0,
+	.driver_data = LPC_BRIDGE,
+	},
+	{
+	0,
+	}			/* table is NULL-terminated */
+};
+MODULE_DEVICE_TABLE(pci, amd8111_edac_dev_tbl);
+
+static struct pci_driver amd8111_edac_dev_driver = {
+	.name = "AMD8111_EDAC_DEV",
+	.probe = amd8111_dev_probe,
+	.remove = amd8111_dev_remove,
+	.id_table = amd8111_edac_dev_tbl,
+};
+
+/* PCI Device ID table for EDAC PCI controller */
+static const struct pci_device_id amd8111_edac_pci_tbl[] = {
+	{
+	PCI_VEND_DEV(AMD, 8111_PCI),
+	.subvendor = PCI_ANY_ID,
+	.subdevice = PCI_ANY_ID,
+	.class = 0,
+	.class_mask = 0,
+	.driver_data = PCI_BRIDGE,
+	},
+	{
+	0,
+	}			/* table is NULL-terminated */
+};
+MODULE_DEVICE_TABLE(pci, amd8111_edac_pci_tbl);
+
+static struct pci_driver amd8111_edac_pci_driver = {
+	.name = "AMD8111_EDAC_PCI",
+	.probe = amd8111_pci_probe,
+	.remove = amd8111_pci_remove,
+	.id_table = amd8111_edac_pci_tbl,
+};
+
+static int __init amd8111_edac_init(void)
+{
+	int val;
+
+	printk(KERN_INFO "AMD8111 EDAC driver "	AMD8111_EDAC_REVISION "\n");
+	printk(KERN_INFO "\t(c) 2008 Wind River Systems, Inc.\n");
+
+	/* Only POLL mode supported so far */
+	edac_op_state = EDAC_OPSTATE_POLL;
+
+	val = pci_register_driver(&amd8111_edac_dev_driver);
+	val |= pci_register_driver(&amd8111_edac_pci_driver);
+
+	return val;
+}
+
+static void __exit amd8111_edac_exit(void)
+{
+	pci_unregister_driver(&amd8111_edac_pci_driver);
+	pci_unregister_driver(&amd8111_edac_dev_driver);
+}
+
+
+module_init(amd8111_edac_init);
+module_exit(amd8111_edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Cao Qingtao <qingtao.cao@windriver.com>\n");
+MODULE_DESCRIPTION("AMD8111 HyperTransport I/O Hub EDAC kernel module");
diff --git a/drivers/edac/amd8111_edac.h b/drivers/edac/amd8111_edac.h
new file mode 100644
index 000000000000..35794331debc
--- /dev/null
+++ b/drivers/edac/amd8111_edac.h
@@ -0,0 +1,130 @@
+/*
+ * amd8111_edac.h, EDAC defs for AMD8111 hypertransport chip
+ *
+ * Copyright (c) 2008 Wind River Systems, Inc.
+ *
+ * Authors:	Cao Qingtao <qingtao.cao@windriver.com>
+ * 		Benjamin Walsh <benjamin.walsh@windriver.com>
+ * 		Hu Yongqi <yongqi.hu@windriver.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _AMD8111_EDAC_H_
+#define _AMD8111_EDAC_H_
+
+/************************************************************
+ *	PCI Bridge Status and Command Register, DevA:0x04
+ ************************************************************/
+#define REG_PCI_STSCMD	0x04
+enum pci_stscmd_bits {
+	PCI_STSCMD_SSE		= BIT(30),
+	PCI_STSCMD_RMA		= BIT(29),
+	PCI_STSCMD_RTA		= BIT(28),
+	PCI_STSCMD_SERREN	= BIT(8),
+	PCI_STSCMD_CLEAR_MASK	= (PCI_STSCMD_SSE |
+				   PCI_STSCMD_RMA |
+				   PCI_STSCMD_RTA)
+};
+
+/************************************************************
+ *	PCI Bridge Memory Base-Limit Register, DevA:0x1c
+ ************************************************************/
+#define REG_MEM_LIM     0x1c
+enum mem_limit_bits {
+	MEM_LIMIT_DPE   = BIT(31),
+	MEM_LIMIT_RSE   = BIT(30),
+	MEM_LIMIT_RMA   = BIT(29),
+	MEM_LIMIT_RTA   = BIT(28),
+	MEM_LIMIT_STA   = BIT(27),
+	MEM_LIMIT_MDPE  = BIT(24),
+	MEM_LIMIT_CLEAR_MASK  = (MEM_LIMIT_DPE |
+				 MEM_LIMIT_RSE |
+				 MEM_LIMIT_RMA |
+				 MEM_LIMIT_RTA |
+				 MEM_LIMIT_STA |
+				 MEM_LIMIT_MDPE)
+};
+
+/************************************************************
+ *	HyperTransport Link Control Register, DevA:0xc4
+ ************************************************************/
+#define REG_HT_LINK	0xc4
+enum ht_link_bits {
+	HT_LINK_LKFAIL	= BIT(4),
+	HT_LINK_CRCFEN	= BIT(1),
+	HT_LINK_CLEAR_MASK = (HT_LINK_LKFAIL)
+};
+
+/************************************************************
+ *	PCI Bridge Interrupt and Bridge Control, DevA:0x3c
+ ************************************************************/
+#define REG_PCI_INTBRG_CTRL	0x3c
+enum pci_intbrg_ctrl_bits {
+	PCI_INTBRG_CTRL_DTSERREN	= BIT(27),
+	PCI_INTBRG_CTRL_DTSTAT		= BIT(26),
+	PCI_INTBRG_CTRL_MARSP		= BIT(21),
+	PCI_INTBRG_CTRL_SERREN		= BIT(17),
+	PCI_INTBRG_CTRL_PEREN		= BIT(16),
+	PCI_INTBRG_CTRL_CLEAR_MASK	= (PCI_INTBRG_CTRL_DTSTAT),
+	PCI_INTBRG_CTRL_POLL_MASK	= (PCI_INTBRG_CTRL_DTSERREN |
+					   PCI_INTBRG_CTRL_MARSP |
+					   PCI_INTBRG_CTRL_SERREN)
+};
+
+/************************************************************
+ *		I/O Control 1 Register, DevB:0x40
+ ************************************************************/
+#define REG_IO_CTRL_1 0x40
+enum io_ctrl_1_bits {
+	IO_CTRL_1_NMIONERR	= BIT(7),
+	IO_CTRL_1_LPC_ERR	= BIT(6),
+	IO_CTRL_1_PW2LPC	= BIT(1),
+	IO_CTRL_1_CLEAR_MASK	= (IO_CTRL_1_LPC_ERR | IO_CTRL_1_PW2LPC)
+};
+
+/************************************************************
+ *		Legacy I/O Space Registers
+ ************************************************************/
+#define REG_AT_COMPAT 0x61
+enum at_compat_bits {
+	AT_COMPAT_SERR		= BIT(7),
+	AT_COMPAT_IOCHK		= BIT(6),
+	AT_COMPAT_CLRIOCHK	= BIT(3),
+	AT_COMPAT_CLRSERR	= BIT(2),
+};
+
+struct amd8111_dev_info {
+	u16 err_dev;	/* PCI Device ID */
+	struct pci_dev *dev;
+	int edac_idx;	/* device index */
+	char *ctl_name;
+	struct edac_device_ctl_info *edac_dev;
+	void (*init)(struct amd8111_dev_info *dev_info);
+	void (*exit)(struct amd8111_dev_info *dev_info);
+	void (*check)(struct edac_device_ctl_info *edac_dev);
+};
+
+struct amd8111_pci_info {
+	u16 err_dev;	/* PCI Device ID */
+	struct pci_dev *dev;
+	int edac_idx;	/* pci index */
+	const char *ctl_name;
+	struct edac_pci_ctl_info *edac_dev;
+	void (*init)(struct amd8111_pci_info *dev_info);
+	void (*exit)(struct amd8111_pci_info *dev_info);
+	void (*check)(struct edac_pci_ctl_info *edac_dev);
+};
+
+#endif /* _AMD8111_EDAC_H_ */
diff --git a/drivers/edac/amd8131_edac.c b/drivers/edac/amd8131_edac.c
new file mode 100644
index 000000000000..c083b31cac5a
--- /dev/null
+++ b/drivers/edac/amd8131_edac.c
@@ -0,0 +1,379 @@
+/*
+ * amd8131_edac.c, AMD8131 hypertransport chip EDAC kernel module
+ *
+ * Copyright (c) 2008 Wind River Systems, Inc.
+ *
+ * Authors:	Cao Qingtao <qingtao.cao@windriver.com>
+ * 		Benjamin Walsh <benjamin.walsh@windriver.com>
+ * 		Hu Yongqi <yongqi.hu@windriver.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/bitops.h>
+#include <linux/edac.h>
+#include <linux/pci_ids.h>
+
+#include "edac_core.h"
+#include "edac_module.h"
+#include "amd8131_edac.h"
+
+#define AMD8131_EDAC_REVISION	" Ver: 1.0.0 " __DATE__
+#define AMD8131_EDAC_MOD_STR	"amd8131_edac"
+
+/* Wrapper functions for accessing PCI configuration space */
+static void edac_pci_read_dword(struct pci_dev *dev, int reg, u32 *val32)
+{
+	int ret;
+
+	ret = pci_read_config_dword(dev, reg, val32);
+	if (ret != 0)
+		printk(KERN_ERR AMD8131_EDAC_MOD_STR
+			" PCI Access Read Error at 0x%x\n", reg);
+}
+
+static void edac_pci_write_dword(struct pci_dev *dev, int reg, u32 val32)
+{
+	int ret;
+
+	ret = pci_write_config_dword(dev, reg, val32);
+	if (ret != 0)
+		printk(KERN_ERR AMD8131_EDAC_MOD_STR
+			" PCI Access Write Error at 0x%x\n", reg);
+}
+
+static char * const bridge_str[] = {
+	[NORTH_A] = "NORTH A",
+	[NORTH_B] = "NORTH B",
+	[SOUTH_A] = "SOUTH A",
+	[SOUTH_B] = "SOUTH B",
+	[NO_BRIDGE] = "NO BRIDGE",
+};
+
+/* Support up to two AMD8131 chipsets on a platform */
+static struct amd8131_dev_info amd8131_devices[] = {
+	{
+	.inst = NORTH_A,
+	.devfn = DEVFN_PCIX_BRIDGE_NORTH_A,
+	.ctl_name = "AMD8131_PCIX_NORTH_A",
+	},
+	{
+	.inst = NORTH_B,
+	.devfn = DEVFN_PCIX_BRIDGE_NORTH_B,
+	.ctl_name = "AMD8131_PCIX_NORTH_B",
+	},
+	{
+	.inst = SOUTH_A,
+	.devfn = DEVFN_PCIX_BRIDGE_SOUTH_A,
+	.ctl_name = "AMD8131_PCIX_SOUTH_A",
+	},
+	{
+	.inst = SOUTH_B,
+	.devfn = DEVFN_PCIX_BRIDGE_SOUTH_B,
+	.ctl_name = "AMD8131_PCIX_SOUTH_B",
+	},
+	{.inst = NO_BRIDGE,},
+};
+
+static void amd8131_pcix_init(struct amd8131_dev_info *dev_info)
+{
+	u32 val32;
+	struct pci_dev *dev = dev_info->dev;
+
+	/* First clear error detection flags */
+	edac_pci_read_dword(dev, REG_MEM_LIM, &val32);
+	if (val32 & MEM_LIMIT_MASK)
+		edac_pci_write_dword(dev, REG_MEM_LIM, val32);
+
+	/* Clear Discard Timer Timedout flag */
+	edac_pci_read_dword(dev, REG_INT_CTLR, &val32);
+	if (val32 & INT_CTLR_DTS)
+		edac_pci_write_dword(dev, REG_INT_CTLR, val32);
+
+	/* Clear CRC Error flag on link side A */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_A, &val32);
+	if (val32 & LNK_CTRL_CRCERR_A)
+		edac_pci_write_dword(dev, REG_LNK_CTRL_A, val32);
+
+	/* Clear CRC Error flag on link side B */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_B, &val32);
+	if (val32 & LNK_CTRL_CRCERR_B)
+		edac_pci_write_dword(dev, REG_LNK_CTRL_B, val32);
+
+	/*
+	 * Then enable all error detections.
+	 *
+	 * Setup Discard Timer Sync Flood Enable,
+	 * System Error Enable and Parity Error Enable.
+	 */
+	edac_pci_read_dword(dev, REG_INT_CTLR, &val32);
+	val32 |= INT_CTLR_PERR | INT_CTLR_SERR | INT_CTLR_DTSE;
+	edac_pci_write_dword(dev, REG_INT_CTLR, val32);
+
+	/* Enable overall SERR Error detection */
+	edac_pci_read_dword(dev, REG_STS_CMD, &val32);
+	val32 |= STS_CMD_SERREN;
+	edac_pci_write_dword(dev, REG_STS_CMD, val32);
+
+	/* Setup CRC Flood Enable for link side A */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_A, &val32);
+	val32 |= LNK_CTRL_CRCFEN;
+	edac_pci_write_dword(dev, REG_LNK_CTRL_A, val32);
+
+	/* Setup CRC Flood Enable for link side B */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_B, &val32);
+	val32 |= LNK_CTRL_CRCFEN;
+	edac_pci_write_dword(dev, REG_LNK_CTRL_B, val32);
+}
+
+static void amd8131_pcix_exit(struct amd8131_dev_info *dev_info)
+{
+	u32 val32;
+	struct pci_dev *dev = dev_info->dev;
+
+	/* Disable SERR, PERR and DTSE Error detection */
+	edac_pci_read_dword(dev, REG_INT_CTLR, &val32);
+	val32 &= ~(INT_CTLR_PERR | INT_CTLR_SERR | INT_CTLR_DTSE);
+	edac_pci_write_dword(dev, REG_INT_CTLR, val32);
+
+	/* Disable overall System Error detection */
+	edac_pci_read_dword(dev, REG_STS_CMD, &val32);
+	val32 &= ~STS_CMD_SERREN;
+	edac_pci_write_dword(dev, REG_STS_CMD, val32);
+
+	/* Disable CRC Sync Flood on link side A */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_A, &val32);
+	val32 &= ~LNK_CTRL_CRCFEN;
+	edac_pci_write_dword(dev, REG_LNK_CTRL_A, val32);
+
+	/* Disable CRC Sync Flood on link side B */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_B, &val32);
+	val32 &= ~LNK_CTRL_CRCFEN;
+	edac_pci_write_dword(dev, REG_LNK_CTRL_B, val32);
+}
+
+static void amd8131_pcix_check(struct edac_pci_ctl_info *edac_dev)
+{
+	struct amd8131_dev_info *dev_info = edac_dev->pvt_info;
+	struct pci_dev *dev = dev_info->dev;
+	u32 val32;
+
+	/* Check PCI-X Bridge Memory Base-Limit Register for errors */
+	edac_pci_read_dword(dev, REG_MEM_LIM, &val32);
+	if (val32 & MEM_LIMIT_MASK) {
+		printk(KERN_INFO "Error(s) in mem limit register "
+			"on %s bridge\n", dev_info->ctl_name);
+		printk(KERN_INFO "DPE: %d, RSE: %d, RMA: %d\n"
+			"RTA: %d, STA: %d, MDPE: %d\n",
+			val32 & MEM_LIMIT_DPE,
+			val32 & MEM_LIMIT_RSE,
+			val32 & MEM_LIMIT_RMA,
+			val32 & MEM_LIMIT_RTA,
+			val32 & MEM_LIMIT_STA,
+			val32 & MEM_LIMIT_MDPE);
+
+		val32 |= MEM_LIMIT_MASK;
+		edac_pci_write_dword(dev, REG_MEM_LIM, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+
+	/* Check if Discard Timer timed out */
+	edac_pci_read_dword(dev, REG_INT_CTLR, &val32);
+	if (val32 & INT_CTLR_DTS) {
+		printk(KERN_INFO "Error(s) in interrupt and control register "
+			"on %s bridge\n", dev_info->ctl_name);
+		printk(KERN_INFO "DTS: %d\n", val32 & INT_CTLR_DTS);
+
+		val32 |= INT_CTLR_DTS;
+		edac_pci_write_dword(dev, REG_INT_CTLR, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+
+	/* Check if CRC error happens on link side A */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_A, &val32);
+	if (val32 & LNK_CTRL_CRCERR_A) {
+		printk(KERN_INFO "Error(s) in link conf and control register "
+			"on %s bridge\n", dev_info->ctl_name);
+		printk(KERN_INFO "CRCERR: %d\n", val32 & LNK_CTRL_CRCERR_A);
+
+		val32 |= LNK_CTRL_CRCERR_A;
+		edac_pci_write_dword(dev, REG_LNK_CTRL_A, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+
+	/* Check if CRC error happens on link side B */
+	edac_pci_read_dword(dev, REG_LNK_CTRL_B, &val32);
+	if (val32 & LNK_CTRL_CRCERR_B) {
+		printk(KERN_INFO "Error(s) in link conf and control register "
+			"on %s bridge\n", dev_info->ctl_name);
+		printk(KERN_INFO "CRCERR: %d\n", val32 & LNK_CTRL_CRCERR_B);
+
+		val32 |= LNK_CTRL_CRCERR_B;
+		edac_pci_write_dword(dev, REG_LNK_CTRL_B, val32);
+
+		edac_pci_handle_npe(edac_dev, edac_dev->ctl_name);
+	}
+}
+
+static struct amd8131_info amd8131_chipset = {
+	.err_dev = PCI_DEVICE_ID_AMD_8131_APIC,
+	.devices = amd8131_devices,
+	.init = amd8131_pcix_init,
+	.exit = amd8131_pcix_exit,
+	.check = amd8131_pcix_check,
+};
+
+/*
+ * There are 4 PCIX Bridges on ATCA-6101 that share the same PCI Device ID,
+ * so amd8131_probe() would be called by kernel 4 times, with different
+ * address of pci_dev for each of them each time.
+ */
+static int amd8131_probe(struct pci_dev *dev, const struct pci_device_id *id)
+{
+	struct amd8131_dev_info *dev_info;
+
+	for (dev_info = amd8131_chipset.devices; dev_info->inst != NO_BRIDGE;
+		dev_info++)
+		if (dev_info->devfn == dev->devfn)
+			break;
+
+	if (dev_info->inst == NO_BRIDGE) /* should never happen */
+		return -ENODEV;
+
+	/*
+	 * We can't call pci_get_device() as we are used to do because
+	 * there are 4 of them but pci_dev_get() instead.
+	 */
+	dev_info->dev = pci_dev_get(dev);
+
+	if (pci_enable_device(dev_info->dev)) {
+		pci_dev_put(dev_info->dev);
+		printk(KERN_ERR "failed to enable:"
+			"vendor %x, device %x, devfn %x, name %s\n",
+			PCI_VENDOR_ID_AMD, amd8131_chipset.err_dev,
+			dev_info->devfn, dev_info->ctl_name);
+		return -ENODEV;
+	}
+
+	/*
+	 * we do not allocate extra private structure for
+	 * edac_pci_ctl_info, but make use of existing
+	 * one instead.
+	 */
+	dev_info->edac_idx = edac_pci_alloc_index();
+	dev_info->edac_dev = edac_pci_alloc_ctl_info(0, dev_info->ctl_name);
+	if (!dev_info->edac_dev)
+		return -ENOMEM;
+
+	dev_info->edac_dev->pvt_info = dev_info;
+	dev_info->edac_dev->dev = &dev_info->dev->dev;
+	dev_info->edac_dev->mod_name = AMD8131_EDAC_MOD_STR;
+	dev_info->edac_dev->ctl_name = dev_info->ctl_name;
+	dev_info->edac_dev->dev_name = dev_info->dev->dev.bus_id;
+
+	if (edac_op_state == EDAC_OPSTATE_POLL)
+		dev_info->edac_dev->edac_check = amd8131_chipset.check;
+
+	if (amd8131_chipset.init)
+		amd8131_chipset.init(dev_info);
+
+	if (edac_pci_add_device(dev_info->edac_dev, dev_info->edac_idx) > 0) {
+		printk(KERN_ERR "failed edac_pci_add_device() for %s\n",
+			dev_info->ctl_name);
+		edac_pci_free_ctl_info(dev_info->edac_dev);
+		return -ENODEV;
+	}
+
+	printk(KERN_INFO "added one device on AMD8131 "
+		"vendor %x, device %x, devfn %x, name %s\n",
+		PCI_VENDOR_ID_AMD, amd8131_chipset.err_dev,
+		dev_info->devfn, dev_info->ctl_name);
+
+	return 0;
+}
+
+static void amd8131_remove(struct pci_dev *dev)
+{
+	struct amd8131_dev_info *dev_info;
+
+	for (dev_info = amd8131_chipset.devices; dev_info->inst != NO_BRIDGE;
+		dev_info++)
+		if (dev_info->devfn == dev->devfn)
+			break;
+
+	if (dev_info->inst == NO_BRIDGE) /* should never happen */
+		return;
+
+	if (dev_info->edac_dev) {
+		edac_pci_del_device(dev_info->edac_dev->dev);
+		edac_pci_free_ctl_info(dev_info->edac_dev);
+	}
+
+	if (amd8131_chipset.exit)
+		amd8131_chipset.exit(dev_info);
+
+	pci_dev_put(dev_info->dev);
+}
+
+static const struct pci_device_id amd8131_edac_pci_tbl[] = {
+	{
+	PCI_VEND_DEV(AMD, 8131_BRIDGE),
+	.subvendor = PCI_ANY_ID,
+	.subdevice = PCI_ANY_ID,
+	.class = 0,
+	.class_mask = 0,
+	.driver_data = 0,
+	},
+	{
+	0,
+	}			/* table is NULL-terminated */
+};
+MODULE_DEVICE_TABLE(pci, amd8131_edac_pci_tbl);
+
+static struct pci_driver amd8131_edac_driver = {
+	.name = AMD8131_EDAC_MOD_STR,
+	.probe = amd8131_probe,
+	.remove = amd8131_remove,
+	.id_table = amd8131_edac_pci_tbl,
+};
+
+static int __init amd8131_edac_init(void)
+{
+	printk(KERN_INFO "AMD8131 EDAC driver " AMD8131_EDAC_REVISION "\n");
+	printk(KERN_INFO "\t(c) 2008 Wind River Systems, Inc.\n");
+
+	/* Only POLL mode supported so far */
+	edac_op_state = EDAC_OPSTATE_POLL;
+
+	return pci_register_driver(&amd8131_edac_driver);
+}
+
+static void __exit amd8131_edac_exit(void)
+{
+	pci_unregister_driver(&amd8131_edac_driver);
+}
+
+module_init(amd8131_edac_init);
+module_exit(amd8131_edac_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Cao Qingtao <qingtao.cao@windriver.com>\n");
+MODULE_DESCRIPTION("AMD8131 HyperTransport PCI-X Tunnel EDAC kernel module");
diff --git a/drivers/edac/amd8131_edac.h b/drivers/edac/amd8131_edac.h
new file mode 100644
index 000000000000..60e0d1c72dee
--- /dev/null
+++ b/drivers/edac/amd8131_edac.h
@@ -0,0 +1,119 @@
+/*
+ * amd8131_edac.h, EDAC defs for AMD8131 hypertransport chip
+ *
+ * Copyright (c) 2008 Wind River Systems, Inc.
+ *
+ * Authors:	Cao Qingtao <qingtao.cao@windriver.com>
+ * 		Benjamin Walsh <benjamin.walsh@windriver.com>
+ * 		Hu Yongqi <yongqi.hu@windriver.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
+ * See the GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#ifndef _AMD8131_EDAC_H_
+#define _AMD8131_EDAC_H_
+
+#define DEVFN_PCIX_BRIDGE_NORTH_A	8
+#define DEVFN_PCIX_BRIDGE_NORTH_B	16
+#define DEVFN_PCIX_BRIDGE_SOUTH_A	24
+#define DEVFN_PCIX_BRIDGE_SOUTH_B	32
+
+/************************************************************
+ *	PCI-X Bridge Status and Command Register, DevA:0x04
+ ************************************************************/
+#define REG_STS_CMD	0x04
+enum sts_cmd_bits {
+	STS_CMD_SSE	= BIT(30),
+	STS_CMD_SERREN	= BIT(8)
+};
+
+/************************************************************
+ *	PCI-X Bridge Interrupt and Bridge Control Register,
+ ************************************************************/
+#define REG_INT_CTLR	0x3c
+enum int_ctlr_bits {
+	INT_CTLR_DTSE	= BIT(27),
+	INT_CTLR_DTS	= BIT(26),
+	INT_CTLR_SERR	= BIT(17),
+	INT_CTLR_PERR	= BIT(16)
+};
+
+/************************************************************
+ *	PCI-X Bridge Memory Base-Limit Register, DevA:0x1C
+ ************************************************************/
+#define REG_MEM_LIM	0x1c
+enum mem_limit_bits {
+	MEM_LIMIT_DPE 	= BIT(31),
+	MEM_LIMIT_RSE 	= BIT(30),
+	MEM_LIMIT_RMA 	= BIT(29),
+	MEM_LIMIT_RTA 	= BIT(28),
+	MEM_LIMIT_STA	= BIT(27),
+	MEM_LIMIT_MDPE	= BIT(24),
+	MEM_LIMIT_MASK	= MEM_LIMIT_DPE|MEM_LIMIT_RSE|MEM_LIMIT_RMA|
+				MEM_LIMIT_RTA|MEM_LIMIT_STA|MEM_LIMIT_MDPE
+};
+
+/************************************************************
+ *	Link Configuration And Control Register, side A
+ ************************************************************/
+#define REG_LNK_CTRL_A	0xc4
+
+/************************************************************
+ *	Link Configuration And Control Register, side B
+ ************************************************************/
+#define REG_LNK_CTRL_B  0xc8
+
+enum lnk_ctrl_bits {
+	LNK_CTRL_CRCERR_A	= BIT(9),
+	LNK_CTRL_CRCERR_B	= BIT(8),
+	LNK_CTRL_CRCFEN		= BIT(1)
+};
+
+enum pcix_bridge_inst {
+	NORTH_A = 0,
+	NORTH_B = 1,
+	SOUTH_A = 2,
+	SOUTH_B = 3,
+	NO_BRIDGE = 4
+};
+
+struct amd8131_dev_info {
+	int devfn;
+	enum pcix_bridge_inst inst;
+	struct pci_dev *dev;
+	int edac_idx;	/* pci device index */
+	char *ctl_name;
+	struct edac_pci_ctl_info *edac_dev;
+};
+
+/*
+ * AMD8131 chipset has two pairs of PCIX Bridge and related IOAPIC
+ * Controler, and ATCA-6101 has two AMD8131 chipsets, so there are
+ * four PCIX Bridges on ATCA-6101 altogether.
+ *
+ * These PCIX Bridges share the same PCI Device ID and are all of
+ * Function Zero, they could be discrimated by their pci_dev->devfn.
+ * They share the same set of init/check/exit methods, and their
+ * private structures are collected in the devices[] array.
+ */
+struct amd8131_info {
+	u16 err_dev;	/* PCI Device ID for AMD8131 APIC*/
+	struct amd8131_dev_info *devices;
+	void (*init)(struct amd8131_dev_info *dev_info);
+	void (*exit)(struct amd8131_dev_info *dev_info);
+	void (*check)(struct edac_pci_ctl_info *edac_dev);
+};
+
+#endif /* _AMD8131_EDAC_H_ */
+
diff --git a/drivers/edac/edac_core.h b/drivers/edac/edac_core.h
index 4b55ec607a88..28f2c3f959b5 100644
--- a/drivers/edac/edac_core.h
+++ b/drivers/edac/edac_core.h
@@ -49,6 +49,10 @@
 #define edac_printk(level, prefix, fmt, arg...) \
 	printk(level "EDAC " prefix ": " fmt, ##arg)
 
+#define edac_printk_verbose(level, prefix, fmt, arg...) \
+	printk(level "EDAC " prefix ": " "in %s, line at %d: " fmt,	\
+	       __FILE__, __LINE__, ##arg)
+
 #define edac_mc_printk(mci, level, fmt, arg...) \
 	printk(level "EDAC MC%d: " fmt, mci->mc_idx, ##arg)
 
@@ -71,11 +75,20 @@
 #ifdef CONFIG_EDAC_DEBUG
 extern int edac_debug_level;
 
+#ifndef CONFIG_EDAC_DEBUG_VERBOSE
 #define edac_debug_printk(level, fmt, arg...)                            \
 	do {                                                             \
 		if (level <= edac_debug_level)                           \
 			edac_printk(KERN_DEBUG, EDAC_DEBUG, fmt, ##arg); \
-	} while(0)
+	} while (0)
+#else  /* CONFIG_EDAC_DEBUG_VERBOSE */
+#define edac_debug_printk(level, fmt, arg...)                            \
+	do {                                                             \
+		if (level <= edac_debug_level)                           \
+			edac_printk_verbose(KERN_DEBUG, EDAC_DEBUG, fmt, \
+					    ##arg);			\
+	} while (0)
+#endif
 
 #define debugf0( ... ) edac_debug_printk(0, __VA_ARGS__ )
 #define debugf1( ... ) edac_debug_printk(1, __VA_ARGS__ )
@@ -831,6 +844,7 @@ extern void edac_pci_free_ctl_info(struct edac_pci_ctl_info *pci);
 extern void edac_pci_reset_delay_period(struct edac_pci_ctl_info *pci,
 				unsigned long value);
 
+extern int edac_pci_alloc_index(void);
 extern int edac_pci_add_device(struct edac_pci_ctl_info *pci, int edac_idx);
 extern struct edac_pci_ctl_info *edac_pci_del_device(struct device *dev);
 
diff --git a/drivers/edac/edac_pci.c b/drivers/edac/edac_pci.c
index 5d3c8083a40e..5b150aea703a 100644
--- a/drivers/edac/edac_pci.c
+++ b/drivers/edac/edac_pci.c
@@ -30,6 +30,7 @@
 
 static DEFINE_MUTEX(edac_pci_ctls_mutex);
 static LIST_HEAD(edac_pci_list);
+static atomic_t pci_indexes = ATOMIC_INIT(0);
 
 /*
  * edac_pci_alloc_ctl_info
@@ -318,6 +319,19 @@ void edac_pci_reset_delay_period(struct edac_pci_ctl_info *pci,
 EXPORT_SYMBOL_GPL(edac_pci_reset_delay_period);
 
 /*
+ * edac_pci_alloc_index: Allocate a unique PCI index number
+ *
+ * Return:
+ *      allocated index number
+ *
+ */
+int edac_pci_alloc_index(void)
+{
+	return atomic_inc_return(&pci_indexes) - 1;
+}
+EXPORT_SYMBOL_GPL(edac_pci_alloc_index);
+
+/*
  * edac_pci_add_device: Insert the 'edac_dev' structure into the
  * edac_pci global list and create sysfs entries associated with
  * edac_pci structure.
diff --git a/drivers/edac/ppc4xx_edac.c b/drivers/edac/ppc4xx_edac.c
new file mode 100644
index 000000000000..11f2172aa1e6
--- /dev/null
+++ b/drivers/edac/ppc4xx_edac.c
@@ -0,0 +1,1448 @@
+/*
+ * Copyright (c) 2008 Nuovation System Designs, LLC
+ *   Grant Erickson <gerickson@nuovations.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; version 2 of the
+ * License.
+ *
+ */
+
+#include <linux/edac.h>
+#include <linux/interrupt.h>
+#include <linux/irq.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/of_platform.h>
+#include <linux/types.h>
+
+#include <asm/dcr.h>
+
+#include "edac_core.h"
+#include "ppc4xx_edac.h"
+
+/*
+ * This file implements a driver for monitoring and handling events
+ * associated with the IMB DDR2 ECC controller found in the AMCC/IBM
+ * 405EX[r], 440SP, 440SPe, 460EX, 460GT and 460SX.
+ *
+ * As realized in the 405EX[r], this controller features:
+ *
+ *   - Support for registered- and non-registered DDR1 and DDR2 memory.
+ *   - 32-bit or 16-bit memory interface with optional ECC.
+ *
+ *     o ECC support includes:
+ *
+ *       - 4-bit SEC/DED
+ *       - Aligned-nibble error detect
+ *       - Bypass mode
+ *
+ *   - Two (2) memory banks/ranks.
+ *   - Up to 1 GiB per bank/rank in 32-bit mode and up to 512 MiB per
+ *     bank/rank in 16-bit mode.
+ *
+ * As realized in the 440SP and 440SPe, this controller changes/adds:
+ *
+ *   - 64-bit or 32-bit memory interface with optional ECC.
+ *
+ *     o ECC support includes:
+ *
+ *       - 8-bit SEC/DED
+ *       - Aligned-nibble error detect
+ *       - Bypass mode
+ *
+ *   - Up to 4 GiB per bank/rank in 64-bit mode and up to 2 GiB
+ *     per bank/rank in 32-bit mode.
+ *
+ * As realized in the 460EX and 460GT, this controller changes/adds:
+ *
+ *   - 64-bit or 32-bit memory interface with optional ECC.
+ *
+ *     o ECC support includes:
+ *
+ *       - 8-bit SEC/DED
+ *       - Aligned-nibble error detect
+ *       - Bypass mode
+ *
+ *   - Four (4) memory banks/ranks.
+ *   - Up to 16 GiB per bank/rank in 64-bit mode and up to 8 GiB
+ *     per bank/rank in 32-bit mode.
+ *
+ * At present, this driver has ONLY been tested against the controller
+ * realization in the 405EX[r] on the AMCC Kilauea and Haleakala
+ * boards (256 MiB w/o ECC memory soldered onto the board) and a
+ * proprietary board based on those designs (128 MiB ECC memory, also
+ * soldered onto the board).
+ *
+ * Dynamic feature detection and handling needs to be added for the
+ * other realizations of this controller listed above.
+ *
+ * Eventually, this driver will likely be adapted to the above variant
+ * realizations of this controller as well as broken apart to handle
+ * the other known ECC-capable controllers prevalent in other 4xx
+ * processors:
+ *
+ *   - IBM SDRAM (405GP, 405CR and 405EP) "ibm,sdram-4xx"
+ *   - IBM DDR1 (440GP, 440GX, 440EP and 440GR) "ibm,sdram-4xx-ddr"
+ *   - Denali DDR1/DDR2 (440EPX and 440GRX) "denali,sdram-4xx-ddr2"
+ *
+ * For this controller, unfortunately, correctable errors report
+ * nothing more than the beat/cycle and byte/lane the correction
+ * occurred on and the check bit group that covered the error.
+ *
+ * In contrast, uncorrectable errors also report the failing address,
+ * the bus master and the transaction direction (i.e. read or write)
+ *
+ * Regardless of whether the error is a CE or a UE, we report the
+ * following pieces of information in the driver-unique message to the
+ * EDAC subsystem:
+ *
+ *   - Device tree path
+ *   - Bank(s)
+ *   - Check bit error group
+ *   - Beat(s)/lane(s)
+ */
+
+/* Preprocessor Definitions */
+
+#define EDAC_OPSTATE_INT_STR		"interrupt"
+#define EDAC_OPSTATE_POLL_STR		"polled"
+#define EDAC_OPSTATE_UNKNOWN_STR	"unknown"
+
+#define PPC4XX_EDAC_MODULE_NAME		"ppc4xx_edac"
+#define PPC4XX_EDAC_MODULE_REVISION	"v1.0.0 " __DATE__
+
+#define PPC4XX_EDAC_MESSAGE_SIZE	256
+
+/*
+ * Kernel logging without an EDAC instance
+ */
+#define ppc4xx_edac_printk(level, fmt, arg...) \
+	edac_printk(level, "PPC4xx MC", fmt, ##arg)
+
+/*
+ * Kernel logging with an EDAC instance
+ */
+#define ppc4xx_edac_mc_printk(level, mci, fmt, arg...) \
+	edac_mc_chipset_printk(mci, level, "PPC4xx", fmt, ##arg)
+
+/*
+ * Macros to convert bank configuration size enumerations into MiB and
+ * page values.
+ */
+#define SDRAM_MBCF_SZ_MiB_MIN		4
+#define SDRAM_MBCF_SZ_TO_MiB(n)		(SDRAM_MBCF_SZ_MiB_MIN \
+					 << (SDRAM_MBCF_SZ_DECODE(n)))
+#define SDRAM_MBCF_SZ_TO_PAGES(n)	(SDRAM_MBCF_SZ_MiB_MIN \
+					 << (20 - PAGE_SHIFT + \
+					     SDRAM_MBCF_SZ_DECODE(n)))
+
+/*
+ * The ibm,sdram-4xx-ddr2 Device Control Registers (DCRs) are
+ * indirectly acccessed and have a base and length defined by the
+ * device tree. The base can be anything; however, we expect the
+ * length to be precisely two registers, the first for the address
+ * window and the second for the data window.
+ */
+#define SDRAM_DCR_RESOURCE_LEN		2
+#define SDRAM_DCR_ADDR_OFFSET		0
+#define SDRAM_DCR_DATA_OFFSET		1
+
+/*
+ * Device tree interrupt indices
+ */
+#define INTMAP_ECCDED_INDEX		0	/* Double-bit Error Detect */
+#define INTMAP_ECCSEC_INDEX		1	/* Single-bit Error Correct */
+
+/* Type Definitions */
+
+/*
+ * PPC4xx SDRAM memory controller private instance data
+ */
+struct ppc4xx_edac_pdata {
+	dcr_host_t dcr_host;	/* Indirect DCR address/data window mapping */
+	struct {
+		int sec;	/* Single-bit correctable error IRQ assigned */
+		int ded;	/* Double-bit detectable error IRQ assigned */
+	} irqs;
+};
+
+/*
+ * Various status data gathered and manipulated when checking and
+ * reporting ECC status.
+ */
+struct ppc4xx_ecc_status {
+	u32 ecces;
+	u32 besr;
+	u32 bearh;
+	u32 bearl;
+	u32 wmirq;
+};
+
+/* Function Prototypes */
+
+static int ppc4xx_edac_probe(struct of_device *device,
+			     const struct of_device_id *device_id);
+static int ppc4xx_edac_remove(struct of_device *device);
+
+/* Global Variables */
+
+/*
+ * Device tree node type and compatible tuples this driver can match
+ * on.
+ */
+static struct of_device_id ppc4xx_edac_match[] = {
+	{
+		.compatible	= "ibm,sdram-4xx-ddr2"
+	},
+	{ }
+};
+
+static struct of_platform_driver ppc4xx_edac_driver = {
+	.match_table		= ppc4xx_edac_match,
+	.probe			= ppc4xx_edac_probe,
+	.remove			= ppc4xx_edac_remove,
+	.driver			= {
+		.owner	= THIS_MODULE,
+		.name	= PPC4XX_EDAC_MODULE_NAME
+	}
+};
+
+/*
+ * TODO: The row and channel parameters likely need to be dynamically
+ * set based on the aforementioned variant controller realizations.
+ */
+static const unsigned ppc4xx_edac_nr_csrows = 2;
+static const unsigned ppc4xx_edac_nr_chans = 1;
+
+/*
+ * Strings associated with PLB master IDs capable of being posted in
+ * SDRAM_BESR or SDRAM_WMIRQ on uncorrectable ECC errors.
+ */
+static const char * const ppc4xx_plb_masters[9] = {
+	[SDRAM_PLB_M0ID_ICU]	= "ICU",
+	[SDRAM_PLB_M0ID_PCIE0]	= "PCI-E 0",
+	[SDRAM_PLB_M0ID_PCIE1]	= "PCI-E 1",
+	[SDRAM_PLB_M0ID_DMA]	= "DMA",
+	[SDRAM_PLB_M0ID_DCU]	= "DCU",
+	[SDRAM_PLB_M0ID_OPB]	= "OPB",
+	[SDRAM_PLB_M0ID_MAL]	= "MAL",
+	[SDRAM_PLB_M0ID_SEC]	= "SEC",
+	[SDRAM_PLB_M0ID_AHB]	= "AHB"
+};
+
+/**
+ * mfsdram - read and return controller register data
+ * @dcr_host: A pointer to the DCR mapping.
+ * @idcr_n: The indirect DCR register to read.
+ *
+ * This routine reads and returns the data associated with the
+ * controller's specified indirect DCR register.
+ *
+ * Returns the read data.
+ */
+static inline u32
+mfsdram(const dcr_host_t *dcr_host, unsigned int idcr_n)
+{
+	return __mfdcri(dcr_host->base + SDRAM_DCR_ADDR_OFFSET,
+			dcr_host->base + SDRAM_DCR_DATA_OFFSET,
+			idcr_n);
+}
+
+/**
+ * mtsdram - write controller register data
+ * @dcr_host: A pointer to the DCR mapping.
+ * @idcr_n: The indirect DCR register to write.
+ * @value: The data to write.
+ *
+ * This routine writes the provided data to the controller's specified
+ * indirect DCR register.
+ */
+static inline void
+mtsdram(const dcr_host_t *dcr_host, unsigned int idcr_n, u32 value)
+{
+	return __mtdcri(dcr_host->base + SDRAM_DCR_ADDR_OFFSET,
+			dcr_host->base + SDRAM_DCR_DATA_OFFSET,
+			idcr_n,
+			value);
+}
+
+/**
+ * ppc4xx_edac_check_bank_error - check a bank for an ECC bank error
+ * @status: A pointer to the ECC status structure to check for an
+ *          ECC bank error.
+ * @bank: The bank to check for an ECC error.
+ *
+ * This routine determines whether the specified bank has an ECC
+ * error.
+ *
+ * Returns true if the specified bank has an ECC error; otherwise,
+ * false.
+ */
+static bool
+ppc4xx_edac_check_bank_error(const struct ppc4xx_ecc_status *status,
+			     unsigned int bank)
+{
+	switch (bank) {
+	case 0:
+		return status->ecces & SDRAM_ECCES_BK0ER;
+	case 1:
+		return status->ecces & SDRAM_ECCES_BK1ER;
+	default:
+		return false;
+	}
+}
+
+/**
+ * ppc4xx_edac_generate_bank_message - generate interpretted bank status message
+ * @mci: A pointer to the EDAC memory controller instance associated
+ *       with the bank message being generated.
+ * @status: A pointer to the ECC status structure to generate the
+ *          message from.
+ * @buffer: A pointer to the buffer in which to generate the
+ *          message.
+ * @size: The size, in bytes, of space available in buffer.
+ *
+ * This routine generates to the provided buffer the portion of the
+ * driver-unique report message associated with the ECCESS[BKNER]
+ * field of the specified ECC status.
+ *
+ * Returns the number of characters generated on success; otherwise, <
+ * 0 on error.
+ */
+static int
+ppc4xx_edac_generate_bank_message(const struct mem_ctl_info *mci,
+				  const struct ppc4xx_ecc_status *status,
+				  char *buffer,
+				  size_t size)
+{
+	int n, total = 0;
+	unsigned int row, rows;
+
+	n = snprintf(buffer, size, "%s: Banks: ", mci->dev_name);
+
+	if (n < 0 || n >= size)
+		goto fail;
+
+	buffer += n;
+	size -= n;
+	total += n;
+
+	for (rows = 0, row = 0; row < mci->nr_csrows; row++) {
+		if (ppc4xx_edac_check_bank_error(status, row)) {
+			n = snprintf(buffer, size, "%s%u",
+					(rows++ ? ", " : ""), row);
+
+			if (n < 0 || n >= size)
+				goto fail;
+
+			buffer += n;
+			size -= n;
+			total += n;
+		}
+	}
+
+	n = snprintf(buffer, size, "%s; ", rows ? "" : "None");
+
+	if (n < 0 || n >= size)
+		goto fail;
+
+	buffer += n;
+	size -= n;
+	total += n;
+
+ fail:
+	return total;
+}
+
+/**
+ * ppc4xx_edac_generate_checkbit_message - generate interpretted checkbit message
+ * @mci: A pointer to the EDAC memory controller instance associated
+ *       with the checkbit message being generated.
+ * @status: A pointer to the ECC status structure to generate the
+ *          message from.
+ * @buffer: A pointer to the buffer in which to generate the
+ *          message.
+ * @size: The size, in bytes, of space available in buffer.
+ *
+ * This routine generates to the provided buffer the portion of the
+ * driver-unique report message associated with the ECCESS[CKBER]
+ * field of the specified ECC status.
+ *
+ * Returns the number of characters generated on success; otherwise, <
+ * 0 on error.
+ */
+static int
+ppc4xx_edac_generate_checkbit_message(const struct mem_ctl_info *mci,
+				      const struct ppc4xx_ecc_status *status,
+				      char *buffer,
+				      size_t size)
+{
+	const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
+	const char *ckber = NULL;
+
+	switch (status->ecces & SDRAM_ECCES_CKBER_MASK) {
+	case SDRAM_ECCES_CKBER_NONE:
+		ckber = "None";
+		break;
+	case SDRAM_ECCES_CKBER_32_ECC_0_3:
+		ckber = "ECC0:3";
+		break;
+	case SDRAM_ECCES_CKBER_32_ECC_4_8:
+		switch (mfsdram(&pdata->dcr_host, SDRAM_MCOPT1) &
+			SDRAM_MCOPT1_WDTH_MASK) {
+		case SDRAM_MCOPT1_WDTH_16:
+			ckber = "ECC0:3";
+			break;
+		case SDRAM_MCOPT1_WDTH_32:
+			ckber = "ECC4:8";
+			break;
+		default:
+			ckber = "Unknown";
+			break;
+		}
+		break;
+	case SDRAM_ECCES_CKBER_32_ECC_0_8:
+		ckber = "ECC0:8";
+		break;
+	default:
+		ckber = "Unknown";
+		break;
+	}
+
+	return snprintf(buffer, size, "Checkbit Error: %s", ckber);
+}
+
+/**
+ * ppc4xx_edac_generate_lane_message - generate interpretted byte lane message
+ * @mci: A pointer to the EDAC memory controller instance associated
+ *       with the byte lane message being generated.
+ * @status: A pointer to the ECC status structure to generate the
+ *          message from.
+ * @buffer: A pointer to the buffer in which to generate the
+ *          message.
+ * @size: The size, in bytes, of space available in buffer.
+ *
+ * This routine generates to the provided buffer the portion of the
+ * driver-unique report message associated with the ECCESS[BNCE]
+ * field of the specified ECC status.
+ *
+ * Returns the number of characters generated on success; otherwise, <
+ * 0 on error.
+ */
+static int
+ppc4xx_edac_generate_lane_message(const struct mem_ctl_info *mci,
+				  const struct ppc4xx_ecc_status *status,
+				  char *buffer,
+				  size_t size)
+{
+	int n, total = 0;
+	unsigned int lane, lanes;
+	const unsigned int first_lane = 0;
+	const unsigned int lane_count = 16;
+
+	n = snprintf(buffer, size, "; Byte Lane Errors: ");
+
+	if (n < 0 || n >= size)
+		goto fail;
+
+	buffer += n;
+	size -= n;
+	total += n;
+
+	for (lanes = 0, lane = first_lane; lane < lane_count; lane++) {
+		if ((status->ecces & SDRAM_ECCES_BNCE_ENCODE(lane)) != 0) {
+			n = snprintf(buffer, size,
+				     "%s%u",
+				     (lanes++ ? ", " : ""), lane);
+
+			if (n < 0 || n >= size)
+				goto fail;
+
+			buffer += n;
+			size -= n;
+			total += n;
+		}
+	}
+
+	n = snprintf(buffer, size, "%s; ", lanes ? "" : "None");
+
+	if (n < 0 || n >= size)
+		goto fail;
+
+	buffer += n;
+	size -= n;
+	total += n;
+
+ fail:
+	return total;
+}
+
+/**
+ * ppc4xx_edac_generate_ecc_message - generate interpretted ECC status message
+ * @mci: A pointer to the EDAC memory controller instance associated
+ *       with the ECCES message being generated.
+ * @status: A pointer to the ECC status structure to generate the
+ *          message from.
+ * @buffer: A pointer to the buffer in which to generate the
+ *          message.
+ * @size: The size, in bytes, of space available in buffer.
+ *
+ * This routine generates to the provided buffer the portion of the
+ * driver-unique report message associated with the ECCESS register of
+ * the specified ECC status.
+ *
+ * Returns the number of characters generated on success; otherwise, <
+ * 0 on error.
+ */
+static int
+ppc4xx_edac_generate_ecc_message(const struct mem_ctl_info *mci,
+				 const struct ppc4xx_ecc_status *status,
+				 char *buffer,
+				 size_t size)
+{
+	int n, total = 0;
+
+	n = ppc4xx_edac_generate_bank_message(mci, status, buffer, size);
+
+	if (n < 0 || n >= size)
+		goto fail;
+
+	buffer += n;
+	size -= n;
+	total += n;
+
+	n = ppc4xx_edac_generate_checkbit_message(mci, status, buffer, size);
+
+	if (n < 0 || n >= size)
+		goto fail;
+
+	buffer += n;
+	size -= n;
+	total += n;
+
+	n = ppc4xx_edac_generate_lane_message(mci, status, buffer, size);
+
+	if (n < 0 || n >= size)
+		goto fail;
+
+	buffer += n;
+	size -= n;
+	total += n;
+
+ fail:
+	return total;
+}
+
+/**
+ * ppc4xx_edac_generate_plb_message - generate interpretted PLB status message
+ * @mci: A pointer to the EDAC memory controller instance associated
+ *       with the PLB message being generated.
+ * @status: A pointer to the ECC status structure to generate the
+ *          message from.
+ * @buffer: A pointer to the buffer in which to generate the
+ *          message.
+ * @size: The size, in bytes, of space available in buffer.
+ *
+ * This routine generates to the provided buffer the portion of the
+ * driver-unique report message associated with the PLB-related BESR
+ * and/or WMIRQ registers of the specified ECC status.
+ *
+ * Returns the number of characters generated on success; otherwise, <
+ * 0 on error.
+ */
+static int
+ppc4xx_edac_generate_plb_message(const struct mem_ctl_info *mci,
+				 const struct ppc4xx_ecc_status *status,
+				 char *buffer,
+				 size_t size)
+{
+	unsigned int master;
+	bool read;
+
+	if ((status->besr & SDRAM_BESR_MASK) == 0)
+		return 0;
+
+	if ((status->besr & SDRAM_BESR_M0ET_MASK) == SDRAM_BESR_M0ET_NONE)
+		return 0;
+
+	read = ((status->besr & SDRAM_BESR_M0RW_MASK) == SDRAM_BESR_M0RW_READ);
+
+	master = SDRAM_BESR_M0ID_DECODE(status->besr);
+
+	return snprintf(buffer, size,
+			"%s error w/ PLB master %u \"%s\"; ",
+			(read ? "Read" : "Write"),
+			master,
+			(((master >= SDRAM_PLB_M0ID_FIRST) &&
+			  (master <= SDRAM_PLB_M0ID_LAST)) ?
+			 ppc4xx_plb_masters[master] : "UNKNOWN"));
+}
+
+/**
+ * ppc4xx_edac_generate_message - generate interpretted status message
+ * @mci: A pointer to the EDAC memory controller instance associated
+ *       with the driver-unique message being generated.
+ * @status: A pointer to the ECC status structure to generate the
+ *          message from.
+ * @buffer: A pointer to the buffer in which to generate the
+ *          message.
+ * @size: The size, in bytes, of space available in buffer.
+ *
+ * This routine generates to the provided buffer the driver-unique
+ * EDAC report message from the specified ECC status.
+ */
+static void
+ppc4xx_edac_generate_message(const struct mem_ctl_info *mci,
+			     const struct ppc4xx_ecc_status *status,
+			     char *buffer,
+			     size_t size)
+{
+	int n;
+
+	if (buffer == NULL || size == 0)
+		return;
+
+	n = ppc4xx_edac_generate_ecc_message(mci, status, buffer, size);
+
+	if (n < 0 || n >= size)
+		return;
+
+	buffer += n;
+	size -= n;
+
+	ppc4xx_edac_generate_plb_message(mci, status, buffer, size);
+}
+
+#ifdef DEBUG
+/**
+ * ppc4xx_ecc_dump_status - dump controller ECC status registers
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the status being dumped.
+ * @status: A pointer to the ECC status structure to generate the
+ *          dump from.
+ *
+ * This routine dumps to the kernel log buffer the raw and
+ * interpretted specified ECC status.
+ */
+static void
+ppc4xx_ecc_dump_status(const struct mem_ctl_info *mci,
+		       const struct ppc4xx_ecc_status *status)
+{
+	char message[PPC4XX_EDAC_MESSAGE_SIZE];
+
+	ppc4xx_edac_generate_message(mci, status, message, sizeof(message));
+
+	ppc4xx_edac_mc_printk(KERN_INFO, mci,
+			      "\n"
+			      "\tECCES: 0x%08x\n"
+			      "\tWMIRQ: 0x%08x\n"
+			      "\tBESR:  0x%08x\n"
+			      "\tBEAR:  0x%08x%08x\n"
+			      "\t%s\n",
+			      status->ecces,
+			      status->wmirq,
+			      status->besr,
+			      status->bearh,
+			      status->bearl,
+			      message);
+}
+#endif /* DEBUG */
+
+/**
+ * ppc4xx_ecc_get_status - get controller ECC status
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the status being retrieved.
+ * @status: A pointer to the ECC status structure to populate the
+ *          ECC status with.
+ *
+ * This routine reads and masks, as appropriate, all the relevant
+ * status registers that deal with ibm,sdram-4xx-ddr2 ECC errors.
+ * While we read all of them, for correctable errors, we only expect
+ * to deal with ECCES. For uncorrectable errors, we expect to deal
+ * with all of them.
+ */
+static void
+ppc4xx_ecc_get_status(const struct mem_ctl_info *mci,
+		      struct ppc4xx_ecc_status *status)
+{
+	const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
+	const dcr_host_t *dcr_host = &pdata->dcr_host;
+
+	status->ecces = mfsdram(dcr_host, SDRAM_ECCES) & SDRAM_ECCES_MASK;
+	status->wmirq = mfsdram(dcr_host, SDRAM_WMIRQ) & SDRAM_WMIRQ_MASK;
+	status->besr  = mfsdram(dcr_host, SDRAM_BESR)  & SDRAM_BESR_MASK;
+	status->bearl = mfsdram(dcr_host, SDRAM_BEARL);
+	status->bearh = mfsdram(dcr_host, SDRAM_BEARH);
+}
+
+/**
+ * ppc4xx_ecc_clear_status - clear controller ECC status
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the status being cleared.
+ * @status: A pointer to the ECC status structure containing the
+ *          values to write to clear the ECC status.
+ *
+ * This routine clears--by writing the masked (as appropriate) status
+ * values back to--the status registers that deal with
+ * ibm,sdram-4xx-ddr2 ECC errors.
+ */
+static void
+ppc4xx_ecc_clear_status(const struct mem_ctl_info *mci,
+			const struct ppc4xx_ecc_status *status)
+{
+	const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
+	const dcr_host_t *dcr_host = &pdata->dcr_host;
+
+	mtsdram(dcr_host, SDRAM_ECCES,	status->ecces & SDRAM_ECCES_MASK);
+	mtsdram(dcr_host, SDRAM_WMIRQ,	status->wmirq & SDRAM_WMIRQ_MASK);
+	mtsdram(dcr_host, SDRAM_BESR,	status->besr & SDRAM_BESR_MASK);
+	mtsdram(dcr_host, SDRAM_BEARL,	0);
+	mtsdram(dcr_host, SDRAM_BEARH,	0);
+}
+
+/**
+ * ppc4xx_edac_handle_ce - handle controller correctable ECC error (CE)
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the correctable error being handled and reported.
+ * @status: A pointer to the ECC status structure associated with
+ *          the correctable error being handled and reported.
+ *
+ * This routine handles an ibm,sdram-4xx-ddr2 controller ECC
+ * correctable error. Per the aforementioned discussion, there's not
+ * enough status available to use the full EDAC correctable error
+ * interface, so we just pass driver-unique message to the "no info"
+ * interface.
+ */
+static void
+ppc4xx_edac_handle_ce(struct mem_ctl_info *mci,
+		      const struct ppc4xx_ecc_status *status)
+{
+	int row;
+	char message[PPC4XX_EDAC_MESSAGE_SIZE];
+
+	ppc4xx_edac_generate_message(mci, status, message, sizeof(message));
+
+	for (row = 0; row < mci->nr_csrows; row++)
+		if (ppc4xx_edac_check_bank_error(status, row))
+			edac_mc_handle_ce_no_info(mci, message);
+}
+
+/**
+ * ppc4xx_edac_handle_ue - handle controller uncorrectable ECC error (UE)
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the uncorrectable error being handled and
+ *       reported.
+ * @status: A pointer to the ECC status structure associated with
+ *          the uncorrectable error being handled and reported.
+ *
+ * This routine handles an ibm,sdram-4xx-ddr2 controller ECC
+ * uncorrectable error.
+ */
+static void
+ppc4xx_edac_handle_ue(struct mem_ctl_info *mci,
+		      const struct ppc4xx_ecc_status *status)
+{
+	const u64 bear = ((u64)status->bearh << 32 | status->bearl);
+	const unsigned long page = bear >> PAGE_SHIFT;
+	const unsigned long offset = bear & ~PAGE_MASK;
+	int row;
+	char message[PPC4XX_EDAC_MESSAGE_SIZE];
+
+	ppc4xx_edac_generate_message(mci, status, message, sizeof(message));
+
+	for (row = 0; row < mci->nr_csrows; row++)
+		if (ppc4xx_edac_check_bank_error(status, row))
+			edac_mc_handle_ue(mci, page, offset, row, message);
+}
+
+/**
+ * ppc4xx_edac_check - check controller for ECC errors
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the ibm,sdram-4xx-ddr2 controller being
+ *       checked.
+ *
+ * This routine is used to check and post ECC errors and is called by
+ * both the EDAC polling thread and this driver's CE and UE interrupt
+ * handler.
+ */
+static void
+ppc4xx_edac_check(struct mem_ctl_info *mci)
+{
+#ifdef DEBUG
+	static unsigned int count;
+#endif
+	struct ppc4xx_ecc_status status;
+
+	ppc4xx_ecc_get_status(mci, &status);
+
+#ifdef DEBUG
+	if (count++ % 30 == 0)
+		ppc4xx_ecc_dump_status(mci, &status);
+#endif
+
+	if (status.ecces & SDRAM_ECCES_UE)
+		ppc4xx_edac_handle_ue(mci, &status);
+
+	if (status.ecces & SDRAM_ECCES_CE)
+		ppc4xx_edac_handle_ce(mci, &status);
+
+	ppc4xx_ecc_clear_status(mci, &status);
+}
+
+/**
+ * ppc4xx_edac_isr - SEC (CE) and DED (UE) interrupt service routine
+ * @irq:    The virtual interrupt number being serviced.
+ * @dev_id: A pointer to the EDAC memory controller instance
+ *          associated with the interrupt being handled.
+ *
+ * This routine implements the interrupt handler for both correctable
+ * (CE) and uncorrectable (UE) ECC errors for the ibm,sdram-4xx-ddr2
+ * controller. It simply calls through to the same routine used during
+ * polling to check, report and clear the ECC status.
+ *
+ * Unconditionally returns IRQ_HANDLED.
+ */
+static irqreturn_t
+ppc4xx_edac_isr(int irq, void *dev_id)
+{
+	struct mem_ctl_info *mci = dev_id;
+
+	ppc4xx_edac_check(mci);
+
+	return IRQ_HANDLED;
+}
+
+/**
+ * ppc4xx_edac_get_dtype - return the controller memory width
+ * @mcopt1: The 32-bit Memory Controller Option 1 register value
+ *          currently set for the controller, from which the width
+ *          is derived.
+ *
+ * This routine returns the EDAC device type width appropriate for the
+ * current controller configuration.
+ *
+ * TODO: This needs to be conditioned dynamically through feature
+ * flags or some such when other controller variants are supported as
+ * the 405EX[r] is 16-/32-bit and the others are 32-/64-bit with the
+ * 16- and 64-bit field definition/value/enumeration (b1) overloaded
+ * among them.
+ *
+ * Returns a device type width enumeration.
+ */
+static enum dev_type __devinit
+ppc4xx_edac_get_dtype(u32 mcopt1)
+{
+	switch (mcopt1 & SDRAM_MCOPT1_WDTH_MASK) {
+	case SDRAM_MCOPT1_WDTH_16:
+		return DEV_X2;
+	case SDRAM_MCOPT1_WDTH_32:
+		return DEV_X4;
+	default:
+		return DEV_UNKNOWN;
+	}
+}
+
+/**
+ * ppc4xx_edac_get_mtype - return controller memory type
+ * @mcopt1: The 32-bit Memory Controller Option 1 register value
+ *          currently set for the controller, from which the memory type
+ *          is derived.
+ *
+ * This routine returns the EDAC memory type appropriate for the
+ * current controller configuration.
+ *
+ * Returns a memory type enumeration.
+ */
+static enum mem_type __devinit
+ppc4xx_edac_get_mtype(u32 mcopt1)
+{
+	bool rden = ((mcopt1 & SDRAM_MCOPT1_RDEN_MASK) == SDRAM_MCOPT1_RDEN);
+
+	switch (mcopt1 & SDRAM_MCOPT1_DDR_TYPE_MASK) {
+	case SDRAM_MCOPT1_DDR2_TYPE:
+		return rden ? MEM_RDDR2 : MEM_DDR2;
+	case SDRAM_MCOPT1_DDR1_TYPE:
+		return rden ? MEM_RDDR : MEM_DDR;
+	default:
+		return MEM_UNKNOWN;
+	}
+}
+
+/**
+ * ppc4xx_edac_init_csrows - intialize driver instance rows
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the ibm,sdram-4xx-ddr2 controller for which
+ *       the csrows (i.e. banks/ranks) are being initialized.
+ * @mcopt1: The 32-bit Memory Controller Option 1 register value
+ *          currently set for the controller, from which bank width
+ *          and memory typ information is derived.
+ *
+ * This routine intializes the virtual "chip select rows" associated
+ * with the EDAC memory controller instance. An ibm,sdram-4xx-ddr2
+ * controller bank/rank is mapped to a row.
+ *
+ * Returns 0 if OK; otherwise, -EINVAL if the memory bank size
+ * configuration cannot be determined.
+ */
+static int __devinit
+ppc4xx_edac_init_csrows(struct mem_ctl_info *mci, u32 mcopt1)
+{
+	const struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
+	int status = 0;
+	enum mem_type mtype;
+	enum dev_type dtype;
+	enum edac_type edac_mode;
+	int row;
+	u32 mbxcf, size;
+	static u32 ppc4xx_last_page;
+
+	/* Establish the memory type and width */
+
+	mtype = ppc4xx_edac_get_mtype(mcopt1);
+	dtype = ppc4xx_edac_get_dtype(mcopt1);
+
+	/* Establish EDAC mode */
+
+	if (mci->edac_cap & EDAC_FLAG_SECDED)
+		edac_mode = EDAC_SECDED;
+	else if (mci->edac_cap & EDAC_FLAG_EC)
+		edac_mode = EDAC_EC;
+	else
+		edac_mode = EDAC_NONE;
+
+	/*
+	 * Initialize each chip select row structure which correspond
+	 * 1:1 with a controller bank/rank.
+	 */
+
+	for (row = 0; row < mci->nr_csrows; row++) {
+		struct csrow_info *csi = &mci->csrows[row];
+
+		/*
+		 * Get the configuration settings for this
+		 * row/bank/rank and skip disabled banks.
+		 */
+
+		mbxcf = mfsdram(&pdata->dcr_host, SDRAM_MBXCF(row));
+
+		if ((mbxcf & SDRAM_MBCF_BE_MASK) != SDRAM_MBCF_BE_ENABLE)
+			continue;
+
+		/* Map the bank configuration size setting to pages. */
+
+		size = mbxcf & SDRAM_MBCF_SZ_MASK;
+
+		switch (size) {
+		case SDRAM_MBCF_SZ_4MB:
+		case SDRAM_MBCF_SZ_8MB:
+		case SDRAM_MBCF_SZ_16MB:
+		case SDRAM_MBCF_SZ_32MB:
+		case SDRAM_MBCF_SZ_64MB:
+		case SDRAM_MBCF_SZ_128MB:
+		case SDRAM_MBCF_SZ_256MB:
+		case SDRAM_MBCF_SZ_512MB:
+		case SDRAM_MBCF_SZ_1GB:
+		case SDRAM_MBCF_SZ_2GB:
+		case SDRAM_MBCF_SZ_4GB:
+		case SDRAM_MBCF_SZ_8GB:
+			csi->nr_pages = SDRAM_MBCF_SZ_TO_PAGES(size);
+			break;
+		default:
+			ppc4xx_edac_mc_printk(KERN_ERR, mci,
+					      "Unrecognized memory bank %d "
+					      "size 0x%08x\n",
+					      row, SDRAM_MBCF_SZ_DECODE(size));
+			status = -EINVAL;
+			goto done;
+		}
+
+		csi->first_page = ppc4xx_last_page;
+		csi->last_page	= csi->first_page + csi->nr_pages - 1;
+		csi->page_mask	= 0;
+
+		/*
+		 * It's unclear exactly what grain should be set to
+		 * here. The SDRAM_ECCES register allows resolution of
+		 * an error down to a nibble which would potentially
+		 * argue for a grain of '1' byte, even though we only
+		 * know the associated address for uncorrectable
+		 * errors. This value is not used at present for
+		 * anything other than error reporting so getting it
+		 * wrong should be of little consequence. Other
+		 * possible values would be the PLB width (16), the
+		 * page size (PAGE_SIZE) or the memory width (2 or 4).
+		 */
+
+		csi->grain	= 1;
+
+		csi->mtype	= mtype;
+		csi->dtype	= dtype;
+
+		csi->edac_mode	= edac_mode;
+
+		ppc4xx_last_page += csi->nr_pages;
+	}
+
+ done:
+	return status;
+}
+
+/**
+ * ppc4xx_edac_mc_init - intialize driver instance
+ * @mci: A pointer to the EDAC memory controller instance being
+ *       initialized.
+ * @op: A pointer to the OpenFirmware device tree node associated
+ *      with the controller this EDAC instance is bound to.
+ * @match: A pointer to the OpenFirmware device tree match
+ *         information associated with the controller this EDAC instance
+ *         is bound to.
+ * @dcr_host: A pointer to the DCR data containing the DCR mapping
+ *            for this controller instance.
+ * @mcopt1: The 32-bit Memory Controller Option 1 register value
+ *          currently set for the controller, from which ECC capabilities
+ *          and scrub mode are derived.
+ *
+ * This routine performs initialization of the EDAC memory controller
+ * instance and related driver-private data associated with the
+ * ibm,sdram-4xx-ddr2 memory controller the instance is bound to.
+ *
+ * Returns 0 if OK; otherwise, < 0 on error.
+ */
+static int __devinit
+ppc4xx_edac_mc_init(struct mem_ctl_info *mci,
+		    struct of_device *op,
+		    const struct of_device_id *match,
+		    const dcr_host_t *dcr_host,
+		    u32 mcopt1)
+{
+	int status = 0;
+	const u32 memcheck = (mcopt1 & SDRAM_MCOPT1_MCHK_MASK);
+	struct ppc4xx_edac_pdata *pdata = NULL;
+	const struct device_node *np = op->node;
+
+	if (match == NULL)
+		return -EINVAL;
+
+	/* Initial driver pointers and private data */
+
+	mci->dev		= &op->dev;
+
+	dev_set_drvdata(mci->dev, mci);
+
+	pdata			= mci->pvt_info;
+
+	pdata->dcr_host		= *dcr_host;
+	pdata->irqs.sec		= NO_IRQ;
+	pdata->irqs.ded		= NO_IRQ;
+
+	/* Initialize controller capabilities and configuration */
+
+	mci->mtype_cap		= (MEM_FLAG_DDR | MEM_FLAG_RDDR |
+				   MEM_FLAG_DDR2 | MEM_FLAG_RDDR2);
+
+	mci->edac_ctl_cap	= (EDAC_FLAG_NONE |
+				   EDAC_FLAG_EC |
+				   EDAC_FLAG_SECDED);
+
+	mci->scrub_cap		= SCRUB_NONE;
+	mci->scrub_mode		= SCRUB_NONE;
+
+	/*
+	 * Update the actual capabilites based on the MCOPT1[MCHK]
+	 * settings. Scrubbing is only useful if reporting is enabled.
+	 */
+
+	switch (memcheck) {
+	case SDRAM_MCOPT1_MCHK_CHK:
+		mci->edac_cap	= EDAC_FLAG_EC;
+		break;
+	case SDRAM_MCOPT1_MCHK_CHK_REP:
+		mci->edac_cap	= (EDAC_FLAG_EC | EDAC_FLAG_SECDED);
+		mci->scrub_mode	= SCRUB_SW_SRC;
+		break;
+	default:
+		mci->edac_cap	= EDAC_FLAG_NONE;
+		break;
+	}
+
+	/* Initialize strings */
+
+	mci->mod_name		= PPC4XX_EDAC_MODULE_NAME;
+	mci->mod_ver		= PPC4XX_EDAC_MODULE_REVISION;
+	mci->ctl_name		= match->compatible,
+	mci->dev_name		= np->full_name;
+
+	/* Initialize callbacks */
+
+	mci->edac_check		= ppc4xx_edac_check;
+	mci->ctl_page_to_phys	= NULL;
+
+	/* Initialize chip select rows */
+
+	status = ppc4xx_edac_init_csrows(mci, mcopt1);
+
+	if (status)
+		ppc4xx_edac_mc_printk(KERN_ERR, mci,
+				      "Failed to initialize rows!\n");
+
+	return status;
+}
+
+/**
+ * ppc4xx_edac_register_irq - setup and register controller interrupts
+ * @op: A pointer to the OpenFirmware device tree node associated
+ *      with the controller this EDAC instance is bound to.
+ * @mci: A pointer to the EDAC memory controller instance
+ *       associated with the ibm,sdram-4xx-ddr2 controller for which
+ *       interrupts are being registered.
+ *
+ * This routine parses the correctable (CE) and uncorrectable error (UE)
+ * interrupts from the device tree node and maps and assigns them to
+ * the associated EDAC memory controller instance.
+ *
+ * Returns 0 if OK; otherwise, -ENODEV if the interrupts could not be
+ * mapped and assigned.
+ */
+static int __devinit
+ppc4xx_edac_register_irq(struct of_device *op, struct mem_ctl_info *mci)
+{
+	int status = 0;
+	int ded_irq, sec_irq;
+	struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
+	struct device_node *np = op->node;
+
+	ded_irq = irq_of_parse_and_map(np, INTMAP_ECCDED_INDEX);
+	sec_irq = irq_of_parse_and_map(np, INTMAP_ECCSEC_INDEX);
+
+	if (ded_irq == NO_IRQ || sec_irq == NO_IRQ) {
+		ppc4xx_edac_mc_printk(KERN_ERR, mci,
+				      "Unable to map interrupts.\n");
+		status = -ENODEV;
+		goto fail;
+	}
+
+	status = request_irq(ded_irq,
+			     ppc4xx_edac_isr,
+			     IRQF_DISABLED,
+			     "[EDAC] MC ECCDED",
+			     mci);
+
+	if (status < 0) {
+		ppc4xx_edac_mc_printk(KERN_ERR, mci,
+				      "Unable to request irq %d for ECC DED",
+				      ded_irq);
+		status = -ENODEV;
+		goto fail1;
+	}
+
+	status = request_irq(sec_irq,
+			     ppc4xx_edac_isr,
+			     IRQF_DISABLED,
+			     "[EDAC] MC ECCSEC",
+			     mci);
+
+	if (status < 0) {
+		ppc4xx_edac_mc_printk(KERN_ERR, mci,
+				      "Unable to request irq %d for ECC SEC",
+				      sec_irq);
+		status = -ENODEV;
+		goto fail2;
+	}
+
+	ppc4xx_edac_mc_printk(KERN_INFO, mci, "ECCDED irq is %d\n", ded_irq);
+	ppc4xx_edac_mc_printk(KERN_INFO, mci, "ECCSEC irq is %d\n", sec_irq);
+
+	pdata->irqs.ded = ded_irq;
+	pdata->irqs.sec = sec_irq;
+
+	return 0;
+
+ fail2:
+	free_irq(sec_irq, mci);
+
+ fail1:
+	free_irq(ded_irq, mci);
+
+ fail:
+	return status;
+}
+
+/**
+ * ppc4xx_edac_map_dcrs - locate and map controller registers
+ * @np: A pointer to the device tree node containing the DCR
+ *      resources to map.
+ * @dcr_host: A pointer to the DCR data to populate with the
+ *            DCR mapping.
+ *
+ * This routine attempts to locate in the device tree and map the DCR
+ * register resources associated with the controller's indirect DCR
+ * address and data windows.
+ *
+ * Returns 0 if the DCRs were successfully mapped; otherwise, < 0 on
+ * error.
+ */
+static int __devinit
+ppc4xx_edac_map_dcrs(const struct device_node *np, dcr_host_t *dcr_host)
+{
+	unsigned int dcr_base, dcr_len;
+
+	if (np == NULL || dcr_host == NULL)
+		return -EINVAL;
+
+	/* Get the DCR resource extent and sanity check the values. */
+
+	dcr_base = dcr_resource_start(np, 0);
+	dcr_len = dcr_resource_len(np, 0);
+
+	if (dcr_base == 0 || dcr_len == 0) {
+		ppc4xx_edac_printk(KERN_ERR,
+				   "Failed to obtain DCR property.\n");
+		return -ENODEV;
+	}
+
+	if (dcr_len != SDRAM_DCR_RESOURCE_LEN) {
+		ppc4xx_edac_printk(KERN_ERR,
+				   "Unexpected DCR length %d, expected %d.\n",
+				   dcr_len, SDRAM_DCR_RESOURCE_LEN);
+		return -ENODEV;
+	}
+
+	/*  Attempt to map the DCR extent. */
+
+	*dcr_host = dcr_map(np, dcr_base, dcr_len);
+
+	if (!DCR_MAP_OK(*dcr_host)) {
+		ppc4xx_edac_printk(KERN_INFO, "Failed to map DCRs.\n");
+		    return -ENODEV;
+	}
+
+	return 0;
+}
+
+/**
+ * ppc4xx_edac_probe - check controller and bind driver
+ * @op: A pointer to the OpenFirmware device tree node associated
+ *      with the controller being probed for driver binding.
+ * @match: A pointer to the OpenFirmware device tree match
+ *         information associated with the controller being probed
+ *         for driver binding.
+ *
+ * This routine probes a specific ibm,sdram-4xx-ddr2 controller
+ * instance for binding with the driver.
+ *
+ * Returns 0 if the controller instance was successfully bound to the
+ * driver; otherwise, < 0 on error.
+ */
+static int __devinit
+ppc4xx_edac_probe(struct of_device *op, const struct of_device_id *match)
+{
+	int status = 0;
+	u32 mcopt1, memcheck;
+	dcr_host_t dcr_host;
+	const struct device_node *np = op->node;
+	struct mem_ctl_info *mci = NULL;
+	static int ppc4xx_edac_instance;
+
+	/*
+	 * At this point, we only support the controller realized on
+	 * the AMCC PPC 405EX[r]. Reject anything else.
+	 */
+
+	if (!of_device_is_compatible(np, "ibm,sdram-405ex") &&
+	    !of_device_is_compatible(np, "ibm,sdram-405exr")) {
+		ppc4xx_edac_printk(KERN_NOTICE,
+				   "Only the PPC405EX[r] is supported.\n");
+		return -ENODEV;
+	}
+
+	/*
+	 * Next, get the DCR property and attempt to map it so that we
+	 * can probe the controller.
+	 */
+
+	status = ppc4xx_edac_map_dcrs(np, &dcr_host);
+
+	if (status)
+		return status;
+
+	/*
+	 * First determine whether ECC is enabled at all. If not,
+	 * there is no useful checking or monitoring that can be done
+	 * for this controller.
+	 */
+
+	mcopt1 = mfsdram(&dcr_host, SDRAM_MCOPT1);
+	memcheck = (mcopt1 & SDRAM_MCOPT1_MCHK_MASK);
+
+	if (memcheck == SDRAM_MCOPT1_MCHK_NON) {
+		ppc4xx_edac_printk(KERN_INFO, "%s: No ECC memory detected or "
+				   "ECC is disabled.\n", np->full_name);
+		status = -ENODEV;
+		goto done;
+	}
+
+	/*
+	 * At this point, we know ECC is enabled, allocate an EDAC
+	 * controller instance and perform the appropriate
+	 * initialization.
+	 */
+
+	mci = edac_mc_alloc(sizeof(struct ppc4xx_edac_pdata),
+			    ppc4xx_edac_nr_csrows,
+			    ppc4xx_edac_nr_chans,
+			    ppc4xx_edac_instance);
+
+	if (mci == NULL) {
+		ppc4xx_edac_printk(KERN_ERR, "%s: "
+				   "Failed to allocate EDAC MC instance!\n",
+				   np->full_name);
+		status = -ENOMEM;
+		goto done;
+	}
+
+	status = ppc4xx_edac_mc_init(mci, op, match, &dcr_host, mcopt1);
+
+	if (status) {
+		ppc4xx_edac_mc_printk(KERN_ERR, mci,
+				      "Failed to initialize instance!\n");
+		goto fail;
+	}
+
+	/*
+	 * We have a valid, initialized EDAC instance bound to the
+	 * controller. Attempt to register it with the EDAC subsystem
+	 * and, if necessary, register interrupts.
+	 */
+
+	if (edac_mc_add_mc(mci)) {
+		ppc4xx_edac_mc_printk(KERN_ERR, mci,
+				      "Failed to add instance!\n");
+		status = -ENODEV;
+		goto fail;
+	}
+
+	if (edac_op_state == EDAC_OPSTATE_INT) {
+		status = ppc4xx_edac_register_irq(op, mci);
+
+		if (status)
+			goto fail1;
+	}
+
+	ppc4xx_edac_instance++;
+
+	return 0;
+
+ fail1:
+	edac_mc_del_mc(mci->dev);
+
+ fail:
+	edac_mc_free(mci);
+
+ done:
+	return status;
+}
+
+/**
+ * ppc4xx_edac_remove - unbind driver from controller
+ * @op: A pointer to the OpenFirmware device tree node associated
+ *      with the controller this EDAC instance is to be unbound/removed
+ *      from.
+ *
+ * This routine unbinds the EDAC memory controller instance associated
+ * with the specified ibm,sdram-4xx-ddr2 controller described by the
+ * OpenFirmware device tree node passed as a parameter.
+ *
+ * Unconditionally returns 0.
+ */
+static int
+ppc4xx_edac_remove(struct of_device *op)
+{
+	struct mem_ctl_info *mci = dev_get_drvdata(&op->dev);
+	struct ppc4xx_edac_pdata *pdata = mci->pvt_info;
+
+	if (edac_op_state == EDAC_OPSTATE_INT) {
+		free_irq(pdata->irqs.sec, mci);
+		free_irq(pdata->irqs.ded, mci);
+	}
+
+	dcr_unmap(pdata->dcr_host, SDRAM_DCR_RESOURCE_LEN);
+
+	edac_mc_del_mc(mci->dev);
+	edac_mc_free(mci);
+
+	return 0;
+}
+
+/**
+ * ppc4xx_edac_opstate_init - initialize EDAC reporting method
+ *
+ * This routine ensures that the EDAC memory controller reporting
+ * method is mapped to a sane value as the EDAC core defines the value
+ * to EDAC_OPSTATE_INVAL by default. We don't call the global
+ * opstate_init as that defaults to polling and we want interrupt as
+ * the default.
+ */
+static inline void __init
+ppc4xx_edac_opstate_init(void)
+{
+	switch (edac_op_state) {
+	case EDAC_OPSTATE_POLL:
+	case EDAC_OPSTATE_INT:
+		break;
+	default:
+		edac_op_state = EDAC_OPSTATE_INT;
+		break;
+	}
+
+	ppc4xx_edac_printk(KERN_INFO, "Reporting type: %s\n",
+			   ((edac_op_state == EDAC_OPSTATE_POLL) ?
+			    EDAC_OPSTATE_POLL_STR :
+			    ((edac_op_state == EDAC_OPSTATE_INT) ?
+			     EDAC_OPSTATE_INT_STR :
+			     EDAC_OPSTATE_UNKNOWN_STR)));
+}
+
+/**
+ * ppc4xx_edac_init - driver/module insertion entry point
+ *
+ * This routine is the driver/module insertion entry point. It
+ * initializes the EDAC memory controller reporting state and
+ * registers the driver as an OpenFirmware device tree platform
+ * driver.
+ */
+static int __init
+ppc4xx_edac_init(void)
+{
+	ppc4xx_edac_printk(KERN_INFO, PPC4XX_EDAC_MODULE_REVISION "\n");
+
+	ppc4xx_edac_opstate_init();
+
+	return of_register_platform_driver(&ppc4xx_edac_driver);
+}
+
+/**
+ * ppc4xx_edac_exit - driver/module removal entry point
+ *
+ * This routine is the driver/module removal entry point. It
+ * unregisters the driver as an OpenFirmware device tree platform
+ * driver.
+ */
+static void __exit
+ppc4xx_edac_exit(void)
+{
+	of_unregister_platform_driver(&ppc4xx_edac_driver);
+}
+
+module_init(ppc4xx_edac_init);
+module_exit(ppc4xx_edac_exit);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Grant Erickson <gerickson@nuovations.com>");
+MODULE_DESCRIPTION("EDAC MC Driver for the PPC4xx IBM DDR2 Memory Controller");
+module_param(edac_op_state, int, 0444);
+MODULE_PARM_DESC(edac_op_state, "EDAC Error Reporting State: "
+		 "0=" EDAC_OPSTATE_POLL_STR ", 2=" EDAC_OPSTATE_INT_STR);
diff --git a/drivers/edac/ppc4xx_edac.h b/drivers/edac/ppc4xx_edac.h
new file mode 100644
index 000000000000..d3154764c449
--- /dev/null
+++ b/drivers/edac/ppc4xx_edac.h
@@ -0,0 +1,172 @@
+/*
+ * Copyright (c) 2008 Nuovation System Designs, LLC
+ *   Grant Erickson <gerickson@nuovations.com>
+ *
+ * This file defines processor mnemonics for accessing and managing
+ * the IBM DDR1/DDR2 ECC controller found in the 405EX[r], 440SP,
+ * 440SPe, 460EX, 460GT and 460SX.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation; version 2 of the
+ * License.
+ *
+ */
+
+#ifndef __PPC4XX_EDAC_H
+#define __PPC4XX_EDAC_H
+
+#include <linux/types.h>
+
+/*
+ * Macro for generating register field mnemonics
+ */
+#define PPC_REG_BITS			32
+#define PPC_REG_VAL(bit, val)		((val) << ((PPC_REG_BITS - 1) - (bit)))
+#define PPC_REG_DECODE(bit, val)	((val) >> ((PPC_REG_BITS - 1) - (bit)))
+
+/*
+ * IBM 4xx DDR1/DDR2 SDRAM memory controller registers (at least those
+ * relevant to ECC)
+ */
+#define SDRAM_BESR			0x00	/* Error status (read/clear) */
+#define SDRAM_BESRT			0x01	/* Error statuss (test/set)  */
+#define SDRAM_BEARL			0x02	/* Error address low	     */
+#define SDRAM_BEARH			0x03	/* Error address high	     */
+#define SDRAM_WMIRQ			0x06	/* Write master (read/clear) */
+#define SDRAM_WMIRQT			0x07	/* Write master (test/set)   */
+#define SDRAM_MCOPT1			0x20	/* Controller options 1	     */
+#define SDRAM_MBXCF_BASE		0x40	/* Bank n configuration base */
+#define	SDRAM_MBXCF(n)			(SDRAM_MBXCF_BASE + (4 * (n)))
+#define SDRAM_MB0CF			SDRAM_MBXCF(0)
+#define SDRAM_MB1CF			SDRAM_MBXCF(1)
+#define SDRAM_MB2CF			SDRAM_MBXCF(2)
+#define SDRAM_MB3CF			SDRAM_MBXCF(3)
+#define SDRAM_ECCCR			0x98	/* ECC error status	     */
+#define SDRAM_ECCES			SDRAM_ECCCR
+
+/*
+ * PLB Master IDs
+ */
+#define	SDRAM_PLB_M0ID_FIRST		0
+#define	SDRAM_PLB_M0ID_ICU		SDRAM_PLB_M0ID_FIRST
+#define	SDRAM_PLB_M0ID_PCIE0		1
+#define	SDRAM_PLB_M0ID_PCIE1		2
+#define	SDRAM_PLB_M0ID_DMA		3
+#define	SDRAM_PLB_M0ID_DCU		4
+#define	SDRAM_PLB_M0ID_OPB		5
+#define	SDRAM_PLB_M0ID_MAL		6
+#define	SDRAM_PLB_M0ID_SEC		7
+#define	SDRAM_PLB_M0ID_AHB		8
+#define SDRAM_PLB_M0ID_LAST		SDRAM_PLB_M0ID_AHB
+#define SDRAM_PLB_M0ID_COUNT		(SDRAM_PLB_M0ID_LAST - \
+					 SDRAM_PLB_M0ID_FIRST + 1)
+
+/*
+ * Memory Controller Bus Error Status Register
+ */
+#define SDRAM_BESR_MASK			PPC_REG_VAL(7, 0xFF)
+#define SDRAM_BESR_M0ID_MASK		PPC_REG_VAL(3, 0xF)
+#define	SDRAM_BESR_M0ID_DECODE(n)	PPC_REG_DECODE(3, n)
+#define SDRAM_BESR_M0ID_ICU		PPC_REG_VAL(3, SDRAM_PLB_M0ID_ICU)
+#define SDRAM_BESR_M0ID_PCIE0		PPC_REG_VAL(3, SDRAM_PLB_M0ID_PCIE0)
+#define SDRAM_BESR_M0ID_PCIE1		PPC_REG_VAL(3, SDRAM_PLB_M0ID_PCIE1)
+#define SDRAM_BESR_M0ID_DMA		PPC_REG_VAL(3, SDRAM_PLB_M0ID_DMA)
+#define SDRAM_BESR_M0ID_DCU		PPC_REG_VAL(3, SDRAM_PLB_M0ID_DCU)
+#define SDRAM_BESR_M0ID_OPB		PPC_REG_VAL(3, SDRAM_PLB_M0ID_OPB)
+#define SDRAM_BESR_M0ID_MAL		PPC_REG_VAL(3, SDRAM_PLB_M0ID_MAL)
+#define SDRAM_BESR_M0ID_SEC		PPC_REG_VAL(3, SDRAM_PLB_M0ID_SEC)
+#define SDRAM_BESR_M0ID_AHB		PPC_REG_VAL(3, SDRAM_PLB_M0ID_AHB)
+#define SDRAM_BESR_M0ET_MASK		PPC_REG_VAL(6, 0x7)
+#define SDRAM_BESR_M0ET_NONE		PPC_REG_VAL(6, 0)
+#define SDRAM_BESR_M0ET_ECC		PPC_REG_VAL(6, 1)
+#define SDRAM_BESR_M0RW_MASK		PPC_REG_VAL(7, 1)
+#define SDRAM_BESR_M0RW_WRITE		PPC_REG_VAL(7, 0)
+#define SDRAM_BESR_M0RW_READ		PPC_REG_VAL(7, 1)
+
+/*
+ * Memory Controller PLB Write Master Interrupt Register
+ */
+#define SDRAM_WMIRQ_MASK		PPC_REG_VAL(8, 0x1FF)
+#define	SDRAM_WMIRQ_ENCODE(id)		PPC_REG_VAL((id % \
+						     SDRAM_PLB_M0ID_COUNT), 1)
+#define SDRAM_WMIRQ_ICU			PPC_REG_VAL(SDRAM_PLB_M0ID_ICU, 1)
+#define SDRAM_WMIRQ_PCIE0		PPC_REG_VAL(SDRAM_PLB_M0ID_PCIE0, 1)
+#define SDRAM_WMIRQ_PCIE1		PPC_REG_VAL(SDRAM_PLB_M0ID_PCIE1, 1)
+#define SDRAM_WMIRQ_DMA			PPC_REG_VAL(SDRAM_PLB_M0ID_DMA, 1)
+#define SDRAM_WMIRQ_DCU			PPC_REG_VAL(SDRAM_PLB_M0ID_DCU, 1)
+#define SDRAM_WMIRQ_OPB			PPC_REG_VAL(SDRAM_PLB_M0ID_OPB, 1)
+#define SDRAM_WMIRQ_MAL			PPC_REG_VAL(SDRAM_PLB_M0ID_MAL, 1)
+#define SDRAM_WMIRQ_SEC			PPC_REG_VAL(SDRAM_PLB_M0ID_SEC, 1)
+#define SDRAM_WMIRQ_AHB			PPC_REG_VAL(SDRAM_PLB_M0ID_AHB, 1)
+
+/*
+ * Memory Controller Options 1 Register
+ */
+#define SDRAM_MCOPT1_MCHK_MASK	    PPC_REG_VAL(3, 0x3)	 /* ECC mask	     */
+#define SDRAM_MCOPT1_MCHK_NON	    PPC_REG_VAL(3, 0x0)	 /* No ECC gen	     */
+#define SDRAM_MCOPT1_MCHK_GEN	    PPC_REG_VAL(3, 0x2)	 /* ECC gen	     */
+#define SDRAM_MCOPT1_MCHK_CHK	    PPC_REG_VAL(3, 0x1)	 /* ECC gen and chk  */
+#define SDRAM_MCOPT1_MCHK_CHK_REP   PPC_REG_VAL(3, 0x3)	 /* ECC gen/chk/rpt  */
+#define SDRAM_MCOPT1_MCHK_DECODE(n) ((((u32)(n)) >> 28) & 0x3)
+#define SDRAM_MCOPT1_RDEN_MASK	    PPC_REG_VAL(4, 0x1)	 /* Rgstrd DIMM mask */
+#define SDRAM_MCOPT1_RDEN	    PPC_REG_VAL(4, 0x1)	 /* Rgstrd DIMM enbl */
+#define SDRAM_MCOPT1_WDTH_MASK	    PPC_REG_VAL(7, 0x1)	 /* Width mask	     */
+#define SDRAM_MCOPT1_WDTH_32	    PPC_REG_VAL(7, 0x0)	 /* 32 bits	     */
+#define SDRAM_MCOPT1_WDTH_16	    PPC_REG_VAL(7, 0x1)	 /* 16 bits	     */
+#define SDRAM_MCOPT1_DDR_TYPE_MASK  PPC_REG_VAL(11, 0x1) /* DDR type mask    */
+#define SDRAM_MCOPT1_DDR1_TYPE	    PPC_REG_VAL(11, 0x0) /* DDR1 type	     */
+#define SDRAM_MCOPT1_DDR2_TYPE	    PPC_REG_VAL(11, 0x1) /* DDR2 type	     */
+
+/*
+ * Memory Bank 0 - n Configuration Register
+ */
+#define SDRAM_MBCF_BA_MASK		PPC_REG_VAL(12, 0x1FFF)
+#define SDRAM_MBCF_SZ_MASK		PPC_REG_VAL(19, 0xF)
+#define SDRAM_MBCF_SZ_DECODE(mbxcf)	PPC_REG_DECODE(19, mbxcf)
+#define SDRAM_MBCF_SZ_4MB		PPC_REG_VAL(19, 0x0)
+#define SDRAM_MBCF_SZ_8MB		PPC_REG_VAL(19, 0x1)
+#define SDRAM_MBCF_SZ_16MB		PPC_REG_VAL(19, 0x2)
+#define SDRAM_MBCF_SZ_32MB		PPC_REG_VAL(19, 0x3)
+#define SDRAM_MBCF_SZ_64MB		PPC_REG_VAL(19, 0x4)
+#define SDRAM_MBCF_SZ_128MB		PPC_REG_VAL(19, 0x5)
+#define SDRAM_MBCF_SZ_256MB		PPC_REG_VAL(19, 0x6)
+#define SDRAM_MBCF_SZ_512MB		PPC_REG_VAL(19, 0x7)
+#define SDRAM_MBCF_SZ_1GB		PPC_REG_VAL(19, 0x8)
+#define SDRAM_MBCF_SZ_2GB		PPC_REG_VAL(19, 0x9)
+#define SDRAM_MBCF_SZ_4GB		PPC_REG_VAL(19, 0xA)
+#define SDRAM_MBCF_SZ_8GB		PPC_REG_VAL(19, 0xB)
+#define SDRAM_MBCF_AM_MASK		PPC_REG_VAL(23, 0xF)
+#define SDRAM_MBCF_AM_MODE0		PPC_REG_VAL(23, 0x0)
+#define SDRAM_MBCF_AM_MODE1		PPC_REG_VAL(23, 0x1)
+#define SDRAM_MBCF_AM_MODE2		PPC_REG_VAL(23, 0x2)
+#define SDRAM_MBCF_AM_MODE3		PPC_REG_VAL(23, 0x3)
+#define SDRAM_MBCF_AM_MODE4		PPC_REG_VAL(23, 0x4)
+#define SDRAM_MBCF_AM_MODE5		PPC_REG_VAL(23, 0x5)
+#define SDRAM_MBCF_AM_MODE6		PPC_REG_VAL(23, 0x6)
+#define SDRAM_MBCF_AM_MODE7		PPC_REG_VAL(23, 0x7)
+#define SDRAM_MBCF_AM_MODE8		PPC_REG_VAL(23, 0x8)
+#define SDRAM_MBCF_AM_MODE9		PPC_REG_VAL(23, 0x9)
+#define SDRAM_MBCF_BE_MASK		PPC_REG_VAL(31, 0x1)
+#define SDRAM_MBCF_BE_DISABLE		PPC_REG_VAL(31, 0x0)
+#define SDRAM_MBCF_BE_ENABLE		PPC_REG_VAL(31, 0x1)
+
+/*
+ * ECC Error Status
+ */
+#define SDRAM_ECCES_MASK		PPC_REG_VAL(21, 0x3FFFFF)
+#define SDRAM_ECCES_BNCE_MASK		PPC_REG_VAL(15, 0xFFFF)
+#define SDRAM_ECCES_BNCE_ENCODE(lane)	PPC_REG_VAL(((lane) & 0xF), 1)
+#define SDRAM_ECCES_CKBER_MASK		PPC_REG_VAL(17, 0x3)
+#define SDRAM_ECCES_CKBER_NONE		PPC_REG_VAL(17, 0)
+#define SDRAM_ECCES_CKBER_16_ECC_0_3	PPC_REG_VAL(17, 2)
+#define SDRAM_ECCES_CKBER_32_ECC_0_3	PPC_REG_VAL(17, 1)
+#define SDRAM_ECCES_CKBER_32_ECC_4_8	PPC_REG_VAL(17, 2)
+#define SDRAM_ECCES_CKBER_32_ECC_0_8	PPC_REG_VAL(17, 3)
+#define SDRAM_ECCES_CE			PPC_REG_VAL(18, 1)
+#define SDRAM_ECCES_UE			PPC_REG_VAL(19, 1)
+#define SDRAM_ECCES_BKNER_MASK		PPC_REG_VAL(21, 0x3)
+#define SDRAM_ECCES_BK0ER		PPC_REG_VAL(20, 1)
+#define SDRAM_ECCES_BK1ER		PPC_REG_VAL(21, 1)
+
+#endif /* __PPC4XX_EDAC_H */
diff --git a/drivers/gpio/Kconfig b/drivers/gpio/Kconfig
index 3d2565441b36..edb02530e461 100644
--- a/drivers/gpio/Kconfig
+++ b/drivers/gpio/Kconfig
@@ -42,9 +42,9 @@ config DEBUG_GPIO
 	depends on DEBUG_KERNEL
 	help
 	  Say Y here to add some extra checks and diagnostics to GPIO calls.
-	  The checks help ensure that GPIOs have been properly initialized
-	  before they are used and that sleeping calls aren not made from
-	  nonsleeping contexts.  They can make bitbanged serial protocols
+	  These checks help ensure that GPIOs have been properly initialized
+	  before they are used, and that sleeping calls are not made from
+	  non-sleeping contexts.  They can make bitbanged serial protocols
 	  slower.  The diagnostics help catch the type of setup errors
 	  that are most common when setting up new platforms or boards.
 
diff --git a/drivers/gpio/gpiolib.c b/drivers/gpio/gpiolib.c
index 42fb2fd24c0c..51a8d4103be5 100644
--- a/drivers/gpio/gpiolib.c
+++ b/drivers/gpio/gpiolib.c
@@ -69,20 +69,24 @@ static inline void desc_set_label(struct gpio_desc *d, const char *label)
  * those calls have no teeth) we can't avoid autorequesting.  This nag
  * message should motivate switching to explicit requests... so should
  * the weaker cleanup after faults, compared to gpio_request().
+ *
+ * NOTE: the autorequest mechanism is going away; at this point it's
+ * only "legal" in the sense that (old) code using it won't break yet,
+ * but instead only triggers a WARN() stack dump.
  */
 static int gpio_ensure_requested(struct gpio_desc *desc, unsigned offset)
 {
-	if (test_and_set_bit(FLAG_REQUESTED, &desc->flags) == 0) {
-		struct gpio_chip *chip = desc->chip;
-		int gpio = chip->base + offset;
+	const struct gpio_chip *chip = desc->chip;
+	const int gpio = chip->base + offset;
 
+	if (WARN(test_and_set_bit(FLAG_REQUESTED, &desc->flags) == 0,
+			"autorequest GPIO-%d\n", gpio)) {
 		if (!try_module_get(chip->owner)) {
 			pr_err("GPIO-%d: module can't be gotten \n", gpio);
 			clear_bit(FLAG_REQUESTED, &desc->flags);
 			/* lose */
 			return -EIO;
 		}
-		pr_warning("GPIO-%d autorequested\n", gpio);
 		desc_set_label(desc, "[auto]");
 		/* caller must chip->request() w/o spinlock */
 		if (chip->request)
@@ -438,6 +442,7 @@ int gpio_export(unsigned gpio, bool direction_may_change)
 	unsigned long		flags;
 	struct gpio_desc	*desc;
 	int			status = -EINVAL;
+	char			*ioname = NULL;
 
 	/* can't export until sysfs is available ... */
 	if (!gpio_class.p) {
@@ -461,11 +466,14 @@ int gpio_export(unsigned gpio, bool direction_may_change)
 	}
 	spin_unlock_irqrestore(&gpio_lock, flags);
 
+	if (desc->chip->names && desc->chip->names[gpio - desc->chip->base])
+		ioname = desc->chip->names[gpio - desc->chip->base];
+
 	if (status == 0) {
 		struct device	*dev;
 
 		dev = device_create(&gpio_class, desc->chip->dev, MKDEV(0, 0),
-					desc, "gpio%d", gpio);
+				    desc, ioname ? ioname : "gpio%d", gpio);
 		if (dev) {
 			if (direction_may_change)
 				status = sysfs_create_group(&dev->kobj,
@@ -513,6 +521,7 @@ void gpio_unexport(unsigned gpio)
 	mutex_lock(&sysfs_lock);
 
 	desc = &gpio_desc[gpio];
+
 	if (test_bit(FLAG_EXPORT, &desc->flags)) {
 		struct device	*dev = NULL;
 
diff --git a/drivers/gpu/drm/drm_crtc_helper.c b/drivers/gpu/drm/drm_crtc_helper.c
index 1c3a8c557140..a04639dc633d 100644
--- a/drivers/gpu/drm/drm_crtc_helper.c
+++ b/drivers/gpu/drm/drm_crtc_helper.c
@@ -42,6 +42,26 @@ static struct drm_display_mode std_modes[] = {
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
 };
 
+static void drm_mode_validate_flag(struct drm_connector *connector,
+				   int flags)
+{
+	struct drm_display_mode *mode, *t;
+
+	if (flags == (DRM_MODE_FLAG_DBLSCAN | DRM_MODE_FLAG_INTERLACE))
+		return;
+
+	list_for_each_entry_safe(mode, t, &connector->modes, head) {
+		if ((mode->flags & DRM_MODE_FLAG_INTERLACE) &&
+				!(flags & DRM_MODE_FLAG_INTERLACE))
+			mode->status = MODE_NO_INTERLACE;
+		if ((mode->flags & DRM_MODE_FLAG_DBLSCAN) &&
+				!(flags & DRM_MODE_FLAG_DBLSCAN))
+			mode->status = MODE_NO_DBLESCAN;
+	}
+
+	return;
+}
+
 /**
  * drm_helper_probe_connector_modes - get complete set of display modes
  * @dev: DRM device
@@ -72,6 +92,7 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 	struct drm_connector_helper_funcs *connector_funcs =
 		connector->helper_private;
 	int count = 0;
+	int mode_flags = 0;
 
 	DRM_DEBUG("%s\n", drm_get_connector_name(connector));
 	/* set all modes to the unverified state */
@@ -96,6 +117,13 @@ int drm_helper_probe_single_connector_modes(struct drm_connector *connector,
 	if (maxX && maxY)
 		drm_mode_validate_size(dev, &connector->modes, maxX,
 				       maxY, 0);
+
+	if (connector->interlace_allowed)
+		mode_flags |= DRM_MODE_FLAG_INTERLACE;
+	if (connector->doublescan_allowed)
+		mode_flags |= DRM_MODE_FLAG_DBLSCAN;
+	drm_mode_validate_flag(connector, mode_flags);
+
 	list_for_each_entry_safe(mode, t, &connector->modes, head) {
 		if (mode->status == MODE_OK)
 			mode->status = connector_funcs->mode_valid(connector,
@@ -885,7 +913,6 @@ bool drm_helper_plugged_event(struct drm_device *dev)
 /**
  * drm_initial_config - setup a sane initial connector configuration
  * @dev: DRM device
- * @can_grow: this configuration is growable
  *
  * LOCKING:
  * Called at init time, must take mode config lock.
@@ -897,7 +924,7 @@ bool drm_helper_plugged_event(struct drm_device *dev)
  * RETURNS:
  * Zero if everything went ok, nonzero otherwise.
  */
-bool drm_helper_initial_config(struct drm_device *dev, bool can_grow)
+bool drm_helper_initial_config(struct drm_device *dev)
 {
 	struct drm_connector *connector;
 	int count = 0;
diff --git a/drivers/gpu/drm/drm_edid.c b/drivers/gpu/drm/drm_edid.c
index c67400067b85..ca9c61656714 100644
--- a/drivers/gpu/drm/drm_edid.c
+++ b/drivers/gpu/drm/drm_edid.c
@@ -125,10 +125,8 @@ static bool edid_is_valid(struct edid *edid)
 		DRM_ERROR("EDID has major version %d, instead of 1\n", edid->version);
 		goto bad;
 	}
-	if (edid->revision > 3) {
-		DRM_ERROR("EDID has minor version %d, which is not between 0-3\n", edid->revision);
-		goto bad;
-	}
+	if (edid->revision > 4)
+		DRM_DEBUG("EDID minor > 4, assuming backward compatibility\n");
 
 	for (i = 0; i < EDID_LENGTH; i++)
 		csum += raw_edid[i];
@@ -162,7 +160,7 @@ static bool edid_vendor(struct edid *edid, char *vendor)
 	edid_vendor[0] = ((edid->mfg_id[0] & 0x7c) >> 2) + '@';
 	edid_vendor[1] = (((edid->mfg_id[0] & 0x3) << 3) |
 			  ((edid->mfg_id[1] & 0xe0) >> 5)) + '@';
-	edid_vendor[2] = (edid->mfg_id[2] & 0x1f) + '@';
+	edid_vendor[2] = (edid->mfg_id[1] & 0x1f) + '@';
 
 	return !strncmp(edid_vendor, vendor, 3);
 }
diff --git a/drivers/gpu/drm/drm_gem.c b/drivers/gpu/drm/drm_gem.c
index c1173d8c4588..4984aa89cf3d 100644
--- a/drivers/gpu/drm/drm_gem.c
+++ b/drivers/gpu/drm/drm_gem.c
@@ -505,7 +505,6 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	struct drm_local_map *map = NULL;
 	struct drm_gem_object *obj;
 	struct drm_hash_item *hash;
-	unsigned long prot;
 	int ret = 0;
 
 	mutex_lock(&dev->struct_mutex);
@@ -538,11 +537,7 @@ int drm_gem_mmap(struct file *filp, struct vm_area_struct *vma)
 	vma->vm_ops = obj->dev->driver->gem_vm_ops;
 	vma->vm_private_data = map->handle;
 	/* FIXME: use pgprot_writecombine when available */
-	prot = pgprot_val(vma->vm_page_prot);
-#ifdef CONFIG_X86
-	prot |= _PAGE_CACHE_WC;
-#endif
-	vma->vm_page_prot = __pgprot(prot);
+	vma->vm_page_prot = pgprot_writecombine(vma->vm_page_prot);
 
 	/* Take a ref for this mapping of the object, so that the fault
 	 * handler can dereference the mmap offset's pointer to the object.
diff --git a/drivers/gpu/drm/drm_sysfs.c b/drivers/gpu/drm/drm_sysfs.c
index 5de573a981cb..bc0c6849360c 100644
--- a/drivers/gpu/drm/drm_sysfs.c
+++ b/drivers/gpu/drm/drm_sysfs.c
@@ -451,6 +451,7 @@ void drm_sysfs_hotplug_event(struct drm_device *dev)
 
 	kobject_uevent_env(&dev->primary->kdev.kobj, KOBJ_CHANGE, envp);
 }
+EXPORT_SYMBOL(drm_sysfs_hotplug_event);
 
 /**
  * drm_sysfs_device_add - adds a class device to sysfs for a character driver
diff --git a/drivers/gpu/drm/i915/i915_dma.c b/drivers/gpu/drm/i915/i915_dma.c
index 85549f615b1f..c23b3a95b7ce 100644
--- a/drivers/gpu/drm/i915/i915_dma.c
+++ b/drivers/gpu/drm/i915/i915_dma.c
@@ -922,7 +922,7 @@ static int i915_probe_agp(struct drm_device *dev, unsigned long *aperture_size,
 	 * Some of the preallocated space is taken by the GTT
 	 * and popup.  GTT is 1K per MB of aperture size, and popup is 4K.
 	 */
-	if (IS_G4X(dev))
+	if (IS_G4X(dev) || IS_IGD(dev))
 		overhead = 4096;
 	else
 		overhead = (*aperture_size / 1024) + 4096;
@@ -1030,13 +1030,6 @@ static int i915_load_modeset_init(struct drm_device *dev)
 	if (ret)
 		goto destroy_ringbuffer;
 
-	/* FIXME: re-add hotplug support */
-#if 0
-	ret = drm_hotplug_init(dev);
-	if (ret)
-		goto destroy_ringbuffer;
-#endif
-
 	/* Always safe in the mode setting case. */
 	/* FIXME: do pre/post-mode set stuff in core KMS code */
 	dev->vblank_disable_allowed = 1;
@@ -1049,7 +1042,7 @@ static int i915_load_modeset_init(struct drm_device *dev)
 
 	intel_modeset_init(dev);
 
-	drm_helper_initial_config(dev, false);
+	drm_helper_initial_config(dev);
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c1685d0c704f..317b1223e091 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -159,6 +159,9 @@ typedef struct drm_i915_private {
 	u32 irq_mask_reg;
 	u32 pipestat[2];
 
+	u32 hotplug_supported_mask;
+	struct work_struct hotplug_work;
+
 	int tex_lru_log_granularity;
 	int allow_batchbuffer;
 	struct mem_block *agp_heap;
@@ -297,6 +300,7 @@ typedef struct drm_i915_private {
 		 *
 		 * A reference is held on the buffer while on this list.
 		 */
+		spinlock_t active_list_lock;
 		struct list_head active_list;
 
 		/**
@@ -810,6 +814,7 @@ extern int i915_wait_ring(struct drm_device * dev, int n, const char *caller);
 #define HAS_128_BYTE_Y_TILING(dev) (IS_I9XX(dev) && !(IS_I915G(dev) || \
 						      IS_I915GM(dev)))
 #define SUPPORTS_INTEGRATED_HDMI(dev)	(IS_G4X(dev))
+#define I915_HAS_HOTPLUG(dev) (IS_I945G(dev) || IS_I945GM(dev) || IS_I965G(dev))
 
 #define PRIMARY_RINGBUFFER_SIZE         (128*1024)
 
diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index e0389ad1477d..1449b452cc63 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -1072,6 +1072,7 @@ int i915_gem_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	case -EAGAIN:
 		return VM_FAULT_OOM;
 	case -EFAULT:
+	case -EINVAL:
 		return VM_FAULT_SIGBUS;
 	default:
 		return VM_FAULT_NOPAGE;
@@ -1324,8 +1325,10 @@ i915_gem_object_move_to_active(struct drm_gem_object *obj, uint32_t seqno)
 		obj_priv->active = 1;
 	}
 	/* Move from whatever list we were on to the tail of execution. */
+	spin_lock(&dev_priv->mm.active_list_lock);
 	list_move_tail(&obj_priv->list,
 		       &dev_priv->mm.active_list);
+	spin_unlock(&dev_priv->mm.active_list_lock);
 	obj_priv->last_rendering_seqno = seqno;
 }
 
@@ -1467,6 +1470,7 @@ i915_gem_retire_request(struct drm_device *dev,
 	/* Move any buffers on the active list that are no longer referenced
 	 * by the ringbuffer to the flushing/inactive lists as appropriate.
 	 */
+	spin_lock(&dev_priv->mm.active_list_lock);
 	while (!list_empty(&dev_priv->mm.active_list)) {
 		struct drm_gem_object *obj;
 		struct drm_i915_gem_object *obj_priv;
@@ -1481,7 +1485,7 @@ i915_gem_retire_request(struct drm_device *dev,
 		 * this seqno.
 		 */
 		if (obj_priv->last_rendering_seqno != request->seqno)
-			return;
+			goto out;
 
 #if WATCH_LRU
 		DRM_INFO("%s: retire %d moves to inactive list %p\n",
@@ -1493,6 +1497,8 @@ i915_gem_retire_request(struct drm_device *dev,
 		else
 			i915_gem_object_move_to_inactive(obj);
 	}
+out:
+	spin_unlock(&dev_priv->mm.active_list_lock);
 }
 
 /**
@@ -1990,20 +1996,23 @@ static void i830_write_fence_reg(struct drm_i915_fence_reg *reg)
 	int regnum = obj_priv->fence_reg;
 	uint32_t val;
 	uint32_t pitch_val;
+	uint32_t fence_size_bits;
 
-	if ((obj_priv->gtt_offset & ~I915_FENCE_START_MASK) ||
+	if ((obj_priv->gtt_offset & ~I830_FENCE_START_MASK) ||
 	    (obj_priv->gtt_offset & (obj->size - 1))) {
-		WARN(1, "%s: object 0x%08x not 1M or size aligned\n",
+		WARN(1, "%s: object 0x%08x not 512K or size aligned\n",
 		     __func__, obj_priv->gtt_offset);
 		return;
 	}
 
 	pitch_val = (obj_priv->stride / 128) - 1;
-
+	WARN_ON(pitch_val & ~0x0000000f);
 	val = obj_priv->gtt_offset;
 	if (obj_priv->tiling_mode == I915_TILING_Y)
 		val |= 1 << I830_FENCE_TILING_Y_SHIFT;
-	val |= I830_FENCE_SIZE_BITS(obj->size);
+	fence_size_bits = I830_FENCE_SIZE_BITS(obj->size);
+	WARN_ON(fence_size_bits & ~0x00000f00);
+	val |= fence_size_bits;
 	val |= pitch_val << I830_FENCE_PITCH_SHIFT;
 	val |= I830_FENCE_REG_VALID;
 
@@ -2194,7 +2203,7 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 		return -EBUSY;
 	if (alignment == 0)
 		alignment = i915_gem_get_gtt_alignment(obj);
-	if (alignment & (PAGE_SIZE - 1)) {
+	if (alignment & (i915_gem_get_gtt_alignment(obj) - 1)) {
 		DRM_ERROR("Invalid object alignment requested %u\n", alignment);
 		return -EINVAL;
 	}
@@ -2211,15 +2220,20 @@ i915_gem_object_bind_to_gtt(struct drm_gem_object *obj, unsigned alignment)
 		}
 	}
 	if (obj_priv->gtt_space == NULL) {
+		bool lists_empty;
+
 		/* If the gtt is empty and we're still having trouble
 		 * fitting our object in, we're out of memory.
 		 */
 #if WATCH_LRU
 		DRM_INFO("%s: GTT full, evicting something\n", __func__);
 #endif
-		if (list_empty(&dev_priv->mm.inactive_list) &&
-		    list_empty(&dev_priv->mm.flushing_list) &&
-		    list_empty(&dev_priv->mm.active_list)) {
+		spin_lock(&dev_priv->mm.active_list_lock);
+		lists_empty = (list_empty(&dev_priv->mm.inactive_list) &&
+			       list_empty(&dev_priv->mm.flushing_list) &&
+			       list_empty(&dev_priv->mm.active_list));
+		spin_unlock(&dev_priv->mm.active_list_lock);
+		if (lists_empty) {
 			DRM_ERROR("GTT full, but LRU list empty\n");
 			return -ENOMEM;
 		}
@@ -3675,6 +3689,7 @@ i915_gem_idle(struct drm_device *dev)
 
 	i915_gem_retire_requests(dev);
 
+	spin_lock(&dev_priv->mm.active_list_lock);
 	if (!dev_priv->mm.wedged) {
 		/* Active and flushing should now be empty as we've
 		 * waited for a sequence higher than any pending execbuffer
@@ -3701,6 +3716,7 @@ i915_gem_idle(struct drm_device *dev)
 		obj_priv->obj->write_domain &= ~I915_GEM_GPU_DOMAINS;
 		i915_gem_object_move_to_inactive(obj_priv->obj);
 	}
+	spin_unlock(&dev_priv->mm.active_list_lock);
 
 	while (!list_empty(&dev_priv->mm.flushing_list)) {
 		struct drm_i915_gem_object *obj_priv;
@@ -3949,7 +3965,10 @@ i915_gem_entervt_ioctl(struct drm_device *dev, void *data,
 	if (ret != 0)
 		return ret;
 
+	spin_lock(&dev_priv->mm.active_list_lock);
 	BUG_ON(!list_empty(&dev_priv->mm.active_list));
+	spin_unlock(&dev_priv->mm.active_list_lock);
+
 	BUG_ON(!list_empty(&dev_priv->mm.flushing_list));
 	BUG_ON(!list_empty(&dev_priv->mm.inactive_list));
 	BUG_ON(!list_empty(&dev_priv->mm.request_list));
@@ -3993,6 +4012,7 @@ i915_gem_load(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = dev->dev_private;
 
+	spin_lock_init(&dev_priv->mm.active_list_lock);
 	INIT_LIST_HEAD(&dev_priv->mm.active_list);
 	INIT_LIST_HEAD(&dev_priv->mm.flushing_list);
 	INIT_LIST_HEAD(&dev_priv->mm.inactive_list);
diff --git a/drivers/gpu/drm/i915/i915_gem_debug.c b/drivers/gpu/drm/i915/i915_gem_debug.c
index 131c088f8c8a..8d0b943e2c5a 100644
--- a/drivers/gpu/drm/i915/i915_gem_debug.c
+++ b/drivers/gpu/drm/i915/i915_gem_debug.c
@@ -105,12 +105,14 @@ i915_dump_lru(struct drm_device *dev, const char *where)
 	struct drm_i915_gem_object	*obj_priv;
 
 	DRM_INFO("active list %s {\n", where);
+	spin_lock(&dev_priv->mm.active_list_lock);
 	list_for_each_entry(obj_priv, &dev_priv->mm.active_list,
 			    list)
 	{
 		DRM_INFO("    %p: %08x\n", obj_priv,
 			 obj_priv->last_rendering_seqno);
 	}
+	spin_unlock(&dev_priv->mm.active_list_lock);
 	DRM_INFO("}\n");
 	DRM_INFO("flushing list %s {\n", where);
 	list_for_each_entry(obj_priv, &dev_priv->mm.flushing_list,
diff --git a/drivers/gpu/drm/i915/i915_gem_debugfs.c b/drivers/gpu/drm/i915/i915_gem_debugfs.c
index 455ec970b385..a1ac0c5e7307 100644
--- a/drivers/gpu/drm/i915/i915_gem_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_gem_debugfs.c
@@ -69,10 +69,13 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 	struct drm_device *dev = node->minor->dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj_priv;
+	spinlock_t *lock = NULL;
 
 	switch (list) {
 	case ACTIVE_LIST:
 		seq_printf(m, "Active:\n");
+		lock = &dev_priv->mm.active_list_lock;
+		spin_lock(lock);
 		head = &dev_priv->mm.active_list;
 		break;
 	case INACTIVE_LIST:
@@ -104,6 +107,9 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 			seq_printf(m, " (fence: %d\n", obj_priv->fence_reg);
 		seq_printf(m, "\n");
 	}
+
+	if (lock)
+	    spin_unlock(lock);
 	return 0;
 }
 
diff --git a/drivers/gpu/drm/i915/i915_gem_tiling.c b/drivers/gpu/drm/i915/i915_gem_tiling.c
index 4cce1aef438e..6be3f927c86a 100644
--- a/drivers/gpu/drm/i915/i915_gem_tiling.c
+++ b/drivers/gpu/drm/i915/i915_gem_tiling.c
@@ -216,6 +216,22 @@ i915_tiling_ok(struct drm_device *dev, int stride, int size, int tiling_mode)
 	else
 		tile_width = 512;
 
+	/* check maximum stride & object size */
+	if (IS_I965G(dev)) {
+		/* i965 stores the end address of the gtt mapping in the fence
+		 * reg, so dont bother to check the size */
+		if (stride / 128 > I965_FENCE_MAX_PITCH_VAL)
+			return false;
+	} else if (IS_I9XX(dev)) {
+		if (stride / tile_width > I830_FENCE_MAX_PITCH_VAL ||
+		    size > (I830_FENCE_MAX_SIZE_VAL << 20))
+			return false;
+	} else {
+		if (stride / 128 > I830_FENCE_MAX_PITCH_VAL ||
+		    size > (I830_FENCE_MAX_SIZE_VAL << 19))
+			return false;
+	}
+
 	/* 965+ just needs multiples of tile width */
 	if (IS_I965G(dev)) {
 		if (stride & (tile_width - 1))
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 87b6b603469e..ee7ce7b78cf7 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -48,10 +48,6 @@
 /** Interrupts that we mask and unmask at runtime. */
 #define I915_INTERRUPT_ENABLE_VAR (I915_USER_INTERRUPT)
 
-/** These are all of the interrupts used by the driver */
-#define I915_INTERRUPT_ENABLE_MASK (I915_INTERRUPT_ENABLE_FIX | \
-				    I915_INTERRUPT_ENABLE_VAR)
-
 #define I915_PIPE_VBLANK_STATUS	(PIPE_START_VBLANK_INTERRUPT_STATUS |\
 				 PIPE_VBLANK_INTERRUPT_STATUS)
 
@@ -187,6 +183,19 @@ u32 gm45_get_vblank_counter(struct drm_device *dev, int pipe)
 	return I915_READ(reg);
 }
 
+/*
+ * Handle hotplug events outside the interrupt handler proper.
+ */
+static void i915_hotplug_work_func(struct work_struct *work)
+{
+	drm_i915_private_t *dev_priv = container_of(work, drm_i915_private_t,
+						    hotplug_work);
+	struct drm_device *dev = dev_priv->dev;
+
+	/* Just fire off a uevent and let userspace tell us what to do */
+	drm_sysfs_hotplug_event(dev);
+}
+
 irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS)
 {
 	struct drm_device *dev = (struct drm_device *) arg;
@@ -244,6 +253,20 @@ irqreturn_t i915_driver_irq_handler(DRM_IRQ_ARGS)
 
 		ret = IRQ_HANDLED;
 
+		/* Consume port.  Then clear IIR or we'll miss events */
+		if ((I915_HAS_HOTPLUG(dev)) &&
+		    (iir & I915_DISPLAY_PORT_INTERRUPT)) {
+			u32 hotplug_status = I915_READ(PORT_HOTPLUG_STAT);
+
+			DRM_DEBUG("hotplug event received, stat 0x%08x\n",
+				  hotplug_status);
+			if (hotplug_status & dev_priv->hotplug_supported_mask)
+				schedule_work(&dev_priv->hotplug_work);
+
+			I915_WRITE(PORT_HOTPLUG_STAT, hotplug_status);
+			I915_READ(PORT_HOTPLUG_STAT);
+		}
+
 		I915_WRITE(IIR, iir);
 		new_iir = I915_READ(IIR); /* Flush posted writes */
 
@@ -528,17 +551,24 @@ void i915_driver_irq_preinstall(struct drm_device * dev)
 
 	atomic_set(&dev_priv->irq_received, 0);
 
+	if (I915_HAS_HOTPLUG(dev)) {
+		I915_WRITE(PORT_HOTPLUG_EN, 0);
+		I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
+	}
+
 	I915_WRITE(HWSTAM, 0xeffe);
 	I915_WRITE(PIPEASTAT, 0);
 	I915_WRITE(PIPEBSTAT, 0);
 	I915_WRITE(IMR, 0xffffffff);
 	I915_WRITE(IER, 0x0);
 	(void) I915_READ(IER);
+	INIT_WORK(&dev_priv->hotplug_work, i915_hotplug_work_func);
 }
 
 int i915_driver_irq_postinstall(struct drm_device *dev)
 {
 	drm_i915_private_t *dev_priv = (drm_i915_private_t *) dev->dev_private;
+	u32 enable_mask = I915_INTERRUPT_ENABLE_FIX | I915_INTERRUPT_ENABLE_VAR;
 
 	dev_priv->vblank_pipe = DRM_I915_VBLANK_PIPE_A | DRM_I915_VBLANK_PIPE_B;
 
@@ -550,13 +580,35 @@ int i915_driver_irq_postinstall(struct drm_device *dev)
 	dev_priv->pipestat[0] = 0;
 	dev_priv->pipestat[1] = 0;
 
+	if (I915_HAS_HOTPLUG(dev)) {
+		u32 hotplug_en = I915_READ(PORT_HOTPLUG_EN);
+
+		/* Leave other bits alone */
+		hotplug_en |= HOTPLUG_EN_MASK;
+		I915_WRITE(PORT_HOTPLUG_EN, hotplug_en);
+
+		dev_priv->hotplug_supported_mask = CRT_HOTPLUG_INT_STATUS |
+			TV_HOTPLUG_INT_STATUS | SDVOC_HOTPLUG_INT_STATUS |
+			SDVOB_HOTPLUG_INT_STATUS;
+		if (IS_G4X(dev)) {
+			dev_priv->hotplug_supported_mask |=
+				HDMIB_HOTPLUG_INT_STATUS |
+				HDMIC_HOTPLUG_INT_STATUS |
+				HDMID_HOTPLUG_INT_STATUS;
+		}
+		/* Enable in IER... */
+		enable_mask |= I915_DISPLAY_PORT_INTERRUPT;
+		/* and unmask in IMR */
+		i915_enable_irq(dev_priv, I915_DISPLAY_PORT_INTERRUPT);
+	}
+
 	/* Disable pipe interrupt enables, clear pending pipe status */
 	I915_WRITE(PIPEASTAT, I915_READ(PIPEASTAT) & 0x8000ffff);
 	I915_WRITE(PIPEBSTAT, I915_READ(PIPEBSTAT) & 0x8000ffff);
 	/* Clear pending interrupt status */
 	I915_WRITE(IIR, I915_READ(IIR));
 
-	I915_WRITE(IER, I915_INTERRUPT_ENABLE_MASK);
+	I915_WRITE(IER, enable_mask);
 	I915_WRITE(IMR, dev_priv->irq_mask_reg);
 	(void) I915_READ(IER);
 
@@ -575,6 +627,11 @@ void i915_driver_irq_uninstall(struct drm_device * dev)
 
 	dev_priv->vblank_pipe = 0;
 
+	if (I915_HAS_HOTPLUG(dev)) {
+		I915_WRITE(PORT_HOTPLUG_EN, 0);
+		I915_WRITE(PORT_HOTPLUG_STAT, I915_READ(PORT_HOTPLUG_STAT));
+	}
+
 	I915_WRITE(HWSTAM, 0xffffffff);
 	I915_WRITE(PIPEASTAT, 0);
 	I915_WRITE(PIPEBSTAT, 0);
diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 377cc588f5e9..e805b590ae71 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -190,6 +190,8 @@
 #define   I830_FENCE_SIZE_BITS(size)	((ffs((size) >> 19) - 1) << 8)
 #define   I830_FENCE_PITCH_SHIFT	4
 #define   I830_FENCE_REG_VALID		(1<<0)
+#define   I830_FENCE_MAX_PITCH_VAL	0x10
+#define   I830_FENCE_MAX_SIZE_VAL	(1<<8)
 
 #define   I915_FENCE_START_MASK		0x0ff00000
 #define   I915_FENCE_SIZE_BITS(size)	((ffs((size) >> 20) - 1) << 8)
@@ -198,6 +200,7 @@
 #define   I965_FENCE_PITCH_SHIFT	2
 #define   I965_FENCE_TILING_Y_SHIFT	1
 #define   I965_FENCE_REG_VALID		(1<<0)
+#define   I965_FENCE_MAX_PITCH_VAL	0x0400
 
 /*
  * Instruction and interrupt control regs
@@ -648,6 +651,14 @@
 #define CRT_HOTPLUG_DETECT_VOLTAGE_325MV	(0 << 2)
 #define CRT_HOTPLUG_DETECT_VOLTAGE_475MV	(1 << 2)
 #define CRT_HOTPLUG_MASK			(0x3fc) /* Bits 9-2 */
+#define CRT_FORCE_HOTPLUG_MASK			0xfffffe1f
+#define HOTPLUG_EN_MASK (HDMIB_HOTPLUG_INT_EN | \
+			 HDMIC_HOTPLUG_INT_EN |	  \
+			 HDMID_HOTPLUG_INT_EN |	  \
+			 SDVOB_HOTPLUG_INT_EN |	  \
+			 SDVOC_HOTPLUG_INT_EN |	  \
+			 TV_HOTPLUG_INT_EN |	  \
+			 CRT_HOTPLUG_INT_EN)
 
 
 #define PORT_HOTPLUG_STAT	0x61114
diff --git a/drivers/gpu/drm/i915/intel_crt.c b/drivers/gpu/drm/i915/intel_crt.c
index 2b6d44381c31..9bdd959260a5 100644
--- a/drivers/gpu/drm/i915/intel_crt.c
+++ b/drivers/gpu/drm/i915/intel_crt.c
@@ -41,7 +41,7 @@ static void intel_crt_dpms(struct drm_encoder *encoder, int mode)
 
 	temp = I915_READ(ADPA);
 	temp &= ~(ADPA_HSYNC_CNTL_DISABLE | ADPA_VSYNC_CNTL_DISABLE);
-	temp &= ~ADPA_DAC_ENABLE;
+	temp |= ADPA_DAC_ENABLE;
 
 	switch(mode) {
 	case DRM_MODE_DPMS_ON:
@@ -158,7 +158,7 @@ static bool intel_crt_detect_hotplug(struct drm_connector *connector)
 	else
 		tries = 1;
 	hotplug_en = I915_READ(PORT_HOTPLUG_EN);
-	hotplug_en &= ~(CRT_HOTPLUG_MASK);
+	hotplug_en &= CRT_FORCE_HOTPLUG_MASK;
 	hotplug_en |= CRT_HOTPLUG_FORCE_DETECT;
 
 	if (IS_GM45(dev))
diff --git a/drivers/gpu/drm/i915/intel_display.c b/drivers/gpu/drm/i915/intel_display.c
index d9c50ff94d76..64773ce52964 100644
--- a/drivers/gpu/drm/i915/intel_display.c
+++ b/drivers/gpu/drm/i915/intel_display.c
@@ -636,7 +636,7 @@ void
 intel_wait_for_vblank(struct drm_device *dev)
 {
 	/* Wait for 20ms, i.e. one cycle at 50hz. */
-	udelay(20000);
+	mdelay(20);
 }
 
 static int
@@ -1106,6 +1106,26 @@ static int intel_crtc_mode_set(struct drm_crtc *crtc,
 		return -EINVAL;
 	}
 
+	/* SDVO TV has fixed PLL values depend on its clock range,
+	   this mirrors vbios setting. */
+	if (is_sdvo && is_tv) {
+		if (adjusted_mode->clock >= 100000
+				&& adjusted_mode->clock < 140500) {
+			clock.p1 = 2;
+			clock.p2 = 10;
+			clock.n = 3;
+			clock.m1 = 16;
+			clock.m2 = 8;
+		} else if (adjusted_mode->clock >= 140500
+				&& adjusted_mode->clock <= 200000) {
+			clock.p1 = 1;
+			clock.p2 = 10;
+			clock.n = 6;
+			clock.m1 = 12;
+			clock.m2 = 8;
+		}
+	}
+
 	if (IS_IGD(dev))
 		fp = (1 << clock.n) << 16 | clock.m1 << 8 | clock.m2;
 	else
diff --git a/drivers/gpu/drm/i915/intel_modes.c b/drivers/gpu/drm/i915/intel_modes.c
index e42019e5d661..07d7ec976168 100644
--- a/drivers/gpu/drm/i915/intel_modes.c
+++ b/drivers/gpu/drm/i915/intel_modes.c
@@ -76,6 +76,7 @@ int intel_ddc_get_modes(struct intel_output *intel_output)
 		drm_mode_connector_update_edid_property(&intel_output->base,
 							edid);
 		ret = drm_add_edid_modes(&intel_output->base, edid);
+		intel_output->base.display_info.raw_edid = NULL;
 		kfree(edid);
 	}
 
diff --git a/drivers/gpu/drm/i915/intel_sdvo.c b/drivers/gpu/drm/i915/intel_sdvo.c
index fbe6f3931b1b..7b31f55f55c8 100644
--- a/drivers/gpu/drm/i915/intel_sdvo.c
+++ b/drivers/gpu/drm/i915/intel_sdvo.c
@@ -273,20 +273,20 @@ static void intel_sdvo_debug_write(struct intel_output *intel_output, u8 cmd,
 	struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv;
 	int i;
 
-	DRM_DEBUG("%s: W: %02X ", SDVO_NAME(sdvo_priv), cmd);
+	printk(KERN_DEBUG "%s: W: %02X ", SDVO_NAME(sdvo_priv), cmd);
 	for (i = 0; i < args_len; i++)
-		printk("%02X ", ((u8 *)args)[i]);
+		printk(KERN_DEBUG "%02X ", ((u8 *)args)[i]);
 	for (; i < 8; i++)
-		printk("   ");
+		printk(KERN_DEBUG "   ");
 	for (i = 0; i < sizeof(sdvo_cmd_names) / sizeof(sdvo_cmd_names[0]); i++) {
 		if (cmd == sdvo_cmd_names[i].cmd) {
-			printk("(%s)", sdvo_cmd_names[i].name);
+			printk(KERN_DEBUG "(%s)", sdvo_cmd_names[i].name);
 			break;
 		}
 	}
 	if (i == sizeof(sdvo_cmd_names)/ sizeof(sdvo_cmd_names[0]))
-		printk("(%02X)",cmd);
-	printk("\n");
+		printk(KERN_DEBUG "(%02X)", cmd);
+	printk(KERN_DEBUG "\n");
 }
 #else
 #define intel_sdvo_debug_write(o, c, a, l)
@@ -323,17 +323,18 @@ static void intel_sdvo_debug_response(struct intel_output *intel_output,
 				      u8 status)
 {
 	struct intel_sdvo_priv *sdvo_priv = intel_output->dev_priv;
+	int i;
 
-	DRM_DEBUG("%s: R: ", SDVO_NAME(sdvo_priv));
+	printk(KERN_DEBUG "%s: R: ", SDVO_NAME(sdvo_priv));
 	for (i = 0; i < response_len; i++)
-		printk("%02X ", ((u8 *)response)[i]);
+		printk(KERN_DEBUG "%02X ", ((u8 *)response)[i]);
 	for (; i < 8; i++)
-		printk("   ");
+		printk(KERN_DEBUG "   ");
 	if (status <= SDVO_CMD_STATUS_SCALING_NOT_SUPP)
-		printk("(%s)", cmd_status_names[status]);
+		printk(KERN_DEBUG "(%s)", cmd_status_names[status]);
 	else
-		printk("(??? %d)", status);
-	printk("\n");
+		printk(KERN_DEBUG "(??? %d)", status);
+	printk(KERN_DEBUG "\n");
 }
 #else
 #define intel_sdvo_debug_response(o, r, l, s)
@@ -588,9 +589,12 @@ intel_sdvo_create_preferred_input_timing(struct intel_output *output,
 	struct intel_sdvo_preferred_input_timing_args args;
 	uint8_t status;
 
+	memset(&args, 0, sizeof(args));
 	args.clock = clock;
 	args.width = width;
 	args.height = height;
+	args.interlace = 0;
+	args.scaled = 0;
 	intel_sdvo_write_cmd(output, SDVO_CMD_CREATE_PREFERRED_INPUT_TIMING,
 			     &args, sizeof(args));
 	status = intel_sdvo_read_response(output, NULL, 0);
@@ -683,7 +687,7 @@ static void intel_sdvo_get_dtd_from_mode(struct intel_sdvo_dtd *dtd,
 	dtd->part1.v_high = (((height >> 8) & 0xf) << 4) |
 		((v_blank_len >> 8) & 0xf);
 
-	dtd->part2.h_sync_off = h_sync_offset;
+	dtd->part2.h_sync_off = h_sync_offset & 0xff;
 	dtd->part2.h_sync_width = h_sync_len & 0xff;
 	dtd->part2.v_sync_off_width = (v_sync_offset & 0xf) << 4 |
 		(v_sync_len & 0xf);
@@ -705,27 +709,10 @@ static void intel_sdvo_get_dtd_from_mode(struct intel_sdvo_dtd *dtd,
 static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode * mode,
 					 struct intel_sdvo_dtd *dtd)
 {
-	uint16_t width, height;
-	uint16_t h_blank_len, h_sync_len, v_blank_len, v_sync_len;
-	uint16_t h_sync_offset, v_sync_offset;
-
-	width = mode->crtc_hdisplay;
-	height = mode->crtc_vdisplay;
-
-	/* do some mode translations */
-	h_blank_len = mode->crtc_hblank_end - mode->crtc_hblank_start;
-	h_sync_len = mode->crtc_hsync_end - mode->crtc_hsync_start;
-
-	v_blank_len = mode->crtc_vblank_end - mode->crtc_vblank_start;
-	v_sync_len = mode->crtc_vsync_end - mode->crtc_vsync_start;
-
-	h_sync_offset = mode->crtc_hsync_start - mode->crtc_hblank_start;
-	v_sync_offset = mode->crtc_vsync_start - mode->crtc_vblank_start;
-
 	mode->hdisplay = dtd->part1.h_active;
 	mode->hdisplay += ((dtd->part1.h_high >> 4) & 0x0f) << 8;
 	mode->hsync_start = mode->hdisplay + dtd->part2.h_sync_off;
-	mode->hsync_start += (dtd->part2.sync_off_width_high & 0xa0) << 2;
+	mode->hsync_start += (dtd->part2.sync_off_width_high & 0xc0) << 2;
 	mode->hsync_end = mode->hsync_start + dtd->part2.h_sync_width;
 	mode->hsync_end += (dtd->part2.sync_off_width_high & 0x30) << 4;
 	mode->htotal = mode->hdisplay + dtd->part1.h_blank;
@@ -735,7 +722,7 @@ static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode * mode,
 	mode->vdisplay += ((dtd->part1.v_high >> 4) & 0x0f) << 8;
 	mode->vsync_start = mode->vdisplay;
 	mode->vsync_start += (dtd->part2.v_sync_off_width >> 4) & 0xf;
-	mode->vsync_start += (dtd->part2.sync_off_width_high & 0x0a) << 2;
+	mode->vsync_start += (dtd->part2.sync_off_width_high & 0x0c) << 2;
 	mode->vsync_start += dtd->part2.v_sync_off_high & 0xc0;
 	mode->vsync_end = mode->vsync_start +
 		(dtd->part2.v_sync_off_width & 0xf);
@@ -745,7 +732,7 @@ static void intel_sdvo_get_mode_from_dtd(struct drm_display_mode * mode,
 
 	mode->clock = dtd->part1.clock * 10;
 
-	mode->flags &= (DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC);
+	mode->flags &= ~(DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC);
 	if (dtd->part2.dtd_flags & 0x2)
 		mode->flags |= DRM_MODE_FLAG_PHSYNC;
 	if (dtd->part2.dtd_flags & 0x4)
@@ -924,6 +911,27 @@ static void intel_sdvo_set_avi_infoframe(struct intel_output *output,
 				SDVO_HBUF_TX_VSYNC);
 }
 
+static void intel_sdvo_set_tv_format(struct intel_output *output)
+{
+	struct intel_sdvo_priv *sdvo_priv = output->dev_priv;
+	struct intel_sdvo_tv_format *format, unset;
+	u8 status;
+
+	format = &sdvo_priv->tv_format;
+	memset(&unset, 0, sizeof(unset));
+	if (memcmp(format, &unset, sizeof(*format))) {
+		DRM_DEBUG("%s: Choosing default TV format of NTSC-M\n",
+				SDVO_NAME(sdvo_priv));
+		format->ntsc_m = 1;
+		intel_sdvo_write_cmd(output, SDVO_CMD_SET_TV_FORMAT, format,
+				sizeof(*format));
+		status = intel_sdvo_read_response(output, NULL, 0);
+		if (status != SDVO_CMD_STATUS_SUCCESS)
+			DRM_DEBUG("%s: Failed to set TV format\n",
+					SDVO_NAME(sdvo_priv));
+	}
+}
+
 static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder,
 				  struct drm_display_mode *mode,
 				  struct drm_display_mode *adjusted_mode)
@@ -968,6 +976,12 @@ static bool intel_sdvo_mode_fixup(struct drm_encoder *encoder,
 							     &input_dtd);
 			intel_sdvo_get_mode_from_dtd(adjusted_mode, &input_dtd);
 
+			drm_mode_set_crtcinfo(adjusted_mode, 0);
+
+			mode->clock = adjusted_mode->clock;
+
+			adjusted_mode->clock *=
+				intel_sdvo_get_pixel_multiplier(mode);
 		} else {
 			return false;
 		}
@@ -1012,7 +1026,12 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder,
 		sdvox |= SDVO_AUDIO_ENABLE;
 	}
 
-	intel_sdvo_get_dtd_from_mode(&input_dtd, mode);
+	/* We have tried to get input timing in mode_fixup, and filled into
+	   adjusted_mode */
+	if (sdvo_priv->is_tv)
+		intel_sdvo_get_dtd_from_mode(&input_dtd, adjusted_mode);
+	else
+		intel_sdvo_get_dtd_from_mode(&input_dtd, mode);
 
 	/* If it's a TV, we already set the output timing in mode_fixup.
 	 * Otherwise, the output timing is equal to the input timing.
@@ -1027,6 +1046,9 @@ static void intel_sdvo_mode_set(struct drm_encoder *encoder,
 	/* Set the input timing to the screen. Assume always input 0. */
 	intel_sdvo_set_target_input(output, true, false);
 
+	if (sdvo_priv->is_tv)
+		intel_sdvo_set_tv_format(output);
+
 	/* We would like to use intel_sdvo_create_preferred_input_timing() to
 	 * provide the device with a timing it can support, if it supports that
 	 * feature.  However, presumably we would need to adjust the CRTC to
@@ -1395,7 +1417,7 @@ static void
 intel_sdvo_check_tv_format(struct intel_output *output)
 {
 	struct intel_sdvo_priv *dev_priv = output->dev_priv;
-	struct intel_sdvo_tv_format format, unset;
+	struct intel_sdvo_tv_format format;
 	uint8_t status;
 
 	intel_sdvo_write_cmd(output, SDVO_CMD_GET_TV_FORMAT, NULL, 0);
@@ -1403,15 +1425,7 @@ intel_sdvo_check_tv_format(struct intel_output *output)
 	if (status != SDVO_CMD_STATUS_SUCCESS)
 		return;
 
-	memset(&unset, 0, sizeof(unset));
-	if (memcmp(&format, &unset, sizeof(format))) {
-		DRM_DEBUG("%s: Choosing default TV format of NTSC-M\n",
-			  SDVO_NAME(dev_priv));
-
-		format.ntsc_m = true;
-		intel_sdvo_write_cmd(output, SDVO_CMD_SET_TV_FORMAT, NULL, 0);
-		status = intel_sdvo_read_response(output, NULL, 0);
-	}
+	memcpy(&dev_priv->tv_format, &format, sizeof(format));
 }
 
 /*
@@ -1420,68 +1434,70 @@ intel_sdvo_check_tv_format(struct intel_output *output)
  * XXX: all 60Hz refresh?
  */
 struct drm_display_mode sdvo_tv_modes[] = {
-	{ DRM_MODE("320x200", DRM_MODE_TYPE_DRIVER, 5815680, 321, 384, 416,
-		   200, 0, 232, 201, 233, 4196112, 0,
+	{ DRM_MODE("320x200", DRM_MODE_TYPE_DRIVER, 5815, 320, 321, 384,
+		   416, 0, 200, 201, 232, 233, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("320x240", DRM_MODE_TYPE_DRIVER, 6814080, 321, 384, 416,
-		   240, 0, 272, 241, 273, 4196112, 0,
+	{ DRM_MODE("320x240", DRM_MODE_TYPE_DRIVER, 6814, 320, 321, 384,
+		   416, 0, 240, 241, 272, 273, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("400x300", DRM_MODE_TYPE_DRIVER, 9910080, 401, 464, 496,
-		   300, 0, 332, 301, 333, 4196112, 0,
+	{ DRM_MODE("400x300", DRM_MODE_TYPE_DRIVER, 9910, 400, 401, 464,
+		   496, 0, 300, 301, 332, 333, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("640x350", DRM_MODE_TYPE_DRIVER, 16913280, 641, 704, 736,
-		   350, 0, 382, 351, 383, 4196112, 0,
+	{ DRM_MODE("640x350", DRM_MODE_TYPE_DRIVER, 16913, 640, 641, 704,
+		   736, 0, 350, 351, 382, 383, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("640x400", DRM_MODE_TYPE_DRIVER, 19121280, 641, 704, 736,
-		   400, 0, 432, 401, 433, 4196112, 0,
+	{ DRM_MODE("640x400", DRM_MODE_TYPE_DRIVER, 19121, 640, 641, 704,
+		   736, 0, 400, 401, 432, 433, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("640x400", DRM_MODE_TYPE_DRIVER, 19121280, 641, 704, 736,
-		   400, 0, 432, 401, 433, 4196112, 0,
+	{ DRM_MODE("640x480", DRM_MODE_TYPE_DRIVER, 22654, 640, 641, 704,
+		   736, 0, 480, 481, 512, 513, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("704x480", DRM_MODE_TYPE_DRIVER, 24624000, 705, 768, 800,
-		   480, 0, 512, 481, 513, 4196112, 0,
+	{ DRM_MODE("704x480", DRM_MODE_TYPE_DRIVER, 24624, 704, 705, 768,
+		   800, 0, 480, 481, 512, 513, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("704x576", DRM_MODE_TYPE_DRIVER, 29232000, 705, 768, 800,
-		   576, 0, 608, 577, 609, 4196112, 0,
+	{ DRM_MODE("704x576", DRM_MODE_TYPE_DRIVER, 29232, 704, 705, 768,
+		   800, 0, 576, 577, 608, 609, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("720x350", DRM_MODE_TYPE_DRIVER, 18751680, 721, 784, 816,
-		   350, 0, 382, 351, 383, 4196112, 0,
+	{ DRM_MODE("720x350", DRM_MODE_TYPE_DRIVER, 18751, 720, 721, 784,
+		   816, 0, 350, 351, 382, 383, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("720x400", DRM_MODE_TYPE_DRIVER, 21199680, 721, 784, 816,
-		   400, 0, 432, 401, 433, 4196112, 0,
+	{ DRM_MODE("720x400", DRM_MODE_TYPE_DRIVER, 21199, 720, 721, 784,
+		   816, 0, 400, 401, 432, 433, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 25116480, 721, 784, 816,
-		   480, 0, 512, 481, 513, 4196112, 0,
+	{ DRM_MODE("720x480", DRM_MODE_TYPE_DRIVER, 25116, 720, 721, 784,
+		   816, 0, 480, 481, 512, 513, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("720x540", DRM_MODE_TYPE_DRIVER, 28054080, 721, 784, 816,
-		   540, 0, 572, 541, 573, 4196112, 0,
+	{ DRM_MODE("720x540", DRM_MODE_TYPE_DRIVER, 28054, 720, 721, 784,
+		   816, 0, 540, 541, 572, 573, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 29816640, 721, 784, 816,
-		   576, 0, 608, 577, 609, 4196112, 0,
+	{ DRM_MODE("720x576", DRM_MODE_TYPE_DRIVER, 29816, 720, 721, 784,
+		   816, 0, 576, 577, 608, 609, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("768x576", DRM_MODE_TYPE_DRIVER, 31570560, 769, 832, 864,
-		   576, 0, 608, 577, 609, 4196112, 0,
+	{ DRM_MODE("768x576", DRM_MODE_TYPE_DRIVER, 31570, 768, 769, 832,
+		   864, 0, 576, 577, 608, 609, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 34030080, 801, 864, 896,
-		   600, 0, 632, 601, 633, 4196112, 0,
+	{ DRM_MODE("800x600", DRM_MODE_TYPE_DRIVER, 34030, 800, 801, 864,
+		   896, 0, 600, 601, 632, 633, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("832x624", DRM_MODE_TYPE_DRIVER, 36581760, 833, 896, 928,
-		   624, 0, 656, 625, 657, 4196112, 0,
+	{ DRM_MODE("832x624", DRM_MODE_TYPE_DRIVER, 36581, 832, 833, 896,
+		   928, 0, 624, 625, 656, 657, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("920x766", DRM_MODE_TYPE_DRIVER, 48707040, 921, 984, 1016,
-		   766, 0, 798, 767, 799, 4196112, 0,
+	{ DRM_MODE("920x766", DRM_MODE_TYPE_DRIVER, 48707, 920, 921, 984,
+		   1016, 0, 766, 767, 798, 799, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 53827200, 1025, 1088, 1120,
-		   768, 0, 800, 769, 801, 4196112, 0,
+	{ DRM_MODE("1024x768", DRM_MODE_TYPE_DRIVER, 53827, 1024, 1025, 1088,
+		   1120, 0, 768, 769, 800, 801, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
-	{ DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 87265920, 1281, 1344, 1376,
-		   1024, 0, 1056, 1025, 1057, 4196112, 0,
+	{ DRM_MODE("1280x1024", DRM_MODE_TYPE_DRIVER, 87265, 1280, 1281, 1344,
+		   1376, 0, 1024, 1025, 1056, 1057, 0,
 		   DRM_MODE_FLAG_PHSYNC | DRM_MODE_FLAG_PVSYNC) },
 };
 
 static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 {
 	struct intel_output *output = to_intel_output(connector);
+	struct intel_sdvo_priv *sdvo_priv = output->dev_priv;
+	struct intel_sdvo_sdtv_resolution_request tv_res;
 	uint32_t reply = 0;
 	uint8_t status;
 	int i = 0;
@@ -1491,15 +1507,22 @@ static void intel_sdvo_get_tv_modes(struct drm_connector *connector)
 	/* Read the list of supported input resolutions for the selected TV
 	 * format.
 	 */
+	memset(&tv_res, 0, sizeof(tv_res));
+	memcpy(&tv_res, &sdvo_priv->tv_format, sizeof(tv_res));
 	intel_sdvo_write_cmd(output, SDVO_CMD_GET_SDTV_RESOLUTION_SUPPORT,
-			     NULL, 0);
+			     &tv_res, sizeof(tv_res));
 	status = intel_sdvo_read_response(output, &reply, 3);
 	if (status != SDVO_CMD_STATUS_SUCCESS)
 		return;
 
 	for (i = 0; i < ARRAY_SIZE(sdvo_tv_modes); i++)
-		if (reply & (1 << i))
-			drm_mode_probed_add(connector, &sdvo_tv_modes[i]);
+		if (reply & (1 << i)) {
+			struct drm_display_mode *nmode;
+			nmode = drm_mode_duplicate(connector->dev,
+					&sdvo_tv_modes[i]);
+			if (nmode)
+				drm_mode_probed_add(connector, nmode);
+		}
 }
 
 static int intel_sdvo_get_modes(struct drm_connector *connector)
diff --git a/drivers/gpu/drm/i915/intel_sdvo_regs.h b/drivers/gpu/drm/i915/intel_sdvo_regs.h
index 1117b9c151a6..193938b7d7f9 100644
--- a/drivers/gpu/drm/i915/intel_sdvo_regs.h
+++ b/drivers/gpu/drm/i915/intel_sdvo_regs.h
@@ -100,6 +100,9 @@ struct intel_sdvo_preferred_input_timing_args {
     u16 clock;
     u16 width;
     u16 height;
+    u8	interlace:1;
+    u8	scaled:1;
+    u8	pad:6;
 } __attribute__((packed));
 
 /* I2C registers for SDVO */
diff --git a/drivers/gpu/drm/i915/intel_tv.c b/drivers/gpu/drm/i915/intel_tv.c
index ceca9471a75a..d2c32983242d 100644
--- a/drivers/gpu/drm/i915/intel_tv.c
+++ b/drivers/gpu/drm/i915/intel_tv.c
@@ -1570,33 +1570,49 @@ intel_tv_set_property(struct drm_connector *connector, struct drm_property *prop
 	struct drm_device *dev = connector->dev;
 	struct intel_output *intel_output = to_intel_output(connector);
 	struct intel_tv_priv *tv_priv = intel_output->dev_priv;
+	struct drm_encoder *encoder = &intel_output->enc;
+	struct drm_crtc *crtc = encoder->crtc;
 	int ret = 0;
+	bool changed = false;
 
 	ret = drm_connector_property_set_value(connector, property, val);
 	if (ret < 0)
 		goto out;
 
-	if (property == dev->mode_config.tv_left_margin_property)
+	if (property == dev->mode_config.tv_left_margin_property &&
+		tv_priv->margin[TV_MARGIN_LEFT] != val) {
 		tv_priv->margin[TV_MARGIN_LEFT] = val;
-	else if (property == dev->mode_config.tv_right_margin_property)
+		changed = true;
+	} else if (property == dev->mode_config.tv_right_margin_property &&
+		tv_priv->margin[TV_MARGIN_RIGHT] != val) {
 		tv_priv->margin[TV_MARGIN_RIGHT] = val;
-	else if (property == dev->mode_config.tv_top_margin_property)
+		changed = true;
+	} else if (property == dev->mode_config.tv_top_margin_property &&
+		tv_priv->margin[TV_MARGIN_TOP] != val) {
 		tv_priv->margin[TV_MARGIN_TOP] = val;
-	else if (property == dev->mode_config.tv_bottom_margin_property)
+		changed = true;
+	} else if (property == dev->mode_config.tv_bottom_margin_property &&
+		tv_priv->margin[TV_MARGIN_BOTTOM] != val) {
 		tv_priv->margin[TV_MARGIN_BOTTOM] = val;
-	else if (property == dev->mode_config.tv_mode_property) {
+		changed = true;
+	} else if (property == dev->mode_config.tv_mode_property) {
 		if (val >= NUM_TV_MODES) {
 			ret = -EINVAL;
 			goto out;
 		}
+		if (!strcmp(tv_priv->tv_format, tv_modes[val].name))
+			goto out;
+
 		tv_priv->tv_format = tv_modes[val].name;
-		intel_tv_mode_set(&intel_output->enc, NULL, NULL);
+		changed = true;
 	} else {
 		ret = -EINVAL;
 		goto out;
 	}
 
-	intel_tv_mode_set(&intel_output->enc, NULL, NULL);
+	if (changed && crtc)
+		drm_crtc_helper_set_mode(crtc, &crtc->mode, crtc->x,
+				crtc->y, crtc->fb);
 out:
 	return ret;
 }
diff --git a/drivers/gpu/drm/radeon/r600_cp.c b/drivers/gpu/drm/radeon/r600_cp.c
index 9d14eee3ed09..bc9d09dfa8e7 100644
--- a/drivers/gpu/drm/radeon/r600_cp.c
+++ b/drivers/gpu/drm/radeon/r600_cp.c
@@ -388,17 +388,17 @@ static void r600_cp_load_microcode(drm_radeon_private_t *dev_priv)
 		DRM_INFO("Loading RS780 CP Microcode\n");
 		for (i = 0; i < PM4_UCODE_SIZE; i++) {
 			RADEON_WRITE(R600_CP_ME_RAM_DATA,
-				     RV670_cp_microcode[i][0]);
+				     RS780_cp_microcode[i][0]);
 			RADEON_WRITE(R600_CP_ME_RAM_DATA,
-				     RV670_cp_microcode[i][1]);
+				     RS780_cp_microcode[i][1]);
 			RADEON_WRITE(R600_CP_ME_RAM_DATA,
-				     RV670_cp_microcode[i][2]);
+				     RS780_cp_microcode[i][2]);
 		}
 
 		RADEON_WRITE(R600_CP_PFP_UCODE_ADDR, 0);
 		DRM_INFO("Loading RS780 PFP Microcode\n");
 		for (i = 0; i < PFP_UCODE_SIZE; i++)
-			RADEON_WRITE(R600_CP_PFP_UCODE_DATA, RV670_pfp_microcode[i]);
+			RADEON_WRITE(R600_CP_PFP_UCODE_DATA, RS780_pfp_microcode[i]);
 	}
 	RADEON_WRITE(R600_CP_PFP_UCODE_ADDR, 0);
 	RADEON_WRITE(R600_CP_ME_RAM_WADDR, 0);
diff --git a/drivers/hid/Kconfig b/drivers/hid/Kconfig
index e85c8fe9ffcf..7e67dcb3d4f6 100644
--- a/drivers/hid/Kconfig
+++ b/drivers/hid/Kconfig
@@ -29,11 +29,11 @@ config HID
 
 	  For docs and specs, see http://www.usb.org/developers/hidpage/
 
-	  If unsure, say Y
+	  If unsure, say Y.
 
 config HID_DEBUG
 	bool "HID debugging support"
-	default y if !EMBEDDED
+	default y
 	depends on HID
 	---help---
 	This option lets the HID layer output diagnostics about its internal
@@ -44,7 +44,7 @@ config HID_DEBUG
 	This feature is useful for those who are either debugging the HID parser
 	or any HID hardware device.
 
-	If unsure, say N
+	If unsure, say Y.
 
 config HIDRAW
 	bool "/dev/hidraw raw HID device support"
@@ -70,18 +70,6 @@ source "drivers/hid/usbhid/Kconfig"
 menu "Special HID drivers"
 	depends on HID
 
-config HID_COMPAT
-	bool "Load all HID drivers on hid core load"
-	default y
-	---help---
-	Compatible option for older userspace. If you have system without udev
-	support of module loading through aliases and also old
-	module-init-tools which can't handle hid bus, choose Y here. Otherwise
-	say N. If you say N and your userspace is old enough, the only
-	functionality you lose is modules autoloading.
-
-	If unsure, say Y.
-
 config HID_A4TECH
 	tristate "A4 tech" if EMBEDDED
 	depends on USB_HID
@@ -128,6 +116,14 @@ config HID_CYPRESS
 	---help---
 	Support for cypress mouse and barcode readers.
 
+config DRAGONRISE_FF
+	tristate "DragonRise Inc. force feedback support"
+	depends on USB_HID
+	select INPUT_FF_MEMLESS
+	---help---
+	Say Y here if you want to enable force feedback support for DragonRise Inc.
+	game controllers.
+
 config HID_EZKEY
 	tristate "Ezkey" if EMBEDDED
 	depends on USB_HID
@@ -135,6 +131,13 @@ config HID_EZKEY
 	---help---
 	Support for Ezkey BTC 8193 keyboard.
 
+config HID_KYE
+	tristate "Kye" if EMBEDDED
+	depends on USB_HID
+	default !EMBEDDED
+	---help---
+	Support for Kye/Genius Ergo Mouse.
+
 config HID_GYRATION
 	tristate "Gyration" if EMBEDDED
 	depends on USB_HID
@@ -142,6 +145,13 @@ config HID_GYRATION
 	---help---
 	Support for Gyration remote control.
 
+config HID_KENSINGTON
+	tristate "Kensington" if EMBEDDED
+	depends on USB_HID
+	default !EMBEDDED
+	---help---
+	Support for Kensington Slimblade Trackball.
+
 config HID_LOGITECH
 	tristate "Logitech" if EMBEDDED
 	depends on USB_HID
@@ -243,7 +253,7 @@ config GREENASIA_FF
 	select INPUT_FF_MEMLESS
 	---help---
 	Say Y here if you have a GreenAsia (Product ID 0x12) based game controller
-	(like MANTA Warior MM816 and SpeedLink Strike2 SL-6635) or adapter
+	(like MANTA Warrior MM816 and SpeedLink Strike2 SL-6635) or adapter
 	and want to enable force feedback support for it.
 
 config HID_TOPSEED
diff --git a/drivers/hid/Makefile b/drivers/hid/Makefile
index fbd021f153f1..1f7cb0fd4505 100644
--- a/drivers/hid/Makefile
+++ b/drivers/hid/Makefile
@@ -8,10 +8,6 @@ obj-$(CONFIG_HID)		+= hid.o
 hid-$(CONFIG_HID_DEBUG)		+= hid-debug.o
 hid-$(CONFIG_HIDRAW)		+= hidraw.o
 
-ifdef CONFIG_HID_COMPAT
-obj-m				+= hid-dummy.o
-endif
-
 hid-logitech-objs		:= hid-lg.o
 ifdef CONFIG_LOGITECH_FF
 	hid-logitech-objs	+= hid-lgff.o
@@ -26,8 +22,11 @@ obj-$(CONFIG_HID_BELKIN)	+= hid-belkin.o
 obj-$(CONFIG_HID_CHERRY)	+= hid-cherry.o
 obj-$(CONFIG_HID_CHICONY)	+= hid-chicony.o
 obj-$(CONFIG_HID_CYPRESS)	+= hid-cypress.o
+obj-$(CONFIG_DRAGONRISE_FF)	+= hid-drff.o
 obj-$(CONFIG_HID_EZKEY)		+= hid-ezkey.o
 obj-$(CONFIG_HID_GYRATION)	+= hid-gyration.o
+obj-$(CONFIG_HID_KENSINGTON)	+= hid-kensington.o
+obj-$(CONFIG_HID_KYE)		+= hid-kye.o
 obj-$(CONFIG_HID_LOGITECH)	+= hid-logitech.o
 obj-$(CONFIG_HID_MICROSOFT)	+= hid-microsoft.o
 obj-$(CONFIG_HID_MONTEREY)	+= hid-monterey.o
diff --git a/drivers/hid/hid-a4tech.c b/drivers/hid/hid-a4tech.c
index ebca00e6c103..42ea359e94cf 100644
--- a/drivers/hid/hid-a4tech.c
+++ b/drivers/hid/hid-a4tech.c
@@ -158,5 +158,3 @@ static void a4_exit(void)
 module_init(a4_init);
 module_exit(a4_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(a4tech);
diff --git a/drivers/hid/hid-apple.c b/drivers/hid/hid-apple.c
index aa28aed0e46c..7359d9d88e46 100644
--- a/drivers/hid/hid-apple.c
+++ b/drivers/hid/hid-apple.c
@@ -53,7 +53,7 @@ struct apple_key_translation {
 	u8 flags;
 };
 
-static struct apple_key_translation apple_fn_keys[] = {
+static const struct apple_key_translation apple_fn_keys[] = {
 	{ KEY_BACKSPACE, KEY_DELETE },
 	{ KEY_ENTER,	KEY_INSERT },
 	{ KEY_F1,	KEY_BRIGHTNESSDOWN, APPLE_FLAG_FKEY },
@@ -75,7 +75,7 @@ static struct apple_key_translation apple_fn_keys[] = {
 	{ }
 };
 
-static struct apple_key_translation powerbook_fn_keys[] = {
+static const struct apple_key_translation powerbook_fn_keys[] = {
 	{ KEY_BACKSPACE, KEY_DELETE },
 	{ KEY_F1,	KEY_BRIGHTNESSDOWN,     APPLE_FLAG_FKEY },
 	{ KEY_F2,	KEY_BRIGHTNESSUP,       APPLE_FLAG_FKEY },
@@ -94,7 +94,7 @@ static struct apple_key_translation powerbook_fn_keys[] = {
 	{ }
 };
 
-static struct apple_key_translation powerbook_numlock_keys[] = {
+static const struct apple_key_translation powerbook_numlock_keys[] = {
 	{ KEY_J,	KEY_KP1 },
 	{ KEY_K,	KEY_KP2 },
 	{ KEY_L,	KEY_KP3 },
@@ -117,16 +117,16 @@ static struct apple_key_translation powerbook_numlock_keys[] = {
 	{ }
 };
 
-static struct apple_key_translation apple_iso_keyboard[] = {
+static const struct apple_key_translation apple_iso_keyboard[] = {
 	{ KEY_GRAVE,	KEY_102ND },
 	{ KEY_102ND,	KEY_GRAVE },
 	{ }
 };
 
-static struct apple_key_translation *apple_find_translation(
-		struct apple_key_translation *table, u16 from)
+static const struct apple_key_translation *apple_find_translation(
+		const struct apple_key_translation *table, u16 from)
 {
-	struct apple_key_translation *trans;
+	const struct apple_key_translation *trans;
 
 	/* Look for the translation */
 	for (trans = table; trans->from; trans++)
@@ -140,7 +140,7 @@ static int hidinput_apple_event(struct hid_device *hid, struct input_dev *input,
 		struct hid_usage *usage, __s32 value)
 {
 	struct apple_sc *asc = hid_get_drvdata(hid);
-	struct apple_key_translation *trans;
+	const struct apple_key_translation *trans;
 
 	if (usage->code == KEY_FN) {
 		asc->fn_on = !!value;
@@ -253,7 +253,7 @@ static void apple_report_fixup(struct hid_device *hdev, __u8 *rdesc,
 
 static void apple_setup_input(struct input_dev *input)
 {
-	struct apple_key_translation *trans;
+	const struct apple_key_translation *trans;
 
 	set_bit(KEY_NUMLOCK, input->keybit);
 
@@ -387,6 +387,12 @@ static const struct hid_device_id apple_devices[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_JIS),
 		.driver_data = APPLE_NUMLOCK_EMULATION | APPLE_HAS_FN |
 			APPLE_RDESC_JIS },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ANSI),
+		.driver_data = APPLE_HAS_FN },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ISO),
+		.driver_data = APPLE_HAS_FN | APPLE_ISO_KEYBOARD },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_JIS),
+		.driver_data = APPLE_HAS_FN },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ANSI),
 		.driver_data = APPLE_HAS_FN },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ISO),
@@ -468,5 +474,3 @@ static void apple_exit(void)
 module_init(apple_init);
 module_exit(apple_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(apple);
diff --git a/drivers/hid/hid-belkin.c b/drivers/hid/hid-belkin.c
index 12c8a9ba6ed6..2f6723133a4b 100644
--- a/drivers/hid/hid-belkin.c
+++ b/drivers/hid/hid-belkin.c
@@ -101,5 +101,3 @@ static void belkin_exit(void)
 module_init(belkin_init);
 module_exit(belkin_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(belkin);
diff --git a/drivers/hid/hid-cherry.c b/drivers/hid/hid-cherry.c
index b833b9769aba..ab8209e7e45c 100644
--- a/drivers/hid/hid-cherry.c
+++ b/drivers/hid/hid-cherry.c
@@ -83,5 +83,3 @@ static void ch_exit(void)
 module_init(ch_init);
 module_exit(ch_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(cherry);
diff --git a/drivers/hid/hid-chicony.c b/drivers/hid/hid-chicony.c
index a54d4096e0f7..7f91076d8493 100644
--- a/drivers/hid/hid-chicony.c
+++ b/drivers/hid/hid-chicony.c
@@ -76,5 +76,3 @@ static void ch_exit(void)
 module_init(ch_init);
 module_exit(ch_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(chicony);
diff --git a/drivers/hid/hid-core.c b/drivers/hid/hid-core.c
index 1cc967448f4d..5746a5903bce 100644
--- a/drivers/hid/hid-core.c
+++ b/drivers/hid/hid-core.c
@@ -1236,6 +1236,9 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_GEYSER4_JIS) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ANSI) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_ISO) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_MINI_JIS) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ANSI) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_ISO) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_APPLE, USB_DEVICE_ID_APPLE_ALU_JIS) },
@@ -1262,6 +1265,7 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_1) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_BARCODE_2) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_CYPRESS, USB_DEVICE_ID_CYPRESS_MOUSE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0006) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_EZKEY, USB_DEVICE_ID_BTC_8193) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PSX_ADAPTOR) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR) },
@@ -1269,6 +1273,8 @@ static const struct hid_device_id hid_blacklist[] = {
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, 0x0012) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GYRATION, USB_DEVICE_ID_GYRATION_REMOTE) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GYRATION, USB_DEVICE_ID_GYRATION_REMOTE_2) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KENSINGTON, USB_DEVICE_ID_KS_SLIMBLADE) },
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LABTEC, USB_DEVICE_ID_LABTEC_WIRELESS_KEYBOARD) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_MX3000_RECEIVER) },
 	{ HID_USB_DEVICE(USB_VENDOR_ID_LOGITECH, USB_DEVICE_ID_S510_RECEIVER) },
@@ -1813,14 +1819,21 @@ void hid_unregister_driver(struct hid_driver *hdrv)
 }
 EXPORT_SYMBOL_GPL(hid_unregister_driver);
 
-#ifdef CONFIG_HID_COMPAT
-static void hid_compat_load(struct work_struct *ws)
+int hid_check_keys_pressed(struct hid_device *hid)
 {
-	request_module("hid-dummy");
+	struct hid_input *hidinput;
+	int i;
+
+	list_for_each_entry(hidinput, &hid->inputs, list) {
+		for (i = 0; i < BITS_TO_LONGS(KEY_MAX); i++)
+			if (hidinput->input->key[i])
+				return 1;
+	}
+
+	return 0;
 }
-static DECLARE_WORK(hid_compat_work, hid_compat_load);
-static struct workqueue_struct *hid_compat_wq;
-#endif
+
+EXPORT_SYMBOL_GPL(hid_check_keys_pressed);
 
 static int __init hid_init(void)
 {
@@ -1836,15 +1849,6 @@ static int __init hid_init(void)
 	if (ret)
 		goto err_bus;
 
-#ifdef CONFIG_HID_COMPAT
-	hid_compat_wq = create_singlethread_workqueue("hid_compat");
-	if (!hid_compat_wq) {
-		hidraw_exit();
-		goto err;
-	}
-	queue_work(hid_compat_wq, &hid_compat_work);
-#endif
-
 	return 0;
 err_bus:
 	bus_unregister(&hid_bus_type);
@@ -1854,9 +1858,6 @@ err:
 
 static void __exit hid_exit(void)
 {
-#ifdef CONFIG_HID_COMPAT
-	destroy_workqueue(hid_compat_wq);
-#endif
 	hidraw_exit();
 	bus_unregister(&hid_bus_type);
 }
diff --git a/drivers/hid/hid-cypress.c b/drivers/hid/hid-cypress.c
index 5d69d27b935d..9d6d3b91773b 100644
--- a/drivers/hid/hid-cypress.c
+++ b/drivers/hid/hid-cypress.c
@@ -154,5 +154,3 @@ static void cp_exit(void)
 module_init(cp_init);
 module_exit(cp_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(cypress);
diff --git a/drivers/hid/hid-drff.c b/drivers/hid/hid-drff.c
new file mode 100644
index 000000000000..34f3eb65100b
--- /dev/null
+++ b/drivers/hid/hid-drff.c
@@ -0,0 +1,188 @@
+/*
+ * Force feedback support for DragonRise Inc. game controllers
+ *
+ * From what I have gathered, these devices are mass produced in China and are
+ * distributed under several vendors. They often share the same design as
+ * the original PlayStation DualShock controller.
+ *
+ * 0079:0006 "DragonRise Inc.   Generic   USB  Joystick  "
+ *  - tested with a Tesun USB-703 game controller.
+ *
+ * Copyright (c) 2009 Richard Walmsley <richwalm@gmail.com>
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA
+ */
+
+#include <linux/input.h>
+#include <linux/usb.h>
+#include <linux/hid.h>
+
+#include "hid-ids.h"
+#include "usbhid/usbhid.h"
+
+struct drff_device {
+	struct hid_report *report;
+};
+
+static int drff_play(struct input_dev *dev, void *data,
+				 struct ff_effect *effect)
+{
+	struct hid_device *hid = input_get_drvdata(dev);
+	struct drff_device *drff = data;
+	int strong, weak;
+
+	strong = effect->u.rumble.strong_magnitude;
+	weak = effect->u.rumble.weak_magnitude;
+
+	dbg_hid("called with 0x%04x 0x%04x", strong, weak);
+
+	if (strong || weak) {
+		strong = strong * 0xff / 0xffff;
+		weak = weak * 0xff / 0xffff;
+
+		/* While reverse engineering this device, I found that when
+		   this value is set, it causes the strong rumble to function
+		   at a near maximum speed, so we'll bypass it. */
+		if (weak == 0x0a)
+			weak = 0x0b;
+
+		drff->report->field[0]->value[0] = 0x51;
+		drff->report->field[0]->value[1] = 0x00;
+		drff->report->field[0]->value[2] = weak;
+		drff->report->field[0]->value[4] = strong;
+		usbhid_submit_report(hid, drff->report, USB_DIR_OUT);
+
+		drff->report->field[0]->value[0] = 0xfa;
+		drff->report->field[0]->value[1] = 0xfe;
+	} else {
+		drff->report->field[0]->value[0] = 0xf3;
+		drff->report->field[0]->value[1] = 0x00;
+	}
+
+	drff->report->field[0]->value[2] = 0x00;
+	drff->report->field[0]->value[4] = 0x00;
+	dbg_hid("running with 0x%02x 0x%02x", strong, weak);
+	usbhid_submit_report(hid, drff->report, USB_DIR_OUT);
+
+	return 0;
+}
+
+static int drff_init(struct hid_device *hid)
+{
+	struct drff_device *drff;
+	struct hid_report *report;
+	struct hid_input *hidinput = list_first_entry(&hid->inputs,
+						struct hid_input, list);
+	struct list_head *report_list =
+			&hid->report_enum[HID_OUTPUT_REPORT].report_list;
+	struct input_dev *dev = hidinput->input;
+	int error;
+
+	if (list_empty(report_list)) {
+		dev_err(&hid->dev, "no output reports found\n");
+		return -ENODEV;
+	}
+
+	report = list_first_entry(report_list, struct hid_report, list);
+	if (report->maxfield < 1) {
+		dev_err(&hid->dev, "no fields in the report\n");
+		return -ENODEV;
+	}
+
+	if (report->field[0]->report_count < 7) {
+		dev_err(&hid->dev, "not enough values in the field\n");
+		return -ENODEV;
+	}
+
+	drff = kzalloc(sizeof(struct drff_device), GFP_KERNEL);
+	if (!drff)
+		return -ENOMEM;
+
+	set_bit(FF_RUMBLE, dev->ffbit);
+
+	error = input_ff_create_memless(dev, drff, drff_play);
+	if (error) {
+		kfree(drff);
+		return error;
+	}
+
+	drff->report = report;
+	drff->report->field[0]->value[0] = 0xf3;
+	drff->report->field[0]->value[1] = 0x00;
+	drff->report->field[0]->value[2] = 0x00;
+	drff->report->field[0]->value[3] = 0x00;
+	drff->report->field[0]->value[4] = 0x00;
+	drff->report->field[0]->value[5] = 0x00;
+	drff->report->field[0]->value[6] = 0x00;
+	usbhid_submit_report(hid, drff->report, USB_DIR_OUT);
+
+	dev_info(&hid->dev, "Force Feedback for DragonRise Inc. game "
+	       "controllers by Richard Walmsley <richwalm@gmail.com>\n");
+
+	return 0;
+}
+
+static int dr_probe(struct hid_device *hdev, const struct hid_device_id *id)
+{
+	int ret;
+
+	dev_dbg(&hdev->dev, "DragonRise Inc. HID hardware probe...");
+
+	ret = hid_parse(hdev);
+	if (ret) {
+		dev_err(&hdev->dev, "parse failed\n");
+		goto err;
+	}
+
+	ret = hid_hw_start(hdev, HID_CONNECT_DEFAULT & ~HID_CONNECT_FF);
+	if (ret) {
+		dev_err(&hdev->dev, "hw start failed\n");
+		goto err;
+	}
+
+	drff_init(hdev);
+
+	return 0;
+err:
+	return ret;
+}
+
+static const struct hid_device_id dr_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_DRAGONRISE, 0x0006),  },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, dr_devices);
+
+static struct hid_driver dr_driver = {
+	.name = "dragonrise",
+	.id_table = dr_devices,
+	.probe = dr_probe,
+};
+
+static int __init dr_init(void)
+{
+	return hid_register_driver(&dr_driver);
+}
+
+static void __exit dr_exit(void)
+{
+	hid_unregister_driver(&dr_driver);
+}
+
+module_init(dr_init);
+module_exit(dr_exit);
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/hid-dummy.c b/drivers/hid/hid-dummy.c
deleted file mode 100644
index b4cc0f743d63..000000000000
--- a/drivers/hid/hid-dummy.c
+++ /dev/null
@@ -1,78 +0,0 @@
-#include <linux/autoconf.h>
-#include <linux/module.h>
-#include <linux/hid.h>
-
-static int __init hid_dummy_init(void)
-{
-#ifdef CONFIG_HID_A4TECH_MODULE
-	HID_COMPAT_CALL_DRIVER(a4tech);
-#endif
-#ifdef CONFIG_HID_APPLE_MODULE
-	HID_COMPAT_CALL_DRIVER(apple);
-#endif
-#ifdef CONFIG_HID_BELKIN_MODULE
-	HID_COMPAT_CALL_DRIVER(belkin);
-#endif
-#ifdef CONFIG_HID_BRIGHT_MODULE
-	HID_COMPAT_CALL_DRIVER(bright);
-#endif
-#ifdef CONFIG_HID_CHERRY_MODULE
-	HID_COMPAT_CALL_DRIVER(cherry);
-#endif
-#ifdef CONFIG_HID_CHICONY_MODULE
-	HID_COMPAT_CALL_DRIVER(chicony);
-#endif
-#ifdef CONFIG_HID_CYPRESS_MODULE
-	HID_COMPAT_CALL_DRIVER(cypress);
-#endif
-#ifdef CONFIG_HID_DELL_MODULE
-	HID_COMPAT_CALL_DRIVER(dell);
-#endif
-#ifdef CONFIG_HID_EZKEY_MODULE
-	HID_COMPAT_CALL_DRIVER(ezkey);
-#endif
-#ifdef CONFIG_HID_GYRATION_MODULE
-	HID_COMPAT_CALL_DRIVER(gyration);
-#endif
-#ifdef CONFIG_HID_LOGITECH_MODULE
-	HID_COMPAT_CALL_DRIVER(logitech);
-#endif
-#ifdef CONFIG_HID_MICROSOFT_MODULE
-	HID_COMPAT_CALL_DRIVER(microsoft);
-#endif
-#ifdef CONFIG_HID_MONTEREY_MODULE
-	HID_COMPAT_CALL_DRIVER(monterey);
-#endif
-#ifdef CONFIG_HID_NTRIG_MODULE
-	HID_COMPAT_CALL_DRIVER(ntrig);
-#endif
-#ifdef CONFIG_HID_PANTHERLORD_MODULE
-	HID_COMPAT_CALL_DRIVER(pantherlord);
-#endif
-#ifdef CONFIG_HID_PETALYNX_MODULE
-	HID_COMPAT_CALL_DRIVER(petalynx);
-#endif
-#ifdef CONFIG_HID_SAMSUNG_MODULE
-	HID_COMPAT_CALL_DRIVER(samsung);
-#endif
-#ifdef CONFIG_HID_SONY_MODULE
-	HID_COMPAT_CALL_DRIVER(sony);
-#endif
-#ifdef CONFIG_HID_SUNPLUS_MODULE
-	HID_COMPAT_CALL_DRIVER(sunplus);
-#endif
-#ifdef CONFIG_GREENASIA_FF_MODULE
-	HID_COMPAT_CALL_DRIVER(greenasia);
-#endif
-#ifdef CONFIG_THRUSTMASTER_FF_MODULE
-	HID_COMPAT_CALL_DRIVER(thrustmaster);
-#endif
-#ifdef CONFIG_ZEROPLUS_FF_MODULE
-	HID_COMPAT_CALL_DRIVER(zeroplus);
-#endif
-
-	return -EIO;
-}
-module_init(hid_dummy_init);
-
-MODULE_LICENSE("GPL");
diff --git a/drivers/hid/hid-ezkey.c b/drivers/hid/hid-ezkey.c
index deb42f931b7e..0a1fe054799b 100644
--- a/drivers/hid/hid-ezkey.c
+++ b/drivers/hid/hid-ezkey.c
@@ -91,5 +91,3 @@ static void ez_exit(void)
 module_init(ez_init);
 module_exit(ez_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(ezkey);
diff --git a/drivers/hid/hid-gaff.c b/drivers/hid/hid-gaff.c
index 71211f6a4f02..510ad3ab8d33 100644
--- a/drivers/hid/hid-gaff.c
+++ b/drivers/hid/hid-gaff.c
@@ -181,5 +181,3 @@ static void __exit ga_exit(void)
 module_init(ga_init);
 module_exit(ga_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(greenasia);
diff --git a/drivers/hid/hid-gyration.c b/drivers/hid/hid-gyration.c
index 04a0afec52ac..d42d222097a8 100644
--- a/drivers/hid/hid-gyration.c
+++ b/drivers/hid/hid-gyration.c
@@ -94,5 +94,3 @@ static void gyration_exit(void)
 module_init(gyration_init);
 module_exit(gyration_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(gyration);
diff --git a/drivers/hid/hid-ids.h b/drivers/hid/hid-ids.h
index 88511970508d..bdeda4c7cc13 100644
--- a/drivers/hid/hid-ids.h
+++ b/drivers/hid/hid-ids.h
@@ -67,6 +67,9 @@
 #define USB_DEVICE_ID_APPLE_GEYSER4_ANSI	0x021a
 #define USB_DEVICE_ID_APPLE_GEYSER4_ISO	0x021b
 #define USB_DEVICE_ID_APPLE_GEYSER4_JIS	0x021c
+#define USB_DEVICE_ID_APPLE_ALU_MINI_ANSI	0x021d
+#define USB_DEVICE_ID_APPLE_ALU_MINI_ISO	0x021e
+#define USB_DEVICE_ID_APPLE_ALU_MINI_JIS	0x021f
 #define USB_DEVICE_ID_APPLE_ALU_ANSI	0x0220
 #define USB_DEVICE_ID_APPLE_ALU_ISO	0x0221
 #define USB_DEVICE_ID_APPLE_ALU_JIS	0x0222
@@ -148,6 +151,8 @@
 #define USB_VENDOR_ID_DMI		0x0c0b
 #define USB_DEVICE_ID_DMI_ENC		0x5fab
 
+#define USB_VENDOR_ID_DRAGONRISE	0x0079
+
 #define USB_VENDOR_ID_ELO		0x04E7
 #define USB_DEVICE_ID_ELO_TS2700	0x0020
 
@@ -272,6 +277,9 @@
 #define USB_DEVICE_ID_LD_POWERCONTROL	0x2030
 #define USB_DEVICE_ID_LD_MACHINETEST	0x2040
 
+#define USB_VENDOR_ID_KENSINGTON	0x047d
+#define USB_DEVICE_ID_KS_SLIMBLADE	0x2041
+
 #define USB_VENDOR_ID_LOGITECH		0x046d
 #define USB_DEVICE_ID_LOGITECH_RECEIVER	0xc101
 #define USB_DEVICE_ID_LOGITECH_HARMONY_FIRST  0xc110
@@ -418,6 +426,8 @@
 #define USB_VENDOR_ID_ZEROPLUS		0x0c12
 
 #define USB_VENDOR_ID_KYE		0x0458
+#define USB_DEVICE_ID_KYE_ERGO_525V	0x0087
 #define USB_DEVICE_ID_KYE_GPEN_560	0x5003
 
+
 #endif
diff --git a/drivers/hid/hid-kensington.c b/drivers/hid/hid-kensington.c
new file mode 100644
index 000000000000..7353bd79cbe9
--- /dev/null
+++ b/drivers/hid/hid-kensington.c
@@ -0,0 +1,63 @@
+/*
+ *  HID driver for Kensigton Slimblade Trackball
+ *
+ *  Copyright (c) 2009 Jiri Kosina
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/input.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+
+#include "hid-ids.h"
+
+#define ks_map_key(c)	hid_map_usage(hi, usage, bit, max, EV_KEY, (c))
+
+static int ks_input_mapping(struct hid_device *hdev, struct hid_input *hi,
+		struct hid_field *field, struct hid_usage *usage,
+		unsigned long **bit, int *max)
+{
+	if ((usage->hid & HID_USAGE_PAGE) != HID_UP_MSVENDOR)
+		return 0;
+
+	switch (usage->hid & HID_USAGE) {
+	case 0x01: ks_map_key(BTN_MIDDLE);	break;
+	case 0x02: ks_map_key(BTN_SIDE);	break;
+	default:
+		return 0;
+	}
+	return 1;
+}
+
+static const struct hid_device_id ks_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KENSINGTON, USB_DEVICE_ID_KS_SLIMBLADE) },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, ks_devices);
+
+static struct hid_driver ks_driver = {
+	.name = "kensington",
+	.id_table = ks_devices,
+	.input_mapping = ks_input_mapping,
+};
+
+static int ks_init(void)
+{
+	return hid_register_driver(&ks_driver);
+}
+
+static void ks_exit(void)
+{
+	hid_unregister_driver(&ks_driver);
+}
+
+module_init(ks_init);
+module_exit(ks_exit);
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/hid-kye.c b/drivers/hid/hid-kye.c
new file mode 100644
index 000000000000..72ee3fec56d9
--- /dev/null
+++ b/drivers/hid/hid-kye.c
@@ -0,0 +1,69 @@
+/*
+ *  HID driver for Kye/Genius devices not fully compliant with HID standard
+ *
+ *  Copyright (c) 2009 Jiri Kosina
+ *  Copyright (c) 2009 Tomas Hanak
+ */
+
+/*
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License as published by the Free
+ * Software Foundation; either version 2 of the License, or (at your option)
+ * any later version.
+ */
+
+#include <linux/device.h>
+#include <linux/hid.h>
+#include <linux/module.h>
+
+#include "hid-ids.h"
+
+/* the fixups that need to be done:
+ *   - change led usage page to button for extra buttons
+ *   - report size 8 count 1 must be size 1 count 8 for button bitfield
+ *   - change the button usage range to 4-7 for the extra buttons
+ */
+static void kye_report_fixup(struct hid_device *hdev, __u8 *rdesc,
+		unsigned int rsize)
+{
+	if (rsize >= 74 &&
+		rdesc[61] == 0x05 && rdesc[62] == 0x08 &&
+		rdesc[63] == 0x19 && rdesc[64] == 0x08 &&
+		rdesc[65] == 0x29 && rdesc[66] == 0x0f &&
+		rdesc[71] == 0x75 && rdesc[72] == 0x08 &&
+		rdesc[73] == 0x95 && rdesc[74] == 0x01) {
+		dev_info(&hdev->dev, "fixing up Kye/Genius Ergo Mouse report "
+				"descriptor\n");
+		rdesc[62] = 0x09;
+		rdesc[64] = 0x04;
+		rdesc[66] = 0x07;
+		rdesc[72] = 0x01;
+		rdesc[74] = 0x08;
+	}
+}
+
+static const struct hid_device_id kye_devices[] = {
+	{ HID_USB_DEVICE(USB_VENDOR_ID_KYE, USB_DEVICE_ID_KYE_ERGO_525V) },
+	{ }
+};
+MODULE_DEVICE_TABLE(hid, kye_devices);
+
+static struct hid_driver kye_driver = {
+	.name = "kye",
+	.id_table = kye_devices,
+	.report_fixup = kye_report_fixup,
+};
+
+static int kye_init(void)
+{
+	return hid_register_driver(&kye_driver);
+}
+
+static void kye_exit(void)
+{
+	hid_unregister_driver(&kye_driver);
+}
+
+module_init(kye_init);
+module_exit(kye_exit);
+MODULE_LICENSE("GPL");
diff --git a/drivers/hid/hid-lg.c b/drivers/hid/hid-lg.c
index 83e07c9f4144..7b80cb694982 100644
--- a/drivers/hid/hid-lg.c
+++ b/drivers/hid/hid-lg.c
@@ -326,5 +326,3 @@ static void lg_exit(void)
 module_init(lg_init);
 module_exit(lg_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(logitech);
diff --git a/drivers/hid/hid-microsoft.c b/drivers/hid/hid-microsoft.c
index 25b10dcad90d..5e9e37a0506d 100644
--- a/drivers/hid/hid-microsoft.c
+++ b/drivers/hid/hid-microsoft.c
@@ -210,5 +210,3 @@ static void ms_exit(void)
 module_init(ms_init);
 module_exit(ms_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(microsoft);
diff --git a/drivers/hid/hid-monterey.c b/drivers/hid/hid-monterey.c
index f3a85a065f18..240f87618be6 100644
--- a/drivers/hid/hid-monterey.c
+++ b/drivers/hid/hid-monterey.c
@@ -78,5 +78,3 @@ static void mr_exit(void)
 module_init(mr_init);
 module_exit(mr_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(monterey);
diff --git a/drivers/hid/hid-ntrig.c b/drivers/hid/hid-ntrig.c
index db44fbd7bdf6..c5b252be9c21 100644
--- a/drivers/hid/hid-ntrig.c
+++ b/drivers/hid/hid-ntrig.c
@@ -78,5 +78,3 @@ static void ntrig_exit(void)
 module_init(ntrig_init);
 module_exit(ntrig_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(ntrig);
diff --git a/drivers/hid/hid-petalynx.c b/drivers/hid/hid-petalynx.c
index 10945fe12d50..2e83e8ff891a 100644
--- a/drivers/hid/hid-petalynx.c
+++ b/drivers/hid/hid-petalynx.c
@@ -118,5 +118,3 @@ static void pl_exit(void)
 module_init(pl_init);
 module_exit(pl_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(petalynx);
diff --git a/drivers/hid/hid-pl.c b/drivers/hid/hid-pl.c
index 46941f979b9d..4db9a3483760 100644
--- a/drivers/hid/hid-pl.c
+++ b/drivers/hid/hid-pl.c
@@ -9,9 +9,12 @@
  *   - contains two reports, one for each port (HID_QUIRK_MULTI_INPUT)
  *
  *  0e8f:0003 "GreenAsia Inc.    USB Joystick     "
- *   - tested with K??ng Gaming gamepad
+ *   - tested with König Gaming gamepad
  *
- *  Copyright (c) 2007 Anssi Hannula <anssi.hannula@gmail.com>
+ *  0e8f:0003 "GASIA USB Gamepad"
+ *   - another version of the König gamepad
+ *
+ *  Copyright (c) 2007, 2009 Anssi Hannula <anssi.hannula@gmail.com>
  */
 
 /*
@@ -46,6 +49,8 @@
 
 struct plff_device {
 	struct hid_report *report;
+	s32 *strong;
+	s32 *weak;
 };
 
 static int hid_plff_play(struct input_dev *dev, void *data,
@@ -62,8 +67,8 @@ static int hid_plff_play(struct input_dev *dev, void *data,
 	left = left * 0x7f / 0xffff;
 	right = right * 0x7f / 0xffff;
 
-	plff->report->field[0]->value[2] = left;
-	plff->report->field[0]->value[3] = right;
+	*plff->strong = left;
+	*plff->weak = right;
 	debug("running with 0x%02x 0x%02x", left, right);
 	usbhid_submit_report(hid, plff->report, USB_DIR_OUT);
 
@@ -80,6 +85,8 @@ static int plff_init(struct hid_device *hid)
 	struct list_head *report_ptr = report_list;
 	struct input_dev *dev;
 	int error;
+	s32 *strong;
+	s32 *weak;
 
 	/* The device contains one output report per physical device, all
 	   containing 1 field, which contains 4 ff00.0002 usages and 4 16bit
@@ -87,7 +94,12 @@ static int plff_init(struct hid_device *hid)
 
 	   The input reports also contain a field which contains
 	   8 ff00.0001 usages and 8 boolean values. Their meaning is
-	   currently unknown. */
+	   currently unknown.
+	   
+	   A version of the 0e8f:0003 exists that has all the values in
+	   separate fields and misses the extra input field, thus resembling
+	   Zeroplus (hid-zpff) devices.
+	*/
 
 	if (list_empty(report_list)) {
 		dev_err(&hid->dev, "no output reports found\n");
@@ -110,8 +122,21 @@ static int plff_init(struct hid_device *hid)
 			return -ENODEV;
 		}
 
-		if (report->field[0]->report_count < 4) {
-			dev_err(&hid->dev, "not enough values in the field\n");
+		if (report->field[0]->report_count >= 4) {
+			report->field[0]->value[0] = 0x00;
+			report->field[0]->value[1] = 0x00;
+			strong = &report->field[0]->value[2];
+			weak = &report->field[0]->value[3];
+			debug("detected single-field device");
+		} else if (report->maxfield >= 4 && report->field[0]->maxusage == 1 &&
+				report->field[0]->usage[0].hid == (HID_UP_LED | 0x43)) {
+			report->field[0]->value[0] = 0x00;
+			report->field[1]->value[0] = 0x00;
+			strong = &report->field[2]->value[0];
+			weak = &report->field[3]->value[0];
+			debug("detected 4-field device");
+		} else {
+			dev_err(&hid->dev, "not enough fields or values\n");
 			return -ENODEV;
 		}
 
@@ -130,10 +155,11 @@ static int plff_init(struct hid_device *hid)
 		}
 
 		plff->report = report;
-		plff->report->field[0]->value[0] = 0x00;
-		plff->report->field[0]->value[1] = 0x00;
-		plff->report->field[0]->value[2] = 0x00;
-		plff->report->field[0]->value[3] = 0x00;
+		plff->strong = strong;
+		plff->weak = weak;
+
+		*strong = 0x00;
+		*weak = 0x00;
 		usbhid_submit_report(hid, plff->report, USB_DIR_OUT);
 	}
 
@@ -180,7 +206,7 @@ static const struct hid_device_id pl_devices[] = {
 		.driver_data = 1 }, /* Twin USB Joystick */
 	{ HID_USB_DEVICE(USB_VENDOR_ID_GAMERON, USB_DEVICE_ID_GAMERON_DUAL_PCS_ADAPTOR),
 		.driver_data = 1 }, /* Twin USB Joystick */
-	{ HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, 0x0003), }, /* GreenAsia Inc. USB Joystick */
+	{ HID_USB_DEVICE(USB_VENDOR_ID_GREENASIA, 0x0003), },
 	{ }
 };
 MODULE_DEVICE_TABLE(hid, pl_devices);
@@ -204,5 +230,3 @@ static void pl_exit(void)
 module_init(pl_init);
 module_exit(pl_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(pantherlord);
diff --git a/drivers/hid/hid-samsung.c b/drivers/hid/hid-samsung.c
index 15f3c0492450..07083aa6c19a 100644
--- a/drivers/hid/hid-samsung.c
+++ b/drivers/hid/hid-samsung.c
@@ -96,5 +96,3 @@ static void samsung_exit(void)
 module_init(samsung_init);
 module_exit(samsung_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(samsung);
diff --git a/drivers/hid/hid-sony.c b/drivers/hid/hid-sony.c
index dd5a3979a4de..c2599388a350 100644
--- a/drivers/hid/hid-sony.c
+++ b/drivers/hid/hid-sony.c
@@ -148,5 +148,3 @@ static void sony_exit(void)
 module_init(sony_init);
 module_exit(sony_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(sony);
diff --git a/drivers/hid/hid-sunplus.c b/drivers/hid/hid-sunplus.c
index 5ba68f7dbb78..e0a8fd36a85b 100644
--- a/drivers/hid/hid-sunplus.c
+++ b/drivers/hid/hid-sunplus.c
@@ -78,5 +78,3 @@ static void sp_exit(void)
 module_init(sp_init);
 module_exit(sp_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(sunplus);
diff --git a/drivers/hid/hid-tmff.c b/drivers/hid/hid-tmff.c
index 1b7cba0f7e1f..7c1f7b50330c 100644
--- a/drivers/hid/hid-tmff.c
+++ b/drivers/hid/hid-tmff.c
@@ -265,5 +265,3 @@ static void tm_exit(void)
 module_init(tm_init);
 module_exit(tm_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(thrustmaster);
diff --git a/drivers/hid/hid-topseed.c b/drivers/hid/hid-topseed.c
index cca64a0564a9..152ccfabeba5 100644
--- a/drivers/hid/hid-topseed.c
+++ b/drivers/hid/hid-topseed.c
@@ -73,5 +73,3 @@ static void ts_exit(void)
 module_init(ts_init);
 module_exit(ts_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(topseed);
diff --git a/drivers/hid/hid-zpff.c b/drivers/hid/hid-zpff.c
index ea82f3718b21..85a198a18537 100644
--- a/drivers/hid/hid-zpff.c
+++ b/drivers/hid/hid-zpff.c
@@ -158,5 +158,3 @@ static void zp_exit(void)
 module_init(zp_init);
 module_exit(zp_exit);
 MODULE_LICENSE("GPL");
-
-HID_COMPAT_LOAD_DRIVER(zeroplus);
diff --git a/drivers/hid/hidraw.c b/drivers/hid/hidraw.c
index 02b19db5442e..e263d4731179 100644
--- a/drivers/hid/hidraw.c
+++ b/drivers/hid/hidraw.c
@@ -181,9 +181,17 @@ static int hidraw_open(struct inode *inode, struct file *file)
 
 	dev = hidraw_table[minor];
 	if (!dev->open++) {
+		if (dev->hid->ll_driver->power) {
+			err = dev->hid->ll_driver->power(dev->hid, PM_HINT_FULLON);
+			if (err < 0)
+				goto out_unlock;
+		}
 		err = dev->hid->ll_driver->open(dev->hid);
-		if (err < 0)
+		if (err < 0) {
+			if (dev->hid->ll_driver->power)
+				dev->hid->ll_driver->power(dev->hid, PM_HINT_NORMAL);
 			dev->open--;
+		}
 	}
 
 out_unlock:
@@ -209,10 +217,13 @@ static int hidraw_release(struct inode * inode, struct file * file)
 	list_del(&list->node);
 	dev = hidraw_table[minor];
 	if (!--dev->open) {
-		if (list->hidraw->exist)
+		if (list->hidraw->exist) {
+			if (dev->hid->ll_driver->power)
+				dev->hid->ll_driver->power(dev->hid, PM_HINT_NORMAL);
 			dev->hid->ll_driver->close(dev->hid);
-		else
+		} else {
 			kfree(list->hidraw);
+		}
 	}
 
 	kfree(list);
diff --git a/drivers/hid/usbhid/hid-core.c b/drivers/hid/usbhid/hid-core.c
index f0a0f72238ab..4306cb1b8ce5 100644
--- a/drivers/hid/usbhid/hid-core.c
+++ b/drivers/hid/usbhid/hid-core.c
@@ -5,6 +5,7 @@
  *  Copyright (c) 2000-2005 Vojtech Pavlik <vojtech@suse.cz>
  *  Copyright (c) 2005 Michael Haboustak <mike-@cinci.rr.com> for Concept2, Inc
  *  Copyright (c) 2006-2008 Jiri Kosina
+ *  Copyright (c) 2007-2008 Oliver Neukum
  */
 
 /*
@@ -27,6 +28,7 @@
 #include <asm/byteorder.h>
 #include <linux/input.h>
 #include <linux/wait.h>
+#include <linux/workqueue.h>
 
 #include <linux/usb.h>
 
@@ -53,6 +55,10 @@ static unsigned int hid_mousepoll_interval;
 module_param_named(mousepoll, hid_mousepoll_interval, uint, 0644);
 MODULE_PARM_DESC(mousepoll, "Polling interval of mice");
 
+static unsigned int ignoreled;
+module_param_named(ignoreled, ignoreled, uint, 0644);
+MODULE_PARM_DESC(ignoreled, "Autosuspend with active leds");
+
 /* Quirks specified at module load time */
 static char *quirks_param[MAX_USBHID_BOOT_QUIRKS] = { [ 0 ... (MAX_USBHID_BOOT_QUIRKS - 1) ] = NULL };
 module_param_array_named(quirks, quirks_param, charp, NULL, 0444);
@@ -63,8 +69,13 @@ MODULE_PARM_DESC(quirks, "Add/modify USB HID quirks by specifying "
 /*
  * Input submission and I/O error handler.
  */
+static DEFINE_MUTEX(hid_open_mut);
+static struct workqueue_struct *resumption_waker;
 
 static void hid_io_error(struct hid_device *hid);
+static int hid_submit_out(struct hid_device *hid);
+static int hid_submit_ctrl(struct hid_device *hid);
+static void hid_cancel_delayed_stuff(struct usbhid_device *usbhid);
 
 /* Start up the input URB */
 static int hid_start_in(struct hid_device *hid)
@@ -73,15 +84,16 @@ static int hid_start_in(struct hid_device *hid)
 	int rc = 0;
 	struct usbhid_device *usbhid = hid->driver_data;
 
-	spin_lock_irqsave(&usbhid->inlock, flags);
-	if (hid->open > 0 && !test_bit(HID_SUSPENDED, &usbhid->iofl) &&
+	spin_lock_irqsave(&usbhid->lock, flags);
+	if (hid->open > 0 &&
 			!test_bit(HID_DISCONNECTED, &usbhid->iofl) &&
+			!test_bit(HID_REPORTED_IDLE, &usbhid->iofl) &&
 			!test_and_set_bit(HID_IN_RUNNING, &usbhid->iofl)) {
 		rc = usb_submit_urb(usbhid->urbin, GFP_ATOMIC);
 		if (rc != 0)
 			clear_bit(HID_IN_RUNNING, &usbhid->iofl);
 	}
-	spin_unlock_irqrestore(&usbhid->inlock, flags);
+	spin_unlock_irqrestore(&usbhid->lock, flags);
 	return rc;
 }
 
@@ -145,7 +157,7 @@ static void hid_io_error(struct hid_device *hid)
 	unsigned long flags;
 	struct usbhid_device *usbhid = hid->driver_data;
 
-	spin_lock_irqsave(&usbhid->inlock, flags);
+	spin_lock_irqsave(&usbhid->lock, flags);
 
 	/* Stop when disconnected */
 	if (test_bit(HID_DISCONNECTED, &usbhid->iofl))
@@ -175,7 +187,51 @@ static void hid_io_error(struct hid_device *hid)
 	mod_timer(&usbhid->io_retry,
 			jiffies + msecs_to_jiffies(usbhid->retry_delay));
 done:
-	spin_unlock_irqrestore(&usbhid->inlock, flags);
+	spin_unlock_irqrestore(&usbhid->lock, flags);
+}
+
+static void usbhid_mark_busy(struct usbhid_device *usbhid)
+{
+	struct usb_interface *intf = usbhid->intf;
+
+	usb_mark_last_busy(interface_to_usbdev(intf));
+}
+
+static int usbhid_restart_out_queue(struct usbhid_device *usbhid)
+{
+	struct hid_device *hid = usb_get_intfdata(usbhid->intf);
+	int kicked;
+
+	if (!hid)
+		return 0;
+
+	if ((kicked = (usbhid->outhead != usbhid->outtail))) {
+		dbg("Kicking head %d tail %d", usbhid->outhead, usbhid->outtail);
+		if (hid_submit_out(hid)) {
+			clear_bit(HID_OUT_RUNNING, &usbhid->iofl);
+			wake_up(&usbhid->wait);
+		}
+	}
+	return kicked;
+}
+
+static int usbhid_restart_ctrl_queue(struct usbhid_device *usbhid)
+{
+	struct hid_device *hid = usb_get_intfdata(usbhid->intf);
+	int kicked;
+
+	WARN_ON(hid == NULL);
+	if (!hid)
+		return 0;
+
+	if ((kicked = (usbhid->ctrlhead != usbhid->ctrltail))) {
+		dbg("Kicking head %d tail %d", usbhid->ctrlhead, usbhid->ctrltail);
+		if (hid_submit_ctrl(hid)) {
+			clear_bit(HID_CTRL_RUNNING, &usbhid->iofl);
+			wake_up(&usbhid->wait);
+		}
+	}
+	return kicked;
 }
 
 /*
@@ -190,12 +246,23 @@ static void hid_irq_in(struct urb *urb)
 
 	switch (urb->status) {
 	case 0:			/* success */
+		usbhid_mark_busy(usbhid);
 		usbhid->retry_delay = 0;
 		hid_input_report(urb->context, HID_INPUT_REPORT,
 				 urb->transfer_buffer,
 				 urb->actual_length, 1);
+		/*
+		 * autosuspend refused while keys are pressed
+		 * because most keyboards don't wake up when
+		 * a key is released
+		 */
+		if (hid_check_keys_pressed(hid))
+			set_bit(HID_KEYS_PRESSED, &usbhid->iofl);
+		else
+			clear_bit(HID_KEYS_PRESSED, &usbhid->iofl);
 		break;
 	case -EPIPE:		/* stall */
+		usbhid_mark_busy(usbhid);
 		clear_bit(HID_IN_RUNNING, &usbhid->iofl);
 		set_bit(HID_CLEAR_HALT, &usbhid->iofl);
 		schedule_work(&usbhid->reset_work);
@@ -209,6 +276,7 @@ static void hid_irq_in(struct urb *urb)
 	case -EPROTO:		/* protocol error or unplug */
 	case -ETIME:		/* protocol error or unplug */
 	case -ETIMEDOUT:	/* Should never happen, but... */
+		usbhid_mark_busy(usbhid);
 		clear_bit(HID_IN_RUNNING, &usbhid->iofl);
 		hid_io_error(hid);
 		return;
@@ -239,16 +307,25 @@ static int hid_submit_out(struct hid_device *hid)
 	report = usbhid->out[usbhid->outtail].report;
 	raw_report = usbhid->out[usbhid->outtail].raw_report;
 
-	usbhid->urbout->transfer_buffer_length = ((report->size - 1) >> 3) + 1 + (report->id > 0);
-	usbhid->urbout->dev = hid_to_usb_dev(hid);
-	memcpy(usbhid->outbuf, raw_report, usbhid->urbout->transfer_buffer_length);
-	kfree(raw_report);
+	if (!test_bit(HID_REPORTED_IDLE, &usbhid->iofl)) {
+		usbhid->urbout->transfer_buffer_length = ((report->size - 1) >> 3) + 1 + (report->id > 0);
+		usbhid->urbout->dev = hid_to_usb_dev(hid);
+		memcpy(usbhid->outbuf, raw_report, usbhid->urbout->transfer_buffer_length);
+		kfree(raw_report);
 
-	dbg_hid("submitting out urb\n");
+		dbg_hid("submitting out urb\n");
 
-	if (usb_submit_urb(usbhid->urbout, GFP_ATOMIC)) {
-		err_hid("usb_submit_urb(out) failed");
-		return -1;
+		if (usb_submit_urb(usbhid->urbout, GFP_ATOMIC)) {
+			err_hid("usb_submit_urb(out) failed");
+			return -1;
+		}
+	} else {
+		/*
+		 * queue work to wake up the device.
+		 * as the work queue is freezeable, this is safe
+		 * with respect to STD and STR
+		 */
+		queue_work(resumption_waker, &usbhid->restart_work);
 	}
 
 	return 0;
@@ -266,41 +343,50 @@ static int hid_submit_ctrl(struct hid_device *hid)
 	raw_report = usbhid->ctrl[usbhid->ctrltail].raw_report;
 	dir = usbhid->ctrl[usbhid->ctrltail].dir;
 
-	len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
-	if (dir == USB_DIR_OUT) {
-		usbhid->urbctrl->pipe = usb_sndctrlpipe(hid_to_usb_dev(hid), 0);
-		usbhid->urbctrl->transfer_buffer_length = len;
-		memcpy(usbhid->ctrlbuf, raw_report, len);
-		kfree(raw_report);
-	} else {
-		int maxpacket, padlen;
-
-		usbhid->urbctrl->pipe = usb_rcvctrlpipe(hid_to_usb_dev(hid), 0);
-		maxpacket = usb_maxpacket(hid_to_usb_dev(hid), usbhid->urbctrl->pipe, 0);
-		if (maxpacket > 0) {
-			padlen = DIV_ROUND_UP(len, maxpacket);
-			padlen *= maxpacket;
-			if (padlen > usbhid->bufsize)
-				padlen = usbhid->bufsize;
-		} else
-			padlen = 0;
-		usbhid->urbctrl->transfer_buffer_length = padlen;
-	}
-	usbhid->urbctrl->dev = hid_to_usb_dev(hid);
+	if (!test_bit(HID_REPORTED_IDLE, &usbhid->iofl)) {
+		len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
+		if (dir == USB_DIR_OUT) {
+			usbhid->urbctrl->pipe = usb_sndctrlpipe(hid_to_usb_dev(hid), 0);
+			usbhid->urbctrl->transfer_buffer_length = len;
+			memcpy(usbhid->ctrlbuf, raw_report, len);
+			kfree(raw_report);
+		} else {
+			int maxpacket, padlen;
+
+			usbhid->urbctrl->pipe = usb_rcvctrlpipe(hid_to_usb_dev(hid), 0);
+			maxpacket = usb_maxpacket(hid_to_usb_dev(hid), usbhid->urbctrl->pipe, 0);
+			if (maxpacket > 0) {
+				padlen = DIV_ROUND_UP(len, maxpacket);
+				padlen *= maxpacket;
+				if (padlen > usbhid->bufsize)
+					padlen = usbhid->bufsize;
+			} else
+				padlen = 0;
+			usbhid->urbctrl->transfer_buffer_length = padlen;
+		}
+		usbhid->urbctrl->dev = hid_to_usb_dev(hid);
 
-	usbhid->cr->bRequestType = USB_TYPE_CLASS | USB_RECIP_INTERFACE | dir;
-	usbhid->cr->bRequest = (dir == USB_DIR_OUT) ? HID_REQ_SET_REPORT : HID_REQ_GET_REPORT;
-	usbhid->cr->wValue = cpu_to_le16(((report->type + 1) << 8) | report->id);
-	usbhid->cr->wIndex = cpu_to_le16(usbhid->ifnum);
-	usbhid->cr->wLength = cpu_to_le16(len);
+		usbhid->cr->bRequestType = USB_TYPE_CLASS | USB_RECIP_INTERFACE | dir;
+		usbhid->cr->bRequest = (dir == USB_DIR_OUT) ? HID_REQ_SET_REPORT : HID_REQ_GET_REPORT;
+		usbhid->cr->wValue = cpu_to_le16(((report->type + 1) << 8) | report->id);
+		usbhid->cr->wIndex = cpu_to_le16(usbhid->ifnum);
+		usbhid->cr->wLength = cpu_to_le16(len);
 
-	dbg_hid("submitting ctrl urb: %s wValue=0x%04x wIndex=0x%04x wLength=%u\n",
-		usbhid->cr->bRequest == HID_REQ_SET_REPORT ? "Set_Report" : "Get_Report",
-		usbhid->cr->wValue, usbhid->cr->wIndex, usbhid->cr->wLength);
+		dbg_hid("submitting ctrl urb: %s wValue=0x%04x wIndex=0x%04x wLength=%u\n",
+			usbhid->cr->bRequest == HID_REQ_SET_REPORT ? "Set_Report" : "Get_Report",
+			usbhid->cr->wValue, usbhid->cr->wIndex, usbhid->cr->wLength);
 
-	if (usb_submit_urb(usbhid->urbctrl, GFP_ATOMIC)) {
-		err_hid("usb_submit_urb(ctrl) failed");
-		return -1;
+		if (usb_submit_urb(usbhid->urbctrl, GFP_ATOMIC)) {
+			err_hid("usb_submit_urb(ctrl) failed");
+			return -1;
+		}
+	} else {
+		/*
+		 * queue work to wake up the device.
+		 * as the work queue is freezeable, this is safe
+		 * with respect to STD and STR
+		 */
+		queue_work(resumption_waker, &usbhid->restart_work);
 	}
 
 	return 0;
@@ -332,7 +418,7 @@ static void hid_irq_out(struct urb *urb)
 				"received\n", urb->status);
 	}
 
-	spin_lock_irqsave(&usbhid->outlock, flags);
+	spin_lock_irqsave(&usbhid->lock, flags);
 
 	if (unplug)
 		usbhid->outtail = usbhid->outhead;
@@ -344,12 +430,12 @@ static void hid_irq_out(struct urb *urb)
 			clear_bit(HID_OUT_RUNNING, &usbhid->iofl);
 			wake_up(&usbhid->wait);
 		}
-		spin_unlock_irqrestore(&usbhid->outlock, flags);
+		spin_unlock_irqrestore(&usbhid->lock, flags);
 		return;
 	}
 
 	clear_bit(HID_OUT_RUNNING, &usbhid->iofl);
-	spin_unlock_irqrestore(&usbhid->outlock, flags);
+	spin_unlock_irqrestore(&usbhid->lock, flags);
 	wake_up(&usbhid->wait);
 }
 
@@ -361,12 +447,11 @@ static void hid_ctrl(struct urb *urb)
 {
 	struct hid_device *hid = urb->context;
 	struct usbhid_device *usbhid = hid->driver_data;
-	unsigned long flags;
-	int unplug = 0;
+	int unplug = 0, status = urb->status;
 
-	spin_lock_irqsave(&usbhid->ctrllock, flags);
+	spin_lock(&usbhid->lock);
 
-	switch (urb->status) {
+	switch (status) {
 	case 0:			/* success */
 		if (usbhid->ctrl[usbhid->ctrltail].dir == USB_DIR_IN)
 			hid_input_report(urb->context,
@@ -383,7 +468,7 @@ static void hid_ctrl(struct urb *urb)
 		break;
 	default:		/* error */
 		dev_warn(&urb->dev->dev, "ctrl urb status %d "
-				"received\n", urb->status);
+				"received\n", status);
 	}
 
 	if (unplug)
@@ -396,19 +481,18 @@ static void hid_ctrl(struct urb *urb)
 			clear_bit(HID_CTRL_RUNNING, &usbhid->iofl);
 			wake_up(&usbhid->wait);
 		}
-		spin_unlock_irqrestore(&usbhid->ctrllock, flags);
+		spin_unlock(&usbhid->lock);
 		return;
 	}
 
 	clear_bit(HID_CTRL_RUNNING, &usbhid->iofl);
-	spin_unlock_irqrestore(&usbhid->ctrllock, flags);
+	spin_unlock(&usbhid->lock);
 	wake_up(&usbhid->wait);
 }
 
-void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir)
+void __usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir)
 {
 	int head;
-	unsigned long flags;
 	struct usbhid_device *usbhid = hid->driver_data;
 	int len = ((report->size - 1) >> 3) + 1 + (report->id > 0);
 
@@ -416,18 +500,13 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns
 		return;
 
 	if (usbhid->urbout && dir == USB_DIR_OUT && report->type == HID_OUTPUT_REPORT) {
-
-		spin_lock_irqsave(&usbhid->outlock, flags);
-
 		if ((head = (usbhid->outhead + 1) & (HID_OUTPUT_FIFO_SIZE - 1)) == usbhid->outtail) {
-			spin_unlock_irqrestore(&usbhid->outlock, flags);
 			dev_warn(&hid->dev, "output queue full\n");
 			return;
 		}
 
 		usbhid->out[usbhid->outhead].raw_report = kmalloc(len, GFP_ATOMIC);
 		if (!usbhid->out[usbhid->outhead].raw_report) {
-			spin_unlock_irqrestore(&usbhid->outlock, flags);
 			dev_warn(&hid->dev, "output queueing failed\n");
 			return;
 		}
@@ -438,15 +517,10 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns
 		if (!test_and_set_bit(HID_OUT_RUNNING, &usbhid->iofl))
 			if (hid_submit_out(hid))
 				clear_bit(HID_OUT_RUNNING, &usbhid->iofl);
-
-		spin_unlock_irqrestore(&usbhid->outlock, flags);
 		return;
 	}
 
-	spin_lock_irqsave(&usbhid->ctrllock, flags);
-
 	if ((head = (usbhid->ctrlhead + 1) & (HID_CONTROL_FIFO_SIZE - 1)) == usbhid->ctrltail) {
-		spin_unlock_irqrestore(&usbhid->ctrllock, flags);
 		dev_warn(&hid->dev, "control queue full\n");
 		return;
 	}
@@ -454,7 +528,6 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns
 	if (dir == USB_DIR_OUT) {
 		usbhid->ctrl[usbhid->ctrlhead].raw_report = kmalloc(len, GFP_ATOMIC);
 		if (!usbhid->ctrl[usbhid->ctrlhead].raw_report) {
-			spin_unlock_irqrestore(&usbhid->ctrllock, flags);
 			dev_warn(&hid->dev, "control queueing failed\n");
 			return;
 		}
@@ -467,15 +540,25 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns
 	if (!test_and_set_bit(HID_CTRL_RUNNING, &usbhid->iofl))
 		if (hid_submit_ctrl(hid))
 			clear_bit(HID_CTRL_RUNNING, &usbhid->iofl);
+}
+
+void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir)
+{
+	struct usbhid_device *usbhid = hid->driver_data;
+	unsigned long flags;
 
-	spin_unlock_irqrestore(&usbhid->ctrllock, flags);
+	spin_lock_irqsave(&usbhid->lock, flags);
+	__usbhid_submit_report(hid, report, dir);
+	spin_unlock_irqrestore(&usbhid->lock, flags);
 }
 EXPORT_SYMBOL_GPL(usbhid_submit_report);
 
 static int usb_hidinput_input_event(struct input_dev *dev, unsigned int type, unsigned int code, int value)
 {
 	struct hid_device *hid = input_get_drvdata(dev);
+	struct usbhid_device *usbhid = hid->driver_data;
 	struct hid_field *field;
+	unsigned long flags;
 	int offset;
 
 	if (type == EV_FF)
@@ -490,6 +573,15 @@ static int usb_hidinput_input_event(struct input_dev *dev, unsigned int type, un
 	}
 
 	hid_set_field(field, offset, value);
+	if (value) {
+		spin_lock_irqsave(&usbhid->lock, flags);
+		usbhid->ledcount++;
+		spin_unlock_irqrestore(&usbhid->lock, flags);
+	} else {
+		spin_lock_irqsave(&usbhid->lock, flags);
+		usbhid->ledcount--;
+		spin_unlock_irqrestore(&usbhid->lock, flags);
+	}
 	usbhid_submit_report(hid, field->report, USB_DIR_OUT);
 
 	return 0;
@@ -538,15 +630,22 @@ int usbhid_open(struct hid_device *hid)
 	struct usbhid_device *usbhid = hid->driver_data;
 	int res;
 
+	mutex_lock(&hid_open_mut);
 	if (!hid->open++) {
 		res = usb_autopm_get_interface(usbhid->intf);
+		/* the device must be awake to reliable request remote wakeup */
 		if (res < 0) {
 			hid->open--;
+			mutex_unlock(&hid_open_mut);
 			return -EIO;
 		}
+		usbhid->intf->needs_remote_wakeup = 1;
+		if (hid_start_in(hid))
+			hid_io_error(hid);
+ 
+		usb_autopm_put_interface(usbhid->intf);
 	}
-	if (hid_start_in(hid))
-		hid_io_error(hid);
+	mutex_unlock(&hid_open_mut);
 	return 0;
 }
 
@@ -554,10 +653,22 @@ void usbhid_close(struct hid_device *hid)
 {
 	struct usbhid_device *usbhid = hid->driver_data;
 
+	mutex_lock(&hid_open_mut);
+
+	/* protecting hid->open to make sure we don't restart
+	 * data acquistion due to a resumption we no longer
+	 * care about
+	 */
+	spin_lock_irq(&usbhid->lock);
 	if (!--hid->open) {
+		spin_unlock_irq(&usbhid->lock);
 		usb_kill_urb(usbhid->urbin);
-		usb_autopm_put_interface(usbhid->intf);
+		flush_scheduled_work();
+		usbhid->intf->needs_remote_wakeup = 0;
+	} else {
+		spin_unlock_irq(&usbhid->lock);
 	}
+	mutex_unlock(&hid_open_mut);
 }
 
 /*
@@ -687,6 +798,25 @@ static int usbhid_output_raw_report(struct hid_device *hid, __u8 *buf, size_t co
 	return ret;
 }
 
+static void usbhid_restart_queues(struct usbhid_device *usbhid)
+{
+	if (usbhid->urbout)
+		usbhid_restart_out_queue(usbhid);
+	usbhid_restart_ctrl_queue(usbhid);
+}
+
+static void __usbhid_restart_queues(struct work_struct *work)
+{
+	struct usbhid_device *usbhid =
+		container_of(work, struct usbhid_device, restart_work);
+	int r;
+
+	r = usb_autopm_get_interface(usbhid->intf);
+	if (r < 0)
+		return;
+	usb_autopm_put_interface(usbhid->intf);
+}
+
 static void hid_free_buffers(struct usb_device *dev, struct hid_device *hid)
 {
 	struct usbhid_device *usbhid = hid->driver_data;
@@ -711,6 +841,9 @@ static int usbhid_parse(struct hid_device *hid)
 	quirks = usbhid_lookup_quirk(le16_to_cpu(dev->descriptor.idVendor),
 			le16_to_cpu(dev->descriptor.idProduct));
 
+	if (quirks & HID_QUIRK_IGNORE)
+		return -ENODEV;
+
 	/* Many keyboards and mice don't like to be polled for reports,
 	 * so we will always set the HID_QUIRK_NOGET flag for them. */
 	if (interface->desc.bInterfaceSubClass == USB_INTERFACE_SUBCLASS_BOOT) {
@@ -850,11 +983,11 @@ static int usbhid_start(struct hid_device *hid)
 
 	init_waitqueue_head(&usbhid->wait);
 	INIT_WORK(&usbhid->reset_work, hid_reset);
+	INIT_WORK(&usbhid->restart_work, __usbhid_restart_queues);
 	setup_timer(&usbhid->io_retry, hid_retry_timeout, (unsigned long) hid);
 
-	spin_lock_init(&usbhid->inlock);
-	spin_lock_init(&usbhid->outlock);
-	spin_lock_init(&usbhid->ctrllock);
+	spin_lock_init(&usbhid->lock);
+	spin_lock_init(&usbhid->lock);
 
 	usbhid->intf = intf;
 	usbhid->ifnum = interface->desc.bInterfaceNumber;
@@ -906,15 +1039,14 @@ static void usbhid_stop(struct hid_device *hid)
 		return;
 
 	clear_bit(HID_STARTED, &usbhid->iofl);
-	spin_lock_irq(&usbhid->inlock);	/* Sync with error handler */
+	spin_lock_irq(&usbhid->lock);	/* Sync with error handler */
 	set_bit(HID_DISCONNECTED, &usbhid->iofl);
-	spin_unlock_irq(&usbhid->inlock);
+	spin_unlock_irq(&usbhid->lock);
 	usb_kill_urb(usbhid->urbin);
 	usb_kill_urb(usbhid->urbout);
 	usb_kill_urb(usbhid->urbctrl);
 
-	del_timer_sync(&usbhid->io_retry);
-	cancel_work_sync(&usbhid->reset_work);
+	hid_cancel_delayed_stuff(usbhid);
 
 	if (hid->claimed & HID_CLAIMED_INPUT)
 		hidinput_disconnect(hid);
@@ -935,12 +1067,28 @@ static void usbhid_stop(struct hid_device *hid)
 	hid_free_buffers(hid_to_usb_dev(hid), hid);
 }
 
+static int usbhid_power(struct hid_device *hid, int lvl)
+{
+	int r = 0;
+
+	switch (lvl) {
+	case PM_HINT_FULLON:
+		r = usbhid_get_power(hid);
+		break;
+	case PM_HINT_NORMAL:
+		usbhid_put_power(hid);
+		break;
+	}
+	return r;
+}
+
 static struct hid_ll_driver usb_hid_driver = {
 	.parse = usbhid_parse,
 	.start = usbhid_start,
 	.stop = usbhid_stop,
 	.open = usbhid_open,
 	.close = usbhid_close,
+	.power = usbhid_power,
 	.hidinput_input_event = usb_hidinput_input_event,
 };
 
@@ -1049,19 +1197,126 @@ static void hid_disconnect(struct usb_interface *intf)
 	kfree(usbhid);
 }
 
+static void hid_cancel_delayed_stuff(struct usbhid_device *usbhid)
+{
+	del_timer_sync(&usbhid->io_retry);
+	cancel_work_sync(&usbhid->restart_work);
+	cancel_work_sync(&usbhid->reset_work);
+}
+
+static void hid_cease_io(struct usbhid_device *usbhid)
+{
+	del_timer(&usbhid->io_retry);
+	usb_kill_urb(usbhid->urbin);
+	usb_kill_urb(usbhid->urbctrl);
+	usb_kill_urb(usbhid->urbout);
+}
+
+/* Treat USB reset pretty much the same as suspend/resume */
+static int hid_pre_reset(struct usb_interface *intf)
+{
+	struct hid_device *hid = usb_get_intfdata(intf);
+	struct usbhid_device *usbhid = hid->driver_data;
+
+	spin_lock_irq(&usbhid->lock);
+	set_bit(HID_RESET_PENDING, &usbhid->iofl);
+	spin_unlock_irq(&usbhid->lock);
+	cancel_work_sync(&usbhid->restart_work);
+	hid_cease_io(usbhid);
+
+	return 0;
+}
+
+/* Same routine used for post_reset and reset_resume */
+static int hid_post_reset(struct usb_interface *intf)
+{
+	struct usb_device *dev = interface_to_usbdev (intf);
+	struct hid_device *hid = usb_get_intfdata(intf);
+	struct usbhid_device *usbhid = hid->driver_data;
+	int status;
+ 
+	spin_lock_irq(&usbhid->lock);
+	clear_bit(HID_RESET_PENDING, &usbhid->iofl);
+	spin_unlock_irq(&usbhid->lock);
+	hid_set_idle(dev, intf->cur_altsetting->desc.bInterfaceNumber, 0, 0);
+	/* FIXME: Any more reinitialization needed? */
+	status = hid_start_in(hid);
+	if (status < 0)
+		hid_io_error(hid);
+	usbhid_restart_queues(usbhid);
+
+	return 0;
+}
+
+int usbhid_get_power(struct hid_device *hid)
+{
+	struct usbhid_device *usbhid = hid->driver_data;
+ 
+	return usb_autopm_get_interface(usbhid->intf);
+}
+
+void usbhid_put_power(struct hid_device *hid)
+{
+	struct usbhid_device *usbhid = hid->driver_data;
+ 
+	usb_autopm_put_interface(usbhid->intf);
+}
+
+
+#ifdef CONFIG_PM
 static int hid_suspend(struct usb_interface *intf, pm_message_t message)
 {
-	struct hid_device *hid = usb_get_intfdata (intf);
+	struct hid_device *hid = usb_get_intfdata(intf);
 	struct usbhid_device *usbhid = hid->driver_data;
+	struct usb_device *udev = interface_to_usbdev(intf);
+	int status;
 
-	if (!test_bit(HID_STARTED, &usbhid->iofl))
-		return 0;
+	if (udev->auto_pm) {
+		spin_lock_irq(&usbhid->lock);	/* Sync with error handler */
+		if (!test_bit(HID_RESET_PENDING, &usbhid->iofl)
+		    && !test_bit(HID_CLEAR_HALT, &usbhid->iofl)
+		    && !test_bit(HID_OUT_RUNNING, &usbhid->iofl)
+		    && !test_bit(HID_CTRL_RUNNING, &usbhid->iofl)
+		    && !test_bit(HID_KEYS_PRESSED, &usbhid->iofl)
+		    && (!usbhid->ledcount || ignoreled))
+		{
+			set_bit(HID_REPORTED_IDLE, &usbhid->iofl);
+			spin_unlock_irq(&usbhid->lock);
+		} else {
+			usbhid_mark_busy(usbhid);
+			spin_unlock_irq(&usbhid->lock);
+			return -EBUSY;
+		}
 
-	spin_lock_irq(&usbhid->inlock);	/* Sync with error handler */
-	set_bit(HID_SUSPENDED, &usbhid->iofl);
-	spin_unlock_irq(&usbhid->inlock);
-	del_timer_sync(&usbhid->io_retry);
-	usb_kill_urb(usbhid->urbin);
+	} else {
+		spin_lock_irq(&usbhid->lock);
+		set_bit(HID_REPORTED_IDLE, &usbhid->iofl);
+		spin_unlock_irq(&usbhid->lock);
+		if (usbhid_wait_io(hid) < 0)
+			return -EIO;
+	}
+
+	if (!ignoreled && udev->auto_pm) {
+		spin_lock_irq(&usbhid->lock);
+		if (test_bit(HID_LED_ON, &usbhid->iofl)) {
+			spin_unlock_irq(&usbhid->lock);
+			usbhid_mark_busy(usbhid);
+			return -EBUSY;
+		}
+		spin_unlock_irq(&usbhid->lock);
+	}
+
+	hid_cancel_delayed_stuff(usbhid);
+	hid_cease_io(usbhid);
+
+	if (udev->auto_pm && test_bit(HID_KEYS_PRESSED, &usbhid->iofl)) {
+		/* lost race against keypresses */
+		status = hid_start_in(hid);
+		if (status < 0)
+			hid_io_error(hid);
+		usbhid_mark_busy(usbhid);
+		return -EBUSY;
+	}
 	dev_dbg(&intf->dev, "suspend\n");
 	return 0;
 }
@@ -1075,32 +1330,33 @@ static int hid_resume(struct usb_interface *intf)
 	if (!test_bit(HID_STARTED, &usbhid->iofl))
 		return 0;
 
-	clear_bit(HID_SUSPENDED, &usbhid->iofl);
+	clear_bit(HID_REPORTED_IDLE, &usbhid->iofl);
+	usbhid_mark_busy(usbhid);
+
+	if (test_bit(HID_CLEAR_HALT, &usbhid->iofl) ||
+	    test_bit(HID_RESET_PENDING, &usbhid->iofl))
+		schedule_work(&usbhid->reset_work);
 	usbhid->retry_delay = 0;
 	status = hid_start_in(hid);
-	dev_dbg(&intf->dev, "resume status %d\n", status);
-	return status;
-}
+	if (status < 0)
+		hid_io_error(hid);
+	usbhid_restart_queues(usbhid);
 
-/* Treat USB reset pretty much the same as suspend/resume */
-static int hid_pre_reset(struct usb_interface *intf)
-{
-	/* FIXME: What if the interface is already suspended? */
-	hid_suspend(intf, PMSG_ON);
+	dev_dbg(&intf->dev, "resume status %d\n", status);
 	return 0;
 }
 
-/* Same routine used for post_reset and reset_resume */
-static int hid_post_reset(struct usb_interface *intf)
+static int hid_reset_resume(struct usb_interface *intf)
 {
-	struct usb_device *dev = interface_to_usbdev (intf);
-
-	hid_set_idle(dev, intf->cur_altsetting->desc.bInterfaceNumber, 0, 0);
-	/* FIXME: Any more reinitialization needed? */
+	struct hid_device *hid = usb_get_intfdata(intf);
+	struct usbhid_device *usbhid = hid->driver_data;
 
-	return hid_resume(intf);
+	clear_bit(HID_REPORTED_IDLE, &usbhid->iofl);
+	return hid_post_reset(intf);
 }
 
+#endif /* CONFIG_PM */
+
 static struct usb_device_id hid_usb_ids [] = {
 	{ .match_flags = USB_DEVICE_ID_MATCH_INT_CLASS,
 		.bInterfaceClass = USB_INTERFACE_CLASS_HID },
@@ -1113,9 +1369,11 @@ static struct usb_driver hid_driver = {
 	.name =		"usbhid",
 	.probe =	hid_probe,
 	.disconnect =	hid_disconnect,
+#ifdef CONFIG_PM
 	.suspend =	hid_suspend,
 	.resume =	hid_resume,
-	.reset_resume =	hid_post_reset,
+	.reset_resume =	hid_reset_resume,
+#endif
 	.pre_reset =	hid_pre_reset,
 	.post_reset =	hid_post_reset,
 	.id_table =	hid_usb_ids,
@@ -1134,7 +1392,11 @@ static struct hid_driver hid_usb_driver = {
 
 static int __init hid_init(void)
 {
-	int retval;
+	int retval = -ENOMEM;
+
+	resumption_waker = create_freezeable_workqueue("usbhid_resumer");
+	if (!resumption_waker)
+		goto no_queue;
 	retval = hid_register_driver(&hid_usb_driver);
 	if (retval)
 		goto hid_register_fail;
@@ -1158,6 +1420,8 @@ hiddev_init_fail:
 usbhid_quirks_init_fail:
 	hid_unregister_driver(&hid_usb_driver);
 hid_register_fail:
+	destroy_workqueue(resumption_waker);
+no_queue:
 	return retval;
 }
 
@@ -1167,6 +1431,7 @@ static void __exit hid_exit(void)
 	hiddev_exit();
 	usbhid_quirks_exit();
 	hid_unregister_driver(&hid_usb_driver);
+	destroy_workqueue(resumption_waker);
 }
 
 module_init(hid_init);
diff --git a/drivers/hid/usbhid/hiddev.c b/drivers/hid/usbhid/hiddev.c
index aa214170baf4..e9b436d2d944 100644
--- a/drivers/hid/usbhid/hiddev.c
+++ b/drivers/hid/usbhid/hiddev.c
@@ -246,10 +246,12 @@ static int hiddev_release(struct inode * inode, struct file * file)
 	spin_unlock_irqrestore(&list->hiddev->list_lock, flags);
 
 	if (!--list->hiddev->open) {
-		if (list->hiddev->exist)
+		if (list->hiddev->exist) {
 			usbhid_close(list->hiddev->hid);
-		else
+			usbhid_put_power(list->hiddev->hid);
+		} else {
 			kfree(list->hiddev);
+		}
 	}
 
 	kfree(list);
@@ -300,6 +302,17 @@ static int hiddev_open(struct inode *inode, struct file *file)
 	list_add_tail(&list->node, &hiddev_table[i]->list);
 	spin_unlock_irq(&list->hiddev->list_lock);
 
+	if (!list->hiddev->open++)
+		if (list->hiddev->exist) {
+			struct hid_device *hid = hiddev_table[i]->hid;
+			res = usbhid_get_power(hid);
+			if (res < 0) {
+				res = -EIO;
+				goto bail;
+			}
+			usbhid_open(hid);
+		}
+
 	return 0;
 bail:
 	file->private_data = NULL;
@@ -875,16 +888,21 @@ int hiddev_connect(struct hid_device *hid, unsigned int force)
 	hiddev->hid = hid;
 	hiddev->exist = 1;
 
+	/* when lock_kernel() usage is fixed in usb_open(),
+	 * we could also fix it here */
+	lock_kernel();
 	retval = usb_register_dev(usbhid->intf, &hiddev_class);
 	if (retval) {
 		err_hid("Not able to get a minor for this device.");
 		hid->hiddev = NULL;
+		unlock_kernel();
 		kfree(hiddev);
 		return -1;
 	} else {
 		hid->minor = usbhid->intf->minor;
 		hiddev_table[usbhid->intf->minor - HIDDEV_MINOR_BASE] = hiddev;
 	}
+	unlock_kernel();
 
 	return 0;
 }
diff --git a/drivers/hid/usbhid/usbhid.h b/drivers/hid/usbhid/usbhid.h
index 9eb30564be9c..08f505ca2e3d 100644
--- a/drivers/hid/usbhid/usbhid.h
+++ b/drivers/hid/usbhid/usbhid.h
@@ -38,7 +38,10 @@ int usbhid_wait_io(struct hid_device* hid);
 void usbhid_close(struct hid_device *hid);
 int usbhid_open(struct hid_device *hid);
 void usbhid_init_reports(struct hid_device *hid);
-void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, unsigned char dir);
+void usbhid_submit_report
+(struct hid_device *hid, struct hid_report *report, unsigned char dir);
+int usbhid_get_power(struct hid_device *hid);
+void usbhid_put_power(struct hid_device *hid);
 
 /* iofl flags */
 #define HID_CTRL_RUNNING	1
@@ -49,6 +52,9 @@ void usbhid_submit_report(struct hid_device *hid, struct hid_report *report, uns
 #define HID_CLEAR_HALT		6
 #define HID_DISCONNECTED	7
 #define HID_STARTED		8
+#define HID_REPORTED_IDLE	9
+#define HID_KEYS_PRESSED	10
+#define HID_LED_ON		11
 
 /*
  * USB-specific HID struct, to be pointed to
@@ -66,7 +72,6 @@ struct usbhid_device {
 	struct urb *urbin;                                              /* Input URB */
 	char *inbuf;                                                    /* Input buffer */
 	dma_addr_t inbuf_dma;                                           /* Input buffer dma */
-	spinlock_t inlock;                                              /* Input fifo spinlock */
 
 	struct urb *urbctrl;                                            /* Control URB */
 	struct usb_ctrlrequest *cr;                                     /* Control request struct */
@@ -75,21 +80,22 @@ struct usbhid_device {
 	unsigned char ctrlhead, ctrltail;                               /* Control fifo head & tail */
 	char *ctrlbuf;                                                  /* Control buffer */
 	dma_addr_t ctrlbuf_dma;                                         /* Control buffer dma */
-	spinlock_t ctrllock;                                            /* Control fifo spinlock */
 
 	struct urb *urbout;                                             /* Output URB */
 	struct hid_output_fifo out[HID_CONTROL_FIFO_SIZE];              /* Output pipe fifo */
 	unsigned char outhead, outtail;                                 /* Output pipe fifo head & tail */
 	char *outbuf;                                                   /* Output buffer */
 	dma_addr_t outbuf_dma;                                          /* Output buffer dma */
-	spinlock_t outlock;                                             /* Output fifo spinlock */
 
+	spinlock_t lock;						/* fifo spinlock */
 	unsigned long iofl;                                             /* I/O flags (CTRL_RUNNING, OUT_RUNNING) */
 	struct timer_list io_retry;                                     /* Retry timer */
 	unsigned long stop_retry;                                       /* Time to give up, in jiffies */
 	unsigned int retry_delay;                                       /* Delay length in ms */
 	struct work_struct reset_work;                                  /* Task context for resets */
+	struct work_struct restart_work;				/* waking up for output to be done in a task */
 	wait_queue_head_t wait;						/* For sleeping */
+	int ledcount;							/* counting the number of active leds */
 };
 
 #define	hid_to_usb_dev(hid_dev) \
diff --git a/drivers/hwmon/f75375s.c b/drivers/hwmon/f75375s.c
index 18a1ba888165..e2107e533ede 100644
--- a/drivers/hwmon/f75375s.c
+++ b/drivers/hwmon/f75375s.c
@@ -1,7 +1,7 @@
 /*
  * f75375s.c - driver for the Fintek F75375/SP and F75373
  *             hardware monitoring features
- * Copyright (C) 2006-2007  Riku Voipio <riku.voipio@movial.fi>
+ * Copyright (C) 2006-2007  Riku Voipio
  *
  * Datasheets available at:
  *
@@ -721,7 +721,7 @@ static void __exit sensors_f75375_exit(void)
 	i2c_del_driver(&f75375_driver);
 }
 
-MODULE_AUTHOR("Riku Voipio <riku.voipio@movial.fi>");
+MODULE_AUTHOR("Riku Voipio");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("F75373/F75375 hardware monitoring driver");
 
diff --git a/drivers/input/Kconfig b/drivers/input/Kconfig
index 5f9d860925a1..cd50c00ab20f 100644
--- a/drivers/input/Kconfig
+++ b/drivers/input/Kconfig
@@ -143,7 +143,7 @@ config INPUT_APMPOWER
 	---help---
 	  Say Y here if you want suspend key events to trigger a user
 	  requested suspend through APM. This is useful on embedded
-	  systems where such behviour is desired without userspace
+	  systems where such behaviour is desired without userspace
 	  interaction. If unsure, say N.
 
 	  To compile this driver as a module, choose M here: the
diff --git a/drivers/input/mouse/gpio_mouse.c b/drivers/input/mouse/gpio_mouse.c
index 0db8d16c5edd..5e5eb88d8d1e 100644
--- a/drivers/input/mouse/gpio_mouse.c
+++ b/drivers/input/mouse/gpio_mouse.c
@@ -18,7 +18,7 @@
 
 /*
  * Timer function which is run every scan_ms ms when the device is opened.
- * The dev input varaible is set to the the input_dev pointer.
+ * The dev input variable is set to the the input_dev pointer.
  */
 static void gpio_mouse_scan(struct input_polled_dev *dev)
 {
diff --git a/drivers/input/mouse/hgpk.c b/drivers/input/mouse/hgpk.c
index 81e6ebf323e9..55cd0fa68339 100644
--- a/drivers/input/mouse/hgpk.c
+++ b/drivers/input/mouse/hgpk.c
@@ -381,7 +381,7 @@ static void hgpk_disconnect(struct psmouse *psmouse)
 
 static void hgpk_recalib_work(struct work_struct *work)
 {
-	struct delayed_work *w = container_of(work, struct delayed_work, work);
+	struct delayed_work *w = to_delayed_work(work);
 	struct hgpk_data *priv = container_of(w, struct hgpk_data, recalib_wq);
 	struct psmouse *psmouse = priv->psmouse;
 
diff --git a/drivers/input/touchscreen/ads7846.c b/drivers/input/touchscreen/ads7846.c
index 7c27c8b9b6d0..056ac77e2cf0 100644
--- a/drivers/input/touchscreen/ads7846.c
+++ b/drivers/input/touchscreen/ads7846.c
@@ -295,7 +295,7 @@ name ## _show(struct device *dev, struct device_attribute *attr, char *buf) \
 static DEVICE_ATTR(name, S_IRUGO, name ## _show, NULL);
 
 
-/* Sysfs conventions report temperatures in millidegrees Celcius.
+/* Sysfs conventions report temperatures in millidegrees Celsius.
  * ADS7846 could use the low-accuracy two-sample scheme, but can't do the high
  * accuracy scheme without calibration data.  For now we won't try either;
  * userspace sees raw sensor values, and must scale/calibrate appropriately.
diff --git a/drivers/isdn/mISDN/Kconfig b/drivers/isdn/mISDN/Kconfig
index 4938355c4072..1747a02a019a 100644
--- a/drivers/isdn/mISDN/Kconfig
+++ b/drivers/isdn/mISDN/Kconfig
@@ -14,13 +14,15 @@ config MISDN_DSP
 	depends on MISDN
 	help
 	  Enable support for digital audio processing capability.
+
 	  This module may be used for special applications that require
-	  cross connecting of bchannels, conferencing, dtmf decoding
+	  cross connecting of bchannels, conferencing, dtmf decoding,
 	  echo cancelation, tone generation, and Blowfish encryption and
-	  decryption.
-	  It may use hardware features if available.
+	  decryption. It may use hardware features if available.
+
 	  E.g. it is required for PBX4Linux. Go to http://isdn.eversberg.eu
-	  and get more informations about this module and it's usage.
+	  and get more information about this module and its usage.
+
 	  If unsure, say 'N'.
 
 config MISDN_L1OIP
diff --git a/drivers/isdn/mISDN/l1oip_codec.c b/drivers/isdn/mISDN/l1oip_codec.c
index 2ec4b28d9edc..e4ecba3d48df 100644
--- a/drivers/isdn/mISDN/l1oip_codec.c
+++ b/drivers/isdn/mISDN/l1oip_codec.c
@@ -331,7 +331,7 @@ l1oip_4bit_alloc(int ulaw)
 	/* alloc conversion tables */
 	table_com = vmalloc(65536);
 	table_dec = vmalloc(512);
-	if (!table_com | !table_dec) {
+	if (!table_com || !table_dec) {
 		l1oip_4bit_free();
 		return -ENOMEM;
 	}
diff --git a/drivers/leds/Kconfig b/drivers/leds/Kconfig
index 556aeca0d860..d9db17624f12 100644
--- a/drivers/leds/Kconfig
+++ b/drivers/leds/Kconfig
@@ -100,7 +100,7 @@ config LEDS_HP6XX
 	tristate "LED Support for the HP Jornada 6xx"
 	depends on LEDS_CLASS && SH_HP6XX
 	help
-	  This option enables led support for the handheld
+	  This option enables LED support for the handheld
 	  HP Jornada 620/660/680/690.
 
 config LEDS_PCA9532
@@ -108,7 +108,7 @@ config LEDS_PCA9532
 	depends on LEDS_CLASS && I2C && INPUT && EXPERIMENTAL
 	help
 	  This option enables support for NXP pca9532
-	  led controller. It is generally only usefull
+	  LED controller. It is generally only useful
 	  as a platform driver
 
 config LEDS_GPIO
@@ -144,7 +144,7 @@ config LEDS_CLEVO_MAIL
 	  	Positivo Mobile (Clevo M5x0V)
 
 	  If your model is not listed here you can try the "nodetect"
-	  module paramter.
+	  module parameter.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called leds-clevo-mail.
diff --git a/drivers/leds/leds-pca9532.c b/drivers/leds/leds-pca9532.c
index 76ec7498e2d5..bd3b431c9710 100644
--- a/drivers/leds/leds-pca9532.c
+++ b/drivers/leds/leds-pca9532.c
@@ -1,7 +1,7 @@
 /*
  * pca9532.c - 16-bit Led dimmer
  *
- * Copyright (C) 2008 Riku Voipio <riku.voipio@movial.fi>
+ * Copyright (C) 2008 Riku Voipio
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License as published by
@@ -367,7 +367,7 @@ static void __exit pca9532_exit(void)
 	i2c_del_driver(&pca9532_driver);
 }
 
-MODULE_AUTHOR("Riku Voipio <riku.voipio@movial.fi>");
+MODULE_AUTHOR("Riku Voipio");
 MODULE_LICENSE("GPL");
 MODULE_DESCRIPTION("PCA 9532 LED dimmer");
 
diff --git a/drivers/md/Kconfig b/drivers/md/Kconfig
index 2281b5098e95..36e0675be9f7 100644
--- a/drivers/md/Kconfig
+++ b/drivers/md/Kconfig
@@ -121,6 +121,7 @@ config MD_RAID10
 config MD_RAID456
 	tristate "RAID-4/RAID-5/RAID-6 mode"
 	depends on BLK_DEV_MD
+	select MD_RAID6_PQ
 	select ASYNC_MEMCPY
 	select ASYNC_XOR
 	---help---
@@ -151,34 +152,8 @@ config MD_RAID456
 
 	  If unsure, say Y.
 
-config MD_RAID5_RESHAPE
-	bool "Support adding drives to a raid-5 array"
-	depends on MD_RAID456
-	default y
-	---help---
-	  A RAID-5 set can be expanded by adding extra drives. This
-	  requires "restriping" the array which means (almost) every
-	  block must be written to a different place.
-
-          This option allows such restriping to be done while the array
-	  is online.
-
-	  You will need mdadm version 2.4.1 or later to use this
-	  feature safely.  During the early stage of reshape there is
-	  a critical section where live data is being over-written.  A
-	  crash during this time needs extra care for recovery.  The
-	  newer mdadm takes a copy of the data in the critical section
-	  and will restore it, if necessary, after a crash.
-
-	  The mdadm usage is e.g.
-	       mdadm --grow /dev/md1 --raid-disks=6
-	  to grow '/dev/md1' to having 6 disks.
-
-	  Note: The array can only be expanded, not contracted.
-	  There should be enough spares already present to make the new
-	  array workable.
-
-	  If unsure, say Y.
+config MD_RAID6_PQ
+	tristate
 
 config MD_MULTIPATH
 	tristate "Multipath I/O support"
diff --git a/drivers/md/Makefile b/drivers/md/Makefile
index 72880b7e28d9..45cc5951d928 100644
--- a/drivers/md/Makefile
+++ b/drivers/md/Makefile
@@ -2,20 +2,21 @@
 # Makefile for the kernel software RAID and LVM drivers.
 #
 
-dm-mod-objs	:= dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
+dm-mod-y	+= dm.o dm-table.o dm-target.o dm-linear.o dm-stripe.o \
 		   dm-ioctl.o dm-io.o dm-kcopyd.o dm-sysfs.o
-dm-multipath-objs := dm-path-selector.o dm-mpath.o
-dm-snapshot-objs := dm-snap.o dm-exception-store.o dm-snap-transient.o \
+dm-multipath-y	+= dm-path-selector.o dm-mpath.o
+dm-snapshot-y	+= dm-snap.o dm-exception-store.o dm-snap-transient.o \
 		    dm-snap-persistent.o
-dm-mirror-objs	:= dm-raid1.o
-md-mod-objs     := md.o bitmap.o
-raid456-objs	:= raid5.o raid6algos.o raid6recov.o raid6tables.o \
+dm-mirror-y	+= dm-raid1.o
+md-mod-y	+= md.o bitmap.o
+raid456-y	+= raid5.o
+raid6_pq-y	+= raid6algos.o raid6recov.o raid6tables.o \
 		   raid6int1.o raid6int2.o raid6int4.o \
 		   raid6int8.o raid6int16.o raid6int32.o \
 		   raid6altivec1.o raid6altivec2.o raid6altivec4.o \
 		   raid6altivec8.o \
 		   raid6mmx.o raid6sse1.o raid6sse2.o
-hostprogs-y	:= mktables
+hostprogs-y	+= mktables
 
 # Note: link order is important.  All raid personalities
 # and must come before md.o, as they each initialise 
@@ -26,6 +27,7 @@ obj-$(CONFIG_MD_LINEAR)		+= linear.o
 obj-$(CONFIG_MD_RAID0)		+= raid0.o
 obj-$(CONFIG_MD_RAID1)		+= raid1.o
 obj-$(CONFIG_MD_RAID10)		+= raid10.o
+obj-$(CONFIG_MD_RAID6_PQ)	+= raid6_pq.o
 obj-$(CONFIG_MD_RAID456)	+= raid456.o
 obj-$(CONFIG_MD_MULTIPATH)	+= multipath.o
 obj-$(CONFIG_MD_FAULTY)		+= faulty.o
diff --git a/drivers/md/bitmap.c b/drivers/md/bitmap.c
index 719943763391..f8a9f7ab2cb8 100644
--- a/drivers/md/bitmap.c
+++ b/drivers/md/bitmap.c
@@ -16,6 +16,7 @@
  * wait if count gets too high, wake when it drops to half.
  */
 
+#include <linux/blkdev.h>
 #include <linux/module.h>
 #include <linux/errno.h>
 #include <linux/slab.h>
@@ -26,8 +27,8 @@
 #include <linux/file.h>
 #include <linux/mount.h>
 #include <linux/buffer_head.h>
-#include <linux/raid/md.h>
-#include <linux/raid/bitmap.h>
+#include "md.h"
+#include "bitmap.h"
 
 /* debug macros */
 
@@ -111,9 +112,10 @@ static int bitmap_checkpage(struct bitmap *bitmap, unsigned long page, int creat
 	unsigned char *mappage;
 
 	if (page >= bitmap->pages) {
-		printk(KERN_ALERT
-			"%s: invalid bitmap page request: %lu (> %lu)\n",
-			bmname(bitmap), page, bitmap->pages-1);
+		/* This can happen if bitmap_start_sync goes beyond
+		 * End-of-device while looking for a whole page.
+		 * It is harmless.
+		 */
 		return -EINVAL;
 	}
 
@@ -265,7 +267,6 @@ static mdk_rdev_t *next_active_rdev(mdk_rdev_t *rdev, mddev_t *mddev)
 	list_for_each_continue_rcu(pos, &mddev->disks) {
 		rdev = list_entry(pos, mdk_rdev_t, same_set);
 		if (rdev->raid_disk >= 0 &&
-		    test_bit(In_sync, &rdev->flags) &&
 		    !test_bit(Faulty, &rdev->flags)) {
 			/* this is a usable devices */
 			atomic_inc(&rdev->nr_pending);
@@ -297,7 +298,7 @@ static int write_sb_page(struct bitmap *bitmap, struct page *page, int wait)
 				    + size/512 > 0)
 					/* bitmap runs in to metadata */
 					goto bad_alignment;
-				if (rdev->data_offset + mddev->size*2
+				if (rdev->data_offset + mddev->dev_sectors
 				    > rdev->sb_start + bitmap->offset)
 					/* data runs in to bitmap */
 					goto bad_alignment;
@@ -570,7 +571,7 @@ static int bitmap_read_sb(struct bitmap *bitmap)
 	else if (le32_to_cpu(sb->version) < BITMAP_MAJOR_LO ||
 		 le32_to_cpu(sb->version) > BITMAP_MAJOR_HI)
 		reason = "unrecognized superblock version";
-	else if (chunksize < PAGE_SIZE)
+	else if (chunksize < 512)
 		reason = "bitmap chunksize too small";
 	else if ((1 << ffz(~chunksize)) != chunksize)
 		reason = "bitmap chunksize not a power of 2";
@@ -1306,6 +1307,9 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 		PRINTK(KERN_DEBUG "dec write-behind count %d/%d\n",
 		  atomic_read(&bitmap->behind_writes), bitmap->max_write_behind);
 	}
+	if (bitmap->mddev->degraded)
+		/* Never clear bits or update events_cleared when degraded */
+		success = 0;
 
 	while (sectors) {
 		int blocks;
@@ -1345,8 +1349,8 @@ void bitmap_endwrite(struct bitmap *bitmap, sector_t offset, unsigned long secto
 	}
 }
 
-int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
-			int degraded)
+static int __bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+			       int degraded)
 {
 	bitmap_counter_t *bmc;
 	int rv;
@@ -1374,6 +1378,29 @@ int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
 	return rv;
 }
 
+int bitmap_start_sync(struct bitmap *bitmap, sector_t offset, int *blocks,
+		      int degraded)
+{
+	/* bitmap_start_sync must always report on multiples of whole
+	 * pages, otherwise resync (which is very PAGE_SIZE based) will
+	 * get confused.
+	 * So call __bitmap_start_sync repeatedly (if needed) until
+	 * At least PAGE_SIZE>>9 blocks are covered.
+	 * Return the 'or' of the result.
+	 */
+	int rv = 0;
+	int blocks1;
+
+	*blocks = 0;
+	while (*blocks < (PAGE_SIZE>>9)) {
+		rv |= __bitmap_start_sync(bitmap, offset,
+					  &blocks1, degraded);
+		offset += blocks1;
+		*blocks += blocks1;
+	}
+	return rv;
+}
+
 void bitmap_end_sync(struct bitmap *bitmap, sector_t offset, int *blocks, int aborted)
 {
 	bitmap_counter_t *bmc;
@@ -1443,6 +1470,8 @@ void bitmap_cond_end_sync(struct bitmap *bitmap, sector_t sector)
 	wait_event(bitmap->mddev->recovery_wait,
 		   atomic_read(&bitmap->mddev->recovery_active) == 0);
 
+	bitmap->mddev->curr_resync_completed = bitmap->mddev->curr_resync;
+	set_bit(MD_CHANGE_CLEAN, &bitmap->mddev->flags);
 	sector &= ~((1ULL << CHUNK_BLOCK_SHIFT(bitmap)) - 1);
 	s = 0;
 	while (s < sector && s < bitmap->mddev->resync_max_sectors) {
diff --git a/include/linux/raid/bitmap.h b/drivers/md/bitmap.h
index e98900671ca9..e98900671ca9 100644
--- a/include/linux/raid/bitmap.h
+++ b/drivers/md/bitmap.h
diff --git a/drivers/md/dm-bio-list.h b/drivers/md/dm-bio-list.h
index d4509be0fe67..345098b4ca77 100644
--- a/drivers/md/dm-bio-list.h
+++ b/drivers/md/dm-bio-list.h
@@ -52,6 +52,16 @@ static inline void bio_list_add(struct bio_list *bl, struct bio *bio)
 	bl->tail = bio;
 }
 
+static inline void bio_list_add_head(struct bio_list *bl, struct bio *bio)
+{
+	bio->bi_next = bl->head;
+
+	bl->head = bio;
+
+	if (!bl->tail)
+		bl->tail = bio;
+}
+
 static inline void bio_list_merge(struct bio_list *bl, struct bio_list *bl2)
 {
 	if (!bl2->head)
diff --git a/drivers/md/dm-bio-record.h b/drivers/md/dm-bio-record.h
index d3ec217847d6..3a8cfa2645c7 100644
--- a/drivers/md/dm-bio-record.h
+++ b/drivers/md/dm-bio-record.h
@@ -16,30 +16,56 @@
  * functions in this file help the target record and restore the
  * original bio state.
  */
+
+struct dm_bio_vec_details {
+#if PAGE_SIZE < 65536
+	__u16 bv_len;
+	__u16 bv_offset;
+#else
+	unsigned bv_len;
+	unsigned bv_offset;
+#endif
+};
+
 struct dm_bio_details {
 	sector_t bi_sector;
 	struct block_device *bi_bdev;
 	unsigned int bi_size;
 	unsigned short bi_idx;
 	unsigned long bi_flags;
+	struct dm_bio_vec_details bi_io_vec[BIO_MAX_PAGES];
 };
 
 static inline void dm_bio_record(struct dm_bio_details *bd, struct bio *bio)
 {
+	unsigned i;
+
 	bd->bi_sector = bio->bi_sector;
 	bd->bi_bdev = bio->bi_bdev;
 	bd->bi_size = bio->bi_size;
 	bd->bi_idx = bio->bi_idx;
 	bd->bi_flags = bio->bi_flags;
+
+	for (i = 0; i < bio->bi_vcnt; i++) {
+		bd->bi_io_vec[i].bv_len = bio->bi_io_vec[i].bv_len;
+		bd->bi_io_vec[i].bv_offset = bio->bi_io_vec[i].bv_offset;
+	}
 }
 
 static inline void dm_bio_restore(struct dm_bio_details *bd, struct bio *bio)
 {
+	unsigned i;
+
 	bio->bi_sector = bd->bi_sector;
 	bio->bi_bdev = bd->bi_bdev;
 	bio->bi_size = bd->bi_size;
 	bio->bi_idx = bd->bi_idx;
 	bio->bi_flags = bd->bi_flags;
+
+	for (i = 0; i < bio->bi_vcnt; i++) {
+		bio->bi_io_vec[i].bv_len = bd->bi_io_vec[i].bv_len;
+		bio->bi_io_vec[i].bv_offset = bd->bi_io_vec[i].bv_offset;
+	}
 }
 
 #endif
diff --git a/drivers/md/dm-crypt.c b/drivers/md/dm-crypt.c
index bfefd079a955..53394e863c74 100644
--- a/drivers/md/dm-crypt.c
+++ b/drivers/md/dm-crypt.c
@@ -1156,8 +1156,7 @@ bad_ivmode:
 	crypto_free_ablkcipher(tfm);
 bad_cipher:
 	/* Must zero key material before freeing */
-	memset(cc, 0, sizeof(*cc) + cc->key_size * sizeof(u8));
-	kfree(cc);
+	kzfree(cc);
 	return -EINVAL;
 }
 
@@ -1183,8 +1182,7 @@ static void crypt_dtr(struct dm_target *ti)
 	dm_put_device(ti, cc->dev);
 
 	/* Must zero key material before freeing */
-	memset(cc, 0, sizeof(*cc) + cc->key_size * sizeof(u8));
-	kfree(cc);
+	kzfree(cc);
 }
 
 static int crypt_map(struct dm_target *ti, struct bio *bio,
diff --git a/drivers/md/dm-exception-store.c b/drivers/md/dm-exception-store.c
index dccbfb0e010f..a2e26c242141 100644
--- a/drivers/md/dm-exception-store.c
+++ b/drivers/md/dm-exception-store.c
@@ -7,6 +7,7 @@
 
 #include "dm-exception-store.h"
 
+#include <linux/ctype.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
 #include <linux/vmalloc.h>
@@ -14,6 +15,257 @@
 
 #define DM_MSG_PREFIX "snapshot exception stores"
 
+static LIST_HEAD(_exception_store_types);
+static DEFINE_SPINLOCK(_lock);
+
+static struct dm_exception_store_type *__find_exception_store_type(const char *name)
+{
+	struct dm_exception_store_type *type;
+
+	list_for_each_entry(type, &_exception_store_types, list)
+		if (!strcmp(name, type->name))
+			return type;
+
+	return NULL;
+}
+
+static struct dm_exception_store_type *_get_exception_store_type(const char *name)
+{
+	struct dm_exception_store_type *type;
+
+	spin_lock(&_lock);
+
+	type = __find_exception_store_type(name);
+
+	if (type && !try_module_get(type->module))
+		type = NULL;
+
+	spin_unlock(&_lock);
+
+	return type;
+}
+
+/*
+ * get_type
+ * @type_name
+ *
+ * Attempt to retrieve the dm_exception_store_type by name.  If not already
+ * available, attempt to load the appropriate module.
+ *
+ * Exstore modules are named "dm-exstore-" followed by the 'type_name'.
+ * Modules may contain multiple types.
+ * This function will first try the module "dm-exstore-<type_name>",
+ * then truncate 'type_name' on the last '-' and try again.
+ *
+ * For example, if type_name was "clustered-shared", it would search
+ * 'dm-exstore-clustered-shared' then 'dm-exstore-clustered'.
+ *
+ * 'dm-exception-store-<type_name>' is too long of a name in my
+ * opinion, which is why I've chosen to have the files
+ * containing exception store implementations be 'dm-exstore-<type_name>'.
+ * If you want your module to be autoloaded, you will follow this
+ * naming convention.
+ *
+ * Returns: dm_exception_store_type* on success, NULL on failure
+ */
+static struct dm_exception_store_type *get_type(const char *type_name)
+{
+	char *p, *type_name_dup;
+	struct dm_exception_store_type *type;
+
+	type = _get_exception_store_type(type_name);
+	if (type)
+		return type;
+
+	type_name_dup = kstrdup(type_name, GFP_KERNEL);
+	if (!type_name_dup) {
+		DMERR("No memory left to attempt load for \"%s\"", type_name);
+		return NULL;
+	}
+
+	while (request_module("dm-exstore-%s", type_name_dup) ||
+	       !(type = _get_exception_store_type(type_name))) {
+		p = strrchr(type_name_dup, '-');
+		if (!p)
+			break;
+		p[0] = '\0';
+	}
+
+	if (!type)
+		DMWARN("Module for exstore type \"%s\" not found.", type_name);
+
+	kfree(type_name_dup);
+
+	return type;
+}
+
+static void put_type(struct dm_exception_store_type *type)
+{
+	spin_lock(&_lock);
+	module_put(type->module);
+	spin_unlock(&_lock);
+}
+
+int dm_exception_store_type_register(struct dm_exception_store_type *type)
+{
+	int r = 0;
+
+	spin_lock(&_lock);
+	if (!__find_exception_store_type(type->name))
+		list_add(&type->list, &_exception_store_types);
+	else
+		r = -EEXIST;
+	spin_unlock(&_lock);
+
+	return r;
+}
+EXPORT_SYMBOL(dm_exception_store_type_register);
+
+int dm_exception_store_type_unregister(struct dm_exception_store_type *type)
+{
+	spin_lock(&_lock);
+
+	if (!__find_exception_store_type(type->name)) {
+		spin_unlock(&_lock);
+		return -EINVAL;
+	}
+
+	list_del(&type->list);
+
+	spin_unlock(&_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(dm_exception_store_type_unregister);
+
+/*
+ * Round a number up to the nearest 'size' boundary.  size must
+ * be a power of 2.
+ */
+static ulong round_up(ulong n, ulong size)
+{
+	size--;
+	return (n + size) & ~size;
+}
+
+static int set_chunk_size(struct dm_exception_store *store,
+			  const char *chunk_size_arg, char **error)
+{
+	unsigned long chunk_size_ulong;
+	char *value;
+
+	chunk_size_ulong = simple_strtoul(chunk_size_arg, &value, 10);
+	if (*chunk_size_arg == '\0' || *value != '\0') {
+		*error = "Invalid chunk size";
+		return -EINVAL;
+	}
+
+	if (!chunk_size_ulong) {
+		store->chunk_size = store->chunk_mask = store->chunk_shift = 0;
+		return 0;
+	}
+
+	/*
+	 * Chunk size must be multiple of page size.  Silently
+	 * round up if it's not.
+	 */
+	chunk_size_ulong = round_up(chunk_size_ulong, PAGE_SIZE >> 9);
+
+	/* Check chunk_size is a power of 2 */
+	if (!is_power_of_2(chunk_size_ulong)) {
+		*error = "Chunk size is not a power of 2";
+		return -EINVAL;
+	}
+
+	/* Validate the chunk size against the device block size */
+	if (chunk_size_ulong % (bdev_hardsect_size(store->cow->bdev) >> 9)) {
+		*error = "Chunk size is not a multiple of device blocksize";
+		return -EINVAL;
+	}
+
+	store->chunk_size = chunk_size_ulong;
+	store->chunk_mask = chunk_size_ulong - 1;
+	store->chunk_shift = ffs(chunk_size_ulong) - 1;
+
+	return 0;
+}
+
+int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
+			      unsigned *args_used,
+			      struct dm_exception_store **store)
+{
+	int r = 0;
+	struct dm_exception_store_type *type;
+	struct dm_exception_store *tmp_store;
+	char persistent;
+
+	if (argc < 3) {
+		ti->error = "Insufficient exception store arguments";
+		return -EINVAL;
+	}
+
+	tmp_store = kmalloc(sizeof(*tmp_store), GFP_KERNEL);
+	if (!tmp_store) {
+		ti->error = "Exception store allocation failed";
+		return -ENOMEM;
+	}
+
+	persistent = toupper(*argv[1]);
+	if (persistent != 'P' && persistent != 'N') {
+		ti->error = "Persistent flag is not P or N";
+		return -EINVAL;
+	}
+
+	type = get_type(argv[1]);
+	if (!type) {
+		ti->error = "Exception store type not recognised";
+		r = -EINVAL;
+		goto bad_type;
+	}
+
+	tmp_store->type = type;
+	tmp_store->ti = ti;
+
+	r = dm_get_device(ti, argv[0], 0, 0,
+			  FMODE_READ | FMODE_WRITE, &tmp_store->cow);
+	if (r) {
+		ti->error = "Cannot get COW device";
+		goto bad_cow;
+	}
+
+	r = set_chunk_size(tmp_store, argv[2], &ti->error);
+	if (r)
+		goto bad_cow;
+
+	r = type->ctr(tmp_store, 0, NULL);
+	if (r) {
+		ti->error = "Exception store type constructor failed";
+		goto bad_ctr;
+	}
+
+	*args_used = 3;
+	*store = tmp_store;
+	return 0;
+
+bad_ctr:
+	dm_put_device(ti, tmp_store->cow);
+bad_cow:
+	put_type(type);
+bad_type:
+	kfree(tmp_store);
+	return r;
+}
+EXPORT_SYMBOL(dm_exception_store_create);
+
+void dm_exception_store_destroy(struct dm_exception_store *store)
+{
+	store->type->dtr(store);
+	dm_put_device(store->ti, store->cow);
+	put_type(store->type);
+	kfree(store);
+}
+EXPORT_SYMBOL(dm_exception_store_destroy);
+
 int dm_exception_store_init(void)
 {
 	int r;
diff --git a/drivers/md/dm-exception-store.h b/drivers/md/dm-exception-store.h
index bb9f33d5daa2..0a2e6e7f67b3 100644
--- a/drivers/md/dm-exception-store.h
+++ b/drivers/md/dm-exception-store.h
@@ -37,11 +37,18 @@ struct dm_snap_exception {
  * Abstraction to handle the meta/layout of exception stores (the
  * COW device).
  */
-struct dm_exception_store {
+struct dm_exception_store;
+struct dm_exception_store_type {
+	const char *name;
+	struct module *module;
+
+	int (*ctr) (struct dm_exception_store *store,
+		    unsigned argc, char **argv);
+
 	/*
 	 * Destroys this object when you've finished with it.
 	 */
-	void (*destroy) (struct dm_exception_store *store);
+	void (*dtr) (struct dm_exception_store *store);
 
 	/*
 	 * The target shouldn't read the COW device until this is
@@ -72,8 +79,9 @@ struct dm_exception_store {
 	 */
 	void (*drop_snapshot) (struct dm_exception_store *store);
 
-	int (*status) (struct dm_exception_store *store, status_type_t status,
-		       char *result, unsigned int maxlen);
+	unsigned (*status) (struct dm_exception_store *store,
+			    status_type_t status, char *result,
+			    unsigned maxlen);
 
 	/*
 	 * Return how full the snapshot is.
@@ -82,7 +90,21 @@ struct dm_exception_store {
 			       sector_t *numerator,
 			       sector_t *denominator);
 
-	struct dm_snapshot *snap;
+	/* For internal device-mapper use only. */
+	struct list_head list;
+};
+
+struct dm_exception_store {
+	struct dm_exception_store_type *type;
+	struct dm_target *ti;
+
+	struct dm_dev *cow;
+
+	/* Size of data blocks saved - must be a power of 2 */
+	chunk_t chunk_size;
+	chunk_t chunk_mask;
+	chunk_t chunk_shift;
+
 	void *context;
 };
 
@@ -129,6 +151,28 @@ static inline void dm_consecutive_chunk_count_inc(struct dm_snap_exception *e)
 
 #  endif
 
+/*
+ * Return the number of sectors in the device.
+ */
+static inline sector_t get_dev_size(struct block_device *bdev)
+{
+	return bdev->bd_inode->i_size >> SECTOR_SHIFT;
+}
+
+static inline chunk_t sector_to_chunk(struct dm_exception_store *store,
+				      sector_t sector)
+{
+	return (sector & ~store->chunk_mask) >> store->chunk_shift;
+}
+
+int dm_exception_store_type_register(struct dm_exception_store_type *type);
+int dm_exception_store_type_unregister(struct dm_exception_store_type *type);
+
+int dm_exception_store_create(struct dm_target *ti, int argc, char **argv,
+			      unsigned *args_used,
+			      struct dm_exception_store **store);
+void dm_exception_store_destroy(struct dm_exception_store *store);
+
 int dm_exception_store_init(void);
 void dm_exception_store_exit(void);
 
@@ -141,8 +185,4 @@ void dm_persistent_snapshot_exit(void);
 int dm_transient_snapshot_init(void);
 void dm_transient_snapshot_exit(void);
 
-int dm_create_persistent(struct dm_exception_store *store);
-
-int dm_create_transient(struct dm_exception_store *store);
-
 #endif /* _LINUX_DM_EXCEPTION_STORE */
diff --git a/drivers/md/dm-io.c b/drivers/md/dm-io.c
index 36e2b5e46a6b..e73aabd61cd7 100644
--- a/drivers/md/dm-io.c
+++ b/drivers/md/dm-io.c
@@ -370,16 +370,13 @@ static int sync_io(struct dm_io_client *client, unsigned int num_regions,
 	while (1) {
 		set_current_state(TASK_UNINTERRUPTIBLE);
 
-		if (!atomic_read(&io.count) || signal_pending(current))
+		if (!atomic_read(&io.count))
 			break;
 
 		io_schedule();
 	}
 	set_current_state(TASK_RUNNING);
 
-	if (atomic_read(&io.count))
-		return -EINTR;
-
 	if (error_bits)
 		*error_bits = io.error_bits;
 
diff --git a/drivers/md/dm-log.c b/drivers/md/dm-log.c
index 737961f275c1..be233bc4d917 100644
--- a/drivers/md/dm-log.c
+++ b/drivers/md/dm-log.c
@@ -16,40 +16,29 @@
 
 #define DM_MSG_PREFIX "dirty region log"
 
-struct dm_dirty_log_internal {
-	struct dm_dirty_log_type *type;
-
-	struct list_head list;
-	long use;
-};
-
 static LIST_HEAD(_log_types);
 static DEFINE_SPINLOCK(_lock);
 
-static struct dm_dirty_log_internal *__find_dirty_log_type(const char *name)
+static struct dm_dirty_log_type *__find_dirty_log_type(const char *name)
 {
-	struct dm_dirty_log_internal *log_type;
+	struct dm_dirty_log_type *log_type;
 
 	list_for_each_entry(log_type, &_log_types, list)
-		if (!strcmp(name, log_type->type->name))
+		if (!strcmp(name, log_type->name))
 			return log_type;
 
 	return NULL;
 }
 
-static struct dm_dirty_log_internal *_get_dirty_log_type(const char *name)
+static struct dm_dirty_log_type *_get_dirty_log_type(const char *name)
 {
-	struct dm_dirty_log_internal *log_type;
+	struct dm_dirty_log_type *log_type;
 
 	spin_lock(&_lock);
 
 	log_type = __find_dirty_log_type(name);
-	if (log_type) {
-		if (!log_type->use && !try_module_get(log_type->type->module))
-			log_type = NULL;
-		else
-			log_type->use++;
-	}
+	if (log_type && !try_module_get(log_type->module))
+		log_type = NULL;
 
 	spin_unlock(&_lock);
 
@@ -76,14 +65,14 @@ static struct dm_dirty_log_internal *_get_dirty_log_type(const char *name)
 static struct dm_dirty_log_type *get_type(const char *type_name)
 {
 	char *p, *type_name_dup;
-	struct dm_dirty_log_internal *log_type;
+	struct dm_dirty_log_type *log_type;
 
 	if (!type_name)
 		return NULL;
 
 	log_type = _get_dirty_log_type(type_name);
 	if (log_type)
-		return log_type->type;
+		return log_type;
 
 	type_name_dup = kstrdup(type_name, GFP_KERNEL);
 	if (!type_name_dup) {
@@ -105,56 +94,33 @@ static struct dm_dirty_log_type *get_type(const char *type_name)
 
 	kfree(type_name_dup);
 
-	return log_type ? log_type->type : NULL;
+	return log_type;
 }
 
 static void put_type(struct dm_dirty_log_type *type)
 {
-	struct dm_dirty_log_internal *log_type;
-
 	if (!type)
 		return;
 
 	spin_lock(&_lock);
-	log_type = __find_dirty_log_type(type->name);
-	if (!log_type)
+	if (!__find_dirty_log_type(type->name))
 		goto out;
 
-	if (!--log_type->use)
-		module_put(type->module);
-
-	BUG_ON(log_type->use < 0);
+	module_put(type->module);
 
 out:
 	spin_unlock(&_lock);
 }
 
-static struct dm_dirty_log_internal *_alloc_dirty_log_type(struct dm_dirty_log_type *type)
-{
-	struct dm_dirty_log_internal *log_type = kzalloc(sizeof(*log_type),
-							 GFP_KERNEL);
-
-	if (log_type)
-		log_type->type = type;
-
-	return log_type;
-}
-
 int dm_dirty_log_type_register(struct dm_dirty_log_type *type)
 {
-	struct dm_dirty_log_internal *log_type = _alloc_dirty_log_type(type);
 	int r = 0;
 
-	if (!log_type)
-		return -ENOMEM;
-
 	spin_lock(&_lock);
 	if (!__find_dirty_log_type(type->name))
-		list_add(&log_type->list, &_log_types);
-	else {
-		kfree(log_type);
+		list_add(&type->list, &_log_types);
+	else
 		r = -EEXIST;
-	}
 	spin_unlock(&_lock);
 
 	return r;
@@ -163,25 +129,16 @@ EXPORT_SYMBOL(dm_dirty_log_type_register);
 
 int dm_dirty_log_type_unregister(struct dm_dirty_log_type *type)
 {
-	struct dm_dirty_log_internal *log_type;
-
 	spin_lock(&_lock);
 
-	log_type = __find_dirty_log_type(type->name);
-	if (!log_type) {
+	if (!__find_dirty_log_type(type->name)) {
 		spin_unlock(&_lock);
 		return -EINVAL;
 	}
 
-	if (log_type->use) {
-		spin_unlock(&_lock);
-		return -ETXTBSY;
-	}
-
-	list_del(&log_type->list);
+	list_del(&type->list);
 
 	spin_unlock(&_lock);
-	kfree(log_type);
 
 	return 0;
 }
diff --git a/drivers/md/dm-path-selector.c b/drivers/md/dm-path-selector.c
index 96ea226155b1..42c04f04a0c4 100644
--- a/drivers/md/dm-path-selector.c
+++ b/drivers/md/dm-path-selector.c
@@ -17,9 +17,7 @@
 
 struct ps_internal {
 	struct path_selector_type pst;
-
 	struct list_head list;
-	long use;
 };
 
 #define pst_to_psi(__pst) container_of((__pst), struct ps_internal, pst)
@@ -45,12 +43,8 @@ static struct ps_internal *get_path_selector(const char *name)
 
 	down_read(&_ps_lock);
 	psi = __find_path_selector_type(name);
-	if (psi) {
-		if ((psi->use == 0) && !try_module_get(psi->pst.module))
-			psi = NULL;
-		else
-			psi->use++;
-	}
+	if (psi && !try_module_get(psi->pst.module))
+		psi = NULL;
 	up_read(&_ps_lock);
 
 	return psi;
@@ -84,11 +78,7 @@ void dm_put_path_selector(struct path_selector_type *pst)
 	if (!psi)
 		goto out;
 
-	if (--psi->use == 0)
-		module_put(psi->pst.module);
-
-	BUG_ON(psi->use < 0);
-
+	module_put(psi->pst.module);
 out:
 	up_read(&_ps_lock);
 }
@@ -136,11 +126,6 @@ int dm_unregister_path_selector(struct path_selector_type *pst)
 		return -EINVAL;
 	}
 
-	if (psi->use) {
-		up_write(&_ps_lock);
-		return -ETXTBSY;
-	}
-
 	list_del(&psi->list);
 
 	up_write(&_ps_lock);
diff --git a/drivers/md/dm-raid1.c b/drivers/md/dm-raid1.c
index 4d6bc101962e..536ef0bef154 100644
--- a/drivers/md/dm-raid1.c
+++ b/drivers/md/dm-raid1.c
@@ -145,6 +145,8 @@ struct dm_raid1_read_record {
 	struct dm_bio_details details;
 };
 
+static struct kmem_cache *_dm_raid1_read_record_cache;
+
 /*
  * Every mirror should look like this one.
  */
@@ -586,6 +588,9 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	int state;
 	struct bio *bio;
 	struct bio_list sync, nosync, recover, *this_list = NULL;
+	struct bio_list requeue;
+	struct dm_dirty_log *log = dm_rh_dirty_log(ms->rh);
+	region_t region;
 
 	if (!writes->head)
 		return;
@@ -596,10 +601,18 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	bio_list_init(&sync);
 	bio_list_init(&nosync);
 	bio_list_init(&recover);
+	bio_list_init(&requeue);
 
 	while ((bio = bio_list_pop(writes))) {
-		state = dm_rh_get_state(ms->rh,
-					dm_rh_bio_to_region(ms->rh, bio), 1);
+		region = dm_rh_bio_to_region(ms->rh, bio);
+
+		if (log->type->is_remote_recovering &&
+		    log->type->is_remote_recovering(log, region)) {
+			bio_list_add(&requeue, bio);
+			continue;
+		}
+
+		state = dm_rh_get_state(ms->rh, region, 1);
 		switch (state) {
 		case DM_RH_CLEAN:
 		case DM_RH_DIRTY:
@@ -619,6 +632,16 @@ static void do_writes(struct mirror_set *ms, struct bio_list *writes)
 	}
 
 	/*
+	 * Add bios that are delayed due to remote recovery
+	 * back on to the write queue
+	 */
+	if (unlikely(requeue.head)) {
+		spin_lock_irq(&ms->lock);
+		bio_list_merge(&ms->writes, &requeue);
+		spin_unlock_irq(&ms->lock);
+	}
+
+	/*
 	 * Increment the pending counts for any regions that will
 	 * be written to (writes to recover regions are going to
 	 * be delayed).
@@ -764,9 +787,9 @@ static struct mirror_set *alloc_context(unsigned int nr_mirrors,
 	atomic_set(&ms->suspend, 0);
 	atomic_set(&ms->default_mirror, DEFAULT_MIRROR);
 
-	len = sizeof(struct dm_raid1_read_record);
-	ms->read_record_pool = mempool_create_kmalloc_pool(MIN_READ_RECORDS,
-							   len);
+	ms->read_record_pool = mempool_create_slab_pool(MIN_READ_RECORDS,
+						_dm_raid1_read_record_cache);
+
 	if (!ms->read_record_pool) {
 		ti->error = "Error creating mirror read_record_pool";
 		kfree(ms);
@@ -1279,16 +1302,31 @@ static int __init dm_mirror_init(void)
 {
 	int r;
 
+	_dm_raid1_read_record_cache = KMEM_CACHE(dm_raid1_read_record, 0);
+	if (!_dm_raid1_read_record_cache) {
+		DMERR("Can't allocate dm_raid1_read_record cache");
+		r = -ENOMEM;
+		goto bad_cache;
+	}
+
 	r = dm_register_target(&mirror_target);
-	if (r < 0)
+	if (r < 0) {
 		DMERR("Failed to register mirror target");
+		goto bad_target;
+	}
+
+	return 0;
 
+bad_target:
+	kmem_cache_destroy(_dm_raid1_read_record_cache);
+bad_cache:
 	return r;
 }
 
 static void __exit dm_mirror_exit(void)
 {
 	dm_unregister_target(&mirror_target);
+	kmem_cache_destroy(_dm_raid1_read_record_cache);
 }
 
 /* Module hooks */
diff --git a/drivers/md/dm-snap-persistent.c b/drivers/md/dm-snap-persistent.c
index 936b34e0959f..e75c6dd76a9a 100644
--- a/drivers/md/dm-snap-persistent.c
+++ b/drivers/md/dm-snap-persistent.c
@@ -6,7 +6,6 @@
  */
 
 #include "dm-exception-store.h"
-#include "dm-snap.h"
 
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -89,7 +88,7 @@ struct commit_callback {
  * The top level structure for a persistent exception store.
  */
 struct pstore {
-	struct dm_snapshot *snap;	/* up pointer to my snapshot */
+	struct dm_exception_store *store;
 	int version;
 	int valid;
 	uint32_t exceptions_per_area;
@@ -141,7 +140,7 @@ static int alloc_area(struct pstore *ps)
 	int r = -ENOMEM;
 	size_t len;
 
-	len = ps->snap->chunk_size << SECTOR_SHIFT;
+	len = ps->store->chunk_size << SECTOR_SHIFT;
 
 	/*
 	 * Allocate the chunk_size block of memory that will hold
@@ -163,9 +162,12 @@ static int alloc_area(struct pstore *ps)
 
 static void free_area(struct pstore *ps)
 {
-	vfree(ps->area);
+	if (ps->area)
+		vfree(ps->area);
 	ps->area = NULL;
-	vfree(ps->zero_area);
+
+	if (ps->zero_area)
+		vfree(ps->zero_area);
 	ps->zero_area = NULL;
 }
 
@@ -189,9 +191,9 @@ static void do_metadata(struct work_struct *work)
 static int chunk_io(struct pstore *ps, chunk_t chunk, int rw, int metadata)
 {
 	struct dm_io_region where = {
-		.bdev = ps->snap->cow->bdev,
-		.sector = ps->snap->chunk_size * chunk,
-		.count = ps->snap->chunk_size,
+		.bdev = ps->store->cow->bdev,
+		.sector = ps->store->chunk_size * chunk,
+		.count = ps->store->chunk_size,
 	};
 	struct dm_io_request io_req = {
 		.bi_rw = rw,
@@ -247,15 +249,15 @@ static int area_io(struct pstore *ps, int rw)
 
 static void zero_memory_area(struct pstore *ps)
 {
-	memset(ps->area, 0, ps->snap->chunk_size << SECTOR_SHIFT);
+	memset(ps->area, 0, ps->store->chunk_size << SECTOR_SHIFT);
 }
 
 static int zero_disk_area(struct pstore *ps, chunk_t area)
 {
 	struct dm_io_region where = {
-		.bdev = ps->snap->cow->bdev,
-		.sector = ps->snap->chunk_size * area_location(ps, area),
-		.count = ps->snap->chunk_size,
+		.bdev = ps->store->cow->bdev,
+		.sector = ps->store->chunk_size * area_location(ps, area),
+		.count = ps->store->chunk_size,
 	};
 	struct dm_io_request io_req = {
 		.bi_rw = WRITE,
@@ -278,15 +280,15 @@ static int read_header(struct pstore *ps, int *new_snapshot)
 	/*
 	 * Use default chunk size (or hardsect_size, if larger) if none supplied
 	 */
-	if (!ps->snap->chunk_size) {
-		ps->snap->chunk_size = max(DM_CHUNK_SIZE_DEFAULT_SECTORS,
-		    bdev_hardsect_size(ps->snap->cow->bdev) >> 9);
-		ps->snap->chunk_mask = ps->snap->chunk_size - 1;
-		ps->snap->chunk_shift = ffs(ps->snap->chunk_size) - 1;
+	if (!ps->store->chunk_size) {
+		ps->store->chunk_size = max(DM_CHUNK_SIZE_DEFAULT_SECTORS,
+		    bdev_hardsect_size(ps->store->cow->bdev) >> 9);
+		ps->store->chunk_mask = ps->store->chunk_size - 1;
+		ps->store->chunk_shift = ffs(ps->store->chunk_size) - 1;
 		chunk_size_supplied = 0;
 	}
 
-	ps->io_client = dm_io_client_create(sectors_to_pages(ps->snap->
+	ps->io_client = dm_io_client_create(sectors_to_pages(ps->store->
 							     chunk_size));
 	if (IS_ERR(ps->io_client))
 		return PTR_ERR(ps->io_client);
@@ -317,22 +319,22 @@ static int read_header(struct pstore *ps, int *new_snapshot)
 	ps->version = le32_to_cpu(dh->version);
 	chunk_size = le32_to_cpu(dh->chunk_size);
 
-	if (!chunk_size_supplied || ps->snap->chunk_size == chunk_size)
+	if (!chunk_size_supplied || ps->store->chunk_size == chunk_size)
 		return 0;
 
 	DMWARN("chunk size %llu in device metadata overrides "
 	       "table chunk size of %llu.",
 	       (unsigned long long)chunk_size,
-	       (unsigned long long)ps->snap->chunk_size);
+	       (unsigned long long)ps->store->chunk_size);
 
 	/* We had a bogus chunk_size. Fix stuff up. */
 	free_area(ps);
 
-	ps->snap->chunk_size = chunk_size;
-	ps->snap->chunk_mask = chunk_size - 1;
-	ps->snap->chunk_shift = ffs(chunk_size) - 1;
+	ps->store->chunk_size = chunk_size;
+	ps->store->chunk_mask = chunk_size - 1;
+	ps->store->chunk_shift = ffs(chunk_size) - 1;
 
-	r = dm_io_client_resize(sectors_to_pages(ps->snap->chunk_size),
+	r = dm_io_client_resize(sectors_to_pages(ps->store->chunk_size),
 				ps->io_client);
 	if (r)
 		return r;
@@ -349,13 +351,13 @@ static int write_header(struct pstore *ps)
 {
 	struct disk_header *dh;
 
-	memset(ps->area, 0, ps->snap->chunk_size << SECTOR_SHIFT);
+	memset(ps->area, 0, ps->store->chunk_size << SECTOR_SHIFT);
 
 	dh = (struct disk_header *) ps->area;
 	dh->magic = cpu_to_le32(SNAP_MAGIC);
 	dh->valid = cpu_to_le32(ps->valid);
 	dh->version = cpu_to_le32(ps->version);
-	dh->chunk_size = cpu_to_le32(ps->snap->chunk_size);
+	dh->chunk_size = cpu_to_le32(ps->store->chunk_size);
 
 	return chunk_io(ps, 0, WRITE, 1);
 }
@@ -474,18 +476,25 @@ static struct pstore *get_info(struct dm_exception_store *store)
 static void persistent_fraction_full(struct dm_exception_store *store,
 				     sector_t *numerator, sector_t *denominator)
 {
-	*numerator = get_info(store)->next_free * store->snap->chunk_size;
-	*denominator = get_dev_size(store->snap->cow->bdev);
+	*numerator = get_info(store)->next_free * store->chunk_size;
+	*denominator = get_dev_size(store->cow->bdev);
 }
 
-static void persistent_destroy(struct dm_exception_store *store)
+static void persistent_dtr(struct dm_exception_store *store)
 {
 	struct pstore *ps = get_info(store);
 
 	destroy_workqueue(ps->metadata_wq);
-	dm_io_client_destroy(ps->io_client);
-	vfree(ps->callbacks);
+
+	/* Created in read_header */
+	if (ps->io_client)
+		dm_io_client_destroy(ps->io_client);
 	free_area(ps);
+
+	/* Allocated in persistent_read_metadata */
+	if (ps->callbacks)
+		vfree(ps->callbacks);
+
 	kfree(ps);
 }
 
@@ -507,7 +516,7 @@ static int persistent_read_metadata(struct dm_exception_store *store,
 	/*
 	 * Now we know correct chunk_size, complete the initialisation.
 	 */
-	ps->exceptions_per_area = (ps->snap->chunk_size << SECTOR_SHIFT) /
+	ps->exceptions_per_area = (ps->store->chunk_size << SECTOR_SHIFT) /
 				  sizeof(struct disk_exception);
 	ps->callbacks = dm_vcalloc(ps->exceptions_per_area,
 			sizeof(*ps->callbacks));
@@ -564,10 +573,10 @@ static int persistent_prepare_exception(struct dm_exception_store *store,
 	struct pstore *ps = get_info(store);
 	uint32_t stride;
 	chunk_t next_free;
-	sector_t size = get_dev_size(store->snap->cow->bdev);
+	sector_t size = get_dev_size(store->cow->bdev);
 
 	/* Is there enough room ? */
-	if (size < ((ps->next_free + 1) * store->snap->chunk_size))
+	if (size < ((ps->next_free + 1) * store->chunk_size))
 		return -ENOSPC;
 
 	e->new_chunk = ps->next_free;
@@ -656,16 +665,17 @@ static void persistent_drop_snapshot(struct dm_exception_store *store)
 		DMWARN("write header failed");
 }
 
-int dm_create_persistent(struct dm_exception_store *store)
+static int persistent_ctr(struct dm_exception_store *store,
+			  unsigned argc, char **argv)
 {
 	struct pstore *ps;
 
 	/* allocate the pstore */
-	ps = kmalloc(sizeof(*ps), GFP_KERNEL);
+	ps = kzalloc(sizeof(*ps), GFP_KERNEL);
 	if (!ps)
 		return -ENOMEM;
 
-	ps->snap = store->snap;
+	ps->store = store;
 	ps->valid = 1;
 	ps->version = SNAPSHOT_DISK_VERSION;
 	ps->area = NULL;
@@ -683,22 +693,77 @@ int dm_create_persistent(struct dm_exception_store *store)
 		return -ENOMEM;
 	}
 
-	store->destroy = persistent_destroy;
-	store->read_metadata = persistent_read_metadata;
-	store->prepare_exception = persistent_prepare_exception;
-	store->commit_exception = persistent_commit_exception;
-	store->drop_snapshot = persistent_drop_snapshot;
-	store->fraction_full = persistent_fraction_full;
 	store->context = ps;
 
 	return 0;
 }
 
+static unsigned persistent_status(struct dm_exception_store *store,
+				  status_type_t status, char *result,
+				  unsigned maxlen)
+{
+	unsigned sz = 0;
+
+	switch (status) {
+	case STATUSTYPE_INFO:
+		break;
+	case STATUSTYPE_TABLE:
+		DMEMIT(" %s P %llu", store->cow->name,
+		       (unsigned long long)store->chunk_size);
+	}
+
+	return sz;
+}
+
+static struct dm_exception_store_type _persistent_type = {
+	.name = "persistent",
+	.module = THIS_MODULE,
+	.ctr = persistent_ctr,
+	.dtr = persistent_dtr,
+	.read_metadata = persistent_read_metadata,
+	.prepare_exception = persistent_prepare_exception,
+	.commit_exception = persistent_commit_exception,
+	.drop_snapshot = persistent_drop_snapshot,
+	.fraction_full = persistent_fraction_full,
+	.status = persistent_status,
+};
+
+static struct dm_exception_store_type _persistent_compat_type = {
+	.name = "P",
+	.module = THIS_MODULE,
+	.ctr = persistent_ctr,
+	.dtr = persistent_dtr,
+	.read_metadata = persistent_read_metadata,
+	.prepare_exception = persistent_prepare_exception,
+	.commit_exception = persistent_commit_exception,
+	.drop_snapshot = persistent_drop_snapshot,
+	.fraction_full = persistent_fraction_full,
+	.status = persistent_status,
+};
+
 int dm_persistent_snapshot_init(void)
 {
-	return 0;
+	int r;
+
+	r = dm_exception_store_type_register(&_persistent_type);
+	if (r) {
+		DMERR("Unable to register persistent exception store type");
+		return r;
+	}
+
+	r = dm_exception_store_type_register(&_persistent_compat_type);
+	if (r) {
+		DMERR("Unable to register old-style persistent exception "
+		      "store type");
+		dm_exception_store_type_unregister(&_persistent_type);
+		return r;
+	}
+
+	return r;
 }
 
 void dm_persistent_snapshot_exit(void)
 {
+	dm_exception_store_type_unregister(&_persistent_type);
+	dm_exception_store_type_unregister(&_persistent_compat_type);
 }
diff --git a/drivers/md/dm-snap-transient.c b/drivers/md/dm-snap-transient.c
index 7f6e2e6dcb0d..cde5aa558e6d 100644
--- a/drivers/md/dm-snap-transient.c
+++ b/drivers/md/dm-snap-transient.c
@@ -6,7 +6,6 @@
  */
 
 #include "dm-exception-store.h"
-#include "dm-snap.h"
 
 #include <linux/mm.h>
 #include <linux/pagemap.h>
@@ -23,7 +22,7 @@ struct transient_c {
 	sector_t next_free;
 };
 
-static void transient_destroy(struct dm_exception_store *store)
+static void transient_dtr(struct dm_exception_store *store)
 {
 	kfree(store->context);
 }
@@ -39,14 +38,14 @@ static int transient_read_metadata(struct dm_exception_store *store,
 static int transient_prepare_exception(struct dm_exception_store *store,
 				       struct dm_snap_exception *e)
 {
-	struct transient_c *tc = (struct transient_c *) store->context;
-	sector_t size = get_dev_size(store->snap->cow->bdev);
+	struct transient_c *tc = store->context;
+	sector_t size = get_dev_size(store->cow->bdev);
 
-	if (size < (tc->next_free + store->snap->chunk_size))
+	if (size < (tc->next_free + store->chunk_size))
 		return -1;
 
-	e->new_chunk = sector_to_chunk(store->snap, tc->next_free);
-	tc->next_free += store->snap->chunk_size;
+	e->new_chunk = sector_to_chunk(store, tc->next_free);
+	tc->next_free += store->chunk_size;
 
 	return 0;
 }
@@ -64,20 +63,14 @@ static void transient_fraction_full(struct dm_exception_store *store,
 				    sector_t *numerator, sector_t *denominator)
 {
 	*numerator = ((struct transient_c *) store->context)->next_free;
-	*denominator = get_dev_size(store->snap->cow->bdev);
+	*denominator = get_dev_size(store->cow->bdev);
 }
 
-int dm_create_transient(struct dm_exception_store *store)
+static int transient_ctr(struct dm_exception_store *store,
+			 unsigned argc, char **argv)
 {
 	struct transient_c *tc;
 
-	store->destroy = transient_destroy;
-	store->read_metadata = transient_read_metadata;
-	store->prepare_exception = transient_prepare_exception;
-	store->commit_exception = transient_commit_exception;
-	store->drop_snapshot = NULL;
-	store->fraction_full = transient_fraction_full;
-
 	tc = kmalloc(sizeof(struct transient_c), GFP_KERNEL);
 	if (!tc)
 		return -ENOMEM;
@@ -88,11 +81,70 @@ int dm_create_transient(struct dm_exception_store *store)
 	return 0;
 }
 
+static unsigned transient_status(struct dm_exception_store *store,
+				 status_type_t status, char *result,
+				 unsigned maxlen)
+{
+	unsigned sz = 0;
+
+	switch (status) {
+	case STATUSTYPE_INFO:
+		break;
+	case STATUSTYPE_TABLE:
+		DMEMIT(" %s N %llu", store->cow->name,
+		       (unsigned long long)store->chunk_size);
+	}
+
+	return sz;
+}
+
+static struct dm_exception_store_type _transient_type = {
+	.name = "transient",
+	.module = THIS_MODULE,
+	.ctr = transient_ctr,
+	.dtr = transient_dtr,
+	.read_metadata = transient_read_metadata,
+	.prepare_exception = transient_prepare_exception,
+	.commit_exception = transient_commit_exception,
+	.fraction_full = transient_fraction_full,
+	.status = transient_status,
+};
+
+static struct dm_exception_store_type _transient_compat_type = {
+	.name = "N",
+	.module = THIS_MODULE,
+	.ctr = transient_ctr,
+	.dtr = transient_dtr,
+	.read_metadata = transient_read_metadata,
+	.prepare_exception = transient_prepare_exception,
+	.commit_exception = transient_commit_exception,
+	.fraction_full = transient_fraction_full,
+	.status = transient_status,
+};
+
 int dm_transient_snapshot_init(void)
 {
-	return 0;
+	int r;
+
+	r = dm_exception_store_type_register(&_transient_type);
+	if (r) {
+		DMWARN("Unable to register transient exception store type");
+		return r;
+	}
+
+	r = dm_exception_store_type_register(&_transient_compat_type);
+	if (r) {
+		DMWARN("Unable to register old-style transient "
+		       "exception store type");
+		dm_exception_store_type_unregister(&_transient_type);
+		return r;
+	}
+
+	return r;
 }
 
 void dm_transient_snapshot_exit(void)
 {
+	dm_exception_store_type_unregister(&_transient_type);
+	dm_exception_store_type_unregister(&_transient_compat_type);
 }
diff --git a/drivers/md/dm-snap.c b/drivers/md/dm-snap.c
index 65ff82ff124e..981a0413068f 100644
--- a/drivers/md/dm-snap.c
+++ b/drivers/md/dm-snap.c
@@ -7,7 +7,6 @@
  */
 
 #include <linux/blkdev.h>
-#include <linux/ctype.h>
 #include <linux/device-mapper.h>
 #include <linux/delay.h>
 #include <linux/fs.h>
@@ -20,9 +19,9 @@
 #include <linux/vmalloc.h>
 #include <linux/log2.h>
 #include <linux/dm-kcopyd.h>
+#include <linux/workqueue.h>
 
 #include "dm-exception-store.h"
-#include "dm-snap.h"
 #include "dm-bio-list.h"
 
 #define DM_MSG_PREFIX "snapshots"
@@ -47,9 +46,76 @@
  */
 #define MIN_IOS 256
 
+#define DM_TRACKED_CHUNK_HASH_SIZE	16
+#define DM_TRACKED_CHUNK_HASH(x)	((unsigned long)(x) & \
+					 (DM_TRACKED_CHUNK_HASH_SIZE - 1))
+
+struct exception_table {
+	uint32_t hash_mask;
+	unsigned hash_shift;
+	struct list_head *table;
+};
+
+struct dm_snapshot {
+	struct rw_semaphore lock;
+
+	struct dm_dev *origin;
+
+	/* List of snapshots per Origin */
+	struct list_head list;
+
+	/* You can't use a snapshot if this is 0 (e.g. if full) */
+	int valid;
+
+	/* Origin writes don't trigger exceptions until this is set */
+	int active;
+
+	mempool_t *pending_pool;
+
+	atomic_t pending_exceptions_count;
+
+	struct exception_table pending;
+	struct exception_table complete;
+
+	/*
+	 * pe_lock protects all pending_exception operations and access
+	 * as well as the snapshot_bios list.
+	 */
+	spinlock_t pe_lock;
+
+	/* The on disk metadata handler */
+	struct dm_exception_store *store;
+
+	struct dm_kcopyd_client *kcopyd_client;
+
+	/* Queue of snapshot writes for ksnapd to flush */
+	struct bio_list queued_bios;
+	struct work_struct queued_bios_work;
+
+	/* Chunks with outstanding reads */
+	mempool_t *tracked_chunk_pool;
+	spinlock_t tracked_chunk_lock;
+	struct hlist_head tracked_chunk_hash[DM_TRACKED_CHUNK_HASH_SIZE];
+};
+
 static struct workqueue_struct *ksnapd;
 static void flush_queued_bios(struct work_struct *work);
 
+static sector_t chunk_to_sector(struct dm_exception_store *store,
+				chunk_t chunk)
+{
+	return chunk << store->chunk_shift;
+}
+
+static int bdev_equal(struct block_device *lhs, struct block_device *rhs)
+{
+	/*
+	 * There is only ever one instance of a particular block
+	 * device so we can compare pointers safely.
+	 */
+	return lhs == rhs;
+}
+
 struct dm_snap_pending_exception {
 	struct dm_snap_exception e;
 
@@ -476,11 +542,11 @@ static int init_hash_tables(struct dm_snapshot *s)
 	 * Calculate based on the size of the original volume or
 	 * the COW volume...
 	 */
-	cow_dev_size = get_dev_size(s->cow->bdev);
+	cow_dev_size = get_dev_size(s->store->cow->bdev);
 	origin_dev_size = get_dev_size(s->origin->bdev);
 	max_buckets = calc_max_buckets();
 
-	hash_size = min(origin_dev_size, cow_dev_size) >> s->chunk_shift;
+	hash_size = min(origin_dev_size, cow_dev_size) >> s->store->chunk_shift;
 	hash_size = min(hash_size, max_buckets);
 
 	hash_size = rounddown_pow_of_two(hash_size);
@@ -505,58 +571,6 @@ static int init_hash_tables(struct dm_snapshot *s)
 }
 
 /*
- * Round a number up to the nearest 'size' boundary.  size must
- * be a power of 2.
- */
-static ulong round_up(ulong n, ulong size)
-{
-	size--;
-	return (n + size) & ~size;
-}
-
-static int set_chunk_size(struct dm_snapshot *s, const char *chunk_size_arg,
-			  char **error)
-{
-	unsigned long chunk_size;
-	char *value;
-
-	chunk_size = simple_strtoul(chunk_size_arg, &value, 10);
-	if (*chunk_size_arg == '\0' || *value != '\0') {
-		*error = "Invalid chunk size";
-		return -EINVAL;
-	}
-
-	if (!chunk_size) {
-		s->chunk_size = s->chunk_mask = s->chunk_shift = 0;
-		return 0;
-	}
-
-	/*
-	 * Chunk size must be multiple of page size.  Silently
-	 * round up if it's not.
-	 */
-	chunk_size = round_up(chunk_size, PAGE_SIZE >> 9);
-
-	/* Check chunk_size is a power of 2 */
-	if (!is_power_of_2(chunk_size)) {
-		*error = "Chunk size is not a power of 2";
-		return -EINVAL;
-	}
-
-	/* Validate the chunk size against the device block size */
-	if (chunk_size % (bdev_hardsect_size(s->cow->bdev) >> 9)) {
-		*error = "Chunk size is not a multiple of device blocksize";
-		return -EINVAL;
-	}
-
-	s->chunk_size = chunk_size;
-	s->chunk_mask = chunk_size - 1;
-	s->chunk_shift = ffs(chunk_size) - 1;
-
-	return 0;
-}
-
-/*
  * Construct a snapshot mapping: <origin_dev> <COW-dev> <p/n> <chunk-size>
  */
 static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
@@ -564,91 +578,68 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	struct dm_snapshot *s;
 	int i;
 	int r = -EINVAL;
-	char persistent;
 	char *origin_path;
-	char *cow_path;
+	struct dm_exception_store *store;
+	unsigned args_used;
 
 	if (argc != 4) {
 		ti->error = "requires exactly 4 arguments";
 		r = -EINVAL;
-		goto bad1;
+		goto bad_args;
 	}
 
 	origin_path = argv[0];
-	cow_path = argv[1];
-	persistent = toupper(*argv[2]);
+	argv++;
+	argc--;
 
-	if (persistent != 'P' && persistent != 'N') {
-		ti->error = "Persistent flag is not P or N";
+	r = dm_exception_store_create(ti, argc, argv, &args_used, &store);
+	if (r) {
+		ti->error = "Couldn't create exception store";
 		r = -EINVAL;
-		goto bad1;
+		goto bad_args;
 	}
 
+	argv += args_used;
+	argc -= args_used;
+
 	s = kmalloc(sizeof(*s), GFP_KERNEL);
-	if (s == NULL) {
+	if (!s) {
 		ti->error = "Cannot allocate snapshot context private "
 		    "structure";
 		r = -ENOMEM;
-		goto bad1;
+		goto bad_snap;
 	}
 
 	r = dm_get_device(ti, origin_path, 0, ti->len, FMODE_READ, &s->origin);
 	if (r) {
 		ti->error = "Cannot get origin device";
-		goto bad2;
-	}
-
-	r = dm_get_device(ti, cow_path, 0, 0,
-			  FMODE_READ | FMODE_WRITE, &s->cow);
-	if (r) {
-		dm_put_device(ti, s->origin);
-		ti->error = "Cannot get COW device";
-		goto bad2;
+		goto bad_origin;
 	}
 
-	r = set_chunk_size(s, argv[3], &ti->error);
-	if (r)
-		goto bad3;
-
-	s->type = persistent;
-
+	s->store = store;
 	s->valid = 1;
 	s->active = 0;
 	atomic_set(&s->pending_exceptions_count, 0);
 	init_rwsem(&s->lock);
 	spin_lock_init(&s->pe_lock);
-	s->ti = ti;
 
 	/* Allocate hash table for COW data */
 	if (init_hash_tables(s)) {
 		ti->error = "Unable to allocate hash table space";
 		r = -ENOMEM;
-		goto bad3;
-	}
-
-	s->store.snap = s;
-
-	if (persistent == 'P')
-		r = dm_create_persistent(&s->store);
-	else
-		r = dm_create_transient(&s->store);
-
-	if (r) {
-		ti->error = "Couldn't create exception store";
-		r = -EINVAL;
-		goto bad4;
+		goto bad_hash_tables;
 	}
 
 	r = dm_kcopyd_client_create(SNAPSHOT_PAGES, &s->kcopyd_client);
 	if (r) {
 		ti->error = "Could not create kcopyd client";
-		goto bad5;
+		goto bad_kcopyd;
 	}
 
 	s->pending_pool = mempool_create_slab_pool(MIN_IOS, pending_cache);
 	if (!s->pending_pool) {
 		ti->error = "Could not allocate mempool for pending exceptions";
-		goto bad6;
+		goto bad_pending_pool;
 	}
 
 	s->tracked_chunk_pool = mempool_create_slab_pool(MIN_IOS,
@@ -665,7 +656,8 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	spin_lock_init(&s->tracked_chunk_lock);
 
 	/* Metadata must only be loaded into one table at once */
-	r = s->store.read_metadata(&s->store, dm_add_exception, (void *)s);
+	r = s->store->type->read_metadata(s->store, dm_add_exception,
+					  (void *)s);
 	if (r < 0) {
 		ti->error = "Failed to read snapshot metadata";
 		goto bad_load_and_register;
@@ -686,34 +678,33 @@ static int snapshot_ctr(struct dm_target *ti, unsigned int argc, char **argv)
 	}
 
 	ti->private = s;
-	ti->split_io = s->chunk_size;
+	ti->split_io = s->store->chunk_size;
 
 	return 0;
 
- bad_load_and_register:
+bad_load_and_register:
 	mempool_destroy(s->tracked_chunk_pool);
 
- bad_tracked_chunk_pool:
+bad_tracked_chunk_pool:
 	mempool_destroy(s->pending_pool);
 
- bad6:
+bad_pending_pool:
 	dm_kcopyd_client_destroy(s->kcopyd_client);
 
- bad5:
-	s->store.destroy(&s->store);
-
- bad4:
+bad_kcopyd:
 	exit_exception_table(&s->pending, pending_cache);
 	exit_exception_table(&s->complete, exception_cache);
 
- bad3:
-	dm_put_device(ti, s->cow);
+bad_hash_tables:
 	dm_put_device(ti, s->origin);
 
- bad2:
+bad_origin:
 	kfree(s);
 
- bad1:
+bad_snap:
+	dm_exception_store_destroy(store);
+
+bad_args:
 	return r;
 }
 
@@ -724,8 +715,6 @@ static void __free_exceptions(struct dm_snapshot *s)
 
 	exit_exception_table(&s->pending, pending_cache);
 	exit_exception_table(&s->complete, exception_cache);
-
-	s->store.destroy(&s->store);
 }
 
 static void snapshot_dtr(struct dm_target *ti)
@@ -761,7 +750,8 @@ static void snapshot_dtr(struct dm_target *ti)
 	mempool_destroy(s->pending_pool);
 
 	dm_put_device(ti, s->origin);
-	dm_put_device(ti, s->cow);
+
+	dm_exception_store_destroy(s->store);
 
 	kfree(s);
 }
@@ -820,12 +810,12 @@ static void __invalidate_snapshot(struct dm_snapshot *s, int err)
 	else if (err == -ENOMEM)
 		DMERR("Invalidating snapshot: Unable to allocate exception.");
 
-	if (s->store.drop_snapshot)
-		s->store.drop_snapshot(&s->store);
+	if (s->store->type->drop_snapshot)
+		s->store->type->drop_snapshot(s->store);
 
 	s->valid = 0;
 
-	dm_table_event(s->ti->table);
+	dm_table_event(s->store->ti->table);
 }
 
 static void get_pending_exception(struct dm_snap_pending_exception *pe)
@@ -943,8 +933,8 @@ static void copy_callback(int read_err, unsigned long write_err, void *context)
 
 	else
 		/* Update the metadata if we are persistent */
-		s->store.commit_exception(&s->store, &pe->e, commit_callback,
-					  pe);
+		s->store->type->commit_exception(s->store, &pe->e,
+						 commit_callback, pe);
 }
 
 /*
@@ -960,11 +950,11 @@ static void start_copy(struct dm_snap_pending_exception *pe)
 	dev_size = get_dev_size(bdev);
 
 	src.bdev = bdev;
-	src.sector = chunk_to_sector(s, pe->e.old_chunk);
-	src.count = min(s->chunk_size, dev_size - src.sector);
+	src.sector = chunk_to_sector(s->store, pe->e.old_chunk);
+	src.count = min(s->store->chunk_size, dev_size - src.sector);
 
-	dest.bdev = s->cow->bdev;
-	dest.sector = chunk_to_sector(s, pe->e.new_chunk);
+	dest.bdev = s->store->cow->bdev;
+	dest.sector = chunk_to_sector(s->store, pe->e.new_chunk);
 	dest.count = src.count;
 
 	/* Hand over to kcopyd */
@@ -972,6 +962,17 @@ static void start_copy(struct dm_snap_pending_exception *pe)
 		    &src, 1, &dest, 0, copy_callback, pe);
 }
 
+static struct dm_snap_pending_exception *
+__lookup_pending_exception(struct dm_snapshot *s, chunk_t chunk)
+{
+	struct dm_snap_exception *e = lookup_exception(&s->pending, chunk);
+
+	if (!e)
+		return NULL;
+
+	return container_of(e, struct dm_snap_pending_exception, e);
+}
+
 /*
  * Looks to see if this snapshot already has a pending exception
  * for this chunk, otherwise it allocates a new one and inserts
@@ -981,40 +982,15 @@ static void start_copy(struct dm_snap_pending_exception *pe)
  * this.
  */
 static struct dm_snap_pending_exception *
-__find_pending_exception(struct dm_snapshot *s, struct bio *bio)
+__find_pending_exception(struct dm_snapshot *s,
+			 struct dm_snap_pending_exception *pe, chunk_t chunk)
 {
-	struct dm_snap_exception *e;
-	struct dm_snap_pending_exception *pe;
-	chunk_t chunk = sector_to_chunk(s, bio->bi_sector);
+	struct dm_snap_pending_exception *pe2;
 
-	/*
-	 * Is there a pending exception for this already ?
-	 */
-	e = lookup_exception(&s->pending, chunk);
-	if (e) {
-		/* cast the exception to a pending exception */
-		pe = container_of(e, struct dm_snap_pending_exception, e);
-		goto out;
-	}
-
-	/*
-	 * Create a new pending exception, we don't want
-	 * to hold the lock while we do this.
-	 */
-	up_write(&s->lock);
-	pe = alloc_pending_exception(s);
-	down_write(&s->lock);
-
-	if (!s->valid) {
-		free_pending_exception(pe);
-		return NULL;
-	}
-
-	e = lookup_exception(&s->pending, chunk);
-	if (e) {
+	pe2 = __lookup_pending_exception(s, chunk);
+	if (pe2) {
 		free_pending_exception(pe);
-		pe = container_of(e, struct dm_snap_pending_exception, e);
-		goto out;
+		return pe2;
 	}
 
 	pe->e.old_chunk = chunk;
@@ -1024,7 +1000,7 @@ __find_pending_exception(struct dm_snapshot *s, struct bio *bio)
 	atomic_set(&pe->ref_count, 0);
 	pe->started = 0;
 
-	if (s->store.prepare_exception(&s->store, &pe->e)) {
+	if (s->store->type->prepare_exception(s->store, &pe->e)) {
 		free_pending_exception(pe);
 		return NULL;
 	}
@@ -1032,17 +1008,18 @@ __find_pending_exception(struct dm_snapshot *s, struct bio *bio)
 	get_pending_exception(pe);
 	insert_exception(&s->pending, &pe->e);
 
- out:
 	return pe;
 }
 
 static void remap_exception(struct dm_snapshot *s, struct dm_snap_exception *e,
 			    struct bio *bio, chunk_t chunk)
 {
-	bio->bi_bdev = s->cow->bdev;
-	bio->bi_sector = chunk_to_sector(s, dm_chunk_number(e->new_chunk) +
-			 (chunk - e->old_chunk)) +
-			 (bio->bi_sector & s->chunk_mask);
+	bio->bi_bdev = s->store->cow->bdev;
+	bio->bi_sector = chunk_to_sector(s->store,
+					 dm_chunk_number(e->new_chunk) +
+					 (chunk - e->old_chunk)) +
+					 (bio->bi_sector &
+					  s->store->chunk_mask);
 }
 
 static int snapshot_map(struct dm_target *ti, struct bio *bio,
@@ -1054,7 +1031,7 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio,
 	chunk_t chunk;
 	struct dm_snap_pending_exception *pe = NULL;
 
-	chunk = sector_to_chunk(s, bio->bi_sector);
+	chunk = sector_to_chunk(s->store, bio->bi_sector);
 
 	/* Full snapshots are not usable */
 	/* To get here the table must be live so s->active is always set. */
@@ -1083,11 +1060,31 @@ static int snapshot_map(struct dm_target *ti, struct bio *bio,
 	 * writeable.
 	 */
 	if (bio_rw(bio) == WRITE) {
-		pe = __find_pending_exception(s, bio);
+		pe = __lookup_pending_exception(s, chunk);
 		if (!pe) {
-			__invalidate_snapshot(s, -ENOMEM);
-			r = -EIO;
-			goto out_unlock;
+			up_write(&s->lock);
+			pe = alloc_pending_exception(s);
+			down_write(&s->lock);
+
+			if (!s->valid) {
+				free_pending_exception(pe);
+				r = -EIO;
+				goto out_unlock;
+			}
+
+			e = lookup_exception(&s->complete, chunk);
+			if (e) {
+				free_pending_exception(pe);
+				remap_exception(s, e, bio, chunk);
+				goto out_unlock;
+			}
+
+			pe = __find_pending_exception(s, pe, chunk);
+			if (!pe) {
+				__invalidate_snapshot(s, -ENOMEM);
+				r = -EIO;
+				goto out_unlock;
+			}
 		}
 
 		remap_exception(s, &pe->e, bio, chunk);
@@ -1137,24 +1134,25 @@ static void snapshot_resume(struct dm_target *ti)
 static int snapshot_status(struct dm_target *ti, status_type_t type,
 			   char *result, unsigned int maxlen)
 {
+	unsigned sz = 0;
 	struct dm_snapshot *snap = ti->private;
 
 	switch (type) {
 	case STATUSTYPE_INFO:
 		if (!snap->valid)
-			snprintf(result, maxlen, "Invalid");
+			DMEMIT("Invalid");
 		else {
-			if (snap->store.fraction_full) {
+			if (snap->store->type->fraction_full) {
 				sector_t numerator, denominator;
-				snap->store.fraction_full(&snap->store,
-							  &numerator,
-							  &denominator);
-				snprintf(result, maxlen, "%llu/%llu",
-					(unsigned long long)numerator,
-					(unsigned long long)denominator);
+				snap->store->type->fraction_full(snap->store,
+								 &numerator,
+								 &denominator);
+				DMEMIT("%llu/%llu",
+				       (unsigned long long)numerator,
+				       (unsigned long long)denominator);
 			}
 			else
-				snprintf(result, maxlen, "Unknown");
+				DMEMIT("Unknown");
 		}
 		break;
 
@@ -1164,10 +1162,9 @@ static int snapshot_status(struct dm_target *ti, status_type_t type,
 		 * to make private copies if the output is to
 		 * make sense.
 		 */
-		snprintf(result, maxlen, "%s %s %c %llu",
-			 snap->origin->name, snap->cow->name,
-			 snap->type,
-			 (unsigned long long)snap->chunk_size);
+		DMEMIT("%s", snap->origin->name);
+		snap->store->type->status(snap->store, type, result + sz,
+					  maxlen - sz);
 		break;
 	}
 
@@ -1196,14 +1193,14 @@ static int __origin_write(struct list_head *snapshots, struct bio *bio)
 			goto next_snapshot;
 
 		/* Nothing to do if writing beyond end of snapshot */
-		if (bio->bi_sector >= dm_table_get_size(snap->ti->table))
+		if (bio->bi_sector >= dm_table_get_size(snap->store->ti->table))
 			goto next_snapshot;
 
 		/*
 		 * Remember, different snapshots can have
 		 * different chunk sizes.
 		 */
-		chunk = sector_to_chunk(snap, bio->bi_sector);
+		chunk = sector_to_chunk(snap->store, bio->bi_sector);
 
 		/*
 		 * Check exception table to see if block
@@ -1217,10 +1214,28 @@ static int __origin_write(struct list_head *snapshots, struct bio *bio)
 		if (e)
 			goto next_snapshot;
 
-		pe = __find_pending_exception(snap, bio);
+		pe = __lookup_pending_exception(snap, chunk);
 		if (!pe) {
-			__invalidate_snapshot(snap, -ENOMEM);
-			goto next_snapshot;
+			up_write(&snap->lock);
+			pe = alloc_pending_exception(snap);
+			down_write(&snap->lock);
+
+			if (!snap->valid) {
+				free_pending_exception(pe);
+				goto next_snapshot;
+			}
+
+			e = lookup_exception(&snap->complete, chunk);
+			if (e) {
+				free_pending_exception(pe);
+				goto next_snapshot;
+			}
+
+			pe = __find_pending_exception(snap, pe, chunk);
+			if (!pe) {
+				__invalidate_snapshot(snap, -ENOMEM);
+				goto next_snapshot;
+			}
 		}
 
 		if (!primary_pe) {
@@ -1360,7 +1375,8 @@ static void origin_resume(struct dm_target *ti)
 	o = __lookup_origin(dev->bdev);
 	if (o)
 		list_for_each_entry (snap, &o->snapshots, list)
-			chunk_size = min_not_zero(chunk_size, snap->chunk_size);
+			chunk_size = min_not_zero(chunk_size,
+						  snap->store->chunk_size);
 	up_read(&_origins_lock);
 
 	ti->split_io = chunk_size;
diff --git a/drivers/md/dm-snap.h b/drivers/md/dm-snap.h
deleted file mode 100644
index d9e62b43cf85..000000000000
--- a/drivers/md/dm-snap.h
+++ /dev/null
@@ -1,105 +0,0 @@
-/*
- * Copyright (C) 2001-2002 Sistina Software (UK) Limited.
- *
- * This file is released under the GPL.
- */
-
-#ifndef DM_SNAPSHOT_H
-#define DM_SNAPSHOT_H
-
-#include <linux/device-mapper.h>
-#include "dm-exception-store.h"
-#include "dm-bio-list.h"
-#include <linux/blkdev.h>
-#include <linux/workqueue.h>
-
-struct exception_table {
-	uint32_t hash_mask;
-	unsigned hash_shift;
-	struct list_head *table;
-};
-
-#define DM_TRACKED_CHUNK_HASH_SIZE	16
-#define DM_TRACKED_CHUNK_HASH(x)	((unsigned long)(x) & \
-					 (DM_TRACKED_CHUNK_HASH_SIZE - 1))
-
-struct dm_snapshot {
-	struct rw_semaphore lock;
-	struct dm_target *ti;
-
-	struct dm_dev *origin;
-	struct dm_dev *cow;
-
-	/* List of snapshots per Origin */
-	struct list_head list;
-
-	/* Size of data blocks saved - must be a power of 2 */
-	chunk_t chunk_size;
-	chunk_t chunk_mask;
-	chunk_t chunk_shift;
-
-	/* You can't use a snapshot if this is 0 (e.g. if full) */
-	int valid;
-
-	/* Origin writes don't trigger exceptions until this is set */
-	int active;
-
-	/* Used for display of table */
-	char type;
-
-	mempool_t *pending_pool;
-
-	atomic_t pending_exceptions_count;
-
-	struct exception_table pending;
-	struct exception_table complete;
-
-	/*
-	 * pe_lock protects all pending_exception operations and access
-	 * as well as the snapshot_bios list.
-	 */
-	spinlock_t pe_lock;
-
-	/* The on disk metadata handler */
-	struct dm_exception_store store;
-
-	struct dm_kcopyd_client *kcopyd_client;
-
-	/* Queue of snapshot writes for ksnapd to flush */
-	struct bio_list queued_bios;
-	struct work_struct queued_bios_work;
-
-	/* Chunks with outstanding reads */
-	mempool_t *tracked_chunk_pool;
-	spinlock_t tracked_chunk_lock;
-	struct hlist_head tracked_chunk_hash[DM_TRACKED_CHUNK_HASH_SIZE];
-};
-
-/*
- * Return the number of sectors in the device.
- */
-static inline sector_t get_dev_size(struct block_device *bdev)
-{
-	return bdev->bd_inode->i_size >> SECTOR_SHIFT;
-}
-
-static inline chunk_t sector_to_chunk(struct dm_snapshot *s, sector_t sector)
-{
-	return (sector & ~s->chunk_mask) >> s->chunk_shift;
-}
-
-static inline sector_t chunk_to_sector(struct dm_snapshot *s, chunk_t chunk)
-{
-	return chunk << s->chunk_shift;
-}
-
-static inline int bdev_equal(struct block_device *lhs, struct block_device *rhs)
-{
-	/*
-	 * There is only ever one instance of a particular block
-	 * device so we can compare pointers safely.
-	 */
-	return lhs == rhs;
-}
-
-#endif
diff --git a/drivers/md/dm-table.c b/drivers/md/dm-table.c
index 2fd66c30f7f8..e8361b191b9b 100644
--- a/drivers/md/dm-table.c
+++ b/drivers/md/dm-table.c
@@ -399,28 +399,30 @@ static int check_device_area(struct dm_dev_internal *dd, sector_t start,
 }
 
 /*
- * This upgrades the mode on an already open dm_dev.  Being
+ * This upgrades the mode on an already open dm_dev, being
  * careful to leave things as they were if we fail to reopen the
- * device.
+ * device and not to touch the existing bdev field in case
+ * it is accessed concurrently inside dm_table_any_congested().
  */
 static int upgrade_mode(struct dm_dev_internal *dd, fmode_t new_mode,
 			struct mapped_device *md)
 {
 	int r;
-	struct dm_dev_internal dd_copy;
-	dev_t dev = dd->dm_dev.bdev->bd_dev;
+	struct dm_dev_internal dd_new, dd_old;
 
-	dd_copy = *dd;
+	dd_new = dd_old = *dd;
+
+	dd_new.dm_dev.mode |= new_mode;
+	dd_new.dm_dev.bdev = NULL;
+
+	r = open_dev(&dd_new, dd->dm_dev.bdev->bd_dev, md);
+	if (r)
+		return r;
 
 	dd->dm_dev.mode |= new_mode;
-	dd->dm_dev.bdev = NULL;
-	r = open_dev(dd, dev, md);
-	if (!r)
-		close_dev(&dd_copy, md);
-	else
-		*dd = dd_copy;
+	close_dev(&dd_old, md);
 
-	return r;
+	return 0;
 }
 
 /*
diff --git a/drivers/md/dm-target.c b/drivers/md/dm-target.c
index 7decf10006e4..04feccf2a997 100644
--- a/drivers/md/dm-target.c
+++ b/drivers/md/dm-target.c
@@ -14,45 +14,34 @@
 
 #define DM_MSG_PREFIX "target"
 
-struct tt_internal {
-	struct target_type tt;
-
-	struct list_head list;
-	long use;
-};
-
 static LIST_HEAD(_targets);
 static DECLARE_RWSEM(_lock);
 
 #define DM_MOD_NAME_SIZE 32
 
-static inline struct tt_internal *__find_target_type(const char *name)
+static inline struct target_type *__find_target_type(const char *name)
 {
-	struct tt_internal *ti;
+	struct target_type *tt;
 
-	list_for_each_entry (ti, &_targets, list)
-		if (!strcmp(name, ti->tt.name))
-			return ti;
+	list_for_each_entry(tt, &_targets, list)
+		if (!strcmp(name, tt->name))
+			return tt;
 
 	return NULL;
 }
 
-static struct tt_internal *get_target_type(const char *name)
+static struct target_type *get_target_type(const char *name)
 {
-	struct tt_internal *ti;
+	struct target_type *tt;
 
 	down_read(&_lock);
 
-	ti = __find_target_type(name);
-	if (ti) {
-		if ((ti->use == 0) && !try_module_get(ti->tt.module))
-			ti = NULL;
-		else
-			ti->use++;
-	}
+	tt = __find_target_type(name);
+	if (tt && !try_module_get(tt->module))
+		tt = NULL;
 
 	up_read(&_lock);
-	return ti;
+	return tt;
 }
 
 static void load_module(const char *name)
@@ -62,92 +51,59 @@ static void load_module(const char *name)
 
 struct target_type *dm_get_target_type(const char *name)
 {
-	struct tt_internal *ti = get_target_type(name);
+	struct target_type *tt = get_target_type(name);
 
-	if (!ti) {
+	if (!tt) {
 		load_module(name);
-		ti = get_target_type(name);
+		tt = get_target_type(name);
 	}
 
-	return ti ? &ti->tt : NULL;
+	return tt;
 }
 
-void dm_put_target_type(struct target_type *t)
+void dm_put_target_type(struct target_type *tt)
 {
-	struct tt_internal *ti = (struct tt_internal *) t;
-
 	down_read(&_lock);
-	if (--ti->use == 0)
-		module_put(ti->tt.module);
-
-	BUG_ON(ti->use < 0);
+	module_put(tt->module);
 	up_read(&_lock);
-
-	return;
-}
-
-static struct tt_internal *alloc_target(struct target_type *t)
-{
-	struct tt_internal *ti = kzalloc(sizeof(*ti), GFP_KERNEL);
-
-	if (ti)
-		ti->tt = *t;
-
-	return ti;
 }
 
-
 int dm_target_iterate(void (*iter_func)(struct target_type *tt,
 					void *param), void *param)
 {
-	struct tt_internal *ti;
+	struct target_type *tt;
 
 	down_read(&_lock);
-	list_for_each_entry (ti, &_targets, list)
-		iter_func(&ti->tt, param);
+	list_for_each_entry(tt, &_targets, list)
+		iter_func(tt, param);
 	up_read(&_lock);
 
 	return 0;
 }
 
-int dm_register_target(struct target_type *t)
+int dm_register_target(struct target_type *tt)
 {
 	int rv = 0;
-	struct tt_internal *ti = alloc_target(t);
-
-	if (!ti)
-		return -ENOMEM;
 
 	down_write(&_lock);
-	if (__find_target_type(t->name))
+	if (__find_target_type(tt->name))
 		rv = -EEXIST;
 	else
-		list_add(&ti->list, &_targets);
+		list_add(&tt->list, &_targets);
 
 	up_write(&_lock);
-	if (rv)
-		kfree(ti);
 	return rv;
 }
 
-void dm_unregister_target(struct target_type *t)
+void dm_unregister_target(struct target_type *tt)
 {
-	struct tt_internal *ti;
-
 	down_write(&_lock);
-	if (!(ti = __find_target_type(t->name))) {
-		DMCRIT("Unregistering unrecognised target: %s", t->name);
-		BUG();
-	}
-
-	if (ti->use) {
-		DMCRIT("Attempt to unregister target still in use: %s",
-		       t->name);
+	if (!__find_target_type(tt->name)) {
+		DMCRIT("Unregistering unrecognised target: %s", tt->name);
 		BUG();
 	}
 
-	list_del(&ti->list);
-	kfree(ti);
+	list_del(&tt->list);
 
 	up_write(&_lock);
 }
@@ -156,17 +112,17 @@ void dm_unregister_target(struct target_type *t)
  * io-err: always fails an io, useful for bringing
  * up LVs that have holes in them.
  */
-static int io_err_ctr(struct dm_target *ti, unsigned int argc, char **args)
+static int io_err_ctr(struct dm_target *tt, unsigned int argc, char **args)
 {
 	return 0;
 }
 
-static void io_err_dtr(struct dm_target *ti)
+static void io_err_dtr(struct dm_target *tt)
 {
 	/* empty */
 }
 
-static int io_err_map(struct dm_target *ti, struct bio *bio,
+static int io_err_map(struct dm_target *tt, struct bio *bio,
 		      union map_info *map_context)
 {
 	return -EIO;
diff --git a/drivers/md/dm.c b/drivers/md/dm.c
index 8d40f27cce89..788ba96a6256 100644
--- a/drivers/md/dm.c
+++ b/drivers/md/dm.c
@@ -99,19 +99,9 @@ union map_info *dm_get_mapinfo(struct bio *bio)
 /*
  * Work processed by per-device workqueue.
  */
-struct dm_wq_req {
-	enum {
-		DM_WQ_FLUSH_DEFERRED,
-	} type;
-	struct work_struct work;
-	struct mapped_device *md;
-	void *context;
-};
-
 struct mapped_device {
 	struct rw_semaphore io_lock;
 	struct mutex suspend_lock;
-	spinlock_t pushback_lock;
 	rwlock_t map_lock;
 	atomic_t holders;
 	atomic_t open_count;
@@ -129,8 +119,9 @@ struct mapped_device {
 	 */
 	atomic_t pending;
 	wait_queue_head_t wait;
+	struct work_struct work;
 	struct bio_list deferred;
-	struct bio_list pushback;
+	spinlock_t deferred_lock;
 
 	/*
 	 * Processing queue (flush/barriers)
@@ -453,7 +444,9 @@ static int queue_io(struct mapped_device *md, struct bio *bio)
 		return 1;
 	}
 
+	spin_lock_irq(&md->deferred_lock);
 	bio_list_add(&md->deferred, bio);
+	spin_unlock_irq(&md->deferred_lock);
 
 	up_write(&md->io_lock);
 	return 0;		/* deferred successfully */
@@ -537,16 +530,14 @@ static void dec_pending(struct dm_io *io, int error)
 		if (io->error == DM_ENDIO_REQUEUE) {
 			/*
 			 * Target requested pushing back the I/O.
-			 * This must be handled before the sleeper on
-			 * suspend queue merges the pushback list.
 			 */
-			spin_lock_irqsave(&md->pushback_lock, flags);
+			spin_lock_irqsave(&md->deferred_lock, flags);
 			if (__noflush_suspending(md))
-				bio_list_add(&md->pushback, io->bio);
+				bio_list_add(&md->deferred, io->bio);
 			else
 				/* noflush suspend was interrupted. */
 				io->error = -EIO;
-			spin_unlock_irqrestore(&md->pushback_lock, flags);
+			spin_unlock_irqrestore(&md->deferred_lock, flags);
 		}
 
 		end_io_acct(io);
@@ -834,20 +825,22 @@ static int __clone_and_map(struct clone_info *ci)
 }
 
 /*
- * Split the bio into several clones.
+ * Split the bio into several clones and submit it to targets.
  */
-static int __split_bio(struct mapped_device *md, struct bio *bio)
+static void __split_and_process_bio(struct mapped_device *md, struct bio *bio)
 {
 	struct clone_info ci;
 	int error = 0;
 
 	ci.map = dm_get_table(md);
-	if (unlikely(!ci.map))
-		return -EIO;
+	if (unlikely(!ci.map)) {
+		bio_io_error(bio);
+		return;
+	}
 	if (unlikely(bio_barrier(bio) && !dm_table_barrier_ok(ci.map))) {
 		dm_table_put(ci.map);
 		bio_endio(bio, -EOPNOTSUPP);
-		return 0;
+		return;
 	}
 	ci.md = md;
 	ci.bio = bio;
@@ -867,8 +860,6 @@ static int __split_bio(struct mapped_device *md, struct bio *bio)
 	/* drop the extra reference count */
 	dec_pending(ci.io, error);
 	dm_table_put(ci.map);
-
-	return 0;
 }
 /*-----------------------------------------------------------------
  * CRUD END
@@ -959,8 +950,9 @@ static int dm_request(struct request_queue *q, struct bio *bio)
 		down_read(&md->io_lock);
 	}
 
-	r = __split_bio(md, bio);
+	__split_and_process_bio(md, bio);
 	up_read(&md->io_lock);
+	return 0;
 
 out_req:
 	if (r < 0)
@@ -1074,6 +1066,8 @@ out:
 
 static struct block_device_operations dm_blk_dops;
 
+static void dm_wq_work(struct work_struct *work);
+
 /*
  * Allocate and initialise a blank device with a given minor.
  */
@@ -1101,7 +1095,7 @@ static struct mapped_device *alloc_dev(int minor)
 
 	init_rwsem(&md->io_lock);
 	mutex_init(&md->suspend_lock);
-	spin_lock_init(&md->pushback_lock);
+	spin_lock_init(&md->deferred_lock);
 	rwlock_init(&md->map_lock);
 	atomic_set(&md->holders, 1);
 	atomic_set(&md->open_count, 0);
@@ -1118,6 +1112,7 @@ static struct mapped_device *alloc_dev(int minor)
 	md->queue->backing_dev_info.congested_fn = dm_any_congested;
 	md->queue->backing_dev_info.congested_data = md;
 	blk_queue_make_request(md->queue, dm_request);
+	blk_queue_ordered(md->queue, QUEUE_ORDERED_DRAIN, NULL);
 	blk_queue_bounce_limit(md->queue, BLK_BOUNCE_ANY);
 	md->queue->unplug_fn = dm_unplug_all;
 	blk_queue_merge_bvec(md->queue, dm_merge_bvec);
@@ -1140,6 +1135,7 @@ static struct mapped_device *alloc_dev(int minor)
 
 	atomic_set(&md->pending, 0);
 	init_waitqueue_head(&md->wait);
+	INIT_WORK(&md->work, dm_wq_work);
 	init_waitqueue_head(&md->eventq);
 
 	md->disk->major = _major;
@@ -1379,18 +1375,24 @@ void dm_put(struct mapped_device *md)
 }
 EXPORT_SYMBOL_GPL(dm_put);
 
-static int dm_wait_for_completion(struct mapped_device *md)
+static int dm_wait_for_completion(struct mapped_device *md, int interruptible)
 {
 	int r = 0;
+	DECLARE_WAITQUEUE(wait, current);
+
+	dm_unplug_all(md->queue);
+
+	add_wait_queue(&md->wait, &wait);
 
 	while (1) {
-		set_current_state(TASK_INTERRUPTIBLE);
+		set_current_state(interruptible);
 
 		smp_mb();
 		if (!atomic_read(&md->pending))
 			break;
 
-		if (signal_pending(current)) {
+		if (interruptible == TASK_INTERRUPTIBLE &&
+		    signal_pending(current)) {
 			r = -EINTR;
 			break;
 		}
@@ -1399,67 +1401,40 @@ static int dm_wait_for_completion(struct mapped_device *md)
 	}
 	set_current_state(TASK_RUNNING);
 
+	remove_wait_queue(&md->wait, &wait);
+
 	return r;
 }
 
 /*
  * Process the deferred bios
  */
-static void __flush_deferred_io(struct mapped_device *md)
+static void dm_wq_work(struct work_struct *work)
 {
+	struct mapped_device *md = container_of(work, struct mapped_device,
+						work);
 	struct bio *c;
 
-	while ((c = bio_list_pop(&md->deferred))) {
-		if (__split_bio(md, c))
-			bio_io_error(c);
-	}
-
-	clear_bit(DMF_BLOCK_IO, &md->flags);
-}
+	down_write(&md->io_lock);
 
-static void __merge_pushback_list(struct mapped_device *md)
-{
-	unsigned long flags;
+next_bio:
+	spin_lock_irq(&md->deferred_lock);
+	c = bio_list_pop(&md->deferred);
+	spin_unlock_irq(&md->deferred_lock);
 
-	spin_lock_irqsave(&md->pushback_lock, flags);
-	clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
-	bio_list_merge_head(&md->deferred, &md->pushback);
-	bio_list_init(&md->pushback);
-	spin_unlock_irqrestore(&md->pushback_lock, flags);
-}
+	if (c) {
+		__split_and_process_bio(md, c);
+		goto next_bio;
+	}
 
-static void dm_wq_work(struct work_struct *work)
-{
-	struct dm_wq_req *req = container_of(work, struct dm_wq_req, work);
-	struct mapped_device *md = req->md;
+	clear_bit(DMF_BLOCK_IO, &md->flags);
 
-	down_write(&md->io_lock);
-	switch (req->type) {
-	case DM_WQ_FLUSH_DEFERRED:
-		__flush_deferred_io(md);
-		break;
-	default:
-		DMERR("dm_wq_work: unrecognised work type %d", req->type);
-		BUG();
-	}
 	up_write(&md->io_lock);
 }
 
-static void dm_wq_queue(struct mapped_device *md, int type, void *context,
-			struct dm_wq_req *req)
-{
-	req->type = type;
-	req->md = md;
-	req->context = context;
-	INIT_WORK(&req->work, dm_wq_work);
-	queue_work(md->wq, &req->work);
-}
-
-static void dm_queue_flush(struct mapped_device *md, int type, void *context)
+static void dm_queue_flush(struct mapped_device *md)
 {
-	struct dm_wq_req req;
-
-	dm_wq_queue(md, type, context, &req);
+	queue_work(md->wq, &md->work);
 	flush_workqueue(md->wq);
 }
 
@@ -1534,7 +1509,6 @@ static void unlock_fs(struct mapped_device *md)
 int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 {
 	struct dm_table *map = NULL;
-	DECLARE_WAITQUEUE(wait, current);
 	int r = 0;
 	int do_lockfs = suspend_flags & DM_SUSPEND_LOCKFS_FLAG ? 1 : 0;
 	int noflush = suspend_flags & DM_SUSPEND_NOFLUSH_FLAG ? 1 : 0;
@@ -1584,28 +1558,22 @@ int dm_suspend(struct mapped_device *md, unsigned suspend_flags)
 	down_write(&md->io_lock);
 	set_bit(DMF_BLOCK_IO, &md->flags);
 
-	add_wait_queue(&md->wait, &wait);
 	up_write(&md->io_lock);
 
-	/* unplug */
-	if (map)
-		dm_table_unplug_all(map);
-
 	/*
 	 * Wait for the already-mapped ios to complete.
 	 */
-	r = dm_wait_for_completion(md);
+	r = dm_wait_for_completion(md, TASK_INTERRUPTIBLE);
 
 	down_write(&md->io_lock);
-	remove_wait_queue(&md->wait, &wait);
 
 	if (noflush)
-		__merge_pushback_list(md);
+		clear_bit(DMF_NOFLUSH_SUSPENDING, &md->flags);
 	up_write(&md->io_lock);
 
 	/* were we interrupted ? */
 	if (r < 0) {
-		dm_queue_flush(md, DM_WQ_FLUSH_DEFERRED, NULL);
+		dm_queue_flush(md);
 
 		unlock_fs(md);
 		goto out; /* pushback list is already flushed, so skip flush */
@@ -1645,7 +1613,7 @@ int dm_resume(struct mapped_device *md)
 	if (r)
 		goto out;
 
-	dm_queue_flush(md, DM_WQ_FLUSH_DEFERRED, NULL);
+	dm_queue_flush(md);
 
 	unlock_fs(md);
 
diff --git a/drivers/md/dm.h b/drivers/md/dm.h
index 20194e000c5a..b48397c0abbd 100644
--- a/drivers/md/dm.h
+++ b/drivers/md/dm.h
@@ -60,7 +60,7 @@ int dm_table_barrier_ok(struct dm_table *t);
 int dm_target_init(void);
 void dm_target_exit(void);
 struct target_type *dm_get_target_type(const char *name);
-void dm_put_target_type(struct target_type *t);
+void dm_put_target_type(struct target_type *tt);
 int dm_target_iterate(void (*iter_func)(struct target_type *tt,
 					void *param), void *param);
 
diff --git a/drivers/md/faulty.c b/drivers/md/faulty.c
index 86d9adf90e79..8695809b24b0 100644
--- a/drivers/md/faulty.c
+++ b/drivers/md/faulty.c
@@ -62,7 +62,10 @@
 #define	ModeShift	5
 
 #define MaxFault	50
-#include <linux/raid/md.h>
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include "md.h"
+#include <linux/seq_file.h>
 
 
 static void faulty_fail(struct bio *bio, int error)
@@ -280,6 +283,17 @@ static int reconfig(mddev_t *mddev, int layout, int chunk_size)
 	return 0;
 }
 
+static sector_t faulty_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	WARN_ONCE(raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+
+	if (sectors == 0)
+		return mddev->dev_sectors;
+
+	return sectors;
+}
+
 static int run(mddev_t *mddev)
 {
 	mdk_rdev_t *rdev;
@@ -298,7 +312,7 @@ static int run(mddev_t *mddev)
 	list_for_each_entry(rdev, &mddev->disks, same_set)
 		conf->rdev = rdev;
 
-	mddev->array_sectors = mddev->size * 2;
+	md_set_array_sectors(mddev, faulty_size(mddev, 0, 0));
 	mddev->private = conf;
 
 	reconfig(mddev, mddev->layout, -1);
@@ -325,6 +339,7 @@ static struct mdk_personality faulty_personality =
 	.stop		= stop,
 	.status		= status,
 	.reconfig	= reconfig,
+	.size		= faulty_size,
 };
 
 static int __init raid_init(void)
diff --git a/drivers/md/linear.c b/drivers/md/linear.c
index 09658b218474..7a36e38393a1 100644
--- a/drivers/md/linear.c
+++ b/drivers/md/linear.c
@@ -16,7 +16,11 @@
    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
-#include <linux/raid/linear.h>
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "linear.h"
 
 /*
  * find which device holds a particular offset 
@@ -97,6 +101,16 @@ static int linear_congested(void *data, int bits)
 	return ret;
 }
 
+static sector_t linear_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	linear_conf_t *conf = mddev_to_conf(mddev);
+
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+
+	return conf->array_sectors;
+}
+
 static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 {
 	linear_conf_t *conf;
@@ -135,8 +149,8 @@ static linear_conf_t *linear_conf(mddev_t *mddev, int raid_disks)
 		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
-		disk->num_sectors = rdev->size * 2;
-		conf->array_sectors += rdev->size * 2;
+		disk->num_sectors = rdev->sectors;
+		conf->array_sectors += rdev->sectors;
 
 		cnt++;
 	}
@@ -249,7 +263,7 @@ static int linear_run (mddev_t *mddev)
 	if (!conf)
 		return 1;
 	mddev->private = conf;
-	mddev->array_sectors = conf->array_sectors;
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 
 	blk_queue_merge_bvec(mddev->queue, linear_mergeable_bvec);
 	mddev->queue->unplug_fn = linear_unplug;
@@ -283,7 +297,7 @@ static int linear_add(mddev_t *mddev, mdk_rdev_t *rdev)
 	newconf->prev = mddev_to_conf(mddev);
 	mddev->private = newconf;
 	mddev->raid_disks++;
-	mddev->array_sectors = newconf->array_sectors;
+	md_set_array_sectors(mddev, linear_size(mddev, 0, 0));
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	return 0;
 }
@@ -381,6 +395,7 @@ static struct mdk_personality linear_personality =
 	.stop		= linear_stop,
 	.status		= linear_status,
 	.hot_add_disk	= linear_add,
+	.size		= linear_size,
 };
 
 static int __init linear_init (void)
diff --git a/include/linux/raid/linear.h b/drivers/md/linear.h
index f38b9c586afb..bf8179587f95 100644
--- a/include/linux/raid/linear.h
+++ b/drivers/md/linear.h
@@ -1,8 +1,6 @@
 #ifndef _LINEAR_H
 #define _LINEAR_H
 
-#include <linux/raid/md.h>
-
 struct dev_info {
 	mdk_rdev_t	*rdev;
 	sector_t	num_sectors;
diff --git a/drivers/md/md.c b/drivers/md/md.c
index a307f87eb90e..ed5727c089a9 100644
--- a/drivers/md/md.c
+++ b/drivers/md/md.c
@@ -33,9 +33,9 @@
 */
 
 #include <linux/kthread.h>
-#include <linux/raid/md.h>
-#include <linux/raid/bitmap.h>
+#include <linux/blkdev.h>
 #include <linux/sysctl.h>
+#include <linux/seq_file.h>
 #include <linux/buffer_head.h> /* for invalidate_bdev */
 #include <linux/poll.h>
 #include <linux/ctype.h>
@@ -45,11 +45,10 @@
 #include <linux/reboot.h>
 #include <linux/file.h>
 #include <linux/delay.h>
-
-#define MAJOR_NR MD_MAJOR
-
-/* 63 partitions with the alternate major number (mdp) */
-#define MdpMinorShift 6
+#include <linux/raid/md_p.h>
+#include <linux/raid/md_u.h>
+#include "md.h"
+#include "bitmap.h"
 
 #define DEBUG 0
 #define dprintk(x...) ((void)(DEBUG && printk(x)))
@@ -202,12 +201,68 @@ static DEFINE_SPINLOCK(all_mddevs_lock);
 		)
 
 
-static int md_fail_request(struct request_queue *q, struct bio *bio)
+/* Rather than calling directly into the personality make_request function,
+ * IO requests come here first so that we can check if the device is
+ * being suspended pending a reconfiguration.
+ * We hold a refcount over the call to ->make_request.  By the time that
+ * call has finished, the bio has been linked into some internal structure
+ * and so is visible to ->quiesce(), so we don't need the refcount any more.
+ */
+static int md_make_request(struct request_queue *q, struct bio *bio)
 {
-	bio_io_error(bio);
-	return 0;
+	mddev_t *mddev = q->queuedata;
+	int rv;
+	if (mddev == NULL || mddev->pers == NULL) {
+		bio_io_error(bio);
+		return 0;
+	}
+	rcu_read_lock();
+	if (mddev->suspended) {
+		DEFINE_WAIT(__wait);
+		for (;;) {
+			prepare_to_wait(&mddev->sb_wait, &__wait,
+					TASK_UNINTERRUPTIBLE);
+			if (!mddev->suspended)
+				break;
+			rcu_read_unlock();
+			schedule();
+			rcu_read_lock();
+		}
+		finish_wait(&mddev->sb_wait, &__wait);
+	}
+	atomic_inc(&mddev->active_io);
+	rcu_read_unlock();
+	rv = mddev->pers->make_request(q, bio);
+	if (atomic_dec_and_test(&mddev->active_io) && mddev->suspended)
+		wake_up(&mddev->sb_wait);
+
+	return rv;
+}
+
+static void mddev_suspend(mddev_t *mddev)
+{
+	BUG_ON(mddev->suspended);
+	mddev->suspended = 1;
+	synchronize_rcu();
+	wait_event(mddev->sb_wait, atomic_read(&mddev->active_io) == 0);
+	mddev->pers->quiesce(mddev, 1);
+	md_unregister_thread(mddev->thread);
+	mddev->thread = NULL;
+	/* we now know that no code is executing in the personality module,
+	 * except possibly the tail end of a ->bi_end_io function, but that
+	 * is certain to complete before the module has a chance to get
+	 * unloaded
+	 */
+}
+
+static void mddev_resume(mddev_t *mddev)
+{
+	mddev->suspended = 0;
+	wake_up(&mddev->sb_wait);
+	mddev->pers->quiesce(mddev, 0);
 }
 
+
 static inline mddev_t *mddev_get(mddev_t *mddev)
 {
 	atomic_inc(&mddev->active);
@@ -310,6 +365,7 @@ static mddev_t * mddev_find(dev_t unit)
 	init_timer(&new->safemode_timer);
 	atomic_set(&new->active, 1);
 	atomic_set(&new->openers, 0);
+	atomic_set(&new->active_io, 0);
 	spin_lock_init(&new->write_lock);
 	init_waitqueue_head(&new->sb_wait);
 	init_waitqueue_head(&new->recovery_wait);
@@ -326,6 +382,11 @@ static inline int mddev_lock(mddev_t * mddev)
 	return mutex_lock_interruptible(&mddev->reconfig_mutex);
 }
 
+static inline int mddev_is_locked(mddev_t *mddev)
+{
+	return mutex_is_locked(&mddev->reconfig_mutex);
+}
+
 static inline int mddev_trylock(mddev_t * mddev)
 {
 	return mutex_trylock(&mddev->reconfig_mutex);
@@ -409,7 +470,7 @@ static void free_disk_sb(mdk_rdev_t * rdev)
 		rdev->sb_loaded = 0;
 		rdev->sb_page = NULL;
 		rdev->sb_start = 0;
-		rdev->size = 0;
+		rdev->sectors = 0;
 	}
 }
 
@@ -775,9 +836,9 @@ static int super_90_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version
 		else 
 			ret = 0;
 	}
-	rdev->size = calc_num_sectors(rdev, sb->chunk_size) / 2;
+	rdev->sectors = calc_num_sectors(rdev, sb->chunk_size);
 
-	if (rdev->size < sb->size && sb->level > 1)
+	if (rdev->sectors < sb->size * 2 && sb->level > 1)
 		/* "this cannot possibly happen" ... */
 		ret = -EINVAL;
 
@@ -812,7 +873,7 @@ static int super_90_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 		mddev->clevel[0] = 0;
 		mddev->layout = sb->layout;
 		mddev->raid_disks = sb->raid_disks;
-		mddev->size = sb->size;
+		mddev->dev_sectors = sb->size * 2;
 		mddev->events = ev1;
 		mddev->bitmap_offset = 0;
 		mddev->default_bitmap_offset = MD_SB_BYTES >> 9;
@@ -926,7 +987,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 
 	sb->ctime = mddev->ctime;
 	sb->level = mddev->level;
-	sb->size  = mddev->size;
+	sb->size = mddev->dev_sectors / 2;
 	sb->raid_disks = mddev->raid_disks;
 	sb->md_minor = mddev->md_minor;
 	sb->not_persistent = 0;
@@ -1024,7 +1085,7 @@ static void super_90_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 static unsigned long long
 super_90_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
 {
-	if (num_sectors && num_sectors < rdev->mddev->size * 2)
+	if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
 		return 0; /* component must fit device */
 	if (rdev->mddev->bitmap_offset)
 		return 0; /* can't move bitmap */
@@ -1180,16 +1241,17 @@ static int super_1_load(mdk_rdev_t *rdev, mdk_rdev_t *refdev, int minor_version)
 			ret = 0;
 	}
 	if (minor_version)
-		rdev->size = ((rdev->bdev->bd_inode->i_size>>9) - le64_to_cpu(sb->data_offset)) / 2;
+		rdev->sectors = (rdev->bdev->bd_inode->i_size >> 9) -
+			le64_to_cpu(sb->data_offset);
 	else
-		rdev->size = rdev->sb_start / 2;
-	if (rdev->size < le64_to_cpu(sb->data_size)/2)
+		rdev->sectors = rdev->sb_start;
+	if (rdev->sectors < le64_to_cpu(sb->data_size))
 		return -EINVAL;
-	rdev->size = le64_to_cpu(sb->data_size)/2;
+	rdev->sectors = le64_to_cpu(sb->data_size);
 	if (le32_to_cpu(sb->chunksize))
-		rdev->size &= ~((sector_t)le32_to_cpu(sb->chunksize)/2 - 1);
+		rdev->sectors &= ~((sector_t)le32_to_cpu(sb->chunksize) - 1);
 
-	if (le64_to_cpu(sb->size) > rdev->size*2)
+	if (le64_to_cpu(sb->size) > rdev->sectors)
 		return -EINVAL;
 	return ret;
 }
@@ -1216,7 +1278,7 @@ static int super_1_validate(mddev_t *mddev, mdk_rdev_t *rdev)
 		mddev->clevel[0] = 0;
 		mddev->layout = le32_to_cpu(sb->layout);
 		mddev->raid_disks = le32_to_cpu(sb->raid_disks);
-		mddev->size = le64_to_cpu(sb->size)/2;
+		mddev->dev_sectors = le64_to_cpu(sb->size);
 		mddev->events = ev1;
 		mddev->bitmap_offset = 0;
 		mddev->default_bitmap_offset = 1024 >> 9;
@@ -1312,7 +1374,7 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 	sb->cnt_corrected_read = cpu_to_le32(atomic_read(&rdev->corrected_errors));
 
 	sb->raid_disks = cpu_to_le32(mddev->raid_disks);
-	sb->size = cpu_to_le64(mddev->size<<1);
+	sb->size = cpu_to_le64(mddev->dev_sectors);
 
 	if (mddev->bitmap && mddev->bitmap_file == NULL) {
 		sb->bitmap_offset = cpu_to_le32((__u32)mddev->bitmap_offset);
@@ -1320,10 +1382,15 @@ static void super_1_sync(mddev_t *mddev, mdk_rdev_t *rdev)
 	}
 
 	if (rdev->raid_disk >= 0 &&
-	    !test_bit(In_sync, &rdev->flags) &&
-	    rdev->recovery_offset > 0) {
-		sb->feature_map |= cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
-		sb->recovery_offset = cpu_to_le64(rdev->recovery_offset);
+	    !test_bit(In_sync, &rdev->flags)) {
+		if (mddev->curr_resync_completed > rdev->recovery_offset)
+			rdev->recovery_offset = mddev->curr_resync_completed;
+		if (rdev->recovery_offset > 0) {
+			sb->feature_map |=
+				cpu_to_le32(MD_FEATURE_RECOVERY_OFFSET);
+			sb->recovery_offset =
+				cpu_to_le64(rdev->recovery_offset);
+		}
 	}
 
 	if (mddev->reshape_position != MaxSector) {
@@ -1365,7 +1432,7 @@ super_1_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
 {
 	struct mdp_superblock_1 *sb;
 	sector_t max_sectors;
-	if (num_sectors && num_sectors < rdev->mddev->size * 2)
+	if (num_sectors && num_sectors < rdev->mddev->dev_sectors)
 		return 0; /* component must fit device */
 	if (rdev->sb_start < rdev->data_offset) {
 		/* minor versions 1 and 2; superblock before data */
@@ -1381,7 +1448,7 @@ super_1_rdev_size_change(mdk_rdev_t *rdev, sector_t num_sectors)
 		sector_t sb_start;
 		sb_start = (rdev->bdev->bd_inode->i_size >> 9) - 8*2;
 		sb_start &= ~(sector_t)(4*2 - 1);
-		max_sectors = rdev->size * 2 + sb_start - rdev->sb_start;
+		max_sectors = rdev->sectors + sb_start - rdev->sb_start;
 		if (!num_sectors || num_sectors > max_sectors)
 			num_sectors = max_sectors;
 		rdev->sb_start = sb_start;
@@ -1433,6 +1500,38 @@ static int match_mddev_units(mddev_t *mddev1, mddev_t *mddev2)
 
 static LIST_HEAD(pending_raid_disks);
 
+static void md_integrity_check(mdk_rdev_t *rdev, mddev_t *mddev)
+{
+	struct mdk_personality *pers = mddev->pers;
+	struct gendisk *disk = mddev->gendisk;
+	struct blk_integrity *bi_rdev = bdev_get_integrity(rdev->bdev);
+	struct blk_integrity *bi_mddev = blk_get_integrity(disk);
+
+	/* Data integrity passthrough not supported on RAID 4, 5 and 6 */
+	if (pers && pers->level >= 4 && pers->level <= 6)
+		return;
+
+	/* If rdev is integrity capable, register profile for mddev */
+	if (!bi_mddev && bi_rdev) {
+		if (blk_integrity_register(disk, bi_rdev))
+			printk(KERN_ERR "%s: %s Could not register integrity!\n",
+			       __func__, disk->disk_name);
+		else
+			printk(KERN_NOTICE "Enabling data integrity on %s\n",
+			       disk->disk_name);
+		return;
+	}
+
+	/* Check that mddev and rdev have matching profiles */
+	if (blk_integrity_compare(disk, rdev->bdev->bd_disk) < 0) {
+		printk(KERN_ERR "%s: %s/%s integrity mismatch!\n", __func__,
+		       disk->disk_name, rdev->bdev->bd_disk->disk_name);
+		printk(KERN_NOTICE "Disabling data integrity on %s\n",
+		       disk->disk_name);
+		blk_integrity_unregister(disk);
+	}
+}
+
 static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 {
 	char b[BDEVNAME_SIZE];
@@ -1449,8 +1548,9 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 	if (find_rdev(mddev, rdev->bdev->bd_dev))
 		return -EEXIST;
 
-	/* make sure rdev->size exceeds mddev->size */
-	if (rdev->size && (mddev->size == 0 || rdev->size < mddev->size)) {
+	/* make sure rdev->sectors exceeds mddev->dev_sectors */
+	if (rdev->sectors && (mddev->dev_sectors == 0 ||
+			rdev->sectors < mddev->dev_sectors)) {
 		if (mddev->pers) {
 			/* Cannot change size, so fail
 			 * If mddev->level <= 0, then we don't care
@@ -1459,7 +1559,7 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 			if (mddev->level > 0)
 				return -ENOSPC;
 		} else
-			mddev->size = rdev->size;
+			mddev->dev_sectors = rdev->sectors;
 	}
 
 	/* Verify rdev->desc_nr is unique.
@@ -1503,6 +1603,8 @@ static int bind_rdev_to_array(mdk_rdev_t * rdev, mddev_t * mddev)
 
 	/* May as well allow recovery to be retried once */
 	mddev->recovery_disabled = 0;
+
+	md_integrity_check(rdev, mddev);
 	return 0;
 
  fail:
@@ -1713,8 +1815,8 @@ static void print_sb_1(struct mdp_superblock_1 *sb)
 static void print_rdev(mdk_rdev_t *rdev, int major_version)
 {
 	char b[BDEVNAME_SIZE];
-	printk(KERN_INFO "md: rdev %s, SZ:%08llu F:%d S:%d DN:%u\n",
-		bdevname(rdev->bdev,b), (unsigned long long)rdev->size,
+	printk(KERN_INFO "md: rdev %s, Sect:%08llu F:%d S:%d DN:%u\n",
+		bdevname(rdev->bdev, b), (unsigned long long)rdev->sectors,
 	        test_bit(Faulty, &rdev->flags), test_bit(In_sync, &rdev->flags),
 	        rdev->desc_nr);
 	if (rdev->sb_loaded) {
@@ -2153,7 +2255,7 @@ offset_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		return -EINVAL;
 	if (rdev->mddev->pers && rdev->raid_disk >= 0)
 		return -EBUSY;
-	if (rdev->size && rdev->mddev->external)
+	if (rdev->sectors && rdev->mddev->external)
 		/* Must set offset before size, so overlap checks
 		 * can be sane */
 		return -EBUSY;
@@ -2167,7 +2269,7 @@ __ATTR(offset, S_IRUGO|S_IWUSR, offset_show, offset_store);
 static ssize_t
 rdev_size_show(mdk_rdev_t *rdev, char *page)
 {
-	return sprintf(page, "%llu\n", (unsigned long long)rdev->size);
+	return sprintf(page, "%llu\n", (unsigned long long)rdev->sectors / 2);
 }
 
 static int overlaps(sector_t s1, sector_t l1, sector_t s2, sector_t l2)
@@ -2180,34 +2282,52 @@ static int overlaps(sector_t s1, sector_t l1, sector_t s2, sector_t l2)
 	return 1;
 }
 
+static int strict_blocks_to_sectors(const char *buf, sector_t *sectors)
+{
+	unsigned long long blocks;
+	sector_t new;
+
+	if (strict_strtoull(buf, 10, &blocks) < 0)
+		return -EINVAL;
+
+	if (blocks & 1ULL << (8 * sizeof(blocks) - 1))
+		return -EINVAL; /* sector conversion overflow */
+
+	new = blocks * 2;
+	if (new != blocks * 2)
+		return -EINVAL; /* unsigned long long to sector_t overflow */
+
+	*sectors = new;
+	return 0;
+}
+
 static ssize_t
 rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 {
-	unsigned long long size;
-	unsigned long long oldsize = rdev->size;
 	mddev_t *my_mddev = rdev->mddev;
+	sector_t oldsectors = rdev->sectors;
+	sector_t sectors;
 
-	if (strict_strtoull(buf, 10, &size) < 0)
+	if (strict_blocks_to_sectors(buf, &sectors) < 0)
 		return -EINVAL;
 	if (my_mddev->pers && rdev->raid_disk >= 0) {
 		if (my_mddev->persistent) {
-			size = super_types[my_mddev->major_version].
-				rdev_size_change(rdev, size * 2);
-			if (!size)
+			sectors = super_types[my_mddev->major_version].
+				rdev_size_change(rdev, sectors);
+			if (!sectors)
 				return -EBUSY;
-		} else if (!size) {
-			size = (rdev->bdev->bd_inode->i_size >> 10);
-			size -= rdev->data_offset/2;
-		}
+		} else if (!sectors)
+			sectors = (rdev->bdev->bd_inode->i_size >> 9) -
+				rdev->data_offset;
 	}
-	if (size < my_mddev->size)
+	if (sectors < my_mddev->dev_sectors)
 		return -EINVAL; /* component must fit device */
 
-	rdev->size = size;
-	if (size > oldsize && my_mddev->external) {
+	rdev->sectors = sectors;
+	if (sectors > oldsectors && my_mddev->external) {
 		/* need to check that all other rdevs with the same ->bdev
 		 * do not overlap.  We need to unlock the mddev to avoid
-		 * a deadlock.  We have already changed rdev->size, and if
+		 * a deadlock.  We have already changed rdev->sectors, and if
 		 * we have to change it back, we will have the lock again.
 		 */
 		mddev_t *mddev;
@@ -2223,9 +2343,9 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 				if (test_bit(AllReserved, &rdev2->flags) ||
 				    (rdev->bdev == rdev2->bdev &&
 				     rdev != rdev2 &&
-				     overlaps(rdev->data_offset, rdev->size * 2,
+				     overlaps(rdev->data_offset, rdev->sectors,
 					      rdev2->data_offset,
-					      rdev2->size * 2))) {
+					      rdev2->sectors))) {
 					overlap = 1;
 					break;
 				}
@@ -2239,11 +2359,11 @@ rdev_size_store(mdk_rdev_t *rdev, const char *buf, size_t len)
 		if (overlap) {
 			/* Someone else could have slipped in a size
 			 * change here, but doing so is just silly.
-			 * We put oldsize back because we *know* it is
+			 * We put oldsectors back because we *know* it is
 			 * safe, and trust userspace not to race with
 			 * itself
 			 */
-			rdev->size = oldsize;
+			rdev->sectors = oldsectors;
 			return -EBUSY;
 		}
 	}
@@ -2547,18 +2667,101 @@ level_show(mddev_t *mddev, char *page)
 static ssize_t
 level_store(mddev_t *mddev, const char *buf, size_t len)
 {
+	char level[16];
 	ssize_t rv = len;
-	if (mddev->pers)
+	struct mdk_personality *pers;
+	void *priv;
+
+	if (mddev->pers == NULL) {
+		if (len == 0)
+			return 0;
+		if (len >= sizeof(mddev->clevel))
+			return -ENOSPC;
+		strncpy(mddev->clevel, buf, len);
+		if (mddev->clevel[len-1] == '\n')
+			len--;
+		mddev->clevel[len] = 0;
+		mddev->level = LEVEL_NONE;
+		return rv;
+	}
+
+	/* request to change the personality.  Need to ensure:
+	 *  - array is not engaged in resync/recovery/reshape
+	 *  - old personality can be suspended
+	 *  - new personality will access other array.
+	 */
+
+	if (mddev->sync_thread || mddev->reshape_position != MaxSector)
 		return -EBUSY;
-	if (len == 0)
-		return 0;
-	if (len >= sizeof(mddev->clevel))
-		return -ENOSPC;
-	strncpy(mddev->clevel, buf, len);
-	if (mddev->clevel[len-1] == '\n')
+
+	if (!mddev->pers->quiesce) {
+		printk(KERN_WARNING "md: %s: %s does not support online personality change\n",
+		       mdname(mddev), mddev->pers->name);
+		return -EINVAL;
+	}
+
+	/* Now find the new personality */
+	if (len == 0 || len >= sizeof(level))
+		return -EINVAL;
+	strncpy(level, buf, len);
+	if (level[len-1] == '\n')
 		len--;
-	mddev->clevel[len] = 0;
-	mddev->level = LEVEL_NONE;
+	level[len] = 0;
+
+	request_module("md-%s", level);
+	spin_lock(&pers_lock);
+	pers = find_pers(LEVEL_NONE, level);
+	if (!pers || !try_module_get(pers->owner)) {
+		spin_unlock(&pers_lock);
+		printk(KERN_WARNING "md: personality %s not loaded\n", level);
+		return -EINVAL;
+	}
+	spin_unlock(&pers_lock);
+
+	if (pers == mddev->pers) {
+		/* Nothing to do! */
+		module_put(pers->owner);
+		return rv;
+	}
+	if (!pers->takeover) {
+		module_put(pers->owner);
+		printk(KERN_WARNING "md: %s: %s does not support personality takeover\n",
+		       mdname(mddev), level);
+		return -EINVAL;
+	}
+
+	/* ->takeover must set new_* and/or delta_disks
+	 * if it succeeds, and may set them when it fails.
+	 */
+	priv = pers->takeover(mddev);
+	if (IS_ERR(priv)) {
+		mddev->new_level = mddev->level;
+		mddev->new_layout = mddev->layout;
+		mddev->new_chunk = mddev->chunk_size;
+		mddev->raid_disks -= mddev->delta_disks;
+		mddev->delta_disks = 0;
+		module_put(pers->owner);
+		printk(KERN_WARNING "md: %s: %s would not accept array\n",
+		       mdname(mddev), level);
+		return PTR_ERR(priv);
+	}
+
+	/* Looks like we have a winner */
+	mddev_suspend(mddev);
+	mddev->pers->stop(mddev);
+	module_put(mddev->pers->owner);
+	mddev->pers = pers;
+	mddev->private = priv;
+	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
+	mddev->level = mddev->new_level;
+	mddev->layout = mddev->new_layout;
+	mddev->chunk_size = mddev->new_chunk;
+	mddev->delta_disks = 0;
+	pers->run(mddev);
+	mddev_resume(mddev);
+	set_bit(MD_CHANGE_DEVS, &mddev->flags);
+	set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
+	md_wakeup_thread(mddev->thread);
 	return rv;
 }
 
@@ -2586,12 +2789,18 @@ layout_store(mddev_t *mddev, const char *buf, size_t len)
 	if (!*buf || (*e && *e != '\n'))
 		return -EINVAL;
 
-	if (mddev->pers)
-		return -EBUSY;
-	if (mddev->reshape_position != MaxSector)
+	if (mddev->pers) {
+		int err;
+		if (mddev->pers->reconfig == NULL)
+			return -EBUSY;
+		err = mddev->pers->reconfig(mddev, n, -1);
+		if (err)
+			return err;
+	} else {
 		mddev->new_layout = n;
-	else
-		mddev->layout = n;
+		if (mddev->reshape_position == MaxSector)
+			mddev->layout = n;
+	}
 	return len;
 }
 static struct md_sysfs_entry md_layout =
@@ -2648,19 +2857,24 @@ chunk_size_show(mddev_t *mddev, char *page)
 static ssize_t
 chunk_size_store(mddev_t *mddev, const char *buf, size_t len)
 {
-	/* can only set chunk_size if array is not yet active */
 	char *e;
 	unsigned long n = simple_strtoul(buf, &e, 10);
 
 	if (!*buf || (*e && *e != '\n'))
 		return -EINVAL;
 
-	if (mddev->pers)
-		return -EBUSY;
-	else if (mddev->reshape_position != MaxSector)
+	if (mddev->pers) {
+		int err;
+		if (mddev->pers->reconfig == NULL)
+			return -EBUSY;
+		err = mddev->pers->reconfig(mddev, -1, n);
+		if (err)
+			return err;
+	} else {
 		mddev->new_chunk = n;
-	else
-		mddev->chunk_size = n;
+		if (mddev->reshape_position == MaxSector)
+			mddev->chunk_size = n;
+	}
 	return len;
 }
 static struct md_sysfs_entry md_chunk_size =
@@ -2669,6 +2883,8 @@ __ATTR(chunk_size, S_IRUGO|S_IWUSR, chunk_size_show, chunk_size_store);
 static ssize_t
 resync_start_show(mddev_t *mddev, char *page)
 {
+	if (mddev->recovery_cp == MaxSector)
+		return sprintf(page, "none\n");
 	return sprintf(page, "%llu\n", (unsigned long long)mddev->recovery_cp);
 }
 
@@ -2766,7 +2982,7 @@ array_state_show(mddev_t *mddev, char *page)
 	else {
 		if (list_empty(&mddev->disks) &&
 		    mddev->raid_disks == 0 &&
-		    mddev->size == 0)
+		    mddev->dev_sectors == 0)
 			st = clear;
 		else
 			st = inactive;
@@ -2973,7 +3189,8 @@ __ATTR(bitmap_set_bits, S_IWUSR, null_show, bitmap_store);
 static ssize_t
 size_show(mddev_t *mddev, char *page)
 {
-	return sprintf(page, "%llu\n", (unsigned long long)mddev->size);
+	return sprintf(page, "%llu\n",
+		(unsigned long long)mddev->dev_sectors / 2);
 }
 
 static int update_size(mddev_t *mddev, sector_t num_sectors);
@@ -2985,20 +3202,18 @@ size_store(mddev_t *mddev, const char *buf, size_t len)
 	 * not increase it (except from 0).
 	 * If array is active, we can try an on-line resize
 	 */
-	char *e;
-	int err = 0;
-	unsigned long long size = simple_strtoull(buf, &e, 10);
-	if (!*buf || *buf == '\n' ||
-	    (*e && *e != '\n'))
-		return -EINVAL;
+	sector_t sectors;
+	int err = strict_blocks_to_sectors(buf, &sectors);
 
+	if (err < 0)
+		return err;
 	if (mddev->pers) {
-		err = update_size(mddev, size * 2);
+		err = update_size(mddev, sectors);
 		md_update_sb(mddev, 1);
 	} else {
-		if (mddev->size == 0 ||
-		    mddev->size > size)
-			mddev->size = size;
+		if (mddev->dev_sectors == 0 ||
+		    mddev->dev_sectors > sectors)
+			mddev->dev_sectors = sectors;
 		else
 			err = -ENOSPC;
 	}
@@ -3251,6 +3466,8 @@ static ssize_t
 sync_speed_show(mddev_t *mddev, char *page)
 {
 	unsigned long resync, dt, db;
+	if (mddev->curr_resync == 0)
+		return sprintf(page, "none\n");
 	resync = mddev->curr_mark_cnt - atomic_read(&mddev->recovery_active);
 	dt = (jiffies - mddev->resync_mark) / HZ;
 	if (!dt) dt++;
@@ -3263,15 +3480,15 @@ static struct md_sysfs_entry md_sync_speed = __ATTR_RO(sync_speed);
 static ssize_t
 sync_completed_show(mddev_t *mddev, char *page)
 {
-	unsigned long max_blocks, resync;
+	unsigned long max_sectors, resync;
 
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
-		max_blocks = mddev->resync_max_sectors;
+		max_sectors = mddev->resync_max_sectors;
 	else
-		max_blocks = mddev->size << 1;
+		max_sectors = mddev->dev_sectors;
 
 	resync = (mddev->curr_resync - atomic_read(&mddev->recovery_active));
-	return sprintf(page, "%lu / %lu\n", resync, max_blocks);
+	return sprintf(page, "%lu / %lu\n", resync, max_sectors);
 }
 
 static struct md_sysfs_entry md_sync_completed = __ATTR_RO(sync_completed);
@@ -3431,6 +3648,57 @@ static struct md_sysfs_entry md_reshape_position =
 __ATTR(reshape_position, S_IRUGO|S_IWUSR, reshape_position_show,
        reshape_position_store);
 
+static ssize_t
+array_size_show(mddev_t *mddev, char *page)
+{
+	if (mddev->external_size)
+		return sprintf(page, "%llu\n",
+			       (unsigned long long)mddev->array_sectors/2);
+	else
+		return sprintf(page, "default\n");
+}
+
+static ssize_t
+array_size_store(mddev_t *mddev, const char *buf, size_t len)
+{
+	sector_t sectors;
+
+	if (strncmp(buf, "default", 7) == 0) {
+		if (mddev->pers)
+			sectors = mddev->pers->size(mddev, 0, 0);
+		else
+			sectors = mddev->array_sectors;
+
+		mddev->external_size = 0;
+	} else {
+		if (strict_blocks_to_sectors(buf, &sectors) < 0)
+			return -EINVAL;
+		if (mddev->pers && mddev->pers->size(mddev, 0, 0) < sectors)
+			return -EINVAL;
+
+		mddev->external_size = 1;
+	}
+
+	mddev->array_sectors = sectors;
+	set_capacity(mddev->gendisk, mddev->array_sectors);
+	if (mddev->pers) {
+		struct block_device *bdev = bdget_disk(mddev->gendisk, 0);
+
+		if (bdev) {
+			mutex_lock(&bdev->bd_inode->i_mutex);
+			i_size_write(bdev->bd_inode,
+				     (loff_t)mddev->array_sectors << 9);
+			mutex_unlock(&bdev->bd_inode->i_mutex);
+			bdput(bdev);
+		}
+	}
+
+	return len;
+}
+
+static struct md_sysfs_entry md_array_size =
+__ATTR(array_size, S_IRUGO|S_IWUSR, array_size_show,
+       array_size_store);
 
 static struct attribute *md_default_attrs[] = {
 	&md_level.attr,
@@ -3444,6 +3712,7 @@ static struct attribute *md_default_attrs[] = {
 	&md_safe_delay.attr,
 	&md_array_state.attr,
 	&md_reshape_position.attr,
+	&md_array_size.attr,
 	NULL,
 };
 
@@ -3602,10 +3871,12 @@ static int md_alloc(dev_t dev, char *name)
 		mddev_put(mddev);
 		return -ENOMEM;
 	}
+	mddev->queue->queuedata = mddev;
+
 	/* Can be unlocked because the queue is new: no concurrency */
 	queue_flag_set_unlocked(QUEUE_FLAG_CLUSTER, mddev->queue);
 
-	blk_queue_make_request(mddev->queue, md_fail_request);
+	blk_queue_make_request(mddev->queue, md_make_request);
 
 	disk = alloc_disk(1 << shift);
 	if (!disk) {
@@ -3731,13 +4002,13 @@ static int do_md_run(mddev_t * mddev)
 		list_for_each_entry(rdev, &mddev->disks, same_set) {
 			if (test_bit(Faulty, &rdev->flags))
 				continue;
-			if (rdev->size < chunk_size / 1024) {
+			if (rdev->sectors < chunk_size / 512) {
 				printk(KERN_WARNING
 					"md: Dev %s smaller than chunk_size:"
-					" %lluk < %dk\n",
+					" %llu < %d\n",
 					bdevname(rdev->bdev,b),
-					(unsigned long long)rdev->size,
-					chunk_size / 1024);
+					(unsigned long long)rdev->sectors,
+					chunk_size / 512);
 				return -EINVAL;
 			}
 		}
@@ -3761,11 +4032,11 @@ static int do_md_run(mddev_t * mddev)
 
 		/* perform some consistency tests on the device.
 		 * We don't want the data to overlap the metadata,
-		 * Internal Bitmap issues has handled elsewhere.
+		 * Internal Bitmap issues have been handled elsewhere.
 		 */
 		if (rdev->data_offset < rdev->sb_start) {
-			if (mddev->size &&
-			    rdev->data_offset + mddev->size*2
+			if (mddev->dev_sectors &&
+			    rdev->data_offset + mddev->dev_sectors
 			    > rdev->sb_start) {
 				printk("md: %s: data overlaps metadata\n",
 				       mdname(mddev));
@@ -3801,9 +4072,16 @@ static int do_md_run(mddev_t * mddev)
 	}
 	mddev->pers = pers;
 	spin_unlock(&pers_lock);
-	mddev->level = pers->level;
+	if (mddev->level != pers->level) {
+		mddev->level = pers->level;
+		mddev->new_level = pers->level;
+	}
 	strlcpy(mddev->clevel, pers->name, sizeof(mddev->clevel));
 
+	if (pers->level >= 4 && pers->level <= 6)
+		/* Cannot support integrity (yet) */
+		blk_integrity_unregister(mddev->gendisk);
+
 	if (mddev->reshape_position != MaxSector &&
 	    pers->start_reshape == NULL) {
 		/* This personality cannot handle reshaping... */
@@ -3843,7 +4121,9 @@ static int do_md_run(mddev_t * mddev)
 	}
 
 	mddev->recovery = 0;
-	mddev->resync_max_sectors = mddev->size << 1; /* may be over-ridden by personality */
+	/* may be over-ridden by personality */
+	mddev->resync_max_sectors = mddev->dev_sectors;
+
 	mddev->barriers_work = 1;
 	mddev->ok_start_degraded = start_dirty_degraded;
 
@@ -3853,7 +4133,17 @@ static int do_md_run(mddev_t * mddev)
 	err = mddev->pers->run(mddev);
 	if (err)
 		printk(KERN_ERR "md: pers->run() failed ...\n");
-	else if (mddev->pers->sync_request) {
+	else if (mddev->pers->size(mddev, 0, 0) < mddev->array_sectors) {
+		WARN_ONCE(!mddev->external_size, "%s: default size too small,"
+			  " but 'external_size' not in effect?\n", __func__);
+		printk(KERN_ERR
+		       "md: invalid array_size %llu > default size %llu\n",
+		       (unsigned long long)mddev->array_sectors / 2,
+		       (unsigned long long)mddev->pers->size(mddev, 0, 0) / 2);
+		err = -EINVAL;
+		mddev->pers->stop(mddev);
+	}
+	if (err == 0 && mddev->pers->sync_request) {
 		err = bitmap_create(mddev);
 		if (err) {
 			printk(KERN_ERR "%s: failed to create bitmap (%d)\n",
@@ -3899,16 +4189,6 @@ static int do_md_run(mddev_t * mddev)
 
 	set_capacity(disk, mddev->array_sectors);
 
-	/* If we call blk_queue_make_request here, it will
-	 * re-initialise max_sectors etc which may have been
-	 * refined inside -> run.  So just set the bits we need to set.
-	 * Most initialisation happended when we called
-	 * blk_queue_make_request(..., md_fail_request)
-	 * earlier.
-	 */
-	mddev->queue->queuedata = mddev;
-	mddev->queue->make_request_fn = mddev->pers->make_request;
-
 	/* If there is a partially-recovered drive we need to
 	 * start recovery here.  If we leave it to md_check_recovery,
 	 * it will remove the drives and not do the right thing
@@ -4038,7 +4318,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 			md_super_wait(mddev);
 			if (mddev->ro)
 				set_disk_ro(disk, 0);
-			blk_queue_make_request(mddev->queue, md_fail_request);
+
 			mddev->pers->stop(mddev);
 			mddev->queue->merge_bvec_fn = NULL;
 			mddev->queue->unplug_fn = NULL;
@@ -4095,7 +4375,8 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		export_array(mddev);
 
 		mddev->array_sectors = 0;
-		mddev->size = 0;
+		mddev->external_size = 0;
+		mddev->dev_sectors = 0;
 		mddev->raid_disks = 0;
 		mddev->recovery_cp = 0;
 		mddev->resync_min = 0;
@@ -4135,6 +4416,7 @@ static int do_md_stop(mddev_t * mddev, int mode, int is_open)
 		printk(KERN_INFO "md: %s switched to read-only mode.\n",
 			mdname(mddev));
 	err = 0;
+	blk_integrity_unregister(disk);
 	md_new_event(mddev);
 	sysfs_notify_dirent(mddev->sysfs_state);
 out:
@@ -4300,8 +4582,8 @@ static int get_array_info(mddev_t * mddev, void __user * arg)
 	info.patch_version = MD_PATCHLEVEL_VERSION;
 	info.ctime         = mddev->ctime;
 	info.level         = mddev->level;
-	info.size          = mddev->size;
-	if (info.size != mddev->size) /* overflow */
+	info.size          = mddev->dev_sectors / 2;
+	if (info.size != mddev->dev_sectors / 2) /* overflow */
 		info.size = -1;
 	info.nr_disks      = nr;
 	info.raid_disks    = mddev->raid_disks;
@@ -4480,6 +4762,8 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 		clear_bit(In_sync, &rdev->flags); /* just to be sure */
 		if (info->state & (1<<MD_DISK_WRITEMOSTLY))
 			set_bit(WriteMostly, &rdev->flags);
+		else
+			clear_bit(WriteMostly, &rdev->flags);
 
 		rdev->raid_disk = -1;
 		err = bind_rdev_to_array(rdev, mddev);
@@ -4543,7 +4827,7 @@ static int add_new_disk(mddev_t * mddev, mdu_disk_info_t *info)
 			rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
 		} else 
 			rdev->sb_start = calc_dev_sboffset(rdev->bdev);
-		rdev->size = calc_num_sectors(rdev, mddev->chunk_size) / 2;
+		rdev->sectors = calc_num_sectors(rdev, mddev->chunk_size);
 
 		err = bind_rdev_to_array(rdev, mddev);
 		if (err) {
@@ -4613,7 +4897,7 @@ static int hot_add_disk(mddev_t * mddev, dev_t dev)
 	else
 		rdev->sb_start = rdev->bdev->bd_inode->i_size / 512;
 
-	rdev->size = calc_num_sectors(rdev, mddev->chunk_size) / 2;
+	rdev->sectors = calc_num_sectors(rdev, mddev->chunk_size);
 
 	if (test_bit(Faulty, &rdev->flags)) {
 		printk(KERN_WARNING 
@@ -4749,7 +5033,7 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
 
 	mddev->level         = info->level;
 	mddev->clevel[0]     = 0;
-	mddev->size          = info->size;
+	mddev->dev_sectors   = 2 * (sector_t)info->size;
 	mddev->raid_disks    = info->raid_disks;
 	/* don't set md_minor, it is determined by which /dev/md* was
 	 * openned
@@ -4788,6 +5072,17 @@ static int set_array_info(mddev_t * mddev, mdu_array_info_t *info)
 	return 0;
 }
 
+void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors)
+{
+	WARN(!mddev_is_locked(mddev), "%s: unlocked mddev!\n", __func__);
+
+	if (mddev->external_size)
+		return;
+
+	mddev->array_sectors = array_sectors;
+}
+EXPORT_SYMBOL(md_set_array_sectors);
+
 static int update_size(mddev_t *mddev, sector_t num_sectors)
 {
 	mdk_rdev_t *rdev;
@@ -4814,8 +5109,7 @@ static int update_size(mddev_t *mddev, sector_t num_sectors)
 		 */
 		return -EBUSY;
 	list_for_each_entry(rdev, &mddev->disks, same_set) {
-		sector_t avail;
-		avail = rdev->size * 2;
+		sector_t avail = rdev->sectors;
 
 		if (fit && (num_sectors == 0 || num_sectors > avail))
 			num_sectors = avail;
@@ -4887,12 +5181,18 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
 		)
 		return -EINVAL;
 	/* Check there is only one change */
-	if (info->size >= 0 && mddev->size != info->size) cnt++;
-	if (mddev->raid_disks != info->raid_disks) cnt++;
-	if (mddev->layout != info->layout) cnt++;
-	if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT)) cnt++;
-	if (cnt == 0) return 0;
-	if (cnt > 1) return -EINVAL;
+	if (info->size >= 0 && mddev->dev_sectors / 2 != info->size)
+		cnt++;
+	if (mddev->raid_disks != info->raid_disks)
+		cnt++;
+	if (mddev->layout != info->layout)
+		cnt++;
+	if ((state ^ info->state) & (1<<MD_SB_BITMAP_PRESENT))
+		cnt++;
+	if (cnt == 0)
+		return 0;
+	if (cnt > 1)
+		return -EINVAL;
 
 	if (mddev->layout != info->layout) {
 		/* Change layout
@@ -4904,7 +5204,7 @@ static int update_array_info(mddev_t *mddev, mdu_array_info_t *info)
 		else
 			return mddev->pers->reconfig(mddev, info->layout, -1);
 	}
-	if (info->size >= 0 && mddev->size != info->size)
+	if (info->size >= 0 && mddev->dev_sectors / 2 != info->size)
 		rv = update_size(mddev, (sector_t)info->size * 2);
 
 	if (mddev->raid_disks    != info->raid_disks)
@@ -5331,6 +5631,8 @@ mdk_thread_t *md_register_thread(void (*run) (mddev_t *), mddev_t *mddev,
 
 void md_unregister_thread(mdk_thread_t *thread)
 {
+	if (!thread)
+		return;
 	dprintk("interrupting MD-thread pid %d\n", task_pid_nr(thread->tsk));
 
 	kthread_stop(thread->tsk);
@@ -5404,7 +5706,7 @@ static void status_resync(struct seq_file *seq, mddev_t * mddev)
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
 		max_blocks = mddev->resync_max_sectors >> 1;
 	else
-		max_blocks = mddev->size;
+		max_blocks = mddev->dev_sectors / 2;
 
 	/*
 	 * Should not happen.
@@ -5537,7 +5839,7 @@ struct mdstat_info {
 static int md_seq_show(struct seq_file *seq, void *v)
 {
 	mddev_t *mddev = v;
-	sector_t size;
+	sector_t sectors;
 	mdk_rdev_t *rdev;
 	struct mdstat_info *mi = seq->private;
 	struct bitmap *bitmap;
@@ -5573,7 +5875,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 			seq_printf(seq, " %s", mddev->pers->name);
 		}
 
-		size = 0;
+		sectors = 0;
 		list_for_each_entry(rdev, &mddev->disks, same_set) {
 			char b[BDEVNAME_SIZE];
 			seq_printf(seq, " %s[%d]",
@@ -5585,7 +5887,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 				continue;
 			} else if (rdev->raid_disk < 0)
 				seq_printf(seq, "(S)"); /* spare */
-			size += rdev->size;
+			sectors += rdev->sectors;
 		}
 
 		if (!list_empty(&mddev->disks)) {
@@ -5595,7 +5897,7 @@ static int md_seq_show(struct seq_file *seq, void *v)
 					   mddev->array_sectors / 2);
 			else
 				seq_printf(seq, "\n      %llu blocks",
-					   (unsigned long long)size);
+					   (unsigned long long)sectors / 2);
 		}
 		if (mddev->persistent) {
 			if (mddev->major_version != 0 ||
@@ -5722,19 +6024,19 @@ int unregister_md_personality(struct mdk_personality *p)
 	return 0;
 }
 
-static int is_mddev_idle(mddev_t *mddev)
+static int is_mddev_idle(mddev_t *mddev, int init)
 {
 	mdk_rdev_t * rdev;
 	int idle;
-	long curr_events;
+	int curr_events;
 
 	idle = 1;
 	rcu_read_lock();
 	rdev_for_each_rcu(rdev, mddev) {
 		struct gendisk *disk = rdev->bdev->bd_contains->bd_disk;
-		curr_events = part_stat_read(&disk->part0, sectors[0]) +
-				part_stat_read(&disk->part0, sectors[1]) -
-				atomic_read(&disk->sync_io);
+		curr_events = (int)part_stat_read(&disk->part0, sectors[0]) +
+			      (int)part_stat_read(&disk->part0, sectors[1]) -
+			      atomic_read(&disk->sync_io);
 		/* sync IO will cause sync_io to increase before the disk_stats
 		 * as sync_io is counted when a request starts, and
 		 * disk_stats is counted when it completes.
@@ -5757,7 +6059,7 @@ static int is_mddev_idle(mddev_t *mddev)
 		 * always make curr_events less than last_events.
 		 *
 		 */
-		if (curr_events - rdev->last_events > 4096) {
+		if (init || curr_events - rdev->last_events > 64) {
 			rdev->last_events = curr_events;
 			idle = 0;
 		}
@@ -5980,10 +6282,10 @@ void md_do_sync(mddev_t *mddev)
 			j = mddev->recovery_cp;
 
 	} else if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery))
-		max_sectors = mddev->size << 1;
+		max_sectors = mddev->dev_sectors;
 	else {
 		/* recovery follows the physical size of devices */
-		max_sectors = mddev->size << 1;
+		max_sectors = mddev->dev_sectors;
 		j = MaxSector;
 		list_for_each_entry(rdev, &mddev->disks, same_set)
 			if (rdev->raid_disk >= 0 &&
@@ -6000,7 +6302,7 @@ void md_do_sync(mddev_t *mddev)
 	       "(but not more than %d KB/sec) for %s.\n",
 	       speed_max(mddev), desc);
 
-	is_mddev_idle(mddev); /* this also initializes IO event counters */
+	is_mddev_idle(mddev, 1); /* this initializes IO event counters */
 
 	io_sectors = 0;
 	for (m = 0; m < SYNC_MARKS; m++) {
@@ -6040,6 +6342,18 @@ void md_do_sync(mddev_t *mddev)
 		}
 		if (kthread_should_stop())
 			goto interrupted;
+
+		if (mddev->curr_resync > mddev->curr_resync_completed &&
+		    (mddev->curr_resync - mddev->curr_resync_completed)
+		    > (max_sectors >> 4)) {
+			/* time to update curr_resync_completed */
+			blk_unplug(mddev->queue);
+			wait_event(mddev->recovery_wait,
+				   atomic_read(&mddev->recovery_active) == 0);
+			mddev->curr_resync_completed =
+				mddev->curr_resync;
+			set_bit(MD_CHANGE_CLEAN, &mddev->flags);
+		}
 		sectors = mddev->pers->sync_request(mddev, j, &skipped,
 						  currspeed < speed_min(mddev));
 		if (sectors == 0) {
@@ -6102,7 +6416,7 @@ void md_do_sync(mddev_t *mddev)
 
 		if (currspeed > speed_min(mddev)) {
 			if ((currspeed > speed_max(mddev)) ||
-					!is_mddev_idle(mddev)) {
+					!is_mddev_idle(mddev, 0)) {
 				msleep(500);
 				goto repeat;
 			}
@@ -6173,6 +6487,8 @@ static int remove_and_add_spares(mddev_t *mddev)
 	mdk_rdev_t *rdev;
 	int spares = 0;
 
+	mddev->curr_resync_completed = 0;
+
 	list_for_each_entry(rdev, &mddev->disks, same_set)
 		if (rdev->raid_disk >= 0 &&
 		    !test_bit(Blocked, &rdev->flags) &&
@@ -6327,6 +6643,9 @@ void md_check_recovery(mddev_t *mddev)
 					sysfs_notify(&mddev->kobj, NULL,
 						     "degraded");
 			}
+			if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery) &&
+			    mddev->pers->finish_reshape)
+				mddev->pers->finish_reshape(mddev);
 			md_update_sb(mddev, 1);
 
 			/* if array is no-longer degraded, then any saved_raid_disk
@@ -6470,13 +6789,13 @@ static void md_geninit(void)
 
 static int __init md_init(void)
 {
-	if (register_blkdev(MAJOR_NR, "md"))
+	if (register_blkdev(MD_MAJOR, "md"))
 		return -1;
 	if ((mdp_major=register_blkdev(0, "mdp"))<=0) {
-		unregister_blkdev(MAJOR_NR, "md");
+		unregister_blkdev(MD_MAJOR, "md");
 		return -1;
 	}
-	blk_register_region(MKDEV(MAJOR_NR, 0), 1UL<<MINORBITS, THIS_MODULE,
+	blk_register_region(MKDEV(MD_MAJOR, 0), 1UL<<MINORBITS, THIS_MODULE,
 			    md_probe, NULL, NULL);
 	blk_register_region(MKDEV(mdp_major, 0), 1UL<<MINORBITS, THIS_MODULE,
 			    md_probe, NULL, NULL);
@@ -6562,10 +6881,10 @@ static __exit void md_exit(void)
 	mddev_t *mddev;
 	struct list_head *tmp;
 
-	blk_unregister_region(MKDEV(MAJOR_NR,0), 1U << MINORBITS);
+	blk_unregister_region(MKDEV(MD_MAJOR,0), 1U << MINORBITS);
 	blk_unregister_region(MKDEV(mdp_major,0), 1U << MINORBITS);
 
-	unregister_blkdev(MAJOR_NR,"md");
+	unregister_blkdev(MD_MAJOR,"md");
 	unregister_blkdev(mdp_major, "mdp");
 	unregister_reboot_notifier(&md_notifier);
 	unregister_sysctl_table(raid_table_header);
diff --git a/include/linux/raid/md_k.h b/drivers/md/md.h
index 9743e4dbc918..e9b7f54c24d6 100644
--- a/include/linux/raid/md_k.h
+++ b/drivers/md/md.h
@@ -15,21 +15,8 @@
 #ifndef _MD_K_H
 #define _MD_K_H
 
-/* and dm-bio-list.h is not under include/linux because.... ??? */
-#include "../../../drivers/md/dm-bio-list.h"
-
 #ifdef CONFIG_BLOCK
 
-#define	LEVEL_MULTIPATH		(-4)
-#define	LEVEL_LINEAR		(-1)
-#define	LEVEL_FAULTY		(-5)
-
-/* we need a value for 'no level specified' and 0
- * means 'raid0', so we need something else.  This is
- * for internal use only
- */
-#define	LEVEL_NONE		(-1000000)
-
 #define MaxSector (~(sector_t)0)
 
 typedef struct mddev_s mddev_t;
@@ -49,9 +36,9 @@ struct mdk_rdev_s
 {
 	struct list_head same_set;	/* RAID devices within the same set */
 
-	sector_t size;			/* Device size (in blocks) */
+	sector_t sectors;		/* Device size (in 512bytes sectors) */
 	mddev_t *mddev;			/* RAID array if running */
-	long last_events;		/* IO event timestamp */
+	int last_events;		/* IO event timestamp */
 
 	struct block_device *bdev;	/* block device handle */
 
@@ -132,6 +119,8 @@ struct mddev_s
 #define MD_CHANGE_CLEAN 1	/* transition to or from 'clean' */
 #define MD_CHANGE_PENDING 2	/* superblock update in progress */
 
+	int				suspended;
+	atomic_t			active_io;
 	int				ro;
 
 	struct gendisk			*gendisk;
@@ -155,8 +144,11 @@ struct mddev_s
 	char				clevel[16];
 	int				raid_disks;
 	int				max_disks;
-	sector_t			size; /* used size of component devices */
+	sector_t			dev_sectors; 	/* used size of
+							 * component devices */
 	sector_t			array_sectors; /* exported array size */
+	int				external_size; /* size managed
+							* externally */
 	__u64				events;
 
 	char				uuid[16];
@@ -172,6 +164,13 @@ struct mddev_s
 	struct mdk_thread_s		*thread;	/* management thread */
 	struct mdk_thread_s		*sync_thread;	/* doing resync or reconstruct */
 	sector_t			curr_resync;	/* last block scheduled */
+	/* As resync requests can complete out of order, we cannot easily track
+	 * how much resync has been completed.  So we occasionally pause until
+	 * everything completes, then set curr_resync_completed to curr_resync.
+	 * As such it may be well behind the real resync mark, but it is a value
+	 * we are certain of.
+	 */
+	sector_t			curr_resync_completed;
 	unsigned long			resync_mark;	/* a recent timestamp */
 	sector_t			resync_mark_cnt;/* blocks written at resync_mark */
 	sector_t			curr_mark_cnt; /* blocks scheduled now */
@@ -315,8 +314,10 @@ struct mdk_personality
 	int (*spare_active) (mddev_t *mddev);
 	sector_t (*sync_request)(mddev_t *mddev, sector_t sector_nr, int *skipped, int go_faster);
 	int (*resize) (mddev_t *mddev, sector_t sectors);
+	sector_t (*size) (mddev_t *mddev, sector_t sectors, int raid_disks);
 	int (*check_reshape) (mddev_t *mddev);
 	int (*start_reshape) (mddev_t *mddev);
+	void (*finish_reshape) (mddev_t *mddev);
 	int (*reconfig) (mddev_t *mddev, int layout, int chunk_size);
 	/* quiesce moves between quiescence states
 	 * 0 - fully active
@@ -324,6 +325,16 @@ struct mdk_personality
 	 * others - reserved
 	 */
 	void (*quiesce) (mddev_t *mddev, int state);
+	/* takeover is used to transition an array from one
+	 * personality to another.  The new personality must be able
+	 * to handle the data in the current layout.
+	 * e.g. 2drive raid1 -> 2drive raid5
+	 *      ndrive raid5 -> degraded n+1drive raid6 with special layout
+	 * If the takeover succeeds, a new 'private' structure is returned.
+	 * This needs to be installed and then ->run used to activate the
+	 * array.
+	 */
+	void *(*takeover) (mddev_t *mddev);
 };
 
 
@@ -400,3 +411,26 @@ static inline void safe_put_page(struct page *p)
 #endif /* CONFIG_BLOCK */
 #endif
 
+
+extern int register_md_personality(struct mdk_personality *p);
+extern int unregister_md_personality(struct mdk_personality *p);
+extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev),
+				mddev_t *mddev, const char *name);
+extern void md_unregister_thread(mdk_thread_t *thread);
+extern void md_wakeup_thread(mdk_thread_t *thread);
+extern void md_check_recovery(mddev_t *mddev);
+extern void md_write_start(mddev_t *mddev, struct bio *bi);
+extern void md_write_end(mddev_t *mddev);
+extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
+extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
+
+extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
+			   sector_t sector, int size, struct page *page);
+extern void md_super_wait(mddev_t *mddev);
+extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
+			struct page *page, int rw);
+extern void md_do_sync(mddev_t *mddev);
+extern void md_new_event(mddev_t *mddev);
+extern int md_allow_write(mddev_t *mddev);
+extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
+extern void md_set_array_sectors(mddev_t *mddev, sector_t array_sectors);
diff --git a/drivers/md/mktables.c b/drivers/md/mktables.c
index b61d5767aae7..3b1500843bba 100644
--- a/drivers/md/mktables.c
+++ b/drivers/md/mktables.c
@@ -59,7 +59,7 @@ int main(int argc, char *argv[])
 	uint8_t v;
 	uint8_t exptbl[256], invtbl[256];
 
-	printf("#include \"raid6.h\"\n");
+	printf("#include <linux/raid/pq.h>\n");
 
 	/* Compute multiplication table */
 	printf("\nconst u8  __attribute__((aligned(256)))\n"
@@ -76,6 +76,9 @@ int main(int argc, char *argv[])
 		printf("\t},\n");
 	}
 	printf("};\n");
+	printf("#ifdef __KERNEL__\n");
+	printf("EXPORT_SYMBOL(raid6_gfmul);\n");
+	printf("#endif\n");
 
 	/* Compute power-of-2 table (exponent) */
 	v = 1;
@@ -92,6 +95,9 @@ int main(int argc, char *argv[])
 		}
 	}
 	printf("};\n");
+	printf("#ifdef __KERNEL__\n");
+	printf("EXPORT_SYMBOL(raid6_gfexp);\n");
+	printf("#endif\n");
 
 	/* Compute inverse table x^-1 == x^254 */
 	printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -104,6 +110,9 @@ int main(int argc, char *argv[])
 		}
 	}
 	printf("};\n");
+	printf("#ifdef __KERNEL__\n");
+	printf("EXPORT_SYMBOL(raid6_gfinv);\n");
+	printf("#endif\n");
 
 	/* Compute inv(2^x + 1) (exponent-xor-inverse) table */
 	printf("\nconst u8 __attribute__((aligned(256)))\n"
@@ -115,6 +124,9 @@ int main(int argc, char *argv[])
 			       (j == 7) ? '\n' : ' ');
 	}
 	printf("};\n");
+	printf("#ifdef __KERNEL__\n");
+	printf("EXPORT_SYMBOL(raid6_gfexi);\n");
+	printf("#endif\n");
 
 	return 0;
 }
diff --git a/drivers/md/multipath.c b/drivers/md/multipath.c
index f6d08f241671..41ced0cbe823 100644
--- a/drivers/md/multipath.c
+++ b/drivers/md/multipath.c
@@ -19,7 +19,11 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include <linux/raid/multipath.h>
+#include <linux/blkdev.h>
+#include <linux/raid/md_u.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "multipath.h"
 
 #define MAX_WORK_PER_DISK 128
 
@@ -402,6 +406,14 @@ static void multipathd (mddev_t *mddev)
 	spin_unlock_irqrestore(&conf->device_lock, flags);
 }
 
+static sector_t multipath_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+
+	return mddev->dev_sectors;
+}
+
 static int multipath_run (mddev_t *mddev)
 {
 	multipath_conf_t *conf;
@@ -498,7 +510,7 @@ static int multipath_run (mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_sectors = mddev->size * 2;
+	md_set_array_sectors(mddev, multipath_size(mddev, 0, 0));
 
 	mddev->queue->unplug_fn = multipath_unplug;
 	mddev->queue->backing_dev_info.congested_fn = multipath_congested;
@@ -543,6 +555,7 @@ static struct mdk_personality multipath_personality =
 	.error_handler	= multipath_error,
 	.hot_add_disk	= multipath_add_disk,
 	.hot_remove_disk= multipath_remove_disk,
+	.size		= multipath_size,
 };
 
 static int __init multipath_init (void)
diff --git a/include/linux/raid/multipath.h b/drivers/md/multipath.h
index 6f53fc177a47..6fa70b400cda 100644
--- a/include/linux/raid/multipath.h
+++ b/drivers/md/multipath.h
@@ -1,8 +1,6 @@
 #ifndef _MULTIPATH_H
 #define _MULTIPATH_H
 
-#include <linux/raid/md.h>
-
 struct multipath_info {
 	mdk_rdev_t	*rdev;
 };
diff --git a/drivers/md/raid0.c b/drivers/md/raid0.c
index c605ba805586..c08d7559be55 100644
--- a/drivers/md/raid0.c
+++ b/drivers/md/raid0.c
@@ -18,7 +18,10 @@
    Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
 */
 
-#include <linux/raid/raid0.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid0.h"
 
 static void raid0_unplug(struct request_queue *q)
 {
@@ -73,16 +76,15 @@ static int create_strip_zones (mddev_t *mddev)
 		list_for_each_entry(rdev2, &mddev->disks, same_set) {
 			printk(KERN_INFO "raid0:   comparing %s(%llu)",
 			       bdevname(rdev1->bdev,b),
-			       (unsigned long long)rdev1->size);
+			       (unsigned long long)rdev1->sectors);
 			printk(KERN_INFO " with %s(%llu)\n",
 			       bdevname(rdev2->bdev,b),
-			       (unsigned long long)rdev2->size);
+			       (unsigned long long)rdev2->sectors);
 			if (rdev2 == rdev1) {
 				printk(KERN_INFO "raid0:   END\n");
 				break;
 			}
-			if (rdev2->size == rdev1->size)
-			{
+			if (rdev2->sectors == rdev1->sectors) {
 				/*
 				 * Not unique, don't count it as a new
 				 * group
@@ -145,7 +147,7 @@ static int create_strip_zones (mddev_t *mddev)
 		    mddev->queue->max_sectors > (PAGE_SIZE>>9))
 			blk_queue_max_sectors(mddev->queue, PAGE_SIZE>>9);
 
-		if (!smallest || (rdev1->size <smallest->size))
+		if (!smallest || (rdev1->sectors < smallest->sectors))
 			smallest = rdev1;
 		cnt++;
 	}
@@ -155,10 +157,10 @@ static int create_strip_zones (mddev_t *mddev)
 		goto abort;
 	}
 	zone->nb_dev = cnt;
-	zone->sectors = smallest->size * cnt * 2;
+	zone->sectors = smallest->sectors * cnt;
 	zone->zone_start = 0;
 
-	current_start = smallest->size * 2;
+	current_start = smallest->sectors;
 	curr_zone_start = zone->sectors;
 
 	/* now do the other zones */
@@ -177,29 +179,29 @@ static int create_strip_zones (mddev_t *mddev)
 			rdev = conf->strip_zone[0].dev[j];
 			printk(KERN_INFO "raid0: checking %s ...",
 				bdevname(rdev->bdev, b));
-			if (rdev->size > current_start / 2) {
-				printk(KERN_INFO " contained as device %d\n",
-					c);
-				zone->dev[c] = rdev;
-				c++;
-				if (!smallest || (rdev->size <smallest->size)) {
-					smallest = rdev;
-					printk(KERN_INFO "  (%llu) is smallest!.\n",
-						(unsigned long long)rdev->size);
-				}
-			} else
+			if (rdev->sectors <= current_start) {
 				printk(KERN_INFO " nope.\n");
+				continue;
+			}
+			printk(KERN_INFO " contained as device %d\n", c);
+			zone->dev[c] = rdev;
+			c++;
+			if (!smallest || rdev->sectors < smallest->sectors) {
+				smallest = rdev;
+				printk(KERN_INFO "  (%llu) is smallest!.\n",
+					(unsigned long long)rdev->sectors);
+			}
 		}
 
 		zone->nb_dev = c;
-		zone->sectors = (smallest->size * 2 - current_start) * c;
+		zone->sectors = (smallest->sectors - current_start) * c;
 		printk(KERN_INFO "raid0: zone->nb_dev: %d, sectors: %llu\n",
 			zone->nb_dev, (unsigned long long)zone->sectors);
 
 		zone->zone_start = curr_zone_start;
 		curr_zone_start += zone->sectors;
 
-		current_start = smallest->size * 2;
+		current_start = smallest->sectors;
 		printk(KERN_INFO "raid0: current zone start: %llu\n",
 			(unsigned long long)current_start);
 	}
@@ -261,12 +263,25 @@ static int raid0_mergeable_bvec(struct request_queue *q,
 		return max;
 }
 
+static sector_t raid0_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	sector_t array_sectors = 0;
+	mdk_rdev_t *rdev;
+
+	WARN_ONCE(sectors || raid_disks,
+		  "%s does not support generic reshape\n", __func__);
+
+	list_for_each_entry(rdev, &mddev->disks, same_set)
+		array_sectors += rdev->sectors;
+
+	return array_sectors;
+}
+
 static int raid0_run (mddev_t *mddev)
 {
 	unsigned  cur=0, i=0, nb_zone;
 	s64 sectors;
 	raid0_conf_t *conf;
-	mdk_rdev_t *rdev;
 
 	if (mddev->chunk_size == 0) {
 		printk(KERN_ERR "md/raid0: non-zero chunk size required.\n");
@@ -291,16 +306,14 @@ static int raid0_run (mddev_t *mddev)
 		goto out_free_conf;
 
 	/* calculate array device size */
-	mddev->array_sectors = 0;
-	list_for_each_entry(rdev, &mddev->disks, same_set)
-		mddev->array_sectors += rdev->size * 2;
+	md_set_array_sectors(mddev, raid0_size(mddev, 0, 0));
 
 	printk(KERN_INFO "raid0 : md_size is %llu sectors.\n",
 		(unsigned long long)mddev->array_sectors);
 	printk(KERN_INFO "raid0 : conf->spacing is %llu sectors.\n",
 		(unsigned long long)conf->spacing);
 	{
-		sector_t s = mddev->array_sectors;
+		sector_t s = raid0_size(mddev, 0, 0);
 		sector_t space = conf->spacing;
 		int round;
 		conf->sector_shift = 0;
@@ -509,6 +522,7 @@ static struct mdk_personality raid0_personality=
 	.run		= raid0_run,
 	.stop		= raid0_stop,
 	.status		= raid0_status,
+	.size		= raid0_size,
 };
 
 static int __init raid0_init (void)
diff --git a/include/linux/raid/raid0.h b/drivers/md/raid0.h
index fd42aa87c391..824b12eb1d4f 100644
--- a/include/linux/raid/raid0.h
+++ b/drivers/md/raid0.h
@@ -1,8 +1,6 @@
 #ifndef _RAID0_H
 #define _RAID0_H
 
-#include <linux/raid/md.h>
-
 struct strip_zone
 {
 	sector_t zone_start;	/* Zone offset in md_dev (in sectors) */
diff --git a/drivers/md/raid1.c b/drivers/md/raid1.c
index e2466425d9ca..b4f4badc0068 100644
--- a/drivers/md/raid1.c
+++ b/drivers/md/raid1.c
@@ -31,10 +31,13 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include "dm-bio-list.h"
 #include <linux/delay.h>
-#include <linux/raid/raid1.h>
-#include <linux/raid/bitmap.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "dm-bio-list.h"
+#include "raid1.h"
+#include "bitmap.h"
 
 #define DEBUG 0
 #if DEBUG
@@ -1723,7 +1726,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			return 0;
 	}
 
-	max_sector = mddev->size << 1;
+	max_sector = mddev->dev_sectors;
 	if (sector_nr >= max_sector) {
 		/* If we aborted, we need to abort the
 		 * sync on the 'current' bitmap chunk (there will
@@ -1919,6 +1922,14 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	return nr_sectors;
 }
 
+static sector_t raid1_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	if (sectors)
+		return sectors;
+
+	return mddev->dev_sectors;
+}
+
 static int run(mddev_t *mddev)
 {
 	conf_t *conf;
@@ -2048,7 +2059,7 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_sectors = mddev->size * 2;
+	md_set_array_sectors(mddev, raid1_size(mddev, 0, 0));
 
 	mddev->queue->unplug_fn = raid1_unplug;
 	mddev->queue->backing_dev_info.congested_fn = raid1_congested;
@@ -2089,6 +2100,9 @@ static int stop(mddev_t *mddev)
 		/* need to kick something here to make sure I/O goes? */
 	}
 
+	raise_barrier(conf);
+	lower_barrier(conf);
+
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
@@ -2110,15 +2124,17 @@ static int raid1_resize(mddev_t *mddev, sector_t sectors)
 	 * any io in the removed space completes, but it hardly seems
 	 * worth it.
 	 */
-	mddev->array_sectors = sectors;
+	md_set_array_sectors(mddev, raid1_size(mddev, sectors, 0));
+	if (mddev->array_sectors > raid1_size(mddev, sectors, 0))
+		return -EINVAL;
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
-	if (mddev->array_sectors / 2 > mddev->size &&
+	if (sectors > mddev->dev_sectors &&
 	    mddev->recovery_cp == MaxSector) {
-		mddev->recovery_cp = mddev->size << 1;
+		mddev->recovery_cp = mddev->dev_sectors;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
-	mddev->size = mddev->array_sectors / 2;
+	mddev->dev_sectors = sectors;
 	mddev->resync_max_sectors = sectors;
 	return 0;
 }
@@ -2264,6 +2280,7 @@ static struct mdk_personality raid1_personality =
 	.spare_active	= raid1_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid1_resize,
+	.size		= raid1_size,
 	.check_reshape	= raid1_reshape,
 	.quiesce	= raid1_quiesce,
 };
diff --git a/include/linux/raid/raid1.h b/drivers/md/raid1.h
index 0a9ba7c3302e..1620eea3d57c 100644
--- a/include/linux/raid/raid1.h
+++ b/drivers/md/raid1.h
@@ -1,8 +1,6 @@
 #ifndef _RAID1_H
 #define _RAID1_H
 
-#include <linux/raid/md.h>
-
 typedef struct mirror_info mirror_info_t;
 
 struct mirror_info {
diff --git a/drivers/md/raid10.c b/drivers/md/raid10.c
index 7301631abe04..e293d92641ac 100644
--- a/drivers/md/raid10.c
+++ b/drivers/md/raid10.c
@@ -18,10 +18,13 @@
  * Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
  */
 
-#include "dm-bio-list.h"
 #include <linux/delay.h>
-#include <linux/raid/raid10.h>
-#include <linux/raid/bitmap.h>
+#include <linux/blkdev.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "dm-bio-list.h"
+#include "raid10.h"
+#include "bitmap.h"
 
 /*
  * RAID10 provides a combination of RAID0 and RAID1 functionality.
@@ -1695,7 +1698,7 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 			return 0;
 
  skipped:
-	max_sector = mddev->size << 1;
+	max_sector = mddev->dev_sectors;
 	if (test_bit(MD_RECOVERY_SYNC, &mddev->recovery))
 		max_sector = mddev->resync_max_sectors;
 	if (sector_nr >= max_sector) {
@@ -2020,6 +2023,25 @@ static sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *skipped, i
 	goto skipped;
 }
 
+static sector_t
+raid10_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	sector_t size;
+	conf_t *conf = mddev_to_conf(mddev);
+
+	if (!raid_disks)
+		raid_disks = mddev->raid_disks;
+	if (!sectors)
+		sectors = mddev->dev_sectors;
+
+	size = sectors >> conf->chunk_shift;
+	sector_div(size, conf->far_copies);
+	size = size * raid_disks;
+	sector_div(size, conf->near_copies);
+
+	return size << conf->chunk_shift;
+}
+
 static int run(mddev_t *mddev)
 {
 	conf_t *conf;
@@ -2076,7 +2098,7 @@ static int run(mddev_t *mddev)
 	conf->far_offset = fo;
 	conf->chunk_mask = (sector_t)(mddev->chunk_size>>9)-1;
 	conf->chunk_shift = ffz(~mddev->chunk_size) - 9;
-	size = mddev->size >> (conf->chunk_shift-1);
+	size = mddev->dev_sectors >> conf->chunk_shift;
 	sector_div(size, fc);
 	size = size * conf->raid_disks;
 	sector_div(size, nc);
@@ -2089,7 +2111,7 @@ static int run(mddev_t *mddev)
 	 */
 	stride += conf->raid_disks - 1;
 	sector_div(stride, conf->raid_disks);
-	mddev->size = stride  << (conf->chunk_shift-1);
+	mddev->dev_sectors = stride << conf->chunk_shift;
 
 	if (fo)
 		stride = 1;
@@ -2171,8 +2193,8 @@ static int run(mddev_t *mddev)
 	/*
 	 * Ok, everything is just fine now
 	 */
-	mddev->array_sectors = size << conf->chunk_shift;
-	mddev->resync_max_sectors = size << conf->chunk_shift;
+	md_set_array_sectors(mddev, raid10_size(mddev, 0, 0));
+	mddev->resync_max_sectors = raid10_size(mddev, 0, 0);
 
 	mddev->queue->unplug_fn = raid10_unplug;
 	mddev->queue->backing_dev_info.congested_fn = raid10_congested;
@@ -2208,6 +2230,9 @@ static int stop(mddev_t *mddev)
 {
 	conf_t *conf = mddev_to_conf(mddev);
 
+	raise_barrier(conf, 0);
+	lower_barrier(conf);
+
 	md_unregister_thread(mddev->thread);
 	mddev->thread = NULL;
 	blk_sync_queue(mddev->queue); /* the unplug fn references 'conf'*/
@@ -2255,6 +2280,7 @@ static struct mdk_personality raid10_personality =
 	.spare_active	= raid10_spare_active,
 	.sync_request	= sync_request,
 	.quiesce	= raid10_quiesce,
+	.size		= raid10_size,
 };
 
 static int __init raid_init(void)
diff --git a/include/linux/raid/raid10.h b/drivers/md/raid10.h
index e9091cfeb286..244dbe507a54 100644
--- a/include/linux/raid/raid10.h
+++ b/drivers/md/raid10.h
@@ -1,8 +1,6 @@
 #ifndef _RAID10_H
 #define _RAID10_H
 
-#include <linux/raid/md.h>
-
 typedef struct mirror_info mirror_info_t;
 
 struct mirror_info {
diff --git a/drivers/md/raid5.c b/drivers/md/raid5.c
index a5ba080d303b..3bbc6d647044 100644
--- a/drivers/md/raid5.c
+++ b/drivers/md/raid5.c
@@ -43,11 +43,14 @@
  * miss any bits.
  */
 
+#include <linux/blkdev.h>
 #include <linux/kthread.h>
-#include "raid6.h"
-
-#include <linux/raid/bitmap.h>
+#include <linux/raid/pq.h>
 #include <linux/async_tx.h>
+#include <linux/seq_file.h>
+#include "md.h"
+#include "raid5.h"
+#include "bitmap.h"
 
 /*
  * Stripe cache
@@ -91,11 +94,6 @@
 
 #define printk_rl(args...) ((void) (printk_ratelimit() && printk(args)))
 
-#if !RAID6_USE_EMPTY_ZERO_PAGE
-/* In .bss so it's zeroed */
-const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
-#endif
-
 /*
  * We maintain a biased count of active stripes in the bottom 16 bits of
  * bi_phys_segments, and a count of processed stripes in the upper 16 bits
@@ -130,12 +128,42 @@ static inline void raid5_set_bi_hw_segments(struct bio *bio, unsigned int cnt)
 	bio->bi_phys_segments = raid5_bi_phys_segments(bio) || (cnt << 16);
 }
 
+/* Find first data disk in a raid6 stripe */
+static inline int raid6_d0(struct stripe_head *sh)
+{
+	if (sh->ddf_layout)
+		/* ddf always start from first device */
+		return 0;
+	/* md starts just after Q block */
+	if (sh->qd_idx == sh->disks - 1)
+		return 0;
+	else
+		return sh->qd_idx + 1;
+}
 static inline int raid6_next_disk(int disk, int raid_disks)
 {
 	disk++;
 	return (disk < raid_disks) ? disk : 0;
 }
 
+/* When walking through the disks in a raid5, starting at raid6_d0,
+ * We need to map each disk to a 'slot', where the data disks are slot
+ * 0 .. raid_disks-3, the parity disk is raid_disks-2 and the Q disk
+ * is raid_disks-1.  This help does that mapping.
+ */
+static int raid6_idx_to_slot(int idx, struct stripe_head *sh,
+			     int *count, int syndrome_disks)
+{
+	int slot;
+
+	if (idx == sh->pd_idx)
+		return syndrome_disks;
+	if (idx == sh->qd_idx)
+		return syndrome_disks + 1;
+	slot = (*count)++;
+	return slot;
+}
+
 static void return_io(struct bio *return_bi)
 {
 	struct bio *bi = return_bi;
@@ -193,6 +221,7 @@ static void __release_stripe(raid5_conf_t *conf, struct stripe_head *sh)
 		}
 	}
 }
+
 static void release_stripe(struct stripe_head *sh)
 {
 	raid5_conf_t *conf = sh->raid_conf;
@@ -270,9 +299,11 @@ static int grow_buffers(struct stripe_head *sh, int num)
 	return 0;
 }
 
-static void raid5_build_block(struct stripe_head *sh, int i);
+static void raid5_build_block(struct stripe_head *sh, int i, int previous);
+static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
+			    struct stripe_head *sh);
 
-static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int disks)
+static void init_stripe(struct stripe_head *sh, sector_t sector, int previous)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int i;
@@ -287,11 +318,12 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int
 
 	remove_hash(sh);
 
+	sh->generation = conf->generation - previous;
+	sh->disks = previous ? conf->previous_raid_disks : conf->raid_disks;
 	sh->sector = sector;
-	sh->pd_idx = pd_idx;
+	stripe_set_idx(sector, conf, previous, sh);
 	sh->state = 0;
 
-	sh->disks = disks;
 
 	for (i = sh->disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
@@ -305,12 +337,13 @@ static void init_stripe(struct stripe_head *sh, sector_t sector, int pd_idx, int
 			BUG();
 		}
 		dev->flags = 0;
-		raid5_build_block(sh, i);
+		raid5_build_block(sh, i, previous);
 	}
 	insert_hash(conf, sh);
 }
 
-static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, int disks)
+static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector,
+					 short generation)
 {
 	struct stripe_head *sh;
 	struct hlist_node *hn;
@@ -318,7 +351,7 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, in
 	CHECK_DEVLOCK();
 	pr_debug("__find_stripe, sector %llu\n", (unsigned long long)sector);
 	hlist_for_each_entry(sh, hn, stripe_hash(conf, sector), hash)
-		if (sh->sector == sector && sh->disks == disks)
+		if (sh->sector == sector && sh->generation == generation)
 			return sh;
 	pr_debug("__stripe %llu not in cache\n", (unsigned long long)sector);
 	return NULL;
@@ -327,8 +360,9 @@ static struct stripe_head *__find_stripe(raid5_conf_t *conf, sector_t sector, in
 static void unplug_slaves(mddev_t *mddev);
 static void raid5_unplug_device(struct request_queue *q);
 
-static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector, int disks,
-					     int pd_idx, int noblock)
+static struct stripe_head *
+get_active_stripe(raid5_conf_t *conf, sector_t sector,
+		  int previous, int noblock)
 {
 	struct stripe_head *sh;
 
@@ -340,7 +374,7 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector
 		wait_event_lock_irq(conf->wait_for_stripe,
 				    conf->quiesce == 0,
 				    conf->device_lock, /* nothing */);
-		sh = __find_stripe(conf, sector, disks);
+		sh = __find_stripe(conf, sector, conf->generation - previous);
 		if (!sh) {
 			if (!conf->inactive_blocked)
 				sh = get_free_stripe(conf);
@@ -358,10 +392,11 @@ static struct stripe_head *get_active_stripe(raid5_conf_t *conf, sector_t sector
 					);
 				conf->inactive_blocked = 0;
 			} else
-				init_stripe(sh, sector, pd_idx, disks);
+				init_stripe(sh, sector, previous);
 		} else {
 			if (atomic_read(&sh->count)) {
-			  BUG_ON(!list_empty(&sh->lru));
+				BUG_ON(!list_empty(&sh->lru)
+				    && !test_bit(STRIPE_EXPANDING, &sh->state));
 			} else {
 				if (!test_bit(STRIPE_HANDLE, &sh->state))
 					atomic_inc(&conf->active_stripes);
@@ -895,8 +930,10 @@ static int grow_stripes(raid5_conf_t *conf, int num)
 	struct kmem_cache *sc;
 	int devs = conf->raid_disks;
 
-	sprintf(conf->cache_name[0], "raid5-%s", mdname(conf->mddev));
-	sprintf(conf->cache_name[1], "raid5-%s-alt", mdname(conf->mddev));
+	sprintf(conf->cache_name[0],
+		"raid%d-%s", conf->level, mdname(conf->mddev));
+	sprintf(conf->cache_name[1],
+		"raid%d-%s-alt", conf->level, mdname(conf->mddev));
 	conf->active_name = 0;
 	sc = kmem_cache_create(conf->cache_name[conf->active_name],
 			       sizeof(struct stripe_head)+(devs-1)*sizeof(struct r5dev),
@@ -911,7 +948,6 @@ static int grow_stripes(raid5_conf_t *conf, int num)
 	return 0;
 }
 
-#ifdef CONFIG_MD_RAID5_RESHAPE
 static int resize_stripes(raid5_conf_t *conf, int newsize)
 {
 	/* Make all the stripes able to hold 'newsize' devices.
@@ -1036,7 +1072,6 @@ static int resize_stripes(raid5_conf_t *conf, int newsize)
 	conf->pool_size = newsize;
 	return err;
 }
-#endif
 
 static int drop_one_stripe(raid5_conf_t *conf)
 {
@@ -1066,7 +1101,7 @@ static void shrink_stripes(raid5_conf_t *conf)
 
 static void raid5_end_read_request(struct bio * bi, int error)
 {
- 	struct stripe_head *sh = bi->bi_private;
+	struct stripe_head *sh = bi->bi_private;
 	raid5_conf_t *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -1148,7 +1183,7 @@ static void raid5_end_read_request(struct bio * bi, int error)
 
 static void raid5_end_write_request(struct bio *bi, int error)
 {
- 	struct stripe_head *sh = bi->bi_private;
+	struct stripe_head *sh = bi->bi_private;
 	raid5_conf_t *conf = sh->raid_conf;
 	int disks = sh->disks, i;
 	int uptodate = test_bit(BIO_UPTODATE, &bi->bi_flags);
@@ -1176,9 +1211,9 @@ static void raid5_end_write_request(struct bio *bi, int error)
 }
 
 
-static sector_t compute_blocknr(struct stripe_head *sh, int i);
+static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous);
 	
-static void raid5_build_block(struct stripe_head *sh, int i)
+static void raid5_build_block(struct stripe_head *sh, int i, int previous)
 {
 	struct r5dev *dev = &sh->dev[i];
 
@@ -1194,7 +1229,7 @@ static void raid5_build_block(struct stripe_head *sh, int i)
 	dev->req.bi_private = sh;
 
 	dev->flags = 0;
-	dev->sector = compute_blocknr(sh, i);
+	dev->sector = compute_blocknr(sh, i, previous);
 }
 
 static void error(mddev_t *mddev, mdk_rdev_t *rdev)
@@ -1227,15 +1262,23 @@ static void error(mddev_t *mddev, mdk_rdev_t *rdev)
  * Input: a 'big' sector number,
  * Output: index of the data and parity disk, and the sector # in them.
  */
-static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
-			unsigned int data_disks, unsigned int * dd_idx,
-			unsigned int * pd_idx, raid5_conf_t *conf)
+static sector_t raid5_compute_sector(raid5_conf_t *conf, sector_t r_sector,
+				     int previous, int *dd_idx,
+				     struct stripe_head *sh)
 {
 	long stripe;
 	unsigned long chunk_number;
 	unsigned int chunk_offset;
+	int pd_idx, qd_idx;
+	int ddf_layout = 0;
 	sector_t new_sector;
-	int sectors_per_chunk = conf->chunk_size >> 9;
+	int algorithm = previous ? conf->prev_algo
+				 : conf->algorithm;
+	int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
+					 : (conf->chunk_size >> 9);
+	int raid_disks = previous ? conf->previous_raid_disks
+				  : conf->raid_disks;
+	int data_disks = raid_disks - conf->max_degraded;
 
 	/* First compute the information on this sector */
 
@@ -1259,68 +1302,170 @@ static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
 	/*
 	 * Select the parity disk based on the user selected algorithm.
 	 */
+	pd_idx = qd_idx = ~0;
 	switch(conf->level) {
 	case 4:
-		*pd_idx = data_disks;
+		pd_idx = data_disks;
 		break;
 	case 5:
-		switch (conf->algorithm) {
+		switch (algorithm) {
 		case ALGORITHM_LEFT_ASYMMETRIC:
-			*pd_idx = data_disks - stripe % raid_disks;
-			if (*dd_idx >= *pd_idx)
+			pd_idx = data_disks - stripe % raid_disks;
+			if (*dd_idx >= pd_idx)
 				(*dd_idx)++;
 			break;
 		case ALGORITHM_RIGHT_ASYMMETRIC:
-			*pd_idx = stripe % raid_disks;
-			if (*dd_idx >= *pd_idx)
+			pd_idx = stripe % raid_disks;
+			if (*dd_idx >= pd_idx)
 				(*dd_idx)++;
 			break;
 		case ALGORITHM_LEFT_SYMMETRIC:
-			*pd_idx = data_disks - stripe % raid_disks;
-			*dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
+			pd_idx = data_disks - stripe % raid_disks;
+			*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
 			break;
 		case ALGORITHM_RIGHT_SYMMETRIC:
-			*pd_idx = stripe % raid_disks;
-			*dd_idx = (*pd_idx + 1 + *dd_idx) % raid_disks;
+			pd_idx = stripe % raid_disks;
+			*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
+			break;
+		case ALGORITHM_PARITY_0:
+			pd_idx = 0;
+			(*dd_idx)++;
+			break;
+		case ALGORITHM_PARITY_N:
+			pd_idx = data_disks;
 			break;
 		default:
 			printk(KERN_ERR "raid5: unsupported algorithm %d\n",
-				conf->algorithm);
+				algorithm);
+			BUG();
 		}
 		break;
 	case 6:
 
-		/**** FIX THIS ****/
-		switch (conf->algorithm) {
+		switch (algorithm) {
 		case ALGORITHM_LEFT_ASYMMETRIC:
-			*pd_idx = raid_disks - 1 - (stripe % raid_disks);
-			if (*pd_idx == raid_disks-1)
-				(*dd_idx)++; 	/* Q D D D P */
-			else if (*dd_idx >= *pd_idx)
+			pd_idx = raid_disks - 1 - (stripe % raid_disks);
+			qd_idx = pd_idx + 1;
+			if (pd_idx == raid_disks-1) {
+				(*dd_idx)++;	/* Q D D D P */
+				qd_idx = 0;
+			} else if (*dd_idx >= pd_idx)
 				(*dd_idx) += 2; /* D D P Q D */
 			break;
 		case ALGORITHM_RIGHT_ASYMMETRIC:
-			*pd_idx = stripe % raid_disks;
-			if (*pd_idx == raid_disks-1)
-				(*dd_idx)++; 	/* Q D D D P */
-			else if (*dd_idx >= *pd_idx)
+			pd_idx = stripe % raid_disks;
+			qd_idx = pd_idx + 1;
+			if (pd_idx == raid_disks-1) {
+				(*dd_idx)++;	/* Q D D D P */
+				qd_idx = 0;
+			} else if (*dd_idx >= pd_idx)
 				(*dd_idx) += 2; /* D D P Q D */
 			break;
 		case ALGORITHM_LEFT_SYMMETRIC:
-			*pd_idx = raid_disks - 1 - (stripe % raid_disks);
-			*dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+			pd_idx = raid_disks - 1 - (stripe % raid_disks);
+			qd_idx = (pd_idx + 1) % raid_disks;
+			*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
 			break;
 		case ALGORITHM_RIGHT_SYMMETRIC:
-			*pd_idx = stripe % raid_disks;
-			*dd_idx = (*pd_idx + 2 + *dd_idx) % raid_disks;
+			pd_idx = stripe % raid_disks;
+			qd_idx = (pd_idx + 1) % raid_disks;
+			*dd_idx = (pd_idx + 2 + *dd_idx) % raid_disks;
+			break;
+
+		case ALGORITHM_PARITY_0:
+			pd_idx = 0;
+			qd_idx = 1;
+			(*dd_idx) += 2;
+			break;
+		case ALGORITHM_PARITY_N:
+			pd_idx = data_disks;
+			qd_idx = data_disks + 1;
 			break;
+
+		case ALGORITHM_ROTATING_ZERO_RESTART:
+			/* Exactly the same as RIGHT_ASYMMETRIC, but or
+			 * of blocks for computing Q is different.
+			 */
+			pd_idx = stripe % raid_disks;
+			qd_idx = pd_idx + 1;
+			if (pd_idx == raid_disks-1) {
+				(*dd_idx)++;	/* Q D D D P */
+				qd_idx = 0;
+			} else if (*dd_idx >= pd_idx)
+				(*dd_idx) += 2; /* D D P Q D */
+			ddf_layout = 1;
+			break;
+
+		case ALGORITHM_ROTATING_N_RESTART:
+			/* Same a left_asymmetric, by first stripe is
+			 * D D D P Q  rather than
+			 * Q D D D P
+			 */
+			pd_idx = raid_disks - 1 - ((stripe + 1) % raid_disks);
+			qd_idx = pd_idx + 1;
+			if (pd_idx == raid_disks-1) {
+				(*dd_idx)++;	/* Q D D D P */
+				qd_idx = 0;
+			} else if (*dd_idx >= pd_idx)
+				(*dd_idx) += 2; /* D D P Q D */
+			ddf_layout = 1;
+			break;
+
+		case ALGORITHM_ROTATING_N_CONTINUE:
+			/* Same as left_symmetric but Q is before P */
+			pd_idx = raid_disks - 1 - (stripe % raid_disks);
+			qd_idx = (pd_idx + raid_disks - 1) % raid_disks;
+			*dd_idx = (pd_idx + 1 + *dd_idx) % raid_disks;
+			ddf_layout = 1;
+			break;
+
+		case ALGORITHM_LEFT_ASYMMETRIC_6:
+			/* RAID5 left_asymmetric, with Q on last device */
+			pd_idx = data_disks - stripe % (raid_disks-1);
+			if (*dd_idx >= pd_idx)
+				(*dd_idx)++;
+			qd_idx = raid_disks - 1;
+			break;
+
+		case ALGORITHM_RIGHT_ASYMMETRIC_6:
+			pd_idx = stripe % (raid_disks-1);
+			if (*dd_idx >= pd_idx)
+				(*dd_idx)++;
+			qd_idx = raid_disks - 1;
+			break;
+
+		case ALGORITHM_LEFT_SYMMETRIC_6:
+			pd_idx = data_disks - stripe % (raid_disks-1);
+			*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
+			qd_idx = raid_disks - 1;
+			break;
+
+		case ALGORITHM_RIGHT_SYMMETRIC_6:
+			pd_idx = stripe % (raid_disks-1);
+			*dd_idx = (pd_idx + 1 + *dd_idx) % (raid_disks-1);
+			qd_idx = raid_disks - 1;
+			break;
+
+		case ALGORITHM_PARITY_0_6:
+			pd_idx = 0;
+			(*dd_idx)++;
+			qd_idx = raid_disks - 1;
+			break;
+
+
 		default:
 			printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
-			       conf->algorithm);
+			       algorithm);
+			BUG();
 		}
 		break;
 	}
 
+	if (sh) {
+		sh->pd_idx = pd_idx;
+		sh->qd_idx = qd_idx;
+		sh->ddf_layout = ddf_layout;
+	}
 	/*
 	 * Finally, compute the new sector number
 	 */
@@ -1329,17 +1474,21 @@ static sector_t raid5_compute_sector(sector_t r_sector, unsigned int raid_disks,
 }
 
 
-static sector_t compute_blocknr(struct stripe_head *sh, int i)
+static sector_t compute_blocknr(struct stripe_head *sh, int i, int previous)
 {
 	raid5_conf_t *conf = sh->raid_conf;
 	int raid_disks = sh->disks;
 	int data_disks = raid_disks - conf->max_degraded;
 	sector_t new_sector = sh->sector, check;
-	int sectors_per_chunk = conf->chunk_size >> 9;
+	int sectors_per_chunk = previous ? (conf->prev_chunk >> 9)
+					 : (conf->chunk_size >> 9);
+	int algorithm = previous ? conf->prev_algo
+				 : conf->algorithm;
 	sector_t stripe;
 	int chunk_offset;
-	int chunk_number, dummy1, dummy2, dd_idx = i;
+	int chunk_number, dummy1, dd_idx = i;
 	sector_t r_sector;
+	struct stripe_head sh2;
 
 
 	chunk_offset = sector_div(new_sector, sectors_per_chunk);
@@ -1351,7 +1500,7 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i)
 	switch(conf->level) {
 	case 4: break;
 	case 5:
-		switch (conf->algorithm) {
+		switch (algorithm) {
 		case ALGORITHM_LEFT_ASYMMETRIC:
 		case ALGORITHM_RIGHT_ASYMMETRIC:
 			if (i > sh->pd_idx)
@@ -1363,19 +1512,27 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i)
 				i += raid_disks;
 			i -= (sh->pd_idx + 1);
 			break;
+		case ALGORITHM_PARITY_0:
+			i -= 1;
+			break;
+		case ALGORITHM_PARITY_N:
+			break;
 		default:
 			printk(KERN_ERR "raid5: unsupported algorithm %d\n",
-			       conf->algorithm);
+			       algorithm);
+			BUG();
 		}
 		break;
 	case 6:
-		if (i == raid6_next_disk(sh->pd_idx, raid_disks))
+		if (i == sh->qd_idx)
 			return 0; /* It is the Q disk */
-		switch (conf->algorithm) {
+		switch (algorithm) {
 		case ALGORITHM_LEFT_ASYMMETRIC:
 		case ALGORITHM_RIGHT_ASYMMETRIC:
-		  	if (sh->pd_idx == raid_disks-1)
-				i--; 	/* Q D D D P */
+		case ALGORITHM_ROTATING_ZERO_RESTART:
+		case ALGORITHM_ROTATING_N_RESTART:
+			if (sh->pd_idx == raid_disks-1)
+				i--;	/* Q D D D P */
 			else if (i > sh->pd_idx)
 				i -= 2; /* D D P Q D */
 			break;
@@ -1390,9 +1547,35 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i)
 				i -= (sh->pd_idx + 2);
 			}
 			break;
+		case ALGORITHM_PARITY_0:
+			i -= 2;
+			break;
+		case ALGORITHM_PARITY_N:
+			break;
+		case ALGORITHM_ROTATING_N_CONTINUE:
+			if (sh->pd_idx == 0)
+				i--;	/* P D D D Q */
+			else if (i > sh->pd_idx)
+				i -= 2; /* D D Q P D */
+			break;
+		case ALGORITHM_LEFT_ASYMMETRIC_6:
+		case ALGORITHM_RIGHT_ASYMMETRIC_6:
+			if (i > sh->pd_idx)
+				i--;
+			break;
+		case ALGORITHM_LEFT_SYMMETRIC_6:
+		case ALGORITHM_RIGHT_SYMMETRIC_6:
+			if (i < sh->pd_idx)
+				i += data_disks + 1;
+			i -= (sh->pd_idx + 1);
+			break;
+		case ALGORITHM_PARITY_0_6:
+			i -= 1;
+			break;
 		default:
 			printk(KERN_CRIT "raid6: unsupported algorithm %d\n",
-			       conf->algorithm);
+			       algorithm);
+			BUG();
 		}
 		break;
 	}
@@ -1400,8 +1583,10 @@ static sector_t compute_blocknr(struct stripe_head *sh, int i)
 	chunk_number = stripe * data_disks + i;
 	r_sector = (sector_t)chunk_number * sectors_per_chunk + chunk_offset;
 
-	check = raid5_compute_sector(r_sector, raid_disks, data_disks, &dummy1, &dummy2, conf);
-	if (check != sh->sector || dummy1 != dd_idx || dummy2 != sh->pd_idx) {
+	check = raid5_compute_sector(conf, r_sector,
+				     previous, &dummy1, &sh2);
+	if (check != sh->sector || dummy1 != dd_idx || sh2.pd_idx != sh->pd_idx
+		|| sh2.qd_idx != sh->qd_idx) {
 		printk(KERN_ERR "compute_blocknr: map not correct\n");
 		return 0;
 	}
@@ -1468,14 +1653,16 @@ static void copy_data(int frombio, struct bio *bio,
 
 static void compute_parity6(struct stripe_head *sh, int method)
 {
-	raid6_conf_t *conf = sh->raid_conf;
-	int i, pd_idx = sh->pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
+	raid5_conf_t *conf = sh->raid_conf;
+	int i, pd_idx, qd_idx, d0_idx, disks = sh->disks, count;
+	int syndrome_disks = sh->ddf_layout ? disks : (disks - 2);
 	struct bio *chosen;
 	/**** FIX THIS: This could be very bad if disks is close to 256 ****/
-	void *ptrs[disks];
+	void *ptrs[syndrome_disks+2];
 
-	qd_idx = raid6_next_disk(pd_idx, disks);
-	d0_idx = raid6_next_disk(qd_idx, disks);
+	pd_idx = sh->pd_idx;
+	qd_idx = sh->qd_idx;
+	d0_idx = raid6_d0(sh);
 
 	pr_debug("compute_parity, stripe %llu, method %d\n",
 		(unsigned long long)sh->sector, method);
@@ -1513,24 +1700,29 @@ static void compute_parity6(struct stripe_head *sh, int method)
 			set_bit(R5_UPTODATE, &sh->dev[i].flags);
 		}
 
-//	switch(method) {
-//	case RECONSTRUCT_WRITE:
-//	case CHECK_PARITY:
-//	case UPDATE_PARITY:
-		/* Note that unlike RAID-5, the ordering of the disks matters greatly. */
-		/* FIX: Is this ordering of drives even remotely optimal? */
-		count = 0;
-		i = d0_idx;
-		do {
-			ptrs[count++] = page_address(sh->dev[i].page);
-			if (count <= disks-2 && !test_bit(R5_UPTODATE, &sh->dev[i].flags))
-				printk("block %d/%d not uptodate on parity calc\n", i,count);
-			i = raid6_next_disk(i, disks);
-		} while ( i != d0_idx );
-//		break;
-//	}
-
-	raid6_call.gen_syndrome(disks, STRIPE_SIZE, ptrs);
+	/* Note that unlike RAID-5, the ordering of the disks matters greatly.*/
+
+	for (i = 0; i < disks; i++)
+		ptrs[i] = (void *)raid6_empty_zero_page;
+
+	count = 0;
+	i = d0_idx;
+	do {
+		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+
+		ptrs[slot] = page_address(sh->dev[i].page);
+		if (slot < syndrome_disks &&
+		    !test_bit(R5_UPTODATE, &sh->dev[i].flags)) {
+			printk(KERN_ERR "block %d/%d not uptodate "
+			       "on parity calc\n", i, count);
+			BUG();
+		}
+
+		i = raid6_next_disk(i, disks);
+	} while (i != d0_idx);
+	BUG_ON(count != syndrome_disks);
+
+	raid6_call.gen_syndrome(syndrome_disks+2, STRIPE_SIZE, ptrs);
 
 	switch(method) {
 	case RECONSTRUCT_WRITE:
@@ -1552,8 +1744,7 @@ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
 {
 	int i, count, disks = sh->disks;
 	void *ptr[MAX_XOR_BLOCKS], *dest, *p;
-	int pd_idx = sh->pd_idx;
-	int qd_idx = raid6_next_disk(pd_idx, disks);
+	int qd_idx = sh->qd_idx;
 
 	pr_debug("compute_block_1, stripe %llu, idx %d\n",
 		(unsigned long long)sh->sector, dd_idx);
@@ -1589,63 +1780,65 @@ static void compute_block_1(struct stripe_head *sh, int dd_idx, int nozero)
 static void compute_block_2(struct stripe_head *sh, int dd_idx1, int dd_idx2)
 {
 	int i, count, disks = sh->disks;
-	int pd_idx = sh->pd_idx;
-	int qd_idx = raid6_next_disk(pd_idx, disks);
-	int d0_idx = raid6_next_disk(qd_idx, disks);
-	int faila, failb;
+	int syndrome_disks = sh->ddf_layout ? disks : disks-2;
+	int d0_idx = raid6_d0(sh);
+	int faila = -1, failb = -1;
+	/**** FIX THIS: This could be very bad if disks is close to 256 ****/
+	void *ptrs[syndrome_disks+2];
 
-	/* faila and failb are disk numbers relative to d0_idx */
-	/* pd_idx become disks-2 and qd_idx become disks-1 */
-	faila = (dd_idx1 < d0_idx) ? dd_idx1+(disks-d0_idx) : dd_idx1-d0_idx;
-	failb = (dd_idx2 < d0_idx) ? dd_idx2+(disks-d0_idx) : dd_idx2-d0_idx;
+	for (i = 0; i < disks ; i++)
+		ptrs[i] = (void *)raid6_empty_zero_page;
+	count = 0;
+	i = d0_idx;
+	do {
+		int slot = raid6_idx_to_slot(i, sh, &count, syndrome_disks);
+
+		ptrs[slot] = page_address(sh->dev[i].page);
+
+		if (i == dd_idx1)
+			faila = slot;
+		if (i == dd_idx2)
+			failb = slot;
+		i = raid6_next_disk(i, disks);
+	} while (i != d0_idx);
+	BUG_ON(count != syndrome_disks);
 
 	BUG_ON(faila == failb);
 	if ( failb < faila ) { int tmp = faila; faila = failb; failb = tmp; }
 
 	pr_debug("compute_block_2, stripe %llu, idx %d,%d (%d,%d)\n",
-	       (unsigned long long)sh->sector, dd_idx1, dd_idx2, faila, failb);
+		 (unsigned long long)sh->sector, dd_idx1, dd_idx2,
+		 faila, failb);
 
-	if ( failb == disks-1 ) {
+	if (failb == syndrome_disks+1) {
 		/* Q disk is one of the missing disks */
-		if ( faila == disks-2 ) {
+		if (faila == syndrome_disks) {
 			/* Missing P+Q, just recompute */
 			compute_parity6(sh, UPDATE_PARITY);
 			return;
 		} else {
 			/* We're missing D+Q; recompute D from P */
-			compute_block_1(sh, (dd_idx1 == qd_idx) ? dd_idx2 : dd_idx1, 0);
+			compute_block_1(sh, ((dd_idx1 == sh->qd_idx) ?
+					     dd_idx2 : dd_idx1),
+					0);
 			compute_parity6(sh, UPDATE_PARITY); /* Is this necessary? */
 			return;
 		}
 	}
 
-	/* We're missing D+P or D+D; build pointer table */
-	{
-		/**** FIX THIS: This could be very bad if disks is close to 256 ****/
-		void *ptrs[disks];
-
-		count = 0;
-		i = d0_idx;
-		do {
-			ptrs[count++] = page_address(sh->dev[i].page);
-			i = raid6_next_disk(i, disks);
-			if (i != dd_idx1 && i != dd_idx2 &&
-			    !test_bit(R5_UPTODATE, &sh->dev[i].flags))
-				printk("compute_2 with missing block %d/%d\n", count, i);
-		} while ( i != d0_idx );
-
-		if ( failb == disks-2 ) {
-			/* We're missing D+P. */
-			raid6_datap_recov(disks, STRIPE_SIZE, faila, ptrs);
-		} else {
-			/* We're missing D+D. */
-			raid6_2data_recov(disks, STRIPE_SIZE, faila, failb, ptrs);
-		}
-
-		/* Both the above update both missing blocks */
-		set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
-		set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
+	/* We're missing D+P or D+D; */
+	if (failb == syndrome_disks) {
+		/* We're missing D+P. */
+		raid6_datap_recov(syndrome_disks+2, STRIPE_SIZE, faila, ptrs);
+	} else {
+		/* We're missing D+D. */
+		raid6_2data_recov(syndrome_disks+2, STRIPE_SIZE, faila, failb,
+				  ptrs);
 	}
+
+	/* Both the above update both missing blocks */
+	set_bit(R5_UPTODATE, &sh->dev[dd_idx1].flags);
+	set_bit(R5_UPTODATE, &sh->dev[dd_idx2].flags);
 }
 
 static void
@@ -1800,17 +1993,21 @@ static int page_is_zero(struct page *p)
 		memcmp(a, a+4, STRIPE_SIZE-4)==0);
 }
 
-static int stripe_to_pdidx(sector_t stripe, raid5_conf_t *conf, int disks)
+static void stripe_set_idx(sector_t stripe, raid5_conf_t *conf, int previous,
+			    struct stripe_head *sh)
 {
-	int sectors_per_chunk = conf->chunk_size >> 9;
-	int pd_idx, dd_idx;
+	int sectors_per_chunk =
+		previous ? (conf->prev_chunk >> 9)
+			 : (conf->chunk_size >> 9);
+	int dd_idx;
 	int chunk_offset = sector_div(stripe, sectors_per_chunk);
+	int disks = previous ? conf->previous_raid_disks : conf->raid_disks;
 
-	raid5_compute_sector(stripe * (disks - conf->max_degraded)
+	raid5_compute_sector(conf,
+			     stripe * (disks - conf->max_degraded)
 			     *sectors_per_chunk + chunk_offset,
-			     disks, disks - conf->max_degraded,
-			     &dd_idx, &pd_idx, conf);
-	return pd_idx;
+			     previous,
+			     &dd_idx, sh);
 }
 
 static void
@@ -2181,7 +2378,7 @@ static void handle_stripe_dirtying6(raid5_conf_t *conf,
 		struct r6_state *r6s, int disks)
 {
 	int rcw = 0, must_compute = 0, pd_idx = sh->pd_idx, i;
-	int qd_idx = r6s->qd_idx;
+	int qd_idx = sh->qd_idx;
 	for (i = disks; i--; ) {
 		struct r5dev *dev = &sh->dev[i];
 		/* Would I have to read this buffer for reconstruct_write */
@@ -2371,7 +2568,7 @@ static void handle_parity_checks6(raid5_conf_t *conf, struct stripe_head *sh,
 	int update_p = 0, update_q = 0;
 	struct r5dev *dev;
 	int pd_idx = sh->pd_idx;
-	int qd_idx = r6s->qd_idx;
+	int qd_idx = sh->qd_idx;
 
 	set_bit(STRIPE_HANDLE, &sh->state);
 
@@ -2467,17 +2664,14 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 	struct dma_async_tx_descriptor *tx = NULL;
 	clear_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 	for (i = 0; i < sh->disks; i++)
-		if (i != sh->pd_idx && (!r6s || i != r6s->qd_idx)) {
-			int dd_idx, pd_idx, j;
+		if (i != sh->pd_idx && i != sh->qd_idx) {
+			int dd_idx, j;
 			struct stripe_head *sh2;
 
-			sector_t bn = compute_blocknr(sh, i);
-			sector_t s = raid5_compute_sector(bn, conf->raid_disks,
-						conf->raid_disks -
-						conf->max_degraded, &dd_idx,
-						&pd_idx, conf);
-			sh2 = get_active_stripe(conf, s, conf->raid_disks,
-						pd_idx, 1);
+			sector_t bn = compute_blocknr(sh, i, 1);
+			sector_t s = raid5_compute_sector(conf, bn, 0,
+							  &dd_idx, NULL);
+			sh2 = get_active_stripe(conf, s, 0, 1);
 			if (sh2 == NULL)
 				/* so far only the early blocks of this stripe
 				 * have been requested.  When later blocks
@@ -2500,8 +2694,7 @@ static void handle_stripe_expansion(raid5_conf_t *conf, struct stripe_head *sh,
 			set_bit(R5_UPTODATE, &sh2->dev[dd_idx].flags);
 			for (j = 0; j < conf->raid_disks; j++)
 				if (j != sh2->pd_idx &&
-				    (!r6s || j != raid6_next_disk(sh2->pd_idx,
-								 sh2->disks)) &&
+				    (!r6s || j != sh2->qd_idx) &&
 				    !test_bit(R5_Expanded, &sh2->dev[j].flags))
 					break;
 			if (j == conf->raid_disks) {
@@ -2750,6 +2943,23 @@ static bool handle_stripe5(struct stripe_head *sh)
 
 	/* Finish reconstruct operations initiated by the expansion process */
 	if (sh->reconstruct_state == reconstruct_state_result) {
+		struct stripe_head *sh2
+			= get_active_stripe(conf, sh->sector, 1, 1);
+		if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
+			/* sh cannot be written until sh2 has been read.
+			 * so arrange for sh to be delayed a little
+			 */
+			set_bit(STRIPE_DELAYED, &sh->state);
+			set_bit(STRIPE_HANDLE, &sh->state);
+			if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
+					      &sh2->state))
+				atomic_inc(&conf->preread_active_stripes);
+			release_stripe(sh2);
+			goto unlock;
+		}
+		if (sh2)
+			release_stripe(sh2);
+
 		sh->reconstruct_state = reconstruct_state_idle;
 		clear_bit(STRIPE_EXPANDING, &sh->state);
 		for (i = conf->raid_disks; i--; ) {
@@ -2763,8 +2973,7 @@ static bool handle_stripe5(struct stripe_head *sh)
 	    !sh->reconstruct_state) {
 		/* Need to write out all blocks after computing parity */
 		sh->disks = conf->raid_disks;
-		sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
-			conf->raid_disks);
+		stripe_set_idx(sh->sector, conf, 0, sh);
 		schedule_reconstruction5(sh, &s, 1, 1);
 	} else if (s.expanded && !sh->reconstruct_state && s.locked == 0) {
 		clear_bit(STRIPE_EXPAND_READY, &sh->state);
@@ -2796,20 +3005,19 @@ static bool handle_stripe5(struct stripe_head *sh)
 
 static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 {
-	raid6_conf_t *conf = sh->raid_conf;
+	raid5_conf_t *conf = sh->raid_conf;
 	int disks = sh->disks;
 	struct bio *return_bi = NULL;
-	int i, pd_idx = sh->pd_idx;
+	int i, pd_idx = sh->pd_idx, qd_idx = sh->qd_idx;
 	struct stripe_head_state s;
 	struct r6_state r6s;
 	struct r5dev *dev, *pdev, *qdev;
 	mdk_rdev_t *blocked_rdev = NULL;
 
-	r6s.qd_idx = raid6_next_disk(pd_idx, disks);
 	pr_debug("handling stripe %llu, state=%#lx cnt=%d, "
 		"pd_idx=%d, qd_idx=%d\n",
 	       (unsigned long long)sh->sector, sh->state,
-	       atomic_read(&sh->count), pd_idx, r6s.qd_idx);
+	       atomic_read(&sh->count), pd_idx, qd_idx);
 	memset(&s, 0, sizeof(s));
 
 	spin_lock(&sh->lock);
@@ -2920,9 +3128,9 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 	pdev = &sh->dev[pd_idx];
 	r6s.p_failed = (s.failed >= 1 && r6s.failed_num[0] == pd_idx)
 		|| (s.failed >= 2 && r6s.failed_num[1] == pd_idx);
-	qdev = &sh->dev[r6s.qd_idx];
-	r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == r6s.qd_idx)
-		|| (s.failed >= 2 && r6s.failed_num[1] == r6s.qd_idx);
+	qdev = &sh->dev[qd_idx];
+	r6s.q_failed = (s.failed >= 1 && r6s.failed_num[0] == qd_idx)
+		|| (s.failed >= 2 && r6s.failed_num[1] == qd_idx);
 
 	if ( s.written &&
 	     ( r6s.p_failed || ((test_bit(R5_Insync, &pdev->flags)
@@ -2980,10 +3188,26 @@ static bool handle_stripe6(struct stripe_head *sh, struct page *tmp_page)
 		}
 
 	if (s.expanded && test_bit(STRIPE_EXPANDING, &sh->state)) {
+		struct stripe_head *sh2
+			= get_active_stripe(conf, sh->sector, 1, 1);
+		if (sh2 && test_bit(STRIPE_EXPAND_SOURCE, &sh2->state)) {
+			/* sh cannot be written until sh2 has been read.
+			 * so arrange for sh to be delayed a little
+			 */
+			set_bit(STRIPE_DELAYED, &sh->state);
+			set_bit(STRIPE_HANDLE, &sh->state);
+			if (!test_and_set_bit(STRIPE_PREREAD_ACTIVE,
+					      &sh2->state))
+				atomic_inc(&conf->preread_active_stripes);
+			release_stripe(sh2);
+			goto unlock;
+		}
+		if (sh2)
+			release_stripe(sh2);
+
 		/* Need to write out all blocks after computing P&Q */
 		sh->disks = conf->raid_disks;
-		sh->pd_idx = stripe_to_pdidx(sh->sector, conf,
-					     conf->raid_disks);
+		stripe_set_idx(sh->sector, conf, 0, sh);
 		compute_parity6(sh, RECONSTRUCT_WRITE);
 		for (i = conf->raid_disks ; i-- ;  ) {
 			set_bit(R5_LOCKED, &sh->dev[i].flags);
@@ -3134,6 +3358,8 @@ static int raid5_mergeable_bvec(struct request_queue *q,
 	if ((bvm->bi_rw & 1) == WRITE)
 		return biovec->bv_len; /* always allow writes to be mergeable */
 
+	if (mddev->new_chunk < mddev->chunk_size)
+		chunk_sectors = mddev->new_chunk >> 9;
 	max =  (chunk_sectors - ((sector & (chunk_sectors - 1)) + bio_sectors)) << 9;
 	if (max < 0) max = 0;
 	if (max <= biovec->bv_len && bio_sectors == 0)
@@ -3149,6 +3375,8 @@ static int in_chunk_boundary(mddev_t *mddev, struct bio *bio)
 	unsigned int chunk_sectors = mddev->chunk_size >> 9;
 	unsigned int bio_sectors = bio->bi_size >> 9;
 
+	if (mddev->new_chunk < mddev->chunk_size)
+		chunk_sectors = mddev->new_chunk >> 9;
 	return  chunk_sectors >=
 		((sector & (chunk_sectors - 1)) + bio_sectors);
 }
@@ -3255,9 +3483,7 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
 {
 	mddev_t *mddev = q->queuedata;
 	raid5_conf_t *conf = mddev_to_conf(mddev);
-	const unsigned int raid_disks = conf->raid_disks;
-	const unsigned int data_disks = raid_disks - conf->max_degraded;
-	unsigned int dd_idx, pd_idx;
+	unsigned int dd_idx;
 	struct bio* align_bi;
 	mdk_rdev_t *rdev;
 
@@ -3266,7 +3492,7 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
 		return 0;
 	}
 	/*
- 	 * use bio_clone to make a copy of the bio
+	 * use bio_clone to make a copy of the bio
 	 */
 	align_bi = bio_clone(raid_bio, GFP_NOIO);
 	if (!align_bi)
@@ -3280,12 +3506,9 @@ static int chunk_aligned_read(struct request_queue *q, struct bio * raid_bio)
 	/*
 	 *	compute position
 	 */
-	align_bi->bi_sector =  raid5_compute_sector(raid_bio->bi_sector,
-					raid_disks,
-					data_disks,
-					&dd_idx,
-					&pd_idx,
-					conf);
+	align_bi->bi_sector =  raid5_compute_sector(conf, raid_bio->bi_sector,
+						    0,
+						    &dd_idx, NULL);
 
 	rcu_read_lock();
 	rdev = rcu_dereference(conf->disks[dd_idx].rdev);
@@ -3377,7 +3600,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 {
 	mddev_t *mddev = q->queuedata;
 	raid5_conf_t *conf = mddev_to_conf(mddev);
-	unsigned int dd_idx, pd_idx;
+	int dd_idx;
 	sector_t new_sector;
 	sector_t logical_sector, last_sector;
 	struct stripe_head *sh;
@@ -3400,7 +3623,7 @@ static int make_request(struct request_queue *q, struct bio * bi)
 	if (rw == READ &&
 	     mddev->reshape_position == MaxSector &&
 	     chunk_aligned_read(q,bi))
-            	return 0;
+		return 0;
 
 	logical_sector = bi->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
 	last_sector = bi->bi_sector + (bi->bi_size>>9);
@@ -3410,26 +3633,31 @@ static int make_request(struct request_queue *q, struct bio * bi)
 	for (;logical_sector < last_sector; logical_sector += STRIPE_SECTORS) {
 		DEFINE_WAIT(w);
 		int disks, data_disks;
+		int previous;
 
 	retry:
+		previous = 0;
+		disks = conf->raid_disks;
 		prepare_to_wait(&conf->wait_for_overlap, &w, TASK_UNINTERRUPTIBLE);
-		if (likely(conf->expand_progress == MaxSector))
-			disks = conf->raid_disks;
-		else {
-			/* spinlock is needed as expand_progress may be
+		if (unlikely(conf->reshape_progress != MaxSector)) {
+			/* spinlock is needed as reshape_progress may be
 			 * 64bit on a 32bit platform, and so it might be
 			 * possible to see a half-updated value
-			 * Ofcourse expand_progress could change after
+			 * Ofcourse reshape_progress could change after
 			 * the lock is dropped, so once we get a reference
 			 * to the stripe that we think it is, we will have
 			 * to check again.
 			 */
 			spin_lock_irq(&conf->device_lock);
-			disks = conf->raid_disks;
-			if (logical_sector >= conf->expand_progress)
+			if (mddev->delta_disks < 0
+			    ? logical_sector < conf->reshape_progress
+			    : logical_sector >= conf->reshape_progress) {
 				disks = conf->previous_raid_disks;
-			else {
-				if (logical_sector >= conf->expand_lo) {
+				previous = 1;
+			} else {
+				if (mddev->delta_disks < 0
+				    ? logical_sector < conf->reshape_safe
+				    : logical_sector >= conf->reshape_safe) {
 					spin_unlock_irq(&conf->device_lock);
 					schedule();
 					goto retry;
@@ -3439,15 +3667,17 @@ static int make_request(struct request_queue *q, struct bio * bi)
 		}
 		data_disks = disks - conf->max_degraded;
 
- 		new_sector = raid5_compute_sector(logical_sector, disks, data_disks,
-						  &dd_idx, &pd_idx, conf);
+		new_sector = raid5_compute_sector(conf, logical_sector,
+						  previous,
+						  &dd_idx, NULL);
 		pr_debug("raid5: make_request, sector %llu logical %llu\n",
 			(unsigned long long)new_sector, 
 			(unsigned long long)logical_sector);
 
-		sh = get_active_stripe(conf, new_sector, disks, pd_idx, (bi->bi_rw&RWA_MASK));
+		sh = get_active_stripe(conf, new_sector, previous,
+				       (bi->bi_rw&RWA_MASK));
 		if (sh) {
-			if (unlikely(conf->expand_progress != MaxSector)) {
+			if (unlikely(previous)) {
 				/* expansion might have moved on while waiting for a
 				 * stripe, so we must do the range check again.
 				 * Expansion could still move past after this
@@ -3458,8 +3688,9 @@ static int make_request(struct request_queue *q, struct bio * bi)
 				 */
 				int must_retry = 0;
 				spin_lock_irq(&conf->device_lock);
-				if (logical_sector <  conf->expand_progress &&
-				    disks == conf->previous_raid_disks)
+				if (mddev->delta_disks < 0
+				    ? logical_sector >= conf->reshape_progress
+				    : logical_sector < conf->reshape_progress)
 					/* mismatch, need to try again */
 					must_retry = 1;
 				spin_unlock_irq(&conf->device_lock);
@@ -3514,6 +3745,8 @@ static int make_request(struct request_queue *q, struct bio * bi)
 	return 0;
 }
 
+static sector_t raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks);
+
 static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped)
 {
 	/* reshaping is quite different to recovery/resync so it is
@@ -3527,61 +3760,118 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 	 */
 	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
 	struct stripe_head *sh;
-	int pd_idx;
 	sector_t first_sector, last_sector;
 	int raid_disks = conf->previous_raid_disks;
 	int data_disks = raid_disks - conf->max_degraded;
 	int new_data_disks = conf->raid_disks - conf->max_degraded;
 	int i;
 	int dd_idx;
-	sector_t writepos, safepos, gap;
-
-	if (sector_nr == 0 &&
-	    conf->expand_progress != 0) {
-		/* restarting in the middle, skip the initial sectors */
-		sector_nr = conf->expand_progress;
+	sector_t writepos, readpos, safepos;
+	sector_t stripe_addr;
+	int reshape_sectors;
+	struct list_head stripes;
+
+	if (sector_nr == 0) {
+		/* If restarting in the middle, skip the initial sectors */
+		if (mddev->delta_disks < 0 &&
+		    conf->reshape_progress < raid5_size(mddev, 0, 0)) {
+			sector_nr = raid5_size(mddev, 0, 0)
+				- conf->reshape_progress;
+		} else if (mddev->delta_disks > 0 &&
+			   conf->reshape_progress > 0)
+			sector_nr = conf->reshape_progress;
 		sector_div(sector_nr, new_data_disks);
-		*skipped = 1;
-		return sector_nr;
+		if (sector_nr) {
+			*skipped = 1;
+			return sector_nr;
+		}
 	}
 
+	/* We need to process a full chunk at a time.
+	 * If old and new chunk sizes differ, we need to process the
+	 * largest of these
+	 */
+	if (mddev->new_chunk > mddev->chunk_size)
+		reshape_sectors = mddev->new_chunk / 512;
+	else
+		reshape_sectors = mddev->chunk_size / 512;
+
 	/* we update the metadata when there is more than 3Meg
 	 * in the block range (that is rather arbitrary, should
 	 * probably be time based) or when the data about to be
 	 * copied would over-write the source of the data at
 	 * the front of the range.
-	 * i.e. one new_stripe forward from expand_progress new_maps
-	 * to after where expand_lo old_maps to
+	 * i.e. one new_stripe along from reshape_progress new_maps
+	 * to after where reshape_safe old_maps to
 	 */
-	writepos = conf->expand_progress +
-		conf->chunk_size/512*(new_data_disks);
+	writepos = conf->reshape_progress;
 	sector_div(writepos, new_data_disks);
-	safepos = conf->expand_lo;
+	readpos = conf->reshape_progress;
+	sector_div(readpos, data_disks);
+	safepos = conf->reshape_safe;
 	sector_div(safepos, data_disks);
-	gap = conf->expand_progress - conf->expand_lo;
+	if (mddev->delta_disks < 0) {
+		writepos -= reshape_sectors;
+		readpos += reshape_sectors;
+		safepos += reshape_sectors;
+	} else {
+		writepos += reshape_sectors;
+		readpos -= reshape_sectors;
+		safepos -= reshape_sectors;
+	}
 
-	if (writepos >= safepos ||
-	    gap > (new_data_disks)*3000*2 /*3Meg*/) {
+	/* 'writepos' is the most advanced device address we might write.
+	 * 'readpos' is the least advanced device address we might read.
+	 * 'safepos' is the least address recorded in the metadata as having
+	 *     been reshaped.
+	 * If 'readpos' is behind 'writepos', then there is no way that we can
+	 * ensure safety in the face of a crash - that must be done by userspace
+	 * making a backup of the data.  So in that case there is no particular
+	 * rush to update metadata.
+	 * Otherwise if 'safepos' is behind 'writepos', then we really need to
+	 * update the metadata to advance 'safepos' to match 'readpos' so that
+	 * we can be safe in the event of a crash.
+	 * So we insist on updating metadata if safepos is behind writepos and
+	 * readpos is beyond writepos.
+	 * In any case, update the metadata every 10 seconds.
+	 * Maybe that number should be configurable, but I'm not sure it is
+	 * worth it.... maybe it could be a multiple of safemode_delay???
+	 */
+	if ((mddev->delta_disks < 0
+	     ? (safepos > writepos && readpos < writepos)
+	     : (safepos < writepos && readpos > writepos)) ||
+	    time_after(jiffies, conf->reshape_checkpoint + 10*HZ)) {
 		/* Cannot proceed until we've updated the superblock... */
 		wait_event(conf->wait_for_overlap,
 			   atomic_read(&conf->reshape_stripes)==0);
-		mddev->reshape_position = conf->expand_progress;
+		mddev->reshape_position = conf->reshape_progress;
+		conf->reshape_checkpoint = jiffies;
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
 		wait_event(mddev->sb_wait, mddev->flags == 0 ||
 			   kthread_should_stop());
 		spin_lock_irq(&conf->device_lock);
-		conf->expand_lo = mddev->reshape_position;
+		conf->reshape_safe = mddev->reshape_position;
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 	}
 
-	for (i=0; i < conf->chunk_size/512; i+= STRIPE_SECTORS) {
+	if (mddev->delta_disks < 0) {
+		BUG_ON(conf->reshape_progress == 0);
+		stripe_addr = writepos;
+		BUG_ON((mddev->dev_sectors &
+			~((sector_t)reshape_sectors - 1))
+		       - reshape_sectors - stripe_addr
+		       != sector_nr);
+	} else {
+		BUG_ON(writepos != sector_nr + reshape_sectors);
+		stripe_addr = sector_nr;
+	}
+	INIT_LIST_HEAD(&stripes);
+	for (i = 0; i < reshape_sectors; i += STRIPE_SECTORS) {
 		int j;
 		int skipped = 0;
-		pd_idx = stripe_to_pdidx(sector_nr+i, conf, conf->raid_disks);
-		sh = get_active_stripe(conf, sector_nr+i,
-				       conf->raid_disks, pd_idx, 0);
+		sh = get_active_stripe(conf, stripe_addr+i, 0, 0);
 		set_bit(STRIPE_EXPANDING, &sh->state);
 		atomic_inc(&conf->reshape_stripes);
 		/* If any of this stripe is beyond the end of the old
@@ -3592,10 +3882,10 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 			if (j == sh->pd_idx)
 				continue;
 			if (conf->level == 6 &&
-			    j == raid6_next_disk(sh->pd_idx, sh->disks))
+			    j == sh->qd_idx)
 				continue;
-			s = compute_blocknr(sh, j);
-			if (s < mddev->array_sectors) {
+			s = compute_blocknr(sh, j, 0);
+			if (s < raid5_size(mddev, 0, 0)) {
 				skipped = 1;
 				continue;
 			}
@@ -3607,10 +3897,13 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 			set_bit(STRIPE_EXPAND_READY, &sh->state);
 			set_bit(STRIPE_HANDLE, &sh->state);
 		}
-		release_stripe(sh);
+		list_add(&sh->lru, &stripes);
 	}
 	spin_lock_irq(&conf->device_lock);
-	conf->expand_progress = (sector_nr + i) * new_data_disks;
+	if (mddev->delta_disks < 0)
+		conf->reshape_progress -= reshape_sectors * new_data_disks;
+	else
+		conf->reshape_progress += reshape_sectors * new_data_disks;
 	spin_unlock_irq(&conf->device_lock);
 	/* Ok, those stripe are ready. We can start scheduling
 	 * reads on the source stripes.
@@ -3618,46 +3911,50 @@ static sector_t reshape_request(mddev_t *mddev, sector_t sector_nr, int *skipped
 	 * block on the destination stripes.
 	 */
 	first_sector =
-		raid5_compute_sector(sector_nr*(new_data_disks),
-				     raid_disks, data_disks,
-				     &dd_idx, &pd_idx, conf);
+		raid5_compute_sector(conf, stripe_addr*(new_data_disks),
+				     1, &dd_idx, NULL);
 	last_sector =
-		raid5_compute_sector((sector_nr+conf->chunk_size/512)
-				     *(new_data_disks) -1,
-				     raid_disks, data_disks,
-				     &dd_idx, &pd_idx, conf);
-	if (last_sector >= (mddev->size<<1))
-		last_sector = (mddev->size<<1)-1;
+		raid5_compute_sector(conf, ((stripe_addr+conf->chunk_size/512)
+					    *(new_data_disks) - 1),
+				     1, &dd_idx, NULL);
+	if (last_sector >= mddev->dev_sectors)
+		last_sector = mddev->dev_sectors - 1;
 	while (first_sector <= last_sector) {
-		pd_idx = stripe_to_pdidx(first_sector, conf,
-					 conf->previous_raid_disks);
-		sh = get_active_stripe(conf, first_sector,
-				       conf->previous_raid_disks, pd_idx, 0);
+		sh = get_active_stripe(conf, first_sector, 1, 0);
 		set_bit(STRIPE_EXPAND_SOURCE, &sh->state);
 		set_bit(STRIPE_HANDLE, &sh->state);
 		release_stripe(sh);
 		first_sector += STRIPE_SECTORS;
 	}
+	/* Now that the sources are clearly marked, we can release
+	 * the destination stripes
+	 */
+	while (!list_empty(&stripes)) {
+		sh = list_entry(stripes.next, struct stripe_head, lru);
+		list_del_init(&sh->lru);
+		release_stripe(sh);
+	}
 	/* If this takes us to the resync_max point where we have to pause,
 	 * then we need to write out the superblock.
 	 */
-	sector_nr += conf->chunk_size>>9;
+	sector_nr += reshape_sectors;
 	if (sector_nr >= mddev->resync_max) {
 		/* Cannot proceed until we've updated the superblock... */
 		wait_event(conf->wait_for_overlap,
 			   atomic_read(&conf->reshape_stripes) == 0);
-		mddev->reshape_position = conf->expand_progress;
+		mddev->reshape_position = conf->reshape_progress;
+		conf->reshape_checkpoint = jiffies;
 		set_bit(MD_CHANGE_DEVS, &mddev->flags);
 		md_wakeup_thread(mddev->thread);
 		wait_event(mddev->sb_wait,
 			   !test_bit(MD_CHANGE_DEVS, &mddev->flags)
 			   || kthread_should_stop());
 		spin_lock_irq(&conf->device_lock);
-		conf->expand_lo = mddev->reshape_position;
+		conf->reshape_safe = mddev->reshape_position;
 		spin_unlock_irq(&conf->device_lock);
 		wake_up(&conf->wait_for_overlap);
 	}
-	return conf->chunk_size>>9;
+	return reshape_sectors;
 }
 
 /* FIXME go_faster isn't used */
@@ -3665,9 +3962,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 {
 	raid5_conf_t *conf = (raid5_conf_t *) mddev->private;
 	struct stripe_head *sh;
-	int pd_idx;
-	int raid_disks = conf->raid_disks;
-	sector_t max_sector = mddev->size << 1;
+	sector_t max_sector = mddev->dev_sectors;
 	int sync_blocks;
 	int still_degraded = 0;
 	int i;
@@ -3675,6 +3970,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 	if (sector_nr >= max_sector) {
 		/* just being told to finish up .. nothing much to do */
 		unplug_slaves(mddev);
+
 		if (test_bit(MD_RECOVERY_RESHAPE, &mddev->recovery)) {
 			end_reshape(conf);
 			return 0;
@@ -3705,7 +4001,7 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 	 */
 	if (mddev->degraded >= conf->max_degraded &&
 	    test_bit(MD_RECOVERY_SYNC, &mddev->recovery)) {
-		sector_t rv = (mddev->size << 1) - sector_nr;
+		sector_t rv = mddev->dev_sectors - sector_nr;
 		*skipped = 1;
 		return rv;
 	}
@@ -3721,10 +4017,9 @@ static inline sector_t sync_request(mddev_t *mddev, sector_t sector_nr, int *ski
 
 	bitmap_cond_end_sync(mddev->bitmap, sector_nr);
 
-	pd_idx = stripe_to_pdidx(sector_nr, conf, raid_disks);
-	sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 1);
+	sh = get_active_stripe(conf, sector_nr, 0, 1);
 	if (sh == NULL) {
-		sh = get_active_stripe(conf, sector_nr, raid_disks, pd_idx, 0);
+		sh = get_active_stripe(conf, sector_nr, 0, 0);
 		/* make sure we don't swamp the stripe cache if someone else
 		 * is trying to get access
 		 */
@@ -3766,19 +4061,15 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
 	 * it will be only one 'dd_idx' and only need one call to raid5_compute_sector.
 	 */
 	struct stripe_head *sh;
-	int dd_idx, pd_idx;
+	int dd_idx;
 	sector_t sector, logical_sector, last_sector;
 	int scnt = 0;
 	int remaining;
 	int handled = 0;
 
 	logical_sector = raid_bio->bi_sector & ~((sector_t)STRIPE_SECTORS-1);
-	sector = raid5_compute_sector(	logical_sector,
-					conf->raid_disks,
-					conf->raid_disks - conf->max_degraded,
-					&dd_idx,
-					&pd_idx,
-					conf);
+	sector = raid5_compute_sector(conf, logical_sector,
+				      0, &dd_idx, NULL);
 	last_sector = raid_bio->bi_sector + (raid_bio->bi_size>>9);
 
 	for (; logical_sector < last_sector;
@@ -3790,7 +4081,7 @@ static int  retry_aligned_read(raid5_conf_t *conf, struct bio *raid_bio)
 			/* already done this stripe */
 			continue;
 
-		sh = get_active_stripe(conf, sector, conf->raid_disks, pd_idx, 1);
+		sh = get_active_stripe(conf, sector, 0, 1);
 
 		if (!sh) {
 			/* failed to get a stripe - must wait */
@@ -3992,89 +4283,69 @@ static struct attribute_group raid5_attrs_group = {
 	.attrs = raid5_attrs,
 };
 
-static int run(mddev_t *mddev)
+static sector_t
+raid5_size(mddev_t *mddev, sector_t sectors, int raid_disks)
+{
+	raid5_conf_t *conf = mddev_to_conf(mddev);
+
+	if (!sectors)
+		sectors = mddev->dev_sectors;
+	if (!raid_disks) {
+		/* size is defined by the smallest of previous and new size */
+		if (conf->raid_disks < conf->previous_raid_disks)
+			raid_disks = conf->raid_disks;
+		else
+			raid_disks = conf->previous_raid_disks;
+	}
+
+	sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
+	sectors &= ~((sector_t)mddev->new_chunk/512 - 1);
+	return sectors * (raid_disks - conf->max_degraded);
+}
+
+static raid5_conf_t *setup_conf(mddev_t *mddev)
 {
 	raid5_conf_t *conf;
 	int raid_disk, memory;
 	mdk_rdev_t *rdev;
 	struct disk_info *disk;
-	int working_disks = 0;
 
-	if (mddev->level != 5 && mddev->level != 4 && mddev->level != 6) {
+	if (mddev->new_level != 5
+	    && mddev->new_level != 4
+	    && mddev->new_level != 6) {
 		printk(KERN_ERR "raid5: %s: raid level not set to 4/5/6 (%d)\n",
-		       mdname(mddev), mddev->level);
-		return -EIO;
+		       mdname(mddev), mddev->new_level);
+		return ERR_PTR(-EIO);
 	}
-
-	if (mddev->chunk_size < PAGE_SIZE) {
-		printk(KERN_ERR "md/raid5: chunk_size must be at least "
-		       "PAGE_SIZE but %d < %ld\n",
-		       mddev->chunk_size, PAGE_SIZE);
-		return -EINVAL;
+	if ((mddev->new_level == 5
+	     && !algorithm_valid_raid5(mddev->new_layout)) ||
+	    (mddev->new_level == 6
+	     && !algorithm_valid_raid6(mddev->new_layout))) {
+		printk(KERN_ERR "raid5: %s: layout %d not supported\n",
+		       mdname(mddev), mddev->new_layout);
+		return ERR_PTR(-EIO);
 	}
-
-	if (mddev->reshape_position != MaxSector) {
-		/* Check that we can continue the reshape.
-		 * Currently only disks can change, it must
-		 * increase, and we must be past the point where
-		 * a stripe over-writes itself
-		 */
-		sector_t here_new, here_old;
-		int old_disks;
-		int max_degraded = (mddev->level == 5 ? 1 : 2);
-
-		if (mddev->new_level != mddev->level ||
-		    mddev->new_layout != mddev->layout ||
-		    mddev->new_chunk != mddev->chunk_size) {
-			printk(KERN_ERR "raid5: %s: unsupported reshape "
-			       "required - aborting.\n",
-			       mdname(mddev));
-			return -EINVAL;
-		}
-		if (mddev->delta_disks <= 0) {
-			printk(KERN_ERR "raid5: %s: unsupported reshape "
-			       "(reduce disks) required - aborting.\n",
-			       mdname(mddev));
-			return -EINVAL;
-		}
-		old_disks = mddev->raid_disks - mddev->delta_disks;
-		/* reshape_position must be on a new-stripe boundary, and one
-		 * further up in new geometry must map after here in old
-		 * geometry.
-		 */
-		here_new = mddev->reshape_position;
-		if (sector_div(here_new, (mddev->chunk_size>>9)*
-			       (mddev->raid_disks - max_degraded))) {
-			printk(KERN_ERR "raid5: reshape_position not "
-			       "on a stripe boundary\n");
-			return -EINVAL;
-		}
-		/* here_new is the stripe we will write to */
-		here_old = mddev->reshape_position;
-		sector_div(here_old, (mddev->chunk_size>>9)*
-			   (old_disks-max_degraded));
-		/* here_old is the first stripe that we might need to read
-		 * from */
-		if (here_new >= here_old) {
-			/* Reading from the same stripe as writing to - bad */
-			printk(KERN_ERR "raid5: reshape_position too early for "
-			       "auto-recovery - aborting.\n");
-			return -EINVAL;
-		}
-		printk(KERN_INFO "raid5: reshape will continue\n");
-		/* OK, we should be able to continue; */
+	if (mddev->new_level == 6 && mddev->raid_disks < 4) {
+		printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n",
+		       mdname(mddev), mddev->raid_disks);
+		return ERR_PTR(-EINVAL);
 	}
 
+	if (!mddev->new_chunk || mddev->new_chunk % PAGE_SIZE) {
+		printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
+			mddev->new_chunk, mdname(mddev));
+		return ERR_PTR(-EINVAL);
+	}
 
-	mddev->private = kzalloc(sizeof (raid5_conf_t), GFP_KERNEL);
-	if ((conf = mddev->private) == NULL)
+	conf = kzalloc(sizeof(raid5_conf_t), GFP_KERNEL);
+	if (conf == NULL)
 		goto abort;
-	if (mddev->reshape_position == MaxSector) {
-		conf->previous_raid_disks = conf->raid_disks = mddev->raid_disks;
-	} else {
-		conf->raid_disks = mddev->raid_disks;
+
+	conf->raid_disks = mddev->raid_disks;
+	if (mddev->reshape_position == MaxSector)
+		conf->previous_raid_disks = mddev->raid_disks;
+	else
 		conf->previous_raid_disks = mddev->raid_disks - mddev->delta_disks;
-	}
 
 	conf->disks = kzalloc(conf->raid_disks * sizeof(struct disk_info),
 			      GFP_KERNEL);
@@ -4086,13 +4357,12 @@ static int run(mddev_t *mddev)
 	if ((conf->stripe_hashtbl = kzalloc(PAGE_SIZE, GFP_KERNEL)) == NULL)
 		goto abort;
 
-	if (mddev->level == 6) {
+	if (mddev->new_level == 6) {
 		conf->spare_page = alloc_page(GFP_KERNEL);
 		if (!conf->spare_page)
 			goto abort;
 	}
 	spin_lock_init(&conf->device_lock);
-	mddev->queue->queue_lock = &conf->device_lock;
 	init_waitqueue_head(&conf->wait_for_stripe);
 	init_waitqueue_head(&conf->wait_for_overlap);
 	INIT_LIST_HEAD(&conf->handle_list);
@@ -4121,47 +4391,134 @@ static int run(mddev_t *mddev)
 			printk(KERN_INFO "raid5: device %s operational as raid"
 				" disk %d\n", bdevname(rdev->bdev,b),
 				raid_disk);
-			working_disks++;
 		} else
 			/* Cannot rely on bitmap to complete recovery */
 			conf->fullsync = 1;
 	}
 
-	/*
-	 * 0 for a fully functional array, 1 or 2 for a degraded array.
-	 */
-	mddev->degraded = conf->raid_disks - working_disks;
-	conf->mddev = mddev;
-	conf->chunk_size = mddev->chunk_size;
-	conf->level = mddev->level;
+	conf->chunk_size = mddev->new_chunk;
+	conf->level = mddev->new_level;
 	if (conf->level == 6)
 		conf->max_degraded = 2;
 	else
 		conf->max_degraded = 1;
-	conf->algorithm = mddev->layout;
+	conf->algorithm = mddev->new_layout;
 	conf->max_nr_stripes = NR_STRIPES;
-	conf->expand_progress = mddev->reshape_position;
-
-	/* device size must be a multiple of chunk size */
-	mddev->size &= ~(mddev->chunk_size/1024 -1);
-	mddev->resync_max_sectors = mddev->size << 1;
+	conf->reshape_progress = mddev->reshape_position;
+	if (conf->reshape_progress != MaxSector) {
+		conf->prev_chunk = mddev->chunk_size;
+		conf->prev_algo = mddev->layout;
+	}
 
-	if (conf->level == 6 && conf->raid_disks < 4) {
-		printk(KERN_ERR "raid6: not enough configured devices for %s (%d, minimum 4)\n",
-		       mdname(mddev), conf->raid_disks);
+	memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
+		 conf->raid_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
+	if (grow_stripes(conf, conf->max_nr_stripes)) {
+		printk(KERN_ERR
+			"raid5: couldn't allocate %dkB for buffers\n", memory);
 		goto abort;
-	}
-	if (!conf->chunk_size || conf->chunk_size % 4) {
-		printk(KERN_ERR "raid5: invalid chunk size %d for %s\n",
-			conf->chunk_size, mdname(mddev));
+	} else
+		printk(KERN_INFO "raid5: allocated %dkB for %s\n",
+			memory, mdname(mddev));
+
+	conf->thread = md_register_thread(raid5d, mddev, "%s_raid5");
+	if (!conf->thread) {
+		printk(KERN_ERR
+		       "raid5: couldn't allocate thread for %s\n",
+		       mdname(mddev));
 		goto abort;
 	}
-	if (conf->algorithm > ALGORITHM_RIGHT_SYMMETRIC) {
-		printk(KERN_ERR 
-			"raid5: unsupported parity algorithm %d for %s\n",
-			conf->algorithm, mdname(mddev));
-		goto abort;
+
+	return conf;
+
+ abort:
+	if (conf) {
+		shrink_stripes(conf);
+		safe_put_page(conf->spare_page);
+		kfree(conf->disks);
+		kfree(conf->stripe_hashtbl);
+		kfree(conf);
+		return ERR_PTR(-EIO);
+	} else
+		return ERR_PTR(-ENOMEM);
+}
+
+static int run(mddev_t *mddev)
+{
+	raid5_conf_t *conf;
+	int working_disks = 0;
+	mdk_rdev_t *rdev;
+
+	if (mddev->reshape_position != MaxSector) {
+		/* Check that we can continue the reshape.
+		 * Currently only disks can change, it must
+		 * increase, and we must be past the point where
+		 * a stripe over-writes itself
+		 */
+		sector_t here_new, here_old;
+		int old_disks;
+		int max_degraded = (mddev->level == 6 ? 2 : 1);
+
+		if (mddev->new_level != mddev->level) {
+			printk(KERN_ERR "raid5: %s: unsupported reshape "
+			       "required - aborting.\n",
+			       mdname(mddev));
+			return -EINVAL;
+		}
+		old_disks = mddev->raid_disks - mddev->delta_disks;
+		/* reshape_position must be on a new-stripe boundary, and one
+		 * further up in new geometry must map after here in old
+		 * geometry.
+		 */
+		here_new = mddev->reshape_position;
+		if (sector_div(here_new, (mddev->new_chunk>>9)*
+			       (mddev->raid_disks - max_degraded))) {
+			printk(KERN_ERR "raid5: reshape_position not "
+			       "on a stripe boundary\n");
+			return -EINVAL;
+		}
+		/* here_new is the stripe we will write to */
+		here_old = mddev->reshape_position;
+		sector_div(here_old, (mddev->chunk_size>>9)*
+			   (old_disks-max_degraded));
+		/* here_old is the first stripe that we might need to read
+		 * from */
+		if (here_new >= here_old) {
+			/* Reading from the same stripe as writing to - bad */
+			printk(KERN_ERR "raid5: reshape_position too early for "
+			       "auto-recovery - aborting.\n");
+			return -EINVAL;
+		}
+		printk(KERN_INFO "raid5: reshape will continue\n");
+		/* OK, we should be able to continue; */
+	} else {
+		BUG_ON(mddev->level != mddev->new_level);
+		BUG_ON(mddev->layout != mddev->new_layout);
+		BUG_ON(mddev->chunk_size != mddev->new_chunk);
+		BUG_ON(mddev->delta_disks != 0);
 	}
+
+	if (mddev->private == NULL)
+		conf = setup_conf(mddev);
+	else
+		conf = mddev->private;
+
+	if (IS_ERR(conf))
+		return PTR_ERR(conf);
+
+	mddev->thread = conf->thread;
+	conf->thread = NULL;
+	mddev->private = conf;
+
+	/*
+	 * 0 for a fully functional array, 1 or 2 for a degraded array.
+	 */
+	list_for_each_entry(rdev, &mddev->disks, same_set)
+		if (rdev->raid_disk >= 0 &&
+		    test_bit(In_sync, &rdev->flags))
+			working_disks++;
+
+	mddev->degraded = conf->raid_disks - working_disks;
+
 	if (mddev->degraded > conf->max_degraded) {
 		printk(KERN_ERR "raid5: not enough operational devices for %s"
 			" (%d/%d failed)\n",
@@ -4169,6 +4526,10 @@ static int run(mddev_t *mddev)
 		goto abort;
 	}
 
+	/* device size must be a multiple of chunk size */
+	mddev->dev_sectors &= ~(mddev->chunk_size / 512 - 1);
+	mddev->resync_max_sectors = mddev->dev_sectors;
+
 	if (mddev->degraded > 0 &&
 	    mddev->recovery_cp != MaxSector) {
 		if (mddev->ok_start_degraded)
@@ -4184,43 +4545,22 @@ static int run(mddev_t *mddev)
 		}
 	}
 
-	{
-		mddev->thread = md_register_thread(raid5d, mddev, "%s_raid5");
-		if (!mddev->thread) {
-			printk(KERN_ERR 
-				"raid5: couldn't allocate thread for %s\n",
-				mdname(mddev));
-			goto abort;
-		}
-	}
-	memory = conf->max_nr_stripes * (sizeof(struct stripe_head) +
-		 conf->raid_disks * ((sizeof(struct bio) + PAGE_SIZE))) / 1024;
-	if (grow_stripes(conf, conf->max_nr_stripes)) {
-		printk(KERN_ERR 
-			"raid5: couldn't allocate %dkB for buffers\n", memory);
-		shrink_stripes(conf);
-		md_unregister_thread(mddev->thread);
-		goto abort;
-	} else
-		printk(KERN_INFO "raid5: allocated %dkB for %s\n",
-			memory, mdname(mddev));
-
 	if (mddev->degraded == 0)
 		printk("raid5: raid level %d set %s active with %d out of %d"
-			" devices, algorithm %d\n", conf->level, mdname(mddev), 
-			mddev->raid_disks-mddev->degraded, mddev->raid_disks,
-			conf->algorithm);
+		       " devices, algorithm %d\n", conf->level, mdname(mddev),
+		       mddev->raid_disks-mddev->degraded, mddev->raid_disks,
+		       mddev->new_layout);
 	else
 		printk(KERN_ALERT "raid5: raid level %d set %s active with %d"
 			" out of %d devices, algorithm %d\n", conf->level,
 			mdname(mddev), mddev->raid_disks - mddev->degraded,
-			mddev->raid_disks, conf->algorithm);
+			mddev->raid_disks, mddev->new_layout);
 
 	print_raid5_conf(conf);
 
-	if (conf->expand_progress != MaxSector) {
+	if (conf->reshape_progress != MaxSector) {
 		printk("...ok start reshape thread\n");
-		conf->expand_lo = conf->expand_progress;
+		conf->reshape_safe = conf->reshape_progress;
 		atomic_set(&conf->reshape_stripes, 0);
 		clear_bit(MD_RECOVERY_SYNC, &mddev->recovery);
 		clear_bit(MD_RECOVERY_CHECK, &mddev->recovery);
@@ -4247,18 +4587,22 @@ static int run(mddev_t *mddev)
 		       "raid5: failed to create sysfs attributes for %s\n",
 		       mdname(mddev));
 
+	mddev->queue->queue_lock = &conf->device_lock;
+
 	mddev->queue->unplug_fn = raid5_unplug_device;
 	mddev->queue->backing_dev_info.congested_data = mddev;
 	mddev->queue->backing_dev_info.congested_fn = raid5_congested;
 
-	mddev->array_sectors = 2 * mddev->size * (conf->previous_raid_disks -
-					    conf->max_degraded);
+	md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
 
 	blk_queue_merge_bvec(mddev->queue, raid5_mergeable_bvec);
 
 	return 0;
 abort:
+	md_unregister_thread(mddev->thread);
+	mddev->thread = NULL;
 	if (conf) {
+		shrink_stripes(conf);
 		print_raid5_conf(conf);
 		safe_put_page(conf->spare_page);
 		kfree(conf->disks);
@@ -4396,6 +4740,10 @@ static int raid5_remove_disk(mddev_t *mddev, int number)
 	print_raid5_conf(conf);
 	rdev = p->rdev;
 	if (rdev) {
+		if (number >= conf->raid_disks &&
+		    conf->reshape_progress == MaxSector)
+			clear_bit(In_sync, &rdev->flags);
+
 		if (test_bit(In_sync, &rdev->flags) ||
 		    atomic_read(&rdev->nr_pending)) {
 			err = -EBUSY;
@@ -4405,7 +4753,8 @@ static int raid5_remove_disk(mddev_t *mddev, int number)
 		 * isn't possible.
 		 */
 		if (!test_bit(Faulty, &rdev->flags) &&
-		    mddev->degraded <= conf->max_degraded) {
+		    mddev->degraded <= conf->max_degraded &&
+		    number < conf->raid_disks) {
 			err = -EBUSY;
 			goto abort;
 		}
@@ -4472,36 +4821,48 @@ static int raid5_resize(mddev_t *mddev, sector_t sectors)
 	 * any io in the removed space completes, but it hardly seems
 	 * worth it.
 	 */
-	raid5_conf_t *conf = mddev_to_conf(mddev);
-
 	sectors &= ~((sector_t)mddev->chunk_size/512 - 1);
-	mddev->array_sectors = sectors * (mddev->raid_disks
-					  - conf->max_degraded);
+	md_set_array_sectors(mddev, raid5_size(mddev, sectors,
+					       mddev->raid_disks));
+	if (mddev->array_sectors >
+	    raid5_size(mddev, sectors, mddev->raid_disks))
+		return -EINVAL;
 	set_capacity(mddev->gendisk, mddev->array_sectors);
 	mddev->changed = 1;
-	if (sectors/2  > mddev->size && mddev->recovery_cp == MaxSector) {
-		mddev->recovery_cp = mddev->size << 1;
+	if (sectors > mddev->dev_sectors && mddev->recovery_cp == MaxSector) {
+		mddev->recovery_cp = mddev->dev_sectors;
 		set_bit(MD_RECOVERY_NEEDED, &mddev->recovery);
 	}
-	mddev->size = sectors /2;
+	mddev->dev_sectors = sectors;
 	mddev->resync_max_sectors = sectors;
 	return 0;
 }
 
-#ifdef CONFIG_MD_RAID5_RESHAPE
 static int raid5_check_reshape(mddev_t *mddev)
 {
 	raid5_conf_t *conf = mddev_to_conf(mddev);
-	int err;
 
-	if (mddev->delta_disks < 0 ||
-	    mddev->new_level != mddev->level)
-		return -EINVAL; /* Cannot shrink array or change level yet */
-	if (mddev->delta_disks == 0)
-		return 0; /* nothing to do */
+	if (mddev->delta_disks == 0 &&
+	    mddev->new_layout == mddev->layout &&
+	    mddev->new_chunk == mddev->chunk_size)
+		return -EINVAL; /* nothing to do */
 	if (mddev->bitmap)
 		/* Cannot grow a bitmap yet */
 		return -EBUSY;
+	if (mddev->degraded > conf->max_degraded)
+		return -EINVAL;
+	if (mddev->delta_disks < 0) {
+		/* We might be able to shrink, but the devices must
+		 * be made bigger first.
+		 * For raid6, 4 is the minimum size.
+		 * Otherwise 2 is the minimum
+		 */
+		int min = 2;
+		if (mddev->level == 6)
+			min = 4;
+		if (mddev->raid_disks + mddev->delta_disks < min)
+			return -EINVAL;
+	}
 
 	/* Can only proceed if there are plenty of stripe_heads.
 	 * We need a minimum of one full stripe,, and for sensible progress
@@ -4514,18 +4875,12 @@ static int raid5_check_reshape(mddev_t *mddev)
 	if ((mddev->chunk_size / STRIPE_SIZE) * 4 > conf->max_nr_stripes ||
 	    (mddev->new_chunk / STRIPE_SIZE) * 4 > conf->max_nr_stripes) {
 		printk(KERN_WARNING "raid5: reshape: not enough stripes.  Needed %lu\n",
-		       (mddev->chunk_size / STRIPE_SIZE)*4);
+		       (max(mddev->chunk_size, mddev->new_chunk)
+			/ STRIPE_SIZE)*4);
 		return -ENOSPC;
 	}
 
-	err = resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
-	if (err)
-		return err;
-
-	if (mddev->degraded > conf->max_degraded)
-		return -EINVAL;
-	/* looks like we might be able to manage this */
-	return 0;
+	return resize_stripes(conf, conf->raid_disks + mddev->delta_disks);
 }
 
 static int raid5_start_reshape(mddev_t *mddev)
@@ -4550,12 +4905,31 @@ static int raid5_start_reshape(mddev_t *mddev)
 		 */
 		return -EINVAL;
 
+	/* Refuse to reduce size of the array.  Any reductions in
+	 * array size must be through explicit setting of array_size
+	 * attribute.
+	 */
+	if (raid5_size(mddev, 0, conf->raid_disks + mddev->delta_disks)
+	    < mddev->array_sectors) {
+		printk(KERN_ERR "md: %s: array size must be reduced "
+		       "before number of disks\n", mdname(mddev));
+		return -EINVAL;
+	}
+
 	atomic_set(&conf->reshape_stripes, 0);
 	spin_lock_irq(&conf->device_lock);
 	conf->previous_raid_disks = conf->raid_disks;
 	conf->raid_disks += mddev->delta_disks;
-	conf->expand_progress = 0;
-	conf->expand_lo = 0;
+	conf->prev_chunk = conf->chunk_size;
+	conf->chunk_size = mddev->new_chunk;
+	conf->prev_algo = conf->algorithm;
+	conf->algorithm = mddev->new_layout;
+	if (mddev->delta_disks < 0)
+		conf->reshape_progress = raid5_size(mddev, 0, 0);
+	else
+		conf->reshape_progress = 0;
+	conf->reshape_safe = conf->reshape_progress;
+	conf->generation++;
 	spin_unlock_irq(&conf->device_lock);
 
 	/* Add some new drives, as many as will fit.
@@ -4580,9 +4954,12 @@ static int raid5_start_reshape(mddev_t *mddev)
 				break;
 		}
 
-	spin_lock_irqsave(&conf->device_lock, flags);
-	mddev->degraded = (conf->raid_disks - conf->previous_raid_disks) - added_devices;
-	spin_unlock_irqrestore(&conf->device_lock, flags);
+	if (mddev->delta_disks > 0) {
+		spin_lock_irqsave(&conf->device_lock, flags);
+		mddev->degraded = (conf->raid_disks - conf->previous_raid_disks)
+			- added_devices;
+		spin_unlock_irqrestore(&conf->device_lock, flags);
+	}
 	mddev->raid_disks = conf->raid_disks;
 	mddev->reshape_position = 0;
 	set_bit(MD_CHANGE_DEVS, &mddev->flags);
@@ -4597,52 +4974,86 @@ static int raid5_start_reshape(mddev_t *mddev)
 		mddev->recovery = 0;
 		spin_lock_irq(&conf->device_lock);
 		mddev->raid_disks = conf->raid_disks = conf->previous_raid_disks;
-		conf->expand_progress = MaxSector;
+		conf->reshape_progress = MaxSector;
 		spin_unlock_irq(&conf->device_lock);
 		return -EAGAIN;
 	}
+	conf->reshape_checkpoint = jiffies;
 	md_wakeup_thread(mddev->sync_thread);
 	md_new_event(mddev);
 	return 0;
 }
-#endif
 
+/* This is called from the reshape thread and should make any
+ * changes needed in 'conf'
+ */
 static void end_reshape(raid5_conf_t *conf)
 {
-	struct block_device *bdev;
 
 	if (!test_bit(MD_RECOVERY_INTR, &conf->mddev->recovery)) {
-		conf->mddev->array_sectors = 2 * conf->mddev->size *
-			(conf->raid_disks - conf->max_degraded);
-		set_capacity(conf->mddev->gendisk, conf->mddev->array_sectors);
-		conf->mddev->changed = 1;
-
-		bdev = bdget_disk(conf->mddev->gendisk, 0);
-		if (bdev) {
-			mutex_lock(&bdev->bd_inode->i_mutex);
-			i_size_write(bdev->bd_inode,
-				     (loff_t)conf->mddev->array_sectors << 9);
-			mutex_unlock(&bdev->bd_inode->i_mutex);
-			bdput(bdev);
-		}
+
 		spin_lock_irq(&conf->device_lock);
-		conf->expand_progress = MaxSector;
+		conf->previous_raid_disks = conf->raid_disks;
+		conf->reshape_progress = MaxSector;
 		spin_unlock_irq(&conf->device_lock);
-		conf->mddev->reshape_position = MaxSector;
+		wake_up(&conf->wait_for_overlap);
 
 		/* read-ahead size must cover two whole stripes, which is
 		 * 2 * (datadisks) * chunksize where 'n' is the number of raid devices
 		 */
 		{
-			int data_disks = conf->previous_raid_disks - conf->max_degraded;
-			int stripe = data_disks *
-				(conf->mddev->chunk_size / PAGE_SIZE);
+			int data_disks = conf->raid_disks - conf->max_degraded;
+			int stripe = data_disks * (conf->chunk_size
+						   / PAGE_SIZE);
 			if (conf->mddev->queue->backing_dev_info.ra_pages < 2 * stripe)
 				conf->mddev->queue->backing_dev_info.ra_pages = 2 * stripe;
 		}
 	}
 }
 
+/* This is called from the raid5d thread with mddev_lock held.
+ * It makes config changes to the device.
+ */
+static void raid5_finish_reshape(mddev_t *mddev)
+{
+	struct block_device *bdev;
+	raid5_conf_t *conf = mddev_to_conf(mddev);
+
+	if (!test_bit(MD_RECOVERY_INTR, &mddev->recovery)) {
+
+		if (mddev->delta_disks > 0) {
+			md_set_array_sectors(mddev, raid5_size(mddev, 0, 0));
+			set_capacity(mddev->gendisk, mddev->array_sectors);
+			mddev->changed = 1;
+
+			bdev = bdget_disk(mddev->gendisk, 0);
+			if (bdev) {
+				mutex_lock(&bdev->bd_inode->i_mutex);
+				i_size_write(bdev->bd_inode,
+					     (loff_t)mddev->array_sectors << 9);
+				mutex_unlock(&bdev->bd_inode->i_mutex);
+				bdput(bdev);
+			}
+		} else {
+			int d;
+			mddev->degraded = conf->raid_disks;
+			for (d = 0; d < conf->raid_disks ; d++)
+				if (conf->disks[d].rdev &&
+				    test_bit(In_sync,
+					     &conf->disks[d].rdev->flags))
+					mddev->degraded--;
+			for (d = conf->raid_disks ;
+			     d < conf->raid_disks - mddev->delta_disks;
+			     d++)
+				raid5_remove_disk(mddev, d);
+		}
+		mddev->layout = conf->algorithm;
+		mddev->chunk_size = conf->chunk_size;
+		mddev->reshape_position = MaxSector;
+		mddev->delta_disks = 0;
+	}
+}
+
 static void raid5_quiesce(mddev_t *mddev, int state)
 {
 	raid5_conf_t *conf = mddev_to_conf(mddev);
@@ -4672,6 +5083,212 @@ static void raid5_quiesce(mddev_t *mddev, int state)
 	}
 }
 
+
+static void *raid5_takeover_raid1(mddev_t *mddev)
+{
+	int chunksect;
+
+	if (mddev->raid_disks != 2 ||
+	    mddev->degraded > 1)
+		return ERR_PTR(-EINVAL);
+
+	/* Should check if there are write-behind devices? */
+
+	chunksect = 64*2; /* 64K by default */
+
+	/* The array must be an exact multiple of chunksize */
+	while (chunksect && (mddev->array_sectors & (chunksect-1)))
+		chunksect >>= 1;
+
+	if ((chunksect<<9) < STRIPE_SIZE)
+		/* array size does not allow a suitable chunk size */
+		return ERR_PTR(-EINVAL);
+
+	mddev->new_level = 5;
+	mddev->new_layout = ALGORITHM_LEFT_SYMMETRIC;
+	mddev->new_chunk = chunksect << 9;
+
+	return setup_conf(mddev);
+}
+
+static void *raid5_takeover_raid6(mddev_t *mddev)
+{
+	int new_layout;
+
+	switch (mddev->layout) {
+	case ALGORITHM_LEFT_ASYMMETRIC_6:
+		new_layout = ALGORITHM_LEFT_ASYMMETRIC;
+		break;
+	case ALGORITHM_RIGHT_ASYMMETRIC_6:
+		new_layout = ALGORITHM_RIGHT_ASYMMETRIC;
+		break;
+	case ALGORITHM_LEFT_SYMMETRIC_6:
+		new_layout = ALGORITHM_LEFT_SYMMETRIC;
+		break;
+	case ALGORITHM_RIGHT_SYMMETRIC_6:
+		new_layout = ALGORITHM_RIGHT_SYMMETRIC;
+		break;
+	case ALGORITHM_PARITY_0_6:
+		new_layout = ALGORITHM_PARITY_0;
+		break;
+	case ALGORITHM_PARITY_N:
+		new_layout = ALGORITHM_PARITY_N;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+	mddev->new_level = 5;
+	mddev->new_layout = new_layout;
+	mddev->delta_disks = -1;
+	mddev->raid_disks -= 1;
+	return setup_conf(mddev);
+}
+
+
+static int raid5_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
+{
+	/* For a 2-drive array, the layout and chunk size can be changed
+	 * immediately as not restriping is needed.
+	 * For larger arrays we record the new value - after validation
+	 * to be used by a reshape pass.
+	 */
+	raid5_conf_t *conf = mddev_to_conf(mddev);
+
+	if (new_layout >= 0 && !algorithm_valid_raid5(new_layout))
+		return -EINVAL;
+	if (new_chunk > 0) {
+		if (new_chunk & (new_chunk-1))
+			/* not a power of 2 */
+			return -EINVAL;
+		if (new_chunk < PAGE_SIZE)
+			return -EINVAL;
+		if (mddev->array_sectors & ((new_chunk>>9)-1))
+			/* not factor of array size */
+			return -EINVAL;
+	}
+
+	/* They look valid */
+
+	if (mddev->raid_disks == 2) {
+
+		if (new_layout >= 0) {
+			conf->algorithm = new_layout;
+			mddev->layout = mddev->new_layout = new_layout;
+		}
+		if (new_chunk > 0) {
+			conf->chunk_size = new_chunk;
+			mddev->chunk_size = mddev->new_chunk = new_chunk;
+		}
+		set_bit(MD_CHANGE_DEVS, &mddev->flags);
+		md_wakeup_thread(mddev->thread);
+	} else {
+		if (new_layout >= 0)
+			mddev->new_layout = new_layout;
+		if (new_chunk > 0)
+			mddev->new_chunk = new_chunk;
+	}
+	return 0;
+}
+
+static int raid6_reconfig(mddev_t *mddev, int new_layout, int new_chunk)
+{
+	if (new_layout >= 0 && !algorithm_valid_raid6(new_layout))
+		return -EINVAL;
+	if (new_chunk > 0) {
+		if (new_chunk & (new_chunk-1))
+			/* not a power of 2 */
+			return -EINVAL;
+		if (new_chunk < PAGE_SIZE)
+			return -EINVAL;
+		if (mddev->array_sectors & ((new_chunk>>9)-1))
+			/* not factor of array size */
+			return -EINVAL;
+	}
+
+	/* They look valid */
+
+	if (new_layout >= 0)
+		mddev->new_layout = new_layout;
+	if (new_chunk > 0)
+		mddev->new_chunk = new_chunk;
+
+	return 0;
+}
+
+static void *raid5_takeover(mddev_t *mddev)
+{
+	/* raid5 can take over:
+	 *  raid0 - if all devices are the same - make it a raid4 layout
+	 *  raid1 - if there are two drives.  We need to know the chunk size
+	 *  raid4 - trivial - just use a raid4 layout.
+	 *  raid6 - Providing it is a *_6 layout
+	 *
+	 * For now, just do raid1
+	 */
+
+	if (mddev->level == 1)
+		return raid5_takeover_raid1(mddev);
+	if (mddev->level == 4) {
+		mddev->new_layout = ALGORITHM_PARITY_N;
+		mddev->new_level = 5;
+		return setup_conf(mddev);
+	}
+	if (mddev->level == 6)
+		return raid5_takeover_raid6(mddev);
+
+	return ERR_PTR(-EINVAL);
+}
+
+
+static struct mdk_personality raid5_personality;
+
+static void *raid6_takeover(mddev_t *mddev)
+{
+	/* Currently can only take over a raid5.  We map the
+	 * personality to an equivalent raid6 personality
+	 * with the Q block at the end.
+	 */
+	int new_layout;
+
+	if (mddev->pers != &raid5_personality)
+		return ERR_PTR(-EINVAL);
+	if (mddev->degraded > 1)
+		return ERR_PTR(-EINVAL);
+	if (mddev->raid_disks > 253)
+		return ERR_PTR(-EINVAL);
+	if (mddev->raid_disks < 3)
+		return ERR_PTR(-EINVAL);
+
+	switch (mddev->layout) {
+	case ALGORITHM_LEFT_ASYMMETRIC:
+		new_layout = ALGORITHM_LEFT_ASYMMETRIC_6;
+		break;
+	case ALGORITHM_RIGHT_ASYMMETRIC:
+		new_layout = ALGORITHM_RIGHT_ASYMMETRIC_6;
+		break;
+	case ALGORITHM_LEFT_SYMMETRIC:
+		new_layout = ALGORITHM_LEFT_SYMMETRIC_6;
+		break;
+	case ALGORITHM_RIGHT_SYMMETRIC:
+		new_layout = ALGORITHM_RIGHT_SYMMETRIC_6;
+		break;
+	case ALGORITHM_PARITY_0:
+		new_layout = ALGORITHM_PARITY_0_6;
+		break;
+	case ALGORITHM_PARITY_N:
+		new_layout = ALGORITHM_PARITY_N;
+		break;
+	default:
+		return ERR_PTR(-EINVAL);
+	}
+	mddev->new_level = 6;
+	mddev->new_layout = new_layout;
+	mddev->delta_disks = 1;
+	mddev->raid_disks += 1;
+	return setup_conf(mddev);
+}
+
+
 static struct mdk_personality raid6_personality =
 {
 	.name		= "raid6",
@@ -4687,11 +5304,13 @@ static struct mdk_personality raid6_personality =
 	.spare_active	= raid5_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid5_resize,
-#ifdef CONFIG_MD_RAID5_RESHAPE
+	.size		= raid5_size,
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
-#endif
+	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
+	.takeover	= raid6_takeover,
+	.reconfig	= raid6_reconfig,
 };
 static struct mdk_personality raid5_personality =
 {
@@ -4708,11 +5327,13 @@ static struct mdk_personality raid5_personality =
 	.spare_active	= raid5_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid5_resize,
-#ifdef CONFIG_MD_RAID5_RESHAPE
+	.size		= raid5_size,
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
-#endif
+	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
+	.takeover	= raid5_takeover,
+	.reconfig	= raid5_reconfig,
 };
 
 static struct mdk_personality raid4_personality =
@@ -4730,20 +5351,15 @@ static struct mdk_personality raid4_personality =
 	.spare_active	= raid5_spare_active,
 	.sync_request	= sync_request,
 	.resize		= raid5_resize,
-#ifdef CONFIG_MD_RAID5_RESHAPE
+	.size		= raid5_size,
 	.check_reshape	= raid5_check_reshape,
 	.start_reshape  = raid5_start_reshape,
-#endif
+	.finish_reshape = raid5_finish_reshape,
 	.quiesce	= raid5_quiesce,
 };
 
 static int __init raid5_init(void)
 {
-	int e;
-
-	e = raid6_select_algo();
-	if ( e )
-		return e;
 	register_md_personality(&raid6_personality);
 	register_md_personality(&raid5_personality);
 	register_md_personality(&raid4_personality);
diff --git a/include/linux/raid/raid5.h b/drivers/md/raid5.h
index 3b2672792457..52ba99954dec 100644
--- a/include/linux/raid/raid5.h
+++ b/drivers/md/raid5.h
@@ -1,7 +1,6 @@
 #ifndef _RAID5_H
 #define _RAID5_H
 
-#include <linux/raid/md.h>
 #include <linux/raid/xor.h>
 
 /*
@@ -197,15 +196,19 @@ enum reconstruct_states {
 
 struct stripe_head {
 	struct hlist_node	hash;
-	struct list_head	lru;			/* inactive_list or handle_list */
-	struct raid5_private_data	*raid_conf;
-	sector_t		sector;			/* sector of this row */
-	int			pd_idx;			/* parity disk index */
-	unsigned long		state;			/* state flags */
-	atomic_t		count;			/* nr of active thread/requests */
+	struct list_head	lru;	      /* inactive_list or handle_list */
+	struct raid5_private_data *raid_conf;
+	short			generation;	/* increments with every
+						 * reshape */
+	sector_t		sector;		/* sector of this row */
+	short			pd_idx;		/* parity disk index */
+	short			qd_idx;		/* 'Q' disk index for raid6 */
+	short			ddf_layout;/* use DDF ordering to calculate Q */
+	unsigned long		state;		/* state flags */
+	atomic_t		count;	      /* nr of active thread/requests */
 	spinlock_t		lock;
 	int			bm_seq;	/* sequence number for bitmap flushes */
-	int			disks;			/* disks in stripe */
+	int			disks;		/* disks in stripe */
 	enum check_states	check_state;
 	enum reconstruct_states reconstruct_state;
 	/* stripe_operations
@@ -238,7 +241,7 @@ struct stripe_head_state {
 
 /* r6_state - extra state data only relevant to r6 */
 struct r6_state {
-	int p_failed, q_failed, qd_idx, failed_num[2];
+	int p_failed, q_failed, failed_num[2];
 };
 
 /* Flags */
@@ -268,6 +271,8 @@ struct r6_state {
 #define READ_MODIFY_WRITE	2
 /* not a write method, but a compute_parity mode */
 #define	CHECK_PARITY		3
+/* Additional compute_parity mode -- updates the parity w/o LOCKING */
+#define UPDATE_PARITY		4
 
 /*
  * Stripe state
@@ -319,7 +324,7 @@ struct r6_state {
  * PREREAD_ACTIVE is set, else we set DELAYED which will send it to the delayed queue.
  * HANDLE gets cleared if stripe_handle leave nothing locked.
  */
- 
+
 
 struct disk_info {
 	mdk_rdev_t	*rdev;
@@ -334,12 +339,21 @@ struct raid5_private_data {
 	int			raid_disks;
 	int			max_nr_stripes;
 
-	/* used during an expand */
-	sector_t		expand_progress;	/* MaxSector when no expand happening */
-	sector_t		expand_lo; /* from here up to expand_progress it out-of-bounds
-					    * as we haven't flushed the metadata yet
-					    */
+	/* reshape_progress is the leading edge of a 'reshape'
+	 * It has value MaxSector when no reshape is happening
+	 * If delta_disks < 0, it is the last sector we started work on,
+	 * else is it the next sector to work on.
+	 */
+	sector_t		reshape_progress;
+	/* reshape_safe is the trailing edge of a reshape.  We know that
+	 * before (or after) this address, all reshape has completed.
+	 */
+	sector_t		reshape_safe;
 	int			previous_raid_disks;
+	int			prev_chunk, prev_algo;
+	short			generation; /* increments with every reshape */
+	unsigned long		reshape_checkpoint; /* Time we last updated
+						     * metadata */
 
 	struct list_head	handle_list; /* stripes needing handling */
 	struct list_head	hold_list; /* preread ready stripes */
@@ -385,6 +399,11 @@ struct raid5_private_data {
 	int			pool_size; /* number of disks in stripeheads in pool */
 	spinlock_t		device_lock;
 	struct disk_info	*disks;
+
+	/* When taking over an array from a different personality, we store
+	 * the new thread here until we fully activate the array.
+	 */
+	struct mdk_thread_s	*thread;
 };
 
 typedef struct raid5_private_data raid5_conf_t;
@@ -394,9 +413,62 @@ typedef struct raid5_private_data raid5_conf_t;
 /*
  * Our supported algorithms
  */
-#define ALGORITHM_LEFT_ASYMMETRIC	0
-#define ALGORITHM_RIGHT_ASYMMETRIC	1
-#define ALGORITHM_LEFT_SYMMETRIC	2
-#define ALGORITHM_RIGHT_SYMMETRIC	3
+#define ALGORITHM_LEFT_ASYMMETRIC	0 /* Rotating Parity N with Data Restart */
+#define ALGORITHM_RIGHT_ASYMMETRIC	1 /* Rotating Parity 0 with Data Restart */
+#define ALGORITHM_LEFT_SYMMETRIC	2 /* Rotating Parity N with Data Continuation */
+#define ALGORITHM_RIGHT_SYMMETRIC	3 /* Rotating Parity 0 with Data Continuation */
+
+/* Define non-rotating (raid4) algorithms.  These allow
+ * conversion of raid4 to raid5.
+ */
+#define ALGORITHM_PARITY_0		4 /* P or P,Q are initial devices */
+#define ALGORITHM_PARITY_N		5 /* P or P,Q are final devices. */
+
+/* DDF RAID6 layouts differ from md/raid6 layouts in two ways.
+ * Firstly, the exact positioning of the parity block is slightly
+ * different between the 'LEFT_*' modes of md and the "_N_*" modes
+ * of DDF.
+ * Secondly, or order of datablocks over which the Q syndrome is computed
+ * is different.
+ * Consequently we have different layouts for DDF/raid6 than md/raid6.
+ * These layouts are from the DDFv1.2 spec.
+ * Interestingly DDFv1.2-Errata-A does not specify N_CONTINUE but
+ * leaves RLQ=3 as 'Vendor Specific'
+ */
+
+#define ALGORITHM_ROTATING_ZERO_RESTART	8 /* DDF PRL=6 RLQ=1 */
+#define ALGORITHM_ROTATING_N_RESTART	9 /* DDF PRL=6 RLQ=2 */
+#define ALGORITHM_ROTATING_N_CONTINUE	10 /*DDF PRL=6 RLQ=3 */
+
+
+/* For every RAID5 algorithm we define a RAID6 algorithm
+ * with exactly the same layout for data and parity, and
+ * with the Q block always on the last device (N-1).
+ * This allows trivial conversion from RAID5 to RAID6
+ */
+#define ALGORITHM_LEFT_ASYMMETRIC_6	16
+#define ALGORITHM_RIGHT_ASYMMETRIC_6	17
+#define ALGORITHM_LEFT_SYMMETRIC_6	18
+#define ALGORITHM_RIGHT_SYMMETRIC_6	19
+#define ALGORITHM_PARITY_0_6		20
+#define ALGORITHM_PARITY_N_6		ALGORITHM_PARITY_N
+
+static inline int algorithm_valid_raid5(int layout)
+{
+	return (layout >= 0) &&
+		(layout <= 5);
+}
+static inline int algorithm_valid_raid6(int layout)
+{
+	return (layout >= 0 && layout <= 5)
+		||
+		(layout == 8 || layout == 10)
+		||
+		(layout >= 16 && layout <= 20);
+}
 
+static inline int algorithm_is_DDF(int layout)
+{
+	return layout >= 8 && layout <= 10;
+}
 #endif
diff --git a/drivers/md/raid6algos.c b/drivers/md/raid6algos.c
index 21987e3dbe6c..866215ac7f25 100644
--- a/drivers/md/raid6algos.c
+++ b/drivers/md/raid6algos.c
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -16,13 +16,20 @@
  * Algorithm list and algorithm selection for RAID-6
  */
 
-#include "raid6.h"
+#include <linux/raid/pq.h>
 #ifndef __KERNEL__
 #include <sys/mman.h>
 #include <stdio.h>
+#else
+#if !RAID6_USE_EMPTY_ZERO_PAGE
+/* In .bss so it's zeroed */
+const char raid6_empty_zero_page[PAGE_SIZE] __attribute__((aligned(256)));
+EXPORT_SYMBOL(raid6_empty_zero_page);
+#endif
 #endif
 
 struct raid6_calls raid6_call;
+EXPORT_SYMBOL_GPL(raid6_call);
 
 /* Various routine sets */
 extern const struct raid6_calls raid6_intx1;
@@ -79,6 +86,7 @@ const struct raid6_calls * const raid6_algos[] = {
 #else
 /* Need more time to be stable in userspace */
 #define RAID6_TIME_JIFFIES_LG2	9
+#define time_before(x, y) ((x) < (y))
 #endif
 
 /* Try to pick the best algorithm */
@@ -152,3 +160,12 @@ int __init raid6_select_algo(void)
 
 	return best ? 0 : -EINVAL;
 }
+
+static void raid6_exit(void)
+{
+	do { } while (0);
+}
+
+subsys_initcall(raid6_select_algo);
+module_exit(raid6_exit);
+MODULE_LICENSE("GPL");
diff --git a/drivers/md/raid6altivec.uc b/drivers/md/raid6altivec.uc
index b9afd35b8812..699dfeee4944 100644
--- a/drivers/md/raid6altivec.uc
+++ b/drivers/md/raid6altivec.uc
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -22,7 +22,7 @@
  * bracked this with preempt_disable/enable or in a lock)
  */
 
-#include "raid6.h"
+#include <linux/raid/pq.h>
 
 #ifdef CONFIG_ALTIVEC
 
diff --git a/drivers/md/raid6int.uc b/drivers/md/raid6int.uc
index ad004cee0e26..f9bf9cba357f 100644
--- a/drivers/md/raid6int.uc
+++ b/drivers/md/raid6int.uc
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -18,7 +18,7 @@
  * This file is postprocessed using unroll.pl
  */
 
-#include "raid6.h"
+#include <linux/raid/pq.h>
 
 /*
  * This is the C data type to use
diff --git a/drivers/md/raid6mmx.c b/drivers/md/raid6mmx.c
index d4e4a1bd70ad..e7f6c13132bf 100644
--- a/drivers/md/raid6mmx.c
+++ b/drivers/md/raid6mmx.c
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -18,7 +18,7 @@
 
 #if defined(__i386__) && !defined(__arch_um__)
 
-#include "raid6.h"
+#include <linux/raid/pq.h>
 #include "raid6x86.h"
 
 /* Shared with raid6sse1.c */
diff --git a/drivers/md/raid6recov.c b/drivers/md/raid6recov.c
index a8c4d9451bd9..2609f00e0d61 100644
--- a/drivers/md/raid6recov.c
+++ b/drivers/md/raid6recov.c
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -18,7 +18,7 @@
  * the syndrome.)
  */
 
-#include "raid6.h"
+#include <linux/raid/pq.h>
 
 /* Recover two failed data blocks. */
 void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
@@ -63,9 +63,7 @@ void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
 		p++; q++;
 	}
 }
-
-
-
+EXPORT_SYMBOL_GPL(raid6_2data_recov);
 
 /* Recover failure of one data block plus the P block */
 void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs)
@@ -97,9 +95,10 @@ void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs)
 		q++; dq++;
 	}
 }
+EXPORT_SYMBOL_GPL(raid6_datap_recov);
 
-
-#ifndef __KERNEL__		/* Testing only */
+#ifndef __KERNEL__
+/* Testing only */
 
 /* Recover two failed blocks. */
 void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, void **ptrs)
diff --git a/drivers/md/raid6sse1.c b/drivers/md/raid6sse1.c
index 0666237276ff..b274dd5eab8f 100644
--- a/drivers/md/raid6sse1.c
+++ b/drivers/md/raid6sse1.c
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -23,7 +23,7 @@
 
 #if defined(__i386__) && !defined(__arch_um__)
 
-#include "raid6.h"
+#include <linux/raid/pq.h>
 #include "raid6x86.h"
 
 /* Defined in raid6mmx.c */
diff --git a/drivers/md/raid6sse2.c b/drivers/md/raid6sse2.c
index b034ad868039..6ed6c6c0389f 100644
--- a/drivers/md/raid6sse2.c
+++ b/drivers/md/raid6sse2.c
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -19,7 +19,7 @@
 
 #if (defined(__i386__) || defined(__x86_64__)) && !defined(__arch_um__)
 
-#include "raid6.h"
+#include <linux/raid/pq.h>
 #include "raid6x86.h"
 
 static const struct raid6_sse_constants {
diff --git a/drivers/md/raid6test/Makefile b/drivers/md/raid6test/Makefile
index 78e0396adf2a..58ffdf4f5161 100644
--- a/drivers/md/raid6test/Makefile
+++ b/drivers/md/raid6test/Makefile
@@ -5,7 +5,7 @@
 
 CC	 = gcc
 OPTFLAGS = -O2			# Adjust as desired
-CFLAGS	 = -I.. -g $(OPTFLAGS)
+CFLAGS	 = -I.. -I ../../../include -g $(OPTFLAGS)
 LD	 = ld
 PERL	 = perl
 AR	 = ar
diff --git a/drivers/md/raid6test/test.c b/drivers/md/raid6test/test.c
index 559cc41b2585..7a930318b17d 100644
--- a/drivers/md/raid6test/test.c
+++ b/drivers/md/raid6test/test.c
@@ -17,7 +17,7 @@
 #include <stdlib.h>
 #include <stdio.h>
 #include <string.h>
-#include "raid6.h"
+#include <linux/raid/pq.h>
 
 #define NDISKS		16	/* Including P and Q */
 
diff --git a/drivers/md/raid6x86.h b/drivers/md/raid6x86.h
index 99fea7a70ca7..4c22c1568558 100644
--- a/drivers/md/raid6x86.h
+++ b/drivers/md/raid6x86.h
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
diff --git a/drivers/media/common/tuners/Kconfig b/drivers/media/common/tuners/Kconfig
index 52c3f65b12d6..607d319ce8ed 100644
--- a/drivers/media/common/tuners/Kconfig
+++ b/drivers/media/common/tuners/Kconfig
@@ -148,7 +148,7 @@ config MEDIA_TUNER_XC5000
 	default m if MEDIA_TUNER_CUSTOMISE
 	help
 	  A driver for the silicon tuner XC5000 from Xceive.
-	  This device is only used inside a SiP called togther with a
+	  This device is only used inside a SiP called together with a
 	  demodulator for now.
 
 config MEDIA_TUNER_MXL5005S
diff --git a/drivers/media/dvb/frontends/Kconfig b/drivers/media/dvb/frontends/Kconfig
index a206cee23f73..a486a7f81fa9 100644
--- a/drivers/media/dvb/frontends/Kconfig
+++ b/drivers/media/dvb/frontends/Kconfig
@@ -479,7 +479,7 @@ config DVB_TUNER_DIB0070
 	default m if DVB_FE_CUSTOMISE
 	help
 	  A driver for the silicon baseband tuner DiB0070 from DiBcom.
-	  This device is only used inside a SiP called togther with a
+	  This device is only used inside a SiP called together with a
 	  demodulator for now.
 
 comment "SEC control devices for DVB-S"
diff --git a/drivers/media/dvb/frontends/drx397xD.c b/drivers/media/dvb/frontends/drx397xD.c
index 1e81e713df63..172f1f928f02 100644
--- a/drivers/media/dvb/frontends/drx397xD.c
+++ b/drivers/media/dvb/frontends/drx397xD.c
@@ -74,7 +74,7 @@ static struct {
 } fw[] = {
 #define _FW_ENTRY(a, b, c)	{					\
 			.name	= a,					\
-			.file	= 0,					\
+			.file	= NULL,					\
 			.lock	= __RW_LOCK_UNLOCKED(fw[c].lock),	\
 			.refcnt = 0,					\
 			.data	= { }		}
diff --git a/drivers/mfd/Kconfig b/drivers/mfd/Kconfig
index 06a2b0f7737c..75f35dbb11dc 100644
--- a/drivers/mfd/Kconfig
+++ b/drivers/mfd/Kconfig
@@ -88,7 +88,7 @@ config MENELAUS
 	help
 	  If you say yes here you get support for the Texas Instruments
 	  TWL92330/Menelaus Power Management chip. This include voltage
-	  regulators, Dual slot memory card tranceivers, real-time clock
+	  regulators, Dual slot memory card transceivers, real-time clock
 	  and other features that are often used in portable devices like
 	  cell phones and PDAs.
 
diff --git a/drivers/mfd/twl4030-core.c b/drivers/mfd/twl4030-core.c
index 68826f1e36bc..ec90e953adce 100644
--- a/drivers/mfd/twl4030-core.c
+++ b/drivers/mfd/twl4030-core.c
@@ -592,11 +592,9 @@ add_children(struct twl4030_platform_data *pdata, unsigned long features)
 
 	/* maybe add LDOs that are omitted on cost-reduced parts */
 	if (twl_has_regulator() && !(features & TPS_SUBSET)) {
-		/*
 		child = add_regulator(TWL4030_REG_VPLL2, pdata->vpll2);
 		if (IS_ERR(child))
 			return PTR_ERR(child);
-		*/
 
 		child = add_regulator(TWL4030_REG_VMMC2, pdata->vmmc2);
 		if (IS_ERR(child))
diff --git a/drivers/misc/Kconfig b/drivers/misc/Kconfig
index 5f3bff434621..6d1ac180f6ee 100644
--- a/drivers/misc/Kconfig
+++ b/drivers/misc/Kconfig
@@ -18,8 +18,8 @@ config ATMEL_PWM
 	depends on AVR32 || ARCH_AT91SAM9263 || ARCH_AT91SAM9RL || ARCH_AT91CAP9
 	help
 	  This option enables device driver support for the PWM channels
-	  on certain Atmel prcoessors.  Pulse Width Modulation is used for
-	  purposes including software controlled power-efficent backlights
+	  on certain Atmel processors.  Pulse Width Modulation is used for
+	  purposes including software controlled power-efficient backlights
 	  on LCD displays, motor control, and waveform generation.
 
 config ATMEL_TCLIB
@@ -142,7 +142,7 @@ config ATMEL_SSC
 	tristate "Device driver for Atmel SSC peripheral"
 	depends on AVR32 || ARCH_AT91
 	---help---
-	  This option enables device driver support for Atmel Syncronized
+	  This option enables device driver support for Atmel Synchronized
 	  Serial Communication peripheral (SSC).
 
 	  The SSC peripheral supports a wide variety of serial frame based
@@ -165,7 +165,7 @@ config SGI_XP
 	depends on (IA64_GENERIC || IA64_SGI_SN2 || IA64_SGI_UV || X86_UV) && SMP
 	select IA64_UNCACHED_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2
 	select GENERIC_ALLOCATOR if IA64_GENERIC || IA64_SGI_SN2
-	select SGI_GRU if (IA64_GENERIC || IA64_SGI_UV || X86_64) && SMP
+	select SGI_GRU if X86_64 && SMP
 	---help---
 	  An SGI machine can be divided into multiple Single System
 	  Images which act independently of each other and have
@@ -189,7 +189,7 @@ config HP_ILO
 
 config SGI_GRU
 	tristate "SGI GRU driver"
-	depends on (X86_UV || IA64_SGI_UV || IA64_GENERIC) && SMP
+	depends on X86_UV && SMP
 	default n
 	select MMU_NOTIFIER
 	---help---
diff --git a/drivers/misc/eeprom/at24.c b/drivers/misc/eeprom/at24.c
index d4775528abc6..d184dfab9631 100644
--- a/drivers/misc/eeprom/at24.c
+++ b/drivers/misc/eeprom/at24.c
@@ -53,6 +53,7 @@
 
 struct at24_data {
 	struct at24_platform_data chip;
+	struct memory_accessor macc;
 	bool use_smbus;
 
 	/*
@@ -225,14 +226,11 @@ static ssize_t at24_eeprom_read(struct at24_data *at24, char *buf,
 		return status;
 }
 
-static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr,
+static ssize_t at24_read(struct at24_data *at24,
 		char *buf, loff_t off, size_t count)
 {
-	struct at24_data *at24;
 	ssize_t retval = 0;
 
-	at24 = dev_get_drvdata(container_of(kobj, struct device, kobj));
-
 	if (unlikely(!count))
 		return count;
 
@@ -262,12 +260,14 @@ static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr,
 	return retval;
 }
 
+static ssize_t at24_bin_read(struct kobject *kobj, struct bin_attribute *attr,
+		char *buf, loff_t off, size_t count)
+{
+	struct at24_data *at24;
 
-/*
- * REVISIT: export at24_bin{read,write}() to let other kernel code use
- * eeprom data. For example, it might hold a board's Ethernet address, or
- * board-specific calibration data generated on the manufacturing floor.
- */
+	at24 = dev_get_drvdata(container_of(kobj, struct device, kobj));
+	return at24_read(at24, buf, off, count);
+}
 
 
 /*
@@ -347,14 +347,11 @@ static ssize_t at24_eeprom_write(struct at24_data *at24, char *buf,
 	return -ETIMEDOUT;
 }
 
-static ssize_t at24_bin_write(struct kobject *kobj, struct bin_attribute *attr,
+static ssize_t at24_write(struct at24_data *at24,
 		char *buf, loff_t off, size_t count)
 {
-	struct at24_data *at24;
 	ssize_t retval = 0;
 
-	at24 = dev_get_drvdata(container_of(kobj, struct device, kobj));
-
 	if (unlikely(!count))
 		return count;
 
@@ -384,6 +381,39 @@ static ssize_t at24_bin_write(struct kobject *kobj, struct bin_attribute *attr,
 	return retval;
 }
 
+static ssize_t at24_bin_write(struct kobject *kobj, struct bin_attribute *attr,
+		char *buf, loff_t off, size_t count)
+{
+	struct at24_data *at24;
+
+	at24 = dev_get_drvdata(container_of(kobj, struct device, kobj));
+	return at24_write(at24, buf, off, count);
+}
+
+/*-------------------------------------------------------------------------*/
+
+/*
+ * This lets other kernel code access the eeprom data. For example, it
+ * might hold a board's Ethernet address, or board-specific calibration
+ * data generated on the manufacturing floor.
+ */
+
+static ssize_t at24_macc_read(struct memory_accessor *macc, char *buf,
+			 off_t offset, size_t count)
+{
+	struct at24_data *at24 = container_of(macc, struct at24_data, macc);
+
+	return at24_read(at24, buf, offset, count);
+}
+
+static ssize_t at24_macc_write(struct memory_accessor *macc, char *buf,
+			  off_t offset, size_t count)
+{
+	struct at24_data *at24 = container_of(macc, struct at24_data, macc);
+
+	return at24_write(at24, buf, offset, count);
+}
+
 /*-------------------------------------------------------------------------*/
 
 static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id)
@@ -413,6 +443,9 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		 * is recommended anyhow.
 		 */
 		chip.page_size = 1;
+
+		chip.setup = NULL;
+		chip.context = NULL;
 	}
 
 	if (!is_power_of_2(chip.byte_len))
@@ -463,6 +496,8 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id)
 	at24->bin.read = at24_bin_read;
 	at24->bin.size = chip.byte_len;
 
+	at24->macc.read = at24_macc_read;
+
 	writable = !(chip.flags & AT24_FLAG_READONLY);
 	if (writable) {
 		if (!use_smbus || i2c_check_functionality(client->adapter,
@@ -470,6 +505,8 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id)
 
 			unsigned write_max = chip.page_size;
 
+			at24->macc.write = at24_macc_write;
+
 			at24->bin.write = at24_bin_write;
 			at24->bin.attr.mode |= S_IWUSR;
 
@@ -520,6 +557,10 @@ static int at24_probe(struct i2c_client *client, const struct i2c_device_id *id)
 		at24->write_max,
 		use_smbus ? ", use_smbus" : "");
 
+	/* export data to kernel code */
+	if (chip.setup)
+		chip.setup(&at24->macc, chip.context);
+
 	return 0;
 
 err_clients:
diff --git a/drivers/misc/eeprom/at25.c b/drivers/misc/eeprom/at25.c
index 290dbe99647a..6bc0dac5c1e8 100644
--- a/drivers/misc/eeprom/at25.c
+++ b/drivers/misc/eeprom/at25.c
@@ -30,6 +30,7 @@
 
 struct at25_data {
 	struct spi_device	*spi;
+	struct memory_accessor	mem;
 	struct mutex		lock;
 	struct spi_eeprom	chip;
 	struct bin_attribute	bin;
@@ -75,6 +76,13 @@ at25_ee_read(
 	struct spi_transfer	t[2];
 	struct spi_message	m;
 
+	if (unlikely(offset >= at25->bin.size))
+		return 0;
+	if ((offset + count) > at25->bin.size)
+		count = at25->bin.size - offset;
+	if (unlikely(!count))
+		return count;
+
 	cp = command;
 	*cp++ = AT25_READ;
 
@@ -127,13 +135,6 @@ at25_bin_read(struct kobject *kobj, struct bin_attribute *bin_attr,
 	dev = container_of(kobj, struct device, kobj);
 	at25 = dev_get_drvdata(dev);
 
-	if (unlikely(off >= at25->bin.size))
-		return 0;
-	if ((off + count) > at25->bin.size)
-		count = at25->bin.size - off;
-	if (unlikely(!count))
-		return count;
-
 	return at25_ee_read(at25, buf, off, count);
 }
 
@@ -146,6 +147,13 @@ at25_ee_write(struct at25_data *at25, char *buf, loff_t off, size_t count)
 	unsigned		buf_size;
 	u8			*bounce;
 
+	if (unlikely(off >= at25->bin.size))
+		return -EFBIG;
+	if ((off + count) > at25->bin.size)
+		count = at25->bin.size - off;
+	if (unlikely(!count))
+		return count;
+
 	/* Temp buffer starts with command and address */
 	buf_size = at25->chip.page_size;
 	if (buf_size > io_limit)
@@ -253,18 +261,31 @@ at25_bin_write(struct kobject *kobj, struct bin_attribute *bin_attr,
 	dev = container_of(kobj, struct device, kobj);
 	at25 = dev_get_drvdata(dev);
 
-	if (unlikely(off >= at25->bin.size))
-		return -EFBIG;
-	if ((off + count) > at25->bin.size)
-		count = at25->bin.size - off;
-	if (unlikely(!count))
-		return count;
-
 	return at25_ee_write(at25, buf, off, count);
 }
 
 /*-------------------------------------------------------------------------*/
 
+/* Let in-kernel code access the eeprom data. */
+
+static ssize_t at25_mem_read(struct memory_accessor *mem, char *buf,
+			 off_t offset, size_t count)
+{
+	struct at25_data *at25 = container_of(mem, struct at25_data, mem);
+
+	return at25_ee_read(at25, buf, offset, count);
+}
+
+static ssize_t at25_mem_write(struct memory_accessor *mem, char *buf,
+			  off_t offset, size_t count)
+{
+	struct at25_data *at25 = container_of(mem, struct at25_data, mem);
+
+	return at25_ee_write(at25, buf, offset, count);
+}
+
+/*-------------------------------------------------------------------------*/
+
 static int at25_probe(struct spi_device *spi)
 {
 	struct at25_data	*at25 = NULL;
@@ -317,6 +338,10 @@ static int at25_probe(struct spi_device *spi)
 	at25->addrlen = addrlen;
 
 	/* Export the EEPROM bytes through sysfs, since that's convenient.
+	 * And maybe to other kernel code; it might hold a board's Ethernet
+	 * address, or board-specific calibration data generated on the
+	 * manufacturing floor.
+	 *
 	 * Default to root-only access to the data; EEPROMs often hold data
 	 * that's sensitive for read and/or write, like ethernet addresses,
 	 * security codes, board-specific manufacturing calibrations, etc.
@@ -324,17 +349,22 @@ static int at25_probe(struct spi_device *spi)
 	at25->bin.attr.name = "eeprom";
 	at25->bin.attr.mode = S_IRUSR;
 	at25->bin.read = at25_bin_read;
+	at25->mem.read = at25_mem_read;
 
 	at25->bin.size = at25->chip.byte_len;
 	if (!(chip->flags & EE_READONLY)) {
 		at25->bin.write = at25_bin_write;
 		at25->bin.attr.mode |= S_IWUSR;
+		at25->mem.write = at25_mem_write;
 	}
 
 	err = sysfs_create_bin_file(&spi->dev.kobj, &at25->bin);
 	if (err)
 		goto fail;
 
+	if (chip->setup)
+		chip->setup(&at25->mem, chip->context);
+
 	dev_info(&spi->dev, "%Zd %s %s eeprom%s, pagesize %u\n",
 		(at25->bin.size < 1024)
 			? at25->bin.size
diff --git a/drivers/misc/sgi-gru/Makefile b/drivers/misc/sgi-gru/Makefile
index 9e9170b3599a..bcd8136d2f98 100644
--- a/drivers/misc/sgi-gru/Makefile
+++ b/drivers/misc/sgi-gru/Makefile
@@ -3,5 +3,5 @@ ifdef CONFIG_SGI_GRU_DEBUG
 endif
 
 obj-$(CONFIG_SGI_GRU) := gru.o
-gru-y := grufile.o grumain.o grufault.o grutlbpurge.o gruprocfs.o grukservices.o
+gru-y := grufile.o grumain.o grufault.o grutlbpurge.o gruprocfs.o grukservices.o gruhandles.o
 
diff --git a/drivers/misc/sgi-gru/gru_instructions.h b/drivers/misc/sgi-gru/gru_instructions.h
index 48762e7b98be..3fde33c1e8f3 100644
--- a/drivers/misc/sgi-gru/gru_instructions.h
+++ b/drivers/misc/sgi-gru/gru_instructions.h
@@ -19,8 +19,11 @@
 #ifndef __GRU_INSTRUCTIONS_H__
 #define __GRU_INSTRUCTIONS_H__
 
-#define gru_flush_cache_hook(p)
-#define gru_emulator_wait_hook(p, w)
+extern int gru_check_status_proc(void *cb);
+extern int gru_wait_proc(void *cb);
+extern void gru_wait_abort_proc(void *cb);
+
+
 
 /*
  * Architecture dependent functions
@@ -29,16 +32,16 @@
 #if defined(CONFIG_IA64)
 #include <linux/compiler.h>
 #include <asm/intrinsics.h>
-#define __flush_cache(p)		ia64_fc(p)
+#define __flush_cache(p)		ia64_fc((unsigned long)p)
 /* Use volatile on IA64 to ensure ordering via st4.rel */
-#define gru_ordered_store_int(p,v)					\
+#define gru_ordered_store_int(p, v)					\
 		do {							\
 			barrier();					\
 			*((volatile int *)(p)) = v; /* force st.rel */	\
 		} while (0)
 #elif defined(CONFIG_X86_64)
 #define __flush_cache(p)		clflush(p)
-#define gru_ordered_store_int(p,v)					\
+#define gru_ordered_store_int(p, v)					\
 		do {							\
 			barrier();					\
 			*(int *)p = v;					\
@@ -558,20 +561,19 @@ extern int gru_get_cb_exception_detail(void *cb,
 
 #define GRU_EXC_STR_SIZE		256
 
-extern int gru_check_status_proc(void *cb);
-extern int gru_wait_proc(void *cb);
-extern void gru_wait_abort_proc(void *cb);
 
 /*
  * Control block definition for checking status
  */
 struct gru_control_block_status {
 	unsigned int	icmd		:1;
-	unsigned int	unused1		:31;
+	unsigned int	ima		:3;
+	unsigned int	reserved0	:4;
+	unsigned int	unused1		:24;
 	unsigned int	unused2		:24;
 	unsigned int	istatus		:2;
 	unsigned int	isubstatus	:4;
-	unsigned int	inused3		:2;
+	unsigned int	unused3		:2;
 };
 
 /* Get CB status */
diff --git a/drivers/misc/sgi-gru/grufault.c b/drivers/misc/sgi-gru/grufault.c
index 3ee698ad8599..ab118558552e 100644
--- a/drivers/misc/sgi-gru/grufault.c
+++ b/drivers/misc/sgi-gru/grufault.c
@@ -32,6 +32,7 @@
 #include <linux/device.h>
 #include <linux/io.h>
 #include <linux/uaccess.h>
+#include <linux/security.h>
 #include <asm/pgtable.h>
 #include "gru.h"
 #include "grutables.h"
@@ -266,6 +267,44 @@ err:
 	return 1;
 }
 
+static int gru_vtop(struct gru_thread_state *gts, unsigned long vaddr,
+		    int write, int atomic, unsigned long *gpa, int *pageshift)
+{
+	struct mm_struct *mm = gts->ts_mm;
+	struct vm_area_struct *vma;
+	unsigned long paddr;
+	int ret, ps;
+
+	vma = find_vma(mm, vaddr);
+	if (!vma)
+		goto inval;
+
+	/*
+	 * Atomic lookup is faster & usually works even if called in non-atomic
+	 * context.
+	 */
+	rmb();	/* Must/check ms_range_active before loading PTEs */
+	ret = atomic_pte_lookup(vma, vaddr, write, &paddr, &ps);
+	if (ret) {
+		if (atomic)
+			goto upm;
+		if (non_atomic_pte_lookup(vma, vaddr, write, &paddr, &ps))
+			goto inval;
+	}
+	if (is_gru_paddr(paddr))
+		goto inval;
+	paddr = paddr & ~((1UL << ps) - 1);
+	*gpa = uv_soc_phys_ram_to_gpa(paddr);
+	*pageshift = ps;
+	return 0;
+
+inval:
+	return -1;
+upm:
+	return -2;
+}
+
+
 /*
  * Drop a TLB entry into the GRU. The fault is described by info in an TFH.
  *	Input:
@@ -280,10 +319,8 @@ static int gru_try_dropin(struct gru_thread_state *gts,
 			  struct gru_tlb_fault_handle *tfh,
 			  unsigned long __user *cb)
 {
-	struct mm_struct *mm = gts->ts_mm;
-	struct vm_area_struct *vma;
-	int pageshift, asid, write, ret;
-	unsigned long paddr, gpa, vaddr;
+	int pageshift = 0, asid, write, ret, atomic = !cb;
+	unsigned long gpa = 0, vaddr = 0;
 
 	/*
 	 * NOTE: The GRU contains magic hardware that eliminates races between
@@ -317,28 +354,19 @@ static int gru_try_dropin(struct gru_thread_state *gts,
 	if (atomic_read(&gts->ts_gms->ms_range_active))
 		goto failactive;
 
-	vma = find_vma(mm, vaddr);
-	if (!vma)
+	ret = gru_vtop(gts, vaddr, write, atomic, &gpa, &pageshift);
+	if (ret == -1)
 		goto failinval;
+	if (ret == -2)
+		goto failupm;
 
-	/*
-	 * Atomic lookup is faster & usually works even if called in non-atomic
-	 * context.
-	 */
-	rmb();	/* Must/check ms_range_active before loading PTEs */
-	ret = atomic_pte_lookup(vma, vaddr, write, &paddr, &pageshift);
-	if (ret) {
-		if (!cb)
+	if (!(gts->ts_sizeavail & GRU_SIZEAVAIL(pageshift))) {
+		gts->ts_sizeavail |= GRU_SIZEAVAIL(pageshift);
+		if (atomic || !gru_update_cch(gts, 0)) {
+			gts->ts_force_cch_reload = 1;
 			goto failupm;
-		if (non_atomic_pte_lookup(vma, vaddr, write, &paddr,
-					  &pageshift))
-			goto failinval;
+		}
 	}
-	if (is_gru_paddr(paddr))
-		goto failinval;
-
-	paddr = paddr & ~((1UL << pageshift) - 1);
-	gpa = uv_soc_phys_ram_to_gpa(paddr);
 	gru_cb_set_istatus_active(cb);
 	tfh_write_restart(tfh, gpa, GAA_RAM, vaddr, asid, write,
 			  GRU_PAGESIZE(pageshift));
@@ -368,6 +396,7 @@ failupm:
 
 failfmm:
 	/* FMM state on UPM call */
+	gru_flush_cache(tfh);
 	STAT(tlb_dropin_fail_fmm);
 	gru_dbg(grudev, "FAILED fmm tfh: 0x%p, state %d\n", tfh, tfh->state);
 	return 0;
@@ -448,6 +477,7 @@ irqreturn_t gru_intr(int irq, void *dev_id)
 			up_read(&gts->ts_mm->mmap_sem);
 		} else {
 			tfh_user_polling_mode(tfh);
+			STAT(intr_mm_lock_failed);
 		}
 	}
 	return IRQ_HANDLED;
@@ -497,10 +527,8 @@ int gru_handle_user_call_os(unsigned long cb)
 	if (!gts)
 		return -EINVAL;
 
-	if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE) {
-		ret = -EINVAL;
+	if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE)
 		goto exit;
-	}
 
 	/*
 	 * If force_unload is set, the UPM TLB fault is phony. The task
@@ -508,6 +536,20 @@ int gru_handle_user_call_os(unsigned long cb)
 	 * unload the context. The task will page fault and assign a new
 	 * context.
 	 */
+	if (gts->ts_tgid_owner == current->tgid && gts->ts_blade >= 0 &&
+				gts->ts_blade != uv_numa_blade_id()) {
+		STAT(call_os_offnode_reference);
+		gts->ts_force_unload = 1;
+	}
+
+	/*
+	 * CCH may contain stale data if ts_force_cch_reload is set.
+	 */
+	if (gts->ts_gru && gts->ts_force_cch_reload) {
+		gru_update_cch(gts, 0);
+		gts->ts_force_cch_reload = 0;
+	}
+
 	ret = -EAGAIN;
 	cbrnum = thread_cbr_number(gts, ucbnum);
 	if (gts->ts_force_unload) {
@@ -541,11 +583,13 @@ int gru_get_exception_detail(unsigned long arg)
 	if (!gts)
 		return -EINVAL;
 
-	if (gts->ts_gru) {
-		ucbnum = get_cb_number((void *)excdet.cb);
+	ucbnum = get_cb_number((void *)excdet.cb);
+	if (ucbnum >= gts->ts_cbr_au_count * GRU_CBR_AU_SIZE) {
+		ret = -EINVAL;
+	} else if (gts->ts_gru) {
 		cbrnum = thread_cbr_number(gts, ucbnum);
 		cbe = get_cbe_by_index(gts->ts_gru, cbrnum);
-		prefetchw(cbe);		/* Harmless on hardware, required for emulator */
+		prefetchw(cbe);/* Harmless on hardware, required for emulator */
 		excdet.opc = cbe->opccpy;
 		excdet.exopc = cbe->exopccpy;
 		excdet.ecause = cbe->ecause;
@@ -567,6 +611,31 @@ int gru_get_exception_detail(unsigned long arg)
 /*
  * User request to unload a context. Content is saved for possible reload.
  */
+static int gru_unload_all_contexts(void)
+{
+	struct gru_thread_state *gts;
+	struct gru_state *gru;
+	int gid, ctxnum;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+	foreach_gid(gid) {
+		gru = GID_TO_GRU(gid);
+		spin_lock(&gru->gs_lock);
+		for (ctxnum = 0; ctxnum < GRU_NUM_CCH; ctxnum++) {
+			gts = gru->gs_gts[ctxnum];
+			if (gts && mutex_trylock(&gts->ts_ctxlock)) {
+				spin_unlock(&gru->gs_lock);
+				gru_unload_context(gts, 1);
+				gru_unlock_gts(gts);
+				spin_lock(&gru->gs_lock);
+			}
+		}
+		spin_unlock(&gru->gs_lock);
+	}
+	return 0;
+}
+
 int gru_user_unload_context(unsigned long arg)
 {
 	struct gru_thread_state *gts;
@@ -578,6 +647,9 @@ int gru_user_unload_context(unsigned long arg)
 
 	gru_dbg(grudev, "gseg 0x%lx\n", req.gseg);
 
+	if (!req.gseg)
+		return gru_unload_all_contexts();
+
 	gts = gru_find_lock_gts(req.gseg);
 	if (!gts)
 		return -EINVAL;
@@ -609,7 +681,7 @@ int gru_user_flush_tlb(unsigned long arg)
 	if (!gts)
 		return -EINVAL;
 
-	gru_flush_tlb_range(gts->ts_gms, req.vaddr, req.vaddr + req.len);
+	gru_flush_tlb_range(gts->ts_gms, req.vaddr, req.len);
 	gru_unlock_gts(gts);
 
 	return 0;
diff --git a/drivers/misc/sgi-gru/grufile.c b/drivers/misc/sgi-gru/grufile.c
index c67e4e8bd62c..3e6e42d2f01b 100644
--- a/drivers/misc/sgi-gru/grufile.c
+++ b/drivers/misc/sgi-gru/grufile.c
@@ -45,7 +45,9 @@
 #include <asm/uv/uv_mmrs.h>
 
 struct gru_blade_state *gru_base[GRU_MAX_BLADES] __read_mostly;
-unsigned long gru_start_paddr, gru_end_paddr __read_mostly;
+unsigned long gru_start_paddr __read_mostly;
+unsigned long gru_end_paddr __read_mostly;
+unsigned int gru_max_gids __read_mostly;
 struct gru_stats_s gru_stats;
 
 /* Guaranteed user available resources on each node */
@@ -101,7 +103,7 @@ static int gru_file_mmap(struct file *file, struct vm_area_struct *vma)
 		return -EPERM;
 
 	if (vma->vm_start & (GRU_GSEG_PAGESIZE - 1) ||
-	    			vma->vm_end & (GRU_GSEG_PAGESIZE - 1))
+				vma->vm_end & (GRU_GSEG_PAGESIZE - 1))
 		return -EINVAL;
 
 	vma->vm_flags |=
@@ -273,8 +275,11 @@ static void gru_init_chiplet(struct gru_state *gru, unsigned long paddr,
 	gru->gs_blade_id = bid;
 	gru->gs_cbr_map = (GRU_CBR_AU == 64) ? ~0 : (1UL << GRU_CBR_AU) - 1;
 	gru->gs_dsr_map = (1UL << GRU_DSR_AU) - 1;
+	gru->gs_asid_limit = MAX_ASID;
 	gru_tgh_flush_init(gru);
-	gru_dbg(grudev, "bid %d, nid %d, gru %x, vaddr %p (0x%lx)\n",
+	if (gru->gs_gid >= gru_max_gids)
+		gru_max_gids = gru->gs_gid + 1;
+	gru_dbg(grudev, "bid %d, nid %d, gid %d, vaddr %p (0x%lx)\n",
 		bid, nid, gru->gs_gid, gru->gs_gru_base_vaddr,
 		gru->gs_gru_base_paddr);
 	gru_kservices_init(gru);
@@ -295,7 +300,7 @@ static int gru_init_tables(unsigned long gru_base_paddr, void *gru_base_vaddr)
 	for_each_online_node(nid) {
 		bid = uv_node_to_blade_id(nid);
 		pnode = uv_node_to_pnode(nid);
-		if (gru_base[bid])
+		if (bid < 0 || gru_base[bid])
 			continue;
 		page = alloc_pages_node(nid, GFP_KERNEL, order);
 		if (!page)
@@ -308,11 +313,11 @@ static int gru_init_tables(unsigned long gru_base_paddr, void *gru_base_vaddr)
 		dsrbytes = 0;
 		cbrs = 0;
 		for (gru = gru_base[bid]->bs_grus, chip = 0;
-		     		chip < GRU_CHIPLETS_PER_BLADE;
+				chip < GRU_CHIPLETS_PER_BLADE;
 				chip++, gru++) {
 			paddr = gru_chiplet_paddr(gru_base_paddr, pnode, chip);
 			vaddr = gru_chiplet_vaddr(gru_base_vaddr, pnode, chip);
-			gru_init_chiplet(gru, paddr, vaddr, bid, nid, chip);
+			gru_init_chiplet(gru, paddr, vaddr, nid, bid, chip);
 			n = hweight64(gru->gs_cbr_map) * GRU_CBR_AU_SIZE;
 			cbrs = max(cbrs, n);
 			n = hweight64(gru->gs_dsr_map) * GRU_DSR_AU_BYTES;
@@ -370,26 +375,26 @@ static int __init gru_init(void)
 	void *gru_start_vaddr;
 
 	if (!is_uv_system())
-		return 0;
+		return -ENODEV;
 
 #if defined CONFIG_IA64
 	gru_start_paddr = 0xd000000000UL; /* ZZZZZZZZZZZZZZZZZZZ fixme */
 #else
 	gru_start_paddr = uv_read_local_mmr(UVH_RH_GAM_GRU_OVERLAY_CONFIG_MMR) &
 				0x7fffffffffffUL;
-
 #endif
 	gru_start_vaddr = __va(gru_start_paddr);
-	gru_end_paddr = gru_start_paddr + MAX_NUMNODES * GRU_SIZE;
+	gru_end_paddr = gru_start_paddr + GRU_MAX_BLADES * GRU_SIZE;
 	printk(KERN_INFO "GRU space: 0x%lx - 0x%lx\n",
 	       gru_start_paddr, gru_end_paddr);
 	irq = get_base_irq();
 	for (chip = 0; chip < GRU_CHIPLETS_PER_BLADE; chip++) {
 		ret = request_irq(irq + chip, gru_intr, 0, id, NULL);
-		/* TODO: fix irq handling on x86. For now ignore failures because
+		/* TODO: fix irq handling on x86. For now ignore failure because
 		 * interrupts are not required & not yet fully supported */
 		if (ret) {
-			printk("!!!WARNING: GRU ignoring request failure!!!\n");
+			printk(KERN_WARNING
+			       "!!!WARNING: GRU ignoring request failure!!!\n");
 			ret = 0;
 		}
 		if (ret) {
@@ -435,7 +440,7 @@ exit1:
 
 static void __exit gru_exit(void)
 {
-	int i, bid;
+	int i, bid, gid;
 	int order = get_order(sizeof(struct gru_state) *
 			      GRU_CHIPLETS_PER_BLADE);
 
@@ -445,6 +450,9 @@ static void __exit gru_exit(void)
 	for (i = 0; i < GRU_CHIPLETS_PER_BLADE; i++)
 		free_irq(IRQ_GRU + i, NULL);
 
+	foreach_gid(gid)
+		gru_kservices_exit(GID_TO_GRU(gid));
+
 	for (bid = 0; bid < GRU_MAX_BLADES; bid++)
 		free_pages((unsigned long)gru_base[bid], order);
 
@@ -469,7 +477,11 @@ struct vm_operations_struct gru_vm_ops = {
 	.fault		= gru_fault,
 };
 
+#ifndef MODULE
 fs_initcall(gru_init);
+#else
+module_init(gru_init);
+#endif
 module_exit(gru_exit);
 
 module_param(gru_options, ulong, 0644);
diff --git a/drivers/misc/sgi-gru/gruhandles.c b/drivers/misc/sgi-gru/gruhandles.c
new file mode 100644
index 000000000000..9b7ccb328697
--- /dev/null
+++ b/drivers/misc/sgi-gru/gruhandles.c
@@ -0,0 +1,183 @@
+/*
+ *              GRU KERNEL MCS INSTRUCTIONS
+ *
+ *  Copyright (c) 2008 Silicon Graphics, Inc.  All Rights Reserved.
+ *
+ *  This program is free software; you can redistribute it and/or modify
+ *  it under the terms of the GNU General Public License as published by
+ *  the Free Software Foundation; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA  02111-1307 USA
+ */
+
+#include <linux/kernel.h>
+#include "gru.h"
+#include "grulib.h"
+#include "grutables.h"
+
+/* 10 sec */
+#ifdef CONFIG_IA64
+#include <asm/processor.h>
+#define GRU_OPERATION_TIMEOUT	(((cycles_t) local_cpu_data->itc_freq)*10)
+#else
+#include <asm/tsc.h>
+#define GRU_OPERATION_TIMEOUT	((cycles_t) tsc_khz*10*1000)
+#endif
+
+/* Extract the status field from a kernel handle */
+#define GET_MSEG_HANDLE_STATUS(h)	(((*(unsigned long *)(h)) >> 16) & 3)
+
+struct mcs_op_statistic mcs_op_statistics[mcsop_last];
+
+static void update_mcs_stats(enum mcs_op op, unsigned long clks)
+{
+	atomic_long_inc(&mcs_op_statistics[op].count);
+	atomic_long_add(clks, &mcs_op_statistics[op].total);
+	if (mcs_op_statistics[op].max < clks)
+		mcs_op_statistics[op].max = clks;
+}
+
+static void start_instruction(void *h)
+{
+	unsigned long *w0 = h;
+
+	wmb();		/* setting CMD bit must be last */
+	*w0 = *w0 | 1;
+	gru_flush_cache(h);
+}
+
+static int wait_instruction_complete(void *h, enum mcs_op opc)
+{
+	int status;
+	cycles_t start_time = get_cycles();
+
+	while (1) {
+		cpu_relax();
+		status = GET_MSEG_HANDLE_STATUS(h);
+		if (status != CCHSTATUS_ACTIVE)
+			break;
+		if (GRU_OPERATION_TIMEOUT < (get_cycles() - start_time))
+			panic("GRU %p is malfunctioning\n", h);
+	}
+	if (gru_options & OPT_STATS)
+		update_mcs_stats(opc, get_cycles() - start_time);
+	return status;
+}
+
+int cch_allocate(struct gru_context_configuration_handle *cch,
+		int asidval, int sizeavail, unsigned long cbrmap,
+		unsigned long dsrmap)
+{
+	int i;
+
+	for (i = 0; i < 8; i++) {
+		cch->asid[i] = (asidval++);
+		cch->sizeavail[i] = sizeavail;
+	}
+	cch->dsr_allocation_map = dsrmap;
+	cch->cbr_allocation_map = cbrmap;
+	cch->opc = CCHOP_ALLOCATE;
+	start_instruction(cch);
+	return wait_instruction_complete(cch, cchop_allocate);
+}
+
+int cch_start(struct gru_context_configuration_handle *cch)
+{
+	cch->opc = CCHOP_START;
+	start_instruction(cch);
+	return wait_instruction_complete(cch, cchop_start);
+}
+
+int cch_interrupt(struct gru_context_configuration_handle *cch)
+{
+	cch->opc = CCHOP_INTERRUPT;
+	start_instruction(cch);
+	return wait_instruction_complete(cch, cchop_interrupt);
+}
+
+int cch_deallocate(struct gru_context_configuration_handle *cch)
+{
+	cch->opc = CCHOP_DEALLOCATE;
+	start_instruction(cch);
+	return wait_instruction_complete(cch, cchop_deallocate);
+}
+
+int cch_interrupt_sync(struct gru_context_configuration_handle
+				     *cch)
+{
+	cch->opc = CCHOP_INTERRUPT_SYNC;
+	start_instruction(cch);
+	return wait_instruction_complete(cch, cchop_interrupt_sync);
+}
+
+int tgh_invalidate(struct gru_tlb_global_handle *tgh,
+				 unsigned long vaddr, unsigned long vaddrmask,
+				 int asid, int pagesize, int global, int n,
+				 unsigned short ctxbitmap)
+{
+	tgh->vaddr = vaddr;
+	tgh->asid = asid;
+	tgh->pagesize = pagesize;
+	tgh->n = n;
+	tgh->global = global;
+	tgh->vaddrmask = vaddrmask;
+	tgh->ctxbitmap = ctxbitmap;
+	tgh->opc = TGHOP_TLBINV;
+	start_instruction(tgh);
+	return wait_instruction_complete(tgh, tghop_invalidate);
+}
+
+void tfh_write_only(struct gru_tlb_fault_handle *tfh,
+				  unsigned long pfn, unsigned long vaddr,
+				  int asid, int dirty, int pagesize)
+{
+	tfh->fillasid = asid;
+	tfh->fillvaddr = vaddr;
+	tfh->pfn = pfn;
+	tfh->dirty = dirty;
+	tfh->pagesize = pagesize;
+	tfh->opc = TFHOP_WRITE_ONLY;
+	start_instruction(tfh);
+}
+
+void tfh_write_restart(struct gru_tlb_fault_handle *tfh,
+				     unsigned long paddr, int gaa,
+				     unsigned long vaddr, int asid, int dirty,
+				     int pagesize)
+{
+	tfh->fillasid = asid;
+	tfh->fillvaddr = vaddr;
+	tfh->pfn = paddr >> GRU_PADDR_SHIFT;
+	tfh->gaa = gaa;
+	tfh->dirty = dirty;
+	tfh->pagesize = pagesize;
+	tfh->opc = TFHOP_WRITE_RESTART;
+	start_instruction(tfh);
+}
+
+void tfh_restart(struct gru_tlb_fault_handle *tfh)
+{
+	tfh->opc = TFHOP_RESTART;
+	start_instruction(tfh);
+}
+
+void tfh_user_polling_mode(struct gru_tlb_fault_handle *tfh)
+{
+	tfh->opc = TFHOP_USER_POLLING_MODE;
+	start_instruction(tfh);
+}
+
+void tfh_exception(struct gru_tlb_fault_handle *tfh)
+{
+	tfh->opc = TFHOP_EXCEPTION;
+	start_instruction(tfh);
+}
+
diff --git a/drivers/misc/sgi-gru/gruhandles.h b/drivers/misc/sgi-gru/gruhandles.h
index b63018d60fe1..1ed74d7508c8 100644
--- a/drivers/misc/sgi-gru/gruhandles.h
+++ b/drivers/misc/sgi-gru/gruhandles.h
@@ -489,170 +489,28 @@ enum gru_cbr_state {
  * 	 64m			26	8
  * 	...
  */
-#define GRU_PAGESIZE(sh)	((((sh) > 20 ? (sh) + 2: (sh)) >> 1) - 6)
+#define GRU_PAGESIZE(sh)	((((sh) > 20 ? (sh) + 2 : (sh)) >> 1) - 6)
 #define GRU_SIZEAVAIL(sh)	(1UL << GRU_PAGESIZE(sh))
 
 /* minimum TLB purge count to ensure a full purge */
 #define GRUMAXINVAL		1024UL
 
-
-/* Extract the status field from a kernel handle */
-#define GET_MSEG_HANDLE_STATUS(h)	(((*(unsigned long *)(h)) >> 16) & 3)
-
-static inline void start_instruction(void *h)
-{
-	unsigned long *w0 = h;
-
-	wmb();		/* setting CMD bit must be last */
-	*w0 = *w0 | 1;
-	gru_flush_cache(h);
-}
-
-static inline int wait_instruction_complete(void *h)
-{
-	int status;
-
-	do {
-		cpu_relax();
-		barrier();
-		status = GET_MSEG_HANDLE_STATUS(h);
-	} while (status == CCHSTATUS_ACTIVE);
-	return status;
-}
-
-#if defined CONFIG_IA64
-static inline void cch_allocate_set_asids(
-		  struct gru_context_configuration_handle *cch, int asidval)
-{
-	int i;
-
-	for (i = 0; i <= RGN_HPAGE; i++) {  /*  assume HPAGE is last region */
-		cch->asid[i] = (asidval++);
-#if 0
-		/* ZZZ hugepages not supported yet */
-		if (i == RGN_HPAGE)
-			cch->sizeavail[i] = GRU_SIZEAVAIL(hpage_shift);
-		else
-#endif
-			cch->sizeavail[i] = GRU_SIZEAVAIL(PAGE_SHIFT);
-	}
-}
-#elif defined CONFIG_X86_64
-static inline void cch_allocate_set_asids(
-		  struct gru_context_configuration_handle *cch, int asidval)
-{
-	int i;
-
-	for (i = 0; i < 8; i++) {
-		cch->asid[i] = asidval++;
-		cch->sizeavail[i] = GRU_SIZEAVAIL(PAGE_SHIFT) |
-			GRU_SIZEAVAIL(21);
-	}
-}
-#endif
-
-static inline int cch_allocate(struct gru_context_configuration_handle *cch,
-			       int asidval, unsigned long cbrmap,
-			       unsigned long dsrmap)
-{
-	cch_allocate_set_asids(cch, asidval);
-	cch->dsr_allocation_map = dsrmap;
-	cch->cbr_allocation_map = cbrmap;
-	cch->opc = CCHOP_ALLOCATE;
-	start_instruction(cch);
-	return wait_instruction_complete(cch);
-}
-
-static inline int cch_start(struct gru_context_configuration_handle *cch)
-{
-	cch->opc = CCHOP_START;
-	start_instruction(cch);
-	return wait_instruction_complete(cch);
-}
-
-static inline int cch_interrupt(struct gru_context_configuration_handle *cch)
-{
-	cch->opc = CCHOP_INTERRUPT;
-	start_instruction(cch);
-	return wait_instruction_complete(cch);
-}
-
-static inline int cch_deallocate(struct gru_context_configuration_handle *cch)
-{
-	cch->opc = CCHOP_DEALLOCATE;
-	start_instruction(cch);
-	return wait_instruction_complete(cch);
-}
-
-static inline int cch_interrupt_sync(struct gru_context_configuration_handle
-				     *cch)
-{
-	cch->opc = CCHOP_INTERRUPT_SYNC;
-	start_instruction(cch);
-	return wait_instruction_complete(cch);
-}
-
-static inline int tgh_invalidate(struct gru_tlb_global_handle *tgh,
-				 unsigned long vaddr, unsigned long vaddrmask,
-				 int asid, int pagesize, int global, int n,
-				 unsigned short ctxbitmap)
-{
-	tgh->vaddr = vaddr;
-	tgh->asid = asid;
-	tgh->pagesize = pagesize;
-	tgh->n = n;
-	tgh->global = global;
-	tgh->vaddrmask = vaddrmask;
-	tgh->ctxbitmap = ctxbitmap;
-	tgh->opc = TGHOP_TLBINV;
-	start_instruction(tgh);
-	return wait_instruction_complete(tgh);
-}
-
-static inline void tfh_write_only(struct gru_tlb_fault_handle *tfh,
-				  unsigned long pfn, unsigned long vaddr,
-				  int asid, int dirty, int pagesize)
-{
-	tfh->fillasid = asid;
-	tfh->fillvaddr = vaddr;
-	tfh->pfn = pfn;
-	tfh->dirty = dirty;
-	tfh->pagesize = pagesize;
-	tfh->opc = TFHOP_WRITE_ONLY;
-	start_instruction(tfh);
-}
-
-static inline void tfh_write_restart(struct gru_tlb_fault_handle *tfh,
-				     unsigned long paddr, int gaa,
-				     unsigned long vaddr, int asid, int dirty,
-				     int pagesize)
-{
-	tfh->fillasid = asid;
-	tfh->fillvaddr = vaddr;
-	tfh->pfn = paddr >> GRU_PADDR_SHIFT;
-	tfh->gaa = gaa;
-	tfh->dirty = dirty;
-	tfh->pagesize = pagesize;
-	tfh->opc = TFHOP_WRITE_RESTART;
-	start_instruction(tfh);
-}
-
-static inline void tfh_restart(struct gru_tlb_fault_handle *tfh)
-{
-	tfh->opc = TFHOP_RESTART;
-	start_instruction(tfh);
-}
-
-static inline void tfh_user_polling_mode(struct gru_tlb_fault_handle *tfh)
-{
-	tfh->opc = TFHOP_USER_POLLING_MODE;
-	start_instruction(tfh);
-}
-
-static inline void tfh_exception(struct gru_tlb_fault_handle *tfh)
-{
-	tfh->opc = TFHOP_EXCEPTION;
-	start_instruction(tfh);
-}
+int cch_allocate(struct gru_context_configuration_handle *cch,
+       int asidval, int sizeavail, unsigned long cbrmap, unsigned long dsrmap);
+
+int cch_start(struct gru_context_configuration_handle *cch);
+int cch_interrupt(struct gru_context_configuration_handle *cch);
+int cch_deallocate(struct gru_context_configuration_handle *cch);
+int cch_interrupt_sync(struct gru_context_configuration_handle *cch);
+int tgh_invalidate(struct gru_tlb_global_handle *tgh, unsigned long vaddr,
+	unsigned long vaddrmask, int asid, int pagesize, int global, int n,
+	unsigned short ctxbitmap);
+void tfh_write_only(struct gru_tlb_fault_handle *tfh, unsigned long pfn,
+	unsigned long vaddr, int asid, int dirty, int pagesize);
+void tfh_write_restart(struct gru_tlb_fault_handle *tfh, unsigned long paddr,
+	int gaa, unsigned long vaddr, int asid, int dirty, int pagesize);
+void tfh_restart(struct gru_tlb_fault_handle *tfh);
+void tfh_user_polling_mode(struct gru_tlb_fault_handle *tfh);
+void tfh_exception(struct gru_tlb_fault_handle *tfh);
 
 #endif /* __GRUHANDLES_H__ */
diff --git a/drivers/misc/sgi-gru/grukservices.c b/drivers/misc/sgi-gru/grukservices.c
index 880c55dfb662..d8bd7d84a7cf 100644
--- a/drivers/misc/sgi-gru/grukservices.c
+++ b/drivers/misc/sgi-gru/grukservices.c
@@ -52,8 +52,10 @@
  */
 
 /* Blade percpu resources PERMANENTLY reserved for kernel use */
-#define GRU_NUM_KERNEL_CBR      1
+#define GRU_NUM_KERNEL_CBR	1
 #define GRU_NUM_KERNEL_DSR_BYTES 256
+#define GRU_NUM_KERNEL_DSR_CL	(GRU_NUM_KERNEL_DSR_BYTES /		\
+					GRU_CACHE_LINE_BYTES)
 #define KERNEL_CTXNUM           15
 
 /* GRU instruction attributes for all instructions */
@@ -94,7 +96,6 @@ struct message_header {
 	char	fill;
 };
 
-#define QLINES(mq)	((mq) + offsetof(struct message_queue, qlines))
 #define HSTATUS(mq, h)	((mq) + offsetof(struct message_queue, hstatus[h]))
 
 static int gru_get_cpu_resources(int dsr_bytes, void **cb, void **dsr)
@@ -122,7 +123,7 @@ int gru_get_cb_exception_detail(void *cb,
 	struct gru_control_block_extended *cbe;
 
 	cbe = get_cbe(GRUBASE(cb), get_cb_number(cb));
-	prefetchw(cbe);         /* Harmless on hardware, required for emulator */
+	prefetchw(cbe);	/* Harmless on hardware, required for emulator */
 	excdet->opc = cbe->opccpy;
 	excdet->exopc = cbe->exopccpy;
 	excdet->ecause = cbe->ecause;
@@ -250,7 +251,8 @@ static inline void restore_present2(void *p, int val)
  * Create a message queue.
  * 	qlines - message queue size in cache lines. Includes 2-line header.
  */
-int gru_create_message_queue(void *p, unsigned int bytes)
+int gru_create_message_queue(struct gru_message_queue_desc *mqd,
+		void *p, unsigned int bytes, int nasid, int vector, int apicid)
 {
 	struct message_queue *mq = p;
 	unsigned int qlines;
@@ -265,6 +267,12 @@ int gru_create_message_queue(void *p, unsigned int bytes)
 	mq->hstatus[0] = 0;
 	mq->hstatus[1] = 1;
 	mq->head = gru_mesq_head(2, qlines / 2 + 1);
+	mqd->mq = mq;
+	mqd->mq_gpa = uv_gpa(mq);
+	mqd->qlines = qlines;
+	mqd->interrupt_pnode = UV_NASID_TO_PNODE(nasid);
+	mqd->interrupt_vector = vector;
+	mqd->interrupt_apicid = apicid;
 	return 0;
 }
 EXPORT_SYMBOL_GPL(gru_create_message_queue);
@@ -277,8 +285,8 @@ EXPORT_SYMBOL_GPL(gru_create_message_queue);
  *		-1 - if mesq sent successfully but queue not full
  *		>0 - unexpected error. MQE_xxx returned
  */
-static int send_noop_message(void *cb,
-				unsigned long mq, void *mesg)
+static int send_noop_message(void *cb, struct gru_message_queue_desc *mqd,
+				void *mesg)
 {
 	const struct message_header noop_header = {
 					.present = MQS_NOOP, .lines = 1};
@@ -289,7 +297,7 @@ static int send_noop_message(void *cb,
 	STAT(mesq_noop);
 	save_mhdr = *mhdr;
 	*mhdr = noop_header;
-	gru_mesq(cb, mq, gru_get_tri(mhdr), 1, IMA);
+	gru_mesq(cb, mqd->mq_gpa, gru_get_tri(mhdr), 1, IMA);
 	ret = gru_wait(cb);
 
 	if (ret) {
@@ -313,7 +321,7 @@ static int send_noop_message(void *cb,
 			break;
 		case CBSS_PUT_NACKED:
 			STAT(mesq_noop_put_nacked);
-			m = mq + (gru_get_amo_value_head(cb) << 6);
+			m = mqd->mq_gpa + (gru_get_amo_value_head(cb) << 6);
 			gru_vstore(cb, m, gru_get_tri(mesg), XTYPE_CL, 1, 1,
 						IMA);
 			if (gru_wait(cb) == CBS_IDLE)
@@ -333,30 +341,20 @@ static int send_noop_message(void *cb,
 /*
  * Handle a gru_mesq full.
  */
-static int send_message_queue_full(void *cb,
-			   unsigned long mq, void *mesg, int lines)
+static int send_message_queue_full(void *cb, struct gru_message_queue_desc *mqd,
+				void *mesg, int lines)
 {
 	union gru_mesqhead mqh;
 	unsigned int limit, head;
 	unsigned long avalue;
-	int half, qlines, save;
+	int half, qlines;
 
 	/* Determine if switching to first/second half of q */
 	avalue = gru_get_amo_value(cb);
 	head = gru_get_amo_value_head(cb);
 	limit = gru_get_amo_value_limit(cb);
 
-	/*
-	 * Fetch "qlines" from the queue header. Since the queue may be
-	 * in memory that can't be accessed using socket addresses, use
-	 * the GRU to access the data. Use DSR space from the message.
-	 */
-	save = *(int *)mesg;
-	gru_vload(cb, QLINES(mq), gru_get_tri(mesg), XTYPE_W, 1, 1, IMA);
-	if (gru_wait(cb) != CBS_IDLE)
-		goto cberr;
-	qlines = *(int *)mesg;
-	*(int *)mesg = save;
+	qlines = mqd->qlines;
 	half = (limit != qlines);
 
 	if (half)
@@ -365,7 +363,7 @@ static int send_message_queue_full(void *cb,
 		mqh = gru_mesq_head(2, qlines / 2 + 1);
 
 	/* Try to get lock for switching head pointer */
-	gru_gamir(cb, EOP_IR_CLR, HSTATUS(mq, half), XTYPE_DW, IMA);
+	gru_gamir(cb, EOP_IR_CLR, HSTATUS(mqd->mq_gpa, half), XTYPE_DW, IMA);
 	if (gru_wait(cb) != CBS_IDLE)
 		goto cberr;
 	if (!gru_get_amo_value(cb)) {
@@ -375,8 +373,8 @@ static int send_message_queue_full(void *cb,
 
 	/* Got the lock. Send optional NOP if queue not full, */
 	if (head != limit) {
-		if (send_noop_message(cb, mq, mesg)) {
-			gru_gamir(cb, EOP_IR_INC, HSTATUS(mq, half),
+		if (send_noop_message(cb, mqd, mesg)) {
+			gru_gamir(cb, EOP_IR_INC, HSTATUS(mqd->mq_gpa, half),
 					XTYPE_DW, IMA);
 			if (gru_wait(cb) != CBS_IDLE)
 				goto cberr;
@@ -387,14 +385,16 @@ static int send_message_queue_full(void *cb,
 	}
 
 	/* Then flip queuehead to other half of queue. */
-	gru_gamer(cb, EOP_ERR_CSWAP, mq, XTYPE_DW, mqh.val, avalue, IMA);
+	gru_gamer(cb, EOP_ERR_CSWAP, mqd->mq_gpa, XTYPE_DW, mqh.val, avalue,
+							IMA);
 	if (gru_wait(cb) != CBS_IDLE)
 		goto cberr;
 
 	/* If not successfully in swapping queue head, clear the hstatus lock */
 	if (gru_get_amo_value(cb) != avalue) {
 		STAT(mesq_qf_switch_head_failed);
-		gru_gamir(cb, EOP_IR_INC, HSTATUS(mq, half), XTYPE_DW, IMA);
+		gru_gamir(cb, EOP_IR_INC, HSTATUS(mqd->mq_gpa, half), XTYPE_DW,
+							IMA);
 		if (gru_wait(cb) != CBS_IDLE)
 			goto cberr;
 	}
@@ -404,15 +404,25 @@ cberr:
 	return MQE_UNEXPECTED_CB_ERR;
 }
 
+/*
+ * Send a cross-partition interrupt to the SSI that contains the target
+ * message queue. Normally, the interrupt is automatically delivered by hardware
+ * but some error conditions require explicit delivery.
+ */
+static void send_message_queue_interrupt(struct gru_message_queue_desc *mqd)
+{
+	if (mqd->interrupt_vector)
+		uv_hub_send_ipi(mqd->interrupt_pnode, mqd->interrupt_apicid,
+				mqd->interrupt_vector);
+}
+
 
 /*
  * Handle a gru_mesq failure. Some of these failures are software recoverable
  * or retryable.
  */
-static int send_message_failure(void *cb,
-				unsigned long mq,
-				void *mesg,
-				int lines)
+static int send_message_failure(void *cb, struct gru_message_queue_desc *mqd,
+				void *mesg, int lines)
 {
 	int substatus, ret = 0;
 	unsigned long m;
@@ -429,7 +439,7 @@ static int send_message_failure(void *cb,
 		break;
 	case CBSS_QLIMIT_REACHED:
 		STAT(mesq_send_qlimit_reached);
-		ret = send_message_queue_full(cb, mq, mesg, lines);
+		ret = send_message_queue_full(cb, mqd, mesg, lines);
 		break;
 	case CBSS_AMO_NACKED:
 		STAT(mesq_send_amo_nacked);
@@ -437,12 +447,14 @@ static int send_message_failure(void *cb,
 		break;
 	case CBSS_PUT_NACKED:
 		STAT(mesq_send_put_nacked);
-		m =mq + (gru_get_amo_value_head(cb) << 6);
+		m = mqd->mq_gpa + (gru_get_amo_value_head(cb) << 6);
 		gru_vstore(cb, m, gru_get_tri(mesg), XTYPE_CL, lines, 1, IMA);
-		if (gru_wait(cb) == CBS_IDLE)
+		if (gru_wait(cb) == CBS_IDLE) {
 			ret = MQE_OK;
-		else
+			send_message_queue_interrupt(mqd);
+		} else {
 			ret = MQE_UNEXPECTED_CB_ERR;
+		}
 		break;
 	default:
 		BUG();
@@ -452,12 +464,12 @@ static int send_message_failure(void *cb,
 
 /*
  * Send a message to a message queue
- * 	cb	GRU control block to use to send message
- * 	mq	message queue
+ * 	mqd	message queue descriptor
  * 	mesg	message. ust be vaddr within a GSEG
  * 	bytes	message size (<= 2 CL)
  */
-int gru_send_message_gpa(unsigned long mq, void *mesg, unsigned int bytes)
+int gru_send_message_gpa(struct gru_message_queue_desc *mqd, void *mesg,
+				unsigned int bytes)
 {
 	struct message_header *mhdr;
 	void *cb;
@@ -481,10 +493,10 @@ int gru_send_message_gpa(unsigned long mq, void *mesg, unsigned int bytes)
 
 	do {
 		ret = MQE_OK;
-		gru_mesq(cb, mq, gru_get_tri(mhdr), clines, IMA);
+		gru_mesq(cb, mqd->mq_gpa, gru_get_tri(mhdr), clines, IMA);
 		istatus = gru_wait(cb);
 		if (istatus != CBS_IDLE)
-			ret = send_message_failure(cb, mq, dsr, clines);
+			ret = send_message_failure(cb, mqd, dsr, clines);
 	} while (ret == MQIE_AGAIN);
 	gru_free_cpu_resources(cb, dsr);
 
@@ -497,9 +509,9 @@ EXPORT_SYMBOL_GPL(gru_send_message_gpa);
 /*
  * Advance the receive pointer for the queue to the next message.
  */
-void gru_free_message(void *rmq, void *mesg)
+void gru_free_message(struct gru_message_queue_desc *mqd, void *mesg)
 {
-	struct message_queue *mq = rmq;
+	struct message_queue *mq = mqd->mq;
 	struct message_header *mhdr = mq->next;
 	void *next, *pnext;
 	int half = -1;
@@ -529,16 +541,16 @@ EXPORT_SYMBOL_GPL(gru_free_message);
  * present. User must call next_message() to move to next message.
  * 	rmq	message queue
  */
-void *gru_get_next_message(void *rmq)
+void *gru_get_next_message(struct gru_message_queue_desc *mqd)
 {
-	struct message_queue *mq = rmq;
+	struct message_queue *mq = mqd->mq;
 	struct message_header *mhdr = mq->next;
 	int present = mhdr->present;
 
 	/* skip NOOP messages */
 	STAT(mesq_receive);
 	while (present == MQS_NOOP) {
-		gru_free_message(rmq, mhdr);
+		gru_free_message(mqd, mhdr);
 		mhdr = mq->next;
 		present = mhdr->present;
 	}
@@ -576,7 +588,7 @@ int gru_copy_gpa(unsigned long dest_gpa, unsigned long src_gpa,
 	if (gru_get_cpu_resources(GRU_NUM_KERNEL_DSR_BYTES, &cb, &dsr))
 		return MQE_BUG_NO_RESOURCES;
 	gru_bcopy(cb, src_gpa, dest_gpa, gru_get_tri(dsr),
-		  XTYPE_B, bytes, GRU_NUM_KERNEL_DSR_BYTES, IMA);
+		  XTYPE_B, bytes, GRU_NUM_KERNEL_DSR_CL, IMA);
 	ret = gru_wait(cb);
 	gru_free_cpu_resources(cb, dsr);
 	return ret;
@@ -611,7 +623,7 @@ static int quicktest(struct gru_state *gru)
 
 	if (word0 != word1 || word0 != MAGIC) {
 		printk
-		    ("GRU quicktest err: gru %d, found 0x%lx, expected 0x%lx\n",
+		    ("GRU quicktest err: gid %d, found 0x%lx, expected 0x%lx\n",
 		     gru->gs_gid, word1, MAGIC);
 		BUG();		/* ZZZ should not be fatal */
 	}
@@ -660,15 +672,15 @@ int gru_kservices_init(struct gru_state *gru)
 	cch->tlb_int_enable = 0;
 	cch->tfm_done_bit_enable = 0;
 	cch->unmap_enable = 1;
-	err = cch_allocate(cch, 0, cbr_map, dsr_map);
+	err = cch_allocate(cch, 0, 0, cbr_map, dsr_map);
 	if (err) {
 		gru_dbg(grudev,
-			"Unable to allocate kernel CCH: gru %d, err %d\n",
+			"Unable to allocate kernel CCH: gid %d, err %d\n",
 			gru->gs_gid, err);
 		BUG();
 	}
 	if (cch_start(cch)) {
-		gru_dbg(grudev, "Unable to start kernel CCH: gru %d, err %d\n",
+		gru_dbg(grudev, "Unable to start kernel CCH: gid %d, err %d\n",
 			gru->gs_gid, err);
 		BUG();
 	}
@@ -678,3 +690,22 @@ int gru_kservices_init(struct gru_state *gru)
 		quicktest(gru);
 	return 0;
 }
+
+void gru_kservices_exit(struct gru_state *gru)
+{
+	struct gru_context_configuration_handle *cch;
+	struct gru_blade_state *bs;
+
+	bs = gru->gs_blade;
+	if (gru != &bs->bs_grus[1])
+		return;
+
+	cch = get_cch(gru->gs_gru_base_vaddr, KERNEL_CTXNUM);
+	lock_cch_handle(cch);
+	if (cch_interrupt_sync(cch))
+		BUG();
+	if (cch_deallocate(cch))
+		BUG();
+	unlock_cch_handle(cch);
+}
+
diff --git a/drivers/misc/sgi-gru/grukservices.h b/drivers/misc/sgi-gru/grukservices.h
index eb17e0a3ac61..747ed315d56f 100644
--- a/drivers/misc/sgi-gru/grukservices.h
+++ b/drivers/misc/sgi-gru/grukservices.h
@@ -41,6 +41,15 @@
  * 	- gru_create_message_queue() needs interrupt vector info
  */
 
+struct gru_message_queue_desc {
+	void		*mq;			/* message queue vaddress */
+	unsigned long	mq_gpa;			/* global address of mq */
+	int		qlines;			/* queue size in CL */
+	int		interrupt_vector;	/* interrupt vector */
+	int		interrupt_pnode;	/* pnode for interrupt */
+	int		interrupt_apicid;	/* lapicid for interrupt */
+};
+
 /*
  * Initialize a user allocated chunk of memory to be used as
  * a message queue. The caller must ensure that the queue is
@@ -51,14 +60,19 @@
  * to manage the queue.
  *
  *  Input:
- * 	p	pointer to user allocated memory.
+ * 	mqd	pointer to message queue descriptor
+ * 	p	pointer to user allocated mesq memory.
  * 	bytes	size of message queue in bytes
+ *      vector	interrupt vector (zero if no interrupts)
+ *      nasid	nasid of blade where interrupt is delivered
+ *      apicid	apicid of cpu for interrupt
  *
  *  Errors:
  *  	0	OK
  *  	>0	error
  */
-extern int gru_create_message_queue(void *p, unsigned int bytes);
+extern int gru_create_message_queue(struct gru_message_queue_desc *mqd,
+		void *p, unsigned int bytes, int nasid, int vector, int apicid);
 
 /*
  * Send a message to a message queue.
@@ -68,7 +82,7 @@ extern int gru_create_message_queue(void *p, unsigned int bytes);
  *
  *
  *   Input:
- * 	xmq	message queue - must be a UV global physical address
+ * 	mqd	pointer to message queue descriptor
  * 	mesg	pointer to message. Must be 64-bit aligned
  * 	bytes	size of message in bytes
  *
@@ -77,8 +91,8 @@ extern int gru_create_message_queue(void *p, unsigned int bytes);
  *     >0	Send failure - see error codes below
  *
  */
-extern int gru_send_message_gpa(unsigned long mq_gpa, void *mesg,
-						unsigned int bytes);
+extern int gru_send_message_gpa(struct gru_message_queue_desc *mqd,
+			void *mesg, unsigned int bytes);
 
 /* Status values for gru_send_message() */
 #define MQE_OK			0	/* message sent successfully */
@@ -94,10 +108,11 @@ extern int gru_send_message_gpa(unsigned long mq_gpa, void *mesg,
  * API extensions may allow for out-of-order freeing.
  *
  *   Input
- * 	mq	message queue
+ * 	mqd	pointer to message queue descriptor
  * 	mesq	message being freed
  */
-extern void gru_free_message(void *mq, void *mesq);
+extern void gru_free_message(struct gru_message_queue_desc *mqd,
+			     void *mesq);
 
 /*
  * Get next message from message queue. Returns pointer to
@@ -106,13 +121,13 @@ extern void gru_free_message(void *mq, void *mesq);
  * in order to move the queue pointers to next message.
  *
  *   Input
- * 	mq	message queue
+ * 	mqd	pointer to message queue descriptor
  *
  *   Output:
  *	p	pointer to message
  *	NULL	no message available
  */
-extern void *gru_get_next_message(void *mq);
+extern void *gru_get_next_message(struct gru_message_queue_desc *mqd);
 
 
 /*
diff --git a/drivers/misc/sgi-gru/grumain.c b/drivers/misc/sgi-gru/grumain.c
index 3d2fc216bae5..ec3f7a17d221 100644
--- a/drivers/misc/sgi-gru/grumain.c
+++ b/drivers/misc/sgi-gru/grumain.c
@@ -76,10 +76,9 @@ int gru_cpu_fault_map_id(void)
 /* Hit the asid limit. Start over */
 static int gru_wrap_asid(struct gru_state *gru)
 {
-	gru_dbg(grudev, "gru %p\n", gru);
+	gru_dbg(grudev, "gid %d\n", gru->gs_gid);
 	STAT(asid_wrap);
 	gru->gs_asid_gen++;
-	gru_flush_all_tlb(gru);
 	return MIN_ASID;
 }
 
@@ -88,19 +87,21 @@ static int gru_reset_asid_limit(struct gru_state *gru, int asid)
 {
 	int i, gid, inuse_asid, limit;
 
-	gru_dbg(grudev, "gru %p, asid 0x%x\n", gru, asid);
+	gru_dbg(grudev, "gid %d, asid 0x%x\n", gru->gs_gid, asid);
 	STAT(asid_next);
 	limit = MAX_ASID;
 	if (asid >= limit)
 		asid = gru_wrap_asid(gru);
+	gru_flush_all_tlb(gru);
 	gid = gru->gs_gid;
 again:
 	for (i = 0; i < GRU_NUM_CCH; i++) {
 		if (!gru->gs_gts[i])
 			continue;
 		inuse_asid = gru->gs_gts[i]->ts_gms->ms_asids[gid].mt_asid;
-		gru_dbg(grudev, "gru %p, inuse_asid 0x%x, cxtnum %d, gts %p\n",
-			gru, inuse_asid, i, gru->gs_gts[i]);
+		gru_dbg(grudev, "gid %d, gts %p, gms %p, inuse 0x%x, cxt %d\n",
+			gru->gs_gid, gru->gs_gts[i], gru->gs_gts[i]->ts_gms,
+			inuse_asid, i);
 		if (inuse_asid == asid) {
 			asid += ASID_INC;
 			if (asid >= limit) {
@@ -120,8 +121,8 @@ again:
 	}
 	gru->gs_asid_limit = limit;
 	gru->gs_asid = asid;
-	gru_dbg(grudev, "gru %p, new asid 0x%x, new_limit 0x%x\n", gru, asid,
-		limit);
+	gru_dbg(grudev, "gid %d, new asid 0x%x, new_limit 0x%x\n", gru->gs_gid,
+					asid, limit);
 	return asid;
 }
 
@@ -130,14 +131,12 @@ static int gru_assign_asid(struct gru_state *gru)
 {
 	int asid;
 
-	spin_lock(&gru->gs_asid_lock);
 	gru->gs_asid += ASID_INC;
 	asid = gru->gs_asid;
 	if (asid >= gru->gs_asid_limit)
 		asid = gru_reset_asid_limit(gru, asid);
-	spin_unlock(&gru->gs_asid_lock);
 
-	gru_dbg(grudev, "gru %p, asid 0x%x\n", gru, asid);
+	gru_dbg(grudev, "gid %d, asid 0x%x\n", gru->gs_gid, asid);
 	return asid;
 }
 
@@ -215,17 +214,20 @@ static int check_gru_resources(struct gru_state *gru, int cbr_au_count,
  * TLB manangment requires tracking all GRU chiplets that have loaded a GSEG
  * context.
  */
-static int gru_load_mm_tracker(struct gru_state *gru, struct gru_mm_struct *gms,
-			       int ctxnum)
+static int gru_load_mm_tracker(struct gru_state *gru,
+					struct gru_thread_state *gts)
 {
+	struct gru_mm_struct *gms = gts->ts_gms;
 	struct gru_mm_tracker *asids = &gms->ms_asids[gru->gs_gid];
-	unsigned short ctxbitmap = (1 << ctxnum);
+	unsigned short ctxbitmap = (1 << gts->ts_ctxnum);
 	int asid;
 
 	spin_lock(&gms->ms_asid_lock);
 	asid = asids->mt_asid;
 
-	if (asid == 0 || asids->mt_asid_gen != gru->gs_asid_gen) {
+	spin_lock(&gru->gs_asid_lock);
+	if (asid == 0 || (asids->mt_ctxbitmap == 0 && asids->mt_asid_gen !=
+			  gru->gs_asid_gen)) {
 		asid = gru_assign_asid(gru);
 		asids->mt_asid = asid;
 		asids->mt_asid_gen = gru->gs_asid_gen;
@@ -233,6 +235,7 @@ static int gru_load_mm_tracker(struct gru_state *gru, struct gru_mm_struct *gms,
 	} else {
 		STAT(asid_reuse);
 	}
+	spin_unlock(&gru->gs_asid_lock);
 
 	BUG_ON(asids->mt_ctxbitmap & ctxbitmap);
 	asids->mt_ctxbitmap |= ctxbitmap;
@@ -241,24 +244,28 @@ static int gru_load_mm_tracker(struct gru_state *gru, struct gru_mm_struct *gms,
 	spin_unlock(&gms->ms_asid_lock);
 
 	gru_dbg(grudev,
-		"gru %x, gms %p, ctxnum 0x%d, asid 0x%x, asidmap 0x%lx\n",
-		gru->gs_gid, gms, ctxnum, asid, gms->ms_asidmap[0]);
+		"gid %d, gts %p, gms %p, ctxnum %d, asid 0x%x, asidmap 0x%lx\n",
+		gru->gs_gid, gts, gms, gts->ts_ctxnum, asid,
+		gms->ms_asidmap[0]);
 	return asid;
 }
 
 static void gru_unload_mm_tracker(struct gru_state *gru,
-				  struct gru_mm_struct *gms, int ctxnum)
+					struct gru_thread_state *gts)
 {
+	struct gru_mm_struct *gms = gts->ts_gms;
 	struct gru_mm_tracker *asids;
 	unsigned short ctxbitmap;
 
 	asids = &gms->ms_asids[gru->gs_gid];
-	ctxbitmap = (1 << ctxnum);
+	ctxbitmap = (1 << gts->ts_ctxnum);
 	spin_lock(&gms->ms_asid_lock);
+	spin_lock(&gru->gs_asid_lock);
 	BUG_ON((asids->mt_ctxbitmap & ctxbitmap) != ctxbitmap);
 	asids->mt_ctxbitmap ^= ctxbitmap;
-	gru_dbg(grudev, "gru %x, gms %p, ctxnum 0x%d, asidmap 0x%lx\n",
-		gru->gs_gid, gms, ctxnum, gms->ms_asidmap[0]);
+	gru_dbg(grudev, "gid %d, gts %p, gms %p, ctxnum 0x%d, asidmap 0x%lx\n",
+		gru->gs_gid, gts, gms, gts->ts_ctxnum, gms->ms_asidmap[0]);
+	spin_unlock(&gru->gs_asid_lock);
 	spin_unlock(&gms->ms_asid_lock);
 }
 
@@ -319,6 +326,7 @@ static struct gru_thread_state *gru_alloc_gts(struct vm_area_struct *vma,
 	gts->ts_vma = vma;
 	gts->ts_tlb_int_select = -1;
 	gts->ts_gms = gru_register_mmu_notifier();
+	gts->ts_sizeavail = GRU_SIZEAVAIL(PAGE_SHIFT);
 	if (!gts->ts_gms)
 		goto err;
 
@@ -399,7 +407,7 @@ static void gru_free_gru_context(struct gru_thread_state *gts)
 	struct gru_state *gru;
 
 	gru = gts->ts_gru;
-	gru_dbg(grudev, "gts %p, gru %p\n", gts, gru);
+	gru_dbg(grudev, "gts %p, gid %d\n", gts, gru->gs_gid);
 
 	spin_lock(&gru->gs_lock);
 	gru->gs_gts[gts->ts_ctxnum] = NULL;
@@ -408,6 +416,7 @@ static void gru_free_gru_context(struct gru_thread_state *gts)
 	__clear_bit(gts->ts_ctxnum, &gru->gs_context_map);
 	gts->ts_ctxnum = NULLCTX;
 	gts->ts_gru = NULL;
+	gts->ts_blade = -1;
 	spin_unlock(&gru->gs_lock);
 
 	gts_drop(gts);
@@ -432,8 +441,8 @@ static inline long gru_copy_handle(void *d, void *s)
 	return GRU_HANDLE_BYTES;
 }
 
-static void gru_prefetch_context(void *gseg, void *cb, void *cbe, unsigned long cbrmap,
-				unsigned long length)
+static void gru_prefetch_context(void *gseg, void *cb, void *cbe,
+				unsigned long cbrmap, unsigned long length)
 {
 	int i, scr;
 
@@ -500,12 +509,12 @@ void gru_unload_context(struct gru_thread_state *gts, int savestate)
 	zap_vma_ptes(gts->ts_vma, UGRUADDR(gts), GRU_GSEG_PAGESIZE);
 	cch = get_cch(gru->gs_gru_base_vaddr, ctxnum);
 
+	gru_dbg(grudev, "gts %p\n", gts);
 	lock_cch_handle(cch);
 	if (cch_interrupt_sync(cch))
 		BUG();
-	gru_dbg(grudev, "gts %p\n", gts);
 
-	gru_unload_mm_tracker(gru, gts->ts_gms, gts->ts_ctxnum);
+	gru_unload_mm_tracker(gru, gts);
 	if (savestate)
 		gru_unload_context_data(gts->ts_gdata, gru->gs_gru_base_vaddr,
 					ctxnum, gts->ts_cbr_map,
@@ -534,7 +543,7 @@ static void gru_load_context(struct gru_thread_state *gts)
 	cch = get_cch(gru->gs_gru_base_vaddr, ctxnum);
 
 	lock_cch_handle(cch);
-	asid = gru_load_mm_tracker(gru, gts->ts_gms, gts->ts_ctxnum);
+	asid = gru_load_mm_tracker(gru, gts);
 	cch->tfm_fault_bit_enable =
 	    (gts->ts_user_options == GRU_OPT_MISS_FMM_POLL
 	     || gts->ts_user_options == GRU_OPT_MISS_FMM_INTR);
@@ -544,7 +553,8 @@ static void gru_load_context(struct gru_thread_state *gts)
 		cch->tlb_int_select = gts->ts_tlb_int_select;
 	}
 	cch->tfm_done_bit_enable = 0;
-	err = cch_allocate(cch, asid, gts->ts_cbr_map, gts->ts_dsr_map);
+	err = cch_allocate(cch, asid, gts->ts_sizeavail, gts->ts_cbr_map,
+				gts->ts_dsr_map);
 	if (err) {
 		gru_dbg(grudev,
 			"err %d: cch %p, gts %p, cbr 0x%lx, dsr 0x%lx\n",
@@ -565,11 +575,12 @@ static void gru_load_context(struct gru_thread_state *gts)
 /*
  * Update fields in an active CCH:
  * 	- retarget interrupts on local blade
+ * 	- update sizeavail mask
  * 	- force a delayed context unload by clearing the CCH asids. This
  * 	  forces TLB misses for new GRU instructions. The context is unloaded
  * 	  when the next TLB miss occurs.
  */
-static int gru_update_cch(struct gru_thread_state *gts, int int_select)
+int gru_update_cch(struct gru_thread_state *gts, int force_unload)
 {
 	struct gru_context_configuration_handle *cch;
 	struct gru_state *gru = gts->ts_gru;
@@ -583,9 +594,11 @@ static int gru_update_cch(struct gru_thread_state *gts, int int_select)
 			goto exit;
 		if (cch_interrupt(cch))
 			BUG();
-		if (int_select >= 0) {
-			gts->ts_tlb_int_select = int_select;
-			cch->tlb_int_select = int_select;
+		if (!force_unload) {
+			for (i = 0; i < 8; i++)
+				cch->sizeavail[i] = gts->ts_sizeavail;
+			gts->ts_tlb_int_select = gru_cpu_fault_map_id();
+			cch->tlb_int_select = gru_cpu_fault_map_id();
 		} else {
 			for (i = 0; i < 8; i++)
 				cch->asid[i] = 0;
@@ -617,7 +630,7 @@ static int gru_retarget_intr(struct gru_thread_state *gts)
 
 	gru_dbg(grudev, "retarget from %d to %d\n", gts->ts_tlb_int_select,
 		gru_cpu_fault_map_id());
-	return gru_update_cch(gts, gru_cpu_fault_map_id());
+	return gru_update_cch(gts, 0);
 }
 
 
@@ -688,7 +701,7 @@ static void gru_steal_context(struct gru_thread_state *gts)
 		STAT(steal_context_failed);
 	}
 	gru_dbg(grudev,
-		"stole gru %x, ctxnum %d from gts %p. Need cb %d, ds %d;"
+		"stole gid %d, ctxnum %d from gts %p. Need cb %d, ds %d;"
 		" avail cb %ld, ds %ld\n",
 		gru->gs_gid, ctxnum, ngts, cbr, dsr, hweight64(gru->gs_cbr_map),
 		hweight64(gru->gs_dsr_map));
@@ -727,6 +740,7 @@ again:
 		}
 		reserve_gru_resources(gru, gts);
 		gts->ts_gru = gru;
+		gts->ts_blade = gru->gs_blade_id;
 		gts->ts_ctxnum =
 		    find_first_zero_bit(&gru->gs_context_map, GRU_NUM_CCH);
 		BUG_ON(gts->ts_ctxnum == GRU_NUM_CCH);
@@ -737,7 +751,7 @@ again:
 
 		STAT(assign_context);
 		gru_dbg(grudev,
-			"gseg %p, gts %p, gru %x, ctx %d, cbr %d, dsr %d\n",
+			"gseg %p, gts %p, gid %d, ctx %d, cbr %d, dsr %d\n",
 			gseg_virtual_address(gts->ts_gru, gts->ts_ctxnum), gts,
 			gts->ts_gru->gs_gid, gts->ts_ctxnum,
 			gts->ts_cbr_au_count, gts->ts_dsr_au_count);
@@ -773,8 +787,8 @@ int gru_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 		return VM_FAULT_SIGBUS;
 
 again:
-	preempt_disable();
 	mutex_lock(&gts->ts_ctxlock);
+	preempt_disable();
 	if (gts->ts_gru) {
 		if (gts->ts_gru->gs_blade_id != uv_numa_blade_id()) {
 			STAT(migrated_nopfn_unload);
diff --git a/drivers/misc/sgi-gru/gruprocfs.c b/drivers/misc/sgi-gru/gruprocfs.c
index 73b0ca061bb5..ee74821b171c 100644
--- a/drivers/misc/sgi-gru/gruprocfs.c
+++ b/drivers/misc/sgi-gru/gruprocfs.c
@@ -62,7 +62,9 @@ static int statistics_show(struct seq_file *s, void *p)
 	printstat(s, asid_wrap);
 	printstat(s, asid_reuse);
 	printstat(s, intr);
+	printstat(s, intr_mm_lock_failed);
 	printstat(s, call_os);
+	printstat(s, call_os_offnode_reference);
 	printstat(s, call_os_check_for_bug);
 	printstat(s, call_os_wait_queue);
 	printstat(s, user_flush_tlb);
@@ -120,6 +122,30 @@ static ssize_t statistics_write(struct file *file, const char __user *userbuf,
 	return count;
 }
 
+static int mcs_statistics_show(struct seq_file *s, void *p)
+{
+	int op;
+	unsigned long total, count, max;
+	static char *id[] = {"cch_allocate", "cch_start", "cch_interrupt",
+		"cch_interrupt_sync", "cch_deallocate", "tgh_invalidate"};
+
+	for (op = 0; op < mcsop_last; op++) {
+		count = atomic_long_read(&mcs_op_statistics[op].count);
+		total = atomic_long_read(&mcs_op_statistics[op].total);
+		max = mcs_op_statistics[op].max;
+		seq_printf(s, "%-20s%12ld%12ld%12ld\n", id[op], count,
+			   count ? total / count : 0, max);
+	}
+	return 0;
+}
+
+static ssize_t mcs_statistics_write(struct file *file,
+			const char __user *userbuf, size_t count, loff_t *data)
+{
+	memset(mcs_op_statistics, 0, sizeof(mcs_op_statistics));
+	return count;
+}
+
 static int options_show(struct seq_file *s, void *p)
 {
 	seq_printf(s, "0x%lx\n", gru_options);
@@ -135,6 +161,7 @@ static ssize_t options_write(struct file *file, const char __user *userbuf,
 	if (copy_from_user
 	    (buf, userbuf, count < sizeof(buf) ? count : sizeof(buf)))
 		return -EFAULT;
+	buf[count - 1] = '\0';
 	if (!strict_strtoul(buf, 10, &val))
 		gru_options = val;
 
@@ -199,7 +226,7 @@ static void seq_stop(struct seq_file *file, void *data)
 
 static void *seq_start(struct seq_file *file, loff_t *gid)
 {
-	if (*gid < GRU_MAX_GRUS)
+	if (*gid < gru_max_gids)
 		return gid;
 	return NULL;
 }
@@ -207,7 +234,7 @@ static void *seq_start(struct seq_file *file, loff_t *gid)
 static void *seq_next(struct seq_file *file, void *data, loff_t *gid)
 {
 	(*gid)++;
-	if (*gid < GRU_MAX_GRUS)
+	if (*gid < gru_max_gids)
 		return gid;
 	return NULL;
 }
@@ -231,6 +258,11 @@ static int statistics_open(struct inode *inode, struct file *file)
 	return single_open(file, statistics_show, NULL);
 }
 
+static int mcs_statistics_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, mcs_statistics_show, NULL);
+}
+
 static int options_open(struct inode *inode, struct file *file)
 {
 	return single_open(file, options_show, NULL);
@@ -255,6 +287,14 @@ static const struct file_operations statistics_fops = {
 	.release 	= single_release,
 };
 
+static const struct file_operations mcs_statistics_fops = {
+	.open 		= mcs_statistics_open,
+	.read 		= seq_read,
+	.write 		= mcs_statistics_write,
+	.llseek 	= seq_lseek,
+	.release 	= single_release,
+};
+
 static const struct file_operations options_fops = {
 	.open 		= options_open,
 	.read 		= seq_read,
@@ -283,6 +323,7 @@ static struct proc_entry {
 	struct proc_dir_entry *entry;
 } proc_files[] = {
 	{"statistics", 0644, &statistics_fops},
+	{"mcs_statistics", 0644, &mcs_statistics_fops},
 	{"debug_options", 0644, &options_fops},
 	{"cch_status", 0444, &cch_fops},
 	{"gru_status", 0444, &gru_fops},
diff --git a/drivers/misc/sgi-gru/grutables.h b/drivers/misc/sgi-gru/grutables.h
index a78f70deeb59..bf1eeb7553ed 100644
--- a/drivers/misc/sgi-gru/grutables.h
+++ b/drivers/misc/sgi-gru/grutables.h
@@ -153,6 +153,7 @@
 extern struct gru_stats_s gru_stats;
 extern struct gru_blade_state *gru_base[];
 extern unsigned long gru_start_paddr, gru_end_paddr;
+extern unsigned int gru_max_gids;
 
 #define GRU_MAX_BLADES		MAX_NUMNODES
 #define GRU_MAX_GRUS		(GRU_MAX_BLADES * GRU_CHIPLETS_PER_BLADE)
@@ -184,7 +185,9 @@ struct gru_stats_s {
 	atomic_long_t asid_wrap;
 	atomic_long_t asid_reuse;
 	atomic_long_t intr;
+	atomic_long_t intr_mm_lock_failed;
 	atomic_long_t call_os;
+	atomic_long_t call_os_offnode_reference;
 	atomic_long_t call_os_check_for_bug;
 	atomic_long_t call_os_wait_queue;
 	atomic_long_t user_flush_tlb;
@@ -237,6 +240,17 @@ struct gru_stats_s {
 
 };
 
+enum mcs_op {cchop_allocate, cchop_start, cchop_interrupt, cchop_interrupt_sync,
+	cchop_deallocate, tghop_invalidate, mcsop_last};
+
+struct mcs_op_statistic {
+	atomic_long_t	count;
+	atomic_long_t	total;
+	unsigned long	max;
+};
+
+extern struct mcs_op_statistic mcs_op_statistics[mcsop_last];
+
 #define OPT_DPRINT	1
 #define OPT_STATS	2
 #define GRU_QUICKLOOK	4
@@ -278,13 +292,12 @@ struct gru_stats_s {
 /* Generate a GRU asid value from a GRU base asid & a virtual address. */
 #if defined CONFIG_IA64
 #define VADDR_HI_BIT		64
-#define GRUREGION(addr)		((addr) >> (VADDR_HI_BIT - 3) & 3)
 #elif defined CONFIG_X86_64
 #define VADDR_HI_BIT		48
-#define GRUREGION(addr)		(0)		/* ZZZ could do better */
 #else
 #error "Unsupported architecture"
 #endif
+#define GRUREGION(addr)		((addr) >> (VADDR_HI_BIT - 3) & 3)
 #define GRUASID(asid, addr)	((asid) + GRUREGION(addr))
 
 /*------------------------------------------------------------------------------
@@ -297,12 +310,12 @@ struct gru_state;
  * This structure is pointed to from the mmstruct via the notifier pointer.
  * There is one of these per address space.
  */
-struct gru_mm_tracker {
-	unsigned int		mt_asid_gen;	/* ASID wrap count */
-	int			mt_asid;	/* current base ASID for gru */
-	unsigned short		mt_ctxbitmap;	/* bitmap of contexts using
+struct gru_mm_tracker {				/* pack to reduce size */
+	unsigned int		mt_asid_gen:24;	/* ASID wrap count */
+	unsigned int		mt_asid:24;	/* current base ASID for gru */
+	unsigned short		mt_ctxbitmap:16;/* bitmap of contexts using
 						   asid */
-};
+} __attribute__ ((packed));
 
 struct gru_mm_struct {
 	struct mmu_notifier	ms_notifier;
@@ -348,6 +361,7 @@ struct gru_thread_state {
 	long			ts_user_options;/* misc user option flags */
 	pid_t			ts_tgid_owner;	/* task that is using the
 						   context - for migration */
+	unsigned short		ts_sizeavail;	/* Pagesizes in use */
 	int			ts_tsid;	/* thread that owns the
 						   structure */
 	int			ts_tlb_int_select;/* target cpu if interrupts
@@ -359,6 +373,9 @@ struct gru_thread_state {
 						   required for contest */
 	unsigned char		ts_cbr_au_count;/* Number of CBR resources
 						   required for contest */
+	char			ts_blade;	/* If >= 0, migrate context if
+						   ref from diferent blade */
+	char			ts_force_cch_reload;
 	char			ts_force_unload;/* force context to be unloaded
 						   after migration */
 	char			ts_cbr_idx[GRU_CBR_AU];/* CBR numbers of each
@@ -392,12 +409,12 @@ struct gru_state {
 							   gru segments (64) */
 	void			*gs_gru_base_vaddr;	/* Virtual address of
 							   gru segments (64) */
-	unsigned char		gs_gid;			/* unique GRU number */
+	unsigned short		gs_gid;			/* unique GRU number */
+	unsigned short		gs_blade_id;		/* blade of GRU */
 	unsigned char		gs_tgh_local_shift;	/* used to pick TGH for
 							   local flush */
 	unsigned char		gs_tgh_first_remote;	/* starting TGH# for
 							   remote flush */
-	unsigned short		gs_blade_id;		/* blade of GRU */
 	spinlock_t		gs_asid_lock;		/* lock used for
 							   assigning asids */
 	spinlock_t		gs_lock;		/* lock used for
@@ -492,6 +509,10 @@ struct gru_blade_state {
 			(i) < GRU_CHIPLETS_PER_BLADE;			\
 			(i)++, (gru)++)
 
+/* Scan all GRUs */
+#define foreach_gid(gid)						\
+	for ((gid) = 0; (gid) < gru_max_gids; (gid)++)
+
 /* Scan all active GTSs on a gru. Note: must hold ss_lock to use this macro. */
 #define for_each_gts_on_gru(gts, gru, ctxnum)				\
 	for ((ctxnum) = 0; (ctxnum) < GRU_NUM_CCH; (ctxnum)++)		\
@@ -578,9 +599,11 @@ extern struct gru_thread_state *gru_find_thread_state(struct vm_area_struct
 extern struct gru_thread_state *gru_alloc_thread_state(struct vm_area_struct
 				*vma, int tsid);
 extern void gru_unload_context(struct gru_thread_state *gts, int savestate);
+extern int gru_update_cch(struct gru_thread_state *gts, int force_unload);
 extern void gts_drop(struct gru_thread_state *gts);
 extern void gru_tgh_flush_init(struct gru_state *gru);
 extern int gru_kservices_init(struct gru_state *gru);
+extern void gru_kservices_exit(struct gru_state *gru);
 extern irqreturn_t gru_intr(int irq, void *dev_id);
 extern int gru_handle_user_call_os(unsigned long address);
 extern int gru_user_flush_tlb(unsigned long arg);
diff --git a/drivers/misc/sgi-gru/grutlbpurge.c b/drivers/misc/sgi-gru/grutlbpurge.c
index c84496a77691..1d125091f5e7 100644
--- a/drivers/misc/sgi-gru/grutlbpurge.c
+++ b/drivers/misc/sgi-gru/grutlbpurge.c
@@ -187,7 +187,7 @@ void gru_flush_tlb_range(struct gru_mm_struct *gms, unsigned long start,
 	"  FLUSH gruid %d, asid 0x%x, num %ld, cbmap 0x%x\n",
 				gid, asid, num, asids->mt_ctxbitmap);
 			tgh = get_lock_tgh_handle(gru);
-			tgh_invalidate(tgh, start, 0, asid, grupagesize, 0,
+			tgh_invalidate(tgh, start, ~0, asid, grupagesize, 0,
 				       num - 1, asids->mt_ctxbitmap);
 			get_unlock_tgh_handle(tgh);
 		} else {
@@ -210,11 +210,10 @@ void gru_flush_all_tlb(struct gru_state *gru)
 {
 	struct gru_tlb_global_handle *tgh;
 
-	gru_dbg(grudev, "gru %p, gid %d\n", gru, gru->gs_gid);
+	gru_dbg(grudev, "gid %d\n", gru->gs_gid);
 	tgh = get_lock_tgh_handle(gru);
-	tgh_invalidate(tgh, 0, ~0, 0, 1, 1, GRUMAXINVAL - 1, 0);
+	tgh_invalidate(tgh, 0, ~0, 0, 1, 1, GRUMAXINVAL - 1, 0xffff);
 	get_unlock_tgh_handle(tgh);
-	preempt_enable();
 }
 
 /*
diff --git a/drivers/misc/sgi-xp/xpc.h b/drivers/misc/sgi-xp/xpc.h
index 275b78896a73..114444cfd496 100644
--- a/drivers/misc/sgi-xp/xpc.h
+++ b/drivers/misc/sgi-xp/xpc.h
@@ -92,7 +92,9 @@ struct xpc_rsvd_page {
 	u8 pad1[3];		/* align to next u64 in 1st 64-byte cacheline */
 	union {
 		unsigned long vars_pa;	/* phys address of struct xpc_vars */
-		unsigned long activate_mq_gpa; /* gru phy addr of activate_mq */
+		unsigned long activate_gru_mq_desc_gpa; /* phys addr of */
+							/* activate mq's */
+							/* gru mq descriptor */
 	} sn;
 	unsigned long ts_jiffies; /* timestamp when rsvd pg was setup by XPC */
 	u64 pad2[10];		/* align to last u64 in 2nd 64-byte cacheline */
@@ -189,7 +191,9 @@ struct xpc_gru_mq_uv {
 	int irq;		/* irq raised when message is received in mq */
 	int mmr_blade;		/* blade where watchlist was allocated from */
 	unsigned long mmr_offset; /* offset of irq mmr located on mmr_blade */
+	unsigned long mmr_value; /* value of irq mmr located on mmr_blade */
 	int watchlist_num;	/* number of watchlist allocatd by BIOS */
+	void *gru_mq_desc;	/* opaque structure used by the GRU driver */
 };
 
 /*
@@ -197,6 +201,7 @@ struct xpc_gru_mq_uv {
  * heartbeat, partition active state, and channel state. This is UV only.
  */
 struct xpc_activate_mq_msghdr_uv {
+	unsigned int gru_msg_hdr; /* FOR GRU INTERNAL USE ONLY */
 	short partid;		/* sender's partid */
 	u8 act_state;		/* sender's act_state at time msg sent */
 	u8 type;		/* message's type */
@@ -232,7 +237,7 @@ struct xpc_activate_mq_msg_heartbeat_req_uv {
 struct xpc_activate_mq_msg_activate_req_uv {
 	struct xpc_activate_mq_msghdr_uv hdr;
 	unsigned long rp_gpa;
-	unsigned long activate_mq_gpa;
+	unsigned long activate_gru_mq_desc_gpa;
 };
 
 struct xpc_activate_mq_msg_deactivate_req_uv {
@@ -263,7 +268,7 @@ struct xpc_activate_mq_msg_chctl_openreply_uv {
 	short ch_number;
 	short remote_nentries;	/* ??? Is this needed? What is? */
 	short local_nentries;	/* ??? Is this needed? What is? */
-	unsigned long local_notify_mq_gpa;
+	unsigned long notify_gru_mq_desc_gpa;
 };
 
 /*
@@ -510,8 +515,8 @@ struct xpc_channel_sn2 {
 };
 
 struct xpc_channel_uv {
-	unsigned long remote_notify_mq_gpa;	/* gru phys address of remote */
-						/* partition's notify mq */
+	void *cached_notify_gru_mq_desc; /* remote partition's notify mq's */
+					 /* gru mq descriptor */
 
 	struct xpc_send_msg_slot_uv *send_msg_slots;
 	void *recv_msg_slots;	/* each slot will hold a xpc_notify_mq_msg_uv */
@@ -682,8 +687,12 @@ struct xpc_partition_sn2 {
 };
 
 struct xpc_partition_uv {
-	unsigned long remote_activate_mq_gpa;	/* gru phys address of remote */
-						/* partition's activate mq */
+	unsigned long activate_gru_mq_desc_gpa;	/* phys addr of parititon's */
+						/* activate mq's gru mq */
+						/* descriptor */
+	void *cached_activate_gru_mq_desc; /* cached copy of partition's */
+					   /* activate mq's gru mq descriptor */
+	struct mutex cached_activate_gru_mq_desc_mutex;
 	spinlock_t flags_lock;	/* protect updating of flags */
 	unsigned int flags;	/* general flags */
 	u8 remote_act_state;	/* remote partition's act_state */
@@ -694,8 +703,9 @@ struct xpc_partition_uv {
 
 /* struct xpc_partition_uv flags */
 
-#define XPC_P_HEARTBEAT_OFFLINE_UV	0x00000001
-#define XPC_P_ENGAGED_UV		0x00000002
+#define XPC_P_HEARTBEAT_OFFLINE_UV		0x00000001
+#define XPC_P_ENGAGED_UV			0x00000002
+#define XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV	0x00000004
 
 /* struct xpc_partition_uv act_state change requests */
 
@@ -804,6 +814,7 @@ extern void xpc_activate_kthreads(struct xpc_channel *, int);
 extern void xpc_create_kthreads(struct xpc_channel *, int, int);
 extern void xpc_disconnect_wait(int);
 extern int (*xpc_setup_partitions_sn) (void);
+extern void (*xpc_teardown_partitions_sn) (void);
 extern enum xp_retval (*xpc_get_partition_rsvd_page_pa) (void *, u64 *,
 							 unsigned long *,
 							 size_t *);
@@ -846,8 +857,8 @@ extern void (*xpc_send_chctl_openrequest) (struct xpc_channel *,
 					   unsigned long *);
 extern void (*xpc_send_chctl_openreply) (struct xpc_channel *, unsigned long *);
 
-extern void (*xpc_save_remote_msgqueue_pa) (struct xpc_channel *,
-					    unsigned long);
+extern enum xp_retval (*xpc_save_remote_msgqueue_pa) (struct xpc_channel *,
+						      unsigned long);
 
 extern enum xp_retval (*xpc_send_payload) (struct xpc_channel *, u32, void *,
 					   u16, u8, xpc_notify_func, void *);
diff --git a/drivers/misc/sgi-xp/xpc_channel.c b/drivers/misc/sgi-xp/xpc_channel.c
index 45fd653dbe31..99a2534c38a1 100644
--- a/drivers/misc/sgi-xp/xpc_channel.c
+++ b/drivers/misc/sgi-xp/xpc_channel.c
@@ -183,6 +183,7 @@ xpc_process_openclose_chctl_flags(struct xpc_partition *part, int ch_number,
 	    &part->remote_openclose_args[ch_number];
 	struct xpc_channel *ch = &part->channels[ch_number];
 	enum xp_retval reason;
+	enum xp_retval ret;
 
 	spin_lock_irqsave(&ch->lock, irq_flags);
 
@@ -399,8 +400,13 @@ again:
 		DBUG_ON(args->local_nentries == 0);
 		DBUG_ON(args->remote_nentries == 0);
 
+		ret = xpc_save_remote_msgqueue_pa(ch, args->local_msgqueue_pa);
+		if (ret != xpSuccess) {
+			XPC_DISCONNECT_CHANNEL(ch, ret, &irq_flags);
+			spin_unlock_irqrestore(&ch->lock, irq_flags);
+			return;
+		}
 		ch->flags |= XPC_C_ROPENREPLY;
-		xpc_save_remote_msgqueue_pa(ch, args->local_msgqueue_pa);
 
 		if (args->local_nentries < ch->remote_nentries) {
 			dev_dbg(xpc_chan, "XPC_CHCTL_OPENREPLY: new "
diff --git a/drivers/misc/sgi-xp/xpc_main.c b/drivers/misc/sgi-xp/xpc_main.c
index 6576170de962..1ab9fda87fab 100644
--- a/drivers/misc/sgi-xp/xpc_main.c
+++ b/drivers/misc/sgi-xp/xpc_main.c
@@ -171,6 +171,7 @@ static struct notifier_block xpc_die_notifier = {
 };
 
 int (*xpc_setup_partitions_sn) (void);
+void (*xpc_teardown_partitions_sn) (void);
 enum xp_retval (*xpc_get_partition_rsvd_page_pa) (void *buf, u64 *cookie,
 						  unsigned long *rp_pa,
 						  size_t *len);
@@ -217,8 +218,8 @@ void (*xpc_send_chctl_openrequest) (struct xpc_channel *ch,
 void (*xpc_send_chctl_openreply) (struct xpc_channel *ch,
 				  unsigned long *irq_flags);
 
-void (*xpc_save_remote_msgqueue_pa) (struct xpc_channel *ch,
-				     unsigned long msgqueue_pa);
+enum xp_retval (*xpc_save_remote_msgqueue_pa) (struct xpc_channel *ch,
+					       unsigned long msgqueue_pa);
 
 enum xp_retval (*xpc_send_payload) (struct xpc_channel *ch, u32 flags,
 				    void *payload, u16 payload_size,
@@ -998,6 +999,7 @@ xpc_setup_partitions(void)
 static void
 xpc_teardown_partitions(void)
 {
+	xpc_teardown_partitions_sn();
 	kfree(xpc_partitions);
 }
 
diff --git a/drivers/misc/sgi-xp/xpc_sn2.c b/drivers/misc/sgi-xp/xpc_sn2.c
index 2e975762c32b..eaaa964942de 100644
--- a/drivers/misc/sgi-xp/xpc_sn2.c
+++ b/drivers/misc/sgi-xp/xpc_sn2.c
@@ -66,6 +66,12 @@ xpc_setup_partitions_sn_sn2(void)
 	return 0;
 }
 
+static void
+xpc_teardown_partitions_sn_sn2(void)
+{
+	/* nothing needs to be done */
+}
+
 /* SH_IPI_ACCESS shub register value on startup */
 static u64 xpc_sh1_IPI_access_sn2;
 static u64 xpc_sh2_IPI_access0_sn2;
@@ -436,11 +442,12 @@ xpc_send_chctl_local_msgrequest_sn2(struct xpc_channel *ch)
 	XPC_SEND_LOCAL_NOTIFY_IRQ_SN2(ch, XPC_CHCTL_MSGREQUEST);
 }
 
-static void
+static enum xp_retval
 xpc_save_remote_msgqueue_pa_sn2(struct xpc_channel *ch,
 				unsigned long msgqueue_pa)
 {
 	ch->sn.sn2.remote_msgqueue_pa = msgqueue_pa;
+	return xpSuccess;
 }
 
 /*
@@ -1737,20 +1744,20 @@ xpc_clear_remote_msgqueue_flags_sn2(struct xpc_channel *ch)
 {
 	struct xpc_channel_sn2 *ch_sn2 = &ch->sn.sn2;
 	struct xpc_msg_sn2 *msg;
-	s64 put;
+	s64 put, remote_nentries = ch->remote_nentries;
 
 	/* flags are zeroed when the buffer is allocated */
-	if (ch_sn2->remote_GP.put < ch->remote_nentries)
+	if (ch_sn2->remote_GP.put < remote_nentries)
 		return;
 
-	put = max(ch_sn2->w_remote_GP.put, ch->remote_nentries);
+	put = max(ch_sn2->w_remote_GP.put, remote_nentries);
 	do {
 		msg = (struct xpc_msg_sn2 *)((u64)ch_sn2->remote_msgqueue +
-					     (put % ch->remote_nentries) *
+					     (put % remote_nentries) *
 					     ch->entry_size);
 		DBUG_ON(!(msg->flags & XPC_M_SN2_READY));
 		DBUG_ON(!(msg->flags & XPC_M_SN2_DONE));
-		DBUG_ON(msg->number != put - ch->remote_nentries);
+		DBUG_ON(msg->number != put - remote_nentries);
 		msg->flags = 0;
 	} while (++put < ch_sn2->remote_GP.put);
 }
@@ -2315,6 +2322,7 @@ xpc_init_sn2(void)
 	size_t buf_size;
 
 	xpc_setup_partitions_sn = xpc_setup_partitions_sn_sn2;
+	xpc_teardown_partitions_sn = xpc_teardown_partitions_sn_sn2;
 	xpc_get_partition_rsvd_page_pa = xpc_get_partition_rsvd_page_pa_sn2;
 	xpc_setup_rsvd_page_sn = xpc_setup_rsvd_page_sn_sn2;
 	xpc_increment_heartbeat = xpc_increment_heartbeat_sn2;
diff --git a/drivers/misc/sgi-xp/xpc_uv.c b/drivers/misc/sgi-xp/xpc_uv.c
index 29c0502a96b2..f7fff4727edb 100644
--- a/drivers/misc/sgi-xp/xpc_uv.c
+++ b/drivers/misc/sgi-xp/xpc_uv.c
@@ -31,6 +31,21 @@
 #include "../sgi-gru/grukservices.h"
 #include "xpc.h"
 
+#if defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
+struct uv_IO_APIC_route_entry {
+	__u64	vector		:  8,
+		delivery_mode	:  3,
+		dest_mode	:  1,
+		delivery_status	:  1,
+		polarity	:  1,
+		__reserved_1	:  1,
+		trigger		:  1,
+		mask		:  1,
+		__reserved_2	: 15,
+		dest		: 32;
+};
+#endif
+
 static atomic64_t xpc_heartbeat_uv;
 static DECLARE_BITMAP(xpc_heartbeating_to_mask_uv, XP_MAX_NPARTITIONS_UV);
 
@@ -56,26 +71,52 @@ xpc_setup_partitions_sn_uv(void)
 	for (partid = 0; partid < XP_MAX_NPARTITIONS_UV; partid++) {
 		part_uv = &xpc_partitions[partid].sn.uv;
 
+		mutex_init(&part_uv->cached_activate_gru_mq_desc_mutex);
 		spin_lock_init(&part_uv->flags_lock);
 		part_uv->remote_act_state = XPC_P_AS_INACTIVE;
 	}
 	return 0;
 }
 
+static void
+xpc_teardown_partitions_sn_uv(void)
+{
+	short partid;
+	struct xpc_partition_uv *part_uv;
+	unsigned long irq_flags;
+
+	for (partid = 0; partid < XP_MAX_NPARTITIONS_UV; partid++) {
+		part_uv = &xpc_partitions[partid].sn.uv;
+
+		if (part_uv->cached_activate_gru_mq_desc != NULL) {
+			mutex_lock(&part_uv->cached_activate_gru_mq_desc_mutex);
+			spin_lock_irqsave(&part_uv->flags_lock, irq_flags);
+			part_uv->flags &= ~XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV;
+			spin_unlock_irqrestore(&part_uv->flags_lock, irq_flags);
+			kfree(part_uv->cached_activate_gru_mq_desc);
+			part_uv->cached_activate_gru_mq_desc = NULL;
+			mutex_unlock(&part_uv->
+				     cached_activate_gru_mq_desc_mutex);
+		}
+	}
+}
+
 static int
 xpc_get_gru_mq_irq_uv(struct xpc_gru_mq_uv *mq, int cpu, char *irq_name)
 {
+	int mmr_pnode = uv_blade_to_pnode(mq->mmr_blade);
+
 #if defined CONFIG_X86_64
 	mq->irq = uv_setup_irq(irq_name, cpu, mq->mmr_blade, mq->mmr_offset);
 	if (mq->irq < 0) {
 		dev_err(xpc_part, "uv_setup_irq() returned error=%d\n",
-			mq->irq);
+			-mq->irq);
+		return mq->irq;
 	}
 
-#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
-	int mmr_pnode;
-	unsigned long mmr_value;
+	mq->mmr_value = uv_read_global_mmr64(mmr_pnode, mq->mmr_offset);
 
+#elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
 	if (strcmp(irq_name, XPC_ACTIVATE_IRQ_NAME) == 0)
 		mq->irq = SGI_XPC_ACTIVATE;
 	else if (strcmp(irq_name, XPC_NOTIFY_IRQ_NAME) == 0)
@@ -83,10 +124,8 @@ xpc_get_gru_mq_irq_uv(struct xpc_gru_mq_uv *mq, int cpu, char *irq_name)
 	else
 		return -EINVAL;
 
-	mmr_pnode = uv_blade_to_pnode(mq->mmr_blade);
-	mmr_value = (unsigned long)cpu_physical_id(cpu) << 32 | mq->irq;
-
-	uv_write_global_mmr64(mmr_pnode, mq->mmr_offset, mmr_value);
+	mq->mmr_value = (unsigned long)cpu_physical_id(cpu) << 32 | mq->irq;
+	uv_write_global_mmr64(mmr_pnode, mq->mmr_offset, mq->mmr_value);
 #else
 	#error not a supported configuration
 #endif
@@ -127,7 +166,7 @@ xpc_gru_mq_watchlist_alloc_uv(struct xpc_gru_mq_uv *mq)
 		return ret;
 	}
 #elif defined CONFIG_IA64_GENERIC || defined CONFIG_IA64_SGI_UV
-	ret = sn_mq_watchlist_alloc(mq->mmr_blade, uv_gpa(mq->address),
+	ret = sn_mq_watchlist_alloc(mq->mmr_blade, (void *)uv_gpa(mq->address),
 				    mq->order, &mq->mmr_offset);
 	if (ret < 0) {
 		dev_err(xpc_part, "sn_mq_watchlist_alloc() failed, ret=%d\n",
@@ -168,12 +207,22 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name,
 	int pg_order;
 	struct page *page;
 	struct xpc_gru_mq_uv *mq;
+	struct uv_IO_APIC_route_entry *mmr_value;
 
 	mq = kmalloc(sizeof(struct xpc_gru_mq_uv), GFP_KERNEL);
 	if (mq == NULL) {
 		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to kmalloc() "
 			"a xpc_gru_mq_uv structure\n");
 		ret = -ENOMEM;
+		goto out_0;
+	}
+
+	mq->gru_mq_desc = kzalloc(sizeof(struct gru_message_queue_desc),
+				  GFP_KERNEL);
+	if (mq->gru_mq_desc == NULL) {
+		dev_err(xpc_part, "xpc_create_gru_mq_uv() failed to kmalloc() "
+			"a gru_message_queue_desc structure\n");
+		ret = -ENOMEM;
 		goto out_1;
 	}
 
@@ -194,14 +243,6 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name,
 	}
 	mq->address = page_address(page);
 
-	ret = gru_create_message_queue(mq->address, mq_size);
-	if (ret != 0) {
-		dev_err(xpc_part, "gru_create_message_queue() returned "
-			"error=%d\n", ret);
-		ret = -EINVAL;
-		goto out_3;
-	}
-
 	/* enable generation of irq when GRU mq operation occurs to this mq */
 	ret = xpc_gru_mq_watchlist_alloc_uv(mq);
 	if (ret != 0)
@@ -214,10 +255,20 @@ xpc_create_gru_mq_uv(unsigned int mq_size, int cpu, char *irq_name,
 	ret = request_irq(mq->irq, irq_handler, 0, irq_name, NULL);
 	if (ret != 0) {
 		dev_err(xpc_part, "request_irq(irq=%d) returned error=%d\n",
-			mq->irq, ret);
+			mq->irq, -ret);
 		goto out_5;
 	}
 
+	mmr_value = (struct uv_IO_APIC_route_entry *)&mq->mmr_value;
+	ret = gru_create_message_queue(mq->gru_mq_desc, mq->address, mq_size,
+				       nid, mmr_value->vector, mmr_value->dest);
+	if (ret != 0) {
+		dev_err(xpc_part, "gru_create_message_queue() returned "
+			"error=%d\n", ret);
+		ret = -EINVAL;
+		goto out_6;
+	}
+
 	/* allow other partitions to access this GRU mq */
 	xp_ret = xp_expand_memprotect(xp_pa(mq->address), mq_size);
 	if (xp_ret != xpSuccess) {
@@ -237,8 +288,10 @@ out_4:
 out_3:
 	free_pages((unsigned long)mq->address, pg_order);
 out_2:
-	kfree(mq);
+	kfree(mq->gru_mq_desc);
 out_1:
+	kfree(mq);
+out_0:
 	return ERR_PTR(ret);
 }
 
@@ -268,13 +321,14 @@ xpc_destroy_gru_mq_uv(struct xpc_gru_mq_uv *mq)
 }
 
 static enum xp_retval
-xpc_send_gru_msg(unsigned long mq_gpa, void *msg, size_t msg_size)
+xpc_send_gru_msg(struct gru_message_queue_desc *gru_mq_desc, void *msg,
+		 size_t msg_size)
 {
 	enum xp_retval xp_ret;
 	int ret;
 
 	while (1) {
-		ret = gru_send_message_gpa(mq_gpa, msg, msg_size);
+		ret = gru_send_message_gpa(gru_mq_desc, msg, msg_size);
 		if (ret == MQE_OK) {
 			xp_ret = xpSuccess;
 			break;
@@ -421,7 +475,15 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part,
 		part_uv->act_state_req = XPC_P_ASR_ACTIVATE_UV;
 		part->remote_rp_pa = msg->rp_gpa; /* !!! _pa is _gpa */
 		part->remote_rp_ts_jiffies = msg_hdr->rp_ts_jiffies;
-		part_uv->remote_activate_mq_gpa = msg->activate_mq_gpa;
+
+		if (msg->activate_gru_mq_desc_gpa !=
+		    part_uv->activate_gru_mq_desc_gpa) {
+			spin_lock_irqsave(&part_uv->flags_lock, irq_flags);
+			part_uv->flags &= ~XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV;
+			spin_unlock_irqrestore(&part_uv->flags_lock, irq_flags);
+			part_uv->activate_gru_mq_desc_gpa =
+			    msg->activate_gru_mq_desc_gpa;
+		}
 		spin_unlock_irqrestore(&xpc_activate_IRQ_rcvd_lock, irq_flags);
 
 		(*wakeup_hb_checker)++;
@@ -498,7 +560,7 @@ xpc_handle_activate_mq_msg_uv(struct xpc_partition *part,
 		args = &part->remote_openclose_args[msg->ch_number];
 		args->remote_nentries = msg->remote_nentries;
 		args->local_nentries = msg->local_nentries;
-		args->local_msgqueue_pa = msg->local_notify_mq_gpa;
+		args->local_msgqueue_pa = msg->notify_gru_mq_desc_gpa;
 
 		spin_lock_irqsave(&part->chctl_lock, irq_flags);
 		part->chctl.flags[msg->ch_number] |= XPC_CHCTL_OPENREPLY;
@@ -558,9 +620,10 @@ xpc_handle_activate_IRQ_uv(int irq, void *dev_id)
 	short partid;
 	struct xpc_partition *part;
 	int wakeup_hb_checker = 0;
+	int part_referenced;
 
 	while (1) {
-		msg_hdr = gru_get_next_message(xpc_activate_mq_uv->address);
+		msg_hdr = gru_get_next_message(xpc_activate_mq_uv->gru_mq_desc);
 		if (msg_hdr == NULL)
 			break;
 
@@ -571,14 +634,15 @@ xpc_handle_activate_IRQ_uv(int irq, void *dev_id)
 				partid);
 		} else {
 			part = &xpc_partitions[partid];
-			if (xpc_part_ref(part)) {
-				xpc_handle_activate_mq_msg_uv(part, msg_hdr,
-							    &wakeup_hb_checker);
+
+			part_referenced = xpc_part_ref(part);
+			xpc_handle_activate_mq_msg_uv(part, msg_hdr,
+						      &wakeup_hb_checker);
+			if (part_referenced)
 				xpc_part_deref(part);
-			}
 		}
 
-		gru_free_message(xpc_activate_mq_uv->address, msg_hdr);
+		gru_free_message(xpc_activate_mq_uv->gru_mq_desc, msg_hdr);
 	}
 
 	if (wakeup_hb_checker)
@@ -588,21 +652,73 @@ xpc_handle_activate_IRQ_uv(int irq, void *dev_id)
 }
 
 static enum xp_retval
+xpc_cache_remote_gru_mq_desc_uv(struct gru_message_queue_desc *gru_mq_desc,
+				unsigned long gru_mq_desc_gpa)
+{
+	enum xp_retval ret;
+
+	ret = xp_remote_memcpy(uv_gpa(gru_mq_desc), gru_mq_desc_gpa,
+			       sizeof(struct gru_message_queue_desc));
+	if (ret == xpSuccess)
+		gru_mq_desc->mq = NULL;
+
+	return ret;
+}
+
+static enum xp_retval
 xpc_send_activate_IRQ_uv(struct xpc_partition *part, void *msg, size_t msg_size,
 			 int msg_type)
 {
 	struct xpc_activate_mq_msghdr_uv *msg_hdr = msg;
+	struct xpc_partition_uv *part_uv = &part->sn.uv;
+	struct gru_message_queue_desc *gru_mq_desc;
+	unsigned long irq_flags;
+	enum xp_retval ret;
 
 	DBUG_ON(msg_size > XPC_ACTIVATE_MSG_SIZE_UV);
 
 	msg_hdr->type = msg_type;
-	msg_hdr->partid = XPC_PARTID(part);
+	msg_hdr->partid = xp_partition_id;
 	msg_hdr->act_state = part->act_state;
 	msg_hdr->rp_ts_jiffies = xpc_rsvd_page->ts_jiffies;
 
+	mutex_lock(&part_uv->cached_activate_gru_mq_desc_mutex);
+again:
+	if (!(part_uv->flags & XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV)) {
+		gru_mq_desc = part_uv->cached_activate_gru_mq_desc;
+		if (gru_mq_desc == NULL) {
+			gru_mq_desc = kmalloc(sizeof(struct
+					      gru_message_queue_desc),
+					      GFP_KERNEL);
+			if (gru_mq_desc == NULL) {
+				ret = xpNoMemory;
+				goto done;
+			}
+			part_uv->cached_activate_gru_mq_desc = gru_mq_desc;
+		}
+
+		ret = xpc_cache_remote_gru_mq_desc_uv(gru_mq_desc,
+						      part_uv->
+						      activate_gru_mq_desc_gpa);
+		if (ret != xpSuccess)
+			goto done;
+
+		spin_lock_irqsave(&part_uv->flags_lock, irq_flags);
+		part_uv->flags |= XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV;
+		spin_unlock_irqrestore(&part_uv->flags_lock, irq_flags);
+	}
+
 	/* ??? Is holding a spin_lock (ch->lock) during this call a bad idea? */
-	return xpc_send_gru_msg(part->sn.uv.remote_activate_mq_gpa, msg,
-				msg_size);
+	ret = xpc_send_gru_msg(part_uv->cached_activate_gru_mq_desc, msg,
+			       msg_size);
+	if (ret != xpSuccess) {
+		smp_rmb();	/* ensure a fresh copy of part_uv->flags */
+		if (!(part_uv->flags & XPC_P_CACHED_ACTIVATE_GRU_MQ_DESC_UV))
+			goto again;
+	}
+done:
+	mutex_unlock(&part_uv->cached_activate_gru_mq_desc_mutex);
+	return ret;
 }
 
 static void
@@ -620,7 +736,7 @@ static void
 xpc_send_activate_IRQ_ch_uv(struct xpc_channel *ch, unsigned long *irq_flags,
 			 void *msg, size_t msg_size, int msg_type)
 {
-	struct xpc_partition *part = &xpc_partitions[ch->number];
+	struct xpc_partition *part = &xpc_partitions[ch->partid];
 	enum xp_retval ret;
 
 	ret = xpc_send_activate_IRQ_uv(part, msg, msg_size, msg_type);
@@ -692,7 +808,8 @@ xpc_get_partition_rsvd_page_pa_uv(void *buf, u64 *cookie, unsigned long *rp_pa,
 static int
 xpc_setup_rsvd_page_sn_uv(struct xpc_rsvd_page *rp)
 {
-	rp->sn.activate_mq_gpa = uv_gpa(xpc_activate_mq_uv->address);
+	rp->sn.activate_gru_mq_desc_gpa =
+	    uv_gpa(xpc_activate_mq_uv->gru_mq_desc);
 	return 0;
 }
 
@@ -787,7 +904,8 @@ xpc_request_partition_activation_uv(struct xpc_rsvd_page *remote_rp,
 
 	part->remote_rp_pa = remote_rp_gpa; /* !!! _pa here is really _gpa */
 	part->remote_rp_ts_jiffies = remote_rp->ts_jiffies;
-	part->sn.uv.remote_activate_mq_gpa = remote_rp->sn.activate_mq_gpa;
+	part->sn.uv.activate_gru_mq_desc_gpa =
+	    remote_rp->sn.activate_gru_mq_desc_gpa;
 
 	/*
 	 * ??? Is it a good idea to make this conditional on what is
@@ -795,7 +913,8 @@ xpc_request_partition_activation_uv(struct xpc_rsvd_page *remote_rp,
 	 */
 	if (part->sn.uv.remote_act_state == XPC_P_AS_INACTIVE) {
 		msg.rp_gpa = uv_gpa(xpc_rsvd_page);
-		msg.activate_mq_gpa = xpc_rsvd_page->sn.activate_mq_gpa;
+		msg.activate_gru_mq_desc_gpa =
+		    xpc_rsvd_page->sn.activate_gru_mq_desc_gpa;
 		xpc_send_activate_IRQ_part_uv(part, &msg, sizeof(msg),
 					   XPC_ACTIVATE_MQ_MSG_ACTIVATE_REQ_UV);
 	}
@@ -857,7 +976,8 @@ xpc_get_fifo_entry_uv(struct xpc_fifo_head_uv *head)
 		if (head->first == NULL)
 			head->last = NULL;
 	}
-	head->n_entries++;
+	head->n_entries--;
+	BUG_ON(head->n_entries < 0);
 	spin_unlock_irqrestore(&head->lock, irq_flags);
 	first->next = NULL;
 	return first;
@@ -876,8 +996,7 @@ xpc_put_fifo_entry_uv(struct xpc_fifo_head_uv *head,
 	else
 		head->first = last;
 	head->last = last;
-	head->n_entries--;
-	BUG_ON(head->n_entries < 0);
+	head->n_entries++;
 	spin_unlock_irqrestore(&head->lock, irq_flags);
 }
 
@@ -1037,6 +1156,12 @@ xpc_setup_msg_structures_uv(struct xpc_channel *ch)
 
 	DBUG_ON(ch->flags & XPC_C_SETUP);
 
+	ch_uv->cached_notify_gru_mq_desc = kmalloc(sizeof(struct
+						   gru_message_queue_desc),
+						   GFP_KERNEL);
+	if (ch_uv->cached_notify_gru_mq_desc == NULL)
+		return xpNoMemory;
+
 	ret = xpc_allocate_send_msg_slot_uv(ch);
 	if (ret == xpSuccess) {
 
@@ -1060,7 +1185,8 @@ xpc_teardown_msg_structures_uv(struct xpc_channel *ch)
 
 	DBUG_ON(!spin_is_locked(&ch->lock));
 
-	ch_uv->remote_notify_mq_gpa = 0;
+	kfree(ch_uv->cached_notify_gru_mq_desc);
+	ch_uv->cached_notify_gru_mq_desc = NULL;
 
 	if (ch->flags & XPC_C_SETUP) {
 		xpc_init_fifo_uv(&ch_uv->msg_slot_free_list);
@@ -1111,7 +1237,7 @@ xpc_send_chctl_openreply_uv(struct xpc_channel *ch, unsigned long *irq_flags)
 	msg.ch_number = ch->number;
 	msg.local_nentries = ch->local_nentries;
 	msg.remote_nentries = ch->remote_nentries;
-	msg.local_notify_mq_gpa = uv_gpa(xpc_notify_mq_uv);
+	msg.notify_gru_mq_desc_gpa = uv_gpa(xpc_notify_mq_uv->gru_mq_desc);
 	xpc_send_activate_IRQ_ch_uv(ch, irq_flags, &msg, sizeof(msg),
 				    XPC_ACTIVATE_MQ_MSG_CHCTL_OPENREPLY_UV);
 }
@@ -1128,11 +1254,15 @@ xpc_send_chctl_local_msgrequest_uv(struct xpc_partition *part, int ch_number)
 	xpc_wakeup_channel_mgr(part);
 }
 
-static void
+static enum xp_retval
 xpc_save_remote_msgqueue_pa_uv(struct xpc_channel *ch,
-			       unsigned long msgqueue_pa)
+			       unsigned long gru_mq_desc_gpa)
 {
-	ch->sn.uv.remote_notify_mq_gpa = msgqueue_pa;
+	struct xpc_channel_uv *ch_uv = &ch->sn.uv;
+
+	DBUG_ON(ch_uv->cached_notify_gru_mq_desc == NULL);
+	return xpc_cache_remote_gru_mq_desc_uv(ch_uv->cached_notify_gru_mq_desc,
+					       gru_mq_desc_gpa);
 }
 
 static void
@@ -1339,7 +1469,8 @@ xpc_handle_notify_IRQ_uv(int irq, void *dev_id)
 	short partid;
 	struct xpc_partition *part;
 
-	while ((msg = gru_get_next_message(xpc_notify_mq_uv)) != NULL) {
+	while ((msg = gru_get_next_message(xpc_notify_mq_uv->gru_mq_desc)) !=
+	       NULL) {
 
 		partid = msg->hdr.partid;
 		if (partid < 0 || partid >= XP_MAX_NPARTITIONS_UV) {
@@ -1354,7 +1485,7 @@ xpc_handle_notify_IRQ_uv(int irq, void *dev_id)
 			}
 		}
 
-		gru_free_message(xpc_notify_mq_uv, msg);
+		gru_free_message(xpc_notify_mq_uv->gru_mq_desc, msg);
 	}
 
 	return IRQ_HANDLED;
@@ -1438,7 +1569,8 @@ xpc_send_payload_uv(struct xpc_channel *ch, u32 flags, void *payload,
 	msg->hdr.msg_slot_number = msg_slot->msg_slot_number;
 	memcpy(&msg->payload, payload, payload_size);
 
-	ret = xpc_send_gru_msg(ch->sn.uv.remote_notify_mq_gpa, msg, msg_size);
+	ret = xpc_send_gru_msg(ch->sn.uv.cached_notify_gru_mq_desc, msg,
+			       msg_size);
 	if (ret == xpSuccess)
 		goto out_1;
 
@@ -1529,7 +1661,7 @@ xpc_received_payload_uv(struct xpc_channel *ch, void *payload)
 	msg->hdr.partid = xp_partition_id;
 	msg->hdr.size = 0;	/* size of zero indicates this is an ACK */
 
-	ret = xpc_send_gru_msg(ch->sn.uv.remote_notify_mq_gpa, msg,
+	ret = xpc_send_gru_msg(ch->sn.uv.cached_notify_gru_mq_desc, msg,
 			       sizeof(struct xpc_notify_mq_msghdr_uv));
 	if (ret != xpSuccess)
 		XPC_DEACTIVATE_PARTITION(&xpc_partitions[ch->partid], ret);
@@ -1541,6 +1673,7 @@ int
 xpc_init_uv(void)
 {
 	xpc_setup_partitions_sn = xpc_setup_partitions_sn_uv;
+	xpc_teardown_partitions_sn = xpc_teardown_partitions_sn_uv;
 	xpc_process_activate_IRQ_rcvd = xpc_process_activate_IRQ_rcvd_uv;
 	xpc_get_partition_rsvd_page_pa = xpc_get_partition_rsvd_page_pa_uv;
 	xpc_setup_rsvd_page_sn = xpc_setup_rsvd_page_sn_uv;
diff --git a/drivers/mmc/card/block.c b/drivers/mmc/card/block.c
index 513eb09a638f..fe8041e619ea 100644
--- a/drivers/mmc/card/block.c
+++ b/drivers/mmc/card/block.c
@@ -41,6 +41,8 @@
 
 #include "queue.h"
 
+MODULE_ALIAS("mmc:block");
+
 /*
  * max 8 partitions per card
  */
diff --git a/drivers/mmc/core/bus.c b/drivers/mmc/core/bus.c
index f210a8ee6861..bdb165f93046 100644
--- a/drivers/mmc/core/bus.c
+++ b/drivers/mmc/core/bus.c
@@ -84,6 +84,14 @@ mmc_bus_uevent(struct device *dev, struct kobj_uevent_env *env)
 	}
 
 	retval = add_uevent_var(env, "MMC_NAME=%s", mmc_card_name(card));
+	if (retval)
+		return retval;
+
+	/*
+	 * Request the mmc_block device.  Note: that this is a direct request
+	 * for the module it carries no information as to what is inserted.
+	 */
+	retval = add_uevent_var(env, "MODALIAS=mmc:block");
 
 	return retval;
 }
diff --git a/drivers/mmc/core/core.c b/drivers/mmc/core/core.c
index df6ce4a06cf3..fa073ab3fa34 100644
--- a/drivers/mmc/core/core.c
+++ b/drivers/mmc/core/core.c
@@ -21,6 +21,7 @@
 #include <linux/leds.h>
 #include <linux/scatterlist.h>
 #include <linux/log2.h>
+#include <linux/regulator/consumer.h>
 
 #include <linux/mmc/card.h>
 #include <linux/mmc/host.h>
@@ -297,6 +298,21 @@ void mmc_set_data_timeout(struct mmc_data *data, const struct mmc_card *card)
 			data->timeout_clks = 0;
 		}
 	}
+	/*
+	 * Some cards need very high timeouts if driven in SPI mode.
+	 * The worst observed timeout was 900ms after writing a
+	 * continuous stream of data until the internal logic
+	 * overflowed.
+	 */
+	if (mmc_host_is_spi(card->host)) {
+		if (data->flags & MMC_DATA_WRITE) {
+			if (data->timeout_ns < 1000000000)
+				data->timeout_ns = 1000000000;	/* 1s */
+		} else {
+			if (data->timeout_ns < 100000000)
+				data->timeout_ns =  100000000;	/* 100ms */
+		}
+	}
 }
 EXPORT_SYMBOL(mmc_set_data_timeout);
 
@@ -523,6 +539,105 @@ u32 mmc_vddrange_to_ocrmask(int vdd_min, int vdd_max)
 }
 EXPORT_SYMBOL(mmc_vddrange_to_ocrmask);
 
+#ifdef CONFIG_REGULATOR
+
+/**
+ * mmc_regulator_get_ocrmask - return mask of supported voltages
+ * @supply: regulator to use
+ *
+ * This returns either a negative errno, or a mask of voltages that
+ * can be provided to MMC/SD/SDIO devices using the specified voltage
+ * regulator.  This would normally be called before registering the
+ * MMC host adapter.
+ */
+int mmc_regulator_get_ocrmask(struct regulator *supply)
+{
+	int			result = 0;
+	int			count;
+	int			i;
+
+	count = regulator_count_voltages(supply);
+	if (count < 0)
+		return count;
+
+	for (i = 0; i < count; i++) {
+		int		vdd_uV;
+		int		vdd_mV;
+
+		vdd_uV = regulator_list_voltage(supply, i);
+		if (vdd_uV <= 0)
+			continue;
+
+		vdd_mV = vdd_uV / 1000;
+		result |= mmc_vddrange_to_ocrmask(vdd_mV, vdd_mV);
+	}
+
+	return result;
+}
+EXPORT_SYMBOL(mmc_regulator_get_ocrmask);
+
+/**
+ * mmc_regulator_set_ocr - set regulator to match host->ios voltage
+ * @vdd_bit: zero for power off, else a bit number (host->ios.vdd)
+ * @supply: regulator to use
+ *
+ * Returns zero on success, else negative errno.
+ *
+ * MMC host drivers may use this to enable or disable a regulator using
+ * a particular supply voltage.  This would normally be called from the
+ * set_ios() method.
+ */
+int mmc_regulator_set_ocr(struct regulator *supply, unsigned short vdd_bit)
+{
+	int			result = 0;
+	int			min_uV, max_uV;
+	int			enabled;
+
+	enabled = regulator_is_enabled(supply);
+	if (enabled < 0)
+		return enabled;
+
+	if (vdd_bit) {
+		int		tmp;
+		int		voltage;
+
+		/* REVISIT mmc_vddrange_to_ocrmask() may have set some
+		 * bits this regulator doesn't quite support ... don't
+		 * be too picky, most cards and regulators are OK with
+		 * a 0.1V range goof (it's a small error percentage).
+		 */
+		tmp = vdd_bit - ilog2(MMC_VDD_165_195);
+		if (tmp == 0) {
+			min_uV = 1650 * 1000;
+			max_uV = 1950 * 1000;
+		} else {
+			min_uV = 1900 * 1000 + tmp * 100 * 1000;
+			max_uV = min_uV + 100 * 1000;
+		}
+
+		/* avoid needless changes to this voltage; the regulator
+		 * might not allow this operation
+		 */
+		voltage = regulator_get_voltage(supply);
+		if (voltage < 0)
+			result = voltage;
+		else if (voltage < min_uV || voltage > max_uV)
+			result = regulator_set_voltage(supply, min_uV, max_uV);
+		else
+			result = 0;
+
+		if (result == 0 && !enabled)
+			result = regulator_enable(supply);
+	} else if (enabled) {
+		result = regulator_disable(supply);
+	}
+
+	return result;
+}
+EXPORT_SYMBOL(mmc_regulator_set_ocr);
+
+#endif
+
 /*
  * Mask off any voltages we don't support and select
  * the lowest voltage
@@ -815,6 +930,7 @@ void mmc_stop_host(struct mmc_host *host)
 	spin_unlock_irqrestore(&host->lock, flags);
 #endif
 
+	cancel_delayed_work(&host->detect);
 	mmc_flush_scheduled_work();
 
 	mmc_bus_get(host);
@@ -842,6 +958,7 @@ void mmc_stop_host(struct mmc_host *host)
  */
 int mmc_suspend_host(struct mmc_host *host, pm_message_t state)
 {
+	cancel_delayed_work(&host->detect);
 	mmc_flush_scheduled_work();
 
 	mmc_bus_get(host);
@@ -875,6 +992,7 @@ int mmc_resume_host(struct mmc_host *host)
 	mmc_bus_get(host);
 	if (host->bus_ops && !host->bus_dead) {
 		mmc_power_up(host);
+		mmc_select_voltage(host, host->ocr);
 		BUG_ON(!host->bus_ops->resume);
 		host->bus_ops->resume(host);
 	}
diff --git a/drivers/mmc/core/debugfs.c b/drivers/mmc/core/debugfs.c
index 1237bb4c722b..610dbd1fcc82 100644
--- a/drivers/mmc/core/debugfs.c
+++ b/drivers/mmc/core/debugfs.c
@@ -184,6 +184,68 @@ static int mmc_dbg_card_status_get(void *data, u64 *val)
 DEFINE_SIMPLE_ATTRIBUTE(mmc_dbg_card_status_fops, mmc_dbg_card_status_get,
 		NULL, "%08llx\n");
 
+#define EXT_CSD_STR_LEN 1025
+
+static int mmc_ext_csd_open(struct inode *inode, struct file *filp)
+{
+	struct mmc_card *card = inode->i_private;
+	char *buf;
+	ssize_t n = 0;
+	u8 *ext_csd;
+	int err, i;
+
+	buf = kmalloc(EXT_CSD_STR_LEN + 1, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ext_csd = kmalloc(512, GFP_KERNEL);
+	if (!ext_csd) {
+		err = -ENOMEM;
+		goto out_free;
+	}
+
+	mmc_claim_host(card->host);
+	err = mmc_send_ext_csd(card, ext_csd);
+	mmc_release_host(card->host);
+	if (err)
+		goto out_free;
+
+	for (i = 511; i >= 0; i--)
+		n += sprintf(buf + n, "%02x", ext_csd[i]);
+	n += sprintf(buf + n, "\n");
+	BUG_ON(n != EXT_CSD_STR_LEN);
+
+	filp->private_data = buf;
+	kfree(ext_csd);
+	return 0;
+
+out_free:
+	kfree(buf);
+	kfree(ext_csd);
+	return err;
+}
+
+static ssize_t mmc_ext_csd_read(struct file *filp, char __user *ubuf,
+				size_t cnt, loff_t *ppos)
+{
+	char *buf = filp->private_data;
+
+	return simple_read_from_buffer(ubuf, cnt, ppos,
+				       buf, EXT_CSD_STR_LEN);
+}
+
+static int mmc_ext_csd_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static struct file_operations mmc_dbg_ext_csd_fops = {
+	.open		= mmc_ext_csd_open,
+	.read		= mmc_ext_csd_read,
+	.release	= mmc_ext_csd_release,
+};
+
 void mmc_add_card_debugfs(struct mmc_card *card)
 {
 	struct mmc_host	*host = card->host;
@@ -211,6 +273,11 @@ void mmc_add_card_debugfs(struct mmc_card *card)
 					&mmc_dbg_card_status_fops))
 			goto err;
 
+	if (mmc_card_mmc(card))
+		if (!debugfs_create_file("ext_csd", S_IRUSR, root, card,
+					&mmc_dbg_ext_csd_fops))
+			goto err;
+
 	return;
 
 err:
diff --git a/drivers/mmc/core/sdio_cis.c b/drivers/mmc/core/sdio_cis.c
index 956bd7677502..963f2937c5e3 100644
--- a/drivers/mmc/core/sdio_cis.c
+++ b/drivers/mmc/core/sdio_cis.c
@@ -223,10 +223,18 @@ static int sdio_read_cis(struct mmc_card *card, struct sdio_func *func)
 		if (tpl_code == 0xff)
 			break;
 
+		/* null entries have no link field or data */
+		if (tpl_code == 0x00)
+			continue;
+
 		ret = mmc_io_rw_direct(card, 0, 0, ptr++, 0, &tpl_link);
 		if (ret)
 			break;
 
+		/* a size of 0xff also means we're done */
+		if (tpl_link == 0xff)
+			break;
+
 		this = kmalloc(sizeof(*this) + tpl_link, GFP_KERNEL);
 		if (!this)
 			return -ENOMEM;
diff --git a/drivers/mmc/core/sdio_ops.c b/drivers/mmc/core/sdio_ops.c
index c8fa095a4488..4eb7825fd1a7 100644
--- a/drivers/mmc/core/sdio_ops.c
+++ b/drivers/mmc/core/sdio_ops.c
@@ -76,6 +76,10 @@ int mmc_io_rw_direct(struct mmc_card *card, int write, unsigned fn,
 	BUG_ON(!card);
 	BUG_ON(fn > 7);
 
+	/* sanity check */
+	if (addr & ~0x1FFFF)
+		return -EINVAL;
+
 	memset(&cmd, 0, sizeof(struct mmc_command));
 
 	cmd.opcode = SD_IO_RW_DIRECT;
@@ -125,6 +129,10 @@ int mmc_io_rw_extended(struct mmc_card *card, int write, unsigned fn,
 	WARN_ON(blocks == 0);
 	WARN_ON(blksz == 0);
 
+	/* sanity check */
+	if (addr & ~0x1FFFF)
+		return -EINVAL;
+
 	memset(&mrq, 0, sizeof(struct mmc_request));
 	memset(&cmd, 0, sizeof(struct mmc_command));
 	memset(&data, 0, sizeof(struct mmc_data));
diff --git a/drivers/mmc/host/Kconfig b/drivers/mmc/host/Kconfig
index 99d4b28d52ed..b4cf691f3f64 100644
--- a/drivers/mmc/host/Kconfig
+++ b/drivers/mmc/host/Kconfig
@@ -37,6 +37,13 @@ config MMC_SDHCI
 
 	  If unsure, say N.
 
+config MMC_SDHCI_IO_ACCESSORS
+	bool
+	depends on MMC_SDHCI
+	help
+	  This is silent Kconfig symbol that is selected by the drivers that
+	  need to overwrite SDHCI IO memory accessors.
+
 config MMC_SDHCI_PCI
 	tristate "SDHCI support on PCI bus"
 	depends on MMC_SDHCI && PCI
@@ -65,6 +72,17 @@ config MMC_RICOH_MMC
 
 	  If unsure, say Y.
 
+config MMC_SDHCI_OF
+	tristate "SDHCI support on OpenFirmware platforms"
+	depends on MMC_SDHCI && PPC_OF
+	select MMC_SDHCI_IO_ACCESSORS
+	help
+	  This selects the OF support for Secure Digital Host Controller
+	  Interfaces. So far, only the Freescale eSDHC controller is known
+	  to exist on OF platforms.
+
+	  If unsure, say N.
+
 config MMC_OMAP
 	tristate "TI OMAP Multimedia Card Interface support"
 	depends on ARCH_OMAP
@@ -171,13 +189,24 @@ config MMC_TIFM_SD
           To compile this driver as a module, choose M here: the
 	  module will be called tifm_sd.
 
+config MMC_MVSDIO
+	tristate "Marvell MMC/SD/SDIO host driver"
+	depends on PLAT_ORION
+	---help---
+	  This selects the Marvell SDIO host driver.
+	  SDIO may currently be found on the Kirkwood 88F6281 and 88F6192
+	  SoC controllers.
+
+	  To compile this driver as a module, choose M here: the
+	  module will be called mvsdio.
+
 config MMC_SPI
 	tristate "MMC/SD/SDIO over SPI"
 	depends on SPI_MASTER && !HIGHMEM && HAS_DMA
 	select CRC7
 	select CRC_ITU_T
 	help
-	  Some systems accss MMC/SD/SDIO cards using a SPI controller
+	  Some systems access MMC/SD/SDIO cards using a SPI controller
 	  instead of using a "native" MMC/SD/SDIO controller.  This has a
 	  disadvantage of being relatively high overhead, but a compensating
 	  advantage of working on many systems without dedicated MMC/SD/SDIO
diff --git a/drivers/mmc/host/Makefile b/drivers/mmc/host/Makefile
index dedec55861d9..970a997620e1 100644
--- a/drivers/mmc/host/Makefile
+++ b/drivers/mmc/host/Makefile
@@ -13,6 +13,7 @@ obj-$(CONFIG_MMC_MXC)		+= mxcmmc.o
 obj-$(CONFIG_MMC_SDHCI)		+= sdhci.o
 obj-$(CONFIG_MMC_SDHCI_PCI)	+= sdhci-pci.o
 obj-$(CONFIG_MMC_RICOH_MMC)	+= ricoh_mmc.o
+obj-$(CONFIG_MMC_SDHCI_OF)	+= sdhci-of.o
 obj-$(CONFIG_MMC_WBSD)		+= wbsd.o
 obj-$(CONFIG_MMC_AU1X)		+= au1xmmc.o
 obj-$(CONFIG_MMC_OMAP)		+= omap.o
@@ -20,6 +21,7 @@ obj-$(CONFIG_MMC_OMAP_HS)	+= omap_hsmmc.o
 obj-$(CONFIG_MMC_AT91)		+= at91_mci.o
 obj-$(CONFIG_MMC_ATMELMCI)	+= atmel-mci.o
 obj-$(CONFIG_MMC_TIFM_SD)	+= tifm_sd.o
+obj-$(CONFIG_MMC_MVSDIO)	+= mvsdio.o
 obj-$(CONFIG_MMC_SPI)		+= mmc_spi.o
 ifeq ($(CONFIG_OF),y)
 obj-$(CONFIG_MMC_SPI)		+= of_mmc_spi.o
diff --git a/drivers/mmc/host/atmel-mci.c b/drivers/mmc/host/atmel-mci.c
index e94e92001e7c..cf6a100bb38f 100644
--- a/drivers/mmc/host/atmel-mci.c
+++ b/drivers/mmc/host/atmel-mci.c
@@ -812,7 +812,7 @@ static void atmci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 		slot->sdc_reg |= MCI_SDCBUS_1BIT;
 		break;
 	case MMC_BUS_WIDTH_4:
-		slot->sdc_reg = MCI_SDCBUS_4BIT;
+		slot->sdc_reg |= MCI_SDCBUS_4BIT;
 		break;
 	}
 
diff --git a/drivers/mmc/host/mmc_spi.c b/drivers/mmc/host/mmc_spi.c
index 87e211df68ac..72f8bde4877a 100644
--- a/drivers/mmc/host/mmc_spi.c
+++ b/drivers/mmc/host/mmc_spi.c
@@ -279,8 +279,11 @@ static int mmc_spi_response_get(struct mmc_spi_host *host,
 		 * so it can always DMA directly into the target buffer.
 		 * It'd probably be better to memcpy() the first chunk and
 		 * avoid extra i/o calls...
+		 *
+		 * Note we check for more than 8 bytes, because in practice,
+		 * some SD cards are slow...
 		 */
-		for (i = 2; i < 9; i++) {
+		for (i = 2; i < 16; i++) {
 			value = mmc_spi_readbytes(host, 1);
 			if (value < 0)
 				goto done;
@@ -609,6 +612,7 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	struct spi_device	*spi = host->spi;
 	int			status, i;
 	struct scratch		*scratch = host->data;
+	u32			pattern;
 
 	if (host->mmc->use_spi_crc)
 		scratch->crc_val = cpu_to_be16(
@@ -636,8 +640,27 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	 * doesn't necessarily tell whether the write operation succeeded;
 	 * it just says if the transmission was ok and whether *earlier*
 	 * writes succeeded; see the standard.
+	 *
+	 * In practice, there are (even modern SDHC-)cards which are late
+	 * in sending the response, and miss the time frame by a few bits,
+	 * so we have to cope with this situation and check the response
+	 * bit-by-bit. Arggh!!!
 	 */
-	switch (SPI_MMC_RESPONSE_CODE(scratch->status[0])) {
+	pattern  = scratch->status[0] << 24;
+	pattern |= scratch->status[1] << 16;
+	pattern |= scratch->status[2] << 8;
+	pattern |= scratch->status[3];
+
+	/* First 3 bit of pattern are undefined */
+	pattern |= 0xE0000000;
+
+	/* left-adjust to leading 0 bit */
+	while (pattern & 0x80000000)
+		pattern <<= 1;
+	/* right-adjust for pattern matching. Code is in bit 4..0 now. */
+	pattern >>= 27;
+
+	switch (pattern) {
 	case SPI_RESPONSE_ACCEPTED:
 		status = 0;
 		break;
@@ -668,8 +691,9 @@ mmc_spi_writeblock(struct mmc_spi_host *host, struct spi_transfer *t,
 	/* Return when not busy.  If we didn't collect that status yet,
 	 * we'll need some more I/O.
 	 */
-	for (i = 1; i < sizeof(scratch->status); i++) {
-		if (scratch->status[i] != 0)
+	for (i = 4; i < sizeof(scratch->status); i++) {
+		/* card is non-busy if the most recent bit is 1 */
+		if (scratch->status[i] & 0x01)
 			return 0;
 	}
 	return mmc_spi_wait_unbusy(host, timeout);
@@ -1204,10 +1228,12 @@ static int mmc_spi_probe(struct spi_device *spi)
 
 	/* MMC and SD specs only seem to care that sampling is on the
 	 * rising edge ... meaning SPI modes 0 or 3.  So either SPI mode
-	 * should be legit.  We'll use mode 0 since it seems to be a
-	 * bit less troublesome on some hardware ... unclear why.
+	 * should be legit.  We'll use mode 0 since the steady state is 0,
+	 * which is appropriate for hotplugging, unless the platform data
+	 * specify mode 3 (if hardware is not compatible to mode 0).
 	 */
-	spi->mode = SPI_MODE_0;
+	if (spi->mode != SPI_MODE_3)
+		spi->mode = SPI_MODE_0;
 	spi->bits_per_word = 8;
 
 	status = spi_setup(spi);
diff --git a/drivers/mmc/host/mvsdio.c b/drivers/mmc/host/mvsdio.c
new file mode 100644
index 000000000000..b5c375d94ab3
--- /dev/null
+++ b/drivers/mmc/host/mvsdio.c
@@ -0,0 +1,885 @@
+/*
+ * Marvell MMC/SD/SDIO driver
+ *
+ * Authors: Maen Suleiman, Nicolas Pitre
+ * Copyright (C) 2008-2009 Marvell Ltd.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/platform_device.h>
+#include <linux/mbus.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/dma-mapping.h>
+#include <linux/scatterlist.h>
+#include <linux/irq.h>
+#include <linux/gpio.h>
+#include <linux/mmc/host.h>
+
+#include <asm/sizes.h>
+#include <asm/unaligned.h>
+#include <plat/mvsdio.h>
+
+#include "mvsdio.h"
+
+#define DRIVER_NAME	"mvsdio"
+
+static int maxfreq = MVSD_CLOCKRATE_MAX;
+static int nodma;
+
+struct mvsd_host {
+	void __iomem *base;
+	struct mmc_request *mrq;
+	spinlock_t lock;
+	unsigned int xfer_mode;
+	unsigned int intr_en;
+	unsigned int ctrl;
+	unsigned int pio_size;
+	void *pio_ptr;
+	unsigned int sg_frags;
+	unsigned int ns_per_clk;
+	unsigned int clock;
+	unsigned int base_clock;
+	struct timer_list timer;
+	struct mmc_host *mmc;
+	struct device *dev;
+	struct resource *res;
+	int irq;
+	int gpio_card_detect;
+	int gpio_write_protect;
+};
+
+#define mvsd_write(offs, val)	writel(val, iobase + (offs))
+#define mvsd_read(offs)		readl(iobase + (offs))
+
+static int mvsd_setup_data(struct mvsd_host *host, struct mmc_data *data)
+{
+	void __iomem *iobase = host->base;
+	unsigned int tmout;
+	int tmout_index;
+
+	/* If timeout=0 then maximum timeout index is used. */
+	tmout = DIV_ROUND_UP(data->timeout_ns, host->ns_per_clk);
+	tmout += data->timeout_clks;
+	tmout_index = fls(tmout - 1) - 12;
+	if (tmout_index < 0)
+		tmout_index = 0;
+	if (tmout_index > MVSD_HOST_CTRL_TMOUT_MAX)
+		tmout_index = MVSD_HOST_CTRL_TMOUT_MAX;
+
+	dev_dbg(host->dev, "data %s at 0x%08x: blocks=%d blksz=%d tmout=%u (%d)\n",
+		(data->flags & MMC_DATA_READ) ? "read" : "write",
+		(u32)sg_virt(data->sg), data->blocks, data->blksz,
+		tmout, tmout_index);
+
+	host->ctrl &= ~MVSD_HOST_CTRL_TMOUT_MASK;
+	host->ctrl |= MVSD_HOST_CTRL_TMOUT(tmout_index);
+	mvsd_write(MVSD_HOST_CTRL, host->ctrl);
+	mvsd_write(MVSD_BLK_COUNT, data->blocks);
+	mvsd_write(MVSD_BLK_SIZE, data->blksz);
+
+	if (nodma || (data->blksz | data->sg->offset) & 3) {
+		/*
+		 * We cannot do DMA on a buffer which offset or size
+		 * is not aligned on a 4-byte boundary.
+		 */
+		host->pio_size = data->blocks * data->blksz;
+		host->pio_ptr = sg_virt(data->sg);
+		if (!nodma)
+			printk(KERN_DEBUG "%s: fallback to PIO for data "
+					  "at 0x%p size %d\n",
+					  mmc_hostname(host->mmc),
+					  host->pio_ptr, host->pio_size);
+		return 1;
+	} else {
+		dma_addr_t phys_addr;
+		int dma_dir = (data->flags & MMC_DATA_READ) ?
+			DMA_FROM_DEVICE : DMA_TO_DEVICE;
+		host->sg_frags = dma_map_sg(mmc_dev(host->mmc), data->sg,
+					    data->sg_len, dma_dir);
+		phys_addr = sg_dma_address(data->sg);
+		mvsd_write(MVSD_SYS_ADDR_LOW, (u32)phys_addr & 0xffff);
+		mvsd_write(MVSD_SYS_ADDR_HI,  (u32)phys_addr >> 16);
+		return 0;
+	}
+}
+
+static void mvsd_request(struct mmc_host *mmc, struct mmc_request *mrq)
+{
+	struct mvsd_host *host = mmc_priv(mmc);
+	void __iomem *iobase = host->base;
+	struct mmc_command *cmd = mrq->cmd;
+	u32 cmdreg = 0, xfer = 0, intr = 0;
+	unsigned long flags;
+
+	BUG_ON(host->mrq != NULL);
+	host->mrq = mrq;
+
+	dev_dbg(host->dev, "cmd %d (hw state 0x%04x)\n",
+		cmd->opcode, mvsd_read(MVSD_HW_STATE));
+
+	cmdreg = MVSD_CMD_INDEX(cmd->opcode);
+
+	if (cmd->flags & MMC_RSP_BUSY)
+		cmdreg |= MVSD_CMD_RSP_48BUSY;
+	else if (cmd->flags & MMC_RSP_136)
+		cmdreg |= MVSD_CMD_RSP_136;
+	else if (cmd->flags & MMC_RSP_PRESENT)
+		cmdreg |= MVSD_CMD_RSP_48;
+	else
+		cmdreg |= MVSD_CMD_RSP_NONE;
+
+	if (cmd->flags & MMC_RSP_CRC)
+		cmdreg |= MVSD_CMD_CHECK_CMDCRC;
+
+	if (cmd->flags & MMC_RSP_OPCODE)
+		cmdreg |= MVSD_CMD_INDX_CHECK;
+
+	if (cmd->flags & MMC_RSP_PRESENT) {
+		cmdreg |= MVSD_UNEXPECTED_RESP;
+		intr |= MVSD_NOR_UNEXP_RSP;
+	}
+
+	if (mrq->data) {
+		struct mmc_data *data = mrq->data;
+		int pio;
+
+		cmdreg |= MVSD_CMD_DATA_PRESENT | MVSD_CMD_CHECK_DATACRC16;
+		xfer |= MVSD_XFER_MODE_HW_WR_DATA_EN;
+		if (data->flags & MMC_DATA_READ)
+			xfer |= MVSD_XFER_MODE_TO_HOST;
+
+		pio = mvsd_setup_data(host, data);
+		if (pio) {
+			xfer |= MVSD_XFER_MODE_PIO;
+			/* PIO section of mvsd_irq has comments on those bits */
+			if (data->flags & MMC_DATA_WRITE)
+				intr |= MVSD_NOR_TX_AVAIL;
+			else if (host->pio_size > 32)
+				intr |= MVSD_NOR_RX_FIFO_8W;
+			else
+				intr |= MVSD_NOR_RX_READY;
+		}
+
+		if (data->stop) {
+			struct mmc_command *stop = data->stop;
+			u32 cmd12reg = 0;
+
+			mvsd_write(MVSD_AUTOCMD12_ARG_LOW, stop->arg & 0xffff);
+			mvsd_write(MVSD_AUTOCMD12_ARG_HI,  stop->arg >> 16);
+
+			if (stop->flags & MMC_RSP_BUSY)
+				cmd12reg |= MVSD_AUTOCMD12_BUSY;
+			if (stop->flags & MMC_RSP_OPCODE)
+				cmd12reg |= MVSD_AUTOCMD12_INDX_CHECK;
+			cmd12reg |= MVSD_AUTOCMD12_INDEX(stop->opcode);
+			mvsd_write(MVSD_AUTOCMD12_CMD, cmd12reg);
+
+			xfer |= MVSD_XFER_MODE_AUTO_CMD12;
+			intr |= MVSD_NOR_AUTOCMD12_DONE;
+		} else {
+			intr |= MVSD_NOR_XFER_DONE;
+		}
+	} else {
+		intr |= MVSD_NOR_CMD_DONE;
+	}
+
+	mvsd_write(MVSD_ARG_LOW, cmd->arg & 0xffff);
+	mvsd_write(MVSD_ARG_HI,  cmd->arg >> 16);
+
+	spin_lock_irqsave(&host->lock, flags);
+
+	host->xfer_mode &= MVSD_XFER_MODE_INT_CHK_EN;
+	host->xfer_mode |= xfer;
+	mvsd_write(MVSD_XFER_MODE, host->xfer_mode);
+
+	mvsd_write(MVSD_NOR_INTR_STATUS, ~MVSD_NOR_CARD_INT);
+	mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff);
+	mvsd_write(MVSD_CMD, cmdreg);
+
+	host->intr_en &= MVSD_NOR_CARD_INT;
+	host->intr_en |= intr | MVSD_NOR_ERROR;
+	mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
+	mvsd_write(MVSD_ERR_INTR_EN, 0xffff);
+
+	mod_timer(&host->timer, jiffies + 5 * HZ);
+
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
+static u32 mvsd_finish_cmd(struct mvsd_host *host, struct mmc_command *cmd,
+			   u32 err_status)
+{
+	void __iomem *iobase = host->base;
+
+	if (cmd->flags & MMC_RSP_136) {
+		unsigned int response[8], i;
+		for (i = 0; i < 8; i++)
+			response[i] = mvsd_read(MVSD_RSP(i));
+		cmd->resp[0] =		((response[0] & 0x03ff) << 22) |
+					((response[1] & 0xffff) << 6) |
+					((response[2] & 0xfc00) >> 10);
+		cmd->resp[1] =		((response[2] & 0x03ff) << 22) |
+					((response[3] & 0xffff) << 6) |
+					((response[4] & 0xfc00) >> 10);
+		cmd->resp[2] =		((response[4] & 0x03ff) << 22) |
+					((response[5] & 0xffff) << 6) |
+					((response[6] & 0xfc00) >> 10);
+		cmd->resp[3] =		((response[6] & 0x03ff) << 22) |
+					((response[7] & 0x3fff) << 8);
+	} else if (cmd->flags & MMC_RSP_PRESENT) {
+		unsigned int response[3], i;
+		for (i = 0; i < 3; i++)
+			response[i] = mvsd_read(MVSD_RSP(i));
+		cmd->resp[0] =		((response[2] & 0x003f) << (8 - 8)) |
+					((response[1] & 0xffff) << (14 - 8)) |
+					((response[0] & 0x03ff) << (30 - 8));
+		cmd->resp[1] =		((response[0] & 0xfc00) >> 10);
+		cmd->resp[2] = 0;
+		cmd->resp[3] = 0;
+	}
+
+	if (err_status & MVSD_ERR_CMD_TIMEOUT) {
+		cmd->error = -ETIMEDOUT;
+	} else if (err_status & (MVSD_ERR_CMD_CRC | MVSD_ERR_CMD_ENDBIT |
+				 MVSD_ERR_CMD_INDEX | MVSD_ERR_CMD_STARTBIT)) {
+		cmd->error = -EILSEQ;
+	}
+	err_status &= ~(MVSD_ERR_CMD_TIMEOUT | MVSD_ERR_CMD_CRC |
+			MVSD_ERR_CMD_ENDBIT | MVSD_ERR_CMD_INDEX |
+			MVSD_ERR_CMD_STARTBIT);
+
+	return err_status;
+}
+
+static u32 mvsd_finish_data(struct mvsd_host *host, struct mmc_data *data,
+			    u32 err_status)
+{
+	void __iomem *iobase = host->base;
+
+	if (host->pio_ptr) {
+		host->pio_ptr = NULL;
+		host->pio_size = 0;
+	} else {
+		dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->sg_frags,
+			     (data->flags & MMC_DATA_READ) ?
+				DMA_FROM_DEVICE : DMA_TO_DEVICE);
+	}
+
+	if (err_status & MVSD_ERR_DATA_TIMEOUT)
+		data->error = -ETIMEDOUT;
+	else if (err_status & (MVSD_ERR_DATA_CRC | MVSD_ERR_DATA_ENDBIT))
+		data->error = -EILSEQ;
+	else if (err_status & MVSD_ERR_XFER_SIZE)
+		data->error = -EBADE;
+	err_status &= ~(MVSD_ERR_DATA_TIMEOUT | MVSD_ERR_DATA_CRC |
+			MVSD_ERR_DATA_ENDBIT | MVSD_ERR_XFER_SIZE);
+
+	dev_dbg(host->dev, "data done: blocks_left=%d, bytes_left=%d\n",
+		mvsd_read(MVSD_CURR_BLK_LEFT), mvsd_read(MVSD_CURR_BYTE_LEFT));
+	data->bytes_xfered =
+		(data->blocks - mvsd_read(MVSD_CURR_BLK_LEFT)) * data->blksz;
+	/* We can't be sure about the last block when errors are detected */
+	if (data->bytes_xfered && data->error)
+		data->bytes_xfered -= data->blksz;
+
+	/* Handle Auto cmd 12 response */
+	if (data->stop) {
+		unsigned int response[3], i;
+		for (i = 0; i < 3; i++)
+			response[i] = mvsd_read(MVSD_AUTO_RSP(i));
+		data->stop->resp[0] =	((response[2] & 0x003f) << (8 - 8)) |
+					((response[1] & 0xffff) << (14 - 8)) |
+					((response[0] & 0x03ff) << (30 - 8));
+		data->stop->resp[1] =	((response[0] & 0xfc00) >> 10);
+		data->stop->resp[2] = 0;
+		data->stop->resp[3] = 0;
+
+		if (err_status & MVSD_ERR_AUTOCMD12) {
+			u32 err_cmd12 = mvsd_read(MVSD_AUTOCMD12_ERR_STATUS);
+			dev_dbg(host->dev, "c12err 0x%04x\n", err_cmd12);
+			if (err_cmd12 & MVSD_AUTOCMD12_ERR_NOTEXE)
+				data->stop->error = -ENOEXEC;
+			else if (err_cmd12 & MVSD_AUTOCMD12_ERR_TIMEOUT)
+				data->stop->error = -ETIMEDOUT;
+			else if (err_cmd12)
+				data->stop->error = -EILSEQ;
+			err_status &= ~MVSD_ERR_AUTOCMD12;
+		}
+	}
+
+	return err_status;
+}
+
+static irqreturn_t mvsd_irq(int irq, void *dev)
+{
+	struct mvsd_host *host = dev;
+	void __iomem *iobase = host->base;
+	u32 intr_status, intr_done_mask;
+	int irq_handled = 0;
+
+	intr_status = mvsd_read(MVSD_NOR_INTR_STATUS);
+	dev_dbg(host->dev, "intr 0x%04x intr_en 0x%04x hw_state 0x%04x\n",
+		intr_status, mvsd_read(MVSD_NOR_INTR_EN),
+		mvsd_read(MVSD_HW_STATE));
+
+	spin_lock(&host->lock);
+
+	/* PIO handling, if needed. Messy business... */
+	if (host->pio_size &&
+	    (intr_status & host->intr_en &
+	     (MVSD_NOR_RX_READY | MVSD_NOR_RX_FIFO_8W))) {
+		u16 *p = host->pio_ptr;
+		int s = host->pio_size;
+		while (s >= 32 && (intr_status & MVSD_NOR_RX_FIFO_8W)) {
+			readsw(iobase + MVSD_FIFO, p, 16);
+			p += 16;
+			s -= 32;
+			intr_status = mvsd_read(MVSD_NOR_INTR_STATUS);
+		}
+		/*
+		 * Normally we'd use < 32 here, but the RX_FIFO_8W bit
+		 * doesn't appear to assert when there is exactly 32 bytes
+		 * (8 words) left to fetch in a transfer.
+		 */
+		if (s <= 32) {
+			while (s >= 4 && (intr_status & MVSD_NOR_RX_READY)) {
+				put_unaligned(mvsd_read(MVSD_FIFO), p++);
+				put_unaligned(mvsd_read(MVSD_FIFO), p++);
+				s -= 4;
+				intr_status = mvsd_read(MVSD_NOR_INTR_STATUS);
+			}
+			if (s && s < 4 && (intr_status & MVSD_NOR_RX_READY)) {
+				u16 val[2] = {0, 0};
+				val[0] = mvsd_read(MVSD_FIFO);
+				val[1] = mvsd_read(MVSD_FIFO);
+				memcpy(p, &val, s);
+				s = 0;
+				intr_status = mvsd_read(MVSD_NOR_INTR_STATUS);
+			}
+			if (s == 0) {
+				host->intr_en &=
+				     ~(MVSD_NOR_RX_READY | MVSD_NOR_RX_FIFO_8W);
+				mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
+			} else if (host->intr_en & MVSD_NOR_RX_FIFO_8W) {
+				host->intr_en &= ~MVSD_NOR_RX_FIFO_8W;
+				host->intr_en |= MVSD_NOR_RX_READY;
+				mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
+			}
+		}
+		dev_dbg(host->dev, "pio %d intr 0x%04x hw_state 0x%04x\n",
+			s, intr_status, mvsd_read(MVSD_HW_STATE));
+		host->pio_ptr = p;
+		host->pio_size = s;
+		irq_handled = 1;
+	} else if (host->pio_size &&
+		   (intr_status & host->intr_en &
+		    (MVSD_NOR_TX_AVAIL | MVSD_NOR_TX_FIFO_8W))) {
+		u16 *p = host->pio_ptr;
+		int s = host->pio_size;
+		/*
+		 * The TX_FIFO_8W bit is unreliable. When set, bursting
+		 * 16 halfwords all at once in the FIFO drops data. Actually
+		 * TX_AVAIL does go off after only one word is pushed even if
+		 * TX_FIFO_8W remains set.
+		 */
+		while (s >= 4 && (intr_status & MVSD_NOR_TX_AVAIL)) {
+			mvsd_write(MVSD_FIFO, get_unaligned(p++));
+			mvsd_write(MVSD_FIFO, get_unaligned(p++));
+			s -= 4;
+			intr_status = mvsd_read(MVSD_NOR_INTR_STATUS);
+		}
+		if (s < 4) {
+			if (s && (intr_status & MVSD_NOR_TX_AVAIL)) {
+				u16 val[2] = {0, 0};
+				memcpy(&val, p, s);
+				mvsd_write(MVSD_FIFO, val[0]);
+				mvsd_write(MVSD_FIFO, val[1]);
+				s = 0;
+				intr_status = mvsd_read(MVSD_NOR_INTR_STATUS);
+			}
+			if (s == 0) {
+				host->intr_en &=
+				     ~(MVSD_NOR_TX_AVAIL | MVSD_NOR_TX_FIFO_8W);
+				mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
+			}
+		}
+		dev_dbg(host->dev, "pio %d intr 0x%04x hw_state 0x%04x\n",
+			s, intr_status, mvsd_read(MVSD_HW_STATE));
+		host->pio_ptr = p;
+		host->pio_size = s;
+		irq_handled = 1;
+	}
+
+	mvsd_write(MVSD_NOR_INTR_STATUS, intr_status);
+
+	intr_done_mask = MVSD_NOR_CARD_INT | MVSD_NOR_RX_READY |
+			 MVSD_NOR_RX_FIFO_8W | MVSD_NOR_TX_FIFO_8W;
+	if (intr_status & host->intr_en & ~intr_done_mask) {
+		struct mmc_request *mrq = host->mrq;
+		struct mmc_command *cmd = mrq->cmd;
+		u32 err_status = 0;
+
+		del_timer(&host->timer);
+		host->mrq = NULL;
+
+		host->intr_en &= MVSD_NOR_CARD_INT;
+		mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
+		mvsd_write(MVSD_ERR_INTR_EN, 0);
+
+		spin_unlock(&host->lock);
+
+		if (intr_status & MVSD_NOR_UNEXP_RSP) {
+			cmd->error = -EPROTO;
+		} else if (intr_status & MVSD_NOR_ERROR) {
+			err_status = mvsd_read(MVSD_ERR_INTR_STATUS);
+			dev_dbg(host->dev, "err 0x%04x\n", err_status);
+		}
+
+		err_status = mvsd_finish_cmd(host, cmd, err_status);
+		if (mrq->data)
+			err_status = mvsd_finish_data(host, mrq->data, err_status);
+		if (err_status) {
+			printk(KERN_ERR "%s: unhandled error status %#04x\n",
+					mmc_hostname(host->mmc), err_status);
+			cmd->error = -ENOMSG;
+		}
+
+		mmc_request_done(host->mmc, mrq);
+		irq_handled = 1;
+	} else
+		spin_unlock(&host->lock);
+
+	if (intr_status & MVSD_NOR_CARD_INT) {
+		mmc_signal_sdio_irq(host->mmc);
+		irq_handled = 1;
+	}
+
+	if (irq_handled)
+		return IRQ_HANDLED;
+
+	printk(KERN_ERR "%s: unhandled interrupt status=0x%04x en=0x%04x "
+			"pio=%d\n", mmc_hostname(host->mmc), intr_status,
+			host->intr_en, host->pio_size);
+	return IRQ_NONE;
+}
+
+static void mvsd_timeout_timer(unsigned long data)
+{
+	struct mvsd_host *host = (struct mvsd_host *)data;
+	void __iomem *iobase = host->base;
+	struct mmc_request *mrq;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+	mrq = host->mrq;
+	if (mrq) {
+		printk(KERN_ERR "%s: Timeout waiting for hardware interrupt.\n",
+				mmc_hostname(host->mmc));
+		printk(KERN_ERR "%s: hw_state=0x%04x, intr_status=0x%04x "
+				"intr_en=0x%04x\n", mmc_hostname(host->mmc),
+				mvsd_read(MVSD_HW_STATE),
+				mvsd_read(MVSD_NOR_INTR_STATUS),
+				mvsd_read(MVSD_NOR_INTR_EN));
+
+		host->mrq = NULL;
+
+		mvsd_write(MVSD_SW_RESET, MVSD_SW_RESET_NOW);
+
+		host->xfer_mode &= MVSD_XFER_MODE_INT_CHK_EN;
+		mvsd_write(MVSD_XFER_MODE, host->xfer_mode);
+
+		host->intr_en &= MVSD_NOR_CARD_INT;
+		mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
+		mvsd_write(MVSD_ERR_INTR_EN, 0);
+		mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff);
+
+		mrq->cmd->error = -ETIMEDOUT;
+		mvsd_finish_cmd(host, mrq->cmd, 0);
+		if (mrq->data) {
+			mrq->data->error = -ETIMEDOUT;
+			mvsd_finish_data(host, mrq->data, 0);
+		}
+	}
+	spin_unlock_irqrestore(&host->lock, flags);
+
+	if (mrq)
+		mmc_request_done(host->mmc, mrq);
+}
+
+static irqreturn_t mvsd_card_detect_irq(int irq, void *dev)
+{
+	struct mvsd_host *host = dev;
+	mmc_detect_change(host->mmc, msecs_to_jiffies(100));
+	return IRQ_HANDLED;
+}
+
+static void mvsd_enable_sdio_irq(struct mmc_host *mmc, int enable)
+{
+	struct mvsd_host *host = mmc_priv(mmc);
+	void __iomem *iobase = host->base;
+	unsigned long flags;
+
+	spin_lock_irqsave(&host->lock, flags);
+	if (enable) {
+		host->xfer_mode |= MVSD_XFER_MODE_INT_CHK_EN;
+		host->intr_en |= MVSD_NOR_CARD_INT;
+	} else {
+		host->xfer_mode &= ~MVSD_XFER_MODE_INT_CHK_EN;
+		host->intr_en &= ~MVSD_NOR_CARD_INT;
+	}
+	mvsd_write(MVSD_XFER_MODE, host->xfer_mode);
+	mvsd_write(MVSD_NOR_INTR_EN, host->intr_en);
+	spin_unlock_irqrestore(&host->lock, flags);
+}
+
+static int mvsd_get_ro(struct mmc_host *mmc)
+{
+	struct mvsd_host *host = mmc_priv(mmc);
+
+	if (host->gpio_write_protect)
+		return gpio_get_value(host->gpio_write_protect);
+
+	/*
+	 * Board doesn't support read only detection; let the mmc core
+	 * decide what to do.
+	 */
+	return -ENOSYS;
+}
+
+static void mvsd_power_up(struct mvsd_host *host)
+{
+	void __iomem *iobase = host->base;
+	dev_dbg(host->dev, "power up\n");
+	mvsd_write(MVSD_NOR_INTR_EN, 0);
+	mvsd_write(MVSD_ERR_INTR_EN, 0);
+	mvsd_write(MVSD_SW_RESET, MVSD_SW_RESET_NOW);
+	mvsd_write(MVSD_XFER_MODE, 0);
+	mvsd_write(MVSD_NOR_STATUS_EN, 0xffff);
+	mvsd_write(MVSD_ERR_STATUS_EN, 0xffff);
+	mvsd_write(MVSD_NOR_INTR_STATUS, 0xffff);
+	mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff);
+}
+
+static void mvsd_power_down(struct mvsd_host *host)
+{
+	void __iomem *iobase = host->base;
+	dev_dbg(host->dev, "power down\n");
+	mvsd_write(MVSD_NOR_INTR_EN, 0);
+	mvsd_write(MVSD_ERR_INTR_EN, 0);
+	mvsd_write(MVSD_SW_RESET, MVSD_SW_RESET_NOW);
+	mvsd_write(MVSD_XFER_MODE, MVSD_XFER_MODE_STOP_CLK);
+	mvsd_write(MVSD_NOR_STATUS_EN, 0);
+	mvsd_write(MVSD_ERR_STATUS_EN, 0);
+	mvsd_write(MVSD_NOR_INTR_STATUS, 0xffff);
+	mvsd_write(MVSD_ERR_INTR_STATUS, 0xffff);
+}
+
+static void mvsd_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
+{
+	struct mvsd_host *host = mmc_priv(mmc);
+	void __iomem *iobase = host->base;
+	u32 ctrl_reg = 0;
+
+	if (ios->power_mode == MMC_POWER_UP)
+		mvsd_power_up(host);
+
+	if (ios->clock == 0) {
+		mvsd_write(MVSD_XFER_MODE, MVSD_XFER_MODE_STOP_CLK);
+		mvsd_write(MVSD_CLK_DIV, MVSD_BASE_DIV_MAX);
+		host->clock = 0;
+		dev_dbg(host->dev, "clock off\n");
+	} else if (ios->clock != host->clock) {
+		u32 m = DIV_ROUND_UP(host->base_clock, ios->clock) - 1;
+		if (m > MVSD_BASE_DIV_MAX)
+			m = MVSD_BASE_DIV_MAX;
+		mvsd_write(MVSD_CLK_DIV, m);
+		host->clock = ios->clock;
+		host->ns_per_clk = 1000000000 / (host->base_clock / (m+1));
+		dev_dbg(host->dev, "clock=%d (%d), div=0x%04x\n",
+			ios->clock, host->base_clock / (m+1), m);
+	}
+
+	/* default transfer mode */
+	ctrl_reg |= MVSD_HOST_CTRL_BIG_ENDIAN;
+	ctrl_reg &= ~MVSD_HOST_CTRL_LSB_FIRST;
+
+	/* default to maximum timeout */
+	ctrl_reg |= MVSD_HOST_CTRL_TMOUT_MASK;
+	ctrl_reg |= MVSD_HOST_CTRL_TMOUT_EN;
+
+	if (ios->bus_mode == MMC_BUSMODE_PUSHPULL)
+		ctrl_reg |= MVSD_HOST_CTRL_PUSH_PULL_EN;
+
+	if (ios->bus_width == MMC_BUS_WIDTH_4)
+		ctrl_reg |= MVSD_HOST_CTRL_DATA_WIDTH_4_BITS;
+
+	if (ios->timing == MMC_TIMING_MMC_HS ||
+	    ios->timing == MMC_TIMING_SD_HS)
+		ctrl_reg |= MVSD_HOST_CTRL_HI_SPEED_EN;
+
+	host->ctrl = ctrl_reg;
+	mvsd_write(MVSD_HOST_CTRL, ctrl_reg);
+	dev_dbg(host->dev, "ctrl 0x%04x: %s %s %s\n", ctrl_reg,
+		(ctrl_reg & MVSD_HOST_CTRL_PUSH_PULL_EN) ?
+			"push-pull" : "open-drain",
+		(ctrl_reg & MVSD_HOST_CTRL_DATA_WIDTH_4_BITS) ?
+			"4bit-width" : "1bit-width",
+		(ctrl_reg & MVSD_HOST_CTRL_HI_SPEED_EN) ?
+			"high-speed" : "");
+
+	if (ios->power_mode == MMC_POWER_OFF)
+		mvsd_power_down(host);
+}
+
+static const struct mmc_host_ops mvsd_ops = {
+	.request		= mvsd_request,
+	.get_ro			= mvsd_get_ro,
+	.set_ios		= mvsd_set_ios,
+	.enable_sdio_irq	= mvsd_enable_sdio_irq,
+};
+
+static void __init mv_conf_mbus_windows(struct mvsd_host *host,
+					struct mbus_dram_target_info *dram)
+{
+	void __iomem *iobase = host->base;
+	int i;
+
+	for (i = 0; i < 4; i++) {
+		writel(0, iobase + MVSD_WINDOW_CTRL(i));
+		writel(0, iobase + MVSD_WINDOW_BASE(i));
+	}
+
+	for (i = 0; i < dram->num_cs; i++) {
+		struct mbus_dram_window *cs = dram->cs + i;
+		writel(((cs->size - 1) & 0xffff0000) |
+		       (cs->mbus_attr << 8) |
+		       (dram->mbus_dram_target_id << 4) | 1,
+		       iobase + MVSD_WINDOW_CTRL(i));
+		writel(cs->base, iobase + MVSD_WINDOW_BASE(i));
+	}
+}
+
+static int __init mvsd_probe(struct platform_device *pdev)
+{
+	struct mmc_host *mmc = NULL;
+	struct mvsd_host *host = NULL;
+	const struct mvsdio_platform_data *mvsd_data;
+	struct resource *r;
+	int ret, irq;
+
+	r = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	irq = platform_get_irq(pdev, 0);
+	mvsd_data = pdev->dev.platform_data;
+	if (!r || irq < 0 || !mvsd_data)
+		return -ENXIO;
+
+	r = request_mem_region(r->start, SZ_1K, DRIVER_NAME);
+	if (!r)
+		return -EBUSY;
+
+	mmc = mmc_alloc_host(sizeof(struct mvsd_host), &pdev->dev);
+	if (!mmc) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	host = mmc_priv(mmc);
+	host->mmc = mmc;
+	host->dev = &pdev->dev;
+	host->res = r;
+	host->base_clock = mvsd_data->clock / 2;
+
+	mmc->ops = &mvsd_ops;
+
+	mmc->ocr_avail = MMC_VDD_32_33 | MMC_VDD_33_34;
+	mmc->caps = MMC_CAP_4_BIT_DATA | MMC_CAP_SDIO_IRQ |
+		    MMC_CAP_SD_HIGHSPEED | MMC_CAP_MMC_HIGHSPEED;
+
+	mmc->f_min = DIV_ROUND_UP(host->base_clock, MVSD_BASE_DIV_MAX);
+	mmc->f_max = maxfreq;
+
+	mmc->max_blk_size = 2048;
+	mmc->max_blk_count = 65535;
+
+	mmc->max_hw_segs = 1;
+	mmc->max_phys_segs = 1;
+	mmc->max_seg_size = mmc->max_blk_size * mmc->max_blk_count;
+	mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count;
+
+	spin_lock_init(&host->lock);
+
+	host->base = ioremap(r->start, SZ_4K);
+	if (!host->base) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	/* (Re-)program MBUS remapping windows if we are asked to. */
+	if (mvsd_data->dram != NULL)
+		mv_conf_mbus_windows(host, mvsd_data->dram);
+
+	mvsd_power_down(host);
+
+	ret = request_irq(irq, mvsd_irq, 0, DRIVER_NAME, host);
+	if (ret) {
+		printk(KERN_ERR "%s: cannot assign irq %d\n", DRIVER_NAME, irq);
+		goto out;
+	} else
+		host->irq = irq;
+
+	if (mvsd_data->gpio_card_detect) {
+		ret = gpio_request(mvsd_data->gpio_card_detect,
+				   DRIVER_NAME " cd");
+		if (ret == 0) {
+			gpio_direction_input(mvsd_data->gpio_card_detect);
+			irq = gpio_to_irq(mvsd_data->gpio_card_detect);
+			ret = request_irq(irq, mvsd_card_detect_irq,
+					  IRQ_TYPE_EDGE_RISING | IRQ_TYPE_EDGE_FALLING,
+					  DRIVER_NAME " cd", host);
+			if (ret == 0)
+				host->gpio_card_detect =
+					mvsd_data->gpio_card_detect;
+			else
+				gpio_free(mvsd_data->gpio_card_detect);
+		}
+	}
+	if (!host->gpio_card_detect)
+		mmc->caps |= MMC_CAP_NEEDS_POLL;
+
+	if (mvsd_data->gpio_write_protect) {
+		ret = gpio_request(mvsd_data->gpio_write_protect,
+				   DRIVER_NAME " wp");
+		if (ret == 0) {
+			gpio_direction_input(mvsd_data->gpio_write_protect);
+			host->gpio_write_protect =
+				mvsd_data->gpio_write_protect;
+		}
+	}
+
+	setup_timer(&host->timer, mvsd_timeout_timer, (unsigned long)host);
+	platform_set_drvdata(pdev, mmc);
+	ret = mmc_add_host(mmc);
+	if (ret)
+		goto out;
+
+	printk(KERN_NOTICE "%s: %s driver initialized, ",
+			   mmc_hostname(mmc), DRIVER_NAME);
+	if (host->gpio_card_detect)
+		printk("using GPIO %d for card detection\n",
+		       host->gpio_card_detect);
+	else
+		printk("lacking card detect (fall back to polling)\n");
+	return 0;
+
+out:
+	if (host) {
+		if (host->irq)
+			free_irq(host->irq, host);
+		if (host->gpio_card_detect) {
+			free_irq(gpio_to_irq(host->gpio_card_detect), host);
+			gpio_free(host->gpio_card_detect);
+		}
+		if (host->gpio_write_protect)
+			gpio_free(host->gpio_write_protect);
+		if (host->base)
+			iounmap(host->base);
+	}
+	if (r)
+		release_resource(r);
+	if (mmc)
+		mmc_free_host(mmc);
+
+	return ret;
+}
+
+static int __exit mvsd_remove(struct platform_device *pdev)
+{
+	struct mmc_host *mmc = platform_get_drvdata(pdev);
+
+	if (mmc) {
+		struct mvsd_host *host = mmc_priv(mmc);
+
+		if (host->gpio_card_detect) {
+			free_irq(gpio_to_irq(host->gpio_card_detect), host);
+			gpio_free(host->gpio_card_detect);
+		}
+		mmc_remove_host(mmc);
+		free_irq(host->irq, host);
+		if (host->gpio_write_protect)
+			gpio_free(host->gpio_write_protect);
+		del_timer_sync(&host->timer);
+		mvsd_power_down(host);
+		iounmap(host->base);
+		release_resource(host->res);
+		mmc_free_host(mmc);
+	}
+	platform_set_drvdata(pdev, NULL);
+	return 0;
+}
+
+#ifdef CONFIG_PM
+static int mvsd_suspend(struct platform_device *dev, pm_message_t state,
+			   u32 level)
+{
+	struct mmc_host *mmc = platform_get_drvdata(dev);
+	int ret = 0;
+
+	if (mmc && level == SUSPEND_DISABLE)
+		ret = mmc_suspend_host(mmc, state);
+
+	return ret;
+}
+
+static int mvsd_resume(struct platform_device *dev, u32 level)
+{
+	struct mmc_host *mmc = platform_dev_get_drvdata(dev);
+	int ret = 0;
+
+	if (mmc && level == RESUME_ENABLE)
+		ret = mmc_resume_host(mmc);
+
+	return ret;
+}
+#else
+#define mvsd_suspend	NULL
+#define mvsd_resume	NULL
+#endif
+
+static struct platform_driver mvsd_driver = {
+	.remove		= __exit_p(mvsd_remove),
+	.suspend	= mvsd_suspend,
+	.resume		= mvsd_resume,
+	.driver		= {
+		.name	= DRIVER_NAME,
+	},
+};
+
+static int __init mvsd_init(void)
+{
+	return platform_driver_probe(&mvsd_driver, mvsd_probe);
+}
+
+static void __exit mvsd_exit(void)
+{
+	platform_driver_unregister(&mvsd_driver);
+}
+
+module_init(mvsd_init);
+module_exit(mvsd_exit);
+
+/* maximum card clock frequency (default 50MHz) */
+module_param(maxfreq, int, 0);
+
+/* force PIO transfers all the time */
+module_param(nodma, int, 0);
+
+MODULE_AUTHOR("Maen Suleiman, Nicolas Pitre");
+MODULE_DESCRIPTION("Marvell MMC,SD,SDIO Host Controller driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mmc/host/mvsdio.h b/drivers/mmc/host/mvsdio.h
new file mode 100644
index 000000000000..7d9727b9f5aa
--- /dev/null
+++ b/drivers/mmc/host/mvsdio.h
@@ -0,0 +1,190 @@
+/*
+ *  Copyright (C) 2008 Marvell Semiconductors, All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef __MVSDIO_H
+#define __MVSDIO_H
+
+/*
+ * Clock rates
+ */
+
+#define MVSD_CLOCKRATE_MAX			50000000
+#define MVSD_BASE_DIV_MAX			0x7ff
+
+
+/*
+ * Register offsets
+ */
+
+#define MVSD_SYS_ADDR_LOW			0x000
+#define MVSD_SYS_ADDR_HI			0x004
+#define MVSD_BLK_SIZE				0x008
+#define MVSD_BLK_COUNT				0x00c
+#define MVSD_ARG_LOW				0x010
+#define MVSD_ARG_HI				0x014
+#define MVSD_XFER_MODE				0x018
+#define MVSD_CMD				0x01c
+#define MVSD_RSP(i)				(0x020 + ((i)<<2))
+#define MVSD_RSP0				0x020
+#define MVSD_RSP1				0x024
+#define MVSD_RSP2				0x028
+#define MVSD_RSP3				0x02c
+#define MVSD_RSP4				0x030
+#define MVSD_RSP5				0x034
+#define MVSD_RSP6				0x038
+#define MVSD_RSP7				0x03c
+#define MVSD_FIFO				0x040
+#define MVSD_RSP_CRC7				0x044
+#define MVSD_HW_STATE				0x048
+#define MVSD_HOST_CTRL				0x050
+#define MVSD_BLK_GAP_CTRL			0x054
+#define MVSD_CLK_CTRL				0x058
+#define MVSD_SW_RESET				0x05c
+#define MVSD_NOR_INTR_STATUS			0x060
+#define MVSD_ERR_INTR_STATUS			0x064
+#define MVSD_NOR_STATUS_EN			0x068
+#define MVSD_ERR_STATUS_EN			0x06c
+#define MVSD_NOR_INTR_EN			0x070
+#define MVSD_ERR_INTR_EN			0x074
+#define MVSD_AUTOCMD12_ERR_STATUS		0x078
+#define MVSD_CURR_BYTE_LEFT			0x07c
+#define MVSD_CURR_BLK_LEFT			0x080
+#define MVSD_AUTOCMD12_ARG_LOW			0x084
+#define MVSD_AUTOCMD12_ARG_HI			0x088
+#define MVSD_AUTOCMD12_CMD			0x08c
+#define MVSD_AUTO_RSP(i)			(0x090 + ((i)<<2))
+#define MVSD_AUTO_RSP0				0x090
+#define MVSD_AUTO_RSP1				0x094
+#define MVSD_AUTO_RSP2				0x098
+#define MVSD_CLK_DIV				0x128
+
+#define MVSD_WINDOW_CTRL(i)			(0x108 + ((i) << 3))
+#define MVSD_WINDOW_BASE(i)			(0x10c + ((i) << 3))
+
+
+/*
+ * MVSD_CMD
+ */
+
+#define MVSD_CMD_RSP_NONE			(0 << 0)
+#define MVSD_CMD_RSP_136			(1 << 0)
+#define MVSD_CMD_RSP_48				(2 << 0)
+#define MVSD_CMD_RSP_48BUSY			(3 << 0)
+
+#define MVSD_CMD_CHECK_DATACRC16		(1 << 2)
+#define MVSD_CMD_CHECK_CMDCRC			(1 << 3)
+#define MVSD_CMD_INDX_CHECK			(1 << 4)
+#define MVSD_CMD_DATA_PRESENT			(1 << 5)
+#define MVSD_UNEXPECTED_RESP			(1 << 7)
+#define MVSD_CMD_INDEX(x)			((x) << 8)
+
+
+/*
+ * MVSD_AUTOCMD12_CMD
+ */
+
+#define MVSD_AUTOCMD12_BUSY			(1 << 0)
+#define MVSD_AUTOCMD12_INDX_CHECK		(1 << 1)
+#define MVSD_AUTOCMD12_INDEX(x)			((x) << 8)
+
+/*
+ * MVSD_XFER_MODE
+ */
+
+#define MVSD_XFER_MODE_WR_DATA_START		(1 << 0)
+#define MVSD_XFER_MODE_HW_WR_DATA_EN		(1 << 1)
+#define MVSD_XFER_MODE_AUTO_CMD12		(1 << 2)
+#define MVSD_XFER_MODE_INT_CHK_EN		(1 << 3)
+#define MVSD_XFER_MODE_TO_HOST			(1 << 4)
+#define MVSD_XFER_MODE_STOP_CLK			(1 << 5)
+#define MVSD_XFER_MODE_PIO			(1 << 6)
+
+
+/*
+ * MVSD_HOST_CTRL
+ */
+
+#define MVSD_HOST_CTRL_PUSH_PULL_EN 		(1 << 0)
+
+#define MVSD_HOST_CTRL_CARD_TYPE_MEM_ONLY 	(0 << 1)
+#define MVSD_HOST_CTRL_CARD_TYPE_IO_ONLY 	(1 << 1)
+#define MVSD_HOST_CTRL_CARD_TYPE_IO_MEM_COMBO 	(2 << 1)
+#define MVSD_HOST_CTRL_CARD_TYPE_IO_MMC 	(3 << 1)
+#define MVSD_HOST_CTRL_CARD_TYPE_MASK	 	(3 << 1)
+
+#define MVSD_HOST_CTRL_BIG_ENDIAN 		(1 << 3)
+#define MVSD_HOST_CTRL_LSB_FIRST 		(1 << 4)
+#define MVSD_HOST_CTRL_DATA_WIDTH_4_BITS 	(1 << 9)
+#define MVSD_HOST_CTRL_HI_SPEED_EN 		(1 << 10)
+
+#define MVSD_HOST_CTRL_TMOUT_MAX 		0xf
+#define MVSD_HOST_CTRL_TMOUT_MASK 		(0xf << 11)
+#define MVSD_HOST_CTRL_TMOUT(x) 		((x) << 11)
+#define MVSD_HOST_CTRL_TMOUT_EN 		(1 << 15)
+
+
+/*
+ * MVSD_SW_RESET
+ */
+
+#define MVSD_SW_RESET_NOW			(1 << 8)
+
+
+/*
+ * Normal interrupt status bits
+ */
+
+#define MVSD_NOR_CMD_DONE			(1 << 0)
+#define MVSD_NOR_XFER_DONE			(1 << 1)
+#define MVSD_NOR_BLK_GAP_EVT			(1 << 2)
+#define MVSD_NOR_DMA_DONE			(1 << 3)
+#define MVSD_NOR_TX_AVAIL			(1 << 4)
+#define MVSD_NOR_RX_READY			(1 << 5)
+#define MVSD_NOR_CARD_INT			(1 << 8)
+#define MVSD_NOR_READ_WAIT_ON			(1 << 9)
+#define MVSD_NOR_RX_FIFO_8W			(1 << 10)
+#define MVSD_NOR_TX_FIFO_8W			(1 << 11)
+#define MVSD_NOR_SUSPEND_ON			(1 << 12)
+#define MVSD_NOR_AUTOCMD12_DONE			(1 << 13)
+#define MVSD_NOR_UNEXP_RSP			(1 << 14)
+#define MVSD_NOR_ERROR				(1 << 15)
+
+
+/*
+ * Error status bits
+ */
+
+#define MVSD_ERR_CMD_TIMEOUT			(1 << 0)
+#define MVSD_ERR_CMD_CRC			(1 << 1)
+#define MVSD_ERR_CMD_ENDBIT			(1 << 2)
+#define MVSD_ERR_CMD_INDEX			(1 << 3)
+#define MVSD_ERR_DATA_TIMEOUT			(1 << 4)
+#define MVSD_ERR_DATA_CRC			(1 << 5)
+#define MVSD_ERR_DATA_ENDBIT			(1 << 6)
+#define MVSD_ERR_AUTOCMD12			(1 << 8)
+#define MVSD_ERR_CMD_STARTBIT			(1 << 9)
+#define MVSD_ERR_XFER_SIZE			(1 << 10)
+#define MVSD_ERR_RESP_T_BIT			(1 << 11)
+#define MVSD_ERR_CRC_ENDBIT			(1 << 12)
+#define MVSD_ERR_CRC_STARTBIT			(1 << 13)
+#define MVSD_ERR_CRC_STATUS			(1 << 14)
+
+
+/*
+ * CMD12 error status bits
+ */
+
+#define MVSD_AUTOCMD12_ERR_NOTEXE		(1 << 0)
+#define MVSD_AUTOCMD12_ERR_TIMEOUT		(1 << 1)
+#define MVSD_AUTOCMD12_ERR_CRC			(1 << 2)
+#define MVSD_AUTOCMD12_ERR_ENDBIT		(1 << 3)
+#define MVSD_AUTOCMD12_ERR_INDEX		(1 << 4)
+#define MVSD_AUTOCMD12_ERR_RESP_T_BIT		(1 << 5)
+#define MVSD_AUTOCMD12_ERR_RESP_STARTBIT	(1 << 6)
+
+#endif
diff --git a/drivers/mmc/host/omap_hsmmc.c b/drivers/mmc/host/omap_hsmmc.c
index 3916a5618e28..d183be6f2a5f 100644
--- a/drivers/mmc/host/omap_hsmmc.c
+++ b/drivers/mmc/host/omap_hsmmc.c
@@ -56,6 +56,7 @@
 #define SDVS18			(0x5 << 9)
 #define SDVS30			(0x6 << 9)
 #define SDVS33			(0x7 << 9)
+#define SDVS_MASK		0x00000E00
 #define SDVSCLR			0xFFFFF1FF
 #define SDVSDET			0x00000400
 #define AUTOIDLE		0x1
@@ -76,6 +77,7 @@
 #define MSBS			(1 << 5)
 #define BCE			(1 << 1)
 #define FOUR_BIT		(1 << 1)
+#define DW8			(1 << 5)
 #define CC			0x1
 #define TC			0x02
 #define OD			0x1
@@ -98,10 +100,8 @@
  */
 #define OMAP_MMC1_DEVID		0
 #define OMAP_MMC2_DEVID		1
+#define OMAP_MMC3_DEVID		2
 
-#define OMAP_MMC_DATADIR_NONE	0
-#define OMAP_MMC_DATADIR_READ	1
-#define OMAP_MMC_DATADIR_WRITE	2
 #define MMC_TIMEOUT_MS		20
 #define OMAP_MMC_MASTER_CLOCK	96000000
 #define DRIVER_NAME		"mmci-omap-hs"
@@ -137,18 +137,18 @@ struct mmc_omap_host {
 	resource_size_t		mapbase;
 	unsigned int		id;
 	unsigned int		dma_len;
-	unsigned int		dma_dir;
+	unsigned int		dma_sg_idx;
 	unsigned char		bus_mode;
-	unsigned char		datadir;
 	u32			*buffer;
 	u32			bytesleft;
 	int			suspended;
 	int			irq;
 	int			carddetect;
 	int			use_dma, dma_ch;
-	int			initstr;
+	int			dma_line_tx, dma_line_rx;
 	int			slot_id;
 	int			dbclk_enabled;
+	int			response_busy;
 	struct	omap_mmc_platform_data	*pdata;
 };
 
@@ -218,7 +218,7 @@ mmc_omap_show_slot_name(struct device *dev, struct device_attribute *attr,
 	struct mmc_omap_host *host = mmc_priv(mmc);
 	struct omap_mmc_slot_data slot = host->pdata->slots[host->slot_id];
 
-	return sprintf(buf, "slot:%s\n", slot.name);
+	return sprintf(buf, "%s\n", slot.name);
 }
 
 static DEVICE_ATTR(slot_name, S_IRUGO, mmc_omap_show_slot_name, NULL);
@@ -243,10 +243,14 @@ mmc_omap_start_command(struct mmc_omap_host *host, struct mmc_command *cmd,
 	OMAP_HSMMC_WRITE(host->base, ISE, INT_EN_MASK);
 	OMAP_HSMMC_WRITE(host->base, IE, INT_EN_MASK);
 
+	host->response_busy = 0;
 	if (cmd->flags & MMC_RSP_PRESENT) {
 		if (cmd->flags & MMC_RSP_136)
 			resptype = 1;
-		else
+		else if (cmd->flags & MMC_RSP_BUSY) {
+			resptype = 3;
+			host->response_busy = 1;
+		} else
 			resptype = 2;
 	}
 
@@ -275,19 +279,35 @@ mmc_omap_start_command(struct mmc_omap_host *host, struct mmc_command *cmd,
 	OMAP_HSMMC_WRITE(host->base, CMD, cmdreg);
 }
 
+static int
+mmc_omap_get_dma_dir(struct mmc_omap_host *host, struct mmc_data *data)
+{
+	if (data->flags & MMC_DATA_WRITE)
+		return DMA_TO_DEVICE;
+	else
+		return DMA_FROM_DEVICE;
+}
+
 /*
  * Notify the transfer complete to MMC core
  */
 static void
 mmc_omap_xfer_done(struct mmc_omap_host *host, struct mmc_data *data)
 {
+	if (!data) {
+		struct mmc_request *mrq = host->mrq;
+
+		host->mrq = NULL;
+		mmc_omap_fclk_lazy_disable(host);
+		mmc_request_done(host->mmc, mrq);
+		return;
+	}
+
 	host->data = NULL;
 
 	if (host->use_dma && host->dma_ch != -1)
 		dma_unmap_sg(mmc_dev(host->mmc), data->sg, host->dma_len,
-			host->dma_dir);
-
-	host->datadir = OMAP_MMC_DATADIR_NONE;
+			mmc_omap_get_dma_dir(host, data));
 
 	if (!data->error)
 		data->bytes_xfered += data->blocks * (data->blksz);
@@ -322,7 +342,7 @@ mmc_omap_cmd_done(struct mmc_omap_host *host, struct mmc_command *cmd)
 			cmd->resp[0] = OMAP_HSMMC_READ(host->base, RSP10);
 		}
 	}
-	if (host->data == NULL || cmd->error) {
+	if ((host->data == NULL && !host->response_busy) || cmd->error) {
 		host->mrq = NULL;
 		mmc_request_done(host->mmc, cmd->mrq);
 	}
@@ -331,19 +351,18 @@ mmc_omap_cmd_done(struct mmc_omap_host *host, struct mmc_command *cmd)
 /*
  * DMA clean up for command errors
  */
-static void mmc_dma_cleanup(struct mmc_omap_host *host)
+static void mmc_dma_cleanup(struct mmc_omap_host *host, int errno)
 {
-	host->data->error = -ETIMEDOUT;
+	host->data->error = errno;
 
 	if (host->use_dma && host->dma_ch != -1) {
 		dma_unmap_sg(mmc_dev(host->mmc), host->data->sg, host->dma_len,
-			host->dma_dir);
+			mmc_omap_get_dma_dir(host, host->data));
 		omap_free_dma(host->dma_ch);
 		host->dma_ch = -1;
 		up(&host->sem);
 	}
 	host->data = NULL;
-	host->datadir = OMAP_MMC_DATADIR_NONE;
 }
 
 /*
@@ -412,7 +431,7 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id)
 	struct mmc_data *data;
 	int end_cmd = 0, end_trans = 0, status;
 
-	if (host->cmd == NULL && host->data == NULL) {
+	if (host->mrq == NULL) {
 		OMAP_HSMMC_WRITE(host->base, STAT,
 			OMAP_HSMMC_READ(host->base, STAT));
 		return IRQ_HANDLED;
@@ -437,18 +456,24 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id)
 				}
 				end_cmd = 1;
 			}
-			if (host->data) {
-				mmc_dma_cleanup(host);
+			if (host->data || host->response_busy) {
+				if (host->data)
+					mmc_dma_cleanup(host, -ETIMEDOUT);
+				host->response_busy = 0;
 				mmc_omap_reset_controller_fsm(host, SRD);
 			}
 		}
 		if ((status & DATA_TIMEOUT) ||
 			(status & DATA_CRC)) {
-			if (host->data) {
-				if (status & DATA_TIMEOUT)
-					mmc_dma_cleanup(host);
+			if (host->data || host->response_busy) {
+				int err = (status & DATA_TIMEOUT) ?
+						-ETIMEDOUT : -EILSEQ;
+
+				if (host->data)
+					mmc_dma_cleanup(host, err);
 				else
-					host->data->error = -EILSEQ;
+					host->mrq->cmd->error = err;
+				host->response_busy = 0;
 				mmc_omap_reset_controller_fsm(host, SRD);
 				end_trans = 1;
 			}
@@ -473,6 +498,19 @@ static irqreturn_t mmc_omap_irq(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static void set_sd_bus_power(struct mmc_omap_host *host)
+{
+	unsigned long i;
+
+	OMAP_HSMMC_WRITE(host->base, HCTL,
+			 OMAP_HSMMC_READ(host->base, HCTL) | SDBP);
+	for (i = 0; i < loops_per_jiffy; i++) {
+		if (OMAP_HSMMC_READ(host->base, HCTL) & SDBP)
+			break;
+		cpu_relax();
+	}
+}
+
 /*
  * Switch MMC interface voltage ... only relevant for MMC1.
  *
@@ -485,9 +523,6 @@ static int omap_mmc_switch_opcond(struct mmc_omap_host *host, int vdd)
 	u32 reg_val = 0;
 	int ret;
 
-	if (host->id != OMAP_MMC1_DEVID)
-		return 0;
-
 	/* Disable the clocks */
 	clk_disable(host->fclk);
 	clk_disable(host->iclk);
@@ -532,9 +567,7 @@ static int omap_mmc_switch_opcond(struct mmc_omap_host *host, int vdd)
 		reg_val |= SDVS30;
 
 	OMAP_HSMMC_WRITE(host->base, HCTL, reg_val);
-
-	OMAP_HSMMC_WRITE(host->base, HCTL,
-		OMAP_HSMMC_READ(host->base, HCTL) | SDBP);
+	set_sd_bus_power(host);
 
 	return 0;
 err:
@@ -551,7 +584,10 @@ static void mmc_omap_detect(struct work_struct *work)
 						mmc_carddetect_work);
 	struct omap_mmc_slot_data *slot = &mmc_slot(host);
 
-	host->carddetect = slot->card_detect(slot->card_detect_irq);
+	if (mmc_slot(host).card_detect)
+		host->carddetect = slot->card_detect(slot->card_detect_irq);
+	else
+		host->carddetect = -ENOSYS;
 
 	sysfs_notify(&host->mmc->class_dev.kobj, NULL, "cover_switch");
 	if (host->carddetect) {
@@ -574,6 +610,48 @@ static irqreturn_t omap_mmc_cd_handler(int irq, void *dev_id)
 	return IRQ_HANDLED;
 }
 
+static int mmc_omap_get_dma_sync_dev(struct mmc_omap_host *host,
+				     struct mmc_data *data)
+{
+	int sync_dev;
+
+	if (data->flags & MMC_DATA_WRITE)
+		sync_dev = host->dma_line_tx;
+	else
+		sync_dev = host->dma_line_rx;
+	return sync_dev;
+}
+
+static void mmc_omap_config_dma_params(struct mmc_omap_host *host,
+				       struct mmc_data *data,
+				       struct scatterlist *sgl)
+{
+	int blksz, nblk, dma_ch;
+
+	dma_ch = host->dma_ch;
+	if (data->flags & MMC_DATA_WRITE) {
+		omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
+			(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
+		omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
+			sg_dma_address(sgl), 0, 0);
+	} else {
+		omap_set_dma_src_params(dma_ch, 0, OMAP_DMA_AMODE_CONSTANT,
+					(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
+		omap_set_dma_dest_params(dma_ch, 0, OMAP_DMA_AMODE_POST_INC,
+			sg_dma_address(sgl), 0, 0);
+	}
+
+	blksz = host->data->blksz;
+	nblk = sg_dma_len(sgl) / blksz;
+
+	omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S32,
+			blksz / 4, nblk, OMAP_DMA_SYNC_FRAME,
+			mmc_omap_get_dma_sync_dev(host, data),
+			!(data->flags & MMC_DATA_WRITE));
+
+	omap_start_dma(dma_ch);
+}
+
 /*
  * DMA call back function
  */
@@ -587,6 +665,14 @@ static void mmc_omap_dma_cb(int lch, u16 ch_status, void *data)
 	if (host->dma_ch < 0)
 		return;
 
+	host->dma_sg_idx++;
+	if (host->dma_sg_idx < host->dma_len) {
+		/* Fire up the next transfer. */
+		mmc_omap_config_dma_params(host, host->data,
+					   host->data->sg + host->dma_sg_idx);
+		return;
+	}
+
 	omap_free_dma(host->dma_ch);
 	host->dma_ch = -1;
 	/*
@@ -597,38 +683,28 @@ static void mmc_omap_dma_cb(int lch, u16 ch_status, void *data)
 }
 
 /*
- * Configure dma src and destination parameters
- */
-static int mmc_omap_config_dma_param(int sync_dir, struct mmc_omap_host *host,
-				struct mmc_data *data)
-{
-	if (sync_dir == 0) {
-		omap_set_dma_dest_params(host->dma_ch, 0,
-			OMAP_DMA_AMODE_CONSTANT,
-			(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
-		omap_set_dma_src_params(host->dma_ch, 0,
-			OMAP_DMA_AMODE_POST_INC,
-			sg_dma_address(&data->sg[0]), 0, 0);
-	} else {
-		omap_set_dma_src_params(host->dma_ch, 0,
-			OMAP_DMA_AMODE_CONSTANT,
-			(host->mapbase + OMAP_HSMMC_DATA), 0, 0);
-		omap_set_dma_dest_params(host->dma_ch, 0,
-			OMAP_DMA_AMODE_POST_INC,
-			sg_dma_address(&data->sg[0]), 0, 0);
-	}
-	return 0;
-}
-/*
  * Routine to configure and start DMA for the MMC card
  */
 static int
 mmc_omap_start_dma_transfer(struct mmc_omap_host *host, struct mmc_request *req)
 {
-	int sync_dev, sync_dir = 0;
-	int dma_ch = 0, ret = 0, err = 1;
+	int dma_ch = 0, ret = 0, err = 1, i;
 	struct mmc_data *data = req->data;
 
+	/* Sanity check: all the SG entries must be aligned by block size. */
+	for (i = 0; i < host->dma_len; i++) {
+		struct scatterlist *sgl;
+
+		sgl = data->sg + i;
+		if (sgl->length % data->blksz)
+			return -EINVAL;
+	}
+	if ((data->blksz % 4) != 0)
+		/* REVISIT: The MMC buffer increments only when MSB is written.
+		 * Return error for blksz which is non multiple of four.
+		 */
+		return -EINVAL;
+
 	/*
 	 * If for some reason the DMA transfer is still active,
 	 * we wait for timeout period and free the dma
@@ -647,49 +723,22 @@ mmc_omap_start_dma_transfer(struct mmc_omap_host *host, struct mmc_request *req)
 			return err;
 	}
 
-	if (!(data->flags & MMC_DATA_WRITE)) {
-		host->dma_dir = DMA_FROM_DEVICE;
-		if (host->id == OMAP_MMC1_DEVID)
-			sync_dev = OMAP24XX_DMA_MMC1_RX;
-		else
-			sync_dev = OMAP24XX_DMA_MMC2_RX;
-	} else {
-		host->dma_dir = DMA_TO_DEVICE;
-		if (host->id == OMAP_MMC1_DEVID)
-			sync_dev = OMAP24XX_DMA_MMC1_TX;
-		else
-			sync_dev = OMAP24XX_DMA_MMC2_TX;
-	}
-
-	ret = omap_request_dma(sync_dev, "MMC/SD", mmc_omap_dma_cb,
-			host, &dma_ch);
+	ret = omap_request_dma(mmc_omap_get_dma_sync_dev(host, data), "MMC/SD",
+			       mmc_omap_dma_cb,host, &dma_ch);
 	if (ret != 0) {
-		dev_dbg(mmc_dev(host->mmc),
+		dev_err(mmc_dev(host->mmc),
 			"%s: omap_request_dma() failed with %d\n",
 			mmc_hostname(host->mmc), ret);
 		return ret;
 	}
 
 	host->dma_len = dma_map_sg(mmc_dev(host->mmc), data->sg,
-			data->sg_len, host->dma_dir);
+			data->sg_len, mmc_omap_get_dma_dir(host, data));
 	host->dma_ch = dma_ch;
+	host->dma_sg_idx = 0;
 
-	if (!(data->flags & MMC_DATA_WRITE))
-		mmc_omap_config_dma_param(1, host, data);
-	else
-		mmc_omap_config_dma_param(0, host, data);
-
-	if ((data->blksz % 4) == 0)
-		omap_set_dma_transfer_params(dma_ch, OMAP_DMA_DATA_TYPE_S32,
-			(data->blksz / 4), data->blocks, OMAP_DMA_SYNC_FRAME,
-			sync_dev, sync_dir);
-	else
-		/* REVISIT: The MMC buffer increments only when MSB is written.
-		 * Return error for blksz which is non multiple of four.
-		 */
-		return -EINVAL;
+	mmc_omap_config_dma_params(host, data, data->sg);
 
-	omap_start_dma(dma_ch);
 	return 0;
 }
 
@@ -739,7 +788,6 @@ mmc_omap_prepare_data(struct mmc_omap_host *host, struct mmc_request *req)
 	host->data = req->data;
 
 	if (req->data == NULL) {
-		host->datadir = OMAP_MMC_DATADIR_NONE;
 		OMAP_HSMMC_WRITE(host->base, BLK, 0);
 		return 0;
 	}
@@ -748,9 +796,6 @@ mmc_omap_prepare_data(struct mmc_omap_host *host, struct mmc_request *req)
 					| (req->data->blocks << 16));
 	set_data_timeout(host, req);
 
-	host->datadir = (req->data->flags & MMC_DATA_WRITE) ?
-			OMAP_MMC_DATADIR_WRITE : OMAP_MMC_DATADIR_READ;
-
 	if (host->use_dma) {
 		ret = mmc_omap_start_dma_transfer(host, req);
 		if (ret != 0) {
@@ -782,36 +827,29 @@ static void omap_mmc_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	u16 dsor = 0;
 	unsigned long regval;
 	unsigned long timeout;
+	u32 con;
 
 	switch (ios->power_mode) {
 	case MMC_POWER_OFF:
 		mmc_slot(host).set_power(host->dev, host->slot_id, 0, 0);
-		/*
-		 * Reset interface voltage to 3V if it's 1.8V now;
-		 * only relevant on MMC-1, the others always use 1.8V.
-		 *
-		 * REVISIT: If we are able to detect cards after unplugging
-		 * a 1.8V card, this code should not be needed.
-		 */
-		if (host->id != OMAP_MMC1_DEVID)
-			break;
-		if (!(OMAP_HSMMC_READ(host->base, HCTL) & SDVSDET)) {
-			int vdd = fls(host->mmc->ocr_avail) - 1;
-			if (omap_mmc_switch_opcond(host, vdd) != 0)
-				host->mmc->ios.vdd = vdd;
-		}
 		break;
 	case MMC_POWER_UP:
 		mmc_slot(host).set_power(host->dev, host->slot_id, 1, ios->vdd);
 		break;
 	}
 
+	con = OMAP_HSMMC_READ(host->base, CON);
 	switch (mmc->ios.bus_width) {
+	case MMC_BUS_WIDTH_8:
+		OMAP_HSMMC_WRITE(host->base, CON, con | DW8);
+		break;
 	case MMC_BUS_WIDTH_4:
+		OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8);
 		OMAP_HSMMC_WRITE(host->base, HCTL,
 			OMAP_HSMMC_READ(host->base, HCTL) | FOUR_BIT);
 		break;
 	case MMC_BUS_WIDTH_1:
+		OMAP_HSMMC_WRITE(host->base, CON, con & ~DW8);
 		OMAP_HSMMC_WRITE(host->base, HCTL,
 			OMAP_HSMMC_READ(host->base, HCTL) & ~FOUR_BIT);
 		break;
@@ -891,6 +929,33 @@ static int omap_hsmmc_get_ro(struct mmc_host *mmc)
 	return pdata->slots[0].get_ro(host->dev, 0);
 }
 
+static void omap_hsmmc_init(struct mmc_omap_host *host)
+{
+	u32 hctl, capa, value;
+
+	/* Only MMC1 supports 3.0V */
+	if (host->id == OMAP_MMC1_DEVID) {
+		hctl = SDVS30;
+		capa = VS30 | VS18;
+	} else {
+		hctl = SDVS18;
+		capa = VS18;
+	}
+
+	value = OMAP_HSMMC_READ(host->base, HCTL) & ~SDVS_MASK;
+	OMAP_HSMMC_WRITE(host->base, HCTL, value | hctl);
+
+	value = OMAP_HSMMC_READ(host->base, CAPA);
+	OMAP_HSMMC_WRITE(host->base, CAPA, value | capa);
+
+	/* Set the controller to AUTO IDLE mode */
+	value = OMAP_HSMMC_READ(host->base, SYSCONFIG);
+	OMAP_HSMMC_WRITE(host->base, SYSCONFIG, value | AUTOIDLE);
+
+	/* Set SD bus power bit */
+	set_sd_bus_power(host);
+}
+
 static struct mmc_host_ops mmc_omap_ops = {
 	.request = omap_mmc_request,
 	.set_ios = omap_mmc_set_ios,
@@ -906,7 +971,6 @@ static int __init omap_mmc_probe(struct platform_device *pdev)
 	struct mmc_omap_host *host = NULL;
 	struct resource *res;
 	int ret = 0, irq;
-	u32 hctl, capa;
 
 	if (pdata == NULL) {
 		dev_err(&pdev->dev, "Platform Data is missing\n");
@@ -996,10 +1060,11 @@ static int __init omap_mmc_probe(struct platform_device *pdev)
 		else
 			host->dbclk_enabled = 1;
 
-#ifdef CONFIG_MMC_BLOCK_BOUNCE
-	mmc->max_phys_segs = 1;
-	mmc->max_hw_segs = 1;
-#endif
+	/* Since we do only SG emulation, we can have as many segs
+	 * as we want. */
+	mmc->max_phys_segs = 1024;
+	mmc->max_hw_segs = 1024;
+
 	mmc->max_blk_size = 512;       /* Block Length at max can be 1024 */
 	mmc->max_blk_count = 0xFFFF;    /* No. of Blocks is 16 bits */
 	mmc->max_req_size = mmc->max_blk_size * mmc->max_blk_count;
@@ -1008,31 +1073,31 @@ static int __init omap_mmc_probe(struct platform_device *pdev)
 	mmc->ocr_avail = mmc_slot(host).ocr_mask;
 	mmc->caps |= MMC_CAP_MMC_HIGHSPEED | MMC_CAP_SD_HIGHSPEED;
 
-	if (pdata->slots[host->slot_id].wires >= 4)
+	if (pdata->slots[host->slot_id].wires >= 8)
+		mmc->caps |= MMC_CAP_8_BIT_DATA;
+	else if (pdata->slots[host->slot_id].wires >= 4)
 		mmc->caps |= MMC_CAP_4_BIT_DATA;
 
-	/* Only MMC1 supports 3.0V */
-	if (host->id == OMAP_MMC1_DEVID) {
-		hctl = SDVS30;
-		capa = VS30 | VS18;
-	} else {
-		hctl = SDVS18;
-		capa = VS18;
-	}
-
-	OMAP_HSMMC_WRITE(host->base, HCTL,
-			OMAP_HSMMC_READ(host->base, HCTL) | hctl);
-
-	OMAP_HSMMC_WRITE(host->base, CAPA,
-			OMAP_HSMMC_READ(host->base, CAPA) | capa);
-
-	/* Set the controller to AUTO IDLE mode */
-	OMAP_HSMMC_WRITE(host->base, SYSCONFIG,
-			OMAP_HSMMC_READ(host->base, SYSCONFIG) | AUTOIDLE);
+	omap_hsmmc_init(host);
 
-	/* Set SD bus power bit */
-	OMAP_HSMMC_WRITE(host->base, HCTL,
-			OMAP_HSMMC_READ(host->base, HCTL) | SDBP);
+	/* Select DMA lines */
+	switch (host->id) {
+	case OMAP_MMC1_DEVID:
+		host->dma_line_tx = OMAP24XX_DMA_MMC1_TX;
+		host->dma_line_rx = OMAP24XX_DMA_MMC1_RX;
+		break;
+	case OMAP_MMC2_DEVID:
+		host->dma_line_tx = OMAP24XX_DMA_MMC2_TX;
+		host->dma_line_rx = OMAP24XX_DMA_MMC2_RX;
+		break;
+	case OMAP_MMC3_DEVID:
+		host->dma_line_tx = OMAP34XX_DMA_MMC3_TX;
+		host->dma_line_rx = OMAP34XX_DMA_MMC3_RX;
+		break;
+	default:
+		dev_err(mmc_dev(host->mmc), "Invalid MMC id\n");
+		goto err_irq;
+	}
 
 	/* Request IRQ for MMC operations */
 	ret = request_irq(host->irq, mmc_omap_irq, IRQF_DISABLED,
@@ -1051,7 +1116,7 @@ static int __init omap_mmc_probe(struct platform_device *pdev)
 	}
 
 	/* Request IRQ for card detect */
-	if ((mmc_slot(host).card_detect_irq) && (mmc_slot(host).card_detect)) {
+	if ((mmc_slot(host).card_detect_irq)) {
 		ret = request_irq(mmc_slot(host).card_detect_irq,
 				  omap_mmc_cd_handler,
 				  IRQF_TRIGGER_RISING | IRQF_TRIGGER_FALLING
@@ -1074,8 +1139,8 @@ static int __init omap_mmc_probe(struct platform_device *pdev)
 		if (ret < 0)
 			goto err_slot_name;
 	}
-	if (mmc_slot(host).card_detect_irq && mmc_slot(host).card_detect &&
-			host->pdata->slots[host->slot_id].get_cover_state) {
+	if (mmc_slot(host).card_detect_irq &&
+	    host->pdata->slots[host->slot_id].get_cover_state) {
 		ret = device_create_file(&mmc->class_dev,
 					&dev_attr_cover_switch);
 		if (ret < 0)
@@ -1173,20 +1238,8 @@ static int omap_mmc_suspend(struct platform_device *pdev, pm_message_t state)
 						" level suspend\n");
 			}
 
-			if (host->id == OMAP_MMC1_DEVID
-					&& !(OMAP_HSMMC_READ(host->base, HCTL)
-							& SDVSDET)) {
-				OMAP_HSMMC_WRITE(host->base, HCTL,
-					OMAP_HSMMC_READ(host->base, HCTL)
-					& SDVSCLR);
-				OMAP_HSMMC_WRITE(host->base, HCTL,
-					OMAP_HSMMC_READ(host->base, HCTL)
-					| SDVS30);
-				OMAP_HSMMC_WRITE(host->base, HCTL,
-					OMAP_HSMMC_READ(host->base, HCTL)
-					| SDBP);
-			}
-
+			OMAP_HSMMC_WRITE(host->base, HCTL,
+					 OMAP_HSMMC_READ(host->base, HCTL) & ~SDBP);
 			clk_disable(host->fclk);
 			clk_disable(host->iclk);
 			clk_disable(host->dbclk);
@@ -1222,6 +1275,8 @@ static int omap_mmc_resume(struct platform_device *pdev)
 			dev_dbg(mmc_dev(host->mmc),
 					"Enabling debounce clk failed\n");
 
+		omap_hsmmc_init(host);
+
 		if (host->pdata->resume) {
 			ret = host->pdata->resume(&pdev->dev, host->slot_id);
 			if (ret)
diff --git a/drivers/mmc/host/sdhci-of.c b/drivers/mmc/host/sdhci-of.c
new file mode 100644
index 000000000000..3ff4ac3abe8b
--- /dev/null
+++ b/drivers/mmc/host/sdhci-of.c
@@ -0,0 +1,309 @@
+/*
+ * OpenFirmware bindings for Secure Digital Host Controller Interface.
+ *
+ * Copyright (c) 2007 Freescale Semiconductor, Inc.
+ * Copyright (c) 2009 MontaVista Software, Inc.
+ *
+ * Authors: Xiaobo Xie <X.Xie@freescale.com>
+ *	    Anton Vorontsov <avorontsov@ru.mvista.com>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or (at
+ * your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/io.h>
+#include <linux/interrupt.h>
+#include <linux/delay.h>
+#include <linux/of.h>
+#include <linux/of_platform.h>
+#include <linux/mmc/host.h>
+#include "sdhci.h"
+
+struct sdhci_of_data {
+	unsigned int quirks;
+	struct sdhci_ops ops;
+};
+
+struct sdhci_of_host {
+	unsigned int clock;
+	u16 xfer_mode_shadow;
+};
+
+/*
+ * Ops and quirks for the Freescale eSDHC controller.
+ */
+
+#define ESDHC_DMA_SYSCTL	0x40c
+#define ESDHC_DMA_SNOOP		0x00000040
+
+#define ESDHC_SYSTEM_CONTROL	0x2c
+#define ESDHC_CLOCK_MASK	0x0000fff0
+#define ESDHC_PREDIV_SHIFT	8
+#define ESDHC_DIVIDER_SHIFT	4
+#define ESDHC_CLOCK_PEREN	0x00000004
+#define ESDHC_CLOCK_HCKEN	0x00000002
+#define ESDHC_CLOCK_IPGEN	0x00000001
+
+static u32 esdhc_readl(struct sdhci_host *host, int reg)
+{
+	return in_be32(host->ioaddr + reg);
+}
+
+static u16 esdhc_readw(struct sdhci_host *host, int reg)
+{
+	return in_be16(host->ioaddr + (reg ^ 0x2));
+}
+
+static u8 esdhc_readb(struct sdhci_host *host, int reg)
+{
+	return in_8(host->ioaddr + (reg ^ 0x3));
+}
+
+static void esdhc_writel(struct sdhci_host *host, u32 val, int reg)
+{
+	out_be32(host->ioaddr + reg, val);
+}
+
+static void esdhc_writew(struct sdhci_host *host, u16 val, int reg)
+{
+	struct sdhci_of_host *of_host = sdhci_priv(host);
+	int base = reg & ~0x3;
+	int shift = (reg & 0x2) * 8;
+
+	switch (reg) {
+	case SDHCI_TRANSFER_MODE:
+		/*
+		 * Postpone this write, we must do it together with a
+		 * command write that is down below.
+		 */
+		of_host->xfer_mode_shadow = val;
+		return;
+	case SDHCI_COMMAND:
+		esdhc_writel(host, val << 16 | of_host->xfer_mode_shadow,
+			     SDHCI_TRANSFER_MODE);
+		return;
+	case SDHCI_BLOCK_SIZE:
+		/*
+		 * Two last DMA bits are reserved, and first one is used for
+		 * non-standard blksz of 4096 bytes that we don't support
+		 * yet. So clear the DMA boundary bits.
+		 */
+		val &= ~SDHCI_MAKE_BLKSZ(0x7, 0);
+		/* fall through */
+	}
+	clrsetbits_be32(host->ioaddr + base, 0xffff << shift, val << shift);
+}
+
+static void esdhc_writeb(struct sdhci_host *host, u8 val, int reg)
+{
+	int base = reg & ~0x3;
+	int shift = (reg & 0x3) * 8;
+
+	clrsetbits_be32(host->ioaddr + base , 0xff << shift, val << shift);
+}
+
+static void esdhc_set_clock(struct sdhci_host *host, unsigned int clock)
+{
+	int div;
+	int pre_div = 2;
+
+	clrbits32(host->ioaddr + ESDHC_SYSTEM_CONTROL, ESDHC_CLOCK_IPGEN |
+		  ESDHC_CLOCK_HCKEN | ESDHC_CLOCK_PEREN | ESDHC_CLOCK_MASK);
+
+	if (clock == 0)
+		goto out;
+
+	if (host->max_clk / 16 > clock) {
+		for (; pre_div < 256; pre_div *= 2) {
+			if (host->max_clk / pre_div < clock * 16)
+				break;
+		}
+	}
+
+	for (div = 1; div <= 16; div++) {
+		if (host->max_clk / (div * pre_div) <= clock)
+			break;
+	}
+
+	pre_div >>= 1;
+
+	setbits32(host->ioaddr + ESDHC_SYSTEM_CONTROL, ESDHC_CLOCK_IPGEN |
+		  ESDHC_CLOCK_HCKEN | ESDHC_CLOCK_PEREN |
+		  div << ESDHC_DIVIDER_SHIFT | pre_div << ESDHC_PREDIV_SHIFT);
+	mdelay(100);
+out:
+	host->clock = clock;
+}
+
+static int esdhc_enable_dma(struct sdhci_host *host)
+{
+	setbits32(host->ioaddr + ESDHC_DMA_SYSCTL, ESDHC_DMA_SNOOP);
+	return 0;
+}
+
+static unsigned int esdhc_get_max_clock(struct sdhci_host *host)
+{
+	struct sdhci_of_host *of_host = sdhci_priv(host);
+
+	return of_host->clock;
+}
+
+static unsigned int esdhc_get_timeout_clock(struct sdhci_host *host)
+{
+	struct sdhci_of_host *of_host = sdhci_priv(host);
+
+	return of_host->clock / 1000;
+}
+
+static struct sdhci_of_data sdhci_esdhc = {
+	.quirks = SDHCI_QUIRK_FORCE_BLK_SZ_2048 |
+		  SDHCI_QUIRK_BROKEN_CARD_DETECTION |
+		  SDHCI_QUIRK_INVERTED_WRITE_PROTECT |
+		  SDHCI_QUIRK_NO_BUSY_IRQ |
+		  SDHCI_QUIRK_NONSTANDARD_CLOCK |
+		  SDHCI_QUIRK_PIO_NEEDS_DELAY |
+		  SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET |
+		  SDHCI_QUIRK_NO_CARD_NO_RESET,
+	.ops = {
+		.readl = esdhc_readl,
+		.readw = esdhc_readw,
+		.readb = esdhc_readb,
+		.writel = esdhc_writel,
+		.writew = esdhc_writew,
+		.writeb = esdhc_writeb,
+		.set_clock = esdhc_set_clock,
+		.enable_dma = esdhc_enable_dma,
+		.get_max_clock = esdhc_get_max_clock,
+		.get_timeout_clock = esdhc_get_timeout_clock,
+	},
+};
+
+#ifdef CONFIG_PM
+
+static int sdhci_of_suspend(struct of_device *ofdev, pm_message_t state)
+{
+	struct sdhci_host *host = dev_get_drvdata(&ofdev->dev);
+
+	return mmc_suspend_host(host->mmc, state);
+}
+
+static int sdhci_of_resume(struct of_device *ofdev)
+{
+	struct sdhci_host *host = dev_get_drvdata(&ofdev->dev);
+
+	return mmc_resume_host(host->mmc);
+}
+
+#else
+
+#define sdhci_of_suspend NULL
+#define sdhci_of_resume NULL
+
+#endif
+
+static int __devinit sdhci_of_probe(struct of_device *ofdev,
+				 const struct of_device_id *match)
+{
+	struct device_node *np = ofdev->node;
+	struct sdhci_of_data *sdhci_of_data = match->data;
+	struct sdhci_host *host;
+	struct sdhci_of_host *of_host;
+	const u32 *clk;
+	int size;
+	int ret;
+
+	if (!of_device_is_available(np))
+		return -ENODEV;
+
+	host = sdhci_alloc_host(&ofdev->dev, sizeof(*of_host));
+	if (!host)
+		return -ENOMEM;
+
+	of_host = sdhci_priv(host);
+	dev_set_drvdata(&ofdev->dev, host);
+
+	host->ioaddr = of_iomap(np, 0);
+	if (!host->ioaddr) {
+		ret = -ENOMEM;
+		goto err_addr_map;
+	}
+
+	host->irq = irq_of_parse_and_map(np, 0);
+	if (!host->irq) {
+		ret = -EINVAL;
+		goto err_no_irq;
+	}
+
+	host->hw_name = dev_name(&ofdev->dev);
+	if (sdhci_of_data) {
+		host->quirks = sdhci_of_data->quirks;
+		host->ops = &sdhci_of_data->ops;
+	}
+
+	clk = of_get_property(np, "clock-frequency", &size);
+	if (clk && size == sizeof(*clk) && *clk)
+		of_host->clock = *clk;
+
+	ret = sdhci_add_host(host);
+	if (ret)
+		goto err_add_host;
+
+	return 0;
+
+err_add_host:
+	irq_dispose_mapping(host->irq);
+err_no_irq:
+	iounmap(host->ioaddr);
+err_addr_map:
+	sdhci_free_host(host);
+	return ret;
+}
+
+static int __devexit sdhci_of_remove(struct of_device *ofdev)
+{
+	struct sdhci_host *host = dev_get_drvdata(&ofdev->dev);
+
+	sdhci_remove_host(host, 0);
+	sdhci_free_host(host);
+	irq_dispose_mapping(host->irq);
+	iounmap(host->ioaddr);
+	return 0;
+}
+
+static const struct of_device_id sdhci_of_match[] = {
+	{ .compatible = "fsl,mpc8379-esdhc", .data = &sdhci_esdhc, },
+	{ .compatible = "fsl,mpc8536-esdhc", .data = &sdhci_esdhc, },
+	{ .compatible = "generic-sdhci", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, sdhci_of_match);
+
+static struct of_platform_driver sdhci_of_driver = {
+	.driver.name = "sdhci-of",
+	.match_table = sdhci_of_match,
+	.probe = sdhci_of_probe,
+	.remove = __devexit_p(sdhci_of_remove),
+	.suspend = sdhci_of_suspend,
+	.resume	= sdhci_of_resume,
+};
+
+static int __init sdhci_of_init(void)
+{
+	return of_register_platform_driver(&sdhci_of_driver);
+}
+module_init(sdhci_of_init);
+
+static void __exit sdhci_of_exit(void)
+{
+	of_unregister_platform_driver(&sdhci_of_driver);
+}
+module_exit(sdhci_of_exit);
+
+MODULE_DESCRIPTION("Secure Digital Host Controller Interface OF driver");
+MODULE_AUTHOR("Xiaobo Xie <X.Xie@freescale.com>, "
+	      "Anton Vorontsov <avorontsov@ru.mvista.com>");
+MODULE_LICENSE("GPL");
diff --git a/drivers/mmc/host/sdhci.c b/drivers/mmc/host/sdhci.c
index accb592764ed..30d8e3d4e6fd 100644
--- a/drivers/mmc/host/sdhci.c
+++ b/drivers/mmc/host/sdhci.c
@@ -48,35 +48,35 @@ static void sdhci_dumpregs(struct sdhci_host *host)
 	printk(KERN_DEBUG DRIVER_NAME ": ============== REGISTER DUMP ==============\n");
 
 	printk(KERN_DEBUG DRIVER_NAME ": Sys addr: 0x%08x | Version:  0x%08x\n",
-		readl(host->ioaddr + SDHCI_DMA_ADDRESS),
-		readw(host->ioaddr + SDHCI_HOST_VERSION));
+		sdhci_readl(host, SDHCI_DMA_ADDRESS),
+		sdhci_readw(host, SDHCI_HOST_VERSION));
 	printk(KERN_DEBUG DRIVER_NAME ": Blk size: 0x%08x | Blk cnt:  0x%08x\n",
-		readw(host->ioaddr + SDHCI_BLOCK_SIZE),
-		readw(host->ioaddr + SDHCI_BLOCK_COUNT));
+		sdhci_readw(host, SDHCI_BLOCK_SIZE),
+		sdhci_readw(host, SDHCI_BLOCK_COUNT));
 	printk(KERN_DEBUG DRIVER_NAME ": Argument: 0x%08x | Trn mode: 0x%08x\n",
-		readl(host->ioaddr + SDHCI_ARGUMENT),
-		readw(host->ioaddr + SDHCI_TRANSFER_MODE));
+		sdhci_readl(host, SDHCI_ARGUMENT),
+		sdhci_readw(host, SDHCI_TRANSFER_MODE));
 	printk(KERN_DEBUG DRIVER_NAME ": Present:  0x%08x | Host ctl: 0x%08x\n",
-		readl(host->ioaddr + SDHCI_PRESENT_STATE),
-		readb(host->ioaddr + SDHCI_HOST_CONTROL));
+		sdhci_readl(host, SDHCI_PRESENT_STATE),
+		sdhci_readb(host, SDHCI_HOST_CONTROL));
 	printk(KERN_DEBUG DRIVER_NAME ": Power:    0x%08x | Blk gap:  0x%08x\n",
-		readb(host->ioaddr + SDHCI_POWER_CONTROL),
-		readb(host->ioaddr + SDHCI_BLOCK_GAP_CONTROL));
+		sdhci_readb(host, SDHCI_POWER_CONTROL),
+		sdhci_readb(host, SDHCI_BLOCK_GAP_CONTROL));
 	printk(KERN_DEBUG DRIVER_NAME ": Wake-up:  0x%08x | Clock:    0x%08x\n",
-		readb(host->ioaddr + SDHCI_WAKE_UP_CONTROL),
-		readw(host->ioaddr + SDHCI_CLOCK_CONTROL));
+		sdhci_readb(host, SDHCI_WAKE_UP_CONTROL),
+		sdhci_readw(host, SDHCI_CLOCK_CONTROL));
 	printk(KERN_DEBUG DRIVER_NAME ": Timeout:  0x%08x | Int stat: 0x%08x\n",
-		readb(host->ioaddr + SDHCI_TIMEOUT_CONTROL),
-		readl(host->ioaddr + SDHCI_INT_STATUS));
+		sdhci_readb(host, SDHCI_TIMEOUT_CONTROL),
+		sdhci_readl(host, SDHCI_INT_STATUS));
 	printk(KERN_DEBUG DRIVER_NAME ": Int enab: 0x%08x | Sig enab: 0x%08x\n",
-		readl(host->ioaddr + SDHCI_INT_ENABLE),
-		readl(host->ioaddr + SDHCI_SIGNAL_ENABLE));
+		sdhci_readl(host, SDHCI_INT_ENABLE),
+		sdhci_readl(host, SDHCI_SIGNAL_ENABLE));
 	printk(KERN_DEBUG DRIVER_NAME ": AC12 err: 0x%08x | Slot int: 0x%08x\n",
-		readw(host->ioaddr + SDHCI_ACMD12_ERR),
-		readw(host->ioaddr + SDHCI_SLOT_INT_STATUS));
+		sdhci_readw(host, SDHCI_ACMD12_ERR),
+		sdhci_readw(host, SDHCI_SLOT_INT_STATUS));
 	printk(KERN_DEBUG DRIVER_NAME ": Caps:     0x%08x | Max curr: 0x%08x\n",
-		readl(host->ioaddr + SDHCI_CAPABILITIES),
-		readl(host->ioaddr + SDHCI_MAX_CURRENT));
+		sdhci_readl(host, SDHCI_CAPABILITIES),
+		sdhci_readl(host, SDHCI_MAX_CURRENT));
 
 	printk(KERN_DEBUG DRIVER_NAME ": ===========================================\n");
 }
@@ -87,17 +87,65 @@ static void sdhci_dumpregs(struct sdhci_host *host)
  *                                                                           *
 \*****************************************************************************/
 
+static void sdhci_clear_set_irqs(struct sdhci_host *host, u32 clear, u32 set)
+{
+	u32 ier;
+
+	ier = sdhci_readl(host, SDHCI_INT_ENABLE);
+	ier &= ~clear;
+	ier |= set;
+	sdhci_writel(host, ier, SDHCI_INT_ENABLE);
+	sdhci_writel(host, ier, SDHCI_SIGNAL_ENABLE);
+}
+
+static void sdhci_unmask_irqs(struct sdhci_host *host, u32 irqs)
+{
+	sdhci_clear_set_irqs(host, 0, irqs);
+}
+
+static void sdhci_mask_irqs(struct sdhci_host *host, u32 irqs)
+{
+	sdhci_clear_set_irqs(host, irqs, 0);
+}
+
+static void sdhci_set_card_detection(struct sdhci_host *host, bool enable)
+{
+	u32 irqs = SDHCI_INT_CARD_REMOVE | SDHCI_INT_CARD_INSERT;
+
+	if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
+		return;
+
+	if (enable)
+		sdhci_unmask_irqs(host, irqs);
+	else
+		sdhci_mask_irqs(host, irqs);
+}
+
+static void sdhci_enable_card_detection(struct sdhci_host *host)
+{
+	sdhci_set_card_detection(host, true);
+}
+
+static void sdhci_disable_card_detection(struct sdhci_host *host)
+{
+	sdhci_set_card_detection(host, false);
+}
+
 static void sdhci_reset(struct sdhci_host *host, u8 mask)
 {
 	unsigned long timeout;
+	u32 uninitialized_var(ier);
 
 	if (host->quirks & SDHCI_QUIRK_NO_CARD_NO_RESET) {
-		if (!(readl(host->ioaddr + SDHCI_PRESENT_STATE) &
+		if (!(sdhci_readl(host, SDHCI_PRESENT_STATE) &
 			SDHCI_CARD_PRESENT))
 			return;
 	}
 
-	writeb(mask, host->ioaddr + SDHCI_SOFTWARE_RESET);
+	if (host->quirks & SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET)
+		ier = sdhci_readl(host, SDHCI_INT_ENABLE);
+
+	sdhci_writeb(host, mask, SDHCI_SOFTWARE_RESET);
 
 	if (mask & SDHCI_RESET_ALL)
 		host->clock = 0;
@@ -106,7 +154,7 @@ static void sdhci_reset(struct sdhci_host *host, u8 mask)
 	timeout = 100;
 
 	/* hw clears the bit when it's done */
-	while (readb(host->ioaddr + SDHCI_SOFTWARE_RESET) & mask) {
+	while (sdhci_readb(host, SDHCI_SOFTWARE_RESET) & mask) {
 		if (timeout == 0) {
 			printk(KERN_ERR "%s: Reset 0x%x never completed.\n",
 				mmc_hostname(host->mmc), (int)mask);
@@ -116,42 +164,44 @@ static void sdhci_reset(struct sdhci_host *host, u8 mask)
 		timeout--;
 		mdelay(1);
 	}
+
+	if (host->quirks & SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET)
+		sdhci_clear_set_irqs(host, SDHCI_INT_ALL_MASK, ier);
 }
 
 static void sdhci_init(struct sdhci_host *host)
 {
-	u32 intmask;
-
 	sdhci_reset(host, SDHCI_RESET_ALL);
 
-	intmask = SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT |
+	sdhci_clear_set_irqs(host, SDHCI_INT_ALL_MASK,
+		SDHCI_INT_BUS_POWER | SDHCI_INT_DATA_END_BIT |
 		SDHCI_INT_DATA_CRC | SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_INDEX |
 		SDHCI_INT_END_BIT | SDHCI_INT_CRC | SDHCI_INT_TIMEOUT |
-		SDHCI_INT_CARD_REMOVE | SDHCI_INT_CARD_INSERT |
-		SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL |
-		SDHCI_INT_DMA_END | SDHCI_INT_DATA_END | SDHCI_INT_RESPONSE |
-		SDHCI_INT_ADMA_ERROR;
+		SDHCI_INT_DATA_END | SDHCI_INT_RESPONSE);
+}
 
-	writel(intmask, host->ioaddr + SDHCI_INT_ENABLE);
-	writel(intmask, host->ioaddr + SDHCI_SIGNAL_ENABLE);
+static void sdhci_reinit(struct sdhci_host *host)
+{
+	sdhci_init(host);
+	sdhci_enable_card_detection(host);
 }
 
 static void sdhci_activate_led(struct sdhci_host *host)
 {
 	u8 ctrl;
 
-	ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL);
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
 	ctrl |= SDHCI_CTRL_LED;
-	writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL);
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 }
 
 static void sdhci_deactivate_led(struct sdhci_host *host)
 {
 	u8 ctrl;
 
-	ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL);
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
 	ctrl &= ~SDHCI_CTRL_LED;
-	writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL);
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 }
 
 #ifdef SDHCI_USE_LEDS_CLASS
@@ -205,7 +255,7 @@ static void sdhci_read_block_pio(struct sdhci_host *host)
 
 		while (len) {
 			if (chunk == 0) {
-				scratch = readl(host->ioaddr + SDHCI_BUFFER);
+				scratch = sdhci_readl(host, SDHCI_BUFFER);
 				chunk = 4;
 			}
 
@@ -257,7 +307,7 @@ static void sdhci_write_block_pio(struct sdhci_host *host)
 			len--;
 
 			if ((chunk == 4) || ((len == 0) && (blksize == 0))) {
-				writel(scratch, host->ioaddr + SDHCI_BUFFER);
+				sdhci_writel(host, scratch, SDHCI_BUFFER);
 				chunk = 0;
 				scratch = 0;
 			}
@@ -292,7 +342,10 @@ static void sdhci_transfer_pio(struct sdhci_host *host)
 		(host->data->blocks == 1))
 		mask = ~0;
 
-	while (readl(host->ioaddr + SDHCI_PRESENT_STATE) & mask) {
+	while (sdhci_readl(host, SDHCI_PRESENT_STATE) & mask) {
+		if (host->quirks & SDHCI_QUIRK_PIO_NEEDS_DELAY)
+			udelay(100);
+
 		if (host->data->flags & MMC_DATA_READ)
 			sdhci_read_block_pio(host);
 		else
@@ -561,6 +614,17 @@ static u8 sdhci_calc_timeout(struct sdhci_host *host, struct mmc_data *data)
 	return count;
 }
 
+static void sdhci_set_transfer_irqs(struct sdhci_host *host)
+{
+	u32 pio_irqs = SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL;
+	u32 dma_irqs = SDHCI_INT_DMA_END | SDHCI_INT_ADMA_ERROR;
+
+	if (host->flags & SDHCI_REQ_USE_DMA)
+		sdhci_clear_set_irqs(host, pio_irqs, dma_irqs);
+	else
+		sdhci_clear_set_irqs(host, dma_irqs, pio_irqs);
+}
+
 static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data)
 {
 	u8 count;
@@ -581,7 +645,7 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data)
 	host->data_early = 0;
 
 	count = sdhci_calc_timeout(host, data);
-	writeb(count, host->ioaddr + SDHCI_TIMEOUT_CONTROL);
+	sdhci_writeb(host, count, SDHCI_TIMEOUT_CONTROL);
 
 	if (host->flags & SDHCI_USE_DMA)
 		host->flags |= SDHCI_REQ_USE_DMA;
@@ -661,8 +725,8 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data)
 				WARN_ON(1);
 				host->flags &= ~SDHCI_REQ_USE_DMA;
 			} else {
-				writel(host->adma_addr,
-					host->ioaddr + SDHCI_ADMA_ADDRESS);
+				sdhci_writel(host, host->adma_addr,
+					SDHCI_ADMA_ADDRESS);
 			}
 		} else {
 			int sg_cnt;
@@ -681,8 +745,8 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data)
 				host->flags &= ~SDHCI_REQ_USE_DMA;
 			} else {
 				WARN_ON(sg_cnt != 1);
-				writel(sg_dma_address(data->sg),
-					host->ioaddr + SDHCI_DMA_ADDRESS);
+				sdhci_writel(host, sg_dma_address(data->sg),
+					SDHCI_DMA_ADDRESS);
 			}
 		}
 	}
@@ -693,14 +757,14 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data)
 	 * is ADMA.
 	 */
 	if (host->version >= SDHCI_SPEC_200) {
-		ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL);
+		ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
 		ctrl &= ~SDHCI_CTRL_DMA_MASK;
 		if ((host->flags & SDHCI_REQ_USE_DMA) &&
 			(host->flags & SDHCI_USE_ADMA))
 			ctrl |= SDHCI_CTRL_ADMA32;
 		else
 			ctrl |= SDHCI_CTRL_SDMA;
-		writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL);
+		sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 	}
 
 	if (!(host->flags & SDHCI_REQ_USE_DMA)) {
@@ -709,10 +773,11 @@ static void sdhci_prepare_data(struct sdhci_host *host, struct mmc_data *data)
 		host->blocks = data->blocks;
 	}
 
+	sdhci_set_transfer_irqs(host);
+
 	/* We do not handle DMA boundaries, so set it to max (512 KiB) */
-	writew(SDHCI_MAKE_BLKSZ(7, data->blksz),
-		host->ioaddr + SDHCI_BLOCK_SIZE);
-	writew(data->blocks, host->ioaddr + SDHCI_BLOCK_COUNT);
+	sdhci_writew(host, SDHCI_MAKE_BLKSZ(7, data->blksz), SDHCI_BLOCK_SIZE);
+	sdhci_writew(host, data->blocks, SDHCI_BLOCK_COUNT);
 }
 
 static void sdhci_set_transfer_mode(struct sdhci_host *host,
@@ -733,7 +798,7 @@ static void sdhci_set_transfer_mode(struct sdhci_host *host,
 	if (host->flags & SDHCI_REQ_USE_DMA)
 		mode |= SDHCI_TRNS_DMA;
 
-	writew(mode, host->ioaddr + SDHCI_TRANSFER_MODE);
+	sdhci_writew(host, mode, SDHCI_TRANSFER_MODE);
 }
 
 static void sdhci_finish_data(struct sdhci_host *host)
@@ -802,7 +867,7 @@ static void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 	if (host->mrq->data && (cmd == host->mrq->data->stop))
 		mask &= ~SDHCI_DATA_INHIBIT;
 
-	while (readl(host->ioaddr + SDHCI_PRESENT_STATE) & mask) {
+	while (sdhci_readl(host, SDHCI_PRESENT_STATE) & mask) {
 		if (timeout == 0) {
 			printk(KERN_ERR "%s: Controller never released "
 				"inhibit bit(s).\n", mmc_hostname(host->mmc));
@@ -821,7 +886,7 @@ static void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 
 	sdhci_prepare_data(host, cmd->data);
 
-	writel(cmd->arg, host->ioaddr + SDHCI_ARGUMENT);
+	sdhci_writel(host, cmd->arg, SDHCI_ARGUMENT);
 
 	sdhci_set_transfer_mode(host, cmd->data);
 
@@ -849,8 +914,7 @@ static void sdhci_send_command(struct sdhci_host *host, struct mmc_command *cmd)
 	if (cmd->data)
 		flags |= SDHCI_CMD_DATA;
 
-	writew(SDHCI_MAKE_CMD(cmd->opcode, flags),
-		host->ioaddr + SDHCI_COMMAND);
+	sdhci_writew(host, SDHCI_MAKE_CMD(cmd->opcode, flags), SDHCI_COMMAND);
 }
 
 static void sdhci_finish_command(struct sdhci_host *host)
@@ -863,15 +927,15 @@ static void sdhci_finish_command(struct sdhci_host *host)
 		if (host->cmd->flags & MMC_RSP_136) {
 			/* CRC is stripped so we need to do some shifting. */
 			for (i = 0;i < 4;i++) {
-				host->cmd->resp[i] = readl(host->ioaddr +
+				host->cmd->resp[i] = sdhci_readl(host,
 					SDHCI_RESPONSE + (3-i)*4) << 8;
 				if (i != 3)
 					host->cmd->resp[i] |=
-						readb(host->ioaddr +
+						sdhci_readb(host,
 						SDHCI_RESPONSE + (3-i)*4-1);
 			}
 		} else {
-			host->cmd->resp[0] = readl(host->ioaddr + SDHCI_RESPONSE);
+			host->cmd->resp[0] = sdhci_readl(host, SDHCI_RESPONSE);
 		}
 	}
 
@@ -895,7 +959,13 @@ static void sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 	if (clock == host->clock)
 		return;
 
-	writew(0, host->ioaddr + SDHCI_CLOCK_CONTROL);
+	if (host->ops->set_clock) {
+		host->ops->set_clock(host, clock);
+		if (host->quirks & SDHCI_QUIRK_NONSTANDARD_CLOCK)
+			return;
+	}
+
+	sdhci_writew(host, 0, SDHCI_CLOCK_CONTROL);
 
 	if (clock == 0)
 		goto out;
@@ -908,11 +978,11 @@ static void sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 
 	clk = div << SDHCI_DIVIDER_SHIFT;
 	clk |= SDHCI_CLOCK_INT_EN;
-	writew(clk, host->ioaddr + SDHCI_CLOCK_CONTROL);
+	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
 
 	/* Wait max 10 ms */
 	timeout = 10;
-	while (!((clk = readw(host->ioaddr + SDHCI_CLOCK_CONTROL))
+	while (!((clk = sdhci_readw(host, SDHCI_CLOCK_CONTROL))
 		& SDHCI_CLOCK_INT_STABLE)) {
 		if (timeout == 0) {
 			printk(KERN_ERR "%s: Internal clock never "
@@ -925,7 +995,7 @@ static void sdhci_set_clock(struct sdhci_host *host, unsigned int clock)
 	}
 
 	clk |= SDHCI_CLOCK_CARD_EN;
-	writew(clk, host->ioaddr + SDHCI_CLOCK_CONTROL);
+	sdhci_writew(host, clk, SDHCI_CLOCK_CONTROL);
 
 out:
 	host->clock = clock;
@@ -939,7 +1009,7 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned short power)
 		return;
 
 	if (power == (unsigned short)-1) {
-		writeb(0, host->ioaddr + SDHCI_POWER_CONTROL);
+		sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
 		goto out;
 	}
 
@@ -948,7 +1018,7 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned short power)
 	 * a new value. Some controllers don't seem to like this though.
 	 */
 	if (!(host->quirks & SDHCI_QUIRK_SINGLE_POWER_WRITE))
-		writeb(0, host->ioaddr + SDHCI_POWER_CONTROL);
+		sdhci_writeb(host, 0, SDHCI_POWER_CONTROL);
 
 	pwr = SDHCI_POWER_ON;
 
@@ -973,10 +1043,9 @@ static void sdhci_set_power(struct sdhci_host *host, unsigned short power)
 	 * and set turn on power at the same time, so set the voltage first.
 	 */
 	if ((host->quirks & SDHCI_QUIRK_NO_SIMULT_VDD_AND_POWER))
-		writeb(pwr & ~SDHCI_POWER_ON,
-				host->ioaddr + SDHCI_POWER_CONTROL);
+		sdhci_writeb(host, pwr & ~SDHCI_POWER_ON, SDHCI_POWER_CONTROL);
 
-	writeb(pwr, host->ioaddr + SDHCI_POWER_CONTROL);
+	sdhci_writeb(host, pwr, SDHCI_POWER_CONTROL);
 
 out:
 	host->power = power;
@@ -991,6 +1060,7 @@ out:
 static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 {
 	struct sdhci_host *host;
+	bool present;
 	unsigned long flags;
 
 	host = mmc_priv(mmc);
@@ -1005,8 +1075,14 @@ static void sdhci_request(struct mmc_host *mmc, struct mmc_request *mrq)
 
 	host->mrq = mrq;
 
-	if (!(readl(host->ioaddr + SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT)
-		|| (host->flags & SDHCI_DEVICE_DEAD)) {
+	/* If polling, assume that the card is always present. */
+	if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
+		present = true;
+	else
+		present = sdhci_readl(host, SDHCI_PRESENT_STATE) &
+				SDHCI_CARD_PRESENT;
+
+	if (!present || host->flags & SDHCI_DEVICE_DEAD) {
 		host->mrq->cmd->error = -ENOMEDIUM;
 		tasklet_schedule(&host->finish_tasklet);
 	} else
@@ -1034,8 +1110,8 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	 * Should clear out any weird states.
 	 */
 	if (ios->power_mode == MMC_POWER_OFF) {
-		writel(0, host->ioaddr + SDHCI_SIGNAL_ENABLE);
-		sdhci_init(host);
+		sdhci_writel(host, 0, SDHCI_SIGNAL_ENABLE);
+		sdhci_reinit(host);
 	}
 
 	sdhci_set_clock(host, ios->clock);
@@ -1045,7 +1121,7 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	else
 		sdhci_set_power(host, ios->vdd);
 
-	ctrl = readb(host->ioaddr + SDHCI_HOST_CONTROL);
+	ctrl = sdhci_readb(host, SDHCI_HOST_CONTROL);
 
 	if (ios->bus_width == MMC_BUS_WIDTH_4)
 		ctrl |= SDHCI_CTRL_4BITBUS;
@@ -1057,7 +1133,7 @@ static void sdhci_set_ios(struct mmc_host *mmc, struct mmc_ios *ios)
 	else
 		ctrl &= ~SDHCI_CTRL_HISPD;
 
-	writeb(ctrl, host->ioaddr + SDHCI_HOST_CONTROL);
+	sdhci_writeb(host, ctrl, SDHCI_HOST_CONTROL);
 
 	/*
 	 * Some (ENE) controllers go apeshit on some ios operation,
@@ -1085,10 +1161,12 @@ static int sdhci_get_ro(struct mmc_host *mmc)
 	if (host->flags & SDHCI_DEVICE_DEAD)
 		present = 0;
 	else
-		present = readl(host->ioaddr + SDHCI_PRESENT_STATE);
+		present = sdhci_readl(host, SDHCI_PRESENT_STATE);
 
 	spin_unlock_irqrestore(&host->lock, flags);
 
+	if (host->quirks & SDHCI_QUIRK_INVERTED_WRITE_PROTECT)
+		return !!(present & SDHCI_WRITE_PROTECT);
 	return !(present & SDHCI_WRITE_PROTECT);
 }
 
@@ -1096,7 +1174,6 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 {
 	struct sdhci_host *host;
 	unsigned long flags;
-	u32 ier;
 
 	host = mmc_priv(mmc);
 
@@ -1105,15 +1182,10 @@ static void sdhci_enable_sdio_irq(struct mmc_host *mmc, int enable)
 	if (host->flags & SDHCI_DEVICE_DEAD)
 		goto out;
 
-	ier = readl(host->ioaddr + SDHCI_INT_ENABLE);
-
-	ier &= ~SDHCI_INT_CARD_INT;
 	if (enable)
-		ier |= SDHCI_INT_CARD_INT;
-
-	writel(ier, host->ioaddr + SDHCI_INT_ENABLE);
-	writel(ier, host->ioaddr + SDHCI_SIGNAL_ENABLE);
-
+		sdhci_unmask_irqs(host, SDHCI_INT_CARD_INT);
+	else
+		sdhci_mask_irqs(host, SDHCI_INT_CARD_INT);
 out:
 	mmiowb();
 
@@ -1142,7 +1214,7 @@ static void sdhci_tasklet_card(unsigned long param)
 
 	spin_lock_irqsave(&host->lock, flags);
 
-	if (!(readl(host->ioaddr + SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT)) {
+	if (!(sdhci_readl(host, SDHCI_PRESENT_STATE) & SDHCI_CARD_PRESENT)) {
 		if (host->mrq) {
 			printk(KERN_ERR "%s: Card removed during transfer!\n",
 				mmc_hostname(host->mmc));
@@ -1346,8 +1418,8 @@ static void sdhci_data_irq(struct sdhci_host *host, u32 intmask)
 		 * we need to at least restart the transfer.
 		 */
 		if (intmask & SDHCI_INT_DMA_END)
-			writel(readl(host->ioaddr + SDHCI_DMA_ADDRESS),
-				host->ioaddr + SDHCI_DMA_ADDRESS);
+			sdhci_writel(host, sdhci_readl(host, SDHCI_DMA_ADDRESS),
+				SDHCI_DMA_ADDRESS);
 
 		if (intmask & SDHCI_INT_DATA_END) {
 			if (host->cmd) {
@@ -1373,7 +1445,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 
 	spin_lock(&host->lock);
 
-	intmask = readl(host->ioaddr + SDHCI_INT_STATUS);
+	intmask = sdhci_readl(host, SDHCI_INT_STATUS);
 
 	if (!intmask || intmask == 0xffffffff) {
 		result = IRQ_NONE;
@@ -1384,22 +1456,22 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 		mmc_hostname(host->mmc), intmask);
 
 	if (intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE)) {
-		writel(intmask & (SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE),
-			host->ioaddr + SDHCI_INT_STATUS);
+		sdhci_writel(host, intmask & (SDHCI_INT_CARD_INSERT |
+			SDHCI_INT_CARD_REMOVE), SDHCI_INT_STATUS);
 		tasklet_schedule(&host->card_tasklet);
 	}
 
 	intmask &= ~(SDHCI_INT_CARD_INSERT | SDHCI_INT_CARD_REMOVE);
 
 	if (intmask & SDHCI_INT_CMD_MASK) {
-		writel(intmask & SDHCI_INT_CMD_MASK,
-			host->ioaddr + SDHCI_INT_STATUS);
+		sdhci_writel(host, intmask & SDHCI_INT_CMD_MASK,
+			SDHCI_INT_STATUS);
 		sdhci_cmd_irq(host, intmask & SDHCI_INT_CMD_MASK);
 	}
 
 	if (intmask & SDHCI_INT_DATA_MASK) {
-		writel(intmask & SDHCI_INT_DATA_MASK,
-			host->ioaddr + SDHCI_INT_STATUS);
+		sdhci_writel(host, intmask & SDHCI_INT_DATA_MASK,
+			SDHCI_INT_STATUS);
 		sdhci_data_irq(host, intmask & SDHCI_INT_DATA_MASK);
 	}
 
@@ -1410,7 +1482,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 	if (intmask & SDHCI_INT_BUS_POWER) {
 		printk(KERN_ERR "%s: Card is consuming too much power!\n",
 			mmc_hostname(host->mmc));
-		writel(SDHCI_INT_BUS_POWER, host->ioaddr + SDHCI_INT_STATUS);
+		sdhci_writel(host, SDHCI_INT_BUS_POWER, SDHCI_INT_STATUS);
 	}
 
 	intmask &= ~SDHCI_INT_BUS_POWER;
@@ -1425,7 +1497,7 @@ static irqreturn_t sdhci_irq(int irq, void *dev_id)
 			mmc_hostname(host->mmc), intmask);
 		sdhci_dumpregs(host);
 
-		writel(intmask, host->ioaddr + SDHCI_INT_STATUS);
+		sdhci_writel(host, intmask, SDHCI_INT_STATUS);
 	}
 
 	result = IRQ_HANDLED;
@@ -1455,6 +1527,8 @@ int sdhci_suspend_host(struct sdhci_host *host, pm_message_t state)
 {
 	int ret;
 
+	sdhci_disable_card_detection(host);
+
 	ret = mmc_suspend_host(host->mmc, state);
 	if (ret)
 		return ret;
@@ -1487,6 +1561,8 @@ int sdhci_resume_host(struct sdhci_host *host)
 	if (ret)
 		return ret;
 
+	sdhci_enable_card_detection(host);
+
 	return 0;
 }
 
@@ -1537,7 +1613,7 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	sdhci_reset(host, SDHCI_RESET_ALL);
 
-	host->version = readw(host->ioaddr + SDHCI_HOST_VERSION);
+	host->version = sdhci_readw(host, SDHCI_HOST_VERSION);
 	host->version = (host->version & SDHCI_SPEC_VER_MASK)
 				>> SDHCI_SPEC_VER_SHIFT;
 	if (host->version > SDHCI_SPEC_200) {
@@ -1546,7 +1622,7 @@ int sdhci_add_host(struct sdhci_host *host)
 			host->version);
 	}
 
-	caps = readl(host->ioaddr + SDHCI_CAPABILITIES);
+	caps = sdhci_readl(host, SDHCI_CAPABILITIES);
 
 	if (host->quirks & SDHCI_QUIRK_FORCE_DMA)
 		host->flags |= SDHCI_USE_DMA;
@@ -1614,19 +1690,27 @@ int sdhci_add_host(struct sdhci_host *host)
 
 	host->max_clk =
 		(caps & SDHCI_CLOCK_BASE_MASK) >> SDHCI_CLOCK_BASE_SHIFT;
+	host->max_clk *= 1000000;
 	if (host->max_clk == 0) {
-		printk(KERN_ERR "%s: Hardware doesn't specify base clock "
-			"frequency.\n", mmc_hostname(mmc));
-		return -ENODEV;
+		if (!host->ops->get_max_clock) {
+			printk(KERN_ERR
+			       "%s: Hardware doesn't specify base clock "
+			       "frequency.\n", mmc_hostname(mmc));
+			return -ENODEV;
+		}
+		host->max_clk = host->ops->get_max_clock(host);
 	}
-	host->max_clk *= 1000000;
 
 	host->timeout_clk =
 		(caps & SDHCI_TIMEOUT_CLK_MASK) >> SDHCI_TIMEOUT_CLK_SHIFT;
 	if (host->timeout_clk == 0) {
-		printk(KERN_ERR "%s: Hardware doesn't specify timeout clock "
-			"frequency.\n", mmc_hostname(mmc));
-		return -ENODEV;
+		if (!host->ops->get_timeout_clock) {
+			printk(KERN_ERR
+			       "%s: Hardware doesn't specify timeout clock "
+			       "frequency.\n", mmc_hostname(mmc));
+			return -ENODEV;
+		}
+		host->timeout_clk = host->ops->get_timeout_clock(host);
 	}
 	if (caps & SDHCI_TIMEOUT_CLK_UNIT)
 		host->timeout_clk *= 1000;
@@ -1642,6 +1726,9 @@ int sdhci_add_host(struct sdhci_host *host)
 	if (caps & SDHCI_CAN_DO_HISPD)
 		mmc->caps |= MMC_CAP_SD_HIGHSPEED;
 
+	if (host->quirks & SDHCI_QUIRK_BROKEN_CARD_DETECTION)
+		mmc->caps |= MMC_CAP_NEEDS_POLL;
+
 	mmc->ocr_avail = 0;
 	if (caps & SDHCI_CAN_VDD_330)
 		mmc->ocr_avail |= MMC_VDD_32_33|MMC_VDD_33_34;
@@ -1690,13 +1777,19 @@ int sdhci_add_host(struct sdhci_host *host)
 	 * Maximum block size. This varies from controller to controller and
 	 * is specified in the capabilities register.
 	 */
-	mmc->max_blk_size = (caps & SDHCI_MAX_BLOCK_MASK) >> SDHCI_MAX_BLOCK_SHIFT;
-	if (mmc->max_blk_size >= 3) {
-		printk(KERN_WARNING "%s: Invalid maximum block size, "
-			"assuming 512 bytes\n", mmc_hostname(mmc));
-		mmc->max_blk_size = 512;
-	} else
-		mmc->max_blk_size = 512 << mmc->max_blk_size;
+	if (host->quirks & SDHCI_QUIRK_FORCE_BLK_SZ_2048) {
+		mmc->max_blk_size = 2;
+	} else {
+		mmc->max_blk_size = (caps & SDHCI_MAX_BLOCK_MASK) >>
+				SDHCI_MAX_BLOCK_SHIFT;
+		if (mmc->max_blk_size >= 3) {
+			printk(KERN_WARNING "%s: Invalid maximum block size, "
+				"assuming 512 bytes\n", mmc_hostname(mmc));
+			mmc->max_blk_size = 0;
+		}
+	}
+
+	mmc->max_blk_size = 512 << mmc->max_blk_size;
 
 	/*
 	 * Maximum block count.
@@ -1746,6 +1839,8 @@ int sdhci_add_host(struct sdhci_host *host)
 		(host->flags & SDHCI_USE_ADMA)?"A":"",
 		(host->flags & SDHCI_USE_DMA)?"DMA":"PIO");
 
+	sdhci_enable_card_detection(host);
+
 	return 0;
 
 #ifdef SDHCI_USE_LEDS_CLASS
@@ -1782,6 +1877,8 @@ void sdhci_remove_host(struct sdhci_host *host, int dead)
 		spin_unlock_irqrestore(&host->lock, flags);
 	}
 
+	sdhci_disable_card_detection(host);
+
 	mmc_remove_host(host->mmc);
 
 #ifdef SDHCI_USE_LEDS_CLASS
diff --git a/drivers/mmc/host/sdhci.h b/drivers/mmc/host/sdhci.h
index 43c37c68d07a..f20a834f4309 100644
--- a/drivers/mmc/host/sdhci.h
+++ b/drivers/mmc/host/sdhci.h
@@ -10,6 +10,9 @@
  */
 
 #include <linux/scatterlist.h>
+#include <linux/compiler.h>
+#include <linux/types.h>
+#include <linux/io.h>
 
 /*
  * Controller registers
@@ -123,6 +126,7 @@
 		SDHCI_INT_DATA_AVAIL | SDHCI_INT_SPACE_AVAIL | \
 		SDHCI_INT_DATA_TIMEOUT | SDHCI_INT_DATA_CRC | \
 		SDHCI_INT_DATA_END_BIT)
+#define SDHCI_INT_ALL_MASK	((unsigned int)-1)
 
 #define SDHCI_ACMD12_ERR	0x3C
 
@@ -210,6 +214,18 @@ struct sdhci_host {
 #define SDHCI_QUIRK_BROKEN_SMALL_PIO			(1<<13)
 /* Controller does not provide transfer-complete interrupt when not busy */
 #define SDHCI_QUIRK_NO_BUSY_IRQ				(1<<14)
+/* Controller has unreliable card detection */
+#define SDHCI_QUIRK_BROKEN_CARD_DETECTION		(1<<15)
+/* Controller reports inverted write-protect state */
+#define SDHCI_QUIRK_INVERTED_WRITE_PROTECT		(1<<16)
+/* Controller has nonstandard clock management */
+#define SDHCI_QUIRK_NONSTANDARD_CLOCK			(1<<17)
+/* Controller does not like fast PIO transfers */
+#define SDHCI_QUIRK_PIO_NEEDS_DELAY			(1<<18)
+/* Controller losing signal/interrupt enable states after reset */
+#define SDHCI_QUIRK_RESTORE_IRQS_AFTER_RESET		(1<<19)
+/* Controller has to be forced to use block size of 2048 bytes */
+#define SDHCI_QUIRK_FORCE_BLK_SZ_2048			(1<<20)
 
 	int			irq;		/* Device IRQ */
 	void __iomem *		ioaddr;		/* Mapped address */
@@ -267,9 +283,105 @@ struct sdhci_host {
 
 
 struct sdhci_ops {
+#ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS
+	u32		(*readl)(struct sdhci_host *host, int reg);
+	u16		(*readw)(struct sdhci_host *host, int reg);
+	u8		(*readb)(struct sdhci_host *host, int reg);
+	void		(*writel)(struct sdhci_host *host, u32 val, int reg);
+	void		(*writew)(struct sdhci_host *host, u16 val, int reg);
+	void		(*writeb)(struct sdhci_host *host, u8 val, int reg);
+#endif
+
+	void	(*set_clock)(struct sdhci_host *host, unsigned int clock);
+
 	int		(*enable_dma)(struct sdhci_host *host);
+	unsigned int	(*get_max_clock)(struct sdhci_host *host);
+	unsigned int	(*get_timeout_clock)(struct sdhci_host *host);
 };
 
+#ifdef CONFIG_MMC_SDHCI_IO_ACCESSORS
+
+static inline void sdhci_writel(struct sdhci_host *host, u32 val, int reg)
+{
+	if (unlikely(host->ops->writel))
+		host->ops->writel(host, val, reg);
+	else
+		writel(val, host->ioaddr + reg);
+}
+
+static inline void sdhci_writew(struct sdhci_host *host, u16 val, int reg)
+{
+	if (unlikely(host->ops->writew))
+		host->ops->writew(host, val, reg);
+	else
+		writew(val, host->ioaddr + reg);
+}
+
+static inline void sdhci_writeb(struct sdhci_host *host, u8 val, int reg)
+{
+	if (unlikely(host->ops->writeb))
+		host->ops->writeb(host, val, reg);
+	else
+		writeb(val, host->ioaddr + reg);
+}
+
+static inline u32 sdhci_readl(struct sdhci_host *host, int reg)
+{
+	if (unlikely(host->ops->readl))
+		return host->ops->readl(host, reg);
+	else
+		return readl(host->ioaddr + reg);
+}
+
+static inline u16 sdhci_readw(struct sdhci_host *host, int reg)
+{
+	if (unlikely(host->ops->readw))
+		return host->ops->readw(host, reg);
+	else
+		return readw(host->ioaddr + reg);
+}
+
+static inline u8 sdhci_readb(struct sdhci_host *host, int reg)
+{
+	if (unlikely(host->ops->readb))
+		return host->ops->readb(host, reg);
+	else
+		return readb(host->ioaddr + reg);
+}
+
+#else
+
+static inline void sdhci_writel(struct sdhci_host *host, u32 val, int reg)
+{
+	writel(val, host->ioaddr + reg);
+}
+
+static inline void sdhci_writew(struct sdhci_host *host, u16 val, int reg)
+{
+	writew(val, host->ioaddr + reg);
+}
+
+static inline void sdhci_writeb(struct sdhci_host *host, u8 val, int reg)
+{
+	writeb(val, host->ioaddr + reg);
+}
+
+static inline u32 sdhci_readl(struct sdhci_host *host, int reg)
+{
+	return readl(host->ioaddr + reg);
+}
+
+static inline u16 sdhci_readw(struct sdhci_host *host, int reg)
+{
+	return readw(host->ioaddr + reg);
+}
+
+static inline u8 sdhci_readb(struct sdhci_host *host, int reg)
+{
+	return readb(host->ioaddr + reg);
+}
+
+#endif /* CONFIG_MMC_SDHCI_IO_ACCESSORS */
 
 extern struct sdhci_host *sdhci_alloc_host(struct device *dev,
 	size_t priv_size);
diff --git a/drivers/mmc/host/tmio_mmc.c b/drivers/mmc/host/tmio_mmc.c
index 6a7a61904833..63fbd5b7d312 100644
--- a/drivers/mmc/host/tmio_mmc.c
+++ b/drivers/mmc/host/tmio_mmc.c
@@ -568,11 +568,11 @@ static int __devinit tmio_mmc_probe(struct platform_device *dev)
 	host->mmc = mmc;
 	platform_set_drvdata(dev, mmc);
 
-	host->ctl = ioremap(res_ctl->start, res_ctl->end - res_ctl->start);
+	host->ctl = ioremap(res_ctl->start, resource_size(res_ctl));
 	if (!host->ctl)
 		goto host_free;
 
-	host->cnf = ioremap(res_cnf->start, res_cnf->end - res_cnf->start);
+	host->cnf = ioremap(res_cnf->start, resource_size(res_cnf));
 	if (!host->cnf)
 		goto unmap_ctl;
 
@@ -650,10 +650,10 @@ static int __devexit tmio_mmc_remove(struct platform_device *dev)
 	if (mmc) {
 		struct tmio_mmc_host *host = mmc_priv(mmc);
 		mmc_remove_host(mmc);
-		mmc_free_host(mmc);
 		free_irq(host->irq, host);
 		iounmap(host->ctl);
 		iounmap(host->cnf);
+		mmc_free_host(mmc);
 	}
 
 	return 0;
diff --git a/drivers/mmc/host/tmio_mmc.h b/drivers/mmc/host/tmio_mmc.h
index ba2b4240a86a..9c831ab2ece6 100644
--- a/drivers/mmc/host/tmio_mmc.h
+++ b/drivers/mmc/host/tmio_mmc.h
@@ -8,6 +8,9 @@
  * published by the Free Software Foundation.
  *
  */
+
+#include <linux/highmem.h>
+
 #define CNF_CMD     0x04
 #define CNF_CTL_BASE   0x10
 #define CNF_INT_PIN  0x3d
diff --git a/drivers/mtd/maps/pxa2xx-flash.c b/drivers/mtd/maps/pxa2xx-flash.c
index e9026cb1c5b2..572d32fdf38a 100644
--- a/drivers/mtd/maps/pxa2xx-flash.c
+++ b/drivers/mtd/maps/pxa2xx-flash.c
@@ -117,7 +117,7 @@ static int __init pxa2xx_flash_probe(struct platform_device *pdev)
 	return 0;
 }
 
-static int __exit pxa2xx_flash_remove(struct platform_device *dev)
+static int __devexit pxa2xx_flash_remove(struct platform_device *dev)
 {
 	struct pxa2xx_flash_info *info = platform_get_drvdata(dev);
 
diff --git a/drivers/mtd/nand/diskonchip.c b/drivers/mtd/nand/diskonchip.c
index e4226e02d63e..e51c1ed7ac18 100644
--- a/drivers/mtd/nand/diskonchip.c
+++ b/drivers/mtd/nand/diskonchip.c
@@ -1773,4 +1773,4 @@ module_exit(cleanup_nanddoc);
 
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>");
-MODULE_DESCRIPTION("M-Systems DiskOnChip 2000, Millennium and Millennium Plus device driver\n");
+MODULE_DESCRIPTION("M-Systems DiskOnChip 2000, Millennium and Millennium Plus device driver");
diff --git a/drivers/mtd/nand/nand_base.c b/drivers/mtd/nand/nand_base.c
index 0c3afccde8a2..5f71371eb1b0 100644
--- a/drivers/mtd/nand/nand_base.c
+++ b/drivers/mtd/nand/nand_base.c
@@ -2720,14 +2720,14 @@ int nand_scan_tail(struct mtd_info *mtd)
 	return chip->scan_bbt(mtd);
 }
 
-/* module_text_address() isn't exported, and it's mostly a pointless
+/* is_module_text_address() isn't exported, and it's mostly a pointless
    test if this is a module _anyway_ -- they'd have to try _really_ hard
    to call us from in-kernel code if the core NAND support is modular. */
 #ifdef MODULE
 #define caller_is_module() (1)
 #else
 #define caller_is_module() \
-	module_text_address((unsigned long)__builtin_return_address(0))
+	is_module_text_address((unsigned long)__builtin_return_address(0))
 #endif
 
 /**
diff --git a/drivers/mtd/tests/mtd_oobtest.c b/drivers/mtd/tests/mtd_oobtest.c
index afbc3f8126db..a18e8d2f2557 100644
--- a/drivers/mtd/tests/mtd_oobtest.c
+++ b/drivers/mtd/tests/mtd_oobtest.c
@@ -136,7 +136,7 @@ static int write_eraseblock(int ebnum)
 		ops.ooblen    = use_len;
 		ops.oobretlen = 0;
 		ops.ooboffs   = use_offset;
-		ops.datbuf    = 0;
+		ops.datbuf    = NULL;
 		ops.oobbuf    = writebuf;
 		err = mtd->write_oob(mtd, addr, &ops);
 		if (err || ops.oobretlen != use_len) {
@@ -189,7 +189,7 @@ static int verify_eraseblock(int ebnum)
 		ops.ooblen    = use_len;
 		ops.oobretlen = 0;
 		ops.ooboffs   = use_offset;
-		ops.datbuf    = 0;
+		ops.datbuf    = NULL;
 		ops.oobbuf    = readbuf;
 		err = mtd->read_oob(mtd, addr, &ops);
 		if (err || ops.oobretlen != use_len) {
@@ -216,7 +216,7 @@ static int verify_eraseblock(int ebnum)
 			ops.ooblen    = mtd->ecclayout->oobavail;
 			ops.oobretlen = 0;
 			ops.ooboffs   = 0;
-			ops.datbuf    = 0;
+			ops.datbuf    = NULL;
 			ops.oobbuf    = readbuf;
 			err = mtd->read_oob(mtd, addr, &ops);
 			if (err || ops.oobretlen != mtd->ecclayout->oobavail) {
@@ -281,7 +281,7 @@ static int verify_eraseblock_in_one_go(int ebnum)
 	ops.ooblen    = len;
 	ops.oobretlen = 0;
 	ops.ooboffs   = 0;
-	ops.datbuf    = 0;
+	ops.datbuf    = NULL;
 	ops.oobbuf    = readbuf;
 	err = mtd->read_oob(mtd, addr, &ops);
 	if (err || ops.oobretlen != len) {
@@ -522,7 +522,7 @@ static int __init mtd_oobtest_init(void)
 	ops.ooblen    = 1;
 	ops.oobretlen = 0;
 	ops.ooboffs   = mtd->ecclayout->oobavail;
-	ops.datbuf    = 0;
+	ops.datbuf    = NULL;
 	ops.oobbuf    = writebuf;
 	printk(PRINT_PREF "attempting to start write past end of OOB\n");
 	printk(PRINT_PREF "an error is expected...\n");
@@ -542,7 +542,7 @@ static int __init mtd_oobtest_init(void)
 	ops.ooblen    = 1;
 	ops.oobretlen = 0;
 	ops.ooboffs   = mtd->ecclayout->oobavail;
-	ops.datbuf    = 0;
+	ops.datbuf    = NULL;
 	ops.oobbuf    = readbuf;
 	printk(PRINT_PREF "attempting to start read past end of OOB\n");
 	printk(PRINT_PREF "an error is expected...\n");
@@ -566,7 +566,7 @@ static int __init mtd_oobtest_init(void)
 		ops.ooblen    = mtd->ecclayout->oobavail + 1;
 		ops.oobretlen = 0;
 		ops.ooboffs   = 0;
-		ops.datbuf    = 0;
+		ops.datbuf    = NULL;
 		ops.oobbuf    = writebuf;
 		printk(PRINT_PREF "attempting to write past end of device\n");
 		printk(PRINT_PREF "an error is expected...\n");
@@ -586,7 +586,7 @@ static int __init mtd_oobtest_init(void)
 		ops.ooblen    = mtd->ecclayout->oobavail + 1;
 		ops.oobretlen = 0;
 		ops.ooboffs   = 0;
-		ops.datbuf    = 0;
+		ops.datbuf    = NULL;
 		ops.oobbuf    = readbuf;
 		printk(PRINT_PREF "attempting to read past end of device\n");
 		printk(PRINT_PREF "an error is expected...\n");
@@ -610,7 +610,7 @@ static int __init mtd_oobtest_init(void)
 		ops.ooblen    = mtd->ecclayout->oobavail;
 		ops.oobretlen = 0;
 		ops.ooboffs   = 1;
-		ops.datbuf    = 0;
+		ops.datbuf    = NULL;
 		ops.oobbuf    = writebuf;
 		printk(PRINT_PREF "attempting to write past end of device\n");
 		printk(PRINT_PREF "an error is expected...\n");
@@ -630,7 +630,7 @@ static int __init mtd_oobtest_init(void)
 		ops.ooblen    = mtd->ecclayout->oobavail;
 		ops.oobretlen = 0;
 		ops.ooboffs   = 1;
-		ops.datbuf    = 0;
+		ops.datbuf    = NULL;
 		ops.oobbuf    = readbuf;
 		printk(PRINT_PREF "attempting to read past end of device\n");
 		printk(PRINT_PREF "an error is expected...\n");
@@ -670,7 +670,7 @@ static int __init mtd_oobtest_init(void)
 			ops.ooblen    = sz;
 			ops.oobretlen = 0;
 			ops.ooboffs   = 0;
-			ops.datbuf    = 0;
+			ops.datbuf    = NULL;
 			ops.oobbuf    = writebuf;
 			err = mtd->write_oob(mtd, addr, &ops);
 			if (err)
@@ -698,7 +698,7 @@ static int __init mtd_oobtest_init(void)
 		ops.ooblen    = mtd->ecclayout->oobavail * 2;
 		ops.oobretlen = 0;
 		ops.ooboffs   = 0;
-		ops.datbuf    = 0;
+		ops.datbuf    = NULL;
 		ops.oobbuf    = readbuf;
 		err = mtd->read_oob(mtd, addr, &ops);
 		if (err)
diff --git a/drivers/mtd/tests/mtd_readtest.c b/drivers/mtd/tests/mtd_readtest.c
index 645e77fdc63d..79fc4530987b 100644
--- a/drivers/mtd/tests/mtd_readtest.c
+++ b/drivers/mtd/tests/mtd_readtest.c
@@ -71,7 +71,7 @@ static int read_eraseblock_by_page(int ebnum)
 			ops.ooblen    = mtd->oobsize;
 			ops.oobretlen = 0;
 			ops.ooboffs   = 0;
-			ops.datbuf    = 0;
+			ops.datbuf    = NULL;
 			ops.oobbuf    = oobbuf;
 			ret = mtd->read_oob(mtd, addr, &ops);
 			if (ret || ops.oobretlen != mtd->oobsize) {
diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig
index f062b424704e..16899eee397e 100644
--- a/drivers/net/Kconfig
+++ b/drivers/net/Kconfig
@@ -974,7 +974,7 @@ config ENC28J60_WRITEVERIFY
 
 config ETHOC
 	tristate "OpenCores 10/100 Mbps Ethernet MAC support"
-	depends on NET_ETHERNET
+	depends on NET_ETHERNET && HAS_IOMEM
 	select MII
 	select PHYLIB
 	help
@@ -2547,6 +2547,23 @@ config S2IO
 	  More specific information on configuring the driver is in 
 	  <file:Documentation/networking/s2io.txt>.
 
+config VXGE
+	tristate "Neterion X3100 Series 10GbE PCIe Server Adapter"
+	depends on PCI && INET
+	---help---
+	  This driver supports Neterion Inc's X3100 Series 10 GbE PCIe
+	  I/O Virtualized Server Adapter.
+	  More specific information on configuring the driver is in
+	  <file:Documentation/networking/vxge.txt>.
+
+config VXGE_DEBUG_TRACE_ALL
+	bool "Enabling All Debug trace statments in driver"
+	default n
+	depends on VXGE
+	---help---
+	  Say Y here if you want to enabling all the debug trace statements in
+	  driver. By  default only few debug trace statements are enabled.
+
 config MYRI10GE
 	tristate "Myricom Myri-10G Ethernet support"
 	depends on PCI && INET
diff --git a/drivers/net/Makefile b/drivers/net/Makefile
index 98409c9dd445..edc9a0d6171d 100644
--- a/drivers/net/Makefile
+++ b/drivers/net/Makefile
@@ -220,6 +220,7 @@ obj-$(CONFIG_R8169) += r8169.o
 obj-$(CONFIG_AMD8111_ETH) += amd8111e.o
 obj-$(CONFIG_IBMVETH) += ibmveth.o
 obj-$(CONFIG_S2IO) += s2io.o
+obj-$(CONFIG_VXGE) += vxge/
 obj-$(CONFIG_MYRI10GE) += myri10ge/
 obj-$(CONFIG_SMC91X) += smc91x.o
 obj-$(CONFIG_SMC911X) += smc911x.o
diff --git a/drivers/net/dm9000.c b/drivers/net/dm9000.c
index 254ec62b5f58..d8350860c0f8 100644
--- a/drivers/net/dm9000.c
+++ b/drivers/net/dm9000.c
@@ -559,7 +559,7 @@ static void dm9000_show_carrier(board_info_t *db,
 static void
 dm9000_poll_work(struct work_struct *w)
 {
-	struct delayed_work *dw = container_of(w, struct delayed_work, work);
+	struct delayed_work *dw = to_delayed_work(w);
 	board_info_t *db = container_of(dw, board_info_t, phy_poll);
 	struct net_device *ndev = db->ndev;
 
diff --git a/drivers/net/dnet.c b/drivers/net/dnet.c
index db1e31f95200..33fa9eee4cac 100644
--- a/drivers/net/dnet.c
+++ b/drivers/net/dnet.c
@@ -8,7 +8,6 @@
  * it under the terms of the GNU General Public License version 2 as
  * published by the Free Software Foundation.
  */
-#include <linux/version.h>
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/moduleparam.h>
diff --git a/drivers/net/fec_mpc52xx.c b/drivers/net/fec_mpc52xx.c
index 049b0a7e01f3..8bbe7f617994 100644
--- a/drivers/net/fec_mpc52xx.c
+++ b/drivers/net/fec_mpc52xx.c
@@ -129,7 +129,8 @@ static void mpc52xx_fec_free_rx_buffers(struct net_device *dev, struct bcom_task
 		struct sk_buff *skb;
 
 		skb = bcom_retrieve_buffer(s, NULL, (struct bcom_bd **)&bd);
-		dma_unmap_single(&dev->dev, bd->skb_pa, skb->len, DMA_FROM_DEVICE);
+		dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len,
+				 DMA_FROM_DEVICE);
 		kfree_skb(skb);
 	}
 }
@@ -150,7 +151,7 @@ static int mpc52xx_fec_alloc_rx_buffers(struct net_device *dev, struct bcom_task
 		bd = (struct bcom_fec_bd *)bcom_prepare_next_buffer(rxtsk);
 
 		bd->status = FEC_RX_BUFFER_SIZE;
-		bd->skb_pa = dma_map_single(&dev->dev, skb->data,
+		bd->skb_pa = dma_map_single(dev->dev.parent, skb->data,
 				FEC_RX_BUFFER_SIZE, DMA_FROM_DEVICE);
 
 		bcom_submit_next_buffer(rxtsk, skb);
@@ -270,15 +271,6 @@ static void mpc52xx_fec_phy_stop(struct net_device *dev)
 	phy_write(priv->phydev, MII_BMCR, BMCR_PDOWN);
 }
 
-static int mpc52xx_fec_phy_mii_ioctl(struct mpc52xx_fec_priv *priv,
-		struct mii_ioctl_data *mii_data, int cmd)
-{
-	if (!priv->phydev)
-		return -ENOTSUPP;
-
-	return phy_mii_ioctl(priv->phydev, mii_data, cmd);
-}
-
 static void mpc52xx_fec_phy_hw_init(struct mpc52xx_fec_priv *priv)
 {
 	struct mpc52xx_fec __iomem *fec = priv->fec;
@@ -370,7 +362,7 @@ static int mpc52xx_fec_close(struct net_device *dev)
  * invariant will hold if you make sure that the netif_*_queue()
  * calls are done at the proper times.
  */
-static int mpc52xx_fec_hard_start_xmit(struct sk_buff *skb, struct net_device *dev)
+static int mpc52xx_fec_start_xmit(struct sk_buff *skb, struct net_device *dev)
 {
 	struct mpc52xx_fec_priv *priv = netdev_priv(dev);
 	struct bcom_fec_bd *bd;
@@ -378,7 +370,7 @@ static int mpc52xx_fec_hard_start_xmit(struct sk_buff *skb, struct net_device *d
 	if (bcom_queue_full(priv->tx_dmatsk)) {
 		if (net_ratelimit())
 			dev_err(&dev->dev, "transmit queue overrun\n");
-		return 1;
+		return NETDEV_TX_BUSY;
 	}
 
 	spin_lock_irq(&priv->lock);
@@ -388,7 +380,8 @@ static int mpc52xx_fec_hard_start_xmit(struct sk_buff *skb, struct net_device *d
 		bcom_prepare_next_buffer(priv->tx_dmatsk);
 
 	bd->status = skb->len | BCOM_FEC_TX_BD_TFD | BCOM_FEC_TX_BD_TC;
-	bd->skb_pa = dma_map_single(&dev->dev, skb->data, skb->len, DMA_TO_DEVICE);
+	bd->skb_pa = dma_map_single(dev->dev.parent, skb->data, skb->len,
+				    DMA_TO_DEVICE);
 
 	bcom_submit_next_buffer(priv->tx_dmatsk, skb);
 
@@ -398,7 +391,7 @@ static int mpc52xx_fec_hard_start_xmit(struct sk_buff *skb, struct net_device *d
 
 	spin_unlock_irq(&priv->lock);
 
-	return 0;
+	return NETDEV_TX_OK;
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
@@ -430,7 +423,8 @@ static irqreturn_t mpc52xx_fec_tx_interrupt(int irq, void *dev_id)
 		struct bcom_fec_bd *bd;
 		skb = bcom_retrieve_buffer(priv->tx_dmatsk, NULL,
 				(struct bcom_bd **)&bd);
-		dma_unmap_single(&dev->dev, bd->skb_pa, skb->len, DMA_TO_DEVICE);
+		dma_unmap_single(dev->dev.parent, bd->skb_pa, skb->len,
+				 DMA_TO_DEVICE);
 
 		dev_kfree_skb_irq(skb);
 	}
@@ -455,7 +449,8 @@ static irqreturn_t mpc52xx_fec_rx_interrupt(int irq, void *dev_id)
 
 		rskb = bcom_retrieve_buffer(priv->rx_dmatsk, &status,
 				(struct bcom_bd **)&bd);
-		dma_unmap_single(&dev->dev, bd->skb_pa, rskb->len, DMA_FROM_DEVICE);
+		dma_unmap_single(dev->dev.parent, bd->skb_pa, rskb->len,
+				 DMA_FROM_DEVICE);
 
 		/* Test for errors in received frame */
 		if (status & BCOM_FEC_RX_BD_ERRORS) {
@@ -464,7 +459,8 @@ static irqreturn_t mpc52xx_fec_rx_interrupt(int irq, void *dev_id)
 				bcom_prepare_next_buffer(priv->rx_dmatsk);
 
 			bd->status = FEC_RX_BUFFER_SIZE;
-			bd->skb_pa = dma_map_single(&dev->dev, rskb->data,
+			bd->skb_pa = dma_map_single(dev->dev.parent,
+					rskb->data,
 					FEC_RX_BUFFER_SIZE, DMA_FROM_DEVICE);
 
 			bcom_submit_next_buffer(priv->rx_dmatsk, rskb);
@@ -499,7 +495,7 @@ static irqreturn_t mpc52xx_fec_rx_interrupt(int irq, void *dev_id)
 			bcom_prepare_next_buffer(priv->rx_dmatsk);
 
 		bd->status = FEC_RX_BUFFER_SIZE;
-		bd->skb_pa = dma_map_single(&dev->dev, skb->data,
+		bd->skb_pa = dma_map_single(dev->dev.parent, skb->data,
 				FEC_RX_BUFFER_SIZE, DMA_FROM_DEVICE);
 
 		bcom_submit_next_buffer(priv->rx_dmatsk, skb);
@@ -847,12 +843,20 @@ static void mpc52xx_fec_get_drvinfo(struct net_device *dev,
 static int mpc52xx_fec_get_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 {
 	struct mpc52xx_fec_priv *priv = netdev_priv(dev);
+
+	if (!priv->phydev)
+		return -ENODEV;
+
 	return phy_ethtool_gset(priv->phydev, cmd);
 }
 
 static int mpc52xx_fec_set_settings(struct net_device *dev, struct ethtool_cmd *cmd)
 {
 	struct mpc52xx_fec_priv *priv = netdev_priv(dev);
+
+	if (!priv->phydev)
+		return -ENODEV;
+
 	return phy_ethtool_sset(priv->phydev, cmd);
 }
 
@@ -882,9 +886,28 @@ static int mpc52xx_fec_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
 {
 	struct mpc52xx_fec_priv *priv = netdev_priv(dev);
 
-	return mpc52xx_fec_phy_mii_ioctl(priv, if_mii(rq), cmd);
+	if (!priv->phydev)
+		return -ENOTSUPP;
+
+	return phy_mii_ioctl(priv->phydev, if_mii(rq), cmd);
 }
 
+static const struct net_device_ops mpc52xx_fec_netdev_ops = {
+	.ndo_open = mpc52xx_fec_open,
+	.ndo_stop = mpc52xx_fec_close,
+	.ndo_start_xmit = mpc52xx_fec_start_xmit,
+	.ndo_set_multicast_list = mpc52xx_fec_set_multicast_list,
+	.ndo_set_mac_address = mpc52xx_fec_set_mac_address,
+	.ndo_validate_addr = eth_validate_addr,
+	.ndo_do_ioctl = mpc52xx_fec_ioctl,
+	.ndo_change_mtu = eth_change_mtu,
+	.ndo_tx_timeout = mpc52xx_fec_tx_timeout,
+	.ndo_get_stats = mpc52xx_fec_get_stats,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller = mpc52xx_fec_poll_controller,
+#endif
+};
+
 /* ======================================================================== */
 /* OF Driver                                                                */
 /* ======================================================================== */
@@ -929,22 +952,10 @@ mpc52xx_fec_probe(struct of_device *op, const struct of_device_id *match)
 		return -EBUSY;
 
 	/* Init ether ndev with what we have */
-	ndev->open		= mpc52xx_fec_open;
-	ndev->stop		= mpc52xx_fec_close;
-	ndev->hard_start_xmit	= mpc52xx_fec_hard_start_xmit;
-	ndev->do_ioctl		= mpc52xx_fec_ioctl;
+	ndev->netdev_ops	= &mpc52xx_fec_netdev_ops;
 	ndev->ethtool_ops	= &mpc52xx_fec_ethtool_ops;
-	ndev->get_stats		= mpc52xx_fec_get_stats;
-	ndev->set_mac_address	= mpc52xx_fec_set_mac_address;
-	ndev->set_multicast_list = mpc52xx_fec_set_multicast_list;
-	ndev->tx_timeout	= mpc52xx_fec_tx_timeout;
 	ndev->watchdog_timeo	= FEC_WATCHDOG_TIMEOUT;
 	ndev->base_addr		= mem.start;
-#ifdef CONFIG_NET_POLL_CONTROLLER
-	ndev->poll_controller = mpc52xx_fec_poll_controller;
-#endif
-
-	priv->t_irq = priv->r_irq = ndev->irq = NO_IRQ; /* IRQ are free for now */
 
 	spin_lock_init(&priv->lock);
 
diff --git a/drivers/net/fsl_pq_mdio.c b/drivers/net/fsl_pq_mdio.c
index b3079a5a7f2b..aa1eb88c21fc 100644
--- a/drivers/net/fsl_pq_mdio.c
+++ b/drivers/net/fsl_pq_mdio.c
@@ -204,6 +204,7 @@ void fsl_pq_mdio_bus_name(char *name, struct device_node *np)
 	snprintf(name, MII_BUS_ID_SIZE, "%s@%llx", np->name,
 		(unsigned long long)taddr);
 }
+EXPORT_SYMBOL_GPL(fsl_pq_mdio_bus_name);
 
 /* Scan the bus in reverse, looking for an empty spot */
 static int fsl_pq_mdio_find_free(struct mii_bus *new_bus)
@@ -387,7 +388,7 @@ static int fsl_pq_mdio_probe(struct of_device *ofdev,
 	 * The TBIPHY-only buses will find PHYs at every address,
 	 * so we mask them all but the TBI
 	 */
-	if (!of_device_is_compatible(np, "fsl,gianfar-mdio"))
+	if (of_device_is_compatible(np, "fsl,gianfar-tbi"))
 		new_bus->phy_mask = ~(1 << tbiaddr);
 
 	err = mdiobus_register(new_bus);
diff --git a/drivers/net/gianfar.h b/drivers/net/gianfar.h
index dd499d7cde26..0642d52aef5c 100644
--- a/drivers/net/gianfar.h
+++ b/drivers/net/gianfar.h
@@ -45,7 +45,6 @@
 #include <linux/crc32.h>
 #include <linux/workqueue.h>
 #include <linux/ethtool.h>
-#include <linux/fsl_devices.h>
 
 /* The maximum number of packets to be handled in one call of gfar_poll */
 #define GFAR_DEV_WEIGHT 64
diff --git a/drivers/net/hamradio/yam.c b/drivers/net/hamradio/yam.c
index 500a40b2afe7..b06691937ce9 100644
--- a/drivers/net/hamradio/yam.c
+++ b/drivers/net/hamradio/yam.c
@@ -55,6 +55,8 @@
 #include <asm/system.h>
 #include <linux/interrupt.h>
 #include <linux/ioport.h>
+#include <linux/firmware.h>
+#include <linux/platform_device.h>
 
 #include <linux/netdevice.h>
 #include <linux/if_arp.h>
@@ -71,8 +73,6 @@
 #include <linux/init.h>
 
 #include <linux/yam.h>
-#include "yam9600.h"
-#include "yam1200.h"
 
 /* --------------------------------------------------------------------- */
 
@@ -82,6 +82,9 @@ static const char yam_drvinfo[] __initdata = KERN_INFO \
 
 /* --------------------------------------------------------------------- */
 
+#define FIRMWARE_9600	"yam/9600.bin"
+#define FIRMWARE_1200	"yam/1200.bin"
+
 #define YAM_9600	1
 #define YAM_1200	2
 
@@ -342,9 +345,51 @@ static int fpga_write(int iobase, unsigned char wrd)
 	return 0;
 }
 
-static unsigned char *add_mcs(unsigned char *bits, int bitrate)
+/*
+ * predef should be 0 for loading user defined mcs
+ * predef should be YAM_1200 for loading predef 1200 mcs
+ * predef should be YAM_9600 for loading predef 9600 mcs
+ */
+static unsigned char *add_mcs(unsigned char *bits, int bitrate,
+			      unsigned int predef)
 {
+	const char *fw_name[2] = {FIRMWARE_9600, FIRMWARE_1200};
+	const struct firmware *fw;
+	struct platform_device *pdev;
 	struct yam_mcs *p;
+	int err;
+
+	switch (predef) {
+	case 0:
+		fw = NULL;
+		break;
+	case YAM_1200:
+	case YAM_9600:
+		predef--;
+		pdev = platform_device_register_simple("yam", 0, NULL, 0);
+		if (IS_ERR(pdev)) {
+			printk(KERN_ERR "yam: Failed to register firmware\n");
+			return NULL;
+		}
+		err = request_firmware(&fw, fw_name[predef], &pdev->dev);
+		platform_device_unregister(pdev);
+		if (err) {
+			printk(KERN_ERR "Failed to load firmware \"%s\"\n",
+			       fw_name[predef]);
+			return NULL;
+		}
+		if (fw->size != YAM_FPGA_SIZE) {
+			printk(KERN_ERR "Bogus length %zu in firmware \"%s\"\n",
+			       fw->size, fw_name[predef]);
+			release_firmware(fw);
+			return NULL;
+		}
+		bits = (unsigned char *)fw->data;
+		break;
+	default:
+		printk(KERN_ERR "yam: Invalid predef number %u\n", predef);
+		return NULL;
+	}
 
 	/* If it already exists, replace the bit data */
 	p = yam_data;
@@ -359,6 +404,7 @@ static unsigned char *add_mcs(unsigned char *bits, int bitrate)
 	/* Allocate a new mcs */
 	if ((p = kmalloc(sizeof(struct yam_mcs), GFP_KERNEL)) == NULL) {
 		printk(KERN_WARNING "YAM: no memory to allocate mcs\n");
+		release_firmware(fw);
 		return NULL;
 	}
 	memcpy(p->bits, bits, YAM_FPGA_SIZE);
@@ -366,6 +412,7 @@ static unsigned char *add_mcs(unsigned char *bits, int bitrate)
 	p->next = yam_data;
 	yam_data = p;
 
+	release_firmware(fw);
 	return p->bits;
 }
 
@@ -383,9 +430,11 @@ static unsigned char *get_mcs(int bitrate)
 	/* Load predefined mcs data */
 	switch (bitrate) {
 	case 1200:
-		return add_mcs(bits_1200, bitrate);
+		/* setting predef as YAM_1200 for loading predef 1200 mcs */
+		return add_mcs(NULL, bitrate, YAM_1200);
 	default:
-		return add_mcs(bits_9600, bitrate);
+		/* setting predef as YAM_9600 for loading predef 9600 mcs */
+		return add_mcs(NULL, bitrate, YAM_9600);
 	}
 }
 
@@ -936,7 +985,8 @@ static int yam_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd)
 			kfree(ym);
 			return -EINVAL;
 		}
-		add_mcs(ym->bits, ym->bitrate);
+		/* setting predef as 0 for loading userdefined mcs data */
+		add_mcs(ym->bits, ym->bitrate, 0);
 		kfree(ym);
 		break;
 
@@ -1159,6 +1209,8 @@ static void __exit yam_cleanup_driver(void)
 MODULE_AUTHOR("Frederic Rible F1OAT frible@teaser.fr");
 MODULE_DESCRIPTION("Yam amateur radio modem driver");
 MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(FIRMWARE_1200);
+MODULE_FIRMWARE(FIRMWARE_9600);
 
 module_init(yam_init_driver);
 module_exit(yam_cleanup_driver);
diff --git a/drivers/net/hamradio/yam1200.h b/drivers/net/hamradio/yam1200.h
deleted file mode 100644
index 53ca8a3903a7..000000000000
--- a/drivers/net/hamradio/yam1200.h
+++ /dev/null
@@ -1,343 +0,0 @@
-/*
- *
- * File yam1k2b5.mcs converted to h format by mcs2h
- *
- * (C) F6FBB 1998
- *
- * Tue Aug 25 20:24:08 1998
- *
- */
-
-static unsigned char bits_1200[]= {
-0xff,0xf2,0x00,0xa5,0xad,0xff,0xfe,0x9f,0xff,0xef,0xf3,0xcb,0xff,0xdb,0xfc,0xf2,
-0xff,0xf6,0xff,0x3c,0xbf,0xfd,0xbf,0xdf,0x6e,0x3f,0x6f,0xf1,0x7d,0xb4,0xfd,0xbf,
-0xdf,0x6f,0x3f,0x6f,0xf7,0x0b,0xff,0xdb,0xfd,0xf2,0xff,0xf6,0xff,0xff,0xff,0xff,
-0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xdf,0xff,0xff,0xff,0xef,0xff,0xff,0xff,
-0xfd,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xbf,
-0xff,0xff,0xf7,0xff,0xff,0xfb,0xff,0xff,0xff,0xfc,0xff,0xfe,0xff,0xff,0xff,0xf0,
-0x5f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xf7,0xff,0xff,0xff,0xf1,0xff,0xff,0xfe,0x7f,0xbf,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf7,0xff,0xfb,0xff,0xff,0xff,0xf0,0x9f,
-0xff,0xff,0xff,0xfe,0xff,0xfd,0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xf7,0xff,
-0xff,0xff,0xfb,0xff,0xfb,0xff,0xff,0xff,0xf0,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xf7,0xff,0xff,0xfb,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xef,0xff,0xf0,0x5f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xef,0xff,0xff,0xfb,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xbf,0xff,0xff,0xdf,0xf7,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xfb,0xfe,0xff,0xff,0xff,0xff,0xff,0xf0,0xff,0xff,0xff,
-0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xeb,
-0xff,0xff,0xff,0xfd,0xff,0xbf,0xf1,0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xfb,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x6f,0xff,0xff,0xff,
-0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xf7,0xff,0xff,0xf1,0xff,0xff,0xf7,0xbf,0xe7,0xff,0xff,0xff,0xff,0xfb,
-0xff,0xff,0xff,0xff,0xff,0xff,0x77,0xff,0xff,0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x1f,0xff,0xff,0xff,0xfe,0xdb,
-0xff,0xff,0xf5,0xa5,0xfd,0x4b,0x6e,0xef,0x33,0x32,0xdd,0xd3,0x4a,0xd6,0x92,0xfe,
-0xb3,0x3f,0xbd,0xf1,0xfa,0xdb,0xfe,0xf7,0xf6,0x96,0xbd,0xbd,0xff,0xbd,0xff,0xed,
-0x7f,0x6b,0x7f,0xfb,0xdf,0xfe,0xfb,0xfe,0x90,0xcf,0xff,0xff,0xff,0xfe,0xbe,0xef,
-0xff,0xff,0xdb,0x5f,0xf6,0xff,0xf6,0x8f,0xfd,0xa5,0xdd,0xff,0xff,0xff,0xff,0x6f,
-0x7f,0xdb,0xf1,0xfc,0xbf,0xff,0x6f,0xff,0xef,0xfc,0x5b,0x5d,0xda,0xdf,0xf4,0xff,
-0xf2,0xff,0xfd,0xbf,0xff,0xff,0xff,0xd0,0x1f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,
-0xff,0xfb,0xef,0xb7,0xfc,0x33,0xff,0xfb,0xff,0x04,0x6a,0xf3,0x3c,0x36,0xff,0xf0,
-0x0f,0xf1,0x0f,0xff,0xff,0xff,0xf3,0x15,0x72,0x0f,0xf1,0x6f,0xff,0xfe,0x94,0x3f,
-0xff,0xff,0xff,0x7b,0xff,0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf0,
-0xf7,0xef,0xb7,0xfc,0x33,0xff,0xff,0xff,0x04,0x6a,0xf3,0x3c,0x36,0xff,0xf0,0x0f,
-0xf1,0x0f,0xff,0xff,0xff,0xf3,0x15,0x73,0x8f,0xf2,0x6f,0xff,0xfe,0x94,0x3f,0xff,
-0xff,0xff,0x7d,0x9f,0xff,0xf0,0x0f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0x9e,
-0xff,0xfc,0xef,0xd3,0xfb,0xff,0x7f,0xf5,0x5f,0xfe,0x59,0xff,0xff,0xff,0xfc,0xf1,
-0xfe,0x7f,0xff,0xff,0xfa,0x17,0xff,0xe7,0xef,0xef,0xff,0xff,0x3f,0xf1,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,0xf5,0xff,0xbf,0xff,0xfc,0xea,
-0xff,0xf0,0xff,0xff,0xbf,0xf9,0x3f,0xb1,0xef,0xff,0xd7,0xff,0xfb,0xff,0xf0,0xff,
-0xff,0xf3,0xff,0xdf,0xff,0x7b,0xff,0xfd,0xff,0xf6,0xff,0xbf,0xff,0xff,0xbf,0xff,
-0xff,0xff,0xda,0xf0,0xff,0xff,0xff,0xff,0xfe,0xf2,0xc0,0x01,0x00,0x00,0x02,0x02,
-0x02,0x02,0x00,0x40,0x40,0x40,0x10,0x00,0x00,0x00,0x20,0x00,0x00,0x01,0x00,0x00,
-0x00,0x00,0x00,0x00,0x19,0x00,0x04,0x04,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x10,
-0x00,0x3c,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xfb,0xff,0xfd,0xff,
-0xff,0x7f,0xff,0xff,0xbf,0xff,0xef,0xff,0xff,0xfd,0xff,0xff,0xf1,0xff,0xdf,0xff,
-0xff,0xff,0xff,0xff,0xff,0xbf,0xfe,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xdf,
-0xdb,0xf0,0x6f,0xff,0xff,0xff,0xfe,0xf0,0xbf,0xdf,0xff,0x7f,0xff,0xff,0xff,0xff,
-0xdf,0xdf,0xff,0xef,0xff,0x9e,0xef,0xff,0xff,0x7f,0xff,0xf1,0xef,0xff,0xff,0xff,
-0xf7,0xfa,0xbf,0xff,0xff,0xfe,0x47,0xef,0xff,0xbd,0xf6,0xff,0xff,0xdf,0xf5,0xf0,
-0xf0,0xef,0xff,0xff,0xff,0xfe,0xf8,0x30,0x00,0x00,0x00,0x04,0x00,0x01,0x02,0x08,
-0x16,0x00,0x00,0x00,0x80,0x00,0x01,0x02,0x00,0x80,0x01,0x0c,0x02,0x00,0x00,0x01,
-0x00,0x00,0x20,0x00,0x00,0x06,0x00,0x20,0x00,0x10,0x00,0x14,0x00,0x04,0xc1,0xf0,
-0x2f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xfb,0xff,0xff,0x7f,
-0xec,0xff,0xff,0xfa,0xff,0xbf,0xff,0x6f,0xff,0xe1,0xff,0xff,0xff,0xff,0xbd,0xfe,
-0x46,0xff,0xef,0x7f,0xcd,0xdf,0xff,0xff,0xfd,0xff,0xbd,0xff,0x7f,0x7f,0xf0,0x4f,
-0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x0f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xff,0xfd,0xa4,0xbc,0xcd,0x6d,0x6b,0x6f,0x5b,0xdc,0x33,
-0x5a,0xf6,0xf7,0xf6,0xb3,0x3f,0xbd,0xc1,0xfa,0x5a,0xf6,0xf6,0xb6,0xf7,0xff,0xbd,
-0xbb,0x3c,0xce,0xcf,0x34,0xef,0x33,0xbb,0xcc,0xff,0xff,0xff,0xf0,0x4f,0xff,0xff,
-0xff,0xfe,0xbf,0xff,0xff,0xff,0xdb,0xff,0xf6,0xd6,0xff,0xfd,0xfd,0xbf,0xff,0xad,
-0xbf,0xf9,0x7f,0x6f,0xfc,0xdb,0xf1,0xfd,0xbf,0xff,0x6f,0xff,0xff,0xda,0xdb,0xfc,
-0xdb,0xff,0x76,0x8f,0xf6,0xff,0xcd,0xab,0xfe,0xfb,0xff,0xd0,0xff,0xff,0xff,0xff,
-0xfe,0xff,0x9f,0xff,0xf4,0x20,0xaf,0x6d,0x0b,0xc1,0x7b,0xff,0xff,0xff,0xcb,0xff,
-0x3f,0xf0,0xef,0x7f,0x0f,0xf1,0xc3,0x3c,0xff,0xff,0xff,0xff,0xff,0xff,0xf8,0x0b,
-0x1d,0x6a,0x64,0x05,0x6b,0x99,0x01,0xff,0xfd,0xef,0xf0,0x2f,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xf4,0x00,0x2f,0xcc,0x0b,0xc3,0x7f,0xff,0xff,0xff,0x0a,0xdf,0xbf,
-0xfd,0x7f,0xff,0xff,0xf1,0xc3,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x4a,0x0e,
-0x96,0x64,0x02,0x97,0x99,0x10,0xff,0xff,0xff,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xfe,0x84,0xf9,0xd5,0x27,0xf1,0x7f,0xff,0xf8,0xeb,0xdf,0xf3,0xcf,0x3f,
-0x1f,0xff,0xf7,0x11,0xff,0xcf,0xff,0xfe,0x67,0xff,0xff,0xff,0xff,0xc4,0xff,0xff,
-0xb3,0xa1,0xff,0xf9,0xe0,0xff,0xff,0xff,0xf0,0xef,0xff,0xff,0xff,0xfe,0xf5,0xff,
-0xff,0xfb,0x7f,0xe0,0xff,0xc7,0xfe,0x7f,0x3f,0xff,0xfd,0x77,0x8d,0x7f,0x0f,0xff,
-0xc3,0xff,0xf1,0xbf,0x8f,0xcf,0xff,0xff,0xdd,0x7b,0xff,0xf6,0xfa,0xf7,0xff,0x40,
-0x9f,0xf9,0x7f,0xd8,0xff,0xff,0xfa,0xf0,0x1f,0xff,0xff,0xff,0xfe,0xf1,0xc0,0x00,
-0x00,0x03,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x40,0x00,0x10,0x00,0x00,0x10,
-0x00,0x01,0x00,0x10,0x20,0x20,0x00,0x00,0x10,0x00,0x04,0x01,0x05,0x00,0x00,0x00,
-0x00,0x40,0x40,0x00,0x00,0x3c,0xf0,0x1f,0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,
-0xff,0xff,0xfe,0x7f,0x7f,0xff,0xef,0xff,0xff,0xdf,0xff,0xff,0xdf,0xff,0xef,0xf7,
-0xf1,0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xf7,0xff,0xff,0xff,0xfc,0xfd,0xff,0x7f,
-0x7e,0xff,0xff,0xff,0xdb,0xf0,0x6f,0xff,0xff,0xff,0xfe,0xf0,0xbb,0xff,0xff,0xff,
-0xff,0xff,0xfe,0xeb,0xfd,0x6f,0xff,0xf7,0xfe,0xf5,0x7f,0xff,0xff,0x7f,0xbf,0xb1,
-0xff,0xff,0x9f,0xbf,0xfb,0xff,0xfe,0xff,0xfe,0xff,0xf7,0xeb,0xdf,0xbf,0x5f,0xdd,
-0xff,0xdb,0xfd,0xd0,0xf0,0x6f,0xff,0xff,0xff,0xfe,0xf8,0x30,0x20,0x00,0x42,0x00,
-0x00,0x00,0x30,0x18,0x04,0x08,0x09,0x21,0x82,0x80,0x02,0x00,0x08,0x00,0x01,0x00,
-0x00,0x00,0x0c,0x20,0x10,0x00,0x11,0x00,0x44,0x84,0x00,0x20,0x20,0x84,0x80,0x00,
-0x00,0x00,0xc1,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xff,0xf7,0xff,0xfb,0xdd,0xf9,0xff,
-0xda,0xff,0xdc,0xdd,0xfc,0xfb,0xff,0xbf,0xfb,0x3e,0xd7,0x96,0xfe,0x61,0xf7,0xff,
-0x7f,0xff,0x3f,0xfd,0xff,0xdf,0xcf,0xf7,0xdf,0xf7,0xbf,0xfd,0xff,0xfe,0xef,0xef,
-0xfe,0xff,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xf0,0x2f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf3,0xbd,0xfd,0x4b,0x74,0xcf,
-0x73,0x5b,0xcb,0x3b,0xdf,0xfe,0xf7,0xfe,0xd3,0x75,0xac,0xa1,0xfb,0xdf,0xfe,0xf7,
-0x76,0x96,0xb5,0x24,0xbd,0xa5,0xad,0x49,0x2f,0x69,0x2b,0x52,0x5b,0xbd,0xff,0xff,
-0xf0,0xcf,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xff,0xdb,0xff,0xf6,0xfe,0xff,0xcc,
-0xa7,0xfb,0xad,0xff,0x7f,0x6f,0xff,0x6d,0x7f,0xdb,0xf1,0xfd,0xbf,0xff,0x6f,0xff,
-0x6f,0xff,0xdb,0xff,0xdb,0xff,0xf6,0x97,0xf6,0xff,0xb5,0xb5,0xff,0xff,0xff,0xd0,
-0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfd,0xa5,0xbc,0x43,0xfc,0x7c,0x03,0xe7,
-0xff,0xff,0x20,0xff,0xff,0xff,0xcc,0xfd,0x7d,0xf1,0xff,0xff,0xff,0xff,0xd5,0x59,
-0xba,0x56,0x66,0x6a,0xad,0x9a,0xa9,0x9a,0x97,0xa5,0xaa,0xbb,0xff,0xff,0xf0,0x0f,
-0xff,0xff,0xff,0xfe,0xfe,0xfb,0xff,0xfd,0xf7,0xfd,0x43,0xff,0xfd,0x6b,0xe7,0xff,
-0xff,0xdf,0xff,0xff,0xff,0xff,0xff,0x3f,0xf1,0xff,0xff,0xff,0xff,0xd5,0x59,0xb5,
-0xa6,0x66,0x6a,0xad,0x9a,0xa9,0x99,0x6b,0x5a,0xaa,0xff,0xff,0xb7,0xf0,0x3f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xff,0xfe,0x9c,0xf7,0xfd,0xd2,0x41,0xff,0xff,0xf2,0x7f,
-0x8f,0xff,0xff,0x3d,0xf3,0xff,0x17,0xf1,0xff,0xff,0xff,0xff,0xff,0x7f,0xdf,0xfc,
-0x8f,0x38,0xff,0xef,0x23,0xff,0xfb,0xf7,0xc8,0xff,0xff,0xff,0xf0,0x9f,0xff,0xff,
-0xff,0xfe,0xf5,0x7f,0xff,0xfd,0xff,0xe4,0xff,0xeb,0xff,0xcf,0xbf,0xfa,0xff,0xab,
-0xef,0xff,0xfb,0xff,0xf3,0xfd,0x61,0xff,0xff,0xff,0xff,0xfa,0xff,0xfb,0xfd,0x0d,
-0xff,0xfe,0xff,0x43,0x7f,0xfe,0xbf,0xd0,0xfd,0xff,0xfa,0xf0,0x3f,0xff,0xff,0xff,
-0xfe,0xf3,0xc0,0x00,0x00,0x00,0x02,0x00,0x02,0x01,0x00,0x60,0xc0,0x40,0x00,0x00,
-0x00,0x00,0x34,0x04,0x00,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x08,0x88,0x00,
-0x00,0x03,0x00,0x00,0x40,0x00,0x40,0x00,0x00,0x3c,0xf0,0x3f,0xff,0xff,0xff,0xfe,
-0xfd,0x3f,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,0x7f,0xbf,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xf7,0xf1,0xff,0xff,0xff,0xff,0xff,0xf7,0xff,0xff,0xff,0xfd,0xff,
-0xff,0xff,0xff,0xfe,0xfe,0x5f,0xff,0xff,0xcb,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xf0,
-0xff,0xff,0xfd,0xff,0xef,0xe3,0xde,0xee,0xd9,0xc5,0x93,0xff,0xff,0xfe,0xfe,0xff,
-0xfb,0xee,0xfe,0xf1,0xff,0xff,0xff,0xff,0xff,0xfd,0xff,0xbf,0xf7,0xff,0xff,0x7f,
-0xaf,0xbd,0xdf,0xdf,0xfb,0xf3,0xf3,0xf0,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xf8,0x34,
-0x00,0x06,0x61,0x00,0x18,0x01,0xa0,0x05,0x17,0x00,0x20,0x05,0x28,0x20,0x00,0x00,
-0x05,0x00,0x41,0x00,0x00,0x40,0x00,0x09,0x00,0x01,0x20,0x86,0x82,0x08,0x40,0x03,
-0x80,0x30,0x70,0x08,0x14,0x02,0xc1,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,
-0xff,0xff,0xbd,0xef,0xfb,0xff,0xff,0xfb,0x9c,0x7f,0xef,0xdf,0xff,0xbf,0xeb,0xde,
-0xff,0xc1,0x7f,0xff,0xfb,0x7f,0xff,0xff,0xff,0x5f,0xff,0xff,0xff,0xdf,0xbf,0xef,
-0x3f,0xf7,0x8f,0xef,0x7f,0xff,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xf0,0x3f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xbd,
-0xdf,0xef,0x7d,0x6d,0x2b,0x5a,0x5d,0xd2,0xdf,0xf6,0x92,0xb6,0xb2,0xb3,0xac,0xa1,
-0xfb,0xdf,0xfe,0xf1,0xee,0xf5,0xf6,0xbc,0x6b,0xbd,0x7d,0xaf,0x1a,0xef,0x5f,0x6b,
-0xc6,0xff,0xff,0xff,0xf0,0x5f,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xff,0xdb,0xff,
-0xf6,0xff,0xf6,0xb7,0xfd,0xad,0xfd,0xbf,0xf3,0x6f,0xff,0x6f,0xff,0xdb,0xd1,0xfd,
-0xbf,0xff,0x6f,0xf5,0x6b,0xbc,0x5b,0x3c,0xda,0xef,0x16,0xaf,0x16,0xff,0xcd,0xab,
-0xff,0x6f,0xff,0xd0,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfc,0xbf,0xff,0xff,
-0xff,0x6c,0x03,0x10,0xc1,0xf3,0xff,0xf3,0x3a,0xf3,0xca,0xff,0xaf,0xf1,0xff,0xff,
-0xff,0xff,0xd9,0x96,0xa6,0x65,0xa6,0x66,0x6a,0x95,0x69,0x69,0x6a,0x5a,0x5a,0xff,
-0xff,0x5f,0xf0,0x1f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xbf,0xff,0xff,0xff,
-0xea,0x0f,0x50,0xc3,0xf3,0x7f,0xff,0xf3,0xf3,0xc3,0xff,0xaf,0xf1,0xff,0xff,0xff,
-0xff,0xd9,0x96,0xa6,0x65,0xa6,0x66,0x6a,0x95,0x69,0x69,0x6a,0x5a,0x5a,0xff,0xff,
-0xff,0xf0,0x3f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xd7,0xff,0xff,0x5f,0xc1,
-0x3f,0xf7,0x5e,0xf5,0xce,0x9e,0x5f,0x3f,0x17,0xff,0xf3,0xe1,0xff,0xff,0xff,0xff,
-0xd8,0xff,0xfa,0xfe,0x67,0xff,0xfe,0xbf,0x5a,0xff,0xff,0xaf,0xf5,0xff,0xff,0xff,
-0xf0,0x2f,0xff,0xff,0xff,0xfe,0xf5,0xff,0xff,0xfd,0xff,0xf7,0xff,0xfd,0x4e,0x3d,
-0x3f,0xe7,0x0b,0xbf,0x8f,0xf9,0xff,0xeb,0xe3,0xff,0xe1,0xff,0xff,0xfc,0xff,0xc7,
-0x9f,0xff,0x3e,0x39,0xe5,0xff,0xcf,0x9b,0xf9,0xff,0xff,0xc5,0xff,0xff,0xfa,0xf0,
-0x5f,0xff,0xff,0xff,0xfe,0xf3,0xc0,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x40,0x00,
-0x00,0x00,0x00,0x60,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x00,0x20,0x00,0x20,
-0x00,0x01,0x10,0x08,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x3c,0xf0,0x4f,
-0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xbf,
-0x3f,0xff,0xff,0xbf,0xff,0xff,0xff,0xfb,0xf1,0xff,0xff,0xff,0xff,0xf7,0xff,0xf7,
-0xff,0xed,0xff,0xfb,0xfe,0xff,0x7f,0xff,0x7f,0xdf,0xff,0xff,0xdd,0xf0,0x3f,0xff,
-0xff,0xff,0xfe,0xf0,0xff,0xff,0xf3,0xff,0xf7,0xff,0xfe,0x5f,0xff,0xf7,0xff,0xff,
-0xdf,0xff,0xff,0xff,0xf7,0xfe,0x7b,0xf1,0xff,0xfd,0xfd,0xff,0xdf,0xdf,0xff,0x7d,
-0x73,0xf9,0xff,0xc3,0x7e,0xfe,0xff,0xef,0xd7,0xff,0xcf,0xd0,0xf0,0x6f,0xff,0xff,
-0xff,0xfe,0xf8,0x30,0x00,0x00,0x40,0x04,0x00,0x01,0x41,0x20,0x00,0x04,0x00,0x02,
-0xd5,0x09,0x00,0x02,0x80,0x02,0x01,0x00,0x00,0x00,0x0a,0x04,0x00,0x07,0x00,0x01,
-0x50,0x01,0x80,0x02,0x61,0x40,0x41,0x0c,0x14,0x08,0xc1,0xf0,0x9f,0xff,0xff,0xff,
-0xfe,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfe,0xdf,0xcb,0x5f,0xfe,0xef,0xff,0xfe,
-0xff,0x3f,0xff,0x7f,0xfd,0xc1,0xff,0xff,0x7f,0xff,0xdf,0xfd,0xfc,0xfd,0xf7,0xee,
-0xff,0xff,0x4e,0xff,0xdf,0xcf,0xdb,0xeb,0xff,0xff,0xf0,0x1f,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x2f,0xff,0xff,0xff,0xfe,0x7f,
-0xff,0xff,0xff,0xfd,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,
-0xf7,0xfb,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0x7f,0xff,0xff,0xff,0x7f,0xff,0xf0,0x1f,0xff,0xff,0xff,0xfe,0xdd,0xff,
-0xff,0xff,0xa5,0xff,0x6f,0x6b,0xe9,0x6f,0xda,0xca,0xfb,0xdd,0xee,0xf7,0xf6,0xb2,
-0xb3,0xa4,0xa1,0x5b,0x5b,0xf6,0xd7,0xf4,0xf7,0x7b,0xbd,0xbd,0xad,0xcf,0xef,0x7f,
-0x6b,0x7f,0x3b,0xdf,0xdb,0xff,0xff,0x30,0xcf,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,
-0xff,0xff,0xff,0xf6,0xfe,0x96,0xff,0xfd,0xb5,0xfd,0xbf,0xad,0x7f,0xff,0x6f,0xff,
-0xde,0xd1,0xad,0xad,0xe9,0xff,0xf1,0xec,0xef,0xde,0x3f,0xcb,0xff,0xf6,0xff,0x32,
-0xff,0xc5,0xbd,0xff,0xff,0xff,0xd0,0xbf,0xff,0xff,0xff,0xfe,0xfe,0xfb,0xff,0xf4,
-0x28,0xbf,0xff,0xfd,0xfb,0xd3,0xff,0xff,0x42,0xff,0xff,0xff,0xea,0xb3,0xfc,0xc3,
-0xc1,0xff,0x33,0xff,0xc0,0x15,0x6b,0x70,0xff,0xf0,0xf2,0x4f,0xff,0xfc,0x3e,0x97,
-0x3c,0xff,0xff,0xfd,0xef,0xf0,0xbf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfe,0x78,
-0xbf,0xff,0xfd,0xf3,0xef,0x55,0xff,0x7e,0xff,0xff,0xff,0xea,0xb3,0xfc,0xc3,0xc1,
-0xff,0x33,0xff,0xc0,0x15,0x6f,0xff,0x0f,0xf0,0xf0,0x0f,0xff,0xfc,0x3d,0x6b,0xc3,
-0xff,0xff,0xfe,0xf7,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xfc,0xff,
-0xff,0x23,0xf8,0x7f,0xff,0x4e,0xff,0xff,0xff,0xfb,0xf9,0x17,0xff,0xf6,0xf1,0xff,
-0xcf,0xef,0xff,0xff,0x13,0xdf,0xe6,0x2f,0xc7,0xff,0xff,0xe7,0xc1,0xfd,0xff,0xfe,
-0xff,0xff,0xff,0xf0,0x4f,0xff,0xff,0xff,0xfe,0xf5,0xff,0xff,0xff,0xfe,0xae,0xff,
-0xff,0x7f,0x3b,0x3f,0xfc,0x7f,0xfc,0xef,0xff,0xfc,0xe2,0x7b,0xff,0xf1,0xfd,0xed,
-0xef,0xff,0xff,0x35,0x73,0xff,0xff,0xfe,0xfa,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,
-0xff,0xfa,0xf0,0x8f,0xff,0xff,0xff,0xfe,0xf1,0xc0,0x00,0x00,0x00,0x00,0x00,0x00,
-0x00,0x00,0x00,0x80,0x00,0x00,0x40,0x00,0x00,0x00,0x0c,0x04,0x01,0x40,0x40,0x00,
-0x00,0x30,0x28,0x04,0x00,0x08,0x00,0x00,0x00,0x01,0x00,0x01,0x00,0x00,0x00,0x00,
-0x38,0xf0,0x0f,0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xff,0xff,0xfb,0xff,0x7f,
-0xff,0xff,0x9f,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xdf,0xdf,0xff,
-0xff,0xff,0xff,0xed,0xff,0xfd,0xff,0xff,0xff,0xff,0xff,0xbf,0xbf,0xff,0xff,0xc3,
-0xf0,0x3f,0xff,0xff,0xff,0xfe,0xf0,0xbf,0xfd,0xff,0xbf,0xff,0xff,0xfd,0xff,0xff,
-0xff,0xff,0xff,0xfd,0x7b,0xff,0x7f,0xff,0xbd,0xff,0xf1,0xef,0xff,0xff,0xfd,0xdf,
-0xfd,0xfb,0xff,0xff,0xbf,0xbe,0xff,0xcd,0x7f,0xfc,0xf7,0xf7,0x6f,0xbf,0xd8,0xf0,
-0xef,0xff,0xff,0xff,0xfe,0xf8,0x30,0x00,0x00,0x00,0x04,0x00,0x00,0xa0,0x00,0x00,
-0xc0,0x00,0x00,0x20,0x34,0x00,0x00,0x00,0x0c,0x81,0x00,0x20,0xa4,0x20,0x00,0x10,
-0x08,0x04,0x48,0x08,0x00,0x40,0x93,0x00,0x10,0x00,0x38,0x18,0x20,0xc1,0xf0,0x3f,
-0xff,0xff,0xff,0xfe,0xff,0xfb,0xff,0xff,0xb9,0xdf,0xfe,0xb3,0xff,0xff,0xe7,0xfd,
-0xff,0xff,0x3b,0xff,0x7f,0xff,0xbf,0xff,0xc1,0xff,0xfc,0xff,0xff,0x3f,0x77,0xfe,
-0xfe,0xcf,0xff,0xbf,0xfd,0xbf,0xff,0xfe,0xed,0xf2,0xfd,0xf7,0xff,0xf0,0x2f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xbf,0xff,0xff,
-0xff,0xfe,0xff,0xff,0xff,0xf3,0xad,0xcf,0xef,0x70,0xc9,0x73,0x3b,0xdf,0x5b,0x4a,
-0xf6,0xb7,0xfe,0xd7,0xf5,0xbc,0xc1,0x33,0xca,0xd6,0xb7,0x6e,0xf7,0xfb,0xbd,0xc5,
-0x24,0xcf,0x6f,0x2f,0x4d,0x2b,0xba,0x5a,0xff,0xff,0xff,0xf0,0xaf,0xff,0xff,0xff,
-0xfe,0xbf,0xff,0xff,0xff,0xff,0xf6,0xf6,0xd7,0xff,0xff,0xad,0xbd,0xff,0xff,0xff,
-0xef,0xf7,0x7f,0xfc,0x5b,0xb1,0xfd,0xbd,0x75,0x6f,0xef,0x6a,0xfd,0x5b,0xfb,0xdb,
-0x3a,0xbf,0x8e,0x9f,0xff,0xbf,0xfd,0xff,0x6f,0xff,0xd0,0x6f,0xff,0xff,0xff,0xfe,
-0xff,0xbb,0xff,0xf0,0x3f,0xff,0xff,0xfd,0xfb,0x7f,0xde,0xff,0xff,0x5a,0xd6,0xbf,
-0xd8,0x2a,0xbf,0xbf,0xf1,0xe5,0xff,0xcc,0xc0,0xa9,0x70,0xff,0xf3,0x3c,0x3c,0xfd,
-0x57,0xfd,0x98,0x03,0x00,0xc3,0xff,0xff,0xff,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xff,0x3d,0xbf,0xff,0xfd,0xfb,0xff,0xdb,0xff,0xff,0x0f,0xfc,0x3f,0xd8,
-0x2a,0xbf,0xbf,0xf1,0xef,0xff,0xcc,0xc0,0x96,0xbe,0xff,0xf3,0x3f,0xff,0xfd,0x57,
-0xfd,0x99,0x0f,0xff,0xc3,0xff,0xff,0xff,0xf0,0x4f,0xff,0xff,0xff,0xfe,0xff,0xff,
-0xff,0xf1,0xe7,0xff,0xff,0xf3,0x8e,0x7b,0xff,0xa8,0xff,0xdf,0x7f,0x8e,0x78,0x73,
-0xff,0xf1,0x51,0x62,0xff,0xfc,0x4b,0xff,0xf3,0xff,0x7e,0xcf,0xf9,0xff,0xfd,0xff,
-0xff,0x7f,0xff,0xe0,0xff,0xff,0xff,0xf0,0x4f,0xff,0xff,0xff,0xfe,0xf5,0xff,0xff,
-0xfb,0xfd,0xae,0xff,0xfc,0xfe,0x6f,0x3f,0xf8,0xfd,0x77,0xaf,0xfe,0x37,0xfe,0x7b,
-0xff,0xb1,0x8c,0xff,0xef,0xfd,0xf8,0xe7,0xbf,0xff,0xf1,0xfe,0x3e,0xf7,0xfe,0x95,
-0x3e,0xbf,0xff,0xff,0xff,0xfa,0xf0,0xbf,0xff,0xff,0xff,0xfe,0xf1,0xc0,0x00,0x00,
-0x01,0x04,0x00,0x00,0x00,0x00,0x80,0x02,0x00,0x00,0x10,0x00,0x10,0x00,0x10,0x08,
-0x41,0x80,0x10,0x00,0x00,0x08,0x10,0x84,0x00,0x0c,0x04,0x02,0x61,0x00,0x00,0x81,
-0x00,0x00,0x00,0x00,0x3d,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xff,
-0xff,0xff,0x7f,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,
-0x7f,0xbf,0xf7,0x7f,0xef,0xff,0xef,0xff,0xf7,0xfd,0xff,0xff,0xfd,0x7f,0xff,0xbe,
-0xdf,0xff,0xff,0xd9,0xf0,0xbf,0xff,0xff,0xff,0xfe,0xf0,0xbb,0xff,0x7f,0xfb,0xff,
-0xfb,0xff,0xbf,0xff,0xf3,0x7f,0xfb,0xfd,0xeb,0x7f,0xdf,0xfa,0xff,0xde,0xf0,0xed,
-0xff,0xb1,0xf7,0xf9,0x1f,0xb5,0x5b,0xfe,0x7e,0xf7,0xbe,0xfd,0x7f,0x5f,0xb5,0xf7,
-0xff,0xff,0xd0,0xf0,0x4f,0xff,0xff,0xff,0xfe,0xf8,0x30,0x01,0x00,0x07,0x42,0x01,
-0x00,0x6a,0x18,0x50,0x80,0x00,0x00,0x02,0x40,0x01,0x01,0x20,0x01,0x01,0x24,0x14,
-0x21,0x10,0x02,0x08,0x07,0x08,0x00,0x40,0x10,0x80,0x58,0x00,0x84,0x80,0x18,0x10,
-0x40,0xc1,0xf0,0xbf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf7,0xff,0xdb,0xb7,0xf3,
-0xdf,0x7c,0xf8,0x74,0xff,0xff,0x6f,0x7d,0x3f,0x7e,0xec,0x7f,0xc1,0xf5,0xff,0xcf,
-0x6f,0x9f,0xf9,0xdf,0xbe,0xe5,0xe7,0xff,0xd7,0xf3,0xdd,0xfb,0xff,0xfc,0xff,0xbf,
-0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xf0,0x2f,0xff,0xff,0xff,0xfe,0xd7,0xff,0xff,0xff,0xb4,0xcf,0xef,0x77,0x6f,0x73,
-0x3a,0x4a,0x3a,0xcb,0xd4,0xf7,0x2e,0xd6,0xbd,0xbd,0xa1,0x3b,0xdf,0xd6,0xf7,0xee,
-0xd3,0x35,0xbd,0xfb,0xbd,0xce,0xeb,0x2b,0x4d,0x2f,0xbb,0xda,0xff,0xff,0xfe,0xb0,
-0x5f,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xff,0xdf,0x5f,0x36,0xaf,0x3f,0xed,0xb7,
-0xf5,0xfd,0xf3,0x2b,0xef,0x77,0xff,0xfb,0xda,0xb1,0xbd,0xa3,0x77,0x69,0x7f,0x4f,
-0xff,0xdb,0xfa,0x5b,0xff,0xf2,0xfe,0xff,0x96,0xff,0xff,0xfe,0xdf,0xff,0xd0,0xaf,
-0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfd,0x8f,0xfd,0x40,0x6f,0x9e,0x83,0x5a,0x0f,
-0xfa,0xc3,0xff,0xff,0xfc,0xe9,0x7f,0xf3,0x01,0xd0,0x00,0xfe,0xbf,0xcd,0x3f,0xf0,
-0xef,0xfc,0xc5,0x0c,0x3f,0xfd,0x68,0x0b,0xff,0xff,0xff,0xfe,0xdf,0xf0,0xff,0xff,
-0xff,0xff,0xfe,0xff,0xbb,0xff,0xfd,0x85,0xff,0xd4,0x6f,0x9f,0xc3,0x5a,0x0f,0xff,
-0xff,0xff,0xff,0xfc,0xe9,0x7f,0xf3,0x01,0xf0,0xfb,0xc2,0xbf,0xfc,0x00,0x37,0xef,
-0xfc,0xcd,0xbc,0x3f,0xff,0x0c,0xbf,0xff,0xff,0xff,0xff,0xff,0xf0,0x5f,0xff,0xff,
-0xff,0xfe,0xff,0xff,0xff,0xff,0xd9,0xf7,0xd1,0xb7,0x7e,0x7f,0xf1,0xe4,0xfd,0xff,
-0xfb,0xfb,0xff,0x5f,0xff,0x7f,0xb1,0xbc,0x0f,0x67,0xeb,0xb8,0x3f,0xff,0xe2,0xff,
-0xe9,0xff,0xfd,0xe3,0xff,0x3f,0x9f,0xc2,0xff,0xff,0xff,0xf0,0x9f,0xff,0xff,0xff,
-0xfe,0xf5,0x7f,0xff,0xf0,0x3f,0xbc,0xff,0xd5,0xf5,0xce,0x3f,0xfe,0xff,0xfe,0x6d,
-0xff,0xf1,0xbf,0x7b,0xff,0xf1,0xfd,0xff,0x4f,0xff,0x87,0xff,0xae,0xff,0xb1,0xf8,
-0xfe,0xff,0xff,0x78,0x01,0xb9,0xff,0xff,0xff,0xfa,0xf0,0x2f,0xff,0xff,0xff,0xfe,
-0xf3,0xc0,0x00,0x00,0x00,0x04,0x02,0x13,0x02,0x00,0x80,0x40,0x00,0x90,0x10,0x00,
-0x10,0x00,0x02,0x00,0x01,0x20,0x80,0x12,0x10,0x00,0x40,0x08,0x00,0x04,0x00,0x00,
-0x02,0x00,0x01,0x40,0x00,0x80,0x00,0x00,0x3c,0xf0,0xef,0xff,0xff,0xff,0xfe,0xfd,
-0x1f,0xff,0xff,0xff,0x7f,0xff,0xff,0xff,0xff,0x7f,0xff,0x7f,0xf7,0xdf,0xf7,0xff,
-0xf7,0xfb,0xeb,0xd1,0xff,0xff,0xff,0xff,0xef,0xf7,0xff,0xff,0xfb,0xff,0xfe,0xff,
-0xff,0x7e,0xff,0xfb,0xff,0xff,0xff,0xdb,0xf0,0xff,0xff,0xff,0xff,0xfe,0xf0,0xff,
-0xff,0xb7,0xeb,0xf7,0xdf,0xff,0xfe,0xf5,0x6b,0xe7,0xed,0xf7,0x3e,0xec,0xff,0x54,
-0xef,0x6f,0xf1,0xf5,0xaf,0x6f,0xf6,0xfd,0xff,0xdd,0x7b,0xff,0xef,0xbf,0x7f,0xff,
-0xff,0xf7,0xff,0xf3,0x5f,0xf7,0xd0,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xf8,0x30,0x00,
-0x80,0x40,0x04,0x00,0x81,0x2c,0x04,0x24,0x00,0x02,0x01,0xc8,0x02,0x00,0x02,0x24,
-0x00,0x01,0xb4,0x42,0xdc,0x44,0x02,0x15,0x90,0x02,0x03,0x48,0x39,0x10,0x02,0x24,
-0xa0,0xba,0x00,0x00,0x40,0xc1,0xf0,0xbf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,
-0xfe,0xfc,0xf7,0xf0,0xee,0xb6,0x5d,0xfd,0xf5,0xff,0xdb,0xf7,0x7f,0x7f,0xbe,0xff,
-0xc1,0xfe,0xbf,0xfa,0xfa,0x5f,0xff,0xad,0xff,0xef,0xff,0x7f,0xdf,0x7f,0xfe,0xbf,
-0xb7,0x94,0xbf,0xff,0xff,0xf0,0x9f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf0,0x8f,0xff,0xff,0xff,0xfe,0xd7,0xff,0xff,0xfb,0xb5,0xff,
-0xef,0x7c,0xeb,0x2b,0x52,0x5b,0x3b,0xda,0xd4,0xf3,0x36,0x96,0xb5,0xbd,0xf1,0xfb,
-0xda,0xee,0xf6,0xfe,0xd3,0x35,0xbd,0xdf,0xad,0xcf,0xef,0x7e,0xcd,0x6b,0xbb,0xdf,
-0xff,0xff,0xfd,0xb0,0xef,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xff,0xd3,0x5f,0xf6,
-0xff,0xf6,0xff,0xfd,0xad,0xfd,0xff,0x7f,0xef,0xff,0x6f,0x7f,0xdb,0xf1,0xa5,0xa3,
-0x7f,0x6f,0x6b,0x4f,0xff,0xdb,0xfb,0xcb,0xff,0xf6,0xff,0xf4,0xd7,0xfd,0xbf,0xfe,
-0xdf,0xff,0xd0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf7,0xdf,0xff,0xff,0xff,
-0x3f,0x7f,0xfc,0xe5,0xff,0x20,0xfe,0xff,0xff,0xdf,0x7f,0xff,0xf1,0x7f,0xff,0xfe,
-0xff,0xf0,0x7c,0x3d,0x4f,0xf3,0xc3,0x3f,0xff,0xff,0x6f,0xc3,0xff,0x0f,0xff,0xff,
-0xaf,0xf0,0x2f,0xff,0xff,0xff,0xfe,0xff,0xff,0xfb,0xb7,0xe0,0x0f,0xff,0xff,0x2b,
-0xff,0x7d,0xbf,0xff,0xdf,0xff,0xff,0xf8,0x9f,0x7f,0xff,0xf1,0x55,0xff,0xff,0xff,
-0xfd,0x7c,0x3c,0xff,0xf3,0xc3,0x3f,0xff,0xff,0xef,0xc3,0xff,0xdf,0xff,0xff,0xff,
-0xf0,0x9f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xef,0xff,0xff,0x9f,0xbf,0x7f,
-0xf9,0x19,0x47,0x8e,0xe7,0x9f,0x3f,0x17,0xff,0xfc,0x81,0xc1,0x7e,0xf3,0xd9,0xf9,
-0x73,0xdf,0xf4,0x7f,0xfa,0xff,0xff,0xff,0xfb,0x7f,0x77,0xc7,0xff,0xff,0xff,0xf0,
-0x2f,0xff,0xff,0xff,0xfe,0xf5,0xf7,0xff,0xfb,0xff,0xf7,0x3f,0xfc,0xbf,0x3e,0x3f,
-0xec,0xff,0x81,0xaf,0xfe,0x4f,0xf3,0xbb,0xff,0xf0,0x7e,0xff,0x6f,0xff,0x87,0xff,
-0xbb,0xff,0xd5,0xfc,0xff,0x7f,0xfc,0x6f,0xff,0xef,0xe7,0xff,0xff,0xfa,0xf0,0x3f,
-0xff,0xff,0xff,0xfe,0xf3,0xc0,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,
-0x00,0x30,0x10,0x60,0x20,0x00,0x08,0x00,0x01,0x20,0x80,0x00,0x10,0x00,0x04,0x00,
-0x00,0x00,0x00,0x00,0x00,0x02,0x00,0x80,0x40,0x00,0x08,0x20,0x3c,0xf0,0x6f,0xff,
-0xff,0xff,0xfe,0xf5,0xbf,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0x7f,0xfe,0x3f,0xff,
-0xff,0xff,0xff,0xff,0xef,0xff,0xff,0xf1,0xdf,0xdf,0xff,0xff,0xff,0x7f,0xdf,0xff,
-0xfd,0xbd,0xff,0xff,0xff,0xfb,0xdf,0xff,0xff,0xff,0xff,0x5b,0xf0,0xff,0xff,0xff,
-0xff,0xfe,0xf0,0xbf,0xbf,0xbf,0xff,0xf7,0xfb,0xff,0xfe,0xee,0xfa,0xff,0xff,0xff,
-0x3d,0x3b,0xff,0xff,0xfe,0xfb,0xf1,0xff,0xbf,0x7b,0xff,0xff,0xef,0xff,0xbf,0xff,
-0xff,0xff,0xff,0xff,0xfe,0xff,0xf7,0xef,0xff,0xfb,0xd0,0xf0,0xdf,0xff,0xff,0xff,
-0xfe,0xf8,0x30,0x00,0x00,0x00,0x00,0x00,0x0b,0x10,0x05,0x01,0x00,0x08,0x00,0x02,
-0x01,0x01,0x00,0x00,0x10,0x01,0xc8,0x08,0x00,0x00,0x00,0x00,0x42,0x02,0x00,0x00,
-0x00,0x80,0x02,0x00,0x00,0x40,0x24,0x80,0x00,0xc1,0xf0,0x3f,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0xf7,0xfd,0xf7,0xfa,0xef,0xee,0xf9,0xfd,0xff,0xf7,0xfe,0xbf,
-0x1f,0xfd,0x9e,0xfd,0xd1,0xef,0xff,0xf7,0x7f,0x9f,0xff,0xef,0xff,0xf6,0xff,0xfe,
-0xfe,0x7b,0xff,0xbd,0xff,0x7e,0xff,0xff,0xff,0xf0,0x3f,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xff,0xff,
-0xff,0xf7,0xff,0xff,0xff,0xff,0x7f,0xff,0xff,0xff,0xdf,0xfd,0xff,0xff,0xdf,0xff,
-0xff,0x5f,0xf1,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xff,0xef,0xff,
-0xf7,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x3f,0xfb,0xff,0xff,0xef,0xfb,0xfd,
-0xff,0xf1,0xff,0xff,0xfb,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x2f,0xff,0xff,0xff,0xfe,0xf7,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xfd,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,0xff,0xff,0xe7,0xff,
-0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xcf,0xff,0xfb,0xff,0xfb,0xf1,
-0xff,0xff,0xfb,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf0,0x2f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7b,0xff,0xff,0xff,0x7f,0xff,0xf1,0xff,
-0xff,0xff,0xdf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xef,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xdf,0x57,0xff,0xfe,0xbf,0xfb,0xf1,0xff,0xff,
-0xfd,0xf7,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xd7,0xff,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf7,0xdb,0xff,0xdb,0xfd,
-0xf6,0xff,0xf6,0xff,0x3c,0xbc,0xbc,0xbf,0xdf,0x6f,0xef,0x2f,0xf1,0x3c,0xbf,0xbc,
-0xbf,0xdf,0x6f,0xff,0x6f,0xf7,0xdb,0xff,0xdb,0xfd,0xf6,0xff,0xf6,0xff,0xff,0xff,
-0x01,0xe2,0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff };
diff --git a/drivers/net/hamradio/yam9600.h b/drivers/net/hamradio/yam9600.h
deleted file mode 100644
index 5ed1fe6ff43e..000000000000
--- a/drivers/net/hamradio/yam9600.h
+++ /dev/null
@@ -1,343 +0,0 @@
-/*
- *
- * File yam111.mcs converted to h format by mcs2h
- *
- * (C) F6FBB 1998
- *
- * Tue Aug 25 20:23:03 1998
- *
- */
-
-static unsigned char bits_9600[]= {
-0xff,0xf2,0x00,0xa5,0xad,0xff,0xfe,0x9f,0xff,0xef,0xfb,0xcb,0xff,0xdb,0xfe,0xf2,
-0xff,0xf6,0xff,0x9c,0xbf,0xfd,0xbf,0xef,0x2e,0x3f,0x6f,0xf1,0xfd,0xb4,0xfd,0xbf,
-0xff,0x6f,0xff,0x6f,0xff,0x0b,0xff,0xdb,0xff,0xf2,0xff,0xf6,0xff,0xff,0xff,0xff,
-0xf0,0x6f,0xff,0xff,0xff,0xfe,0xff,0xfd,0xdf,0xff,0xff,0xff,0xf7,0xff,0xff,0xff,
-0xfb,0xff,0xff,0xf7,0xff,0xff,0xff,0xfe,0xff,0x7f,0xf1,0xff,0xfe,0xff,0xbf,0xbf,
-0xff,0xff,0xff,0xff,0xff,0xf7,0xff,0xff,0xff,0xfe,0xff,0xfe,0xff,0xff,0xff,0xf0,
-0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xbf,0xff,0xff,0xff,0xf7,
-0xff,0xff,0xf7,0xef,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0x7e,0xff,0xff,
-0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xff,0xff,0xfd,0xff,0xff,0xff,0xf0,0xdf,
-0xff,0xff,0xff,0xfe,0xff,0xff,0xdf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xef,0xff,0xf3,0xfb,0xfe,0xff,0xf1,0xff,0xfd,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xdf,0xff,0xf0,0x7f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xef,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xdf,0xff,0xff,0xff,0xf7,0xf1,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xf0,0x0f,0xff,0xff,
-0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf5,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x2f,0xff,0xff,0xff,
-0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xfb,0xff,0xff,0xff,0xef,0xff,0x7f,0xff,0xef,
-0xff,0xef,0xff,0x7f,0xef,0xf1,0xff,0xef,0xff,0x7f,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xf0,0x9f,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xbf,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xff,0xbd,0xff,0xef,0x7f,0xef,0x7f,0xfb,0xdf,0xd3,0x5a,0xfe,0xd7,0xd6,
-0xf7,0x7f,0xbd,0xf1,0xbb,0x5d,0xd6,0xf7,0xfe,0x96,0xff,0xbd,0xaf,0xad,0xbf,0xef,
-0x7f,0x6b,0x7f,0xfb,0xd6,0xfe,0xf7,0xff,0x10,0xef,0xff,0xff,0xff,0xfe,0xbe,0xef,
-0xff,0xff,0xdb,0xff,0xf6,0xff,0xf6,0xff,0xfd,0xbf,0xfd,0xbf,0xff,0x7f,0xff,0x7f,
-0xdf,0xdb,0xf1,0xfd,0x35,0xff,0x6f,0xff,0x6f,0xff,0xdb,0xff,0xcb,0xff,0xf6,0xff,
-0xf2,0xfd,0xfd,0xbf,0xff,0xff,0xff,0xd0,0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x55,0xff,0xcc,0xc0,0x3f,0xff,
-0xff,0xf1,0x24,0xf0,0xff,0xff,0xcf,0xef,0x3f,0xff,0xf0,0xff,0xff,0xff,0xfc,0x3f,
-0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x55,0xff,0xcc,0xc0,0x3f,0xff,0xff,
-0xf1,0x00,0xf0,0xff,0xff,0xcf,0xdf,0xff,0xff,0xf0,0xff,0xff,0xff,0xfc,0x3f,0xff,
-0xff,0xff,0x7d,0xff,0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xdf,0xfe,0x7f,0xdf,0xff,0xff,0xff,0xf1,
-0xff,0xcf,0xff,0xf3,0xff,0x97,0xff,0xff,0x8f,0xe7,0xff,0xff,0xfc,0x71,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf0,0xef,0xff,0xff,0xff,0xfe,0xf5,0xff,0xbf,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xe3,0xf7,0xef,0xff,0xff,0xfc,0x7b,0xff,0xf1,0x3f,
-0xff,0xef,0xff,0xcf,0xe3,0xe3,0xff,0xff,0xff,0xff,0x3f,0xff,0xff,0xff,0xbf,0xff,
-0xbf,0xff,0xda,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xf2,0xc0,0x00,0x00,0x00,0x00,0x00,
-0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,
-0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x02,0x00,0x00,0x00,0x00,0x00,
-0x01,0x3c,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xdb,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0x9f,0xff,
-0xff,0xff,0xf7,0xff,0xef,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xdb,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xf0,0xbb,0xdf,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xef,0xfb,0xdf,0xbf,0xf1,0xfe,0xfd,0xf7,0xff,
-0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x77,0xfd,0xf2,
-0xf0,0x1f,0xff,0xff,0xff,0xfe,0xf8,0x38,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x03,
-0x00,0x00,0x00,0x02,0x00,0x90,0x00,0x00,0x00,0x0c,0x01,0x00,0x00,0x04,0x24,0x00,
-0x40,0x01,0x00,0x00,0x00,0x40,0x00,0x00,0x00,0x00,0x02,0x00,0x00,0x01,0xc0,0xf0,
-0x4f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xbf,0xff,0xff,0x6f,0xff,0xdf,0xff,0xd1,0xff,0xfe,0xff,0xff,0xff,0xff,
-0xff,0xff,0xdf,0xff,0xfb,0xff,0xfb,0xef,0xff,0xff,0xee,0xff,0xff,0x7f,0xf0,0xdf,
-0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x8f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xff,0xf5,0xad,0xff,0x69,0x2a,0xed,0x6b,0xfb,0xdf,0x3a,
-0xdc,0xf4,0x96,0xee,0xb3,0x3d,0x35,0xc1,0xbb,0xdd,0xfe,0xf6,0xfe,0xd6,0xb5,0xad,
-0xbf,0xa5,0xad,0x49,0x2f,0x4f,0x2b,0xda,0x5f,0xff,0xff,0xff,0xf0,0x2f,0xff,0xff,
-0xff,0xfe,0xbf,0xff,0xff,0xfb,0x5b,0xf7,0xf6,0xff,0xf6,0xff,0xfd,0xbf,0xfd,0xa5,
-0xf3,0x6f,0xf3,0x6e,0xfa,0x7b,0xd1,0xfd,0xb5,0x77,0x6f,0xe9,0x6f,0xff,0xdb,0xfb,
-0xdb,0xdf,0xf6,0xff,0xf6,0xff,0xfd,0x3f,0xfe,0xf7,0xff,0xd0,0x4f,0xff,0xff,0xff,
-0xfe,0xff,0x9f,0xff,0xff,0x0f,0xff,0xc0,0x3f,0x9c,0x03,0xff,0xff,0x8b,0xa5,0xfe,
-0x80,0x3e,0xc2,0xbf,0xac,0xb1,0x24,0xff,0xff,0xff,0xff,0xff,0xff,0x0f,0xff,0xa3,
-0xff,0xfd,0x6b,0xff,0xff,0xf0,0xa5,0xff,0xff,0xff,0xf0,0xaf,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0x0f,0xff,0xc0,0x3f,0xd4,0x6b,0xff,0xff,0xdb,0xff,0xfe,0x86,
-0xbf,0xc2,0xbf,0x30,0xa1,0x24,0xff,0xff,0xff,0xff,0xcc,0xff,0x0f,0xff,0xa3,0xff,
-0x05,0x6b,0xff,0xff,0xf0,0xa5,0xff,0xff,0xff,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xfb,0xc7,0xff,0xc4,0xff,0xff,0x7f,0xff,0xec,0xfe,0x7f,0xdf,0xd8,0xb9,
-0x47,0xfc,0x36,0xc1,0xdf,0xff,0xff,0xf9,0xff,0xf3,0xff,0xf7,0xff,0xfc,0xff,0xfd,
-0x3f,0xff,0xff,0xff,0x3f,0xff,0xff,0xff,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xf5,0xff,
-0xff,0xff,0xff,0xfe,0xff,0xff,0x7e,0xbd,0x3f,0xff,0x2b,0xfe,0x2f,0xf5,0xa3,0xfc,
-0x5b,0xfe,0x61,0x9f,0x7f,0xef,0xff,0xff,0xa7,0xfb,0xff,0xff,0xfa,0xfe,0xff,0x33,
-0xf1,0xff,0xbf,0xff,0xff,0xff,0xfa,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xf1,0xc0,0x00,
-0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x40,0x00,0x30,0x24,0x04,
-0x00,0x01,0x00,0x80,0x40,0x00,0x08,0x00,0x00,0x00,0x02,0x01,0x01,0x00,0x02,0x00,
-0x00,0x00,0x00,0x00,0x01,0x3d,0xf0,0x2f,0xff,0xff,0xff,0xfe,0xfd,0xbd,0xff,0xfd,
-0xff,0xff,0xff,0xff,0xff,0xfb,0xff,0xff,0x7f,0xf6,0xef,0xbf,0xf7,0xff,0x73,0xeb,
-0xf1,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xff,0xff,0xf9,0xff,0xfd,0xfe,0xff,0xff,
-0xff,0xff,0xff,0xff,0xd9,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xf0,0xbf,0x7f,0xff,0xff,
-0xff,0x7f,0xff,0xff,0xde,0xff,0xff,0xef,0xdd,0xde,0x77,0xf2,0xfb,0xed,0xe7,0xf1,
-0x73,0xfd,0xfd,0xdf,0xff,0x7d,0xbe,0xdf,0xff,0xfb,0xff,0xef,0xff,0xef,0xff,0xff,
-0xff,0xff,0xff,0xd0,0xf0,0xbf,0xff,0xff,0xff,0xfe,0xf8,0x30,0x20,0x02,0x00,0x22,
-0x40,0xc0,0x00,0x00,0x00,0x08,0x00,0x02,0x41,0x02,0x12,0x00,0x21,0x87,0x81,0x00,
-0x00,0x80,0x04,0x0b,0x28,0x01,0xb0,0x00,0x82,0x00,0x40,0x00,0x00,0x00,0x00,0x00,
-0x00,0x00,0xc1,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xfd,0xff,
-0xf7,0xff,0xfe,0x7f,0xed,0x79,0xff,0xde,0xeb,0x7f,0x74,0xf7,0xf7,0xe1,0xf9,0xff,
-0xf6,0x5f,0x7f,0xff,0xff,0xff,0xd7,0xdb,0xef,0xff,0xbb,0xff,0xff,0xff,0xcc,0xff,
-0xff,0xff,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xf0,0x0f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfd,0x3d,0xcd,0x49,0x7f,0x6f,
-0x2b,0xba,0x5c,0xd2,0xda,0xf6,0xf3,0x3e,0xf7,0xff,0xbd,0xf1,0xfa,0xdf,0xfe,0xf7,
-0xcc,0xf6,0xbb,0xa5,0xb3,0xad,0xbf,0x6f,0x7d,0x6f,0x6b,0xdb,0xdf,0xbd,0xff,0xfe,
-0xb0,0x5f,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xfb,0xdb,0x57,0xf6,0xfe,0x9f,0xd5,
-0xb7,0xff,0xaf,0xe5,0x3f,0xff,0xff,0x6f,0xff,0xdb,0xf1,0xfd,0xbf,0xff,0x6f,0x69,
-0x6c,0xdf,0xda,0xdf,0xcb,0xff,0xf6,0xff,0x76,0xfd,0xfd,0xbf,0xff,0xff,0xff,0xd0,
-0x3f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xfd,0xbd,0x08,0x03,0x89,0x4f,0x5a,
-0x0f,0xf0,0xff,0xf8,0xbf,0xff,0xff,0xff,0xff,0xf1,0x5a,0xff,0xff,0xff,0xff,0xf3,
-0xfa,0xa0,0xf0,0xf2,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xff,
-0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xfc,0xfd,0x00,0x6b,0xff,0xff,0x5a,0x0f,
-0xf0,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0x5a,0xff,0xff,0xff,0xff,0xb3,0xf5,
-0x50,0xf0,0xf0,0xff,0xff,0xff,0xd7,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x7f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xff,0xfd,0xbc,0xff,0xe4,0xe7,0x71,0xff,0xf9,0xc4,0xf4,
-0x7f,0x7f,0xcf,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xfb,0xf7,0x73,0xbf,0x14,
-0xff,0xe6,0xff,0xff,0xe1,0x7d,0xff,0xff,0xe7,0xff,0xff,0xff,0xf0,0x3f,0xff,0xff,
-0xff,0xfe,0xf5,0xff,0xff,0xfe,0xd2,0xfa,0xff,0xc4,0xf4,0x5c,0xbf,0xfa,0xff,0xff,
-0xec,0x7e,0xbf,0xff,0xff,0xff,0xf1,0xff,0xff,0xef,0xff,0xff,0x6b,0xdb,0xff,0xdf,
-0xf9,0xfb,0xbf,0xff,0xf1,0xff,0xbf,0xff,0xff,0xff,0xfb,0xf0,0xbf,0xff,0xff,0xff,
-0xfe,0xf3,0xc0,0x00,0x02,0x00,0x00,0x00,0x00,0x82,0x00,0x00,0x00,0x00,0x80,0x00,
-0x00,0x00,0x00,0x40,0x00,0x01,0x00,0x00,0x00,0x01,0x08,0x20,0x00,0x00,0x00,0x00,
-0x01,0x00,0x01,0x00,0x00,0x80,0x02,0x00,0x01,0x3c,0xf0,0x5f,0xff,0xff,0xff,0xfe,
-0xfd,0xbf,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xff,0x7f,0xff,0xdf,0xff,0xef,0xff,
-0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xf7,0xff,0xfb,0xff,0xfd,0xff,
-0xff,0xff,0xff,0xff,0xff,0xfd,0xff,0xff,0xc3,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xf0,
-0xff,0xdf,0xff,0xff,0xf7,0x23,0xff,0xff,0xfd,0xff,0xef,0xff,0xfe,0x7f,0x7d,0xf7,
-0xfe,0xff,0x7f,0x71,0xff,0xfb,0x7f,0xff,0xff,0xff,0x6e,0xfd,0xf7,0xfd,0xff,0xbf,
-0xff,0xbf,0xf9,0xfd,0xff,0xdf,0xef,0xf0,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xf8,0x30,
-0x40,0x01,0x00,0x83,0x00,0x00,0x00,0x0c,0x06,0x08,0x04,0x26,0x26,0x00,0x00,0x06,
-0x03,0x00,0x01,0x00,0x00,0x00,0x00,0x04,0x00,0x70,0x08,0x80,0x00,0x20,0x01,0x20,
-0x00,0x02,0x00,0x30,0x00,0x00,0xc1,0xf0,0x5f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,
-0xff,0xff,0x7b,0x3f,0xf7,0xff,0xd7,0xfe,0xfe,0xfb,0xfe,0x3b,0xfe,0xbd,0xff,0x2f,
-0xff,0x71,0xff,0xfb,0x7f,0xe7,0xff,0xf9,0xef,0xff,0xd7,0xfa,0xff,0xb7,0xbb,0xfe,
-0xff,0xff,0x74,0xff,0xf7,0xff,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xf0,0x8f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xb5,
-0xbd,0x6f,0x7c,0xeb,0x7f,0xfb,0xdb,0xd3,0x4b,0xee,0xd6,0xf6,0xb7,0xfd,0xac,0xa1,
-0xfb,0xdf,0xfe,0xf7,0xf4,0x96,0xbd,0xb4,0xc5,0xa5,0xaf,0x6f,0x69,0x4f,0x7f,0xba,
-0xdb,0xff,0xff,0xff,0xf0,0x3f,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xff,0xdb,0xff,
-0xf6,0xff,0xf6,0xff,0xbd,0xbf,0xa5,0xbf,0xff,0x7d,0x7f,0xef,0xff,0xfb,0xf1,0xfd,
-0xbf,0xff,0x6f,0xff,0x6b,0x7a,0xdb,0xff,0xdb,0xdf,0xf6,0xfe,0xb6,0xfd,0xfd,0xbf,
-0xfe,0xf7,0xff,0xd0,0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xf4,0x2f,0xff,
-0xfc,0x43,0x6b,0xff,0xff,0xff,0x0d,0xff,0xfc,0x33,0x3f,0xf0,0x5f,0xf1,0xff,0xff,
-0xff,0xff,0xf9,0xde,0xf0,0x4c,0xfe,0x77,0xaf,0xff,0xff,0xef,0xff,0xf0,0xff,0xdb,
-0xff,0x5f,0xf0,0xef,0xff,0xff,0xff,0xfe,0xff,0xfe,0xf7,0xff,0xf0,0x2f,0xff,0xfd,
-0x43,0x7f,0xff,0xff,0xf1,0x0f,0xff,0xfc,0x33,0x3f,0xff,0xaf,0xf1,0xff,0xff,0xff,
-0xff,0xf6,0xd7,0xff,0xbc,0xfd,0xbd,0xff,0xff,0xff,0xff,0xff,0xf0,0xff,0xff,0xff,
-0xff,0xf0,0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xfc,0xff,0xff,0xfb,0xf1,
-0xbf,0xff,0xf9,0xfd,0xcf,0xf2,0x70,0xff,0x1f,0x9f,0xf3,0xf1,0xff,0xff,0xff,0xff,
-0xfc,0xf7,0xff,0x13,0x9f,0xfc,0xff,0xff,0x84,0xf7,0xff,0xff,0x47,0xff,0xff,0xff,
-0xf0,0xbf,0xff,0xff,0xff,0xfe,0xf5,0xff,0xff,0xff,0xf1,0xfc,0xff,0xfe,0xfe,0x79,
-0x3f,0xff,0x1d,0x46,0xcf,0xff,0xcf,0xfc,0x7b,0xff,0xf1,0xff,0xff,0xff,0xff,0xed,
-0xf3,0xab,0xff,0xcb,0xff,0xf8,0xff,0xfc,0xf5,0xff,0xbf,0xff,0xff,0xff,0xfa,0xf0,
-0x8f,0xff,0xff,0xff,0xfe,0xf3,0xc2,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x01,0x00,
-0x00,0x00,0x20,0x00,0x20,0x00,0x00,0x04,0x08,0x01,0x00,0x00,0x00,0x00,0x00,0x20,
-0x0c,0x00,0x00,0x04,0x01,0x00,0x01,0x00,0x00,0x80,0x00,0x00,0x01,0x3c,0xf0,0x7f,
-0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xfd,0xfe,0xff,0xff,0xff,0xff,0xfe,0xff,
-0xdf,0xff,0xff,0xf7,0xff,0xff,0xff,0xef,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xeb,
-0xff,0xdf,0xff,0xff,0xfb,0xf7,0x7f,0xff,0xfe,0xff,0xff,0xbf,0xdb,0xf0,0xff,0xff,
-0xff,0xff,0xfe,0xf0,0xff,0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0x7f,0xf7,0xff,
-0xbf,0xbf,0xcf,0xff,0xff,0xff,0x3e,0xf1,0x7f,0xff,0xff,0xef,0xff,0xff,0xff,0xfe,
-0xff,0xfd,0xff,0xbf,0xbd,0xfe,0xff,0xfb,0xf7,0xdf,0xfb,0xd0,0xf0,0x9f,0xff,0xff,
-0xff,0xfe,0xf8,0x30,0x20,0x00,0x40,0x01,0x80,0xc0,0x30,0x00,0x00,0x20,0x00,0x10,
-0x50,0x88,0x20,0x00,0x00,0x13,0x01,0x00,0x00,0x00,0x00,0x00,0x00,0x10,0x00,0x00,
-0x00,0x00,0x01,0x80,0x08,0x00,0x00,0xa0,0x00,0x10,0xc1,0xf0,0xef,0xff,0xff,0xff,
-0xfe,0xfd,0xef,0x7f,0xff,0xff,0xbf,0xff,0xf7,0xff,0xef,0xfb,0xfd,0x77,0xef,0xbf,
-0xf7,0x7f,0xff,0xff,0xbf,0xd1,0x7f,0xff,0xff,0xf7,0xff,0xff,0xff,0xff,0xaf,0xff,
-0xdf,0xf7,0xfb,0xff,0xfd,0xff,0xfc,0xff,0xfd,0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x5f,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,
-0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xe0,0x3f,0xff,0xff,0xff,0xfe,0xdd,0xff,
-0xff,0xff,0xa5,0xfd,0x6f,0x7d,0x6d,0x7f,0x52,0xdf,0x5a,0x4b,0xee,0xb6,0xee,0xf2,
-0xbb,0xac,0xa1,0x5b,0x4d,0xd6,0xf7,0xfe,0xb2,0xbd,0x35,0xb5,0xb5,0xdd,0x6f,0x7f,
-0xe9,0x5f,0x52,0xdf,0xbd,0xff,0xff,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,
-0xff,0xdb,0xfe,0xf6,0xff,0xf6,0xff,0xfd,0xbf,0xfd,0xb5,0xbf,0xf9,0x7f,0x6f,0xff,
-0xdb,0xf1,0xfd,0xbf,0xff,0x6f,0xff,0x69,0x7f,0xdb,0xff,0xd3,0xff,0xf6,0xfe,0xf2,
-0xff,0xad,0xbf,0xff,0xff,0xff,0xd0,0xdf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf5,
-0x30,0x0f,0xff,0xff,0xfd,0x6b,0xca,0xff,0xf0,0x0f,0xd6,0xbf,0xcf,0x3f,0xff,0xff,
-0xf1,0xff,0xff,0xff,0xca,0xfe,0xbf,0xff,0xf0,0x05,0xaf,0x0f,0xff,0xfc,0xf0,0xcf,
-0xf0,0xff,0xff,0xff,0xff,0xf0,0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf5,0x30,
-0x0f,0xff,0xff,0xfc,0x3f,0xca,0xff,0x0f,0x0f,0xd6,0xbf,0xff,0xff,0xf5,0x5f,0xf1,
-0xff,0x8b,0xff,0xc3,0xff,0xff,0xff,0xff,0xff,0xff,0x0f,0xff,0xfc,0xf0,0xcf,0xf0,
-0xff,0xff,0xff,0xff,0xf0,0x3f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xcf,0xff,
-0xff,0xbf,0x9f,0x3f,0xfe,0xfc,0xff,0x4f,0xff,0xff,0xff,0xff,0xff,0xf7,0xf1,0xff,
-0xdf,0xfe,0x7e,0x3f,0x9f,0xf4,0xfc,0x7f,0xfc,0xff,0xff,0x3f,0xff,0x3f,0xfe,0x3f,
-0xff,0xff,0xff,0xf0,0x4f,0xff,0xff,0xff,0xfe,0xf5,0xff,0xff,0xfb,0xff,0xfe,0xff,
-0xff,0xff,0xff,0xbf,0xfb,0xff,0xf8,0xed,0xff,0x8f,0xff,0xbb,0xff,0xb1,0xf3,0xef,
-0x8f,0xf7,0xff,0xff,0xdb,0xff,0xff,0xff,0xef,0xbf,0xfd,0x79,0xbf,0xbf,0xff,0xff,
-0xff,0xfb,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xf3,0xc0,0x00,0x00,0x00,0x04,0x00,0x00,
-0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,0x00,0x04,0x08,0x08,0x01,0x01,0x00,0x90,
-0x00,0x00,0x00,0x04,0x00,0x08,0x00,0x00,0x00,0x00,0x08,0x00,0x04,0x00,0x00,0x01,
-0x3c,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0x9f,0xff,0xaf,0xdf,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,
-0xbf,0xef,0xff,0xff,0xff,0xed,0xff,0xff,0xff,0xef,0xff,0xbf,0xff,0xff,0xff,0xc3,
-0xf0,0x3f,0xff,0xff,0xff,0xfe,0xf0,0xff,0xfd,0xff,0xff,0xff,0xfb,0xff,0xbb,0xff,
-0xff,0xff,0x7f,0xf6,0xff,0x7f,0xfb,0xfd,0xed,0xff,0xf1,0xff,0xfe,0x7f,0xff,0xff,
-0xff,0x5f,0xff,0xf7,0xff,0x7e,0xff,0xfd,0xff,0xef,0xff,0xff,0xff,0xef,0xf0,0xf0,
-0x8f,0xff,0xff,0xff,0xfe,0xf8,0x30,0x80,0x00,0x04,0x00,0x00,0x40,0x02,0x00,0x03,
-0x00,0x05,0x04,0x20,0x00,0x00,0x01,0xd0,0x00,0x81,0x00,0x20,0x04,0x04,0x00,0x00,
-0x81,0x04,0x08,0x80,0x10,0x00,0xc0,0x00,0x00,0x00,0x20,0x00,0x08,0xc1,0xf0,0x6f,
-0xff,0xff,0xff,0xfe,0xff,0xff,0x7f,0xff,0xff,0xff,0xff,0xf3,0xfd,0xff,0xed,0xfc,
-0xff,0xff,0x9f,0xfb,0xfd,0xff,0xff,0xff,0xf1,0xff,0xff,0x7f,0xfb,0x3e,0xff,0x9f,
-0xff,0xff,0xff,0xff,0xfd,0xf9,0xff,0xff,0xff,0xfd,0xff,0xff,0xff,0xf0,0x6f,0xff,
-0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xcf,0xff,0xff,
-0xff,0xfe,0xff,0xff,0xff,0xfd,0xbd,0xff,0xef,0x7c,0xeb,0x7f,0xfb,0xdb,0xfa,0xdc,
-0xee,0xf7,0xf6,0xd7,0xf5,0x2d,0xa1,0xbb,0xdd,0xee,0xf7,0x54,0xf7,0xfb,0x2c,0xb5,
-0xb4,0xbd,0x6b,0x6f,0xef,0x6f,0xbb,0xdf,0xff,0xff,0xff,0xf0,0x1f,0xff,0xff,0xff,
-0xfe,0xbf,0xff,0xff,0xff,0xfb,0xff,0xf6,0xff,0xf6,0xff,0xfd,0xbf,0xff,0xbf,0xef,
-0x6f,0xff,0x6f,0xfa,0xdb,0xf1,0xc5,0xbd,0xf5,0x6f,0xff,0x6f,0xca,0xdb,0xff,0xdb,
-0xfb,0xf6,0x97,0xf6,0xff,0xfd,0xbf,0xfe,0xf7,0xff,0xd0,0x9f,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x8b,0x7f,0xff,0xff,0xe7,0x63,0xff,0xff,
-0xff,0xfc,0x77,0xdf,0xf1,0xdb,0xff,0xd6,0xa8,0x3f,0xff,0xff,0x08,0x2f,0xf0,0xff,
-0xc3,0xff,0xeb,0xff,0xff,0xff,0xff,0xff,0x5f,0xf0,0xef,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x8b,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xfc,0xff,0xcf,0xf1,0xdb,0xff,0xd6,0xa8,0x3f,0xff,0xff,0x08,0x2f,0xf0,0xff,0xc3,
-0xff,0xeb,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x5f,0xff,0xff,0xff,0xfe,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xf5,0xbf,0xff,0xca,0xff,0x9f,0xff,0xfa,0xb9,0xe7,
-0x9f,0xf3,0x81,0xff,0xff,0xfc,0x73,0xd7,0xff,0xff,0x77,0xff,0xfd,0xff,0xfc,0xff,
-0xff,0xff,0xff,0xcf,0xff,0xff,0xff,0xf0,0x1f,0xff,0xff,0xff,0xfe,0xf5,0xff,0xff,
-0xff,0xf7,0xde,0xff,0xfe,0x7e,0xff,0xbf,0xff,0xbf,0xf1,0xb3,0xff,0xff,0xe3,0xfb,
-0xff,0xe1,0x1f,0x7f,0xff,0xf8,0x78,0xff,0xfb,0x1e,0xff,0xf7,0xfe,0xe7,0xff,0xff,
-0xff,0xbf,0xff,0xff,0xff,0xfa,0xf0,0x4f,0xff,0xff,0xff,0xfe,0xf3,0xc0,0x00,0x00,
-0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x50,0x00,0x00,0x00,0x04,0x00,
-0x01,0x80,0x40,0x40,0x20,0x00,0x00,0x08,0x00,0x00,0x00,0x00,0x03,0x00,0x00,0x00,
-0x80,0x00,0x00,0x01,0x3c,0xf0,0xaf,0xff,0xff,0xff,0xfe,0xfd,0xbf,0xff,0xfb,0xff,
-0xff,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xef,0xf7,0xf1,
-0xfd,0xff,0xff,0xff,0xdf,0xff,0xef,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,0xff,
-0xff,0xff,0xff,0xdb,0xf0,0x8f,0xff,0xff,0xff,0xfe,0xf0,0xff,0xdf,0xff,0xff,0x7f,
-0xff,0xff,0xff,0xbe,0xd7,0xff,0xed,0xbd,0x7e,0xbf,0xfe,0xf6,0x7f,0xbf,0x71,0xff,
-0xff,0xda,0xff,0xf9,0xff,0xbf,0x7f,0xfe,0xff,0x6f,0x7f,0xff,0xff,0xff,0xff,0xff,
-0x7f,0xff,0xd0,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xf8,0x30,0x42,0x00,0x00,0x00,0x00,
-0x80,0xc1,0x00,0x00,0x90,0x00,0xc4,0x00,0x00,0x12,0x20,0x43,0x22,0x81,0x84,0x00,
-0x00,0x14,0x00,0x01,0x00,0x08,0x80,0x00,0x02,0x00,0x02,0x00,0x04,0x02,0x00,0x00,
-0x10,0xc1,0xf0,0x1f,0xff,0xff,0xff,0xfe,0xff,0xff,0xfd,0xff,0xff,0xdd,0xfe,0xff,
-0xb6,0x76,0xe5,0xbc,0xf9,0xf7,0xaf,0x5f,0xbf,0xfc,0xdf,0xcf,0xf1,0xff,0xef,0x79,
-0xff,0xbd,0xff,0xef,0xff,0xff,0xf7,0x6f,0x5f,0xff,0xff,0xfd,0xef,0xef,0xbf,0xff,
-0xff,0xf0,0x9f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xf0,0xff,0xff,0xff,0xff,0xfe,0xdb,0xff,0xff,0xfd,0x2d,0xff,0x69,0x2a,0xef,0x77,
-0xbb,0xdd,0x5a,0xdf,0xf6,0xf6,0xd6,0xf7,0x7d,0xbd,0xd1,0xb2,0x4a,0xd6,0xb2,0xbe,
-0x97,0xf5,0xbd,0xb3,0xad,0xff,0xef,0x7f,0x69,0x6b,0xfb,0xdf,0xff,0xff,0xff,0xf0,
-0x2f,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xff,0xdb,0xff,0xf6,0xfe,0x9f,0xd4,0xbf,
-0xed,0xaf,0xff,0x6b,0x6f,0xf7,0xff,0xdd,0xdb,0x31,0xfd,0xbf,0xff,0x6f,0x7f,0xff,
-0xff,0xdb,0xff,0xcb,0xdf,0xf6,0xff,0xf6,0xff,0xfd,0xbf,0xfe,0xf7,0xff,0xd0,0x8f,
-0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfd,0x1f,0xff,0x46,0x2f,0x9f,0xff,0xff,0xff,
-0xa5,0xff,0xff,0xff,0xdf,0xb7,0xff,0xff,0xf1,0xff,0xff,0xff,0xf7,0xe9,0x6a,0xbf,
-0xff,0xff,0xfd,0xff,0xff,0xfd,0x55,0x57,0xff,0xff,0xff,0xff,0xaf,0xf0,0x4f,0xff,
-0xff,0xff,0xfe,0xfe,0xdf,0xff,0xfd,0x1f,0xff,0x46,0x2f,0x9f,0xff,0xff,0xff,0xa5,
-0xff,0xff,0xff,0xc0,0x37,0xff,0xff,0xf1,0x99,0x8e,0xdc,0x7f,0xe9,0x6a,0xbf,0xff,
-0xf0,0x0f,0xff,0xff,0xfd,0x55,0x57,0xff,0xff,0xff,0xff,0xff,0xf0,0x0f,0xff,0xff,
-0xff,0xfe,0xff,0xff,0xff,0xff,0x07,0xff,0xc0,0xbe,0xff,0xff,0xcf,0xef,0x9f,0xff,
-0xff,0xfb,0xff,0xe7,0xff,0xff,0xa1,0xe3,0xce,0x3c,0x58,0x3f,0xf3,0xff,0xfd,0xef,
-0xf9,0xff,0xff,0xf7,0xf1,0x7f,0xff,0xcb,0xff,0xff,0xff,0xf0,0x2f,0xff,0xff,0xff,
-0xfe,0xf5,0x7f,0xff,0xf0,0xff,0xfe,0xff,0xc4,0x75,0xe7,0xb9,0xff,0xff,0xff,0xef,
-0xff,0xc7,0x37,0x3b,0xff,0xf0,0x13,0x9e,0x0f,0xf4,0xff,0xfe,0xfb,0xff,0xff,0xf9,
-0xfc,0xff,0xff,0xff,0xff,0xbf,0xff,0xff,0xff,0xfa,0xf0,0xef,0xff,0xff,0xff,0xfe,
-0xf3,0xc0,0x01,0x00,0x00,0x02,0x00,0x02,0x22,0x00,0x00,0xc0,0x40,0x00,0x40,0x00,
-0x04,0x08,0x04,0x0a,0x01,0x01,0x10,0x20,0x20,0x00,0x00,0x04,0x08,0x08,0x04,0x00,
-0x00,0x00,0x00,0x00,0x01,0x00,0x00,0x01,0x3c,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xfd,
-0x3f,0xff,0xff,0xff,0xff,0xff,0xff,0x7f,0xff,0x7f,0xff,0x7f,0xff,0xcf,0x9d,0xff,
-0xff,0xf7,0xfd,0xf1,0xff,0xff,0xff,0xee,0xbf,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xdb,0xf0,0x6f,0xff,0xff,0xff,0xfe,0xf0,0xff,
-0xff,0xff,0xf7,0xf7,0xff,0xff,0xfe,0xbf,0xf7,0xff,0xff,0x5b,0xff,0xbf,0xf7,0xff,
-0xfd,0x7f,0x71,0xfd,0xff,0xed,0xf7,0xfe,0xef,0xff,0xff,0x7f,0xff,0xff,0xff,0xff,
-0xff,0xff,0xef,0xff,0x7f,0xff,0xd0,0xf0,0xff,0xff,0xff,0xff,0xfe,0xf8,0x30,0x11,
-0x00,0x48,0x60,0x40,0x82,0x60,0x24,0x60,0x00,0xcc,0x00,0x80,0x04,0x01,0x00,0x00,
-0x14,0x01,0x0c,0x04,0x00,0x30,0x00,0x00,0x00,0x08,0x08,0x00,0x01,0x00,0xc2,0x00,
-0x00,0x02,0x00,0x80,0x00,0xc1,0xf0,0x5f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,
-0xf7,0x7b,0xff,0xf3,0xeb,0xbf,0xff,0xf7,0xff,0xff,0xff,0xe7,0x5d,0x3f,0xff,0xf6,
-0xd1,0xfd,0xff,0xeb,0xf7,0x3d,0xff,0xff,0xff,0x5f,0xff,0x7f,0x7f,0xf3,0xff,0xff,
-0xef,0xfd,0xbf,0xff,0xff,0xf0,0x5f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf0,0xdf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf5,0xb5,0xdf,
-0x6f,0x7d,0x69,0x7f,0xfb,0xdf,0x52,0x5f,0xf6,0xf7,0xfe,0xf6,0xf3,0xbd,0xb1,0xda,
-0xcd,0xfe,0xf6,0xee,0xd2,0xbd,0xa5,0xaf,0xbd,0xff,0x6f,0x7c,0xeb,0x2b,0xfa,0xda,
-0xff,0xfe,0xdf,0xf0,0x4f,0xff,0xff,0xff,0xfe,0xbf,0xff,0xff,0xff,0xdb,0xff,0xf6,
-0xff,0xf6,0xff,0xbd,0xbf,0xcd,0xbf,0xeb,0x6f,0xf7,0x6f,0xdf,0xdb,0x51,0xfd,0xbd,
-0xff,0x6f,0xff,0x6f,0xfb,0x5b,0xff,0xdb,0xff,0xf6,0xfe,0xf6,0xfd,0xfd,0xbf,0xfe,
-0xf7,0xff,0xd0,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xfa,0x50,0xff,0xff,0xff,
-0xf0,0x6f,0xff,0xff,0xf0,0x96,0xff,0xff,0xc6,0x2b,0xff,0xff,0xf1,0xfc,0xff,0xff,
-0xf7,0xdb,0xc3,0xff,0x00,0xff,0xff,0xff,0xff,0xff,0xc1,0x4f,0xc3,0xff,0xff,0xff,
-0xaf,0xf0,0x9f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf5,0xa0,0xff,0xff,0xff,0xf0,
-0x6f,0xff,0xff,0xf0,0x96,0xff,0xff,0xc6,0x2b,0xff,0xff,0xf1,0x5a,0xff,0xff,0xff,
-0xf3,0xc3,0xff,0x00,0xff,0xff,0xff,0xff,0xff,0xc1,0x4f,0xc3,0xff,0xff,0xff,0xff,
-0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xfc,0xff,0xff,0x9f,0xf0,0x7f,
-0xff,0xf9,0xfc,0x4f,0xf3,0xff,0x27,0xeb,0xff,0xfc,0x81,0xfc,0x7f,0xfe,0x7b,0xff,
-0xf7,0xff,0x12,0x7f,0xff,0xff,0xff,0xff,0x18,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,
-0x7f,0xff,0xff,0xff,0xfe,0xf5,0xff,0xff,0xff,0xdf,0xfe,0xff,0xfc,0x7e,0x7f,0xbf,
-0xff,0xff,0xaf,0xef,0xff,0xdf,0xdf,0xfb,0xff,0xf1,0xc3,0xfe,0x6f,0xf1,0xcf,0x3f,
-0xfb,0xff,0xff,0xcf,0xfe,0xff,0xff,0xfe,0x7f,0xbf,0xff,0xff,0xbf,0xfa,0xf0,0xdf,
-0xff,0xff,0xff,0xfe,0xf3,0xc0,0x00,0x00,0x01,0x00,0x00,0x00,0x00,0x01,0x00,0x00,
-0x20,0x00,0x01,0x00,0x10,0x00,0x00,0x00,0x01,0x00,0x02,0x00,0x00,0x00,0x00,0x00,
-0x00,0x00,0x00,0x02,0x00,0x00,0x80,0x00,0x02,0x80,0x00,0x02,0x3c,0xf0,0x2f,0xff,
-0xff,0xff,0xfe,0xfd,0xbf,0xff,0xfb,0xfd,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xf5,0xf1,0xff,0x7f,0xff,0xff,0xff,0xff,0xef,0xff,
-0xff,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xdb,0xf0,0x2f,0xff,0xff,
-0xff,0xfe,0xf0,0xff,0xff,0xff,0xfb,0xff,0xbf,0xff,0xff,0xff,0xff,0xf7,0xbf,0xfb,
-0xff,0xff,0xff,0xdf,0xf7,0xff,0xf1,0xf7,0xbf,0xfb,0xff,0xff,0xff,0x7f,0xde,0xff,
-0xff,0xff,0xff,0xff,0xff,0xed,0xf7,0xff,0xff,0x7f,0xd0,0xf0,0x3f,0xff,0xff,0xff,
-0xfe,0xf8,0x30,0x00,0x00,0x00,0x00,0x40,0x00,0x00,0x00,0x00,0xe0,0x00,0x00,0x80,
-0x20,0x01,0x01,0x92,0x00,0x01,0x01,0x00,0xe0,0x1c,0x60,0x20,0x30,0x08,0x08,0x00,
-0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x80,0x00,0xc1,0xf0,0x6f,0xff,0xff,0xff,0xfe,
-0xff,0xff,0xff,0xff,0xff,0xdb,0xfe,0xff,0xff,0xdf,0xff,0xfc,0x7f,0xfb,0xbf,0xff,
-0xff,0xff,0xff,0xff,0xf1,0xf6,0xff,0xf7,0x7e,0x3f,0xff,0x7f,0xff,0xff,0xff,0xf7,
-0xff,0xff,0xff,0xed,0xff,0xdf,0xff,0xb7,0xff,0xf0,0x3f,0xff,0xff,0xff,0xfe,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0xff,0xff,0xff,0xff,0xfe,0xff,0xff,
-0xff,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xdf,0xff,0xff,0xff,0xff,0xbf,0xff,0xdf,
-0x57,0xef,0xf1,0xfd,0xfe,0x7f,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xdf,0xfb,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf0,0x7f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,
-0xff,0xff,0xff,0x7f,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xfb,0xff,0xdf,0xff,
-0xff,0xf1,0xfd,0xff,0x7f,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xfe,0xff,0xff,0xff,0xff,0xf0,0x9f,0xff,0xff,0xff,0xfe,0xf7,0xfd,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xbf,0xff,0xff,0xff,0xff,0xff,
-0xf1,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xf0,0x6f,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xf1,
-0xff,0xff,0xfd,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xfb,0xff,0xff,0xff,0xfe,0xff,0xff,0xfb,0x6f,0xff,0xfe,0xbf,0xff,0xf1,0xff,
-0xf7,0xff,0xff,0x7f,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xfd,
-0xff,0xff,0xff,0xf0,0xef,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xfb,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0x57,0xff,0xfd,0xbf,0xff,0xf1,0xff,0xef,
-0xfe,0xff,0xbf,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xfe,0xff,
-0xde,0xff,0xf0,0xcf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xf7,0xdb,0xff,0xdb,0xfd,
-0xf6,0xff,0xf6,0xff,0x3c,0xbc,0xbc,0xbf,0xdf,0x6f,0xe7,0x2f,0xf1,0x3c,0xbf,0xfd,
-0xbf,0xdf,0x6f,0xff,0x6f,0xf7,0xdb,0xff,0xdb,0xfd,0xf6,0xff,0xf6,0xff,0xff,0xff,
-0x02,0x01,0xdf,0xff,0xff,0xff,0xfe,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,
-0xff,0xff,0xff,0xff,0xff,0xff };
diff --git a/drivers/net/igb/e1000_phy.c b/drivers/net/igb/e1000_phy.c
index de2d48624683..f50fac25be40 100644
--- a/drivers/net/igb/e1000_phy.c
+++ b/drivers/net/igb/e1000_phy.c
@@ -448,8 +448,11 @@ s32 igb_copper_link_setup_igp(struct e1000_hw *hw)
 		goto out;
 	}
 
-	/* Wait 15ms for MAC to configure PHY from NVM settings. */
-	msleep(15);
+	/*
+	 * Wait 100ms for MAC to configure PHY from NVM settings, to avoid
+	 * timeout issues when LFS is enabled.
+	 */
+	msleep(100);
 
 	/*
 	 * The NVM settings will configure LPLU in D3 for
diff --git a/drivers/net/igb/igb_ethtool.c b/drivers/net/igb/igb_ethtool.c
index fb09c8ad9f0d..27eae49e79c2 100644
--- a/drivers/net/igb/igb_ethtool.c
+++ b/drivers/net/igb/igb_ethtool.c
@@ -1419,7 +1419,6 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter)
 {
 	struct e1000_hw *hw = &adapter->hw;
 	u32 ctrl_reg = 0;
-	u32 stat_reg = 0;
 
 	hw->mac.autoneg = false;
 
@@ -1443,18 +1442,11 @@ static int igb_integrated_phy_loopback(struct igb_adapter *adapter)
 	ctrl_reg |= (E1000_CTRL_FRCSPD | /* Set the Force Speed Bit */
 		     E1000_CTRL_FRCDPX | /* Set the Force Duplex Bit */
 		     E1000_CTRL_SPD_1000 |/* Force Speed to 1000 */
-		     E1000_CTRL_FD);	 /* Force Duplex to FULL */
+		     E1000_CTRL_FD |	 /* Force Duplex to FULL */
+		     E1000_CTRL_SLU);	 /* Set link up enable bit */
 
-	if (hw->phy.media_type == e1000_media_type_copper &&
-	    hw->phy.type == e1000_phy_m88)
+	if (hw->phy.type == e1000_phy_m88)
 		ctrl_reg |= E1000_CTRL_ILOS; /* Invert Loss of Signal */
-	else {
-		/* Set the ILOS bit on the fiber Nic if half duplex link is
-		 * detected. */
-		stat_reg = rd32(E1000_STATUS);
-		if ((stat_reg & E1000_STATUS_FD) == 0)
-			ctrl_reg |= (E1000_CTRL_ILOS | E1000_CTRL_SLU);
-	}
 
 	wr32(E1000_CTRL, ctrl_reg);
 
diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c
index ca842163dce4..03aa9593dd9e 100644
--- a/drivers/net/igb/igb_main.c
+++ b/drivers/net/igb/igb_main.c
@@ -135,8 +135,8 @@ static inline int igb_set_vf_rlpml(struct igb_adapter *, int, int);
 static int igb_set_vf_mac(struct igb_adapter *adapter, int, unsigned char *);
 static void igb_restore_vf_multicasts(struct igb_adapter *adapter);
 
-static int igb_suspend(struct pci_dev *, pm_message_t);
 #ifdef CONFIG_PM
+static int igb_suspend(struct pci_dev *, pm_message_t);
 static int igb_resume(struct pci_dev *);
 #endif
 static void igb_shutdown(struct pci_dev *);
@@ -420,6 +420,9 @@ static void igb_free_queues(struct igb_adapter *adapter)
 	for (i = 0; i < adapter->num_rx_queues; i++)
 		netif_napi_del(&adapter->rx_ring[i].napi);
 
+	adapter->num_rx_queues = 0;
+	adapter->num_tx_queues = 0;
+
 	kfree(adapter->tx_ring);
 	kfree(adapter->rx_ring);
 }
@@ -1476,9 +1479,10 @@ static int __devinit igb_probe(struct pci_dev *pdev,
 		 netdev->name,
 		 ((hw->bus.speed == e1000_bus_speed_2500)
 		  ? "2.5Gb/s" : "unknown"),
-		 ((hw->bus.width == e1000_bus_width_pcie_x4)
-		  ? "Width x4" : (hw->bus.width == e1000_bus_width_pcie_x1)
-		  ? "Width x1" : "unknown"),
+		 ((hw->bus.width == e1000_bus_width_pcie_x4) ? "Width x4" :
+		  (hw->bus.width == e1000_bus_width_pcie_x2) ? "Width x2" :
+		  (hw->bus.width == e1000_bus_width_pcie_x1) ? "Width x1" :
+		   "unknown"),
 		 netdev->dev_addr);
 
 	igb_read_part_num(hw, &part_num);
@@ -5056,7 +5060,7 @@ int igb_set_spd_dplx(struct igb_adapter *adapter, u16 spddplx)
 	return 0;
 }
 
-static int igb_suspend(struct pci_dev *pdev, pm_message_t state)
+static int __igb_shutdown(struct pci_dev *pdev, bool *enable_wake)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
 	struct igb_adapter *adapter = netdev_priv(netdev);
@@ -5115,15 +5119,9 @@ static int igb_suspend(struct pci_dev *pdev, pm_message_t state)
 		wr32(E1000_WUFC, 0);
 	}
 
-	/* make sure adapter isn't asleep if manageability/wol is enabled */
-	if (wufc || adapter->en_mng_pt) {
-		pci_enable_wake(pdev, PCI_D3hot, 1);
-		pci_enable_wake(pdev, PCI_D3cold, 1);
-	} else {
+	*enable_wake = wufc || adapter->en_mng_pt;
+	if (!*enable_wake)
 		igb_shutdown_fiber_serdes_link_82575(hw);
-		pci_enable_wake(pdev, PCI_D3hot, 0);
-		pci_enable_wake(pdev, PCI_D3cold, 0);
-	}
 
 	/* Release control of h/w to f/w.  If f/w is AMT enabled, this
 	 * would have already happened in close and is redundant. */
@@ -5131,12 +5129,29 @@ static int igb_suspend(struct pci_dev *pdev, pm_message_t state)
 
 	pci_disable_device(pdev);
 
-	pci_set_power_state(pdev, pci_choose_state(pdev, state));
-
 	return 0;
 }
 
 #ifdef CONFIG_PM
+static int igb_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	int retval;
+	bool wake;
+
+	retval = __igb_shutdown(pdev, &wake);
+	if (retval)
+		return retval;
+
+	if (wake) {
+		pci_prepare_to_sleep(pdev);
+	} else {
+		pci_wake_from_d3(pdev, false);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
+
+	return 0;
+}
+
 static int igb_resume(struct pci_dev *pdev)
 {
 	struct net_device *netdev = pci_get_drvdata(pdev);
@@ -5189,7 +5204,14 @@ static int igb_resume(struct pci_dev *pdev)
 
 static void igb_shutdown(struct pci_dev *pdev)
 {
-	igb_suspend(pdev, PMSG_SUSPEND);
+	bool wake;
+
+	__igb_shutdown(pdev, &wake);
+
+	if (system_state == SYSTEM_POWER_OFF) {
+		pci_wake_from_d3(pdev, wake);
+		pci_set_power_state(pdev, PCI_D3hot);
+	}
 }
 
 #ifdef CONFIG_NET_POLL_CONTROLLER
diff --git a/drivers/net/ixgbe/ixgbe_82598.c b/drivers/net/ixgbe/ixgbe_82598.c
index ed265a7a898f..de4db0dc7879 100644
--- a/drivers/net/ixgbe/ixgbe_82598.c
+++ b/drivers/net/ixgbe/ixgbe_82598.c
@@ -411,7 +411,8 @@ static s32 ixgbe_setup_fc_82598(struct ixgbe_hw *hw, s32 packetbuf_num)
 
 	/* Decide whether to use autoneg or not. */
 	hw->mac.ops.check_link(hw, &speed, &link_up, false);
-	if (hw->phy.multispeed_fiber && (speed == IXGBE_LINK_SPEED_1GB_FULL))
+	if (!hw->fc.disable_fc_autoneg && hw->phy.multispeed_fiber &&
+	    (speed == IXGBE_LINK_SPEED_1GB_FULL))
 		ret_val = ixgbe_fc_autoneg(hw);
 
 	if (ret_val)
diff --git a/drivers/net/ixgbe/ixgbe_common.c b/drivers/net/ixgbe/ixgbe_common.c
index 8cfd3fd309a0..63ab6671d08e 100644
--- a/drivers/net/ixgbe/ixgbe_common.c
+++ b/drivers/net/ixgbe/ixgbe_common.c
@@ -1937,7 +1937,8 @@ s32 ixgbe_setup_fc_generic(struct ixgbe_hw *hw, s32 packetbuf_num)
 
 	/* Decide whether to use autoneg or not. */
 	hw->mac.ops.check_link(hw, &speed, &link_up, false);
-	if (hw->phy.multispeed_fiber && (speed == IXGBE_LINK_SPEED_1GB_FULL))
+	if (!hw->fc.disable_fc_autoneg && hw->phy.multispeed_fiber &&
+	    (speed == IXGBE_LINK_SPEED_1GB_FULL))
 		ret_val = ixgbe_fc_autoneg(hw);
 
 	if (ret_val)
diff --git a/drivers/net/ixgbe/ixgbe_common.h b/drivers/net/ixgbe/ixgbe_common.h
index 7e94d6d399ab..24f73e719c3f 100644
--- a/drivers/net/ixgbe/ixgbe_common.h
+++ b/drivers/net/ixgbe/ixgbe_common.h
@@ -96,14 +96,11 @@ s32 ixgbe_write_analog_reg8_generic(struct ixgbe_hw *hw, u32 reg, u8 val);
 #define IXGBE_WRITE_FLUSH(a) IXGBE_READ_REG(a, IXGBE_STATUS)
 
 #ifdef DEBUG
+extern char *ixgbe_get_hw_dev_name(struct ixgbe_hw *hw);
 #define hw_dbg(hw, format, arg...) \
-printk(KERN_DEBUG, "%s: " format, ixgbe_get_hw_dev_name(hw), ##arg);
+	printk(KERN_DEBUG "%s: " format, ixgbe_get_hw_dev_name(hw), ##arg)
 #else
-static inline int __attribute__ ((format (printf, 2, 3)))
-hw_dbg(struct ixgbe_hw *hw, const char *format, ...)
-{
-	return 0;
-}
+#define hw_dbg(hw, format, arg...) do {} while (0)
 #endif
 
 #endif /* IXGBE_COMMON */
diff --git a/drivers/net/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ixgbe/ixgbe_dcb_nl.c
index 0a8731f1f237..bd0a0c276952 100644
--- a/drivers/net/ixgbe/ixgbe_dcb_nl.c
+++ b/drivers/net/ixgbe/ixgbe_dcb_nl.c
@@ -90,6 +90,8 @@ int ixgbe_copy_dcb_cfg(struct ixgbe_dcb_config *src_dcb_cfg,
 			src_dcb_cfg->tc_config[i - DCB_PFC_UP_ATTR_0].dcb_pfc;
 	}
 
+	dst_dcb_cfg->pfc_mode_enable = src_dcb_cfg->pfc_mode_enable;
+
 	return 0;
 }
 
@@ -298,8 +300,10 @@ static void ixgbe_dcbnl_set_pfc_cfg(struct net_device *netdev, int priority,
 
 	adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc = setting;
 	if (adapter->temp_dcb_cfg.tc_config[priority].dcb_pfc !=
-	    adapter->dcb_cfg.tc_config[priority].dcb_pfc)
+	    adapter->dcb_cfg.tc_config[priority].dcb_pfc) {
 		adapter->dcb_set_bitmap |= BIT_PFC;
+		adapter->temp_dcb_cfg.pfc_mode_enable = true;
+	}
 }
 
 static void ixgbe_dcbnl_get_pfc_cfg(struct net_device *netdev, int priority,
diff --git a/drivers/net/ixgbe/ixgbe_ethtool.c b/drivers/net/ixgbe/ixgbe_ethtool.c
index 18ecba7f6ecb..aafc120f164e 100644
--- a/drivers/net/ixgbe/ixgbe_ethtool.c
+++ b/drivers/net/ixgbe/ixgbe_ethtool.c
@@ -129,6 +129,15 @@ static int ixgbe_get_settings(struct net_device *netdev,
 			ecmd->advertising |= ADVERTISED_10000baseT_Full;
 		if (hw->phy.autoneg_advertised & IXGBE_LINK_SPEED_1GB_FULL)
 			ecmd->advertising |= ADVERTISED_1000baseT_Full;
+		/*
+		 * It's possible that phy.autoneg_advertised may not be
+		 * set yet.  If so display what the default would be -
+		 * both 1G and 10G supported.
+		 */
+		if (!(ecmd->advertising & (ADVERTISED_1000baseT_Full |
+					   ADVERTISED_10000baseT_Full)))
+			ecmd->advertising |= (ADVERTISED_10000baseT_Full |
+					      ADVERTISED_1000baseT_Full);
 
 		ecmd->port = PORT_TP;
 	} else if (hw->phy.media_type == ixgbe_media_type_backplane) {
@@ -225,7 +234,16 @@ static void ixgbe_get_pauseparam(struct net_device *netdev,
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
-	pause->autoneg = (hw->fc.current_mode == ixgbe_fc_full ? 1 : 0);
+	/*
+	 * Flow Control Autoneg isn't on if
+	 *  - we didn't ask for it OR
+	 *  - it failed, we know this by tx & rx being off
+	 */
+	if (hw->fc.disable_fc_autoneg ||
+	    (hw->fc.current_mode == ixgbe_fc_none))
+		pause->autoneg = 0;
+	else
+		pause->autoneg = 1;
 
 	if (hw->fc.current_mode == ixgbe_fc_rx_pause) {
 		pause->rx_pause = 1;
@@ -243,8 +261,12 @@ static int ixgbe_set_pauseparam(struct net_device *netdev,
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
 	struct ixgbe_hw *hw = &adapter->hw;
 
-	if ((pause->autoneg == AUTONEG_ENABLE) ||
-	    (pause->rx_pause && pause->tx_pause))
+	if (pause->autoneg != AUTONEG_ENABLE)
+		hw->fc.disable_fc_autoneg = true;
+	else
+		hw->fc.disable_fc_autoneg = false;
+
+	if (pause->rx_pause && pause->tx_pause)
 		hw->fc.requested_mode = ixgbe_fc_full;
 	else if (pause->rx_pause && !pause->tx_pause)
 		hw->fc.requested_mode = ixgbe_fc_rx_pause;
@@ -712,9 +734,10 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
                                struct ethtool_ringparam *ring)
 {
 	struct ixgbe_adapter *adapter = netdev_priv(netdev);
-	struct ixgbe_ring *temp_ring;
+	struct ixgbe_ring *temp_tx_ring, *temp_rx_ring;
 	int i, err;
 	u32 new_rx_count, new_tx_count;
+	bool need_update = false;
 
 	if ((ring->rx_mini_pending) || (ring->rx_jumbo_pending))
 		return -EINVAL;
@@ -733,80 +756,94 @@ static int ixgbe_set_ringparam(struct net_device *netdev,
 		return 0;
 	}
 
-	temp_ring = kcalloc(adapter->num_tx_queues,
-	                    sizeof(struct ixgbe_ring), GFP_KERNEL);
-	if (!temp_ring)
-		return -ENOMEM;
-
 	while (test_and_set_bit(__IXGBE_RESETTING, &adapter->state))
 		msleep(1);
 
-	if (new_tx_count != adapter->tx_ring->count) {
+	temp_tx_ring = kcalloc(adapter->num_tx_queues,
+	                       sizeof(struct ixgbe_ring), GFP_KERNEL);
+	if (!temp_tx_ring) {
+		err = -ENOMEM;
+		goto err_setup;
+	}
+
+	if (new_tx_count != adapter->tx_ring_count) {
+		memcpy(temp_tx_ring, adapter->tx_ring,
+		       adapter->num_tx_queues * sizeof(struct ixgbe_ring));
 		for (i = 0; i < adapter->num_tx_queues; i++) {
-			temp_ring[i].count = new_tx_count;
-			err = ixgbe_setup_tx_resources(adapter, &temp_ring[i]);
+			temp_tx_ring[i].count = new_tx_count;
+			err = ixgbe_setup_tx_resources(adapter,
+			                               &temp_tx_ring[i]);
 			if (err) {
 				while (i) {
 					i--;
 					ixgbe_free_tx_resources(adapter,
-					                        &temp_ring[i]);
+					                        &temp_tx_ring[i]);
 				}
 				goto err_setup;
 			}
-			temp_ring[i].v_idx = adapter->tx_ring[i].v_idx;
+			temp_tx_ring[i].v_idx = adapter->tx_ring[i].v_idx;
 		}
-		if (netif_running(netdev))
-			netdev->netdev_ops->ndo_stop(netdev);
-		ixgbe_reset_interrupt_capability(adapter);
-		ixgbe_napi_del_all(adapter);
-		INIT_LIST_HEAD(&netdev->napi_list);
-		kfree(adapter->tx_ring);
-		adapter->tx_ring = temp_ring;
-		temp_ring = NULL;
-		adapter->tx_ring_count = new_tx_count;
+		need_update = true;
 	}
 
-	temp_ring = kcalloc(adapter->num_rx_queues,
-	                    sizeof(struct ixgbe_ring), GFP_KERNEL);
-	if (!temp_ring) {
-		if (netif_running(netdev))
-			netdev->netdev_ops->ndo_open(netdev);
-		return -ENOMEM;
+	temp_rx_ring = kcalloc(adapter->num_rx_queues,
+	                       sizeof(struct ixgbe_ring), GFP_KERNEL);
+	if ((!temp_rx_ring) && (need_update)) {
+		for (i = 0; i < adapter->num_tx_queues; i++)
+			ixgbe_free_tx_resources(adapter, &temp_tx_ring[i]);
+		kfree(temp_tx_ring);
+		err = -ENOMEM;
+		goto err_setup;
 	}
 
-	if (new_rx_count != adapter->rx_ring->count) {
+	if (new_rx_count != adapter->rx_ring_count) {
+		memcpy(temp_rx_ring, adapter->rx_ring,
+		       adapter->num_rx_queues * sizeof(struct ixgbe_ring));
 		for (i = 0; i < adapter->num_rx_queues; i++) {
-			temp_ring[i].count = new_rx_count;
-			err = ixgbe_setup_rx_resources(adapter, &temp_ring[i]);
+			temp_rx_ring[i].count = new_rx_count;
+			err = ixgbe_setup_rx_resources(adapter,
+			                               &temp_rx_ring[i]);
 			if (err) {
 				while (i) {
 					i--;
 					ixgbe_free_rx_resources(adapter,
-					                        &temp_ring[i]);
+					                      &temp_rx_ring[i]);
 				}
 				goto err_setup;
 			}
-			temp_ring[i].v_idx = adapter->rx_ring[i].v_idx;
+			temp_rx_ring[i].v_idx = adapter->rx_ring[i].v_idx;
 		}
+		need_update = true;
+	}
+
+	/* if rings need to be updated, here's the place to do it in one shot */
+	if (need_update) {
 		if (netif_running(netdev))
-			netdev->netdev_ops->ndo_stop(netdev);
-		ixgbe_reset_interrupt_capability(adapter);
-		ixgbe_napi_del_all(adapter);
-		INIT_LIST_HEAD(&netdev->napi_list);
-		kfree(adapter->rx_ring);
-		adapter->rx_ring = temp_ring;
-		temp_ring = NULL;
-
-		adapter->rx_ring_count = new_rx_count;
+			ixgbe_down(adapter);
+
+		/* tx */
+		if (new_tx_count != adapter->tx_ring_count) {
+			kfree(adapter->tx_ring);
+			adapter->tx_ring = temp_tx_ring;
+			temp_tx_ring = NULL;
+			adapter->tx_ring_count = new_tx_count;
+		}
+
+		/* rx */
+		if (new_rx_count != adapter->rx_ring_count) {
+			kfree(adapter->rx_ring);
+			adapter->rx_ring = temp_rx_ring;
+			temp_rx_ring = NULL;
+			adapter->rx_ring_count = new_rx_count;
+		}
 	}
 
 	/* success! */
 	err = 0;
-err_setup:
-	ixgbe_init_interrupt_scheme(adapter);
 	if (netif_running(netdev))
-		netdev->netdev_ops->ndo_open(netdev);
+		ixgbe_up(adapter);
 
+err_setup:
 	clear_bit(__IXGBE_RESETTING, &adapter->state);
 	return err;
 }
diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c
index 79aa811c403c..286ecc0e6ab7 100644
--- a/drivers/net/ixgbe/ixgbe_main.c
+++ b/drivers/net/ixgbe/ixgbe_main.c
@@ -187,15 +187,14 @@ static void ixgbe_unmap_and_free_tx_resource(struct ixgbe_adapter *adapter,
                                              struct ixgbe_tx_buffer
                                              *tx_buffer_info)
 {
-	if (tx_buffer_info->dma) {
-		pci_unmap_page(adapter->pdev, tx_buffer_info->dma,
-		               tx_buffer_info->length, PCI_DMA_TODEVICE);
-		tx_buffer_info->dma = 0;
-	}
+	tx_buffer_info->dma = 0;
 	if (tx_buffer_info->skb) {
+		skb_dma_unmap(&adapter->pdev->dev, tx_buffer_info->skb,
+		              DMA_TO_DEVICE);
 		dev_kfree_skb_any(tx_buffer_info->skb);
 		tx_buffer_info->skb = NULL;
 	}
+	tx_buffer_info->time_stamp = 0;
 	/* tx_buffer_info must be completely set up in the transmit path */
 }
 
@@ -204,15 +203,11 @@ static inline bool ixgbe_check_tx_hang(struct ixgbe_adapter *adapter,
                                        unsigned int eop)
 {
 	struct ixgbe_hw *hw = &adapter->hw;
-	u32 head, tail;
 
 	/* Detect a transmit hang in hardware, this serializes the
 	 * check with the clearing of time_stamp and movement of eop */
-	head = IXGBE_READ_REG(hw, tx_ring->head);
-	tail = IXGBE_READ_REG(hw, tx_ring->tail);
 	adapter->detect_tx_hung = false;
-	if ((head != tail) &&
-	    tx_ring->tx_buffer_info[eop].time_stamp &&
+	if (tx_ring->tx_buffer_info[eop].time_stamp &&
 	    time_after(jiffies, tx_ring->tx_buffer_info[eop].time_stamp + HZ) &&
 	    !(IXGBE_READ_REG(&adapter->hw, IXGBE_TFCS) & IXGBE_TFCS_TXOFF)) {
 		/* detected Tx unit hang */
@@ -227,7 +222,8 @@ static inline bool ixgbe_check_tx_hang(struct ixgbe_adapter *adapter,
 			"  time_stamp           <%lx>\n"
 			"  jiffies              <%lx>\n",
 			tx_ring->queue_index,
-			head, tail,
+			IXGBE_READ_REG(hw, tx_ring->head),
+			IXGBE_READ_REG(hw, tx_ring->tail),
 			tx_ring->next_to_use, eop,
 			tx_ring->tx_buffer_info[eop].time_stamp, jiffies);
 		return true;
@@ -2934,6 +2930,7 @@ err_tx_ring_allocation:
  **/
 static int ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter)
 {
+	struct ixgbe_hw *hw = &adapter->hw;
 	int err = 0;
 	int vector, v_budget;
 
@@ -2948,12 +2945,12 @@ static int ixgbe_set_interrupt_capability(struct ixgbe_adapter *adapter)
 
 	/*
 	 * At the same time, hardware can only support a maximum of
-	 * MAX_MSIX_COUNT vectors.  With features such as RSS and VMDq,
-	 * we can easily reach upwards of 64 Rx descriptor queues and
-	 * 32 Tx queues.  Thus, we cap it off in those rare cases where
-	 * the cpu count also exceeds our vector limit.
+	 * hw.mac->max_msix_vectors vectors.  With features
+	 * such as RSS and VMDq, we can easily surpass the number of Rx and Tx
+	 * descriptor queues supported by our device.  Thus, we cap it off in
+	 * those rare cases where the cpu count also exceeds our vector limit.
 	 */
-	v_budget = min(v_budget, MAX_MSIX_COUNT);
+	v_budget = min(v_budget, (int)hw->mac.max_msix_vectors);
 
 	/* A failure in MSI-X entry allocation isn't fatal, but it does
 	 * mean we disable MSI-X capabilities of the adapter. */
@@ -3169,11 +3166,13 @@ static int __devinit ixgbe_sw_init(struct ixgbe_adapter *adapter)
 #endif
 
 	/* default flow control settings */
-	hw->fc.requested_mode = ixgbe_fc_none;
+	hw->fc.requested_mode = ixgbe_fc_full;
+	hw->fc.current_mode = ixgbe_fc_full;	/* init for ethtool output */
 	hw->fc.high_water = IXGBE_DEFAULT_FCRTH;
 	hw->fc.low_water = IXGBE_DEFAULT_FCRTL;
 	hw->fc.pause_time = IXGBE_DEFAULT_FCPAUSE;
 	hw->fc.send_xon = true;
+	hw->fc.disable_fc_autoneg = false;
 
 	/* enable itr by default in dynamic mode */
 	adapter->itr_setting = 1;
@@ -3489,10 +3488,10 @@ err_up:
 	ixgbe_release_hw_control(adapter);
 	ixgbe_free_irq(adapter);
 err_req_irq:
-	ixgbe_free_all_rx_resources(adapter);
 err_setup_rx:
-	ixgbe_free_all_tx_resources(adapter);
+	ixgbe_free_all_rx_resources(adapter);
 err_setup_tx:
+	ixgbe_free_all_tx_resources(adapter);
 	ixgbe_reset(adapter);
 
 	return err;
@@ -4163,32 +4162,39 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter,
                         struct sk_buff *skb, unsigned int first)
 {
 	struct ixgbe_tx_buffer *tx_buffer_info;
-	unsigned int len = skb->len;
+	unsigned int len = skb_headlen(skb);
 	unsigned int offset = 0, size, count = 0, i;
 	unsigned int nr_frags = skb_shinfo(skb)->nr_frags;
 	unsigned int f;
-
-	len -= skb->data_len;
+	dma_addr_t *map;
 
 	i = tx_ring->next_to_use;
 
+	if (skb_dma_map(&adapter->pdev->dev, skb, DMA_TO_DEVICE)) {
+		dev_err(&adapter->pdev->dev, "TX DMA map failed\n");
+		return 0;
+	}
+
+	map = skb_shinfo(skb)->dma_maps;
+
 	while (len) {
 		tx_buffer_info = &tx_ring->tx_buffer_info[i];
 		size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD);
 
 		tx_buffer_info->length = size;
-		tx_buffer_info->dma = pci_map_single(adapter->pdev,
-		                                     skb->data + offset,
-		                                     size, PCI_DMA_TODEVICE);
+		tx_buffer_info->dma = map[0] + offset;
 		tx_buffer_info->time_stamp = jiffies;
 		tx_buffer_info->next_to_watch = i;
 
 		len -= size;
 		offset += size;
 		count++;
-		i++;
-		if (i == tx_ring->count)
-			i = 0;
+
+		if (len) {
+			i++;
+			if (i == tx_ring->count)
+				i = 0;
+		}
 	}
 
 	for (f = 0; f < nr_frags; f++) {
@@ -4196,33 +4202,27 @@ static int ixgbe_tx_map(struct ixgbe_adapter *adapter,
 
 		frag = &skb_shinfo(skb)->frags[f];
 		len = frag->size;
-		offset = frag->page_offset;
+		offset = 0;
 
 		while (len) {
+			i++;
+			if (i == tx_ring->count)
+				i = 0;
+
 			tx_buffer_info = &tx_ring->tx_buffer_info[i];
 			size = min(len, (uint)IXGBE_MAX_DATA_PER_TXD);
 
 			tx_buffer_info->length = size;
-			tx_buffer_info->dma = pci_map_page(adapter->pdev,
-			                                   frag->page,
-			                                   offset,
-			                                   size,
-			                                   PCI_DMA_TODEVICE);
+			tx_buffer_info->dma = map[f + 1] + offset;
 			tx_buffer_info->time_stamp = jiffies;
 			tx_buffer_info->next_to_watch = i;
 
 			len -= size;
 			offset += size;
 			count++;
-			i++;
-			if (i == tx_ring->count)
-				i = 0;
 		}
 	}
-	if (i == 0)
-		i = tx_ring->count - 1;
-	else
-		i = i - 1;
+
 	tx_ring->tx_buffer_info[i].skb = skb;
 	tx_ring->tx_buffer_info[first].next_to_watch = i;
 
@@ -4388,13 +4388,19 @@ static int ixgbe_xmit_frame(struct sk_buff *skb, struct net_device *netdev)
 	         (skb->ip_summed == CHECKSUM_PARTIAL))
 		tx_flags |= IXGBE_TX_FLAGS_CSUM;
 
-	ixgbe_tx_queue(adapter, tx_ring, tx_flags,
-	               ixgbe_tx_map(adapter, tx_ring, skb, first),
-	               skb->len, hdr_len);
+	count = ixgbe_tx_map(adapter, tx_ring, skb, first);
 
-	netdev->trans_start = jiffies;
+	if (count) {
+		ixgbe_tx_queue(adapter, tx_ring, tx_flags, count, skb->len,
+		               hdr_len);
+		netdev->trans_start = jiffies;
+		ixgbe_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED);
 
-	ixgbe_maybe_stop_tx(netdev, tx_ring, DESC_NEEDED);
+	} else {
+		dev_kfree_skb_any(skb);
+		tx_ring->tx_buffer_info[first].time_stamp = 0;
+		tx_ring->next_to_use = first;
+	}
 
 	return NETDEV_TX_OK;
 }
@@ -4987,8 +4993,20 @@ static int ixgbe_notify_dca(struct notifier_block *nb, unsigned long event,
 
 	return ret_val ? NOTIFY_BAD : NOTIFY_DONE;
 }
+
 #endif /* CONFIG_IXGBE_DCA */
+#ifdef DEBUG
+/**
+ * ixgbe_get_hw_dev_name - return device name string
+ * used by hardware layer to print debugging information
+ **/
+char *ixgbe_get_hw_dev_name(struct ixgbe_hw *hw)
+{
+	struct ixgbe_adapter *adapter = hw->back;
+	return adapter->netdev->name;
+}
 
+#endif
 module_exit(ixgbe_exit_module);
 
 /* ixgbe_main.c */
diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h
index 2b2ecba7b609..030ff0a9ea67 100644
--- a/drivers/net/ixgbe/ixgbe_type.h
+++ b/drivers/net/ixgbe/ixgbe_type.h
@@ -2005,6 +2005,7 @@ struct ixgbe_fc_info {
 	u16 pause_time; /* Flow Control Pause timer */
 	bool send_xon; /* Flow control send XON */
 	bool strict_ieee; /* Strict IEEE mode */
+	bool disable_fc_autoneg; /* Turn off autoneg FC mode */
 	enum ixgbe_fc_mode current_mode; /* FC mode in effect */
 	enum ixgbe_fc_mode requested_mode; /* FC mode requested by caller */
 };
diff --git a/drivers/net/mlx4/en_netdev.c b/drivers/net/mlx4/en_netdev.c
index 9f6644a44030..303c23de6cac 100644
--- a/drivers/net/mlx4/en_netdev.c
+++ b/drivers/net/mlx4/en_netdev.c
@@ -505,7 +505,7 @@ out:
 
 static void mlx4_en_do_get_stats(struct work_struct *work)
 {
-	struct delayed_work *delay = container_of(work, struct delayed_work, work);
+	struct delayed_work *delay = to_delayed_work(work);
 	struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv,
 						 stats_task);
 	struct mlx4_en_dev *mdev = priv->mdev;
diff --git a/drivers/net/mlx4/en_rx.c b/drivers/net/mlx4/en_rx.c
index a4130e764991..7e40741fb7d8 100644
--- a/drivers/net/mlx4/en_rx.c
+++ b/drivers/net/mlx4/en_rx.c
@@ -298,7 +298,7 @@ static void mlx4_en_free_rx_buf(struct mlx4_en_priv *priv,
 
 void mlx4_en_rx_refill(struct work_struct *work)
 {
-	struct delayed_work *delay = container_of(work, struct delayed_work, work);
+	struct delayed_work *delay = to_delayed_work(work);
 	struct mlx4_en_priv *priv = container_of(delay, struct mlx4_en_priv,
 						 refill_task);
 	struct mlx4_en_dev *mdev = priv->mdev;
diff --git a/drivers/net/mlx4/sense.c b/drivers/net/mlx4/sense.c
index 6d5089ecb5af..f36ae691cab3 100644
--- a/drivers/net/mlx4/sense.c
+++ b/drivers/net/mlx4/sense.c
@@ -103,7 +103,7 @@ void mlx4_do_sense_ports(struct mlx4_dev *dev,
 
 static void mlx4_sense_port(struct work_struct *work)
 {
-	struct delayed_work *delay = container_of(work, struct delayed_work, work);
+	struct delayed_work *delay = to_delayed_work(work);
 	struct mlx4_sense *sense = container_of(delay, struct mlx4_sense,
 						sense_poll);
 	struct mlx4_dev *dev = sense->dev;
diff --git a/drivers/net/pcmcia/ositech.h b/drivers/net/pcmcia/ositech.h
deleted file mode 100644
index 4126efc355bd..000000000000
--- a/drivers/net/pcmcia/ositech.h
+++ /dev/null
@@ -1,358 +0,0 @@
-/*
-    This file contains the firmware of Seven of Diamonds from OSITECH.
-    (Special thanks to Kevin MacPherson of OSITECH)
-
-    This software may be used and distributed according to the terms of
-    the GNU General Public License, incorporated herein by reference.
-*/
-
-    static const u_char __Xilinx7OD[] = {
-    0xFF, 0x04, 0xA0, 0x36, 0xF3, 0xEC, 0xFF, 0xFF, 0xFF, 0xDF, 0xFB, 0xFF,
-    0xF3, 0xFF, 0xFF, 0xFF, 
-    0xEF, 0x3F, 0xFF, 0xF7, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0x7F, 0xFE, 0xFF,
-    0xCE, 0xFE, 0xFE, 0xFE, 
-    0xFE, 0xDE, 0xBD, 0xDD, 0xFD, 0xFF, 0xFD, 0xCF, 0xF7, 0xBF, 0x7F, 0xFF,
-    0x7F, 0x3F, 0xFE, 0xBF, 
-    0xFF, 0xFF, 0xFF, 0xBC, 0xFF, 0xFF, 0xBD, 0xB5, 0x7F, 0x7F, 0xBF, 0xBF,
-    0x7F, 0xFF, 0xEF, 0xFF, 
-    0xFF, 0xFF, 0xFB, 0xFF, 0xF7, 0xF7, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0xDE,
-    0xFE, 0xFE, 0xFA, 0xDE, 
-    0xBD, 0xFD, 0xED, 0xFD, 0xFD, 0xCF, 0xEF, 0xEF, 0xEF, 0xEF, 0xC7, 0xDF,
-    0xDF, 0xDF, 0xDF, 0xDF, 
-    0xFF, 0x7E, 0xFE, 0xFD, 0x7D, 0x6D, 0xEE, 0xFE, 0x7C, 0xFB, 0xF4, 0xFB,
-    0xCF, 0xDB, 0xDF, 0xFF, 
-    0xFF, 0xBB, 0x7F, 0xFF, 0x7F, 0xFF, 0xF7, 0xFF, 0x9E, 0xBF, 0x3B, 0xBF,
-    0xBF, 0x7F, 0x7F, 0x7F, 
-    0x7E, 0x6F, 0xDF, 0xEF, 0xF5, 0xF6, 0xFD, 0xF6, 0xF5, 0xED, 0xEB, 0xFF,
-    0xEF, 0xEF, 0xEF, 0x7E, 
-    0x7F, 0x7F, 0x6F, 0x7F, 0xFF, 0xFE, 0xFE, 0xFE, 0xFE, 0xFE, 0xEF, 0xBF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xBC, 0x1F, 0x1F, 0xEE, 0xFF, 0xBC,
-    0xB7, 0xFF, 0xDF, 0xFF, 
-    0xDF, 0xEF, 0x3B, 0xE3, 0xD3, 0xFF, 0xFB, 0xFF, 0xFF, 0xDF, 0xFF, 0xFF,
-    0xFF, 0xBA, 0xBF, 0x2D, 
-    0xDB, 0xBD, 0xFD, 0xDB, 0xDF, 0xFA, 0xFB, 0xFF, 0xEF, 0xFB, 0xDB, 0xF3,
-    0xFF, 0xDF, 0xFD, 0x7F, 
-    0xEF, 0xFB, 0xFF, 0xFF, 0xBE, 0xBF, 0x27, 0xBA, 0xFE, 0xFB, 0xDF, 0xFF,
-    0xF6, 0xFF, 0xFF, 0xEF, 
-    0xFB, 0xDB, 0xF3, 0xD9, 0x9A, 0x3F, 0xFF, 0xAF, 0xBF, 0xFF, 0xFF, 0xBE,
-    0x3F, 0x37, 0xBD, 0x96, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xAE, 0xFB, 0xF3, 0xF3, 0xEB, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xF7, 0xFA, 0xBC, 0xAE, 0xFE, 0xBE, 0xFE, 0xBB, 0x7F, 0xFD, 0xFF,
-    0x7F, 0xEF, 0xF7, 0xFB, 
-    0xBB, 0xD7, 0xF7, 0x7F, 0xFF, 0xF7, 0xFF, 0xFF, 0xF7, 0xBC, 0xED, 0xFD,
-    0xBD, 0x9D, 0x7D, 0x7B, 
-    0xFB, 0x7B, 0x7B, 0xFB, 0xAF, 0xFF, 0xFE, 0xFD, 0xFD, 0xFE, 0xFE, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xF7, 
-    0xAA, 0xB9, 0xBF, 0x8F, 0xBF, 0xDF, 0xFF, 0x7F, 0xFF, 0xFF, 0x7F, 0xCF,
-    0xFB, 0xEB, 0xCB, 0xEB, 
-    0xEE, 0xFF, 0xFF, 0xD7, 0xFF, 0xFF, 0xFF, 0x3E, 0x33, 0x3F, 0x1C, 0x7C,
-    0xFC, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xCF, 0xD3, 0xF3, 0xE3, 0xF3, 0xFB, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xEB, 0xFE, 0x35, 
-    0x3F, 0x3D, 0xFD, 0xFD, 0xFF, 0xFF, 0xFF, 0xBF, 0xFF, 0xEF, 0x6F, 0xE3,
-    0xE3, 0xE3, 0xEF, 0xFF, 
-    0xFF, 0xDF, 0xFF, 0xFF, 0xF7, 0xFE, 0x3E, 0x5E, 0xFE, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFD, 0xFF, 0xFF, 
-    0xAF, 0xCF, 0xF2, 0xCB, 0xCF, 0x8E, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFD,
-    0xFC, 0x3E, 0x1F, 0x9E, 
-    0xAD, 0xFD, 0xFF, 0xFF, 0xBF, 0xFF, 0xFF, 0xEF, 0xFF, 0xB3, 0xF7, 0xE7,
-    0xF7, 0xFA, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xEE, 0xEB, 0xAB, 0xAF, 0x9F, 0xE3, 0x7F, 0xFF, 0xDE,
-    0xFF, 0x7F, 0xEE, 0xFF, 
-    0xFF, 0xFB, 0x3A, 0xFA, 0xFF, 0xF2, 0x77, 0xFF, 0xFF, 0xF7, 0xFE, 0xFF,
-    0xFE, 0xBD, 0xAE, 0xDE, 
-    0x7D, 0x7D, 0xFD, 0xFF, 0xBF, 0xEE, 0xFF, 0xFD, 0xFF, 0xDB, 0xFB, 0xFF,
-    0xF7, 0xEF, 0xFB, 0xFF, 
-    0xFF, 0xFE, 0xFF, 0x2D, 0xAF, 0xB9, 0xFD, 0x79, 0xFB, 0xFA, 0xFF, 0xBF,
-    0xEF, 0xFF, 0xFF, 0x91, 
-    0xFA, 0xFB, 0xDF, 0xF7, 0xF7, 0xFF, 0xFF, 0xFF, 0xFC, 0xCF, 0x37, 0xBF,
-    0xBF, 0xFF, 0x7F, 0x7F, 
-    0xFF, 0xFF, 0xFF, 0xAF, 0xFF, 0xFF, 0xF3, 0xFB, 0xFB, 0xFF, 0xF5, 0xEF,
-    0xFF, 0xFF, 0xF7, 0xFA, 
-    0xFF, 0xFF, 0xEE, 0xFA, 0xFE, 0xFB, 0x55, 0xDD, 0xFF, 0x7F, 0xAF, 0xFE,
-    0xFF, 0xFB, 0xFB, 0xF5, 
-    0xFF, 0xF7, 0xEF, 0xFF, 0xFF, 0xFF, 0xBE, 0xBD, 0xBD, 0xBD, 0xBD, 0x7D,
-    0x7B, 0x7B, 0x7B, 0x7B, 
-    0xFB, 0xAE, 0xFF, 0xFD, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xF7, 0xDA, 0xB7, 0x61, 
-    0xFF, 0xB9, 0x59, 0xF3, 0x73, 0xF3, 0xDF, 0x7F, 0x6F, 0xDF, 0xEF, 0xF7,
-    0xEB, 0xEB, 0xD7, 0xFF, 
-    0xD7, 0xFF, 0xFF, 0xF7, 0xFE, 0x7F, 0xFB, 0x3E, 0x38, 0x73, 0xF6, 0x7F,
-    0xFC, 0xFF, 0xFF, 0xCF, 
-    0xFF, 0xB7, 0xFB, 0xB3, 0xB3, 0x67, 0xFF, 0xE7, 0xFD, 0xFF, 0xEF, 0xF6,
-    0x7F, 0xB7, 0xBC, 0xF5, 
-    0x7B, 0xF6, 0xF7, 0xF5, 0xFF, 0xFF, 0xEF, 0xFF, 0xF7, 0xFF, 0xF7, 0xCE,
-    0xE7, 0xFF, 0x9F, 0xFF, 
-    0xFF, 0xF5, 0xFE, 0x7D, 0xFF, 0x5F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xEF, 0xFF, 0xF6, 
-    0xCB, 0xDB, 0xEE, 0xFE, 0xFF, 0xDF, 0xFF, 0xFF, 0xFF, 0xFE, 0x7F, 0xBE,
-    0x1E, 0x3E, 0xFE, 0xFF, 
-    0x7D, 0xFE, 0xFF, 0xFF, 0xEF, 0xBF, 0xE7, 0xFF, 0xE3, 0xE3, 0xFF, 0xDF,
-    0xE7, 0xFF, 0xFF, 0xFF, 
-    0xB8, 0xEF, 0xB7, 0x2F, 0xEE, 0xFF, 0xDF, 0xFF, 0xBF, 0xFF, 0x7F, 0xEF,
-    0xEB, 0xBF, 0xA3, 0xD3, 
-    0xFF, 0x7F, 0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0xBE, 0xFD, 0x3F, 0xCF, 0xFD,
-    0xFB, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xAF, 0xFB, 0xBF, 0xBB, 0xBF, 0xDB, 0xFD, 0xFB, 0xFF, 0xFF,
-    0xFF, 0xFF, 0x3E, 0xFE, 
-    0x3F, 0xBA, 0xBA, 0xFE, 0xFF, 0xFF, 0xFF, 0xEF, 0xFF, 0xEF, 0xC3, 0x7F,
-    0xB2, 0x9B, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFE, 0xFF, 0xFF, 0x3C, 0xFF, 0x3F, 0x3C, 0xFF, 0xFE, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xAF, 0xF3, 0xFE, 0xF3, 0xE3, 0xEB, 0xFF, 0xFF, 0xFF, 0xFB, 0xFF, 0xF7,
-    0x9A, 0xFE, 0xAF, 0x9E, 
-    0xBE, 0xFE, 0xFF, 0xDF, 0xFF, 0xFF, 0x7B, 0xEF, 0xF7, 0xBF, 0xFB, 0xFB,
-    0xFB, 0xFF, 0xFF, 0x7F, 
-    0xFF, 0xFF, 0xFF, 0xBC, 0xBD, 0xFD, 0xBD, 0xDD, 0x7D, 0x7B, 0x7B, 0x7B,
-    0x7B, 0xFB, 0xAE, 0xFF, 
-    0xFF, 0xFF, 0xFE, 0xFE, 0xFF, 0xFD, 0xFF, 0xFF, 0xFF, 0xF7, 0x9A, 0xFF,
-    0x9F, 0xFF, 0xAF, 0xEF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xCF, 0xF3, 0xFF, 0xEB, 0xFF, 0xEB, 0xFF,
-    0xFF, 0xBF, 0xFF, 0xFF, 
-    0xEF, 0xFE, 0xFF, 0x37, 0xFC, 0xBF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xCF, 0xEF, 0xFD, 0xF3, 
-    0xFF, 0xEE, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x6E, 0xFD, 0x2F, 0xFD,
-    0xFF, 0xFD, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xEF, 0xCF, 0xFF, 0xF3, 0xBF, 0x69, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFE, 
-    0xFB, 0x9F, 0xFF, 0xBF, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0x87,
-    0xFE, 0xDA, 0xEF, 0xCF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0xEF, 0xBF, 0xEF, 0xEF, 0xFD,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xEF, 0xFD, 0xFF, 0x7B, 0xFF, 0xEB, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xEB, 0xF8, 0xFF, 0xEF, 
-    0xAF, 0xFF, 0xFF, 0xBD, 0xFF, 0xFF, 0xFF, 0x7F, 0xEE, 0x7F, 0xEF, 0xFF,
-    0xBB, 0xFF, 0xBF, 0xFB, 
-    0xFF, 0xFF, 0xFF, 0xF7, 0xF6, 0xFB, 0xBD, 0xFD, 0xDD, 0xF5, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xAF, 
-    0xFF, 0x5F, 0xF5, 0xDF, 0xFF, 0x7F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xF6,
-    0xF3, 0xFF, 0xDE, 0xFE, 
-    0xEF, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xFF, 0xDE, 0xDF, 0x5F, 0xDF,
-    0xFD, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFE, 0xFF, 0xFF, 0xFE, 0xFE, 0xFF, 0xFD, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xAF, 0xFF, 0xFF, 
-    0xEF, 0xED, 0xFF, 0xDF, 0xFF, 0xFF, 0xFB, 0xFF, 0xFF, 0xDA, 0xBD, 0xBE,
-    0xAE, 0xFE, 0x7F, 0xFD, 
-    0xDF, 0xFF, 0xFF, 0x7F, 0xEF, 0xFF, 0xFB, 0xFB, 0xFB, 0x7F, 0xF7, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xF7, 
-    0xBC, 0xFD, 0xBD, 0xBD, 0xBD, 0xFD, 0x7B, 0x7B, 0x7B, 0x7B, 0xFB, 0xAE,
-    0xFF, 0xFF, 0xFD, 0xFF, 
-    0xFF, 0xFF, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xFA, 0x9F, 0xBF, 0xBF, 0xCF,
-    0x7F, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xAF, 0xFF, 0xEB, 0xEB, 0xEB, 0xFF, 0xD7, 0xFE, 0xFF, 0xFF,
-    0xBF, 0xE7, 0xFE, 0xBF, 
-    0x7F, 0xFC, 0xFF, 0xFF, 0xED, 0xFF, 0xFF, 0xFF, 0xFF, 0x4F, 0xFF, 0xFB,
-    0xFB, 0xFF, 0xFF, 0xDD, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0xBD, 0xDF, 0x9D, 0xFD, 0xDF, 0xB9,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xEF, 0xFF, 0xFB, 0xEF, 0xEB, 0xFF, 0xDE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xF6, 0x9F, 0xFF, 0xFC, 
-    0xFE, 0xFB, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xDF, 0xFA, 0xCD, 0xCF,
-    0xBF, 0x9F, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xF7, 0xFE, 0xBF, 0xFF, 0xDF, 0xEF, 0x5F, 0xFF, 0xFF, 0xFF,
-    0xFF, 0x7F, 0x6F, 0xFF, 
-    0xBB, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7E, 0xFF,
-    0x5F, 0xFF, 0xBF, 0xBF, 
-    0xF9, 0xFF, 0xFF, 0xFF, 0x7F, 0x6E, 0x7B, 0xFF, 0xEF, 0xFD, 0xEB, 0xDF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xF7, 0xB6, 0x3E, 0xFC, 0xFD, 0xBF, 0x7E, 0xFB, 0xFF, 0xFF, 0xFF, 0xF7,
-    0xEF, 0xF7, 0xF3, 0xF7, 
-    0xFF, 0xFB, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x6E, 0x35, 0x79, 0xFF,
-    0xBF, 0xFC, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xEF, 0xFB, 0x53, 0xDF, 0xFF, 0xEB, 0xBF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xBC, 
-    0xFF, 0xFF, 0xFF, 0xBF, 0xFF, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xAF, 0xF5,
-    0xFF, 0xF7, 0xFF, 0xFB, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xBA, 0xAA, 0xEE, 0xFE, 0x3F, 0x7D,
-    0xFD, 0xFF, 0xFF, 0xFF, 
-    0x7F, 0xAF, 0x77, 0xFB, 0xFB, 0xFF, 0xFB, 0xF7, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xF7, 0xBE, 0xBD, 0xBD, 
-    0xBD, 0xBD, 0xFD, 0x7B, 0x7B, 0x7B, 0x7B, 0xFB, 0xAE, 0xFF, 0xEF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFC, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0x9A, 0xD9, 0xB8, 0xFF, 0xFF, 0x79, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xCF, 
-    0xFB, 0xFF, 0xEB, 0xFF, 0xEB, 0xD7, 0xFF, 0xFF, 0xFF, 0xFF, 0xE7, 0xDE,
-    0xF8, 0xFB, 0xFE, 0x3F, 
-    0xFB, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xCF, 0xAD, 0xBF, 0xFA, 0xFF, 0x73,
-    0xDF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0x3A, 0xF5, 0xB7, 0xFC, 0x3F, 0xF9, 0xFD, 0xFF, 0xFF, 0xFF,
-    0x7F, 0xEF, 0xF3, 0xFF, 
-    0xBF, 0xFE, 0xF3, 0x9F, 0xFE, 0xFF, 0xFF, 0xFF, 0xF7, 0x3E, 0xFF, 0xFF,
-    0xFF, 0xBF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xAF, 0xD3, 0xFE, 0xDB, 0xFF, 0xDB, 0xDF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0x3E, 0xFF, 0xBF, 0xFF, 0x7F, 0xFF, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0x8F,
-    0xF3, 0xFF, 0xED, 0xFF, 
-    0xF7, 0xFB, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xF6, 0x3C, 0xFE, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0x9F, 0xEF, 0xEF, 0xD1, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0x7E, 0xBF, 
-    0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xBB, 0xEF, 0xDF, 0xF1,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEE, 0x3E, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xBF, 
-    0xEF, 0xFD, 0xC3, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xBF, 0xFF,
-    0xFC, 0x3E, 0xFE, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x2E, 0xEF, 0xF3, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xF7, 0xBA, 0xBE, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0x7F, 0xAF, 0xFB, 
-    0xFB, 0xFD, 0xFF, 0xFF, 0xFF, 0xFE, 0xFF, 0xFF, 0xFF, 0xF2, 0xD6, 0xED,
-    0xBD, 0xBD, 0xBD, 0x7D, 
-    0x7B, 0x7B, 0x7B, 0x7B, 0xFB, 0xAF, 0xDF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0x92, 0xBF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F,
-    0xAF, 0xEB, 0xEB, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xE7, 0xFE, 0x2E, 0xFE, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0x4F, 0xEF, 0xF3, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFE, 
-    0x3C, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xCE,
-    0xC3, 0xFD, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0x5D, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xEF, 0xCF, 0xEB, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xF7, 0xEE, 0x3E, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xEF, 0xDF, 0xE2, 0xFF,
-    0xFF, 0xFF, 0xFB, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xF6, 0xBE, 0xFC, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0x7F, 0xEE, 
-    0x5F, 0xE6, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x3E,
-    0x7D, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xF3, 0xFB, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xBF, 0xF7, 0x36, 0xBE, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xEF, 0xD3, 0xF6, 
-    0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFC, 0x7F, 0xEE,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xAF, 0xEF, 0xEB, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xBA, 0xBE, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEE,
-    0xFB, 0xFA, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0xD6, 0xFD, 0xBD, 0xBD, 0xBD,
-    0x7D, 0x7B, 0x7B, 0x7B, 
-    0x7B, 0xFB, 0xAE, 0xFF, 0x7E, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xF7, 0xBA, 0xBF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xEF, 0xEB, 0x6B,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0xFE, 0xBE, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0x4F, 0xEF, 0xF7, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF,
-    0x3E, 0x6E, 0xFC, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xC3, 0xC9, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0x3E, 0xBF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xEF, 0xFB, 
-    0xD5, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0xFE,
-    0xFE, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x6F, 0xEF, 0xFB, 0xFF, 0xFF, 0xFF, 0xFB,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xF6, 0xDF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xFE,
-    0xEF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xE7, 0xFF, 0xFE, 0xFF, 0xF7, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0x7F, 0xFA, 0xEF, 0xBF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xE7, 0xFF, 0xFE, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xFE, 0xEF, 0xBF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xA7, 0xFF, 0xFC, 0xF7, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0x7F, 
-    0xFE, 0xAE, 0xFF, 0xFF, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xE7,
-    0xF7, 0xFA, 0xFF, 0xFD, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xAF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xF7, 0xBE, 0xBD, 0xBD, 0xBD, 0xBD, 0x7D, 0x7B, 0x7B,
-    0x7B, 0x7B, 0xFB, 0xAF, 
-    0x7F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xCA,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0x6F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xE7, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xCF, 0xFE, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0xDF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xFF, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xEF, 0xFF, 0xFE, 0xFF, 0xFF, 0xFF, 0xFB, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xE7, 0xF2, 0xFC, 
-    0xEF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xAE, 0xEF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0x7E, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xEF, 0xFF, 0xFE, 0xFF, 0xFF, 0xFF, 0xBF, 0xFF, 0xFF, 0xFF, 0xBF, 0xFF,
-    0xFE, 0xFE, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xDF, 0xEF, 0xDD, 0xFE, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFE, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xAF, 0xEF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xBA, 0xFE,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xFA, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xF6, 0x9C, 0xBD, 0xBD, 0xBD, 0xBD, 0x7D, 0x7B, 0x7B, 0x7B, 0x7B, 0xFB,
-    0xAE, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0x7A, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xDF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0x6F, 0xEF, 0xF7, 0xFF, 0xFF, 0xFF, 0xDF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xF7, 0xFE, 
-    0xFE, 0xFF, 0xFF, 0xFF, 0xDF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xCF, 0xEB,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0x9E, 0xFC, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xEF, 0xEF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFE, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0x7F, 0xEF, 0xCB, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFD, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xBE, 0xFD, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xEF, 
-    0xEF, 0xFF, 0xFF, 0xFF, 0xDF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xF8,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xBF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFB, 0xAF, 0x7F, 0xFF, 
-    0xFF, 0xFF, 0xDF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0xEF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xBF, 0xFF, 
-    0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xAE,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0xFA, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0x7F, 0xEF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xF7, 0xBC, 0xBD, 
-    0xBD, 0xBD, 0xBD, 0x7D, 0x7B, 0x7B, 0x7B, 0x7B, 0xFB, 0xAF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xF7, 0xFA, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0x7F, 
-    0xAF, 0x7F, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF,
-    0xFE, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xCF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFE, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFB, 0xFF,
-    0xFF, 0xFF, 0xEF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFE, 0xFF,
-    0xFF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xBF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFC, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF,
-    0xEF, 0xFF, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFB, 0xFF, 0xFF, 0xFF, 0xFF, 0xEF, 0xFE, 0xFF, 0x9F, 0x9F,
-    0x9F, 0x3F, 0x3F, 0x3F, 
-    0x3F, 0x3F, 0xFF, 0xEF, 0xDF, 0xDF, 0xDF, 0xDF, 0xCF, 0xB7, 0xBF, 0xBF,
-    0xBF, 0xBF, 0xFF, 0xBC, 
-    0xB9, 0x9D, 0xBD, 0xBD, 0x7D, 0x7B, 0x7B, 0x7B, 0x7B, 0xFB, 0xEF, 0xD7,
-    0xF5, 0xF3, 0xF1, 0xD1, 
-    0x65, 0xE3, 0xE3, 0xE3, 0xA3, 0xFF, 0xFE, 0x7F, 0xFE, 0xDE, 0xDE, 0xFF,
-    0xBD, 0xBD, 0xBD, 0xBD, 
-    0xDF, 0xEF, 0xFB, 0xF7, 0xF3, 0xF3, 0xF3, 0xE7, 0xE7, 0xE7, 0xE7, 0xE7,
-    0xFB, 0xFE, 0xFF, 0xFF, 
-    0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF, 0xFF
-    
-    };
diff --git a/drivers/net/pcmcia/smc91c92_cs.c b/drivers/net/pcmcia/smc91c92_cs.c
index 774232c13b31..48dbb35747d8 100644
--- a/drivers/net/pcmcia/smc91c92_cs.c
+++ b/drivers/net/pcmcia/smc91c92_cs.c
@@ -42,6 +42,7 @@
 #include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/jiffies.h>
+#include <linux/firmware.h>
 
 #include <pcmcia/cs_types.h>
 #include <pcmcia/cs.h>
@@ -55,17 +56,18 @@
 #include <asm/system.h>
 #include <asm/uaccess.h>
 
-/* Ositech Seven of Diamonds firmware */
-#include "ositech.h"
-
 /*====================================================================*/
 
 static const char *if_names[] = { "auto", "10baseT", "10base2"};
 
+/* Firmware name */
+#define FIRMWARE_NAME		"ositech/Xilinx7OD.bin"
+
 /* Module parameters */
 
 MODULE_DESCRIPTION("SMC 91c92 series PCMCIA ethernet driver");
 MODULE_LICENSE("GPL");
+MODULE_FIRMWARE(FIRMWARE_NAME);
 
 #define INT_MODULE_PARM(n, v) static int n = v; module_param(n, int, 0)
 
@@ -771,6 +773,26 @@ static int osi_config(struct pcmcia_device *link)
     return i;
 }
 
+static int osi_load_firmware(struct pcmcia_device *link)
+{
+	const struct firmware *fw;
+	int i, err;
+
+	err = request_firmware(&fw, FIRMWARE_NAME, &link->dev);
+	if (err) {
+		pr_err("Failed to load firmware \"%s\"\n", FIRMWARE_NAME);
+		return err;
+	}
+
+	/* Download the Seven of Diamonds firmware */
+	for (i = 0; i < fw->size; i++) {
+	    outb(fw->data[i], link->io.BasePort1 + 2);
+	    udelay(50);
+	}
+	release_firmware(fw);
+	return err;
+}
+
 static int osi_setup(struct pcmcia_device *link, u_short manfid, u_short cardid)
 {
     struct net_device *dev = link->priv;
@@ -811,11 +833,9 @@ static int osi_setup(struct pcmcia_device *link, u_short manfid, u_short cardid)
 	 (cardid == PRODID_OSITECH_SEVEN)) ||
 	((manfid == MANFID_PSION) &&
 	 (cardid == PRODID_PSION_NET100))) {
-	/* Download the Seven of Diamonds firmware */
-	for (i = 0; i < sizeof(__Xilinx7OD); i++) {
-	    outb(__Xilinx7OD[i], link->io.BasePort1+2);
-	    udelay(50);
-	}
+	rc = osi_load_firmware(link);
+	if (rc)
+		goto free_cfg_mem;
     } else if (manfid == MANFID_OSITECH) {
 	/* Make sure both functions are powered up */
 	set_bits(0x300, link->io.BasePort1 + OSITECH_AUI_PWR);
@@ -862,10 +882,10 @@ static int smc91c92_resume(struct pcmcia_device *link)
 	     (smc->cardid == PRODID_OSITECH_SEVEN)) ||
 	    ((smc->manfid == MANFID_PSION) &&
 	     (smc->cardid == PRODID_PSION_NET100))) {
-		/* Download the Seven of Diamonds firmware */
-		for (i = 0; i < sizeof(__Xilinx7OD); i++) {
-			outb(__Xilinx7OD[i], link->io.BasePort1+2);
-			udelay(50);
+		i = osi_load_firmware(link);
+		if (i) {
+			pr_err("smc91c92_cs: Failed to load firmware\n");
+			return i;
 		}
 	}
 	if (link->open) {
diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c
index 58b73b08dde0..3ff1f425f1bb 100644
--- a/drivers/net/phy/phy.c
+++ b/drivers/net/phy/phy.c
@@ -757,8 +757,7 @@ EXPORT_SYMBOL(phy_start);
  */
 static void phy_state_machine(struct work_struct *work)
 {
-	struct delayed_work *dwork =
-			container_of(work, struct delayed_work, work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct phy_device *phydev =
 			container_of(dwork, struct phy_device, state_queue);
 	int needs_aneg = 0;
diff --git a/drivers/net/qlge/qlge_ethtool.c b/drivers/net/qlge/qlge_ethtool.c
index a50078627fb6..913b2a5fafc9 100644
--- a/drivers/net/qlge/qlge_ethtool.c
+++ b/drivers/net/qlge/qlge_ethtool.c
@@ -33,7 +33,6 @@
 #include <linux/mm.h>
 #include <linux/vmalloc.h>
 
-#include <linux/version.h>
 
 #include "qlge.h"
 
diff --git a/drivers/net/r8169.c b/drivers/net/r8169.c
index 06c535222666..e1a638a05f86 100644
--- a/drivers/net/r8169.c
+++ b/drivers/net/r8169.c
@@ -2075,8 +2075,7 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 	if (!tp->pcie_cap && netif_msg_probe(tp))
 		dev_info(&pdev->dev, "no PCI Express capability\n");
 
-	/* Unneeded ? Don't mess with Mrs. Murphy. */
-	rtl8169_irq_mask_and_ack(ioaddr);
+	RTL_W16(IntrMask, 0x0000);
 
 	/* Soft reset the chip. */
 	RTL_W8(ChipCmd, CmdReset);
@@ -2088,6 +2087,8 @@ rtl8169_init_one(struct pci_dev *pdev, const struct pci_device_id *ent)
 		msleep_interruptible(1);
 	}
 
+	RTL_W16(IntrStatus, 0xffff);
+
 	/* Identify chip attached to board */
 	rtl8169_get_mac_version(tp, ioaddr);
 
diff --git a/drivers/net/sb1250-mac.c b/drivers/net/sb1250-mac.c
index 88dd2e09832f..ce7551e17ba7 100644
--- a/drivers/net/sb1250-mac.c
+++ b/drivers/net/sb1250-mac.c
@@ -2299,7 +2299,7 @@ static int sbmac_init(struct platform_device *pldev, long long base)
 	eaddr = sc->sbm_hwaddr;
 
 	/*
-	 * Read the ethernet address.  The firwmare left this programmed
+	 * Read the ethernet address.  The firmware left this programmed
 	 * for us in the ethernet address register for each mac.
 	 */
 
diff --git a/drivers/net/sfc/efx.c b/drivers/net/sfc/efx.c
index 00c23b1babca..dee23b159df2 100644
--- a/drivers/net/sfc/efx.c
+++ b/drivers/net/sfc/efx.c
@@ -448,6 +448,9 @@ static void efx_init_channels(struct efx_nic *efx)
 
 		WARN_ON(channel->rx_pkt != NULL);
 		efx_rx_strategy(channel);
+
+		netif_napi_add(channel->napi_dev, &channel->napi_str,
+			       efx_poll, napi_weight);
 	}
 }
 
@@ -462,10 +465,6 @@ static void efx_start_channel(struct efx_channel *channel)
 
 	EFX_LOG(channel->efx, "starting chan %d\n", channel->channel);
 
-	if (!(channel->efx->net_dev->flags & IFF_UP))
-		netif_napi_add(channel->napi_dev, &channel->napi_str,
-			       efx_poll, napi_weight);
-
 	/* The interrupt handler for this channel may set work_pending
 	 * as soon as we enable it.  Make sure it's cleared before
 	 * then.  Similarly, make sure it sees the enabled flag set. */
diff --git a/drivers/net/skfp/h/hwmtm.h b/drivers/net/skfp/h/hwmtm.h
index 1a606d4bfe5e..e1a7e5f683dc 100644
--- a/drivers/net/skfp/h/hwmtm.h
+++ b/drivers/net/skfp/h/hwmtm.h
@@ -145,7 +145,7 @@ struct hw_modul {
 	int	leave_isr ;		/* leave fddi_isr immedeately if set */
 	int	isr_flag ;		/* set, when HWM is entered from isr */
 	/*
-	 * varaibles for the current transmit frame
+	 * variables for the current transmit frame
 	 */
 	struct s_smt_tx_queue *tx_p ;	/* pointer to the transmit queue */
 	u_long	tx_descr ;		/* tx descriptor for FORMAC+ */
diff --git a/drivers/net/tc35815.c b/drivers/net/tc35815.c
index b52a1c088f37..d91e95b237b7 100644
--- a/drivers/net/tc35815.c
+++ b/drivers/net/tc35815.c
@@ -1908,7 +1908,7 @@ static int tc35815_poll(struct napi_struct *napi, int budget)
 	do {
 		tc_writel(status, &tr->Int_Src);	/* write to clear */
 
-		handled = tc35815_do_interrupt(dev, status, limit);
+		handled = tc35815_do_interrupt(dev, status, budget - received);
 		if (handled >= 0) {
 			received += handled;
 			if (received >= budget)
diff --git a/drivers/net/tg3.c b/drivers/net/tg3.c
index 1205c2a22657..437683aab32c 100644
--- a/drivers/net/tg3.c
+++ b/drivers/net/tg3.c
@@ -11225,7 +11225,7 @@ static int __devinit tg3_phy_probe(struct tg3 *tp)
 		return tg3_phy_init(tp);
 
 	/* Reading the PHY ID register can conflict with ASF
-	 * firwmare access to the PHY hardware.
+	 * firmware access to the PHY hardware.
 	 */
 	err = 0;
 	if ((tp->tg3_flags & TG3_FLAG_ENABLE_ASF) ||
diff --git a/drivers/net/tokenring/3c359.c b/drivers/net/tokenring/3c359.c
index 4a65fc2dd928..534c0f38483c 100644
--- a/drivers/net/tokenring/3c359.c
+++ b/drivers/net/tokenring/3c359.c
@@ -62,6 +62,7 @@
 #include <linux/pci.h>
 #include <linux/spinlock.h>
 #include <linux/bitops.h>
+#include <linux/firmware.h>
 
 #include <net/checksum.h>
 
@@ -73,8 +74,10 @@
 static char version[] __devinitdata  = 
 "3c359.c v1.2.0 2/17/01 - Mike Phillips (mikep@linuxtr.net)" ; 
 
+#define FW_NAME		"3com/3C359.bin"
 MODULE_AUTHOR("Mike Phillips <mikep@linuxtr.net>") ; 
 MODULE_DESCRIPTION("3Com 3C359 Velocity XL Token Ring Adapter Driver \n") ;
+MODULE_FIRMWARE(FW_NAME);
 
 /* Module paramters */
 
@@ -114,8 +117,6 @@ MODULE_PARM_DESC(message_level, "3c359: Level of reported messages") ;
  *	will be stuck with 1555 lines of hex #'s in the code.
  */
 
-#include "3c359_microcode.h" 
-
 static struct pci_device_id xl_pci_tbl[] =
 {
 	{PCI_VENDOR_ID_3COM,PCI_DEVICE_ID_3COM_3C359, PCI_ANY_ID, PCI_ANY_ID, },
@@ -364,10 +365,30 @@ static int __devinit xl_probe(struct pci_dev *pdev,
 	return 0; 
 }
 
+static int xl_init_firmware(struct xl_private *xl_priv)
+{
+	int err;
+
+	err = request_firmware(&xl_priv->fw, FW_NAME, &xl_priv->pdev->dev);
+	if (err) {
+		printk(KERN_ERR "Failed to load firmware \"%s\"\n", FW_NAME);
+		return err;
+	}
+
+	if (xl_priv->fw->size < 16) {
+		printk(KERN_ERR "Bogus length %zu in \"%s\"\n",
+		       xl_priv->fw->size, FW_NAME);
+		release_firmware(xl_priv->fw);
+		err = -EINVAL;
+	}
+
+	return err;
+}
 
 static int __devinit xl_init(struct net_device *dev) 
 {
 	struct xl_private *xl_priv = netdev_priv(dev);
+	int err;
 
 	printk(KERN_INFO "%s \n", version);
 	printk(KERN_INFO "%s: I/O at %hx, MMIO at %p, using irq %d\n",
@@ -375,8 +396,11 @@ static int __devinit xl_init(struct net_device *dev)
 
 	spin_lock_init(&xl_priv->xl_lock) ; 
 
-	return xl_hw_reset(dev) ; 
+	err = xl_init_firmware(xl_priv);
+	if (err == 0)
+		err = xl_hw_reset(dev);
 
+	return err;
 }
 
 
@@ -386,7 +410,7 @@ static int __devinit xl_init(struct net_device *dev)
  */
 
 static int xl_hw_reset(struct net_device *dev) 
-{ 
+{
 	struct xl_private *xl_priv = netdev_priv(dev);
 	u8 __iomem *xl_mmio = xl_priv->xl_mmio ; 
 	unsigned long t ; 
@@ -396,6 +420,9 @@ static int xl_hw_reset(struct net_device *dev)
 	u16 start ; 
 	int j ;
 
+	if (xl_priv->fw == NULL)
+		return -EINVAL;
+
 	/*
 	 *  Reset the card.  If the card has got the microcode on board, we have 
          *  missed the initialization interrupt, so we must always do this.
@@ -458,25 +485,30 @@ static int xl_hw_reset(struct net_device *dev)
 
 		/* 
 		 * Now to write the microcode into the shared ram 
-	 	 * The microcode must finish at position 0xFFFF, so we must subtract
-		 * to get the start position for the code
+	 	 * The microcode must finish at position 0xFFFF,
+	 	 * so we must subtract to get the start position for the code
+	 	 *
+		 * Looks strange but ensures compiler only uses
+		 * 16 bit unsigned int
 		 */
+		start = (0xFFFF - (xl_priv->fw->size) + 1) ;
 
-		start = (0xFFFF - (mc_size) + 1 ) ; /* Looks strange but ensures compiler only uses 16 bit unsigned int for this */ 
-		
 		printk(KERN_INFO "3C359: Uploading Microcode: "); 
-		
-		for (i = start, j = 0; j < mc_size; i++, j++) { 
-			writel(MEM_BYTE_WRITE | 0XD0000 | i, xl_mmio + MMIO_MAC_ACCESS_CMD) ; 
-			writeb(microcode[j],xl_mmio + MMIO_MACDATA) ; 
+
+		for (i = start, j = 0; j < xl_priv->fw->size; i++, j++) {
+			writel(MEM_BYTE_WRITE | 0XD0000 | i,
+			       xl_mmio + MMIO_MAC_ACCESS_CMD);
+			writeb(xl_priv->fw->data[j], xl_mmio + MMIO_MACDATA);
 			if (j % 1024 == 0)
 				printk(".");
 		}
 		printk("\n") ; 
 
-		for (i=0;i < 16; i++) { 
-			writel( (MEM_BYTE_WRITE | 0xDFFF0) + i, xl_mmio + MMIO_MAC_ACCESS_CMD) ; 
-			writeb(microcode[mc_size - 16 + i], xl_mmio + MMIO_MACDATA) ; 
+		for (i = 0; i < 16; i++) {
+			writel((MEM_BYTE_WRITE | 0xDFFF0) + i,
+			       xl_mmio + MMIO_MAC_ACCESS_CMD);
+			writeb(xl_priv->fw->data[xl_priv->fw->size - 16 + i],
+			       xl_mmio + MMIO_MACDATA);
 		}
 
 		/*
@@ -1782,6 +1814,7 @@ static void __devexit xl_remove_one (struct pci_dev *pdev)
 	struct net_device *dev = pci_get_drvdata(pdev);
 	struct xl_private *xl_priv=netdev_priv(dev);
 	
+	release_firmware(xl_priv->fw);
 	unregister_netdev(dev);
 	iounmap(xl_priv->xl_mmio) ; 
 	pci_release_regions(pdev) ; 
diff --git a/drivers/net/tokenring/3c359.h b/drivers/net/tokenring/3c359.h
index 66b1ff603234..bcb1a6b4a4c7 100644
--- a/drivers/net/tokenring/3c359.h
+++ b/drivers/net/tokenring/3c359.h
@@ -284,5 +284,8 @@ struct xl_private {
 	u8 xl_laa[6] ; 
 	u32 rx_ring_dma_addr ; 
 	u32 tx_ring_dma_addr ; 
+
+	/* firmware section */
+	const struct firmware *fw;
 };
 
diff --git a/drivers/net/tokenring/3c359_microcode.h b/drivers/net/tokenring/3c359_microcode.h
deleted file mode 100644
index 0400c029c077..000000000000
--- a/drivers/net/tokenring/3c359_microcode.h
+++ /dev/null
@@ -1,1581 +0,0 @@
-
-/*
- * The firmware this driver downloads into the tokenring card is a
- * separate program and is not GPL'd source code, even though the Linux
- * side driver and the routine that loads this data into the card are.
- *
- * This firmware is licensed to you strictly for use in conjunction
- * with the use of 3Com 3C359 TokenRing adapters. There is no
- * waranty expressed or implied about its fitness for any purpose.
- */
-
-/* 3c359_microcode.mac: 3Com 3C359 Tokenring microcode.
- *
- * Notes:
- *  - Loaded from xl_init upon adapter initialization.
- *
- * Available from 3Com as part of their standard 3C359 driver. 
- *
- * mc_size *must* must match the microcode being used, each version is a 
- * different length.
- */
-
-static int mc_size = 24880 ; 
-
-static const u8 microcode[] = { 
- 0xfe,0x3a,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x30,0x33,0x2f,0x30,0x32,0x2f,0x39,0x39,0x20,0x31
-,0x37,0x3a,0x31,0x33,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x30,0x31,0x32,0x33,0x34,0x35,0x36,0x37,0x38,0x39,0x41,0x42,0x43,0x44,0x45,0x46
-,0x00,0x00,0x07,0xff,0x02,0x00,0xfe,0x9f,0x06,0x00,0x00,0x7c,0x48,0x00,0x00,0x70
-,0x82,0x00,0xff,0xff,0x86,0x00,0xff,0xff,0x88,0x00,0xff,0xff,0x9a,0x00,0xff,0xff
-,0xff,0xff,0x11,0x00,0xc0,0x00,0xff,0xff,0xff,0xff,0x11,0x22,0x33,0x44,0x55,0x66
-,0x33,0x43,0x4f,0x4d,0x20,0x42,0x41,0x42,0x45,0x11,0x40,0xc0,0x00,0xff,0xff,0xff
-,0xff,0x11,0x22,0x33,0x44,0x55,0x66,0x53,0x74,0x61,0x72,0x74,0x20,0x6f,0x66,0x20
-,0x4c,0x4c,0x43,0x20,0x66,0x72,0x61,0x6d,0x65,0x2e,0x20,0x20,0x54,0x6f,0x74,0x61
-,0x6c,0x20,0x64,0x61,0x74,0x61,0x20,0x73,0x69,0x7a,0x65,0x20,0x69,0x73,0x20,0x78
-,0x78,0x78,0x20,0x20,0x20,0x42,0x41,0x42,0x45,0xe8,0xd2,0x01,0x83,0x3e,0xf7,0x34
-,0x00,0x75,0x21,0xe8,0x41,0x00,0x83,0x3e,0xf7,0x34,0x00,0x75,0x17,0xe8,0x82,0x00
-,0x83,0x3e,0xf7,0x34,0x00,0x75,0x0d,0xe8,0xbf,0x00,0x83,0x3e,0xf7,0x34,0x00,0x75
-,0x03,0xe8,0x41,0x02,0xc3,0x1e,0xb8,0x00,0xf0,0x8e,0xd8,0x33,0xf6,0xb9,0x00,0x80
-,0x33,0xdb,0xad,0x03,0xd8,0xe2,0xfb,0x1f,0xb8,0x00,0x00,0x83,0xfb,0x00,0x74,0x03
-,0xb8,0x22,0x00,0xa3,0xf7,0x34,0xc3,0xfa,0xba,0x56,0x00,0xb0,0xff,0xee,0x33,0xc0
-,0x8e,0xc0,0x33,0xf6,0xb9,0xff,0x7f,0x83,0x3e,0xff,0x34,0x00,0x74,0x08,0x8d,0x3e
-,0x30,0x61,0xd1,0xef,0x2b,0xcf,0x26,0x8b,0x1c,0x26,0xc7,0x04,0xff,0xff,0x26,0x83
-,0x3c,0xff,0x75,0x17,0x26,0xc7,0x04,0x00,0x00,0x26,0x83,0x3c,0x00,0x75,0x0c,0x26
-,0x89,0x1c,0x46,0x46,0xe2,0xe0,0xb8,0x00,0x00,0xeb,0x03,0xb8,0x24,0x00,0xa3,0xf7
-,0x34,0xc3,0xfa,0xb4,0xd7,0x9e,0x73,0x3a,0x75,0x38,0x79,0x36,0x7b,0x34,0x9f,0xb1
-,0x05,0xd2,0xec,0x73,0x2d,0xb0,0x40,0xd0,0xe0,0x71,0x27,0x79,0x25,0xd0,0xe0,0x73
-,0x21,0x7b,0x1f,0x32,0xc0,0x75,0x1b,0x32,0xe4,0x9e,0x72,0x16,0x74,0x14,0x78,0x12
-,0x7a,0x10,0x9f,0xd2,0xec,0x72,0x0b,0xd0,0xe4,0x70,0x07,0x75,0x05,0xb8,0x00,0x00
-,0xeb,0x03,0xb8,0x26,0x00,0xa3,0xf7,0x34,0xc3,0xfa,0xba,0x5a,0x00,0x33,0xc0,0xef
-,0xef,0xef,0xef,0xb0,0x00,0xe6,0x56,0xb0,0x00,0xe6,0x54,0xba,0x52,0x00,0xb8,0x01
-,0x01,0xef,0xe8,0xca,0x00,0x3c,0x01,0x75,0x7f,0xe8,0x83,0x00,0xba,0x52,0x00,0xb8
-,0x02,0x02,0xef,0xe8,0xb9,0x00,0x3c,0x02,0x75,0x6e,0xe8,0x7a,0x00,0xba,0x52,0x00
-,0xb8,0x04,0x04,0xef,0xe8,0xa8,0x00,0x3c,0x04,0x75,0x5d,0xe8,0x71,0x00,0xba,0x52
-,0x00,0xb8,0x08,0x08,0xef,0xe8,0x97,0x00,0x3c,0x08,0x75,0x4c,0xe8,0x68,0x00,0xba
-,0x52,0x00,0xb8,0x10,0x10,0xef,0xe8,0x86,0x00,0x3c,0x10,0x75,0x3b,0xe8,0x5f,0x00
-,0xba,0x52,0x00,0xb8,0x20,0x20,0xef,0xe8,0x75,0x00,0x3c,0x20,0x75,0x2a,0xe8,0x56
-,0x00,0xba,0x52,0x00,0xb8,0x40,0x40,0xef,0xe8,0x64,0x00,0x3c,0x40,0x75,0x19,0xe8
-,0x4d,0x00,0xba,0x52,0x00,0xb8,0x80,0x80,0xef,0xe8,0x53,0x00,0x3c,0x80,0x75,0x08
-,0xe8,0x44,0x00,0xb8,0x00,0x00,0xeb,0x03,0xb8,0x28,0x00,0xa3,0xf7,0x34,0xc3,0xba
-,0x5a,0x00,0xb8,0x00,0x80,0xef,0xc3,0xba,0x5a,0x00,0xb8,0x01,0x80,0xef,0xc3,0xba
-,0x5a,0x00,0xb8,0x02,0x80,0xef,0xc3,0xba,0x5a,0x00,0xb8,0x03,0x80,0xef,0xc3,0xba
-,0x5a,0x00,0xb8,0x04,0x80,0xef,0xc3,0xba,0x5a,0x00,0xb8,0x05,0x80,0xef,0xc3,0xba
-,0x5a,0x00,0xb8,0x06,0x80,0xef,0xc3,0xba,0x5a,0x00,0xb8,0x07,0x80,0xef,0xc3,0xb9
-,0xff,0xff,0xe4,0x58,0xe4,0x54,0x3c,0x00,0x75,0x03,0x49,0x75,0xf7,0xc3,0xfa,0x32
-,0xc0,0xe6,0x56,0xe4,0x56,0x3c,0x00,0x74,0x03,0xe9,0x82,0x00,0xb0,0xff,0xe6,0x56
-,0xe4,0x56,0x3c,0xff,0x75,0x78,0xba,0x52,0x00,0xb8,0xff,0xff,0xef,0xed,0x3c,0xff
-,0x75,0x6c,0xb8,0x00,0xff,0xef,0xed,0x3c,0x00,0x75,0x63,0xb0,0xff,0xe6,0x54,0xe4
-,0x54,0x3c,0xff,0x75,0x59,0x32,0xc0,0xe6,0x54,0xe4,0x54,0x3c,0x00,0x75,0x4f,0xb0
-,0x0f,0xe6,0x50,0xe4,0x50,0x24,0x0f,0x3c,0x0f,0x75,0x43,0xb0,0x00,0xe6,0x50,0xe4
-,0x50,0x24,0x0f,0x3c,0x00,0x75,0x37,0x8c,0xc8,0x8e,0xc0,0xbe,0x70,0x00,0x26,0x8b
-,0x14,0x26,0x8b,0x5c,0x02,0xb8,0x00,0x00,0xef,0xed,0x23,0xc3,0x3d,0x00,0x00,0x75
-,0x1d,0xb8,0xff,0xff,0x23,0xc3,0xef,0x8b,0xc8,0xed,0x23,0xc3,0x3b,0xc1,0x75,0x0e
-,0x83,0xc6,0x04,0x26,0x83,0x3c,0xff,0x75,0xd5,0xb8,0x00,0x00,0xeb,0x03,0xb8,0x2a
-,0x00,0xa3,0xf7,0x34,0xc3,0xfa,0x33,0xc0,0xbf,0x00,0x20,0xb9,0x17,0x00,0xf3,0xab
-,0xbf,0x00,0x30,0xb9,0x17,0x00,0xf3,0xab,0xbf,0x00,0x22,0xb9,0x40,0x00,0xf3,0xab
-,0xbf,0x00,0x32,0xb9,0x40,0x00,0xf3,0xab,0xfc,0x1e,0x8c,0xc8,0x8e,0xd8,0x33,0xc0
-,0x8e,0xc0,0xbe,0x92,0x00,0xbf,0x00,0x20,0xb9,0x17,0x00,0xf3,0xa4,0xbe,0xa9,0x00
-,0xbf,0x00,0x22,0xb9,0x40,0x00,0xf3,0xa4,0x1f,0xc7,0x06,0xfb,0x34,0x64,0x00,0xba
-,0x08,0x00,0xb8,0x0f,0x00,0xef,0xe8,0x82,0x01,0xe8,0x9b,0x01,0x72,0x0d,0xc7,0x06
-,0xf7,0x34,0x2c,0x00,0xc7,0x06,0xf9,0x34,0x04,0x00,0xc3,0xba,0x0a,0x00,0x33,0xc0
-,0xef,0xe8,0x98,0x01,0xe8,0xb5,0x01,0xb8,0x17,0x00,0xba,0x9c,0x00,0xef,0xb8,0x00
-,0x10,0xba,0x9a,0x00,0xef,0xb8,0x17,0x00,0xa9,0x01,0x00,0x74,0x01,0x40,0xba,0x8c
-,0x00,0xef,0xb8,0x00,0x18,0xba,0x86,0x00,0xef,0xb8,0x0c,0x00,0xba,0x82,0x00,0xef
-,0xba,0x02,0x00,0xed,0x25,0xf9,0xff,0x0d,0x02,0x00,0xef,0xba,0x06,0x00,0x33,0xc0
-,0xef,0xba,0x04,0x00,0xb8,0x60,0x00,0xef,0xba,0x00,0x00,0xb8,0x18,0x00,0xef,0xba
-,0x80,0x00,0xb9,0xff,0xff,0xed,0xa9,0x01,0x00,0x75,0x04,0xe2,0xf8,0xeb,0x3e,0xba
-,0x0a,0x00,0xed,0xa9,0x00,0x40,0x74,0x35,0xa9,0x00,0x20,0x74,0x30,0x33,0xc0,0xef
-,0x51,0xb9,0xc8,0x00,0xe2,0xfe,0x59,0x1e,0x06,0x1f,0x26,0x8b,0x0e,0x02,0x30,0x83
-,0xf9,0x17,0x75,0x18,0x49,0x49,0xbe,0x02,0x20,0xbf,0x06,0x30,0xf3,0xa6,0x1f,0x23
-,0xc9,0x75,0x0a,0xff,0x0e,0xfb,0x34,0x74,0x12,0xe9,0x4d,0xff,0x1f,0xb8,0x2c,0x00
-,0xbb,0x00,0x00,0xa3,0xf7,0x34,0x89,0x1e,0xf9,0x34,0xc3,0xc7,0x06,0xfb,0x34,0x64
-,0x00,0xe8,0xd3,0x00,0x72,0x0d,0xc7,0x06,0xf7,0x34,0x2c,0x00,0xc7,0x06,0xf9,0x34
-,0x04,0x00,0xc3,0xe8,0xd6,0x00,0xe8,0xf3,0x00,0xb8,0x03,0x00,0xba,0x82,0x00,0xef
-,0xb8,0x40,0x80,0xba,0x98,0x00,0xef,0xb8,0x00,0x11,0xba,0x96,0x00,0xef,0xb8,0x40
-,0x00,0xa9,0x01,0x00,0x74,0x01,0x40,0xba,0x92,0x00,0xef,0xb8,0x00,0x19,0xba,0x8e
-,0x00,0xef,0xba,0x02,0x00,0xed,0x25,0xf9,0xff,0x0d,0x06,0x00,0xef,0xba,0x06,0x00
-,0x33,0xc0,0xef,0xba,0x00,0x00,0xb8,0x18,0x00,0xef,0xba,0x80,0x00,0xb9,0xff,0xff
-,0xed,0xa9,0x20,0x00,0x75,0x04,0xe2,0xf8,0xeb,0x43,0xba,0x0a,0x00,0xed,0xa9,0x00
-,0x40,0x74,0x3a,0xa9,0x00,0x20,0x74,0x35,0x33,0xc0,0xef,0x51,0xb9,0xc8,0x00,0xe2
-,0xfe,0x59,0x1e,0x06,0x1f,0x26,0x8b,0x0e,0x02,0x32,0x83,0xf9,0x40,0x75,0x1d,0x49
-,0x49,0xbe,0x02,0x22,0xbf,0x06,0x32,0xf3,0xa6,0x1f,0x23,0xc9,0x75,0x0f,0xff,0x0e
-,0xfb,0x34,0x74,0x03,0xe9,0x5a,0xff,0xb8,0x00,0x00,0xeb,0x0b,0x1f,0xb8,0x2c,0x00
-,0xbb,0x02,0x00,0x89,0x1e,0xf9,0x34,0xa3,0xf7,0x34,0xc3,0xba,0x02,0x00,0xb8,0x00
-,0x9c,0xef,0xba,0x00,0x00,0xb8,0x00,0x84,0xef,0x33,0xc0,0xef,0xba,0x0a,0x00,0xef
-,0xba,0x0e,0x00,0x33,0xc0,0xef,0xc3,0xba,0x0a,0x00,0xb9,0xff,0xff,0xed,0x25,0x00
-,0x60,0x3d,0x00,0x60,0x74,0x04,0xe2,0xf5,0xf8,0xc3,0xf9,0xc3,0xb0,0x00,0xe6,0x56
-,0xb8,0x00,0xff,0xba,0x52,0x00,0xef,0xb9,0xff,0xff,0xba,0x58,0x00,0xed,0x25,0xef
-,0x00,0x74,0x08,0xba,0x5a,0x00,0x33,0xc0,0xef,0xe2,0xef,0xc3,0xba,0x80,0x00,0xed
-,0xba,0x84,0x00,0xef,0xba,0x80,0x00,0xed,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0xc6,0x06,0xec,0x34,0x15,0x33,0xc0,0x8e,0xd8,0x8e,0xc0,0x1e,0x8c,0xc8,0xbe,0x40
-,0x54,0xbf,0x60,0xfe,0x8e,0xd8,0xb9,0x10,0x00,0xf3,0xa4,0x1f,0xc7,0x06,0x80,0x36
-,0x10,0x35,0xc7,0x06,0x8c,0x36,0x30,0x35,0x8d,0x06,0x38,0x35,0xa3,0x30,0x35,0xa3
-,0x32,0x35,0x05,0x33,0x01,0xa3,0x34,0x35,0xc7,0x06,0x36,0x35,0x50,0x01,0xc7,0x06
-,0x84,0x36,0x80,0xfe,0xc7,0x06,0x88,0x36,0xc0,0xfe,0xc6,0x06,0xc2,0xfe,0xff,0xc6
-,0x06,0x93,0x36,0x80,0xc6,0x06,0x92,0x36,0x00,0xc6,0x06,0x80,0xfe,0x80,0xc7,0x06
-,0x82,0xfe,0x54,0x50,0xc7,0x06,0x84,0xfe,0x2b,0x4d,0xe5,0xce,0xa9,0x02,0x00,0x75
-,0x08,0xc6,0x06,0x81,0xfe,0x23,0xe9,0x05,0x00,0xc6,0x06,0x81,0xfe,0x22,0xa1,0xf7
-,0x34,0xa3,0x86,0xfe,0xb8,0x48,0x34,0x86,0xe0,0xa3,0x88,0xfe,0x8d,0x06,0x4e,0x34
-,0x86,0xe0,0xa3,0x8a,0xfe,0xb8,0x58,0x34,0x86,0xe0,0xa3,0x8c,0xfe,0xb8,0x9c,0x34
-,0x86,0xe0,0xa3,0x8e,0xfe,0x8d,0x06,0x20,0x03,0x86,0xe0,0xa3,0x90,0xfe,0x33,0xc0
-,0xba,0x72,0x00,0xef,0x33,0xc0,0xba,0x74,0x00,0xef,0xba,0x76,0x00,0xef,0xb8,0x80
-,0xfe,0x86,0xe0,0xba,0x72,0x00,0xef,0xe8,0xbf,0x07,0xba,0x0c,0x01,0xb8,0x40,0x40
-,0xef,0xed,0xba,0x6a,0x00,0xb8,0x03,0x00,0xc1,0xe0,0x08,0x0d,0x03,0x00,0xef,0xb9
-,0x0a,0x00,0xe8,0x94,0x00,0xba,0x6a,0x00,0xb8,0x03,0x00,0xc1,0xe0,0x08,0xef,0xa1
-,0x32,0x34,0xa3,0xa2,0x33,0xc7,0x06,0xa6,0x33,0x04,0x00,0x8d,0x06,0xa0,0x33,0xc1
-,0xe8,0x04,0xcd,0x39,0xc7,0x06,0x90,0x36,0xff,0xff,0xe9,0xe3,0x00,0x63,0x0d,0x66
-,0x0d,0x66,0x0d,0x8a,0x0d,0xe6,0x0e,0x75,0x12,0x2e,0x0f,0x03,0x0f,0x50,0x0f,0x60
-,0x0d,0x60,0x0d,0x60,0x0d,0xed,0x0f,0xe9,0x12,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60
-,0x0d,0x60,0x0d,0x22,0x10,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0xfe,0x10,0x60
-,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0xaf,0x0f,0x32,0x10,0x37
-,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60
-,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60,0x0d,0x60
-,0x0d,0x64,0x0e,0x00,0x0f,0x95,0x09,0x60,0x0a,0x49,0xbb,0xff,0xff,0xba,0x6a,0x00
-,0xed,0xa9,0x00,0x20,0x74,0x38,0x80,0x3e,0x80,0xfe,0x12,0x75,0x31,0xe8,0x4a,0x00
-,0xa1,0x32,0x34,0xa3,0xa2,0x33,0xc7,0x06,0xa6,0x33,0x04,0x00,0x8d,0x06,0xa0,0x33
-,0xc1,0xe8,0x04,0xcd,0x39,0xe8,0x22,0x00,0xc7,0x06,0xf3,0x34,0x46,0x00,0xc7,0x06
-,0xf5,0x34,0xff,0xff,0xc7,0x06,0x90,0x36,0xff,0xff,0x58,0xe9,0x32,0x00,0x4b,0x83
-,0xfb,0x00,0x75,0xb9,0x83,0xf9,0x00,0x75,0xb0,0xc3,0x52,0xba,0x6a,0x00,0xb8,0x03
-,0x00,0xc1,0xe0,0x08,0x0d,0x03,0x00,0xef,0x5a,0xc3,0x52,0xba,0x6a,0x00,0xb8,0x03
-,0x00,0xc1,0xe0,0x08,0xef,0x5a,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x68,0x80,0x07,0xa1,0x90,0x36,0xcd,0x35,0x8b,0x36,0x24,0x02,0x2e,0xff,0xa4,0x35
-,0x0a,0xfa,0x8a,0x26,0x94,0x36,0x88,0x26,0xe8,0x34,0xc6,0x06,0x94,0x36,0x00,0xfb
-,0x22,0xe4,0x75,0x01,0xc3,0xf6,0xc4,0x20,0x74,0x7d,0xf6,0xc4,0x08,0x74,0x05,0x80
-,0x0e,0x92,0x36,0x04,0x80,0x26,0xe8,0x34,0xd7,0xc4,0x1e,0x84,0x36,0x26,0x8b,0x37
-,0x81,0xe6,0xff,0x00,0x83,0xfe,0x20,0x76,0x05,0xb0,0x01,0xe9,0x28,0x00,0x53,0x06
-,0xd1,0xe6,0x2e,0xff,0x94,0x9d,0x06,0x07,0x5b,0x26,0x88,0x47,0x02,0x3c,0xff,0x74
-,0x07,0x3c,0xfe,0x75,0x11,0xe9,0x3b,0x00,0xf6,0x06,0x92,0x36,0x08,0x75,0x34,0xf6
-,0x06,0x92,0x36,0x04,0x74,0x2d,0x80,0x26,0x92,0x36,0xf3,0x80,0x3e,0x95,0x36,0x00
-,0x75,0x21,0x26,0x80,0x3f,0x05,0x75,0x13,0xc6,0x06,0x95,0x36,0x00,0x26,0x80,0x7f
-,0x06,0x00,0x74,0x07,0x26,0x8b,0x47,0x04,0xa2,0x95,0x36,0xba,0x0c,0x01,0xb8,0x40
-,0x40,0xef,0xed,0x8a,0x26,0xe8,0x34,0xf6,0xc4,0x10,0x75,0x03,0xe9,0x5b,0x00,0xf6
-,0xc4,0x04,0x74,0x05,0x80,0x0e,0x92,0x36,0x01,0x80,0x26,0xe8,0x34,0xeb,0xc4,0x3e
-,0x88,0x36,0x26,0x8b,0x35,0x83,0xe6,0x7f,0x83,0xfe,0x12,0x72,0x08,0x26,0xc6,0x45
-,0x02,0x01,0xe9,0x24,0x00,0x83,0xc6,0x20,0xd1,0xe6,0x2e,0xff,0x94,0x9d,0x06,0xc4
-,0x3e,0x88,0x36,0x26,0x88,0x45,0x02,0x3c,0xff,0x75,0x0e,0xf6,0x06,0x92,0x36,0x01
-,0x74,0x14,0xf6,0x06,0x92,0x36,0x02,0x75,0x0d,0x80,0x26,0x92,0x36,0xfc,0xba,0x0c
-,0x01,0xb8,0x20,0x20,0xef,0xed,0x8a,0x26,0xe8,0x34,0xf6,0xc4,0x08,0x74,0x22,0x80
-,0x26,0xe8,0x34,0xf7,0x80,0x0e,0x92,0x36,0x04,0xf6,0x06,0x92,0x36,0x08,0x74,0x11
-,0x80,0x26,0x92,0x36,0xf3,0xba,0x0c,0x01,0xb8,0x40,0x40,0xef,0xed,0x8a,0x26,0xe8
-,0x34,0xf6,0xc4,0x04,0x74,0x22,0x80,0x26,0xe8,0x34,0xfb,0x80,0x0e,0x92,0x36,0x01
-,0xf6,0x06,0x92,0x36,0x02,0x75,0x11,0x80,0x26,0x92,0x36,0xfe,0xba,0x0c,0x01,0xb8
-,0x20,0x20,0xef,0xed,0x8a,0x26,0xe8,0x34,0xf6,0xc4,0x01,0x74,0x67,0x80,0x26,0xe8
-,0x34,0xfe,0x80,0x3e,0xe8,0xff,0x00,0x74,0x39,0x80,0x3e,0xe8,0xff,0x04,0x74,0x32
-,0x80,0x3e,0xe8,0xff,0x01,0x75,0x21,0xe5,0x80,0xa9,0x00,0x07,0x74,0x0a,0xba,0x9e
-,0x00,0xb8,0x00,0x02,0xef,0xe9,0xef,0xff,0xc6,0x06,0xe8,0xff,0x03,0xba,0x0c,0x01
-,0xb8,0x08,0x08,0xef,0xed,0xe9,0x28,0x00,0x80,0x3e,0xe8,0xff,0x03,0x74,0x06,0xe9
-,0x1e,0x00,0xe9,0x00,0x00,0xba,0x10,0x01,0xb8,0x02,0x02,0xef,0xed,0xe5,0x00,0x0d
-,0x18,0x00,0xe7,0x00,0xe5,0x82,0x0d,0x02,0x00,0xe7,0x82,0xc6,0x06,0xe8,0xff,0x04
-,0x8a,0x26,0xe8,0x34,0xf6,0xc4,0x02,0x74,0x0d,0x80,0x26,0xe8,0x34,0xfd,0x80,0x26
-,0x92,0x36,0xbf,0xe8,0x4f,0x0b,0xfa,0xa0,0xe8,0x34,0x08,0x06,0x94,0x36,0xc6,0x06
-,0xe8,0x34,0x00,0xfb,0xc3,0xe8,0xe7,0x0f,0xc4,0x1e,0x84,0x36,0x2e,0xff,0x16,0x01
-,0x07,0x26,0x88,0x47,0x02,0xe9,0x7e,0xfe,0xe8,0x2d,0x10,0xc4,0x1e,0x84,0x36,0x2e
-,0xff,0x16,0x03,0x07,0x26,0x88,0x47,0x02,0xe9,0x6b,0xfe,0x8e,0x06,0x26,0x02,0x2e
-,0xff,0x16,0x07,0x07,0xc3,0xc3,0x83,0x3e,0xf5,0x34,0x00,0x74,0x0f,0xff,0x0e,0xf3
-,0x34,0x75,0x09,0xe8,0xc4,0xfd,0xc7,0x06,0xf5,0x34,0x00,0x00,0xf6,0x06,0x93,0x36
-,0x20,0x74,0x30,0xa1,0xc2,0x34,0x3b,0x06,0xe9,0x34,0xa3,0xe9,0x34,0x74,0x24,0x80
-,0x3e,0x95,0x36,0x00,0x75,0x1d,0xf7,0x06,0xe6,0x34,0x20,0x00,0x74,0x12,0xa9,0x20
-,0x00,0x74,0x0d,0x83,0x26,0xc2,0x34,0xdf,0x83,0x26,0xe9,0x34,0xdf,0xe9,0x03,0x00
-,0xe8,0xdd,0x09,0xba,0x06,0x01,0xed,0x8b,0xd0,0x81,0xe2,0x00,0xc0,0xc1,0xea,0x0e
-,0x03,0x16,0x74,0x34,0xc1,0xe0,0x02,0x11,0x06,0x72,0x34,0x73,0x04,0xff,0x06,0x74
-,0x34,0xba,0x02,0x01,0xed,0x8b,0xd0,0x81,0xe2,0x00,0xc0,0xc1,0xea,0x0e,0x03,0x16
-,0x70,0x34,0xc1,0xe0,0x02,0x11,0x06,0x6e,0x34,0x73,0x04,0xff,0x06,0x70,0x34,0xc7
-,0x06,0xa6,0x33,0x04,0x00,0xc7,0x06,0xaa,0x33,0x00,0x00,0x8d,0x06,0xa0,0x33,0xc1
-,0xe8,0x04,0xcd,0x39,0xc3,0x95,0x09,0x95,0x09,0x65,0x09,0x78,0x09,0x95,0x09,0x95
-,0x09,0x91,0x07,0x95,0x09,0x96,0x09,0x8b,0x09,0x95,0x09,0x95,0x09,0x95,0x09,0x95
-,0x09,0x95,0x09,0x95,0x09,0x8b,0xc0,0x8b,0xc0,0x8b,0xc0,0x8b,0xc0,0x8b,0xc0,0x90
-,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xe9,0xcc,0x00,0x8c,0xc0,0x40,0x8e,0xc0,0x26
-,0x8b,0x0e,0x06,0x00,0x86,0xe9,0x26,0x89,0x0e,0x06,0x00,0x8c,0xc2,0xc1,0xe2,0x04
-,0xbe,0x0e,0x00,0x26,0xa1,0x04,0x00,0xd0,0xe0,0x24,0xc0,0x8a,0xe0,0xc0,0xec,0x04
-,0x0a,0xc4,0x26,0xa2,0x05,0x00,0x26,0xa1,0x08,0x00,0xa9,0x00,0xc0,0x74,0x03,0xe9
-,0x9e,0x00,0x26,0xf6,0x06,0x10,0x00,0x80,0x75,0x03,0xe9,0x0a,0x00,0x26,0xa0,0x16
-,0x00,0x24,0x1f,0x32,0xe4,0x03,0xf0,0x80,0x3e,0xec,0x34,0x06,0x72,0x5c,0x80,0x3e
-,0x95,0x36,0x00,0x75,0x66,0x8b,0xfa,0x33,0xdb,0x8e,0xc3,0x26,0x89,0x1d,0x26,0x88
-,0x5d,0x04,0x51,0x50,0xc4,0x1e,0x8c,0x36,0xb9,0x0f,0x00,0x33,0xc0,0xe8,0x21,0x09
-,0x58,0x59,0x0b,0xdb,0x74,0x34,0xfe,0x0e,0xe6,0x3a,0x26,0xc6,0x07,0x81,0x26,0xc6
-,0x47,0x01,0x00,0x26,0xc6,0x47,0x02,0xff,0x26,0xc7,0x47,0x04,0x00,0x00,0x26,0x89
-,0x4f,0x0a,0x86,0xf2,0x26,0x89,0x57,0x06,0x26,0x89,0x77,0x08,0x26,0xc6,0x47,0x09
-,0x00,0x26,0xc6,0x47,0x0c,0x02,0xe8,0x8c,0x09,0xc3,0xff,0x06,0xec,0x33,0x8c,0xc0
-,0x48,0x8e,0xc0,0xfa,0xe8,0x97,0x10,0xfb,0xe9,0xeb,0xff,0x8c,0xc0,0x48,0x8e,0xc0
-,0xfa,0xe8,0x8a,0x10,0xfb,0xc3,0x8c,0xc0,0x8e,0xc0,0xfa,0xe8,0x80,0x10,0xfb,0xc3
-,0x80,0x3e,0x95,0x36,0x00,0x75,0x03,0xe9,0xc2,0x00,0xbf,0x08,0x00,0x26,0xf6,0x06
-,0x10,0x00,0x80,0x75,0x05,0x03,0xfe,0xe9,0x0c,0x00,0x26,0xa0,0x16,0x00,0x24,0x1f
-,0x32,0xe4,0x03,0xf0,0x03,0xfe,0xa0,0x95,0x36,0x3c,0x00,0x75,0x03,0xe9,0x9c,0x00
-,0x3c,0x01,0x74,0x0b,0x3c,0x02,0x74,0x14,0x3c,0x03,0x74,0x1d,0xe9,0x8d,0x00,0xc6
-,0x06,0x96,0x36,0x01,0xe8,0x3c,0x01,0x72,0x27,0xe9,0x80,0x00,0xc6,0x06,0x96,0x36
-,0x02,0xe8,0x83,0x00,0x72,0x1a,0xe9,0x73,0x00,0xc6,0x06,0x96,0x36,0x01,0xe8,0x22
-,0x01,0x72,0x0d,0xc6,0x06,0x96,0x36,0x02,0xe8,0x6c,0x00,0x72,0x03,0xe9,0x5c,0x00
-,0x53,0x06,0x50,0xc4,0x1e,0x8c,0x36,0xb9,0x0b,0x00,0x33,0xc0,0xe8,0x42,0x08,0x58
-,0x26,0xc6,0x07,0x82,0x26,0xc6,0x47,0x02,0xff,0x8d,0x06,0xe0,0xfe,0x86,0xc4,0x26
-,0x89,0x47,0x06,0xa0,0x96,0x36,0x26,0x88,0x47,0x08,0xe8,0xc8,0x08,0x07,0x5b,0x83
-,0x26,0xad,0x36,0xfe,0xa1,0xad,0x36,0xe7,0x04,0xba,0x10,0x01,0xb8,0x80,0x80,0xef
-,0xed,0xba,0x10,0x01,0xb8,0x02,0x02,0xef,0xed,0x52,0xba,0xe0,0x00,0xb8,0x41,0x10
-,0xef,0x5a,0xb8,0x9c,0x03,0xcd,0x39,0xc6,0x06,0x95,0x36,0x00,0x8c,0xc0,0x48,0x8e
-,0xc0,0xfa,0xe8,0xa9,0x0f,0xfb,0xc3,0x1e,0x06,0x1f,0x06,0x33,0xc0,0x8e,0xc0,0x8b
-,0xf0,0x8d,0x3e,0x20,0xf3,0x51,0xb1,0x0a,0x26,0x83,0x7d,0x0c,0x01,0x75,0x2a,0x57
-,0x26,0x83,0x7d,0x0e,0x00,0x74,0x06,0xe8,0x2f,0x00,0xe9,0x03,0x00,0xe8,0x66,0x07
-,0x5f,0x73,0x16,0x33,0xc0,0x8e,0xd8,0x26,0x8b,0x4d,0x12,0x8d,0x75,0x20,0x8d,0x3e
-,0xe0,0xfe,0xf3,0xa4,0x59,0x07,0x1f,0xf9,0xc3,0xfe,0xc9,0x74,0x07,0x81,0xc7,0x20
-,0x01,0xe9,0xc4,0xff,0x59,0x07,0x1f,0xf8,0xc3,0x51,0x50,0x53,0x56,0x52,0x57,0x33
-,0xdb,0x26,0x8a,0x5d,0x0e,0x26,0x8b,0x4d,0x12,0x8d,0x7d,0x20,0x5a,0x87,0xd7,0x26
-,0x8a,0x45,0x14,0x87,0xd7,0x42,0x32,0xff,0x80,0xff,0x08,0x75,0x08,0xfe,0xcb,0x22
-,0xdb,0x75,0xea,0x33,0xdb,0x23,0xdb,0x74,0x06,0xfe,0xc7,0xd0,0xc8,0x73,0x0c,0x50
-,0x26,0x8a,0x05,0x38,0x04,0x58,0x74,0x03,0xe9,0x0a,0x00,0x49,0x46,0x47,0x23,0xc9
-,0x74,0x0a,0xe9,0xd3,0xff,0x5a,0x5e,0x5b,0x58,0x59,0xf8,0xc3,0x5a,0x5e,0x5b,0x58
-,0x59,0xf9,0xc3,0x1e,0x06,0x1f,0x06,0x33,0xc0,0x8e,0xc0,0x86,0xcd,0x2b,0xce,0x8b
-,0xf7,0x8b,0xc1,0x33,0xc9,0x80,0x3c,0xff,0x74,0x16,0x80,0xf9,0x06,0x73,0x09,0x32
-,0xc9,0x46,0x48,0x74,0x2e,0xe9,0xed,0xff,0x3d,0x60,0x00,0x73,0x0c,0xe9,0x23,0x00
-,0xfe,0xc1,0x46,0x48,0x74,0x1d,0xe9,0xdc,0xff,0xb8,0x10,0x00,0x8d,0x3e,0x18,0x34
-,0x32,0xed,0xb1,0x06,0xf3,0xa6,0x74,0x03,0xe9,0x08,0x00,0x48,0x23,0xc0,0x74,0x07
-,0xe9,0xe9,0xff,0x07,0x1f,0xf8,0xc3,0x8d,0x36,0x18,0x34,0x33,0xc0,0x8e,0xd8,0x8d
-,0x3e,0xe0,0xfe,0xb8,0x10,0x00,0xb9,0x06,0x00,0x56,0xf3,0xa4,0x5e,0x48,0x3d,0x00
-,0x00,0x75,0xf3,0x07,0x1f,0xf9,0xc3,0xff,0x06,0xe4,0x33,0xc6,0x06,0xeb,0x34,0x00
-,0x26,0x8b,0x45,0x06,0x86,0xe0,0xc1,0xe8,0x04,0x48,0x06,0x8e,0xc0,0xfe,0x06,0xe6
-,0x3a,0xfa,0xe8,0x69,0x0e,0xfb,0x07,0xb0,0xff,0xc3,0x00,0x00,0x00,0x00,0x00,0x00
-,0xb0,0x01,0xc3,0xb0,0x00,0xc3,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xb0,0x04,0xc3
-,0x8b,0x0e,0x97,0x36,0x81,0xe1,0x80,0x30,0x26,0x8b,0x47,0x04,0x25,0x7f,0xcf,0x0b
-,0xc1,0xa3,0x97,0x36,0xa3,0xe6,0x34,0xb0,0x00,0xc3,0xf6,0x06,0x93,0x36,0x20,0x74
-,0x03,0xb0,0x03,0xc3,0x26,0x8b,0x47,0x08,0xa3,0x97,0x36,0xa3,0xe6,0x34,0x26,0x8a
-,0x47,0x20,0xa2,0xfd,0x34,0x3c,0x01,0x75,0x06,0xc7,0x06,0xa1,0x36,0x00,0x00,0x26
-,0x8a,0x47,0x21,0xa2,0xfe,0x34,0x26,0x8b,0x47,0x0a,0xa3,0x18,0x34,0xa3,0x58,0x34
-,0x26,0x8b,0x47,0x0c,0xa3,0x1a,0x34,0xa3,0x5a,0x34,0x26,0x8b,0x47,0x0e,0xa3,0x1c
-,0x34,0xa3,0x5c,0x34,0xc6,0x06,0x2a,0x34,0xc0,0x26,0x8b,0x47,0x14,0x25,0x7f,0xff
-,0x09,0x06,0x2c,0x34,0x26,0x8b,0x47,0x16,0x25,0xff,0xfe,0x25,0xff,0xfc,0x09,0x06
-,0x2e,0x34,0xc6,0x06,0x00,0x34,0xc0,0x26,0x8b,0x47,0x10,0xa3,0x02,0x34,0x26,0x8b
-,0x47,0x12,0xa3,0x04,0x34,0x06,0x53,0xe8,0x84,0x0a,0x5b,0x07,0x3d,0x00,0x00,0x75
-,0x07,0x80,0x0e,0x92,0x36,0x08,0xb0,0xfe,0xc3,0xb9,0x00,0x01,0xa1,0xac,0x33,0x33
-,0xd2,0xf7,0xf9,0xa3,0xae,0x33,0x91,0x49,0x33,0xd2,0xf7,0xe9,0x05,0x00,0x3b,0xa3
-,0x46,0x34,0xbf,0x00,0x3b,0x89,0x3e,0x44,0x34,0xba,0x68,0x00,0xb8,0xe0,0xe0,0xef
-,0xa1,0xae,0x33,0xe7,0x62,0xa1,0xae,0x33,0xba,0x08,0x01,0xef,0xa1,0x44,0x34,0xe7
-,0x64,0xa1,0x44,0x34,0xba,0x0a,0x01,0xef,0xb8,0x00,0x01,0x2d,0x04,0x00,0x0d,0x00
-,0x10,0xe7,0x92,0xc3,0x3d,0x00,0x00,0x74,0x0a,0x26,0x89,0x47,0x07,0xe8,0x83,0x3a
-,0xb0,0x07,0xc3,0xa1,0xae,0x33,0x26,0x89,0x47,0x2b,0xa1,0x44,0x34,0x26,0x89,0x47
-,0x2d,0xa1,0x46,0x34,0x26,0x89,0x47,0x2f,0x80,0x0e,0x93,0x36,0x20,0xa1,0x88,0x36
-,0x86,0xe0,0x26,0x89,0x47,0x08,0xa1,0x84,0x36,0x86,0xe0,0x26,0x89,0x47,0x0a,0xa1
-,0x80,0x36,0x86,0xe0,0x26,0x89,0x47,0x0c,0xb8,0x60,0xfe,0x86,0xe0,0x26,0x89,0x47
-,0x0e,0xa0,0xa1,0x36,0x26,0x88,0x47,0x10,0x8b,0x36,0x88,0x36,0x26,0xc6,0x44,0x02
-,0xff,0xe5,0x9e,0xa9,0x00,0x08,0x74,0x0c,0xba,0x84,0x00,0xed,0x0d,0x08,0x00,0xef
-,0xba,0x8e,0x00,0xef,0xe5,0x02,0x25,0xf9,0xff,0xe7,0x02,0xba,0x10,0x01,0xb8,0x02
-,0x02,0xef,0xed,0xb0,0x00,0xc3,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xb0,0x01,0xc3
-,0x80,0x26,0x93,0x36,0x9f,0xe8,0x8d,0x0a,0x80,0x0e,0x92,0x36,0x08,0xb0,0xfe,0xc3
-,0xb0,0x00,0xc3,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xb0,0x04,0xc3,0xc6,0x06,0x2a
-,0x34,0xc0,0x26,0x8b,0x47,0x06,0x25,0x7f,0xff,0xa3,0x2c,0x34,0x26,0x8b,0x47,0x08
-,0x25,0xff,0xfe,0x25,0xff,0xfc,0xa3,0x2e,0x34,0xcd,0x52,0xb0,0x00,0xc3,0xf6,0x06
-,0x93,0x36,0x20,0x75,0x03,0xb0,0x04,0xc3,0xc6,0x06,0x00,0x34,0xc0,0x26,0x8b,0x47
-,0x06,0xa3,0x02,0x34,0x26,0x8b,0x47,0x08,0xa3,0x04,0x34,0xcd,0x52,0xb0,0x00,0xc3
-,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xb0,0x04,0xc3,0x57,0x8d,0x7f,0x06,0x51,0xb9
-,0x07,0x00,0x33,0xc0,0xf3,0xab,0x59,0x8d,0x7f,0x06,0xa1,0x7a,0x34,0x03,0x06,0x39
-,0x37,0x26,0x88,0x05,0xa1,0x95,0x37,0x26,0x88,0x45,0x02,0xa1,0x80,0x34,0x03,0x06
-,0x76,0x34,0x26,0x88,0x45,0x07,0xa1,0xc6,0x34,0x26,0x88,0x45,0x09,0xa1,0xd8,0x33
-,0x26,0x88,0x45,0x0a,0x33,0xc0,0xa3,0x7a,0x34,0xa3,0x39,0x37,0xa3,0x95,0x37,0xa3
-,0x80,0x34,0xa3,0x76,0x34,0xa3,0xc6,0x34,0xa3,0xd8,0x33,0x5f,0xb0,0x00,0xc3,0xf6
-,0x06,0x93,0x36,0x20,0x75,0x03,0xb0,0x04,0xc3,0x26,0x8b,0x4f,0x04,0x83,0xf9,0x06
-,0x74,0x12,0x83,0xf9,0x04,0x74,0x0d,0x83,0xf9,0x00,0x74,0x08,0x83,0xf9,0x02,0x74
-,0x03,0xb0,0x01,0xc3,0x89,0x0e,0xe8,0x3a,0x83,0x26,0xab,0x36,0xf9,0x09,0x0e,0xab
-,0x36,0xe5,0x02,0x25,0xf9,0xff,0x0b,0xc1,0xe7,0x02,0xb0,0x00,0xc3,0xf6,0x06,0x93
-,0x36,0x20,0x75,0x03,0xb0,0x04,0xc3,0x26,0x8b,0x4f,0x04,0x80,0xf9,0xff,0x74,0x08
-,0x80,0xf9,0x00,0x74,0x10,0xb0,0x01,0xc3,0x83,0x0e,0xad,0x36,0x02,0xa1,0xad,0x36
-,0xe7,0x04,0xe9,0x0a,0x00,0x83,0x26,0xad,0x36,0xfd,0xa1,0xad,0x36,0xe7,0x04,0xb0
-,0x00,0xc3,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xb0,0x04,0xc3,0xe8,0xd5,0x04,0xb0
-,0x00,0xc3,0xf6,0x06,0x93,0x36,0x80,0x75,0x03,0xb0,0x01,0xc3,0x26,0x83,0x7f,0x06
-,0x05,0x75,0x03,0xe9,0x9d,0x00,0x26,0x8b,0x57,0x04,0x26,0x8b,0x47,0x08,0x26,0x81
-,0x7f,0x06,0x00,0x80,0x75,0x08,0xed,0x26,0x89,0x47,0x0a,0xe9,0x9d,0x00,0x26,0x83
-,0x7f,0x06,0x01,0x75,0x04,0xef,0xe9,0x92,0x00,0x26,0x81,0x7f,0x06,0x01,0x80,0x75
-,0x09,0xef,0xed,0x26,0x89,0x47,0x0a,0xe9,0x81,0x00,0x26,0x83,0x7f,0x06,0x02,0x75
-,0x07,0x26,0x21,0x47,0x04,0xe9,0x73,0x00,0x26,0x81,0x7f,0x06,0x02,0x80,0x75,0x0c
-,0x26,0x21,0x47,0x04,0xed,0x26,0x89,0x47,0x0a,0xe9,0x5f,0x00,0x26,0x83,0x7f,0x06
-,0x03,0x75,0x07,0x26,0x09,0x47,0x04,0xe9,0x51,0x00,0x26,0x81,0x7f,0x06,0x03,0x80
-,0x75,0x0c,0x26,0x09,0x47,0x04,0xed,0x26,0x89,0x47,0x0a,0xe9,0x3d,0x00,0x26,0x83
-,0x7f,0x06,0x04,0x75,0x07,0x26,0x31,0x47,0x04,0xe9,0x2f,0x00,0x26,0x81,0x7f,0x06
-,0x04,0x80,0x75,0x0c,0x26,0x31,0x47,0x04,0xed,0x26,0x89,0x47,0x0a,0xe9,0x1b,0x00
-,0xb0,0x01,0xc3,0xfa,0x53,0x26,0x8b,0x4f,0x08,0x0b,0xc9,0x74,0x0c,0x8d,0x1e,0xe0
-,0xfe,0xe8,0x52,0xff,0x83,0xc3,0x08,0xe2,0xf8,0x5b,0xfb,0xb0,0x00,0xc3,0xf6,0x06
-,0x93,0x36,0x80,0x75,0x0a,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xb0,0x01,0xc3,0x8d
-,0x3e,0xe0,0xfe,0xe5,0x00,0x26,0x89,0x05,0xe5,0x02,0x26,0x89,0x45,0x02,0xa1,0xad
-,0x36,0x26,0x89,0x45,0x04,0xe5,0x06,0x26,0x89,0x45,0x06,0xe5,0x08,0x26,0x89,0x45
-,0x08,0xe5,0x0a,0x26,0x89,0x45,0x0a,0xe5,0x0e,0x26,0x89,0x45,0x0c,0xe5,0x48,0x26
-,0x89,0x45,0x0e,0xe5,0x4a,0x26,0x89,0x45,0x10,0xe5,0x4c,0x26,0x89,0x45,0x12,0xa1
-,0xb7,0x36,0x26,0x89,0x45,0x14,0xe5,0x50,0x26,0x89,0x45,0x16,0xe5,0x52,0x26,0x89
-,0x45,0x18,0xe5,0x54,0x26,0x89,0x45,0x1a,0xe5,0x56,0x26,0x89,0x45,0x1c,0xe5,0x58
-,0x26,0x89,0x45,0x1e,0xe5,0x62,0x26,0x89,0x45,0x20,0xe5,0x64,0x26,0x89,0x45,0x22
-,0xe5,0x66,0x26,0x89,0x45,0x24,0xe5,0x68,0x26,0x89,0x45,0x26,0xe5,0x6a,0x26,0x89
-,0x45,0x28,0xe5,0x6c,0x26,0x89,0x45,0x2a,0xe5,0x70,0x26,0x89,0x45,0x2c,0xe5,0x72
-,0x26,0x89,0x45,0x2e,0xe5,0x74,0x26,0x89,0x45,0x30,0xe5,0x76,0x26,0x89,0x45,0x32
-,0xe5,0x7c,0x26,0x89,0x45,0x34,0xe5,0x7e,0x26,0x89,0x45,0x36,0xe5,0x80,0x26,0x89
-,0x45,0x38,0xe5,0x82,0x26,0x89,0x45,0x3a,0xe5,0x86,0x26,0x89,0x45,0x3c,0xe5,0x88
-,0x26,0x89,0x45,0x3e,0xe5,0x9a,0x26,0x89,0x45,0x40,0xe5,0x9e,0x26,0x89,0x45,0x42
-,0xe5,0xcc,0x26,0x89,0x45,0x44,0xe5,0xce,0x26,0x89,0x45,0x46,0xe5,0xd0,0x26,0x89
-,0x45,0x48,0xe5,0xd2,0x26,0x89,0x45,0x4a,0xba,0x00,0x01,0xed,0x11,0x06,0x66,0x34
-,0x73,0x04,0xff,0x06,0x68,0x34,0x26,0x89,0x45,0x4c,0xba,0x02,0x01,0xed,0xc1,0xe0
-,0x02,0x11,0x06,0x6e,0x34,0x73,0x04,0xff,0x06,0x70,0x34,0x26,0x89,0x45,0x4e,0xba
-,0x04,0x01,0xed,0x11,0x06,0x6a,0x34,0x73,0x04,0xff,0x06,0x6c,0x34,0x26,0x89,0x45
-,0x50,0xba,0x06,0x01,0xed,0xc1,0xe0,0x02,0x11,0x06,0x72,0x34,0x73,0x04,0xff,0x06
-,0x74,0x34,0x26,0x89,0x45,0x52,0xba,0x08,0x01,0xed,0x26,0x89,0x45,0x54,0xba,0x0a
-,0x01,0xed,0x26,0x89,0x45,0x56,0xba,0x0c,0x01,0xed,0x26,0x89,0x45,0x58,0xba,0x0e
-,0x01,0xed,0x01,0x06,0x7a,0x34,0x26,0x89,0x45,0x5e,0xba,0x10,0x01,0xed,0x26,0x89
-,0x45,0x5c,0xb0,0x00,0xc3,0xf6,0x06,0x93,0x36,0x80,0x74,0x07,0xf6,0x06,0x93,0x36
-,0x20,0x75,0x03,0xb0,0x01,0xc3,0x26,0x80,0x7f,0x06,0x00,0x75,0x30,0x80,0x3e,0x95
-,0x36,0x00,0x74,0x52,0xc6,0x06,0x95,0x36,0x00,0x83,0x26,0xad,0x36,0xfe,0xa1,0xad
-,0x36,0xe7,0x04,0xba,0x10,0x01,0xb8,0x80,0x80,0xef,0xed,0xba,0x10,0x01,0xb8,0x02
-,0x02,0xef,0xed,0xba,0xe0,0x00,0xb8,0x00,0x10,0xef,0xb0,0x00,0xc3,0x26,0x8b,0x47
-,0x04,0x3d,0x00,0x00,0x74,0x20,0x3d,0x03,0x00,0x77,0x1b,0xba,0x10,0x01,0xb8,0x02
-,0x00,0xef,0xba,0xe0,0x00,0xb8,0x01,0x10,0xef,0x83,0x0e,0xad,0x36,0x01,0xa1,0xad
-,0x36,0xe7,0x04,0xb0,0x00,0xc3,0xb0,0x06,0xc3,0xf6,0x06,0x93,0x36,0x80,0x75,0x03
-,0xb0,0x01,0xc3,0x26,0x83,0x7f,0x04,0x01,0x74,0x0a,0x26,0x83,0x7f,0x04,0x02,0x74
-,0x19,0xb0,0x06,0xc3,0x26,0x83,0x7f,0x06,0x0c,0x77,0xf6,0x26,0x83,0x7f,0x0a,0x60
-,0x77,0xef,0xe8,0x10,0x00,0x72,0x0b,0xb0,0x46,0xc3,0xe8,0x4e,0x00,0x72,0x03,0xb0
-,0x46,0xc3,0xb0,0x00,0xc3,0x51,0xb1,0x0a,0x8b,0x3e,0x20,0xf3,0x26,0x83,0x7d,0x0c
-,0x02,0x75,0x03,0xe9,0x0e,0x00,0xfe,0xc9,0x74,0x07,0x81,0xc7,0x20,0x01,0xe9,0xeb
-,0xff,0x59,0xf8,0xc3,0x57,0x8d,0x7d,0x0e,0x8d,0x77,0x06,0xb9,0x12,0x00,0xf3,0xa4
-,0x8d,0x7d,0x20,0x8d,0x36,0xe0,0xfe,0x26,0x8b,0x4d,0x12,0xf3,0xa4,0xff,0x06,0x01
-,0x35,0x5f,0x26,0xc7,0x45,0x0c,0x01,0x00,0x59,0xf9,0xc3,0x51,0xb1,0x0a,0x8d,0x3e
-,0x20,0xf3,0x8d,0x36,0xe0,0xfe,0x26,0x83,0x7d,0x0c,0x01,0x75,0x1b,0x57,0xe8,0x25
-,0x00,0x5f,0x73,0x14,0x33,0xc0,0xb9,0x20,0x01,0xf3,0xaa,0x26,0xc7,0x45,0x0c,0x02
-,0x00,0xff,0x0e,0x01,0x35,0x59,0xf9,0xc3,0xfe,0xc9,0x74,0x07,0x81,0xc7,0x20,0x01
-,0xe9,0xd3,0xff,0x59,0xf8,0xc3,0x51,0x26,0x8b,0x4d,0x12,0x8d,0x7d,0x20,0xf3,0xa6
-,0x74,0x03,0x59,0xf8,0xc3,0x59,0xf9,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x80,0x3e,0xec,0x34,0x06,0x72,0x33,0xff,0x06,0xf0,0x33,0x50,0xc4,0x1e,0x8c,0x36
-,0xb9,0x0f,0x00,0x33,0xc0,0xe8,0x29,0x00,0x58,0x81,0x26,0xc2,0x34,0xdf,0x7f,0x81
-,0x26,0xe9,0x34,0xdf,0x7f,0x0b,0xdb,0x74,0x11,0x26,0xc6,0x07,0x84,0x26,0xc6,0x47
-,0x02,0xff,0x26,0x89,0x47,0x06,0xe8,0xac,0x00,0xc3,0xff,0x06,0xea,0x33,0xe9,0xf5
-,0xff,0x57,0x26,0x8b,0x3f,0x03,0xf9,0x26,0x3b,0x7f,0x02,0x74,0x16,0x26,0x3b,0x7f
-,0x04,0x7c,0x2a,0x3d,0x00,0x00,0x75,0x13,0x8d,0x7f,0x08,0x03,0xf9,0x26,0x3b,0x7f
-,0x02,0x7c,0x14,0xff,0x06,0xde,0x33,0x33,0xdb,0x5f,0xc3,0x26,0x8b,0x7f,0x02,0x26
-,0x89,0x3f,0x03,0xf9,0xe9,0x06,0x00,0x26,0x89,0x3f,0x26,0x29,0x0f,0x26,0xc7,0x05
-,0xff,0xff,0x26,0x87,0x3f,0x26,0x89,0x0d,0x8d,0x5d,0x02,0x50,0x8b,0xfb,0x83,0xe9
-,0x02,0x33,0xc0,0xf3,0xaa,0x58,0xfe,0x0e,0xec,0x34,0x5f,0xc3,0x8b,0x7c,0x02,0x3b
-,0x3c,0x74,0x2f,0x83,0x3d,0xff,0x75,0x0b,0x8d,0x7c,0x08,0x89,0x7c,0x02,0x83,0x3d
-,0xff,0x74,0x1e,0x8a,0x45,0x02,0x3c,0x81,0x75,0x0c,0x80,0x3e,0xeb,0x34,0x00,0x74
-,0x05,0x33,0xc0,0xe9,0x0b,0x00,0x8b,0x0d,0x01,0x4c,0x02,0x8d,0x75,0x02,0x83,0xe9
-,0x02,0xc3,0x80,0x3e,0xec,0x34,0x06,0x72,0x05,0x33,0xc0,0xe9,0xf3,0xff,0xff,0x06
-,0xee,0x33,0xe9,0xbe,0xff,0xf6,0x06,0x92,0x36,0x40,0x74,0x01,0xc3,0x57,0x56,0x51
-,0x52,0x8b,0x36,0x8c,0x36,0xe8,0xa4,0xff,0x75,0x03,0xe9,0x1a,0x00,0xe9,0x1c,0x00
-,0xfe,0x06,0xec,0x34,0xc4,0x3e,0x80,0x36,0xf3,0xa4,0x80,0x0e,0x92,0x36,0x40,0xba
-,0x0c,0x01,0xb8,0x80,0x80,0xef,0xed,0x5a,0x59,0x5e,0x5f,0xc3,0xff,0x06,0xe0,0x33
-,0x80,0x3c,0x81,0x75,0x0c,0xff,0x06,0xe2,0x33,0xc6,0x06,0xeb,0x34,0x01,0xe9,0xcf
-,0xff,0x80,0x3c,0x84,0x75,0x07,0xff,0x06,0xe6,0x33,0xe9,0xc3,0xff,0xff,0x06,0xe8
-,0x33,0xe9,0xbc,0xff,0x8d,0x3e,0xe0,0xfe,0xa1,0x72,0x34,0xc7,0x06,0x72,0x34,0x00
-,0x00,0x89,0x05,0xa1,0x74,0x34,0xc7,0x06,0x74,0x34,0x00,0x00,0x89,0x45,0x02,0xba
-,0x04,0x01,0xed,0x89,0x45,0x04,0xc7,0x45,0x06,0x00,0x00,0xa1,0x6e,0x34,0xc7,0x06
-,0x6e,0x34,0x00,0x00,0x89,0x45,0x08,0xa1,0x70,0x34,0xc7,0x06,0x70,0x34,0x00,0x00
-,0x89,0x45,0x0a,0xba,0x00,0x01,0xed,0x89,0x45,0x0c,0xc7,0x45,0x0e,0x00,0x00,0x32
-,0xe4,0xba,0x0e,0x01,0xec,0x89,0x45,0x10,0xa1,0x7e,0x34,0xc7,0x06,0x7e,0x34,0x00
-,0x00,0x89,0x45,0x12,0xa1,0x8c,0x34,0xc7,0x06,0x8c,0x34,0x00,0x00,0x89,0x45,0x14
-,0xa1,0x8a,0x34,0xc7,0x06,0x8a,0x34,0x00,0x00,0x89,0x45,0x16,0xa1,0x7c,0x34,0xc7
-,0x06,0x7c,0x34,0x00,0x00,0x89,0x45,0x18,0xa1,0x88,0x34,0xc7,0x06,0x88,0x34,0x00
-,0x00,0x89,0x45,0x1a,0xa1,0xca,0x33,0xc7,0x06,0xca,0x33,0x00,0x00,0x89,0x45,0x1c
-,0xa1,0x78,0x34,0xc7,0x06,0x78,0x34,0x00,0x00,0x89,0x45,0x1e,0xa1,0xc6,0x34,0xc7
-,0x06,0xc6,0x34,0x00,0x00,0x89,0x45,0x20,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0xfa,0x33,0xc0,0x8e,0xd8,0x8e,0xc0,0xb8,0xa0,0x01,0xc1,0xe8,0x04,0x8e,0xd0,0x8d
-,0x26,0x80,0x00,0xe8,0x00,0x01,0xe8,0x10,0xeb,0x8b,0x1e,0xf7,0x34,0x8b,0x16,0xf9
-,0x34,0x8b,0x36,0xff,0x34,0x33,0xc0,0xb9,0xef,0xff,0x8d,0x3e,0x14,0x00,0x2b,0xcf
-,0x2b,0xce,0xd1,0xe9,0xf3,0xab,0x89,0x1e,0xf7,0x34,0x89,0x16,0xf9,0x34,0x83,0xfe
-,0x00,0x74,0x0c,0xb9,0xef,0xff,0xbf,0x80,0xfe,0x2b,0xcf,0xd1,0xe9,0xf3,0xab,0xb9
-,0xff,0xff,0x81,0xe9,0x00,0x3b,0x83,0xfe,0x00,0x74,0x03,0xe9,0x1b,0x00,0x51,0x1e
-,0xb8,0x00,0xe0,0x8e,0xd8,0x33,0xf6,0x8d,0x3e,0x00,0xd8,0xb9,0x00,0x0c,0xf3,0xa5
-,0x1f,0x59,0xbe,0xff,0xff,0x81,0xee,0x00,0xd8,0x2b,0xce,0x81,0xe1,0x00,0xff,0x89
-,0x0e,0xac,0x33,0x8d,0x06,0x20,0x02,0xc1,0xe8,0x04,0xa3,0x32,0x34,0x8e,0xd0,0x36
-,0xc7,0x06,0x1e,0x00,0x80,0x18,0x36,0xc7,0x06,0x22,0x00,0xff,0x7f,0x36,0xc7,0x06
-,0x0a,0x00,0xff,0xff,0x36,0xc7,0x06,0x1c,0x00,0x80,0x00,0x8d,0x06,0xa0,0x02,0xc1
-,0xe8,0x04,0xa3,0x30,0x34,0x8e,0xd0,0x36,0xc7,0x06,0x1e,0x00,0x50,0x28,0x36,0xc7
-,0x06,0x0a,0x00,0xff,0xff,0x36,0xc7,0x06,0x1c,0x00,0x80,0x00,0xb8,0xa0,0x01,0xc1
-,0xe8,0x04,0xa3,0x34,0x34,0xa3,0xf2,0x33,0x8e,0xd0,0x8d,0x26,0x80,0x00,0xb8,0x00
-,0x90,0xe7,0x02,0x8d,0x3e,0x70,0x01,0x8b,0xc7,0xc1,0xe8,0x04,0xb9,0x03,0x00,0x89
-,0x45,0x0e,0x89,0x45,0x02,0xc7,0x05,0xff,0xff,0x83,0xc7,0x10,0x05,0x01,0x00,0xe2
-,0xee,0xe8,0x5b,0x01,0xe5,0xce,0xa3,0xb5,0x36,0xe8,0x21,0x00,0xe8,0x45,0x01,0xa1
-,0x32,0x34,0x8c,0xcb,0xcd,0x37,0x0e,0x58,0xa9,0x00,0xf0,0x74,0x07,0x33,0xf6,0x89
-,0x36,0xff,0x34,0xc3,0x8d,0x36,0x30,0x61,0x89,0x36,0xff,0x34,0xc3,0x33,0xc0,0x8b
-,0xd0,0x8b,0xf2,0xb9,0x68,0x00,0x2e,0x80,0xbc,0xac,0x17,0x80,0x75,0x01,0xef,0x83
-,0xc2,0x02,0x46,0xe2,0xf1,0xb8,0x02,0x00,0xe7,0x50,0xb9,0x5a,0x00,0x33,0xff,0xc7
-,0x05,0x65,0x18,0x8c,0x4d,0x02,0x83,0xc7,0x04,0xe2,0xf4,0x33,0xc0,0x8e,0xc0,0x8c
-,0xc8,0x8e,0xd8,0x8d,0x3e,0x80,0x00,0x8d,0x36,0x9c,0x17,0xb9,0x08,0x00,0xe8,0x37
-,0x00,0x8d,0x36,0x20,0x21,0x8d,0x3e,0xc0,0x00,0xb9,0x0d,0x00,0xe8,0x29,0x00,0x8d
-,0x3e,0x40,0x01,0xb9,0x0a,0x00,0xe8,0x1f,0x00,0xe8,0x4b,0x0e,0x33,0xc0,0x8e,0xd8
-,0xc7,0x06,0x4e,0x37,0x6f,0x17,0xe7,0x48,0xe7,0x4c,0xb8,0x40,0x9c,0xe7,0x4a,0xe5
-,0x48,0x90,0xb8,0x00,0x70,0xe7,0x48,0xc3,0xa5,0x83,0xc7,0x02,0xe2,0xfa,0xc3,0xe5
-,0x4c,0xc3,0x50,0x51,0x56,0x57,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8,0xe5,0x58,0xd1
-,0xe0,0x73,0x11,0x8b,0xf0,0xd1,0xe6,0x33,0xc0,0x8e,0xd8,0x8b,0xb4,0x80,0x00,0x83
-,0xc6,0x0b,0xff,0xe6,0x1f,0x07,0x5a,0x5f,0x5e,0x59,0x58,0xcf,0x58,0x1c,0xe4,0x1c
-,0x6c,0x1c,0x8e,0x1a,0xc0,0x1f,0x40,0x1a,0x44,0x1c,0x65,0x18,0x80,0x80,0x80,0xff
-,0x80,0x03,0x02,0x80,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff
-,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff
-,0x80,0x03,0x03,0x43,0x80,0x80,0x02,0x80,0x42,0x03,0x02,0xff,0x03,0x01,0x03,0x01
-,0x01,0x03,0x02,0x03,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0x02,0x03,0x01,0x03
-,0x03,0xff,0x01,0x01,0xff,0x01,0xff,0x01,0x01,0x03,0x03,0x03,0xff,0xff,0xff,0xff
-,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff,0xff
-,0xff,0xff,0xff,0x02,0xb8,0x0f,0x00,0xe7,0x84,0xb8,0x0f,0xf8,0xe7,0x82,0xc3,0xb9
-,0x08,0x00,0x89,0x0e,0xe6,0x3a,0x8d,0x06,0x20,0x03,0x8b,0xd0,0xc1,0xe8,0x04,0xa3
-,0x90,0x01,0x8b,0xc2,0x8b,0xd8,0xc1,0xe8,0x04,0x8e,0xc0,0x05,0x61,0x00,0x26,0xa3
-,0x00,0x00,0xa1,0x30,0x34,0x26,0xa3,0x02,0x00,0x83,0xc3,0x14,0xd1,0xeb,0x26,0x89
-,0x1e,0x08,0x00,0x81,0xc2,0x10,0x06,0xe2,0xd9,0x26,0xc7,0x06,0x00,0x00,0xff,0xff
-,0x8c,0x06,0x92,0x01,0xc3,0x50,0x51,0x56,0x57,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8
-,0xe7,0x5a,0xff,0x06,0xbe,0x33,0xba,0xd2,0x00,0xed,0xcf,0x00,0x00,0x00,0x00,0x00
-,0x8c,0xcb,0xa1,0x30,0x34,0xcd,0x37,0xe9,0x06,0xed,0xb8,0x32,0x00,0xc3,0xe8,0x8c
-,0x01,0xfe,0x06,0xe2,0x34,0xe8,0x21,0x01,0x75,0xf0,0xe8,0x53,0x0e,0x81,0x0e,0xaf
-,0x36,0x00,0xc0,0xc7,0x06,0xad,0x36,0x60,0x00,0xf7,0x06,0xe6,0x34,0x80,0x00,0x75
-,0x1a,0xf7,0x06,0xe6,0x34,0x00,0x08,0x74,0x09,0xc7,0x06,0xab,0x36,0x0b,0x00,0xe9
-,0x0f,0x00,0xc7,0x06,0xab,0x36,0x03,0x00,0xe9,0x06,0x00,0xc7,0x06,0xab,0x36,0x11
-,0x9c,0xc7,0x06,0xa9,0x36,0x18,0x00,0xf7,0x06,0xe6,0x34,0x80,0x00,0x75,0x0d,0xf7
-,0x06,0xb5,0x36,0x02,0x00,0x74,0x05,0x83,0x0e,0xa9,0x36,0x20,0xa1,0xa9,0x36,0xe7
-,0x00,0xa1,0xab,0x36,0xe7,0x02,0xf7,0x06,0xe6,0x34,0x80,0x00,0x74,0x2e,0xe8,0xf2
-,0x2f,0x33,0xc0,0x0d,0x41,0x00,0xe7,0x56,0xa1,0xb1,0x36,0x0d,0x00,0x10,0xe7,0x08
-,0xa1,0xb3,0x36,0xe7,0x0a,0xa1,0xaf,0x36,0xe7,0x06,0xb8,0x40,0x00,0xe7,0x4e,0x33
-,0xc0,0xe7,0x0e,0xc7,0x06,0x26,0x02,0x00,0x00,0xe9,0x23,0x00,0xc7,0x06,0x4e,0x37
-,0x3f,0x20,0x8e,0x06,0x30,0x34,0x26,0xf7,0x06,0x0a,0x00,0x00,0x80,0x74,0x07,0x26
-,0x81,0x0e,0x08,0x00,0x00,0x80,0xc6,0x06,0xe0,0x34,0x01,0xb8,0x00,0x00,0xc3,0xfe
-,0x06,0xe1,0x34,0xc6,0x06,0xe0,0x34,0x00,0xa1,0x26,0x02,0x0b,0xc0,0x74,0x01,0xc3
-,0xe8,0x04,0x00,0xb8,0x00,0x00,0xc3,0xa1,0xa9,0x36,0xe7,0x00,0x8b,0x1e,0xab,0x36
-,0x83,0xe3,0x06,0xe5,0x02,0x25,0xf9,0xff,0x0b,0xc3,0x0d,0x10,0x00,0xe7,0x02,0xa1
-,0xad,0x36,0xe7,0x04,0xc3,0xb8,0x0a,0x00,0xe7,0x84,0xfe,0x06,0xe5,0x34,0xc6,0x06
-,0xe3,0x34,0x01,0x8e,0x06,0x30,0x34,0x26,0xf7,0x06,0x0a,0x00,0x00,0x40,0x74,0x07
-,0x26,0x81,0x0e,0x08,0x00,0x00,0x40,0xc3,0xc7,0x06,0x4e,0x37,0x6f,0x17,0xfe,0x06
-,0xe4,0x34,0xc6,0x06,0xe3,0x34,0x00,0xc3,0xc3,0xf6,0x06,0x18,0x34,0x80,0x75,0x0d
-,0xa1,0x18,0x34,0x0b,0x06,0x1a,0x34,0x0b,0x06,0x1c,0x34,0x75,0x01,0xc3,0xa1,0x2e
-,0x34,0x25,0xff,0xfe,0x8b,0x16,0xe7,0x36,0x81,0xe2,0x00,0x01,0x0b,0xc2,0xa3,0x2e
-,0x34,0x8d,0x16,0x10,0x00,0xbf,0x00,0x00,0xb9,0x08,0x00,0x8b,0x85,0x00,0x34,0xef
-,0x83,0xc2,0x10,0x8b,0x85,0x02,0x34,0xef,0x83,0xc2,0x10,0x8b,0x85,0x04,0x34,0xef
-,0x83,0xc2,0xe2,0x83,0xc7,0x06,0x49,0x75,0xe2,0xb8,0x00,0x00,0x8e,0xc0,0xbe,0x00
-,0x34,0xbf,0xb9,0x36,0xb9,0x18,0x00,0xf3,0xa5,0xb8,0x00,0x00,0xc3,0x33,0xc0,0x8e
-,0xc0,0x8d,0x3e,0xb0,0x33,0xb9,0x08,0x00,0xf3,0xab,0x8d,0x3e,0x3e,0x34,0xb9,0x03
-,0x00,0xf3,0xab,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x50,0x51,0x56,0x57,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8,0xe7,0x5a,0xff,0x06,0xba
-,0x33,0xe5,0x56,0x0d,0x20,0x00,0xe7,0x56,0xba,0x7a,0x00,0xed,0x08,0x26,0x94,0x36
-,0x33,0xc0,0xb1,0x08,0x32,0xed,0x06,0x8e,0xc0,0x8d,0x3e,0xe0,0xff,0xf3,0xaa,0x8e
-,0x06,0x32,0x34,0x26,0x81,0x0e,0x08,0x00,0x00,0x02,0x07,0xe5,0x56,0x25,0xdf,0xff
-,0xe7,0x56,0xe9,0xf8,0xfc,0x00,0xbd,0x1b,0x10,0x1b,0xd9,0x1a,0xf3,0x1a,0x50,0x51
-,0x56,0x57,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8,0xe7,0x5a,0xff,0x06,0xb6,0x33,0x53
-,0x06,0x51,0xe5,0x80,0xa3,0xb4,0x33,0x8b,0xd8,0x8b,0xc8,0x25,0x10,0x00,0xa3,0xed
-,0x34,0x0b,0xc0,0x74,0x14,0xff,0x06,0x80,0x34,0x80,0x3e,0xfe,0x34,0x00,0x74,0x03
-,0xe9,0x06,0x00,0xb8,0x80,0x00,0xe8,0x9d,0x04,0x83,0xe3,0x03,0xd1,0xe3,0x2e,0xff
-,0x97,0x86,0x1a,0x59,0x07,0x5b,0xe9,0xa4,0xfc,0xba,0x20,0x00,0x8e,0x06,0x3c,0x34
-,0x83,0x3e,0x3c,0x34,0x00,0x75,0x03,0xe9,0xf0,0x00,0xc7,0x06,0x3c,0x34,0x00,0x00
-,0xe9,0x2a,0x00,0xba,0x10,0x00,0x8e,0x06,0x3a,0x34,0x83,0x3e,0x3a,0x34,0x00,0x75
-,0x03,0xe9,0xd5,0xff,0xc7,0x06,0x3a,0x34,0x00,0x00,0xe8,0x10,0x00,0xe9,0xc9,0xff
-,0xba,0x10,0x00,0x8e,0x06,0x3a,0x34,0xc7,0x06,0x3a,0x34,0x00,0x00,0x26,0xa1,0x14
-,0x00,0x26,0xa3,0x0c,0x00,0x26,0xa1,0x16,0x00,0x26,0xa3,0x0e,0x00,0x26,0xc6,0x06
-,0x0a,0x00,0x00,0xc1,0xea,0x02,0x23,0xd1,0x74,0x1c,0xba,0x20,0x00,0x26,0xc7,0x06
-,0x0e,0x00,0xea,0x05,0x26,0x0b,0x16,0x0c,0x00,0x26,0x89,0x16,0x0c,0x00,0xff,0x06
-,0x86,0x34,0xff,0x06,0xdc,0x33,0x26,0xa1,0x0c,0x00,0xa9,0x00,0x37,0x74,0x16,0x26
-,0xc6,0x06,0x0a,0x00,0x02,0xa9,0x00,0x30,0x74,0x04,0xff,0x06,0x7a,0x34,0xff,0x06
-,0xda,0x33,0xe9,0x49,0x00,0xc0,0xec,0x07,0x83,0x16,0x8a,0x34,0x00,0x24,0x07,0x3c
-,0x07,0x75,0x04,0xff,0x06,0x8c,0x34,0xff,0x06,0x7e,0x34,0xa1,0x30,0x34,0x8c,0xc3
-,0x8e,0xc0,0x8e,0xdb,0x26,0x83,0x0e,0x08,0x00,0x40,0x8c,0xd8,0x26,0x87,0x06,0x16
-,0x00,0x26,0x83,0x3e,0x14,0x00,0xff,0x74,0x0a,0x8e,0xc0,0x26,0x8c,0x1e,0x00,0x00
-,0xe9,0x05,0x00,0x26,0x8c,0x1e,0x14,0x00,0x33,0xc0,0x8e,0xd8,0xc3,0xc3,0x8c,0xc0
-,0x87,0x06,0x92,0x01,0x3d,0xff,0xff,0x74,0x0d,0x8e,0xd8,0x8c,0x06,0x00,0x00,0x33
-,0xc0,0x8e,0xd8,0xe9,0x04,0x00,0x8c,0x06,0x90,0x01,0xe8,0x01,0x00,0xc3,0x06,0x83
-,0x3e,0x90,0x01,0xff,0x74,0x29,0x83,0x3e,0x3a,0x34,0x00,0x75,0x11,0xba,0x86,0x00
-,0xe8,0x1e,0x00,0x8c,0x06,0x3a,0x34,0x83,0x3e,0x90,0x01,0xff,0x74,0x11,0x83,0x3e
-,0x3c,0x34,0x00,0x75,0x0a,0xba,0x88,0x00,0xe8,0x06,0x00,0x8c,0x06,0x3c,0x34,0x07
-,0xc3,0xa1,0x90,0x01,0x8e,0xc0,0x26,0xa1,0x08,0x00,0xef,0x26,0xa1,0x00,0x00,0x26
-,0xc7,0x06,0x00,0x00,0xff,0xff,0xa3,0x90,0x01,0x3d,0xff,0xff,0x75,0x03,0xa3,0x92
-,0x01,0x83,0x3e,0xed,0x34,0x00,0x74,0x0b,0xb8,0x10,0x00,0xe7,0x84,0xc7,0x06,0xed
-,0x34,0x00,0x00,0xc3,0x50,0x51,0x56,0x57,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8,0xe7
-,0x5a,0xff,0x06,0xbc,0x33,0xe9,0x25,0xfb,0x50,0x51,0x56,0x57,0x52,0x06,0x1e,0x33
-,0xc0,0x8e,0xd8,0xe7,0x5a,0xff,0x06,0xb0,0x33,0xe9,0x11,0xfb,0x50,0x51,0x56,0x57
-,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8,0xe7,0x5a,0xff,0x06,0xb4,0x33,0x06,0xff,0x06
-,0x76,0x34,0x80,0x3e,0xfe,0x34,0x00,0x74,0x04,0x07,0xe9,0xf0,0xfa,0xb8,0x80,0x00
-,0xe8,0xd3,0x02,0x07,0xe9,0xe6,0xfa,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0xc6,0x1d,0x08,0x1d,0x91,0x1e,0x5d,0x1e,0x73,0x1e,0x89,0x1e,0x91,0x1e,0xa8,0x1d
-,0x91,0x1e,0x91,0x1e,0xaf,0x1e,0xaf,0x1e,0x15,0x1d,0x15,0x1d,0x91,0x1e,0x99,0x1f
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0x00,0x00,0x02,0x00,0x00
-,0x00,0x01,0x00,0x10,0x00,0x01,0x00,0x40,0x00,0x00,0x00,0x00,0x00,0x01,0x00,0x00
-,0x07,0xe9,0x99,0xfa,0x50,0x51,0x56,0x57,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8,0xe7
-,0x5a,0xff,0x06,0xb2,0x33,0x06,0x68,0xf6,0x1c,0xe5,0x06,0xa3,0xb2,0x33,0x8b,0xf0
-,0x83,0xe6,0x1e,0x2e,0xff,0xa4,0xa0,0x1c,0xe5,0x0c,0xa9,0x80,0x00,0x74,0x06,0xe8
-,0xa4,0x01,0xe5,0x06,0xc3,0x53,0xe5,0x0c,0x8b,0xd8,0xa9,0x01,0x00,0x74,0x14,0x83
-,0x3e,0xe0,0x3a,0x00,0x74,0x0d,0x8e,0x06,0x38,0x34,0xe8,0xbf,0x06,0xc7,0x06,0xe0
-,0x3a,0x00,0x00,0xe5,0x00,0x0d,0x18,0x00,0xe7,0x00,0xe5,0x02,0x0d,0x11,0x00,0xe7
-,0x02,0x8b,0xc3,0x5b,0xa9,0x01,0x00,0x74,0x01,0xc3,0x8b,0xd0,0xb8,0x00,0x08,0xe7
-,0x84,0x8b,0xc2,0x8e,0x06,0x38,0x34,0x26,0xa3,0x0c,0x00,0x8b,0xd0,0xc1,0xe0,0x03
-,0x83,0x16,0x88,0x34,0x00,0xff,0x06,0x7c,0x34,0x26,0x83,0x3e,0x06,0x00,0x0a,0x75
-,0x21,0x8b,0xc2,0x25,0x40,0x18,0x3d,0x40,0x00,0x74,0x0c,0x3d,0x00,0x10,0x75,0x12
-,0x26,0xfe,0x0e,0x0a,0x00,0x74,0x0b,0xf7,0x06,0xef,0x34,0x20,0x00,0x75,0x03,0xe9
-,0x5a,0x06,0x8c,0xc0,0x26,0x8e,0x06,0x02,0x00,0x26,0x83,0x0e,0x08,0x00,0x20,0x26
-,0xa3,0x12,0x00,0x26,0xa3,0x10,0x00,0xc3,0xff,0x06,0xc4,0x33,0xe5,0x0c,0xa9,0x01
-,0x00,0x75,0x01,0xc3,0xa9,0xf0,0x07,0x74,0x01,0xc3,0xff,0x06,0xd4,0x33,0xe5,0x00
-,0x0d,0x18,0x00,0xe7,0x00,0xc3,0xff,0x06,0xca,0x33,0x80,0x3e,0xa0,0x36,0x08,0x75
-,0x14,0x8e,0x06,0x30,0x34,0x26,0xf7,0x06,0x0a,0x00,0x00,0x08,0x74,0x07,0x26,0x81
-,0x0e,0x08,0x00,0x00,0x08,0xe5,0x82,0x25,0xfd,0xff,0xe7,0x82,0xe5,0x0c,0x50,0xe5
-,0x80,0x25,0x00,0x07,0xa3,0xe4,0x3a,0xe5,0x8c,0x25,0x00,0x80,0xa3,0xe2,0x3a,0x58
-,0xa9,0x02,0x00,0x75,0x25,0x83,0x3e,0xe2,0x3a,0x00,0x75,0x1e,0x83,0x3e,0xe4,0x3a
-,0x00,0x75,0x17,0xe5,0x08,0x0d,0x00,0x04,0x25,0xff,0x04,0xe7,0x08,0xe8,0x6a,0x01
-,0xe5,0x82,0x0d,0x02,0x00,0xe7,0x82,0xe9,0x21,0x00,0xe8,0x1a,0x06,0x80,0x3e,0xe8
-,0xff,0x00,0x74,0x0a,0x80,0x3e,0xe8,0xff,0x04,0x74,0x03,0xe9,0x0d,0x00,0xc6,0x06
-,0xe8,0xff,0x01,0xba,0x0c,0x01,0xb8,0x08,0x08,0xef,0xed,0x80,0x3e,0x9f,0x36,0x06
-,0x75,0x05,0x83,0x0e,0x99,0x36,0x40,0xb8,0x00,0x01,0xe9,0x09,0x01,0xff,0x06,0xcc
-,0x33,0x81,0x26,0xaf,0x36,0xff,0xf7,0xa1,0xaf,0x36,0xe7,0x06,0xff,0x06,0xc6,0x34
-,0xe9,0x1e,0x00,0xff,0x06,0xce,0x33,0xff,0x06,0x95,0x37,0x81,0x26,0xaf,0x36,0xff
-,0xef,0xa1,0xaf,0x36,0xe7,0x06,0xe9,0x08,0x00,0xff,0x06,0xd0,0x33,0xff,0x06,0x7a
-,0x34,0xff,0x06,0xd2,0x33,0xd1,0xe6,0x8e,0x06,0x30,0x34,0x2e,0x8b,0x84,0xc0,0x1c
-,0x26,0x09,0x06,0x08,0x00,0x2e,0x8b,0x84,0xc2,0x1c,0x09,0x06,0x66,0x37,0xc3,0xe5
-,0x0c,0xa9,0x80,0x00,0x74,0x56,0x50,0xe8,0xf0,0x00,0x58,0xa9,0x00,0x01,0x75,0x07
-,0xff,0x06,0xc6,0x33,0xe9,0x08,0x00,0xff,0x06,0x78,0x34,0xff,0x06,0xc8,0x33,0xe5
-,0x82,0x25,0xfd,0xff,0xe7,0x82,0xe8,0x6e,0x05,0xba,0x10,0x01,0xed,0x80,0x3e,0xe8
-,0xff,0x00,0x74,0x0a,0x80,0x3e,0xe8,0xff,0x04,0x74,0x03,0xe9,0x1d,0x00,0xc6,0x06
-,0xe8,0xff,0x01,0xba,0x0c,0x01,0xb8,0x08,0x08,0xef,0xed,0xe9,0x0d,0x00,0xc6,0x06
-,0xe8,0xff,0x03,0xba,0x0c,0x01,0xb8,0x08,0x08,0xef,0xed,0xc3,0xa9,0x01,0x00,0x74
-,0x1c,0xe8,0x2c,0x00,0x83,0x3e,0xe0,0x3a,0x00,0x74,0x0f,0x06,0x8e,0x06,0x38,0x34
-,0xe8,0xc9,0x04,0xc7,0x06,0xe0,0x3a,0x00,0x00,0x07,0xe9,0x5d,0x00,0x8b,0xd0,0x8e
-,0x06,0x38,0x34,0x26,0xa3,0x0c,0x00,0xe8,0x06,0x00,0x68,0x69,0x1d,0xe9,0x4a,0x00
-,0xa9,0x00,0x04,0x74,0x0a,0xb8,0x00,0x04,0xff,0x06,0xd8,0x33,0xe9,0x17,0x00,0xa9
-,0x00,0x01,0x74,0x0a,0xff,0x06,0x39,0x37,0xb8,0x00,0x01,0xe9,0x08,0x00,0xa9,0x10
-,0x00,0xb8,0x10,0x00,0x74,0x1d,0x09,0x06,0x66,0x37,0x8c,0xc0,0x8e,0x06,0x30,0x34
-,0x26,0xf7,0x06,0x0a,0x00,0x00,0x01,0x74,0x07,0x26,0x81,0x0e,0x08,0x00,0x00,0x01
-,0x8e,0xc0,0xc3,0xff,0x06,0xc2,0x33,0xe9,0xf8,0xff,0xe5,0x00,0x0d,0x18,0x00,0xe7
-,0x00,0xe5,0x02,0x0d,0x11,0x00,0xe7,0x02,0xc3,0x58,0xe9,0x43,0xfd,0xe5,0x08,0x0d
-,0x00,0x04,0x25,0xff,0x04,0xe7,0x08,0xe9,0xe0,0xff,0xe5,0x0e,0xa9,0x00,0x08,0x75
-,0x01,0xc3,0xe9,0xf5,0xff,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x50,0x51,0x56,0x57,0x52,0x06,0x1e,0x33,0xc0,0x8e,0xd8,0xe7,0x5a,0xff,0x06,0xb8
-,0x33,0xe5,0x48,0x06,0x53,0x57,0xff,0x16,0x4e,0x37,0x5f,0x5b,0x83,0x3e,0x80,0x01
-,0xff,0x74,0x58,0x8e,0x06,0x80,0x01,0x26,0xff,0x0e,0x08,0x00,0x75,0x4d,0x26,0xa1
-,0x00,0x00,0xa3,0x80,0x01,0x26,0xc7,0x06,0x00,0x00,0xff,0xff,0x8c,0xc0,0x26,0x8e
-,0x06,0x02,0x00,0x26,0x81,0x0e,0x08,0x00,0x80,0x00,0x8b,0xd0,0x26,0x87,0x06,0x1a
-,0x00,0x26,0x83,0x3e,0x18,0x00,0xff,0x74,0x0a,0x8e,0xc0,0x26,0x89,0x16,0x00,0x00
-,0xe9,0x05,0x00,0x26,0x89,0x16,0x18,0x00,0x83,0x3e,0x80,0x01,0xff,0x74,0x0c,0x8e
-,0x06,0x80,0x01,0x26,0x83,0x3e,0x08,0x00,0x00,0x74,0xb3,0x07,0xe9,0x3e,0xf7,0xe5
-,0x4c,0x90,0xe5,0x02,0xa9,0x00,0x20,0x74,0x0d,0x25,0xff,0xdf,0x0d,0x01,0x00,0xe7
-,0x02,0x0d,0x00,0x20,0xe7,0x02,0xe5,0x0a,0x8b,0xd8,0xa3,0xf4,0x33,0x25,0xc3,0x57
-,0x0d,0x00,0x10,0xe7,0x0a,0xf7,0x06,0x9b,0x36,0x00,0x80,0x74,0x37,0xf7,0xc3,0x00
-,0x80,0x74,0x06,0xf7,0xc3,0x00,0x08,0x74,0x5d,0x81,0x26,0xc2,0x34,0x7f,0xff,0xc7
-,0x06,0x35,0x37,0x05,0x00,0xb8,0x80,0x03,0xcd,0x39,0x81,0x26,0x9b,0x36,0xff,0x7f
-,0xc7,0x06,0x0f,0x37,0x04,0x00,0xf7,0x06,0x9b,0x36,0x40,0x00,0x75,0x06,0xc7,0x06
-,0x0f,0x37,0x03,0x00,0xf7,0x06,0x9b,0x36,0x00,0x20,0x74,0x2a,0xf7,0xc3,0x00,0x08
-,0x74,0x24,0x80,0x3e,0x9d,0x36,0x06,0x7c,0x1d,0xff,0x06,0x94,0x34,0x83,0x0e,0x66
-,0x37,0x20,0x8e,0x06,0x30,0x34,0x26,0xf7,0x06,0x0a,0x00,0x00,0x01,0x74,0x07,0x26
-,0x81,0x0e,0x08,0x00,0x00,0x01,0xf7,0xc3,0x00,0x20,0x75,0x3b,0xf7,0x06,0x9a,0x37
-,0x80,0x00,0x74,0x0b,0xff,0x06,0x89,0x37,0x33,0xc0,0xe7,0x0e,0xe9,0x04,0x00,0xff
-,0x06,0x3b,0x37,0xf7,0x06,0x9b,0x36,0x00,0x20,0x74,0x1c,0x80,0x26,0x9e,0x36,0xff
-,0x75,0x15,0x8e,0x06,0x30,0x34,0x26,0xf7,0x06,0x0a,0x00,0x00,0x08,0x74,0x07,0x26
-,0x81,0x0e,0x08,0x00,0x00,0x08,0xc3,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x02,0x23,0x02,0x23,0x02,0x23,0x02,0x23,0x03,0x23,0xdd,0x22,0x02,0x23,0xfd,0x21
-,0x02,0x23,0xa4,0x24,0xf3,0x24,0x02,0x23,0x8d,0x22,0x7a,0x23,0x02,0x23,0x97,0x24
-,0x1b,0x24,0x75,0x24,0x02,0x23,0x02,0x23,0x8e,0x25,0xfb,0x8e,0x06,0x7e,0x01,0xfb
-,0x26,0x83,0x3e,0x00,0x00,0xff,0x74,0xf2,0x26,0x8e,0x06,0x00,0x00,0xfa,0x26,0x8b
-,0x1e,0x08,0x00,0x26,0x23,0x1e,0x0a,0x00,0x74,0xe5,0x8c,0xc0,0x8e,0xd0,0x26,0x8b
-,0x26,0x02,0x00,0x8c,0x16,0xf2,0x33,0x22,0xff,0x75,0x6a,0x26,0xa1,0x1c,0x00,0x8a
-,0xe3,0x8a,0xdc,0x22,0xd8,0x75,0x0d,0xd0,0xe8,0x24,0xf8,0x0a,0xc0,0x75,0xf2,0xb0
-,0x80,0xe9,0xed,0xff,0xd0,0xe8,0x24,0xf8,0x0a,0xc0,0x75,0x02,0xb0,0x80,0x32,0xe4
-,0x26,0xa3,0x1c,0x00,0xf7,0xc3,0x08,0x00,0x75,0x47,0x2e,0x8a,0x9f,0xc5,0x25,0x2e
-,0x8b,0xbf,0xc5,0x26,0x80,0xc3,0x10,0x26,0x8e,0x1d,0x26,0x8c,0x1e,0x06,0x00,0x8b
-,0x16,0x00,0x00,0xc7,0x06,0x00,0x00,0xff,0xff,0x26,0x89,0x15,0x83,0xfa,0xff,0x75
-,0x0a,0x2e,0x8b,0x97,0xcd,0x26,0x26,0x21,0x16,0x08,0x00,0x33,0xc0,0x8e,0xd8,0x26
-,0x89,0x1e,0x04,0x00,0xc3,0x8a,0xdf,0xb7,0x00,0x2e,0x8a,0x9f,0xc5,0x25,0xe9,0xe0
-,0xff,0x26,0x83,0x26,0x08,0x00,0xf7,0x83,0xc3,0x10,0xe9,0xde,0xff,0x60,0x06,0x1e
-,0x68,0x87,0x25,0x6a,0x00,0x1f,0x8e,0x06,0xf2,0x33,0x8b,0x0e,0x34,0x34,0x39,0x0e
-,0xf2,0x33,0x74,0x0e,0x26,0x81,0x0e,0x0a,0x00,0x00,0x02,0x26,0x81,0x0e,0x08,0x00
-,0x00,0x02,0x26,0x89,0x26,0x02,0x00,0xa3,0xf2,0x33,0x8e,0xd0,0x8d,0x26,0x80,0x00
-,0x36,0x89,0x26,0x02,0x00,0x36,0x89,0x1e,0x20,0x00,0x36,0xc7,0x06,0x08,0x00,0x00
-,0x00,0xb9,0x04,0x00,0xbe,0x00,0x00,0x2e,0x8b,0xbc,0xc5,0x26,0x36,0xc7,0x05,0xff
-,0xff,0x36,0xc7,0x45,0x02,0xff,0xff,0x83,0xc6,0x02,0xe2,0xeb,0x8e,0x06,0x7e,0x01
-,0x36,0x8b,0x0e,0x22,0x00,0x8c,0xc0,0x26,0x83,0x3e,0x00,0x00,0xff,0x26,0x8e,0x06
-,0x00,0x00,0x74,0x07,0x26,0x3b,0x0e,0x22,0x00,0x7d,0xea,0x36,0x8c,0x06,0x00,0x00
-,0x8e,0xc0,0x26,0x8c,0x16,0x00,0x00,0xfb,0x36,0xff,0x2e,0x1e,0x00,0x06,0x1e,0x68
-,0x8b,0x25,0x6a,0x00,0x1f,0x26,0x09,0x36,0x08,0x00,0xf7,0xc6,0x00,0xff,0x74,0x01
-,0xc3,0x56,0x52,0x2e,0x8b,0xb4,0xc5,0x25,0x81,0xe6,0xff,0x00,0x2e,0x8b,0xb4,0xc5
-,0x26,0x8c,0xc2,0x8e,0xc0,0x26,0xc7,0x06,0x00,0x00,0xff,0xff,0x8e,0xc2,0x26,0x83
-,0x3c,0xff,0x74,0x0f,0x8b,0xd0,0x26,0x87,0x54,0x02,0x8e,0xc2,0x26,0xa3,0x00,0x00
-,0xe9,0x07,0x00,0x26,0x89,0x44,0x02,0x26,0x89,0x04,0x5a,0x5e,0xc3,0x06,0x1e,0x68
-,0x8b,0x25,0x6a,0x00,0x1f,0x8e,0x06,0xf2,0x33,0x26,0xa3,0x0a,0x00,0x26,0x89,0x26
-,0x02,0x00,0xa1,0x34,0x34,0x8e,0xd0,0x8d,0x26,0x80,0x00,0x8c,0x16,0xf2,0x33,0xe9
-,0x4d,0xfe,0xcf,0x50,0x1e,0x52,0x53,0x33,0xc0,0x8e,0xd8,0x26,0x83,0x3e,0x04,0x00
-,0xff,0x26,0xc7,0x06,0x04,0x00,0x00,0x00,0x74,0x03,0xe9,0x1a,0x00,0x83,0x3e,0xe6
-,0x3a,0x02,0x76,0x13,0xff,0x06,0xd6,0x33,0x8c,0xc0,0x8e,0x06,0x32,0x34,0xbe,0x40
-,0x00,0x68,0x3a,0x23,0xe9,0x5e,0xff,0xe8,0x84,0xf8,0x5b,0x5a,0x1f,0x58,0xcf,0xe8
-,0xe1,0x00,0x26,0xc6,0x06,0x18,0x00,0x10,0x26,0x8a,0x1e,0x29,0x00,0x88,0x1e,0x1b
-,0x37,0x26,0xc7,0x06,0x0c,0x00,0xff,0x7f,0x26,0xa1,0x0e,0x00,0xe7,0x9c,0x26,0xa1
-,0x08,0x00,0xe7,0x9a,0xe5,0x00,0x80,0xfb,0x08,0x74,0x09,0x0d,0x18,0xac,0xe7,0x00
-,0x07,0x1f,0x58,0xcf,0x0d,0x18,0x00,0xe9,0xf4,0xff,0x50,0x1e,0x06,0x33,0xc0,0x8e
-,0xd8,0x83,0x3e,0xa1,0x36,0x00,0x75,0xb7,0x26,0x8b,0x36,0x06,0x00,0x2e,0xff,0x94
-,0xdc,0x23,0x07,0x1f,0x58,0xcf,0xe8,0x8a,0x00,0xe5,0x00,0x0d,0x18,0x00,0xe7,0x00
-,0xe8,0x49,0x00,0xc3,0x53,0xf7,0x06,0xef,0x34,0x20,0x00,0x75,0x2d,0xe5,0x8c,0x25
-,0x00,0x70,0x8b,0xd8,0xe5,0x8c,0x25,0x00,0x70,0x3b,0xc3,0x74,0x05,0x8b,0xd8,0xe9
-,0xf2,0xff,0x3d,0x00,0x30,0x75,0x10,0xe5,0x02,0x25,0xef,0xff,0xe7,0x02,0xc7,0x06
-,0xe0,0x3a,0xff,0xff,0xe9,0x03,0x00,0xe8,0x12,0x00,0x5b,0xc3,0xa3,0x23,0x96,0x23
-,0xa4,0x23,0xa4,0x23,0x96,0x23,0xa4,0x23,0x96,0x23,0x96,0x23,0x26,0xa0,0x29,0x00
-,0xa2,0x1b,0x37,0x26,0xc7,0x06,0x0c,0x00,0xff,0x7f,0x26,0xa1,0x0e,0x00,0xe7,0x9c
-,0x26,0xa1,0x08,0x00,0xe7,0x9a,0xe5,0x00,0x25,0xff,0x53,0x26,0x8b,0x36,0x06,0x00
-,0x83,0xe6,0x0e,0x2e,0x0b,0x84,0xad,0x25,0xe7,0x00,0xc3,0x06,0x1e,0x68,0x8b,0x25
-,0x6a,0x00,0x1f,0x83,0x0e,0xef,0x34,0x20,0x83,0x0e,0x9b,0x36,0x08,0xe5,0x00,0x25
-,0xef,0xff,0x0d,0x08,0x00,0xe7,0x00,0xe5,0x00,0xa9,0x10,0x00,0x75,0x01,0xc3,0xe5
-,0x00,0xa9,0x10,0x00,0x75,0xf9,0xc3,0x50,0x53,0x51,0x56,0x06,0x1e,0x33,0xc0,0x8e
-,0xd8,0xb8,0x05,0x00,0xe7,0x84,0xe5,0x08,0x0d,0x00,0x04,0x25,0xff,0x04,0xe7,0x08
-,0xe5,0x00,0x0d,0x18,0x00,0xe7,0x00,0xe5,0x02,0x0d,0x11,0x00,0xe7,0x02,0x1f,0x07
-,0x5e,0x59,0x5b,0x58,0xc3,0x50,0x1e,0x33,0xc0,0x8e,0xd8,0xc7,0x06,0xef,0x34,0x00
-,0x00,0x83,0x26,0x9b,0x36,0xf7,0xe5,0x00,0x0d,0x18,0x00,0xe7,0x00,0xe5,0x02,0x0d
-,0x11,0x00,0xe7,0x02,0x1f,0x58,0xcf,0x60,0x06,0x1e,0x68,0x87,0x25,0x6a,0x00,0x1f
-,0xe8,0x16,0xf5,0xc3,0x06,0x1e,0x68,0x8b,0x25,0x6a,0x00,0x1f,0x8e,0xc0,0x26,0x83
-,0x3e,0x0a,0x00,0x00,0x74,0x03,0xe8,0x43,0x00,0x26,0xc7,0x06,0x0a,0x00,0xff,0xff
-,0x26,0x8b,0x16,0x06,0x00,0x8e,0x1e,0x8e,0x01,0x8c,0xd8,0x8b,0xca,0x83,0x3e,0x00
-,0x00,0xff,0x8e,0x1e,0x00,0x00,0x74,0x0a,0x2b,0x16,0x08,0x00,0x73,0xeb,0x29,0x0e
-,0x08,0x00,0x26,0x89,0x0e,0x08,0x00,0x26,0x8c,0x1e,0x00,0x00,0x8e,0xd8,0x8c,0x06
-,0x00,0x00,0xc3,0x60,0x06,0x1e,0x68,0x87,0x25,0x6a,0x00,0x1f,0x8e,0xc0,0x8b,0xc8
-,0x8e,0x1e,0x8e,0x01,0x26,0xc7,0x06,0x0a,0x00,0x00,0x00,0x8c,0xd8,0x83,0x3e,0x00
-,0x00,0xff,0x74,0x25,0x3b,0x0e,0x00,0x00,0x8e,0x1e,0x00,0x00,0x75,0xed,0x8e,0xd8
-,0x26,0xa1,0x00,0x00,0xa3,0x00,0x00,0x3d,0xff,0xff,0x74,0x56,0x8e,0xd8,0x26,0xa1
-,0x08,0x00,0x01,0x06,0x08,0x00,0xe9,0x49,0x00,0x26,0x8e,0x1e,0x02,0x00,0xbe,0x18
-,0x00,0x83,0x3c,0xff,0x74,0x3c,0x39,0x0c,0x74,0x19,0x8e,0x1c,0xbe,0x00,0x00,0x83
-,0x3e,0x00,0x00,0xff,0x74,0x2c,0x39,0x0e,0x00,0x00,0x74,0x07,0x8e,0x1e,0x00,0x00
-,0xe9,0xec,0xff,0x26,0xa1,0x00,0x00,0x89,0x04,0x33,0xc9,0x8e,0xd9,0x3d,0xff,0xff
-,0x75,0x10,0x83,0xfe,0x18,0x75,0x0b,0x26,0x8e,0x1e,0x02,0x00,0x81,0x26,0x08,0x00
-,0x7f,0xff,0x33,0xc0,0x8e,0xd8,0xc3,0x1f,0x07,0x61,0xcf,0x1f,0x07,0xcf,0x60,0x06
-,0x1e,0x68,0x87,0x25,0x6a,0x00,0x1f,0xe5,0x06,0x25,0x1e,0x00,0x3d,0x1e,0x00,0x75
-,0xf6,0xb9,0x08,0x00,0xe5,0x58,0xe7,0x5a,0x23,0xc0,0xe0,0xf8,0xc3,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0xac,0x00,0x00,0x00,0xa8,0x00,0x8c,0x02,0x04,0x00
-,0x00,0x08,0x10,0x20,0x00,0xff,0x0e,0x0c,0x0c,0x0a,0x0a,0x0a,0x0a,0x08,0x08,0x08
-,0x08,0x08,0x08,0x08,0x08,0x06,0x06,0x06,0x06,0x06,0x06,0x06,0x06,0x06,0x06,0x06
-,0x06,0x06,0x06,0x06,0x06,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04
-,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04,0x04
-,0x04,0x04,0x04,0x04,0x04,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02
-,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02
-,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02
-,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02,0x02
-,0x02,0x02,0x02,0x02,0x02,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x18,0x00,0x14,0x00,0x10,0x00,0x0c,0x00,0xff,0x7f,0xff
-,0xbf,0xff,0xdf,0xff,0xef,0xff,0xf7,0xff,0xfb,0xff,0xfd,0xff,0xfe,0x7f,0xff,0xbf
-,0xff,0xdf,0xff,0xef,0xff,0xf7,0xff,0xfb,0xff,0xfd,0xff,0xfe,0xff,0x00,0x00,0x00
-,0x80,0x3e,0xe2,0x34,0x01,0x76,0x03,0xe9,0xa5,0x00,0xb8,0x00,0x00,0xe7,0x4e,0xb9
-,0x28,0x00,0xe2,0xfe,0xc6,0x06,0x45,0x37,0x02,0xbf,0x3f,0x28,0x2e,0x8b,0x45,0x08
-,0xe7,0x4e,0xb9,0x28,0x00,0xe2,0xfe,0x2e,0x8b,0x1d,0xc7,0x06,0xb3,0x36,0x40,0x11
-,0xc7,0x06,0xb1,0x36,0x27,0x00,0xc7,0x06,0x46,0x37,0x02,0x00,0xc7,0x06,0x48,0x37
-,0x64,0x00,0xf7,0x06,0xb5,0x36,0x02,0x00,0x75,0x1c,0x2e,0x0b,0x5d,0x02,0x81,0x26
-,0xb3,0x36,0xff,0xfe,0xc7,0x06,0xb1,0x36,0x9c,0x00,0xc7,0x06,0x46,0x37,0x08,0x00
-,0xc7,0x06,0x48,0x37,0x90,0x01,0x89,0x1e,0xb7,0x36,0x89,0x1e,0xfe,0x33,0xbe,0x20
-,0x00,0x8b,0xc3,0xe7,0x4e,0xb9,0x28,0x00,0xe2,0xfe,0x2e,0x8b,0x45,0x04,0xe7,0x4e
-,0xb9,0x28,0x00,0xe2,0xfe,0xe5,0x4e,0x8b,0xcb,0x2e,0x23,0x45,0x06,0x2e,0x23,0x4d
-,0x06,0x3a,0xc1,0x74,0x36,0x4e,0x75,0xd9,0x80,0x3e,0x45,0x37,0x00,0x74,0x0b,0xc6
-,0x06,0x45,0x37,0x00,0xbf,0x2f,0x28,0xe9,0x72,0xff,0xc6,0x06,0x45,0x37,0x01,0xf7
-,0x06,0xb5,0x36,0x02,0x00,0x74,0x14,0xe5,0xce,0x25,0xfd,0xff,0xe7,0xce,0xe8,0x43
-,0x00,0xe5,0xce,0x0d,0x02,0x00,0xe7,0xce,0xe8,0x39,0x00,0x80,0x3e,0xe2,0x34,0x01
-,0x76,0x01,0xc3,0xb8,0xea,0x05,0xe7,0x8c,0xfa,0xe8,0x12,0xf4,0xfb,0x8d,0x06,0xd0
-,0x39,0x8b,0xd8,0xc1,0xe8,0x04,0xa3,0x38,0x34,0x8e,0xc0,0xa1,0x30,0x34,0x26,0xa3
-,0x02,0x00,0x26,0xc7,0x06,0x00,0x00,0xff,0xff,0x83,0xc3,0x18,0xd1,0xeb,0x26,0x89
-,0x1e,0x08,0x00,0xc3,0xe5,0x02,0x0d,0x00,0x40,0xe7,0x02,0xe5,0x00,0x0d,0x04,0x00
-,0xe7,0x00,0xb8,0x00,0x00,0xe7,0x0a,0xe5,0x0a,0xa9,0x00,0x80,0x75,0x14,0xe5,0x08
-,0x0d,0x00,0x10,0xe7,0x08,0xe5,0x0a,0x0d,0x00,0x08,0xb9,0x05,0x00,0xe7,0x0a,0xe2
-,0xfc,0xc3,0xe5,0x08,0x0d,0x00,0x10,0xb9,0x05,0x00,0xe7,0x08,0xe2,0xfc,0xc3,0x04
-,0x0c,0x20,0x00,0x01,0x0c,0x7e,0xff,0x00,0x0c,0x02,0x00,0x10,0x00,0x40,0x00,0x0c
-,0xc6,0x01,0x00,0x00,0xc0,0xf7,0xff,0x00,0xc0,0x02,0x00,0x10,0x00,0x40,0x00,0x00
-,0x33,0xc0,0x8e,0xd8,0x8d,0x3e,0x72,0x49,0x8d,0x36,0xb0,0x37,0xb9,0x14,0x00,0x8b
-,0x1e,0x30,0x34,0x89,0x5c,0x02,0x2e,0x8b,0x45,0x02,0x89,0x44,0x06,0x2e,0x8b,0x05
-,0x89,0x44,0x04,0x83,0xc7,0x04,0x83,0xc6,0x10,0xe2,0xe8,0xc6,0x06,0x9e,0x36,0x0e
-,0xe8,0xfd,0x26,0x68,0x83,0x28,0xa1,0xaa,0x02,0xcd,0x35,0x83,0x3e,0xa1,0x36,0x00
-,0x74,0x03,0xe9,0x3b,0x27,0x33,0xff,0x8e,0x06,0xa6,0x02,0x8b,0x36,0xa4,0x02,0x2e
-,0xff,0xa4,0x2e,0x30,0x83,0x0e,0x99,0x36,0x04,0xc7,0x06,0x37,0x37,0x01,0x00,0xc6
-,0x06,0xca,0x34,0x01,0xe9,0x7d,0x19,0x80,0x3e,0xa0,0x36,0x08,0x74,0xe6,0x80,0x26
-,0x9e,0x36,0xff,0x75,0x1a,0xf7,0x06,0x9b,0x36,0x00,0x20,0x74,0x12,0xf7,0x06,0x9b
-,0x36,0x03,0x00,0x75,0x0a,0x83,0x0e,0x66,0x37,0x10,0xc6,0x06,0xa0,0x36,0x08,0xe9
-,0xfb,0x01,0x80,0x3e,0x9e,0x36,0x02,0x75,0xce,0xc6,0x06,0xa0,0x36,0x06,0xe9,0xec
-,0x01,0xc3,0xe9,0xe8,0x01,0x26,0xc7,0x06,0x0a,0x00,0x00,0x00,0x26,0xff,0x26,0x04
-,0x00,0xa1,0xd1,0x36,0x26,0x39,0x06,0x1a,0x00,0x75,0x22,0xa1,0xd3,0x36,0x26,0x39
-,0x06,0x1c,0x00,0x75,0x18,0xa1,0xd5,0x36,0x26,0x39,0x06,0x1e,0x00,0x75,0x0e,0x26
-,0xf7,0x06,0x0c,0x00,0x40,0x00,0x74,0x05,0x83,0x0e,0x66,0x37,0x40,0x81,0x0e,0xaf
-,0x36,0x00,0x10,0xa1,0xaf,0x36,0xe7,0x06,0x80,0x3e,0x9d,0x36,0x02,0x75,0x06,0xcd
-,0x34,0xe9,0xa2,0x1a,0xc3,0xf7,0x06,0x9b,0x36,0x10,0x00,0x75,0x54,0x26,0xf6,0x06
-,0x0a,0x00,0xff,0x75,0x4c,0x26,0xa0,0x19,0x00,0x24,0xc0,0x3c,0x40,0x75,0x11,0x80
-,0x3e,0x95,0x36,0x00,0x74,0x3b,0x26,0xc7,0x06,0x04,0x00,0xff,0xff,0xe9,0x31,0x00
-,0xe8,0xf1,0x04,0xf7,0x06,0x9b,0x36,0x03,0x00,0x74,0x2f,0x8b,0xd8,0xb8,0x7d,0x03
-,0xcd,0x3a,0x8b,0xc3,0xc6,0x06,0xa0,0x36,0x06,0xf7,0x06,0x9b,0x36,0x02,0x00,0x75
-,0x05,0xc6,0x06,0xa0,0x36,0x04,0x81,0x0e,0x9b,0x36,0x80,0x00,0x83,0x26,0x9b,0x36
-,0xfc,0xe9,0x23,0x01,0xe8,0x87,0x1d,0xe9,0x33,0x01,0x50,0x26,0xa1,0x0c,0x00,0x25
-,0x07,0x00,0x3d,0x07,0x00,0x75,0x03,0xe9,0x84,0x00,0x3d,0x05,0x00,0x75,0x03,0xe9
-,0x7c,0x00,0x83,0x3e,0xe8,0x3a,0x04,0x74,0x75,0x83,0x3e,0xe8,0x3a,0x02,0x74,0x6e
-,0xf7,0x06,0xe6,0x34,0x18,0x80,0x75,0x03,0xe9,0x6a,0x00,0xf7,0x06,0xe6,0x34,0x00
-,0x80,0x74,0x35,0x26,0x80,0x3e,0x29,0x00,0x02,0x75,0x2d,0x51,0x56,0x57,0x8d,0x36
-,0x3e,0x34,0x8d,0x3e,0x20,0x00,0xb9,0x06,0x00,0xf3,0xa6,0x5f,0x5e,0x59,0x74,0x45
-,0x26,0xa1,0x20,0x00,0xa3,0x3e,0x34,0x26,0xa1,0x22,0x00,0xa3,0x40,0x34,0x26,0xa1
-,0x24,0x00,0xa3,0x42,0x34,0xe9,0x26,0x00,0xf7,0x06,0xe6,0x34,0x08,0x00,0x74,0x0b
-,0x26,0x80,0x3e,0x19,0x00,0x00,0x74,0x03,0xe9,0x13,0x00,0xf7,0x06,0xe6,0x34,0x10
-,0x00,0x74,0x12,0x26,0xa0,0x28,0x00,0xc0,0xe8,0x04,0x22,0xc0,0x74,0x07,0x26,0xc7
-,0x06,0x04,0x00,0xff,0xff,0x58,0x23,0xc0,0x74,0x03,0xe9,0x57,0xff,0x81,0x26,0x9b
-,0x36,0xff,0xfe,0x83,0xfe,0x06,0x7f,0x24,0x26,0xa1,0x20,0x00,0x3b,0x06,0xd1,0x36
-,0x75,0x1a,0x26,0xa1,0x22,0x00,0x3b,0x06,0xd3,0x36,0x75,0x10,0x26,0xa1,0x24,0x00
-,0x3b,0x06,0xd5,0x36,0x75,0x06,0x81,0x0e,0x9b,0x36,0x00,0x01,0x26,0xa1,0x20,0x00
-,0x25,0x7f,0xff,0xa3,0xb8,0x34,0x26,0xa1,0x22,0x00,0xa3,0xba,0x34,0x26,0xa1,0x24
-,0x00,0xa3,0xbc,0x34,0x8b,0xc6,0x86,0xc4,0xa3,0xc0,0x34,0xd1,0xe6,0x80,0xfc,0x09
-,0x74,0x03,0xe8,0xaa,0x1c,0x8b,0xc6,0x2e,0xff,0xa4,0x30,0x49,0x26,0xa1,0x0c,0x00
-,0x3d,0xff,0x7f,0x74,0x0f,0x26,0xff,0x26,0x04,0x00,0x8e,0x06,0x38,0x34,0xe8,0x36
-,0x06,0xcd,0x50,0xc3,0xe9,0x16,0x00,0xcd,0x34,0xe9,0x11,0x00,0xcd,0x34,0x89,0x36
-,0x3d,0x37,0xa1,0x9d,0x36,0xa3,0x3f,0x37,0xc6,0x06,0xa0,0x36,0x0c,0xe8,0x8e,0x00
-,0xa1,0x9f,0x36,0x22,0xe4,0x75,0x32,0xf7,0x06,0x4c,0x37,0x01,0x00,0x75,0x2a,0xf6
-,0x06,0x9d,0x36,0x80,0x74,0x07,0x88,0x26,0x9e,0x36,0xe9,0x31,0x00,0x3a,0x06,0x9d
-,0x36,0xa3,0x9d,0x36,0x74,0x28,0x8b,0xf0,0x2e,0xff,0xa4,0x0d,0x2b,0x44,0x29,0xee
-,0x42,0x19,0x44,0xcd,0x44,0x2f,0x45,0x5a,0x45,0x3a,0x26,0x9e,0x36,0x75,0x01,0xc3
-,0x32,0xc0,0x86,0xc4,0x8b,0xf0,0xa2,0x9e,0x36,0x2e,0xff,0xa4,0x20,0x49,0x8b,0x2e
-,0x99,0x36,0x23,0xed,0x75,0x01,0xc3,0xbf,0x01,0x00,0xbe,0x00,0x00,0x85,0xfd,0x75
-,0x1a,0x46,0xd1,0xe7,0xe9,0xf6,0xff,0x2a,0x00,0x29,0x00,0x28,0x00,0x27,0x00,0x25
-,0x00,0x05,0x00,0x07,0x00,0x26,0x00,0x06,0x00,0x20,0x00,0xf7,0xd7,0x21,0x3e,0x99
-,0x36,0xd1,0xe6,0x2e,0x8b,0xb4,0x47,0x2b,0xe9,0x4f,0xff,0xe9,0x56,0xff,0x80,0x26
-,0x9e,0x36,0xff,0x75,0x17,0xf7,0x06,0x4c,0x37,0x01,0x00,0x75,0x0f,0xf6,0x06,0x9d
-,0x36,0x80,0x74,0x08,0xf7,0x06,0x66,0x37,0xff,0xff,0x75,0x07,0xc7,0x06,0x66,0x37
-,0x00,0x00,0xc3,0xf7,0x06,0x41,0x37,0x01,0x00,0x75,0x0b,0xb8,0x7f,0x03,0xcd,0x39
-,0xc7,0x06,0x41,0x37,0x01,0x00,0x33,0xf6,0xb8,0x00,0x40,0x85,0x06,0x66,0x37,0x74
-,0x21,0x80,0xbc,0x54,0x37,0xff,0x74,0x04,0xfe,0x84,0x54,0x37,0x80,0xbc,0x96,0x34
-,0xff,0x74,0x04,0xfe,0x84,0x96,0x34,0x31,0x06,0x66,0x37,0x83,0x3e,0x66,0x37,0x00
-,0x74,0x05,0x46,0xd1,0xe8,0x73,0xd4,0xc3,0xa1,0xf4,0x33,0xa9,0x00,0x88,0x74,0x0b
-,0xa9,0x00,0x10,0x75,0x09,0x8b,0x1e,0x43,0x37,0xff,0xe3,0xe9,0xd7,0x00,0xc7,0x06
-,0x35,0x37,0x05,0x00,0xc7,0x06,0x43,0x37,0x1e,0x2c,0xf7,0x06,0xf4,0x33,0x00,0x08
-,0x74,0x06,0xc7,0x06,0x43,0x37,0x10,0x2c,0xb8,0x80,0x03,0xcd,0x39,0xe9,0xcd,0xfe
-,0xa9,0x00,0x08,0x74,0xd9,0xff,0x0e,0x35,0x37,0x75,0xed,0xe9,0x66,0x00,0xa9,0x00
-,0x08,0x75,0xcb,0xff,0x0e,0x35,0x37,0x75,0xdf,0x81,0x0e,0xc2,0x34,0xc0,0x00,0xf6
-,0x06,0x9d,0x36,0x80,0x74,0x48,0x81,0x0e,0x9b,0x36,0x00,0x80,0xf7,0x06,0x9b,0x36
-,0x01,0x00,0x74,0x1e,0xb8,0x7d,0x03,0xcd,0x3a,0x81,0x0e,0x9b,0x36,0x80,0x00,0x83
-,0x26,0x9b,0x36,0xfe,0xc7,0x06,0x0f,0x37,0x02,0x00,0xc6,0x06,0xa0,0x36,0x04,0xe9
-,0x7b,0xfe,0x80,0x3e,0xa0,0x36,0x04,0x75,0x07,0x83,0x3e,0x0f,0x37,0x01,0x75,0x05
-,0xc6,0x06,0xa0,0x36,0x06,0xc7,0x06,0x0f,0x37,0x02,0x00,0xe9,0x5f,0xfe,0xbe,0x02
-,0x00,0xe9,0x4a,0xfe,0x80,0x26,0x9e,0x36,0xff,0x75,0x3a,0xf6,0x06,0x9d,0x36,0x80
-,0x74,0x2d,0xf7,0x06,0x9b,0x36,0x00,0x20,0x75,0x2b,0xc6,0x06,0xa0,0x36,0x06,0xff
-,0x06,0x94,0x34,0x83,0x0e,0x66,0x37,0x20,0x8e,0x06,0x30,0x34,0x26,0xf7,0x06,0x0a
-,0x00,0x00,0x01,0x74,0x07,0x26,0x81,0x0e,0x08,0x00,0x00,0x01,0xe9,0x06,0x00,0xbe
-,0x04,0x00,0xe9,0x09,0xfe,0x81,0x0e,0xaf,0x36,0x00,0x08,0xa1,0xaf,0x36,0xe7,0x06
-,0xe5,0x0a,0xa9,0x00,0x80,0x74,0x0e,0x81,0x26,0xaf,0x36,0xff,0xf7,0xa1,0xaf,0x36
-,0xe7,0x06,0xe9,0x09,0xff,0xe9,0xf5,0xfd,0xc7,0x06,0x41,0x37,0x00,0x00,0x83,0x0e
-,0x99,0x36,0x02,0xe9,0xe7,0xfd,0x80,0x26,0x9e,0x36,0xff,0x75,0x1d,0xf7,0x06,0x9b
-,0x36,0x00,0x40,0x75,0x05,0x83,0x0e,0x99,0x36,0x08,0x83,0x0e,0x99,0x36,0x20,0x81
-,0x26,0x9b,0x36,0xff,0xbf,0xb8,0x85,0x03,0xcd,0x39,0xe9,0xc0,0xfd,0x80,0x3e,0x9e
-,0x36,0x06,0x74,0x07,0x80,0x3e,0x9e,0x36,0x0a,0x75,0x34,0xf6,0x06,0x9d,0x36,0x80
-,0x75,0x06,0xbe,0x07,0x00,0xe9,0x96,0xfd,0xc6,0x06,0xa0,0x36,0x04,0x83,0x3e,0x0f
-,0x37,0x02,0x74,0x1b,0xc7,0x06,0x0f,0x37,0x04,0x00,0x80,0x3e,0x9e,0x36,0x06,0x75
-,0x0e,0xf7,0x06,0x9b,0x36,0x40,0x00,0x75,0x06,0xc7,0x06,0x0f,0x37,0x03,0x00,0xe9
-,0x7b,0xfd,0x80,0x3e,0x9d,0x36,0x04,0x75,0x12,0x81,0x0e,0xc2,0x34,0x00,0x40,0xff
-,0x06,0x92,0x34,0xc6,0x06,0xa0,0x36,0x06,0xe9,0x62,0xfd,0xbe,0x05,0x00,0xe9,0x4d
-,0xfd,0xf6,0x06,0x9d,0x36,0x80,0x75,0x19,0x83,0x0e,0xc2,0x34,0x04,0xbe,0x06,0x00
-,0xe9,0x3b,0xfd,0x80,0x26,0x9e,0x36,0xff,0x75,0xc5,0xff,0x06,0x31,0x37,0xe9,0x00
-,0x00,0x83,0x26,0xc2,0x34,0xbf,0xc6,0x06,0xa0,0x36,0x06,0xe9,0x2f,0xfd,0xe5,0x0a
-,0x50,0x25,0xc3,0xbf,0xe7,0x0a,0x58,0x80,0x26,0x9e,0x36,0xff,0x75,0x0d,0xa9,0x00
-,0x40,0x75,0x08,0xc6,0x06,0xa0,0x36,0x06,0xe9,0x12,0xfd,0xb8,0x83,0x03,0xcd,0x39
-,0xc3,0xb8,0x7c,0x03,0xcd,0x39,0xf7,0x06,0xf4,0x33,0x00,0x10,0x75,0x09,0xc7,0x06
-,0x33,0x37,0x02,0x00,0xe9,0xf6,0xfc,0xff,0x0e,0x33,0x37,0x74,0x03,0xe9,0xed,0xfc
-,0xff,0x06,0x8e,0x34,0xe8,0xf7,0x19,0x83,0x0e,0xc2,0x34,0x08,0xbe,0x03,0x00,0xe9
-,0xcc,0xfc,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x04,0x00,0x04,0x04,0x05
-,0x04,0x04,0x04,0x00,0x03,0x00,0x03,0x03,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x04,0x00,0x08,0x08,0x05,0x08,0x08,0x08,0x00,0x03,0x00,0x03,0x03,0x00,0x00
-,0x02,0x04,0x04,0x04,0x04,0x00,0x00,0x08,0x00,0x00,0x0a,0x14,0x00,0x00,0x1a,0x00
-,0x1c,0x00,0x1e,0x20,0x00,0x00,0x04,0x41,0x06,0x0b,0x08,0xc2,0xff,0xe7,0x04,0x03
-,0x06,0x04,0x04,0x05,0x04,0x06,0x04,0x87,0x04,0x03,0x06,0x04,0x04,0x85,0x4e,0xa2
-,0x04,0xcf,0x04,0xcd,0xc7,0x06,0xa2,0x37,0x00,0x00,0xc7,0x06,0xa6,0x37,0x00,0x00
-,0x26,0xa1,0x20,0x00,0x25,0x7f,0xff,0xa3,0xf5,0x36,0x26,0xa1,0x22,0x00,0xa3,0xf7
-,0x36,0x26,0xa1,0x24,0x00,0xa3,0xf9,0x36,0xe8,0x3b,0x19,0x8b,0xf0,0x26,0x8b,0x0e
-,0x0e,0x00,0x2b,0xc8,0x83,0xe9,0x0e,0xb8,0x01,0x80,0x83,0xf9,0x04,0x7c,0x51,0x26
-,0x8a,0x54,0x28,0x88,0x16,0x1c,0x37,0x40,0x26,0x8b,0x6c,0x26,0x86,0xcd,0x3b,0xcd
-,0x86,0xcd,0x89,0x0e,0xa4,0x37,0x75,0x38,0x40,0x32,0xff,0x26,0x8a,0x5c,0x29,0x80
-,0xfb,0x15,0x77,0x25,0x80,0xfb,0x0a,0x74,0x20,0x80,0xfb,0x01,0x74,0x1b,0xb8,0x04
-,0x80,0x2e,0x3a,0x97,0x02,0x2e,0x74,0x07,0x2e,0x3a,0x97,0x18,0x2e,0x75,0x11,0x33
-,0xc0,0x80,0xfb,0x09,0x75,0x4f,0x8b,0xf3,0xc3,0x26,0xc7,0x06,0x04,0x00,0xff,0xff
-,0x50,0x52,0xa1,0xa4,0x37,0x86,0xc4,0x26,0x3b,0x06,0x26,0x00,0x7c,0x32,0x26,0x81
-,0x3e,0x26,0x00,0x00,0x04,0x7e,0x29,0x8d,0x74,0x2a,0x26,0x8b,0x14,0x22,0xd2,0x74
-,0x1f,0x80,0xe6,0xbf,0x80,0xfe,0x09,0x75,0x17,0xc7,0x06,0xa2,0x37,0x01,0x00,0x80
-,0xfa,0x04,0x75,0x0c,0x26,0x8b,0x44,0x02,0xa3,0x03,0x37,0x86,0xc4,0xa3,0xd0,0x34
-,0x5a,0x58,0xe9,0xb1,0xff,0xbd,0x72,0x37,0x2e,0x8a,0x87,0x2e,0x2e,0x22,0xc0,0x74
-,0x16,0x05,0x44,0x2e,0x8b,0xf8,0x2e,0x8b,0x05,0x3e,0x89,0x46,0x00,0x83,0xc5,0x02
-,0x83,0xc7,0x02,0x22,0xe4,0x7d,0xef,0x8d,0x74,0x2a,0x83,0xe9,0x04,0x75,0x03,0xe9
-,0xa1,0x00,0x26,0x8b,0x14,0x22,0xd2,0x75,0x03,0xe9,0x7c,0x00,0xc7,0x06,0xa6,0x37
-,0x01,0x00,0xbf,0x72,0x37,0x8b,0x05,0x83,0xc7,0x02,0x80,0xe6,0xbf,0x80,0xe4,0x3f
-,0x80,0xfe,0x09,0x75,0x22,0x80,0xfa,0x04,0x75,0x5e,0xc7,0x06,0xa2,0x37,0x01,0x00
-,0x26,0x8b,0x44,0x02,0xa3,0x03,0x37,0x86,0xc4,0xa3,0xd0,0x34,0x86,0xc4,0xc7,0x06
-,0xa6,0x37,0x00,0x00,0xe9,0x47,0x00,0x3b,0xfd,0x7e,0x15,0x26,0x8b,0x04,0xa8,0x40
-,0x74,0x06,0xb8,0x07,0x80,0xe9,0x38,0xff,0x32,0xc0,0x26,0x8b,0x04,0xe9,0x2e,0x00
-,0x3a,0xf4,0x75,0xb1,0xc7,0x45,0xfe,0x00,0x00,0x80,0xfe,0x22,0x75,0x0d,0x3a,0xd0
-,0x77,0x16,0xc7,0x06,0xa6,0x37,0x00,0x00,0xe9,0x13,0x00,0x3a,0xd0,0x75,0x09,0xc7
-,0x06,0xa6,0x37,0x00,0x00,0xe9,0x06,0x00,0xb8,0x05,0x80,0xe9,0x02,0xff,0x32,0xf6
-,0x03,0xf2,0x2b,0xca,0xb8,0x05,0x80,0x23,0xc9,0x76,0x03,0xe9,0x64,0xff,0x74,0x03
-,0xe9,0xed,0xfe,0x33,0xc0,0xbf,0x72,0x37,0x8b,0x15,0x47,0x47,0x3b,0xfd,0x7f,0x1b
-,0xf6,0xc6,0x80,0x74,0x16,0xf7,0x06,0xa6,0x37,0x01,0x00,0x74,0x06,0xb8,0x08,0x80
-,0xe9,0xc3,0xfe,0xf6,0xc6,0x40,0x74,0xe0,0xb8,0x07,0x80,0xe9,0xb8,0xfe,0x7d,0x42
-,0xa3,0x45,0x44,0x29,0x44,0x29,0xb7,0x28,0xe2,0x28,0xee,0x2b,0xf2,0x28,0xf5,0x28
-,0x01,0x29,0xac,0x2a,0x44,0x29,0x44,0x29,0x44,0x29,0x44,0x29,0x44,0x29,0x00,0x00
-,0x73,0x36,0x00,0x00,0x03,0x36,0xc5,0x35,0x83,0x35,0x45,0x35,0x07,0x35,0xd2,0x34
-,0x45,0x34,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0xa6,0x38,0x00,0x00,0xe0,0x38,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0xf2,0x33,0x00,0x00,0xa6,0x33,0x60,0x33,0xfd,0x32,0xbc,0x32,0x77,0x32,0x3c,0x32
-,0xfb,0x31,0x6a,0x31,0x0a,0x31,0xe0,0xe0,0x10,0x10,0x10,0xe0,0xe0,0xe0,0xe0,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0xe0,0x00,0xe0,0xe0,0xe0,0xe0,0xe0,0xe0,0xe0,0xe0
-,0xe0,0x33,0xff,0x26,0xf6,0x06,0x1a,0x00,0x80,0x74,0x1b,0x26,0x80,0x26,0x1a,0x00
-,0x7f,0x26,0x8b,0x3e,0x26,0x00,0x83,0xe7,0x1f,0x74,0x0b,0x26,0x80,0x0e,0x20,0x00
-,0x80,0x26,0x01,0x3e,0x0e,0x00,0xc3,0x60,0x2e,0x8b,0x84,0xa6,0x30,0x26,0xa3,0x18
-,0x00,0xd1,0xe6,0x2e,0xff,0x94,0x50,0x30,0x61,0xc3,0x26,0xc7,0x06,0x04,0x00,0xc4
-,0x2a,0x26,0xc7,0x06,0x0e,0x00,0x16,0x00,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0x26
-,0xc6,0x06,0x19,0x00,0x00,0xe8,0xbf,0x05,0xe8,0x98,0x05,0x26,0xc7,0x06,0x26,0x00
-,0x00,0x08,0x26,0xc6,0x06,0x28,0x00,0x40,0x26,0xc6,0x06,0x29,0x00,0x2a,0xbf,0x2a
-,0x00,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01,0x2a,0xa1,0x93,0x37,0x33,0xdb,0xa9
-,0x40,0x00,0x75,0x02,0xb3,0x01,0xa9,0x00,0x10,0x74,0x02,0xb7,0x88,0xa9,0x00,0x08
-,0x74,0x03,0x80,0xcf,0x44,0x26,0x89,0x5d,0x02,0xc3,0x83,0x0e,0xc2,0x34,0x20,0x26
-,0xc7,0x06,0x04,0x00,0x6b,0x2b,0x26,0xc7,0x06,0x0e,0x00,0x30,0x00,0x26,0xc7,0x06
-,0x06,0x00,0x0a,0x00,0x26,0xc7,0x06,0x0a,0x00,0x04,0x00,0x26,0xc6,0x06,0x19,0x00
-,0x00,0xe8,0x69,0x05,0xe8,0x2c,0x05,0x26,0xc7,0x06,0x26,0x00,0x00,0x22,0x26,0xc6
-,0x06,0x28,0x00,0x60,0x26,0xc6,0x06,0x29,0x00,0x29,0xbf,0x2a,0x00,0x26,0xc6,0x05
-,0x08,0x26,0xc6,0x45,0x01,0x2d,0x8d,0x7d,0x02,0xbe,0x54,0x37,0xb9,0x03,0x00,0xf3
-,0xa5,0x26,0xc6,0x05,0x08,0x26,0xc6,0x45,0x01,0x2e,0x8d,0x7d,0x02,0xbe,0x5a,0x37
-,0xb9,0x03,0x00,0xf3,0xa5,0xe8,0xd4,0x05,0xe8,0x64,0x05,0xb9,0x06,0x00,0xbe,0x54
-,0x37,0x8d,0x2e,0x2c,0x00,0x26,0x8b,0x46,0x00,0x29,0x04,0x83,0xc6,0x02,0x83,0xc5
-,0x02,0x83,0xf9,0x04,0x75,0x02,0x45,0x45,0xe2,0xeb,0xc3,0x26,0xc7,0x06,0x04,0x00
-,0xc4,0x2a,0x26,0xc7,0x06,0x0e,0x00,0x24,0x00,0x26,0xc7,0x06,0x06,0x00,0x06,0x00
-,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0xe4,0x04,0xe8,0xa7,0x04,0x26,0xc7,0x06,0x26
-,0x00,0x00,0x16,0x26,0xc6,0x06,0x28,0x00,0x60,0x26,0xc6,0x06,0x29,0x00,0x28,0xbf
-,0x2a,0x00,0xe8,0x5b,0x06,0xe8,0x74,0x05,0xe8,0x04,0x05,0xc3,0x26,0xc7,0x06,0x04
-,0x00,0xc4,0x2a,0x26,0xc7,0x06,0x0e,0x00,0x1a,0x00,0x26,0xc7,0x06,0x06,0x00,0x06
-,0x00,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0xa3,0x04,0xe8,0x66,0x04,0x26,0xc7,0x06
-,0x26,0x00,0x00,0x0c,0x26,0xc6,0x06,0x28,0x00,0x60,0x26,0xc6,0x06,0x29,0x00,0x27
-,0xbf,0x2a,0x00,0xe8,0x21,0x05,0xc3,0x26,0xc7,0x06,0x04,0x00,0xc4,0x2a,0x26,0xc7
-,0x06,0x0e,0x00,0x20,0x00,0x26,0xc7,0x06,0x06,0x00,0x0a,0x00,0x26,0xc7,0x06,0x0a
-,0x00,0x04,0x00,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0x4b,0x04,0xe8,0x24,0x04,0x26
-,0xc7,0x06,0x26,0x00,0x00,0x12,0x26,0xc6,0x06,0x28,0x00,0x40,0x26,0xc6,0x06,0x29
-,0x00,0x26,0xbf,0x2a,0x00,0xe8,0xf4,0x04,0xe8,0x84,0x04,0xc3,0x26,0xc7,0x06,0x04
-,0x00,0xc4,0x2a,0x26,0xc7,0x06,0x0e,0x00,0x34,0x00,0x26,0xc7,0x06,0x06,0x00,0x06
-,0x00,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0x0d,0x04,0xe8,0xe6,0x03,0x26,0xc7,0x06
-,0x26,0x00,0x00,0x26,0x26,0xc6,0x06,0x28,0x00,0x40,0x26,0xc6,0x06,0x29,0x00,0x25
-,0xbf,0x2a,0x00,0xe8,0xb6,0x04,0xe8,0x46,0x04,0xe8,0xfa,0x04,0xc3,0x26,0xc7,0x06
-,0x04,0x00,0xc4,0x2a,0x26,0xc7,0x06,0x0e,0x00,0x38,0x00,0xa1,0xa2,0x37,0x50,0x0b
-,0xc0,0x75,0x07,0x26,0xc7,0x06,0x0e,0x00,0x34,0x00,0x26,0xc7,0x06,0x06,0x00,0x06
-,0x00,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0x99,0x03,0xe8,0xa4,0xfd,0x26,0xc7,0x45
-,0x26,0x00,0x2a,0x58,0x0b,0xc0,0x75,0x06,0x26,0xc7,0x45,0x26,0x00,0x26,0xa1,0x1c
-,0x37,0xc1,0xe0,0x04,0x26,0x88,0x45,0x28,0x26,0xc6,0x45,0x29,0x24,0x83,0xc7,0x2a
-,0xe8,0x29,0x04,0xe8,0xa0,0x04,0xe8,0x22,0x05,0xe8,0xf8,0x03,0xe8,0x09,0x04,0xc3
-,0x26,0xc7,0x06,0x04,0x00,0xc4,0x2a,0x26,0xc7,0x06,0x0e,0x00,0x32,0x00,0x26,0xc7
-,0x06,0x06,0x00,0x06,0x00,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0x45,0x03,0xe8,0x50
-,0xfd,0x26,0xc7,0x45,0x26,0x00,0x24,0xa1,0x1c,0x37,0xc1,0xe0,0x04,0x26,0x88,0x45
-,0x28,0x26,0xc6,0x45,0x29,0x23,0x83,0xc7,0x2a,0xe8,0xe0,0x03,0xe8,0x6c,0x04,0xe8
-,0x8a,0x04,0xe8,0x9c,0x04,0xc3,0x26,0xc7,0x06,0x04,0x00,0xc4,0x2a,0x26,0xc7,0x06
-,0x0e,0x00,0x34,0x00,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0x26,0xc6,0x06,0x19,0x00
-,0x00,0xe8,0xff,0x02,0xe8,0x0a,0xfd,0x26,0xc7,0x45,0x26,0x00,0x26,0xa1,0x1c,0x37
-,0xc1,0xe0,0x04,0x26,0x88,0x45,0x28,0x26,0xc6,0x45,0x29,0x22,0x83,0xc7,0x2a,0xe8
-,0x9a,0x03,0xe8,0xc7,0x03,0xe8,0x57,0x03,0xe8,0xf8,0x03,0xe8,0x78,0x04,0xe8,0x8a
-,0x04,0xc3,0x26,0xc7,0x06,0x04,0x00,0x74,0x45,0x26,0xc7,0x06,0x0e,0x00,0x3e,0x00
-,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0x26,0xc7,0x06,0x0a,0x00,0x04,0x00,0x26,0xc6
-,0x06,0x19,0x00,0x00,0xe8,0xfc,0x02,0xe8,0xa9,0x02,0x83,0x3e,0x8d,0x37,0x03,0x75
-,0x01,0x90,0x26,0xc7,0x06,0x26,0x00,0x00,0x30,0x26,0xc6,0x06,0x28,0x00,0x50,0x26
-,0xc6,0x06,0x29,0x00,0x20,0xbf,0x2a,0x00,0xe8,0xd0,0x03,0xe8,0x01,0x03,0xe8,0xb5
-,0x03,0xe8,0x9f,0x03,0xc3,0x26,0xc7,0x06,0x04,0x00,0x61,0x43,0xb9,0xf0,0x00,0x83
-,0xe9,0x02,0x26,0x89,0x0e,0x0e,0x00,0x26,0xc7,0x06,0x06,0x00,0x02,0x00,0x26,0xc6
-,0x06,0x19,0x00,0x00,0x26,0xc7,0x06,0x1a,0x00,0x00,0x00,0x26,0xc7,0x06,0x1c,0x00
-,0x00,0x00,0x26,0xc7,0x06,0x1e,0x00,0x00,0x00,0xe8,0x47,0x02,0x83,0xe9,0x0e,0x86
-,0xcd,0x26,0x89,0x0e,0x26,0x00,0x86,0xcd,0x26,0xc6,0x06,0x28,0x00,0x00,0x26,0xc6
-,0x06,0x29,0x00,0x08,0xbf,0x2a,0x00,0x83,0xe9,0x04,0x26,0x89,0x0d,0x26,0xc6,0x45
-,0x01,0x26,0x8d,0x7d,0x02,0x83,0xe9,0x02,0xbb,0x01,0x00,0xb8,0x30,0x30,0x4b,0x75
-,0x17,0xbb,0x0a,0x00,0x8a,0xc4,0x26,0x88,0x05,0xb0,0x31,0x80,0xc4,0x01,0x80,0xfc
-,0x3a,0x75,0x0a,0xb4,0x61,0xe9,0x05,0x00,0x26,0x88,0x05,0x04,0x01,0x47,0x49,0x75
-,0xdd,0xc3,0x26,0xc7,0x06,0x04,0x00,0x04,0x45,0x26,0xc7,0x06,0x0e,0x00,0x12,0x00
-,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0x26,0xc6,0x06,0x19,0x00,0x01,0xe8,0xe5,0x01
-,0xe8,0xd0,0x01,0x26,0xc7,0x06,0x26,0x00,0x00,0x04,0x26,0xc6,0x06,0x28,0x00,0x00
-,0x26,0xc6,0x06,0x29,0x00,0x07,0xc3,0x26,0xc7,0x06,0x04,0x00,0xc4,0x2a,0x26,0xc7
-,0x06,0x0e,0x00,0x20,0x00,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0x26,0xc6,0x06,0x19
-,0x00,0x06,0xe8,0x04,0x02,0xe8,0x9b,0x01,0x26,0xc7,0x06,0x26,0x00,0x00,0x12,0x26
-,0xc6,0x06,0x28,0x00,0x00,0x26,0xc6,0x06,0x29,0x00,0x06,0xbf,0x2a,0x00,0xe8,0x6b
-,0x02,0xe8,0xfb,0x01,0xc3,0x26,0xc7,0x06,0x04,0x00,0xc4,0x2a,0x26,0xc7,0x06,0x0e
-,0x00,0x20,0x00,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0x26,0xc6,0x06,0x19,0x00,0x05
-,0xe8,0xc6,0x01,0xe8,0x5d,0x01,0x26,0xc7,0x06,0x26,0x00,0x00,0x12,0x26,0xc6,0x06
-,0x28,0x00,0x00,0x26,0xc6,0x06,0x29,0x00,0x05,0xbf,0x2a,0x00,0xe8,0x2d,0x02,0xe8
-,0xbd,0x01,0xc3,0xff,0x06,0x82,0x34,0x26,0xc7,0x06,0x04,0x00,0x3d,0x41,0x26,0xc7
-,0x06,0x0e,0x00,0x20,0x00,0x26,0xc7,0x06,0x06,0x00,0x0e,0x00,0x26,0xc6,0x06,0x19
-,0x00,0x04,0xe8,0x84,0x01,0xe8,0x1b,0x01,0x26,0xc7,0x06,0x26,0x00,0x00,0x12,0x26
-,0xc6,0x06,0x28,0x00,0x00,0x26,0xc6,0x06,0x29,0x00,0x04,0xbf,0x2a,0x00,0xe8,0xeb
-,0x01,0xe8,0x7b,0x01,0xc3,0x26,0xc7,0x06,0x04,0x00,0x67,0x42,0x26,0xc7,0x06,0x0e
-,0x00,0x20,0x00,0x26,0xc7,0x06,0x06,0x00,0x08,0x00,0x26,0xc6,0x06,0x19,0x00,0x03
-,0xe8,0x46,0x01,0xe8,0xdd,0x00,0x26,0xc7,0x06,0x26,0x00,0x00,0x12,0x26,0xc6,0x06
-,0x28,0x00,0x00,0x26,0xc6,0x06,0x29,0x00,0x03,0xbf,0x2a,0x00,0xe8,0xad,0x01,0xe8
-,0x3d,0x01,0xc3,0xff,0x06,0x84,0x34,0x26,0xc7,0x06,0x04,0x00,0x67,0x42,0x26,0xc7
-,0x06,0x0e,0x00,0x24,0x00,0x26,0xc7,0x06,0x06,0x00,0x08,0x00,0x26,0xc6,0x06,0x19
-,0x00,0x02,0xe8,0x04,0x01,0xe8,0x9b,0x00,0x26,0xc7,0x06,0x26,0x00,0x00,0x16,0x26
-,0xc6,0x06,0x28,0x00,0x00,0x26,0xc6,0x06,0x29,0x00,0x02,0xbf,0x2a,0x00,0x26,0xc6
-,0x05,0x04,0x26,0xc6,0x45,0x01,0x01,0xa1,0x0f,0x37,0x86,0xe0,0xf6,0x06,0x6f,0x37
-,0x01,0x75,0x0f,0x39,0x06,0xcc,0x34,0x74,0x09,0x8b,0xd8,0xb8,0x89,0x03,0xcd,0x39
-,0x8b,0xc3,0xa3,0xcc,0x34,0x26,0x89,0x45,0x02,0x8d,0x7d,0x04,0xe8,0x3d,0x01,0xe8
-,0xcd,0x00,0xc3,0x26,0xc7,0x06,0x04,0x00,0xc4,0x2a,0x26,0xc7,0x06,0x0e,0x00,0x1c
-,0x00,0xa1,0xa2,0x37,0x50,0x0b,0xc0,0x75,0x07,0x26,0xc7,0x06,0x0e,0x00,0x18,0x00
-,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0x23,0x00
-,0xe8,0x2e,0xfa,0x26,0xc7,0x45,0x26,0x00,0x0e,0x58,0x0b,0xc0,0x75,0x06,0x26,0xc7
-,0x45,0x26,0x00,0x0a,0x26,0xc6,0x45,0x29,0x00,0x83,0xc7,0x2a,0xe8,0xbd,0x00,0xe8
-,0xff,0x00,0xc3,0x56,0x57,0x51,0xb9,0x03,0x00,0xbe,0xd1,0x36,0xbf,0x20,0x00,0xf3
-,0xa5,0x59,0x5f,0x5e,0xc3,0x56,0x57,0x51,0xb9,0x03,0x00,0xbe,0xd1,0x36,0xbf,0x1a
-,0x00,0xf3,0xa5,0x59,0x5f,0x5e,0xc3,0x26,0xc7,0x06,0x1a,0x00,0xc0,0x00,0x26,0xc7
-,0x06,0x1c,0x00,0x00,0x00,0x26,0xc7,0x06,0x1e,0x00,0x00,0x10,0xc3,0x26,0xc7,0x06
-,0x1a,0x00,0xc0,0x00,0x26,0xc7,0x06,0x1c,0x00,0x00,0x00,0x26,0xc7,0x06,0x1e,0x00
-,0x00,0x08,0xc3,0x26,0xc7,0x06,0x1a,0x00,0xc0,0x00,0x26,0xc7,0x06,0x1c,0x00,0x00
-,0x00,0x26,0xc7,0x06,0x1e,0x00,0x00,0x02,0xc3,0x26,0xc7,0x06,0x1a,0x00,0xc0,0x00
-,0x26,0xc7,0x06,0x1c,0x00,0xff,0xff,0x26,0xc7,0x06,0x1e,0x00,0xff,0xff,0xc3,0x26
-,0xc6,0x05,0x08,0x26,0xc6,0x45,0x01,0x02,0x8d,0x7d,0x02,0xbe,0x05,0x37,0xb9,0x03
-,0x00,0xf3,0xa5,0xc3,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01,0x06,0xa1,0x0d,0x37
-,0x26,0x89,0x45,0x02,0x8d,0x7d,0x04,0xc3,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01
-,0x07,0xa1,0x0b,0x37,0x26,0x89,0x45,0x02,0x83,0xc7,0x04,0xc3,0xa1,0xa2,0x37,0x0b
-,0xc0,0x74,0x13,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01,0x09,0xa1,0x03,0x37,0x26
-,0x89,0x45,0x02,0x83,0xc7,0x04,0xc3,0x26,0xc6,0x05,0x08,0x26,0xc6,0x45,0x01,0x02
-,0x8d,0x7d,0x02,0xbe,0x05,0x37,0xb9,0x03,0x00,0xf3,0xa5,0xc3,0x26,0xc6,0x05,0x06
-,0x26,0xc6,0x45,0x01,0x0b,0x8d,0x7d,0x02,0xbe,0xef,0x36,0xb9,0x02,0x00,0xf3,0xa5
-,0xc3,0x26,0xc6,0x05,0x06,0x26,0xc6,0x45,0x01,0x20,0xa1,0x68,0x37,0x26,0x89,0x45
-,0x02,0xa1,0x6a,0x37,0x26,0x88,0x65,0x05,0xc1,0xe0,0x04,0x26,0x88,0x45,0x04,0x83
-,0xc7,0x06,0xc3,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01,0x21,0x26,0xc7,0x45,0x02
-,0x00,0x00,0x83,0xc7,0x04,0xc3,0x26,0xc6,0x05,0x14,0x26,0xc6,0x45,0x01,0x22,0x8d
-,0x7d,0x02,0xbe,0x1f,0x37,0xb9,0x09,0x00,0xf3,0xa5,0xc3,0x26,0xc6,0x05,0x0c,0x26
-,0xc6,0x45,0x01,0x23,0x8d,0x7d,0x02,0x1e,0x0e,0x1f,0x8d,0x36,0x40,0x54,0xb9,0x03
-,0x00,0xf3,0xa5,0x33,0xc0,0xb9,0x02,0x00,0xf3,0xab,0x1f,0xc3,0x26,0xc6,0x05,0x08
-,0x26,0xc6,0x45,0x01,0x28,0x8d,0x7d,0x02,0xbe,0xd1,0x36,0xb9,0x03,0x00,0xf3,0xa5
-,0xc3,0x26,0xc6,0x05,0x08,0x26,0xc6,0x45,0x01,0x29,0xa1,0xc2,0x34,0x86,0xe0,0x26
-,0x89,0x45,0x02,0xa1,0x9b,0x36,0x26,0x89,0x45,0x04,0x26,0x88,0x45,0x06,0x26,0x88
-,0x45,0x07,0x8d,0x7d,0x08,0xc3,0x26,0xc6,0x05,0x06,0x26,0xc6,0x45,0x01,0x2b,0x8d
-,0x7d,0x02,0xbe,0xbb,0x36,0xb9,0x02,0x00,0xf3,0xa5,0xc3,0x26,0xc6,0x05,0x06,0x26
-,0xc6,0x45,0x01,0x2c,0x8d,0x7d,0x02,0xbe,0xe5,0x36,0xb9,0x02,0x00,0xf3,0xa5,0xc3
-,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01,0x30,0xa1,0x37,0x37,0x86,0xe0,0x26,0x89
-,0x45,0x02,0x8d,0x7d,0x04,0xc3,0x26,0xc7,0x06,0x0e,0x00,0x1e,0x00,0x26,0xc7,0x06
-,0x06,0x00,0x02,0x00,0x26,0xc6,0x06,0x19,0x00,0x00,0xe8,0x6c,0xfe,0xe8,0x03,0xfe
-,0x26,0xc7,0x06,0x26,0x00,0x00,0x10,0x26,0xc6,0x06,0x28,0x00,0x30,0x26,0xc6,0x06
-,0x29,0x00,0x11,0xbf,0x2a,0x00,0xe8,0x35,0x00,0xe8,0x45,0x00,0xe8,0x55,0x00,0xc3
-,0x26,0xc7,0x06,0x0e,0x00,0x12,0x00,0x26,0xc7,0x06,0x06,0x00,0x02,0x00,0x26,0xc6
-,0x06,0x19,0x00,0x00,0xe8,0x32,0xfe,0xe8,0xc9,0xfd,0x26,0xc7,0x06,0x26,0x00,0x00
-,0x04,0x26,0xc6,0x06,0x28,0x00,0x30,0x26,0xc6,0x06,0x29,0x00,0x13,0xc3,0x26,0xc6
-,0x05,0x04,0x26,0xc6,0x45,0x01,0x0c,0x26,0xc7,0x45,0x02,0x00,0x01,0x83,0xc7,0x04
-,0xc3,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01,0x0e,0x26,0xc7,0x45,0x02,0x00,0x02
-,0x83,0xc7,0x04,0xc3,0x26,0xc6,0x05,0x04,0x26,0xc6,0x45,0x01,0x21,0x26,0xc7,0x45
-,0x02,0x00,0x00,0x83,0xc7,0x04,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0xb3,0x39,0xc9,0x39,0x83,0x3a,0xb3,0x39,0xb3,0x39,0xb3,0x39,0x1c,0x3a,0x1c,0x3a
-,0xa3,0xb6,0x34,0xa1,0xe9,0x36,0xa3,0x11,0x37,0xa3,0xd2,0x34,0xa1,0xeb,0x36,0xa3
-,0x13,0x37,0xa3,0xd4,0x34,0xa1,0xed,0x36,0xa3,0x15,0x37,0xa3,0xd6,0x34,0xa1,0x01
-,0x37,0xa3,0xce,0x34,0xa1,0xf7,0x36,0xa3,0x17,0x37,0xa3,0xdc,0x34,0xa1,0xf9,0x36
-,0xa3,0x19,0x37,0xa3,0xde,0x34,0xf7,0x06,0x9b,0x36,0x02,0x00,0x75,0x0c,0x33,0xc0
-,0xa0,0x9e,0x36,0x8b,0xf0,0x2e,0xff,0xa4,0x50,0x39,0xe9,0x0f,0x01,0xbe,0x07,0x00
-,0xe9,0x19,0xf1,0xf6,0x06,0x9d,0x36,0x80,0x74,0xf3,0xc6,0x06,0xa0,0x36,0x02,0xc6
-,0x06,0x6e,0x37,0x08,0xc6,0x06,0x70,0x37,0x02,0xb8,0x88,0x03,0xcd,0x39,0xf6,0x06
-,0x6f,0x37,0x01,0x75,0x4a,0xa1,0xd1,0x36,0x3a,0x06,0xe9,0x36,0x75,0x41,0x3a,0x26
-,0xea,0x36,0x75,0x3b,0xa1,0xd3,0x36,0x3a,0x06,0xeb,0x36,0x75,0x32,0x3a,0x26,0xec
-,0x36,0x75,0x2c,0xa1,0xd5,0x36,0x3a,0x06,0xed,0x36,0x75,0x23,0x3a,0x26,0xee,0x36
-,0x75,0x1d,0xc6,0x06,0x70,0x37,0x02,0xfe,0x0e,0x6e,0x37,0x75,0x0f,0xb8,0x88,0x03
-,0xcd,0x3a,0x83,0x0e,0x9b,0x36,0x12,0xc6,0x06,0xa0,0x36,0x0c,0xe9,0xa8,0xf0,0xa1
-,0x05,0x37,0x26,0x3b,0x06,0x20,0x00,0x75,0x40,0xa1,0x07,0x37,0x26,0x3b,0x06,0x22
-,0x00,0x75,0x36,0xa1,0x09,0x37,0x26,0x3b,0x06,0x24,0x00,0x75,0x2c,0xa0,0x9e,0x36
-,0x3c,0x02,0x75,0x08,0x26,0xf6,0x06,0x18,0x00,0x08,0x75,0x47,0xc6,0x06,0x6e,0x37
-,0x08,0xfe,0x0e,0x70,0x37,0x75,0x1c,0xc6,0x06,0x70,0x37,0x02,0xe5,0x02,0x0d,0x01
-,0x04,0x25,0xef,0xff,0xe7,0x02,0xe9,0x5e,0xf0,0xc6,0x06,0x70,0x37,0x02,0xc6,0x06
-,0x6e,0x37,0x08,0xe5,0x02,0x25,0xff,0xfb,0x0d,0x01,0x00,0x25,0xef,0xff,0xe7,0x02
-,0xe9,0x44,0xf0,0xf7,0x06,0x9b,0x36,0x00,0x01,0x74,0x25,0x26,0xf6,0x06,0x18,0x00
-,0x08,0x75,0xed,0x81,0x26,0x9b,0x36,0x7f,0xff,0xb8,0x89,0x03,0xcd,0x3a,0xb8,0x84
-,0x03,0xcd,0x3a,0xc6,0x06,0xa0,0x36,0x06,0x83,0x26,0xc2,0x34,0xaf,0xe9,0x17,0xf0
-,0xa1,0x01,0x37,0x3a,0x26,0x0f,0x37,0x7f,0xc7,0xe9,0xf7,0xfe,0x83,0x26,0x9b,0x36
-,0xec,0xe8,0x2a,0x0d,0x81,0x0e,0x9b,0x36,0x80,0x00,0xbb,0xff,0x7f,0xcd,0x53,0xc6
-,0x06,0xa0,0x36,0x02,0xe9,0xf0,0xef,0x83,0x0e,0x9b,0x36,0x11,0xc6,0x06,0xa0,0x36
-,0x0c,0xe9,0xf9,0xef,0x44,0x3b,0x2c,0x3b,0xc7,0x2a,0x6b,0x3b,0x44,0x3b,0xc7,0x2a
-,0xc7,0x2a,0xc7,0x2a,0xa3,0xb6,0x34,0x81,0x0e,0xc2,0x34,0x00,0x20,0xf7,0x06,0x41
-,0x37,0x01,0x00,0x74,0x1b,0x8c,0xc3,0xc7,0x06,0x41,0x37,0x00,0x00,0xb8,0x7f,0x03
-,0xcd,0x3a,0x33,0xc0,0x8e,0xc0,0xbf,0x54,0x37,0xb9,0x06,0x00,0xf3,0xab,0x8e,0xc3
-,0x33,0xc0,0xa0,0x9e,0x36,0x8b,0xf0,0x2e,0xff,0xa4,0xe4,0x3a,0xf7,0x06,0x9b,0x36
-,0x00,0x01,0x75,0x21,0x83,0x26,0xc2,0x34,0xbf,0xa1,0xa9,0x36,0xe7,0x00,0xa1,0x9b
-,0x36,0xe9,0x09,0x00,0xa1,0x9b,0x36,0x81,0x26,0x9b,0x36,0xff,0xdf,0xa9,0x00,0x20
-,0x75,0x06,0xe9,0x6e,0x00,0xe9,0x6f,0xef,0x83,0x0e,0x99,0x36,0x04,0xc7,0x06,0x37
-,0x37,0x01,0x00,0xc6,0x06,0xca,0x34,0x01,0xe9,0x58,0x00,0x83,0x0e,0x9b,0x36,0x40
-,0xe8,0x58,0x00,0xa1,0x05,0x37,0x3b,0x06,0xe9,0x36,0x75,0x37,0xa1,0x07,0x37,0x3b
-,0x06,0xeb,0x36,0x75,0x2e,0xa1,0x09,0x37,0x3b,0x06,0xed,0x36,0x75,0x25,0xfe,0x0e
-,0x71,0x37,0x75,0x1c,0xb8,0x87,0x03,0xcd,0x3a,0x83,0x0e,0x99,0x36,0x10,0xa1,0x50
-,0x37,0xc7,0x06,0x50,0x37,0x00,0x00,0x09,0x06,0x99,0x36,0xc6,0x06,0xa0,0x36,0x08
-,0xe9,0x14,0xef,0x83,0x0e,0x99,0x36,0x04,0xc7,0x06,0x37,0x37,0x03,0x00,0xc6,0x06
-,0xca,0x34,0x03,0xc6,0x06,0xa0,0x36,0x0a,0xe9,0xfc,0xee,0xa1,0xd1,0x36,0x26,0x3b
-,0x06,0x20,0x00,0x75,0x15,0xa1,0xd3,0x36,0x26,0x3b,0x06,0x22,0x00,0x75,0x12,0xa1
-,0xd5,0x36,0x26,0x3b,0x06,0x24,0x00,0x75,0x0f,0xc3,0x8d,0x36,0x20,0x00,0xe9,0x0b
-,0x00,0x8d,0x36,0x22,0x00,0xe9,0x04,0x00,0x8d,0x36,0x24,0x00,0x83,0xc4,0x02,0xf7
-,0x06,0xe6,0x34,0x01,0x00,0x74,0x15,0x26,0x3a,0x04,0x77,0x08,0x72,0x0e,0x26,0x3a
-,0x64,0x01,0x72,0x08,0xc6,0x06,0xa0,0x36,0x06,0xe9,0xab,0xee,0xe8,0x7c,0x0a,0x8c
-,0xc0,0x3d,0xff,0xff,0x74,0x1b,0x26,0xc6,0x06,0x18,0x00,0x10,0x26,0xc7,0x06,0x04
-,0x00,0x49,0x3c,0x26,0xc7,0x06,0x06,0x00,0x0c,0x00,0xcd,0x50,0xb9,0x4e,0x00,0xe2
-,0xfe,0xc6,0x06,0xa0,0x36,0x0a,0xe9,0x94,0xee,0xe9,0x7b,0xee,0x8f,0x3c,0x06,0x3d
-,0x06,0x3d,0x06,0x3d,0xd2,0x3c,0xea,0x3c,0x06,0x3d,0x06,0x3d,0xa3,0xb6,0x34,0x81
-,0x26,0xc2,0x34,0xaf,0xdf,0xc7,0x06,0x4c,0x37,0x00,0x00,0xb8,0x8a,0x03,0xcd,0x3a
-,0x80,0x3e,0x9d,0x36,0x04,0x75,0x0c,0x80,0x3e,0x9e,0x36,0x06,0x74,0x05,0xc6,0x06
-,0x9f,0x36,0x06,0x33,0xc0,0xa0,0x9e,0x36,0x8b,0xf0,0x2e,0xff,0xa4,0x4c,0x3c,0xf7
-,0x06,0x9b,0x36,0x00,0x20,0x75,0x0e,0x81,0x26,0x9b,0x36,0xff,0xbf,0xb8,0x8b,0x03
-,0xcd,0x3a,0xe9,0x54,0x00,0xf7,0x06,0x9b,0x36,0x00,0x01,0x74,0x03,0xe9,0x17,0xee
-,0xc7,0x06,0x37,0x37,0x02,0x00,0xc6,0x06,0xca,0x34,0x02,0x83,0x0e,0x99,0x36,0x04
-,0x83,0x0e,0x50,0x37,0x04,0xf6,0x06,0x9d,0x36,0x80,0x75,0x2a,0xe8,0x1f,0x0b,0xe9
-,0x27,0x00,0xf7,0x06,0x9b,0x36,0x00,0x01,0x75,0xd3,0xc7,0x06,0x37,0x37,0x02,0x00
-,0xc6,0x06,0xca,0x34,0x02,0x83,0x0e,0x99,0x36,0x04,0xc6,0x06,0xa0,0x36,0x00,0xf6
-,0x06,0x9d,0x36,0x80,0x74,0x03,0xe8,0xde,0x0a,0x81,0x26,0x9b,0x36,0x7c,0xff,0xbb
-,0xff,0xff,0xcd,0x53,0xcd,0x54,0xe9,0xbe,0xed,0xa3,0xb6,0x34,0xe8,0xad,0x01,0xb8
-,0x86,0x03,0xcd,0x39,0xc7,0x06,0x4c,0x37,0x00,0x00,0x81,0x26,0xc2,0x34,0xaf,0xdf
-,0xf6,0x06,0x9d,0x36,0x80,0x74,0x34,0xf7,0x06,0x9b,0x36,0x00,0x20,0x74,0x56,0xf7
-,0x06,0x9b,0x36,0x00,0x01,0x74,0x27,0xe8,0x35,0x01,0x72,0x1c,0xbe,0x00,0x40,0x85
-,0x36,0xc2,0x34,0x75,0x08,0x09,0x36,0xc2,0x34,0xff,0x06,0x92,0x34,0xe8,0x8b,0x01
-,0x73,0x06,0x81,0x0e,0x99,0x36,0x80,0x00,0xe9,0x6c,0xed,0xe9,0xb5,0x00,0xc7,0x06
-,0x37,0x37,0x02,0x00,0xc6,0x06,0xca,0x34,0x02,0x83,0x0e,0x99,0x36,0x04,0x83,0x0e
-,0x50,0x37,0x04,0x80,0x3e,0x9e,0x36,0x08,0x74,0x03,0xe8,0x5a,0x0a,0xe8,0xef,0x00
-,0x72,0xd6,0xe9,0xc8,0xff,0x80,0x3e,0x9e,0x36,0x0a,0x75,0x12,0xc6,0x06,0xa0,0x36
-,0x00,0xf7,0x06,0x9b,0x36,0x08,0x00,0x74,0x02,0xcd,0x54,0xe8,0x39,0x0a,0x81,0x26
-,0x9b,0x36,0xff,0xbf,0xe8,0xc8,0x00,0x72,0xaf,0xb8,0x8b,0x03,0xcd,0x39,0xe9,0x9c
-,0xff,0xf6,0x06,0x9e,0x36,0xff,0x75,0x58,0xa3,0xb6,0x34,0xe8,0xfe,0x00,0x81,0x26
-,0xc2,0x34,0xff,0xbf,0xf6,0x06,0x9d,0x36,0x80,0x74,0x48,0xf7,0x06,0x9b,0x36,0x00
-,0x20,0x74,0x22,0xf7,0x06,0x9b,0x36,0x00,0x40,0x75,0x08,0xe8,0x91,0x00,0x72,0x30
-,0xe9,0x22,0x00,0x26,0xa1,0x0c,0x00,0xa9,0x60,0x00,0x75,0x24,0x81,0x0e,0x66,0x37
-,0x00,0x08,0xe9,0xd2,0xec,0xc7,0x06,0x4c,0x37,0x00,0x00,0xe8,0x71,0x00,0x72,0x10
-,0xb8,0x8b,0x03,0xcd,0x39,0xe8,0xd3,0x00,0x73,0x06,0x81,0x0e,0x99,0x36,0x80,0x00
-,0xe9,0xb4,0xec,0x80,0x3e,0x9d,0x36,0x04,0x75,0x0c,0x80,0x3e,0x9e,0x36,0x06,0x74
-,0x46,0xc6,0x06,0x9f,0x36,0x06,0xf7,0x06,0x9b,0x36,0x00,0x01,0x74,0x0c,0x80,0x3e
-,0x9d,0x36,0x08,0x75,0x05,0xc6,0x06,0x9f,0x36,0x0a,0xe8,0x32,0x00,0x72,0xd1,0xe8
-,0x99,0x00,0x80,0x3e,0x9d,0x36,0x08,0x75,0x13,0x81,0x0e,0x99,0x36,0x80,0x00,0xf7
-,0x06,0x9b,0x36,0x00,0x20,0x75,0x08,0xb8,0x8b,0x03,0xcd,0x39,0xe9,0x68,0xec,0xc6
-,0x06,0x9f,0x36,0x0a,0xe9,0x60,0xec,0xb8,0x86,0x03,0xcd,0x3a,0xe9,0x58,0xec,0x26
-,0xa1,0x0c,0x00,0xa9,0x60,0x00,0x74,0x08,0x81,0x26,0xc2,0x34,0xff,0xbf,0xf9,0xc3
-,0xf7,0x06,0x9b,0x36,0x00,0x40,0x74,0x13,0x81,0x0e,0x66,0x37,0x00,0x08,0xe8,0x4a
-,0x00,0x73,0x06,0x81,0x0e,0x99,0x36,0x80,0x00,0xf9,0xc3,0x81,0x0e,0x9b,0x36,0x00
-,0x40,0x80,0x26,0x6f,0x37,0xfe,0x81,0x26,0x9b,0x36,0x7f,0xff,0xc6,0x06,0xa0,0x36
-,0x00,0xf8,0xc3,0x81,0x0e,0x99,0x36,0x00,0x01,0xe9,0x21,0xec,0x26,0xa1,0x20,0x00
-,0xa3,0xfb,0x36,0xa3,0xaa,0x34,0x26,0xa1,0x22,0x00,0xa3,0xfd,0x36,0xa3,0xac,0x34
-,0x26,0xa1,0x24,0x00,0xa3,0xff,0x36,0xa3,0xae,0x34,0xc3,0xa1,0x05,0x37,0x26,0x3b
-,0x06,0x20,0x00,0x75,0x19,0xa1,0x07,0x37,0x26,0x3b,0x06,0x22,0x00,0x75,0x0f,0xa1
-,0x09,0x37,0x26,0x3b,0x06,0x24,0x00,0x75,0x05,0xe8,0x02,0x00,0xf8,0xc3,0x51,0x1e
-,0x06,0x8b,0xc7,0x8d,0x36,0x20,0x00,0xbf,0x05,0x37,0xb9,0x03,0x00,0x1e,0x06,0x1f
-,0x07,0xf3,0xa5,0x8b,0xf8,0x8d,0x36,0x20,0x00,0xbf,0xa0,0x34,0xb9,0x03,0x00,0xf3
-,0xa5,0x07,0x1f,0x59,0x8b,0xf8,0xa1,0x07,0x37,0xa3,0xa6,0x34,0xa1,0x09,0x37,0xa3
-,0xa8,0x34,0xf9,0xc3,0xc6,0x06,0xb6,0x34,0x01,0xe9,0x8b,0xeb,0xe8,0x87,0x08,0x8b
-,0xf0,0x05,0x12,0x00,0x26,0x29,0x06,0x0e,0x00,0x26,0x8b,0x44,0x2a,0x26,0x3a,0x06
-,0x0e,0x00,0x75,0x5b,0x26,0x83,0x2e,0x0e,0x00,0x02,0x80,0xfc,0x27,0x75,0x50,0x26
-,0x8b,0x44,0x2c,0xa9,0xff,0xff,0x75,0x47,0x8b,0xfe,0x33,0xc0,0x26,0xf6,0x45,0x3c
-,0x80,0x74,0x06,0x26,0x8a,0x45,0x3a,0x24,0x1f,0x03,0xf8,0x26,0x80,0x7d,0x45,0x09
-,0x75,0x2d,0x8c,0xc2,0x8e,0x06,0x38,0x34,0x8e,0xda,0x8b,0x0e,0x0e,0x00,0x26,0x89
-,0x0e,0x0e,0x00,0x8d,0x74,0x2c,0xbf,0x18,0x00,0xf3,0xa4,0x33,0xc0,0x8e,0xd8,0x26
-,0xc7,0x06,0x04,0x00,0xb5,0x3f,0x26,0xc7,0x06,0x06,0x00,0x06,0x00,0xcd,0x50,0xb8
-,0x06,0x80,0xe9,0xef,0xe9,0x26,0xa1,0x0c,0x00,0xa3,0x93,0x37,0x83,0x0e,0x99,0x36
-,0x01,0xe9,0x00,0xeb,0x26,0x80,0x3e,0x1c,0x00,0xff,0x75,0x2f,0x26,0x80,0x3e,0x1e
-,0x00,0xff,0x75,0x27,0x26,0xf7,0x06,0x0c,0x00,0x40,0x00,0x75,0x1b,0xa1,0xd1,0x36
-,0x26,0xa3,0x1a,0x00,0xa1,0xd3,0x36,0x26,0xa3,0x1c,0x00,0xa1,0xd5,0x36,0x26,0xa3
-,0x1e,0x00,0xb8,0x0a,0x80,0xe8,0x36,0x07,0xe9,0xe2,0xea,0xff,0x06,0x90,0x34,0xbe
-,0x0a,0x00,0xc6,0x06,0xb6,0x34,0x01,0xf6,0x06,0x9d,0x36,0x80,0x75,0x05,0x83,0x0e
-,0xc2,0x34,0x01,0xe9,0xb6,0xea,0x80,0x3e,0x9d,0x36,0x0a,0x75,0x0f,0x26,0xa1,0x0c
-,0x00,0x25,0x07,0x00,0x3d,0x04,0x00,0x75,0x03,0xe8,0x79,0x00,0xa1,0xf3,0x36,0x86
-,0xe0,0xe7,0x1e,0xa3,0xe3,0x36,0x81,0x26,0x0b,0x37,0x00,0x03,0x81,0x26,0x0d,0x37
-,0x7b,0x7f,0x83,0x0e,0x0d,0x37,0x48,0xe8,0x1e,0x00,0x26,0xa1,0x0c,0x00,0x25,0x07
-,0x00,0x3d,0x04,0x00,0x74,0x09,0x26,0xf7,0x06,0x0c,0x00,0x20,0x00,0x75,0x06,0xb8
-,0x01,0x00,0xe9,0x3f,0xe9,0xe9,0x5f,0xea,0xc7,0x06,0x41,0x37,0x00,0x00,0xb8,0x7f
-,0x03,0xcd,0x3a,0xa1,0x1d,0x37,0xa3,0xc4,0x34,0x86,0xe0,0x68,0x7f,0x03,0x1f,0xa3
-,0x06,0x00,0x33,0xc0,0x8e,0xd8,0xa1,0x0b,0x37,0xa3,0xb2,0x34,0xa1,0x0d,0x37,0xa3
-,0xb4,0x34,0xa1,0xf3,0x36,0xa3,0xc8,0x34,0xa1,0xef,0x36,0xa3,0x9c,0x34,0xa1,0xf1
-,0x36,0xa3,0x9e,0x34,0xc3,0x80,0x0e,0x9d,0x36,0x80,0xbe,0x00,0x00,0xe8,0xb4,0x07
-,0xb8,0x7b,0x03,0xcd,0x3a,0xb8,0x7c,0x03,0xcd,0x39,0xc7,0x06,0x33,0x37,0x02,0x00
-,0xa1,0xe5,0x36,0xe7,0x2e,0xa1,0xe7,0x36,0xe7,0x3e,0xb8,0x82,0x03,0xcd,0x3a,0xf7
-,0x06,0x9b,0x36,0x00,0x20,0x75,0x03,0xe8,0xfd,0x06,0xa1,0xd3,0x36,0xa3,0xef,0x36
-,0xa3,0x9c,0x34,0xa1,0xd5,0x36,0xa3,0xf1,0x36,0xa3,0x9e,0x34,0xc3,0xf6,0x06,0x9d
-,0x36,0x80,0x74,0x31,0xbe,0x22,0x00,0xe9,0x17,0x00,0xf6,0x06,0x9d,0x36,0x80,0x74
-,0x24,0xbe,0x23,0x00,0xe9,0x0a,0x00,0xf6,0x06,0x9d,0x36,0x80,0x74,0x17,0xbe,0x24
-,0x00,0x56,0xe8,0xa8,0x05,0x8c,0xc0,0x3d,0xff,0xff,0x5e,0x74,0x05,0xe8,0xd7,0xef
-,0xcd,0x50,0xe9,0x1f,0xe8,0xe9,0x9f,0xe9,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0xb8,0x84,0x03,0xcd,0x3a,0xb8,0x8a,0x03,0xcd,0x39,0xe9,0xf7,0x00,0x80,0x3e,0xa0
-,0x36,0x08,0x75,0x2e,0xa9,0xd0,0x07,0x75,0x2c,0xa1,0xb1,0x36,0x0d,0x00,0x04,0xe7
-,0x08,0xe5,0x00,0x25,0xff,0x73,0xe7,0x00,0xb8,0x8a,0x03,0xcd,0x3a,0xe8,0xc3,0x06
-,0x33,0xc0,0xe7,0x0e,0xe5,0x0a,0x25,0xc3,0x17,0xe7,0x0a,0xcd,0x54,0xc6,0x06,0xa0
-,0x36,0x00,0xe9,0x68,0xe9,0xbe,0x04,0x00,0xe9,0x3f,0xe9,0x83,0x26,0x9b,0x36,0xbf
-,0xc6,0x06,0x71,0x37,0x03,0xb8,0x86,0x03,0xcd,0x3a,0xb8,0x88,0x03,0xcd,0x3a,0xb8
-,0x83,0x03,0xcd,0x3a,0xb8,0x87,0x03,0xcd,0x39,0x81,0x0e,0xc2,0x34,0x00,0x20,0xe9
-,0x92,0x00,0xe8,0x49,0x06,0xb8,0x87,0x03,0xcd,0x39,0xbb,0xff,0x7f,0xcd,0x53,0xb8
-,0x84,0x03,0xcd,0x3a,0xb8,0x88,0x03,0xcd,0x3a,0xb8,0x8b,0x03,0xcd,0x3a,0xb8,0x83
-,0x03,0xcd,0x3a,0xb8,0x86,0x03,0xcd,0x3a,0xb8,0x85,0x03,0xcd,0x3a,0xc3,0xe5,0x00
-,0x25,0xff,0x53,0xe7,0x00,0x83,0x0e,0xc2,0x34,0x40,0x83,0x26,0xc2,0x34,0xef,0xe8
-,0x0c,0x06,0xbb,0xff,0x7f,0xcd,0x53,0xb8,0x8a,0x03,0xcd,0x3a,0xb8,0x85,0x03,0xcd
-,0x3a,0xb8,0x86,0x03,0xcd,0x3a,0xb8,0x83,0x03,0xcd,0x3a,0xb8,0x87,0x03,0xcd,0x3a
-,0xb8,0x8b,0x03,0xcd,0x3a,0xb8,0x84,0x03,0xcd,0x3a,0xb8,0x89,0x03,0xcd,0x3a,0xc3
-,0x83,0x0e,0xc2,0x34,0x50,0xe8,0x18,0x04,0xe8,0xd3,0x05,0xf6,0x06,0x6f,0x37,0x01
-,0x75,0x12,0xb8,0x89,0x03,0xcd,0x39,0x83,0x3e,0x0f,0x37,0x00,0x75,0x06,0xc7,0x06
-,0x0f,0x37,0x04,0x00,0xa1,0x9d,0x36,0x80,0xfc,0x08,0x74,0x05,0xb8,0x84,0x03,0xcd
-,0x39,0xe5,0x02,0x0d,0x01,0x08,0x25,0xef,0xff,0xe7,0x02,0xa1,0x9d,0x36,0x86,0xe0
-,0x32,0xe4,0x8b,0xf0,0xd1,0xee,0x33,0xc0,0x0d,0x20,0x00,0x09,0x06,0xad,0x36,0xa1
-,0xad,0x36,0xe7,0x04,0xe9,0x53,0xe8,0xe9,0x5a,0xe8,0x33,0xc0,0xa0,0x1b,0x37,0xd1
-,0xe0,0x3a,0x06,0xa0,0x36,0x75,0x03,0xe9,0xba,0xff,0xe9,0x60,0xe8,0xc7,0x06,0x41
-,0x37,0x00,0x00,0xe8,0xc1,0xe1,0xe8,0x6a,0x06,0x33,0xc0,0x0d,0x41,0x00,0xe7,0x56
-,0xa1,0xb1,0x36,0x0d,0x00,0x10,0xe7,0x08,0xe5,0x02,0x25,0xf9,0xff,0x0d,0x03,0x00
-,0xe7,0x02,0xa1,0xb3,0x36,0xe7,0x0a,0xa1,0xaf,0x36,0xe7,0x06,0xa1,0xad,0x36,0xe7
-,0x04,0xe8,0x7c,0x03,0xe8,0x9f,0x03,0xc7,0x06,0x1d,0x37,0x00,0xc8,0xc7,0x06,0x0b
-,0x37,0x00,0x03,0xc7,0x06,0x0d,0x37,0x7b,0x7f,0x33,0xc0,0xa3,0x99,0x36,0xa3,0x9b
-,0x36,0xa3,0x9d,0x36,0xa3,0x9f,0x36,0xa3,0x4c,0x37,0xa3,0xf3,0x36,0xa3,0xef,0x36
-,0xa3,0xf1,0x36,0xe8,0x82,0xfd,0xc6,0x06,0x9f,0x36,0x02,0xe9,0xef,0xe7,0xe5,0x02
-,0x0d,0x01,0x88,0x25,0xef,0xff,0x0d,0x00,0x40,0x0d,0x00,0x04,0xe7,0x02,0xe8,0xf2
-,0x05,0xe5,0x0a,0x0d,0x40,0x00,0xe7,0x0a,0x33,0xc0,0xa3,0x81,0x37,0xa3,0x85,0x37
-,0xa3,0x83,0x37,0xa3,0x87,0x37,0xa3,0x89,0x37,0xe5,0x00,0x0d,0x00,0x84,0xe7,0x00
-,0xb8,0x8c,0x03,0xcd,0x39,0xb8,0x80,0x00,0xcd,0x35,0xc7,0x06,0xaa,0x02,0xff,0xff
-,0xe5,0x00,0x25,0xff,0x7b,0xe7,0x00,0x81,0x0e,0x9a,0x37,0x80,0x00,0xb8,0x7e,0x03
-,0xcd,0x39,0x33,0xc0,0xe7,0x0e,0xbe,0x08,0x00,0x8e,0x06,0x38,0x34,0xe8,0xa7,0xed
-,0x83,0x26,0xef,0x34,0xdf,0xff,0x06,0x81,0x37,0xcd,0x50,0x83,0x0e,0xef,0x34,0x20
-,0xc3,0xf7,0x06,0x9a,0x37,0x80,0x00,0x74,0x3d,0xa9,0xd0,0x07,0x74,0x10,0xa9,0x00
-,0x04,0x74,0x12,0x33,0xc0,0xe7,0x0e,0xff,0x06,0x87,0x37,0xe9,0xd2,0xff,0xff,0x06
-,0x85,0x37,0xe9,0xcb,0xff,0xff,0x06,0x83,0x37,0xe9,0xc4,0xff,0x83,0x26,0x9a,0x37
-,0x7f,0xa1,0x89,0x37,0x03,0x06,0x87,0x37,0x3d,0x05,0x00,0x7f,0x01,0xc3,0xbb,0xff
-,0x7f,0xcd,0x53,0xe9,0x00,0x00,0xe5,0x02,0x25,0xff,0xfb,0x25,0xef,0xff,0x0d,0x01
-,0x00,0xe7,0x02,0xa1,0x83,0x37,0x3b,0x06,0x46,0x37,0x7f,0x2a,0xa1,0x85,0x37,0x3b
-,0x06,0x48,0x37,0x7c,0x21,0xa1,0x89,0x37,0x03,0x06,0x87,0x37,0x3d,0x05,0x00,0x7f
-,0x15,0xc6,0x06,0x9f,0x36,0x04,0xe5,0x02,0x25,0xff,0xf7,0x0d,0x01,0x00,0x25,0xef
-,0xff,0xe7,0x02,0xe9,0xf7,0xe6,0xbe,0x01,0x00,0xf7,0x06,0x9b,0x36,0x03,0x00,0x74
-,0x0a,0x83,0x26,0x9b,0x36,0xfc,0x83,0x0e,0xc2,0x34,0x04,0xe9,0xd0,0xe6,0xb8,0x7b
-,0x03,0xcd,0x39,0xe5,0x02,0x0d,0x01,0x60,0x25,0xef,0xff,0xe7,0x02,0xc7,0x06,0xf1
-,0x34,0x20,0x03,0xb8,0x8e,0x03,0xcd,0x39,0xc3,0x81,0x26,0xc2,0x34,0x7f,0xff,0x80
-,0x0e,0x6f,0x37,0x01,0xf7,0x06,0x9b,0x36,0x03,0x00,0x74,0xd2,0xb8,0x7b,0x03,0xcd
-,0x3a,0xb8,0x7d,0x03,0xcd,0x39,0x83,0x26,0x9b,0x36,0xef,0x33,0xc0,0xb0,0x8a,0xa2
-,0x9f,0x36,0xa2,0x9d,0x36,0xc7,0x06,0x4c,0x37,0x01,0x00,0xc7,0x06,0x0f,0x37,0x04
-,0x00,0xf7,0x06,0x9b,0x36,0x40,0x00,0x75,0x06,0xc7,0x06,0x0f,0x37,0x03,0x00,0xb8
-,0x8d,0x03,0xcd,0x39,0xe8,0x00,0xd5,0xe5,0x02,0x0d,0x01,0x40,0x25,0xef,0xff,0x8b
-,0xd8,0xb8,0x7c,0x03,0xcd,0x39,0xc7,0x06,0x33,0x37,0x02,0x00,0x8b,0xc3,0x0d,0x00
-,0x20,0x25,0xf9,0xff,0x0b,0x06,0xe8,0x3a,0xe7,0x02,0xc3,0xff,0x0e,0xf1,0x34,0x75
-,0x01,0xc3,0xe5,0x4e,0xa9,0x01,0x00,0x75,0x12,0xe5,0x00,0xa9,0x00,0x04,0x75,0x05
-,0x0d,0x00,0x04,0xe7,0x00,0xb8,0x8e,0x03,0xcd,0x39,0xc3,0xe5,0x00,0xa9,0x00,0x04
-,0x74,0xf3,0x25,0xff,0xfb,0xe7,0x00,0xe9,0xeb,0xff,0xc6,0x06,0xa0,0x36,0x04,0x83
-,0x26,0x9b,0x36,0xfc,0x81,0x0e,0x9b,0x36,0x80,0x00,0xe9,0x10,0xe6,0xb8,0x8e,0x03
-,0xcd,0x3a,0xcd,0x54,0x81,0x0e,0xaf,0x36,0x00,0x18,0xa1,0xaf,0x36,0xe7,0x06,0xb8
-,0x7b,0x03,0xcd,0x39,0xa1,0xd3,0x36,0xa3,0x8f,0x37,0xa1,0xd5,0x36,0xa3,0x91,0x37
-,0xc7,0x06,0x8b,0x37,0x02,0x00,0xc7,0x06,0x8d,0x37,0x02,0x00,0x83,0x0e,0x99,0x36
-,0x40,0xe9,0xd9,0xe5,0x80,0x3e,0x9f,0x36,0x06,0x75,0x15,0xa9,0xd0,0x07,0x75,0xec
-,0x25,0x00,0x18,0x75,0x0e,0xff,0x0e,0x8b,0x37,0x75,0xe1,0xc6,0x06,0x9f,0x36,0x08
-,0xe9,0xba,0xe5,0xff,0x0e,0x8d,0x37,0x75,0xd3,0xbe,0x08,0x00,0xe9,0x9f,0xe5,0xb8
-,0x7b,0x03,0xcd,0x39,0xf7,0x06,0x9b,0x36,0x00,0x20,0x74,0x08,0xc6,0x06,0x9f,0x36
-,0x0a,0xe9,0x0d,0x00,0xf7,0x06,0x9b,0x36,0x00,0x40,0x74,0x0b,0xb8,0x8b,0x03,0xcd
-,0x39,0x81,0x0e,0x99,0x36,0x80,0x00,0xe9,0x83,0xe5,0xb8,0x7b,0x03,0xcd,0x39,0xc7
-,0x06,0x8b,0x37,0x04,0x00,0xc7,0x06,0x8d,0x37,0x04,0x00,0x81,0x0e,0x99,0x36,0x00
-,0x02,0xe9,0x69,0xe5,0xf6,0x06,0x9d,0x36,0x80,0x75,0x1b,0xa9,0xd0,0x07,0x75,0xeb
-,0xa9,0x00,0x18,0x75,0x0c,0xff,0x0e,0x8d,0x37,0x75,0xe0,0xe8,0x17,0xfb,0xe9,0x4c
-,0xe5,0xb8,0x82,0x03,0xcd,0x39,0xc3,0xff,0x0e,0x8b,0x37,0x75,0xce,0xbe,0x09,0x00
-,0xe9,0x2b,0xe5,0xc7,0x06,0x3d,0x37,0x00,0x00,0xc7,0x06,0x9b,0x36,0x00,0x00,0xe8
-,0x3c,0x02,0x81,0x26,0xaf,0x36,0xff,0xe7,0xa1,0xaf,0x36,0xe7,0x06,0x81,0x26,0x9b
-,0x36,0xff,0x7f,0xe5,0x02,0x0d,0x01,0x00,0x25,0xef,0xff,0x25,0xff,0xdf,0xe7,0x02
-,0xbb,0xff,0x7f,0xcd,0x53,0x33,0xc0,0xa3,0x9d,0x36,0xa3,0x9f,0x36,0xe8,0x50,0x00
-,0xe8,0x73,0x00,0xb8,0x81,0x03,0xcd,0x39,0xc3,0xf7,0x06,0x9b,0x36,0x03,0x00,0x74
-,0x0d,0xc6,0x06,0x9f,0x36,0x02,0xc6,0x06,0xa0,0x36,0x00,0xe9,0xdf,0xe4,0x83,0x0e
-,0x9b,0x36,0x10,0xc7,0x06,0x99,0x36,0x00,0x00,0xe8,0xe7,0x02,0xe5,0x56,0x0d,0x02
-,0x00,0xe7,0x56,0xc7,0x06,0xa8,0x02,0x00,0x00,0x8b,0x36,0x3d,0x37,0xe8,0x44,0x02
-,0xc6,0x06,0xa0,0x36,0x0e,0xe9,0xb5,0xe4,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x06,0xb8,0x8a,0x03,0xcd,0x3a,0xb8,0x85,0x03,0xcd,0x3a,0xb8,0x86,0x03,0xcd,0x3a
-,0xb8,0x83,0x03,0xcd,0x3a,0xb8,0x87,0x03,0xcd,0x3a,0xb8,0x8b,0x03,0xcd,0x3a,0xb8
-,0x88,0x03,0xcd,0x3a,0x07,0xc3,0x06,0xb8,0x88,0x03,0xcd,0x3a,0xb8,0x7b,0x03,0xcd
-,0x3a,0xb8,0x82,0x03,0xcd,0x3a,0xb8,0x7f,0x03,0xcd,0x3a,0xb8,0x7c,0x03,0xcd,0x3a
-,0xb8,0x7e,0x03,0xcd,0x3a,0xb8,0x80,0x03,0xcd,0x3a,0xb8,0x81,0x03,0xcd,0x3a,0xb8
-,0x84,0x03,0xcd,0x3a,0xb8,0x89,0x03,0xcd,0x3a,0xb8,0x7d,0x03,0xcd,0x3a,0xb8,0x8d
-,0x03,0xcd,0x3a,0xc7,0x06,0x41,0x37,0x00,0x00,0x07,0xc3,0x06,0x8e,0x06,0x38,0x34
-,0x1f,0x8b,0x0e,0x0e,0x00,0x26,0x89,0x0e,0x0e,0x00,0xbe,0x18,0x00,0xbf,0x18,0x00
-,0xf3,0xa4,0x06,0x1e,0x07,0xcd,0x34,0x07,0x33,0xc0,0x8e,0xd8,0xc3,0x26,0xf6,0x06
-,0x20,0x00,0x80,0x74,0x44,0x33,0xc0,0x26,0xa0,0x26,0x00,0x24,0x1f,0x8b,0xf0,0x26
-,0x8b,0x5c,0x28,0x89,0x1e,0x6a,0x37,0x06,0x8e,0x06,0x38,0x34,0x1f,0xc0,0xe3,0x04
-,0x26,0x88,0x5c,0x28,0x8b,0xc6,0xb9,0x06,0x00,0xbe,0x20,0x00,0xbf,0x1a,0x00,0xf3
-,0xa4,0x8b,0xc8,0x83,0xc7,0x06,0xf3,0xa4,0x26,0x81,0x26,0x26,0x00,0x1f,0x80,0x26
-,0x81,0x36,0x26,0x00,0x00,0x80,0xe9,0xa9,0xff,0x26,0x8b,0x1e,0x28,0x00,0x89,0x1e
-,0x6a,0x37,0x06,0x8e,0x06,0x38,0x34,0x1f,0xc0,0xe3,0x04,0x26,0x88,0x1e,0x28,0x00
-,0xb9,0x06,0x00,0xbe,0x20,0x00,0xbf,0x1a,0x00,0xf3,0xa4,0xe9,0x84,0xff,0x86,0xc4
-,0xa3,0x68,0x37,0xe8,0x87,0xff,0xf7,0x06,0x6a,0x37,0x0f,0x00,0x74,0x10,0x80,0x3e
-,0x9e,0x36,0x00,0x75,0x09,0xbe,0x00,0x00,0xe8,0xac,0xe9,0xcd,0x50,0xc3,0xc3,0x50
-,0x56,0x06,0x33,0xc0,0x26,0xf6,0x06,0x20,0x00,0x80,0x74,0x06,0x26,0xa0,0x26,0x00
-,0x24,0x1f,0x8b,0xf0,0x26,0x8b,0x5c,0x26,0x86,0xfb,0x83,0xeb,0x04,0x74,0x4f,0x83
-,0xc6,0x2a,0x8c,0xc0,0x8e,0xd8,0xb9,0x07,0x00,0x33,0xc0,0x8e,0xc0,0xbf,0x72,0x37
-,0xf3,0xab,0x33,0xc9,0x8a,0x0c,0x80,0xf9,0x00,0x75,0x03,0xe9,0x30,0x00,0x3b,0xd9
-,0x73,0x03,0xe9,0x29,0x00,0x2b,0xd9,0x8a,0x44,0x01,0x25,0x3f,0x00,0x74,0x19,0x3d
-,0x0b,0x00,0x7d,0x14,0xd1,0xe0,0x8b,0xf8,0x2e,0x8b,0xbd,0x5c,0x49,0x8d,0x74,0x02
-,0x83,0xe9,0x02,0xf3,0xa4,0xe9,0x02,0x00,0x03,0xf1,0x23,0xdb,0x75,0xc4,0x33,0xc0
-,0x8e,0xd8,0x07,0x5e,0x58,0xc3,0x33,0xc0,0x26,0xf6,0x06,0x20,0x00,0x80,0x74,0x06
-,0x26,0xa0,0x26,0x00,0x24,0x1f,0xc3,0xe5,0x0a,0x25,0xc3,0xbf,0xe7,0x0a,0xb8,0x86
-,0x03,0xcd,0x39,0xb8,0x83,0x03,0xcd,0x39,0x81,0x26,0x9b,0x36,0x7c,0xdf,0xb8,0x85
-,0x03,0xcd,0x3a,0xe5,0x02,0x25,0xff,0xf3,0x0d,0x01,0x00,0x25,0xef,0xff,0xe7,0x02
-,0xe5,0x00,0x25,0xff,0x53,0xe7,0x00,0xa1,0xe7,0x36,0x25,0xff,0xfe,0xa3,0xe7,0x36
-,0xe7,0x3e,0x83,0x26,0x99,0x36,0xcf,0x81,0x0e,0xaf,0x36,0x00,0x10,0xa1,0xaf,0x36
-,0xe7,0x06,0xc3,0xe5,0x02,0x0d,0x01,0x0c,0x25,0xef,0xff,0xe7,0x02,0xa1,0xe7,0x36
-,0x0d,0x00,0x01,0xe7,0x3e,0xa3,0xe7,0x36,0x81,0x0e,0x9b,0x36,0x00,0x20,0x83,0x0e
-,0x99,0x36,0x20,0x81,0x26,0x9b,0x36,0x7c,0xbf,0x81,0x0e,0xaf,0x36,0x00,0x10,0xa1
-,0xaf,0x36,0xe7,0x06,0xb8,0x86,0x03,0xcd,0x39,0xb8,0x85,0x03,0xcd,0x39,0xb8,0x83
-,0x03,0xcd,0x3a,0xc3,0x0b,0xf6,0x75,0x49,0x06,0x8e,0x06,0x32,0x34,0x80,0x3e,0xe0
-,0x34,0x01,0x75,0x1b,0x26,0x89,0x36,0x06,0x00,0x8e,0x06,0x32,0x34,0x26,0xf7,0x06
-,0x0a,0x00,0x00,0x20,0x74,0x07,0x26,0x81,0x0e,0x08,0x00,0x00,0x20,0x07,0xc3,0x80
-,0x3e,0xe3,0x34,0x01,0x75,0x19,0x26,0x89,0x36,0x06,0x00,0x8e,0x06,0x32,0x34,0x26
-,0xf7,0x06,0x0a,0x00,0x00,0x10,0x74,0x07,0x26,0x81,0x0e,0x08,0x00,0x00,0x10,0x07
-,0xc3,0xe9,0xb4,0xff,0x50,0x51,0x57,0x33,0xc0,0xb9,0x06,0x00,0x8e,0xc0,0xbf,0xd1
-,0x36,0xf3,0xae,0x5f,0x74,0x0c,0x26,0xf6,0x06,0x00,0x00,0xc0,0x75,0x04,0xf8,0x59
-,0x58,0xc3,0xf9,0xe9,0xf9,0xff,0x8b,0x05,0x0b,0x45,0x02,0x0b,0x45,0x04,0xc3,0x52
-,0x50,0xe5,0x06,0x25,0x1e,0x00,0x3d,0x1e,0x00,0x75,0xf6,0xb8,0x01,0x80,0xe7,0x5a
-,0x58,0x5a,0xc3,0xe8,0xe9,0xff,0x50,0xe5,0x02,0x25,0xff,0x7f,0x0d,0x01,0x00,0x25
-,0xef,0xff,0xe7,0x02,0x0d,0x00,0x80,0xe7,0x02,0xa1,0xad,0x36,0xe7,0x04,0xa1,0xaf
-,0x36,0xe7,0x06,0x58,0xc3,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x2e,0x2b,0xce,0x41,0x10,0x42,0x7b,0x41,0x30,0x41,0xa2,0x41,0xaf,0x45,0x44,0x29
-,0xc7,0x2a,0xc7,0x2a,0x60,0x39,0xf4,0x3a,0x5c,0x3c,0x09,0x3d,0xb1,0x3d,0x34,0x3f
-,0xc7,0x2a,0x3c,0x3f,0xc7,0x2a,0xc4,0x3f,0x16,0x40,0x16,0x40,0xed,0x40,0xfa,0x40
-,0x07,0x41,0xc7,0x2a,0xc7,0x2a,0xc7,0x2a,0xc7,0x2a,0xd6,0x52,0x00,0x00,0x01,0x37
-,0xe9,0x36,0xf3,0x36,0xef,0x36,0x1d,0x37,0x0d,0x37,0x0b,0x37,0x9c,0x37,0x03,0x37
-,0xfb,0x36,0x62,0x2d,0x40,0x06,0xd1,0x2d,0xf4,0x01,0xba,0x44,0x40,0x06,0x8c,0x43
-,0x64,0x00,0xe8,0x2c,0xc8,0x00,0xd8,0x2b,0x05,0x00,0xe9,0x45,0x50,0x00,0x97,0x45
-,0xfa,0x00,0xae,0x2d,0x04,0x01,0x6a,0x42,0x02,0x00,0xf6,0x2c,0xbc,0x02,0x93,0x2d
-,0xdc,0x05,0x1d,0x2d,0x64,0x00,0xa1,0x2d,0x14,0x00,0xd7,0x3a,0x08,0x07,0x81,0x2d
-,0x64,0x00,0xb3,0x3e,0x02,0x00,0x30,0x43,0x64,0x00,0xc5,0x2c,0xf4,0x01,0x8b,0x44
-,0x02,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x80,0x3e,0xfd,0x34,0x02,0x74,0x0c,0xe8,0x20,0x05,0xc7,0x06,0xa1,0x36,0x00,0x00
-,0xe9,0x9a,0xf8,0xff,0x06,0xc0,0x33,0xe8,0x10,0x05,0x8b,0x36,0x3d,0x37,0xe8,0x73
-,0xfe,0xc3,0xcd,0x34,0xe9,0xe8,0x05,0xc7,0x06,0xa3,0x36,0x00,0x00,0xc7,0x06,0x41
-,0x37,0x00,0x00,0xe8,0xed,0xfe,0x33,0xc0,0x0d,0x41,0x00,0xe7,0x56,0xa1,0xb1,0x36
-,0x0d,0x00,0x10,0xe7,0x08,0xa1,0xb3,0x36,0xe7,0x0a,0xa1,0xaf,0x36,0xe7,0x06,0xa1
-,0xad,0x36,0xe7,0x04,0xe8,0x2b,0x09,0xc7,0x06,0x1d,0x37,0x00,0xc8,0xc7,0x06,0x0b
-,0x37,0x00,0x03,0xc7,0x06,0x0d,0x37,0x7b,0x7f,0x33,0xc0,0xa3,0x9b,0x36,0xa3,0x9d
-,0x36,0xc7,0x06,0x4c,0x37,0x01,0x00,0xc6,0x06,0x9e,0x36,0xff,0xc7,0x06,0x05,0x37
-,0x00,0x00,0xc7,0x06,0x07,0x37,0x00,0x00,0xc7,0x06,0x09,0x37,0x00,0x00,0xa3,0xf3
-,0x36,0xa3,0xef,0x36,0xa3,0xf1,0x36,0xe8,0xfe,0xf5,0xe5,0x02,0x25,0xf9,0xff,0x0d
-,0x03,0x00,0x0d,0x00,0x88,0x25,0xef,0xff,0x0d,0x00,0x40,0x0d,0x00,0x04,0xe7,0x02
-,0xb8,0x8f,0x03,0xcd,0x39,0xb8,0x80,0x00,0xcd,0x35,0xc7,0x06,0xaa,0x02,0xff,0xff
-,0xa1,0xa9,0x36,0xa3,0xa7,0x36,0x0d,0x00,0xa4,0x0d,0x00,0x08,0xe7,0x00,0xa3,0xa9
-,0x36,0xc7,0x06,0xa3,0x36,0x01,0x00,0xc7,0x06,0xa5,0x36,0x0c,0x00,0x83,0x3e,0xa5
-,0x36,0x00,0x75,0x09,0xc7,0x06,0x3d,0x37,0x05,0x00,0xe9,0x13,0xff,0xff,0x0e,0xa5
-,0x36,0xbe,0x11,0x00,0xe8,0x22,0x05,0xb8,0x90,0x03,0xcd,0x39,0xc3,0x83,0x3e,0xa3
-,0x36,0x01,0x74,0xd9,0xc3,0xb8,0x90,0x03,0xcd,0x3a,0x26,0xa0,0x2b,0x00,0x26,0x8b
-,0x1e,0x2c,0x00,0xcd,0x34,0x83,0x3e,0xa3,0x36,0x01,0x74,0x03,0xe9,0xf0,0x04,0x3c
-,0x0f,0x75,0x1e,0x81,0xfb,0x00,0x02,0x75,0x18,0x26,0xa1,0x20,0x00,0xa3,0x05,0x37
-,0x26,0xa1,0x22,0x00,0xa3,0x07,0x37,0x26,0xa1,0x24,0x00,0xa3,0x09,0x37,0xe9,0x09
-,0x00,0xc7,0x06,0x3d,0x37,0x01,0x00,0xe9,0xb6,0xfe,0xc7,0x06,0xa3,0x36,0x02,0x00
-,0xc6,0x06,0x9e,0x36,0xff,0xe8,0xcb,0xfd,0xe8,0x1c,0xd9,0x33,0xc0,0xa3,0x85,0x37
-,0xa3,0x83,0x37,0xa3,0x87,0x37,0xa3,0x89,0x37,0xb8,0x91,0x03,0xcd,0x39,0xb8,0x80
-,0x00,0xcd,0x35,0xc7,0x06,0xaa,0x02,0xff,0xff,0xe5,0x00,0x25,0xff,0x53,0xe7,0x00
-,0x81,0x0e,0x9a,0x37,0x80,0x00,0xb8,0x92,0x03,0xcd,0x39,0x33,0xc0,0xe7,0x0e,0xbe
-,0x08,0x00,0x8e,0x06,0x38,0x34,0xe8,0x8e,0xe5,0x26,0xc7,0x06,0x04,0x00,0x7d,0x4b
-,0x83,0x26,0xef,0x34,0xdf,0xcd,0x50,0x83,0x0e,0xef,0x34,0x20,0xc3,0xf7,0x06,0x9a
-,0x37,0x80,0x00,0x74,0x32,0xa9,0xd0,0x07,0x74,0x0c,0xa9,0x00,0x04,0x74,0x0e,0x33
-,0xc0,0xe7,0x0e,0xe9,0xda,0xff,0xff,0x06,0x85,0x37,0xe9,0xd3,0xff,0xff,0x06,0x83
-,0x37,0xe9,0xcc,0xff,0xc7,0x06,0x3d,0x37,0x01,0x00,0xe9,0x36,0xfe,0x83,0x26,0x9a
-,0x37,0x7f,0xbb,0xff,0x7f,0xcd,0x53,0xe5,0x00,0x0d,0x00,0xac,0xe7,0x00,0xe5,0x02
-,0x25,0xff,0xfb,0x25,0xef,0xff,0x25,0xff,0xf7,0x0d,0x01,0x00,0xe7,0x02,0xa1,0x83
-,0x37,0x3b,0x06,0x46,0x37,0x7f,0xcd,0xa1,0x85,0x37,0x3b,0x06,0x48,0x37,0x7c,0xc4
-,0xc7,0x06,0xa3,0x36,0x03,0x00,0xbe,0x13,0x00,0xe8,0xfd,0x03,0xb8,0x93,0x03,0xcd
-,0x39,0xb8,0x94,0x03,0xcd,0x39,0xb8,0x96,0x03,0xcd,0x39,0xb8,0x95,0x03,0xcd,0x39
-,0xbe,0x06,0x00,0xe8,0xe3,0x03,0xe9,0xd6,0x03,0x83,0x3e,0xa3,0x36,0x03,0x74,0x01
-,0xc3,0xbe,0x13,0x00,0xe8,0xd2,0x03,0xb8,0x94,0x03,0xcd,0x39,0xc3,0xb8,0x94,0x03
-,0xcd,0x3a,0x26,0xa0,0x2b,0x00,0x26,0x8b,0x1e,0x2c,0x00,0xcd,0x34,0x83,0x3e,0xa3
-,0x36,0x03,0x74,0x03,0xe9,0xa8,0x03,0x3c,0x0d,0x75,0x3e,0x83,0xfb,0x00,0x75,0x39
-,0xe5,0x02,0x0d,0x00,0x20,0xe7,0x02,0xb8,0x93,0x03,0xcd,0x3a,0xc7,0x06,0xa3,0x36
-,0x04,0x00,0xbe,0x00,0x00,0xe8,0x0c,0xfc,0xc6,0x06,0x9d,0x36,0x80,0xc6,0x06,0x9e
-,0x36,0x00,0xc7,0x06,0x33,0x37,0x02,0x00,0xb8,0x9a,0x03,0xcd,0x39,0xe8,0xfc,0x00
-,0xc7,0x06,0x4c,0x37,0x00,0x00,0xe9,0x66,0x03,0xc7,0x06,0x3d,0x37,0x08,0x00,0xe9
-,0x61,0xfd,0x83,0x3e,0xa3,0x36,0x03,0x75,0x09,0xc7,0x06,0x3d,0x37,0x05,0x00,0xe9
-,0x51,0xfd,0xe9,0x4a,0x03,0x83,0x3e,0xa3,0x36,0x04,0x74,0x12,0x83,0x3e,0xa3,0x36
-,0x05,0x74,0x0b,0xcd,0x34,0xc7,0x06,0x3d,0x37,0x07,0x00,0xe9,0x35,0xfd,0xc7,0x06
-,0xa3,0x36,0x06,0x00,0xc6,0x06,0x9e,0x36,0xff,0xb8,0x9a,0x03,0xcd,0x3a,0xb8,0x99
-,0x03,0xcd,0x3a,0xb8,0x96,0x03,0xcd,0x3a,0xb8,0x97,0x03,0xcd,0x39,0xb8,0x98,0x03
-,0xcd,0x39,0xb8,0x9b,0x03,0xcd,0x39,0xe9,0x18,0xfd,0xcd,0x34,0x83,0x3e,0xa3,0x36
-,0x04,0x77,0x18,0x83,0x3e,0xa3,0x36,0x03,0x75,0x08,0xf7,0x06,0x9b,0x36,0x00,0x01
-,0x75,0x09,0xc7,0x06,0x3d,0x37,0x01,0x00,0xe9,0xe8,0xfc,0xe9,0xe1,0x02,0xcd,0x34
-,0x83,0x3e,0xa3,0x36,0x02,0x77,0x09,0xc7,0x06,0x3d,0x37,0x01,0x00,0xe9,0xd3,0xfc
-,0x83,0x3e,0xa3,0x36,0x04,0x77,0x05,0xb8,0x96,0x03,0xcd,0x39,0xe9,0xc0,0x02,0x83
-,0x3e,0xa3,0x36,0x03,0x75,0x10,0x26,0xa1,0x0c,0x00,0x25,0x07,0x00,0x50,0x3d,0x04
-,0x00,0x75,0x03,0xe8,0x36,0x00,0xa1,0xf3,0x36,0x86,0xe0,0xe7,0x1e,0xa3,0xe3,0x36
-,0x81,0x26,0x0b,0x37,0x00,0x03,0x81,0x26,0x0d,0x37,0x7b,0x7f,0x83,0x0e,0x0d,0x37
-,0x48,0xe8,0x14,0xf3,0x58,0x3d,0x04,0x00,0x74,0x09,0x26,0xf7,0x06,0x0c,0x00,0x20
-,0x00,0x75,0x06,0xb8,0x01,0x00,0xe9,0x7a,0x02,0xe9,0x86,0xfc,0xa1,0xe5,0x36,0xe7
-,0x2e,0xa1,0xe7,0x36,0xe7,0x3e,0xa1,0xd3,0x36,0xa3,0x9c,0x34,0xa1,0xd5,0x36,0xa3
-,0x9e,0x34,0xc3,0x26,0x80,0x3e,0x1c,0x00,0xff,0x75,0x2f,0x26,0x80,0x3e,0x1e,0x00
-,0xff,0x75,0x27,0x26,0xf7,0x06,0x0c,0x00,0x40,0x00,0x75,0x1b,0xa1,0xd1,0x36,0x26
-,0xa3,0x1a,0x00,0xa1,0xd3,0x36,0x26,0xa3,0x1c,0x00,0xa1,0xd5,0x36,0x26,0xa3,0x1e
-,0x00,0xb8,0x0a,0x80,0xe9,0x2c,0x02,0xe9,0x38,0xfc,0xff,0x06,0x90,0x34,0xbe,0x0a
-,0x00,0xc6,0x06,0xb6,0x34,0x01,0xf6,0x06,0x9d,0x36,0x80,0x75,0x05,0x83,0x0e,0xc2
-,0x34,0x01,0xcd,0x34,0xe9,0x0c,0xfc,0x83,0x3e,0xa3,0x36,0x03,0x75,0x09,0xc7,0x06
-,0x3d,0x37,0x05,0x00,0xe9,0xfc,0xfb,0xe5,0x02,0x0d,0x03,0x00,0x0d,0x00,0x88,0x0d
-,0x00,0x40,0x0d,0x00,0x04,0xe7,0x02,0xc7,0x06,0xa3,0x36,0x05,0x00,0xc6,0x06,0x9e
-,0x36,0xff,0xbe,0x02,0x00,0xe8,0xe1,0x01,0xb8,0x89,0x03,0xcd,0x3a,0xb8,0x9a,0x03
-,0xcd,0x3a,0xb8,0x99,0x03,0xcd,0x39,0xb8,0x97,0x03,0xcd,0x39,0xb8,0x98,0x03,0xcd
-,0x39,0xe9,0xbb,0x01,0x83,0x3e,0xa3,0x36,0x03,0x74,0x0a,0x83,0x3e,0xa3,0x36,0x04
-,0x74,0x03,0xe9,0xaa,0x01,0xbe,0x06,0x00,0xe8,0xae,0x01,0xb8,0x95,0x03,0xcd,0x39
-,0xe9,0x9c,0x01,0x83,0x3e,0xa3,0x36,0x05,0x74,0x03,0xe9,0x92,0x01,0xbe,0x02,0x00
-,0xe8,0x96,0x01,0xb8,0x99,0x03,0xcd,0x39,0xe9,0x84,0x01,0xc7,0x06,0x0f,0x37,0x05
-,0x00,0xe9,0x7b,0x01,0xe5,0x02,0x25,0xff,0xdf,0xe7,0x02,0xc7,0x06,0xa3,0x36,0x07
-,0x00,0xc7,0x06,0x0f,0x37,0x05,0x00,0xe9,0x65,0x01,0xe8,0xd5,0x04,0xc6,0x06,0x9d
-,0x36,0x00,0xc7,0x06,0x9b,0x36,0x00,0x00,0xc7,0x06,0x0f,0x37,0x05,0x00,0xc7,0x06
-,0xa8,0x02,0x00,0x00,0xc7,0x06,0x4c,0x37,0x01,0x00,0xe5,0x02,0x25,0xf9,0xff,0x0d
-,0x03,0x00,0x0d,0x00,0x88,0x25,0xef,0xff,0x0d,0x00,0x40,0x0d,0x00,0x04,0xe7,0x02
-,0xe9,0x67,0xfc,0xb8,0x9a,0x03,0xcd,0x39,0xf7,0x06,0xf4,0x33,0x00,0x10,0x75,0x09
-,0xc7,0x06,0x33,0x37,0x02,0x00,0xe9,0x16,0x01,0xff,0x0e,0x33,0x37,0x74,0x03,0xe9
-,0x0d,0x01,0xff,0x06,0x8e,0x34,0x83,0x0e,0xc2,0x34,0x08,0xc7,0x06,0x3d,0x37,0x03
-,0x00,0xe9,0xff,0xfa,0xc3,0x52,0x50,0xba,0xe0,0x00,0xb8,0x00,0x10,0xef,0x58,0x5a
-,0xc3,0xc7,0x06,0x3d,0x37,0x00,0x00,0xe9,0xe9,0xfa,0xfa,0xe8,0x54,0x04,0xb8,0x80
-,0x03,0x8e,0xc0,0x26,0xc7,0x06,0x04,0x00,0xd8,0x2b,0xb8,0x7f,0x03,0x8e,0xc0,0x26
-,0xc7,0x06,0x04,0x00,0xe8,0x2c,0x33,0xc0,0x8e,0xc0,0xa1,0xa7,0x36,0xa3,0xa9,0x36
-,0xa1,0xa9,0x36,0xe7,0x00,0xa1,0xab,0x36,0xe7,0x02,0xc7,0x06,0x05,0x37,0x00,0x00
-,0xc7,0x06,0x07,0x37,0x00,0x00,0xc7,0x06,0x09,0x37,0x00,0x00,0xc6,0x06,0x9d,0x36
-,0x00,0xc6,0x06,0x9e,0x36,0xff,0xc7,0x06,0x9b,0x36,0x00,0x00,0xc7,0x06,0xa3,0x36
-,0x00,0x00,0xc7,0x06,0x0f,0x37,0x00,0x00,0xc7,0x06,0xa8,0x02,0x00,0x00,0xc7,0x06
-,0x4c,0x37,0x01,0x00,0x81,0x26,0xaf,0x36,0xff,0xe7,0xa1,0xaf,0x36,0xe7,0x06,0xbb
-,0xff,0x7f,0xcd,0x53,0xe8,0x7c,0xf9,0xe5,0x56,0x0d,0x02,0x00,0xe7,0x56,0xfb,0xc3
-,0x8d,0x3e,0xc0,0x53,0x8d,0x36,0xf0,0x38,0xb9,0x0e,0x00,0x8b,0x1e,0x30,0x34,0x89
-,0x5c,0x02,0x2e,0x8b,0x45,0x02,0x89,0x44,0x06,0x2e,0x8b,0x05,0x89,0x44,0x04,0x83
-,0xc7,0x04,0x83,0xc6,0x10,0xe2,0xe8,0xb8,0x80,0x03,0x8e,0xc0,0x26,0xc7,0x06,0x04
-,0x00,0xe2,0x51,0xb8,0x7f,0x03,0x8e,0xc0,0x26,0xc7,0x06,0x04,0x00,0xb2,0x52,0x33
-,0xc0,0x8e,0xc0,0xc7,0x06,0xa1,0x36,0x01,0x00,0xc7,0x06,0x0f,0x37,0x05,0x00,0xc3
-,0x33,0xff,0x8e,0x06,0xa6,0x02,0x8b,0x36,0xa4,0x02,0x2e,0xff,0xa4,0xa0,0x53,0xe8
-,0x8c,0xdb,0xc3,0xe8,0x48,0xf7,0xe9,0xf6,0xff,0x8e,0x06,0x38,0x34,0xe8,0x07,0xe1
-,0x26,0xc7,0x06,0x04,0x00,0xdf,0x4f,0xcd,0x50,0xc3,0x26,0xc7,0x06,0x0a,0x00,0x00
-,0x00,0x26,0xff,0x26,0x04,0x00,0xcd,0x34,0xe9,0xd4,0xff,0xa1,0xd1,0x36,0x26,0x39
-,0x06,0x1a,0x00,0x75,0x22,0xa1,0xd3,0x36,0x26,0x39,0x06,0x1c,0x00,0x75,0x18,0xa1
-,0xd5,0x36,0x26,0x39,0x06,0x1e,0x00,0x75,0x0e,0x26,0xf7,0x06,0x0c,0x00,0x40,0x00
-,0x74,0x05,0x83,0x0e,0x66,0x37,0x40,0x81,0x0e,0xaf,0x36,0x00,0x10,0xa1,0xaf,0x36
-,0xe7,0x06,0x83,0x3e,0xa3,0x36,0x02,0x75,0x05,0xcd,0x34,0xe9,0x56,0xfb,0x83,0x3e
-,0xa3,0x36,0x00,0x74,0xb1,0x83,0x3e,0xa3,0x36,0x05,0x77,0xaa,0x26,0xf6,0x06,0x0a
-,0x00,0xff,0x75,0xa2,0xe8,0xfd,0xdd,0x50,0xf6,0x06,0x93,0x36,0x20,0x75,0x03,0xe9
-,0x8c,0x00,0x26,0xa1,0x0c,0x00,0x25,0x07,0x00,0x3d,0x07,0x00,0x75,0x03,0xe9,0x76
-,0x00,0x3d,0x05,0x00,0x75,0x03,0xe9,0x6e,0x00,0xf7,0x06,0xe6,0x34,0x18,0x80,0x75
-,0x03,0xe9,0x6a,0x00,0xf7,0x06,0xe6,0x34,0x00,0x80,0x74,0x35,0x26,0x80,0x3e,0x29
-,0x00,0x02,0x75,0x2d,0x51,0x56,0x57,0x8d,0x36,0x3e,0x34,0x8d,0x3e,0x20,0x00,0xb9
-,0x06,0x00,0xf3,0xa6,0x5f,0x5e,0x59,0x75,0x45,0x26,0xa1,0x20,0x00,0xa3,0x3e,0x34
-,0x26,0xa1,0x22,0x00,0xa3,0x40,0x34,0x26,0xa1,0x24,0x00,0xa3,0x42,0x34,0xe9,0x26
-,0x00,0xf7,0x06,0xe6,0x34,0x08,0x00,0x74,0x0b,0x26,0x80,0x3e,0x19,0x00,0x00,0x74
-,0x03,0xe9,0x13,0x00,0xf7,0x06,0xe6,0x34,0x10,0x00,0x74,0x12,0x26,0xa0,0x28,0x00
-,0xc0,0xe8,0x04,0x22,0xc0,0x74,0x07,0x26,0xc7,0x06,0x04,0x00,0xff,0xff,0x58,0x23
-,0xc0,0x74,0x03,0xe9,0xdd,0xfe,0x81,0x26,0x9b,0x36,0xff,0xfe,0x26,0xa1,0x20,0x00
-,0x3b,0x06,0xd1,0x36,0x75,0x1a,0x26,0xa1,0x22,0x00,0x3b,0x06,0xd3,0x36,0x75,0x10
-,0x26,0xa1,0x24,0x00,0x3b,0x06,0xd5,0x36,0x75,0x06,0x81,0x0e,0x9b,0x36,0x00,0x01
-,0x26,0xa1,0x20,0x00,0x25,0x7f,0xff,0xa3,0xb8,0x34,0x26,0xa1,0x22,0x00,0xa3,0xba
-,0x34,0x26,0xa1,0x24,0x00,0xa3,0xbc,0x34,0x8b,0xc6,0x86,0xc4,0xa3,0xc0,0x34,0xd1
-,0xe6,0x80,0xfc,0x09,0x74,0x03,0xe8,0xf6,0xf5,0xa1,0x05,0x37,0x0b,0x06,0x07,0x37
-,0x0b,0x06,0x09,0x37,0x74,0x3e,0x26,0xa1,0x20,0x00,0x3b,0x06,0x05,0x37,0x75,0x17
-,0x26,0xa1,0x22,0x00,0x3b,0x06,0x07,0x37,0x75,0x0d,0x26,0xa1,0x24,0x00,0x3b,0x06
-,0x09,0x37,0x75,0x03,0xe9,0x1d,0x00,0x26,0xa0,0x28,0x00,0x24,0x0f,0x3c,0x03,0x74
-,0x1b,0x3c,0x00,0x75,0x0f,0x83,0x3e,0xa3,0x36,0x04,0x74,0x10,0xf7,0x06,0x9b,0x36
-,0x00,0x01,0x74,0x08,0x2e,0xff,0x94,0xf8,0x53,0xe9,0x33,0xfe,0xcd,0x34,0xc7,0x06
-,0x3d,0x37,0x01,0x00,0xe9,0x2c,0xf8,0x83,0x3e,0xa3,0x36,0x05,0x74,0x10,0x83,0x3e
-,0xa3,0x36,0x01,0x7e,0x09,0x83,0xee,0x16,0x2e,0xff,0x94,0x24,0x54,0xc3,0xcd,0x34
-,0xc3,0x26,0xa1,0x0c,0x00,0x3d,0xff,0x7f,0x74,0x05,0x26,0xff,0x26,0x04,0x00,0xe9
-,0xfd,0xfd,0xa1,0xf4,0x33,0xa9,0x00,0x88,0x74,0x0b,0xa9,0x00,0x10,0x75,0x09,0x8b
-,0x1e,0x43,0x37,0xff,0xe3,0xe9,0x97,0x00,0xc7,0x06,0x35,0x37,0x05,0x00,0xc7,0x06
-,0x43,0x37,0x28,0x52,0xf7,0x06,0xf4,0x33,0x00,0x08,0x74,0x06,0xc7,0x06,0x43,0x37
-,0x1a,0x52,0xb8,0x80,0x03,0xcd,0x39,0xe9,0xc5,0xfd,0xa9,0x00,0x08,0x74,0xd9,0xff
-,0x0e,0x35,0x37,0x75,0xed,0xe9,0x30,0x00,0xa9,0x00,0x08,0x75,0xcb,0xff,0x0e,0x35
-,0x37,0x75,0xdf,0x81,0x0e,0xc2,0x34,0xc0,0x00,0xf6,0x06,0x9d,0x36,0x80,0x74,0x0f
-,0x81,0x0e,0x9b,0x36,0x00,0x80,0xc7,0x06,0x0f,0x37,0x02,0x00,0xe9,0x90,0xfd,0xc7
-,0x06,0x3d,0x37,0x02,0x00,0xe9,0x8b,0xf7,0x80,0x26,0x9e,0x36,0xff,0x75,0x30,0xf6
-,0x06,0x9d,0x36,0x80,0x74,0x20,0xff,0x06,0x94,0x34,0x83,0x0e,0x66,0x37,0x20,0x8e
-,0x06,0x30,0x34,0x26,0xf7,0x06,0x0a,0x00,0x00,0x01,0x74,0x07,0x26,0x81,0x0e,0x08
-,0x00,0x00,0x01,0xe9,0x09,0x00,0xc7,0x06,0x3d,0x37,0x04,0x00,0xe9,0x54,0xf7,0x81
-,0x0e,0xaf,0x36,0x00,0x08,0xa1,0xaf,0x36,0xe7,0x06,0xe5,0x0a,0xa9,0x00,0x80,0x74
-,0x0e,0x81,0x26,0xaf,0x36,0xff,0xf7,0xa1,0xaf,0x36,0xe7,0x06,0xe9,0x49,0xff,0xe9
-,0x2d,0xfd,0xc7,0x06,0x41,0x37,0x00,0x00,0xbe,0x29,0x00,0xe8,0x2b,0xfd,0xe9,0x1e
-,0xfd,0xcd,0x34,0x83,0x3e,0xa3,0x36,0x04,0x77,0x09,0xc7,0x06,0x3d,0x37,0x01,0x00
-,0xe9,0x10,0xf7,0xe9,0x09,0xfd,0xcd,0x34,0xc3,0xc7,0x06,0x9b,0x36,0x00,0x00,0xe8
-,0x0c,0xf5,0x81,0x26,0xaf,0x36,0xff,0xe7,0xa1,0xaf,0x36,0xe7,0x06,0x81,0x26,0x9b
-,0x36,0xff,0x7f,0xe5,0x02,0x0d,0x01,0x00,0x25,0xef,0xff,0x25,0xff,0xdf,0xe7,0x02
-,0xbb,0xff,0x7f,0xcd,0x53,0x33,0xc0,0xa3,0x9d,0x36,0xa3,0x9f,0x36,0xe8,0x20,0xf3
-,0xe8,0x43,0xf3,0x83,0x0e,0x9b,0x36,0x10,0xc7,0x06,0x99,0x36,0x00,0x00,0xe8,0xd2
-,0xf5,0xe5,0x56,0x0d,0x02,0x00,0xe7,0x56,0xc7,0x06,0xa8,0x02,0x00,0x00,0xbe,0x00
-,0x00,0xe8,0x30,0xf5,0xc6,0x06,0xa0,0x36,0x0e,0xb8,0x9c,0x03,0xcd,0x39,0xb8,0x80
-,0x00,0xcd,0x35,0xc7,0x06,0xaa,0x02,0xff,0xff,0xc7,0x06,0xa1,0x36,0x01,0x00,0xe9
-,0xa5,0xf6,0x06,0xb8,0x8f,0x03,0xcd,0x3a,0xb8,0x90,0x03,0xcd,0x3a,0xb8,0x91,0x03
-,0xcd,0x3a,0xb8,0x92,0x03,0xcd,0x3a,0xb8,0x93,0x03,0xcd,0x3a,0xb8,0x94,0x03,0xcd
-,0x3a,0xb8,0x95,0x03,0xcd,0x3a,0xb8,0x96,0x03,0xcd,0x3a,0xb8,0x97,0x03,0xcd,0x3a
-,0xb8,0x98,0x03,0xcd,0x3a,0xb8,0x99,0x03,0xcd,0x3a,0xb8,0x9a,0x03,0xcd,0x3a,0xb8
-,0x9b,0x03,0xcd,0x3a,0xb8,0x7f,0x03,0xcd,0x3a,0xb8,0x80,0x03,0xcd,0x3a,0x07,0xc3
-,0xf7,0x49,0xf1,0x4e,0xdf,0x4f,0xdf,0x4f,0xdf,0x4f,0xdf,0x4f,0xf8,0x51,0xdf,0x4f
-,0xfa,0x4f,0x0b,0x50,0xd1,0x51,0xdf,0x4f,0xdf,0x4f,0xdf,0x4f,0xdf,0x4f,0xdf,0x4f
-,0xe4,0x4e,0x06,0x00,0xcd,0x4a,0x04,0x00,0xe4,0x4e,0x19,0x00,0xad,0x4b,0xfa,0x00
-,0x82,0x4c,0x08,0x07,0x09,0x4c,0x14,0x00,0x24,0x4e,0x64,0x00,0xd7,0x4d,0xf4,0x01
-,0x64,0x4e,0xbc,0x02,0x7a,0x4e,0xe8,0x03,0x43,0x4e,0x02,0x00,0xb3,0x4e,0xf4,0x01
-,0x5b,0x4e,0xf4,0x01,0xe5,0x4e,0x14,0x00,0x06,0x50,0x06,0x50,0x95,0x4c,0xc1,0x52
-,0xc1,0x52,0xfe,0x4c,0xda,0x4c,0x06,0x50,0x06,0x50,0x06,0x50,0x06,0x50,0xb7,0x51
-,0xb7,0x51,0xb7,0x51,0xb7,0x51,0xb7,0x51,0xb7,0x51,0x06,0x50,0xd5,0x4a,0x06,0x50
-,0x1d,0x4c,0x06,0x50,0x83,0x4d,0x1f,0x4d,0x1f,0x4d,0xed,0x40,0xfa,0x40,0x07,0x41
-,0x37,0x37,0x2e,0x37,0x37,0x20,0x20,0x79,0x79,0x2f,0x79,0x79,0x2f,0x79,0x79,0x20
-,0x30,0x31,0x2e,0x39,0x30,0x20,0x20,0x30,0x32,0x2f,0x31,0x37,0x2f,0x39,0x39,0x20
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00
-,0x90,0xea,0xc0,0x15,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x00,0x13,0x06
-} ;  
diff --git a/drivers/net/ucc_geth.c b/drivers/net/ucc_geth.c
index 933fcfbf35e1..d3f39e86eb95 100644
--- a/drivers/net/ucc_geth.c
+++ b/drivers/net/ucc_geth.c
@@ -24,7 +24,6 @@
 #include <linux/spinlock.h>
 #include <linux/mm.h>
 #include <linux/dma-mapping.h>
-#include <linux/fsl_devices.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
 #include <linux/workqueue.h>
@@ -223,10 +222,10 @@ static struct sk_buff *get_new_skb(struct ucc_geth_private *ugeth,
 		    (((unsigned)skb->data) & (UCC_GETH_RX_DATA_BUF_ALIGNMENT -
 					      1)));
 
-	skb->dev = ugeth->dev;
+	skb->dev = ugeth->ndev;
 
 	out_be32(&((struct qe_bd __iomem *)bd)->buf,
-		      dma_map_single(&ugeth->dev->dev,
+		      dma_map_single(ugeth->dev,
 				     skb->data,
 				     ugeth->ug_info->uf_info.max_rx_buf_length +
 				     UCC_GETH_RX_DATA_BUF_ALIGNMENT,
@@ -1872,7 +1871,7 @@ static void ucc_geth_memclean(struct ucc_geth_private *ugeth)
 			continue;
 		for (j = 0; j < ugeth->ug_info->bdRingLenTx[i]; j++) {
 			if (ugeth->tx_skbuff[i][j]) {
-				dma_unmap_single(&ugeth->dev->dev,
+				dma_unmap_single(ugeth->dev,
 						 in_be32(&((struct qe_bd __iomem *)bd)->buf),
 						 (in_be32((u32 __iomem *)bd) &
 						  BD_LENGTH_MASK),
@@ -1900,7 +1899,7 @@ static void ucc_geth_memclean(struct ucc_geth_private *ugeth)
 			bd = ugeth->p_rx_bd_ring[i];
 			for (j = 0; j < ugeth->ug_info->bdRingLenRx[i]; j++) {
 				if (ugeth->rx_skbuff[i][j]) {
-					dma_unmap_single(&ugeth->dev->dev,
+					dma_unmap_single(ugeth->dev,
 						in_be32(&((struct qe_bd __iomem *)bd)->buf),
 						ugeth->ug_info->
 						uf_info.max_rx_buf_length +
@@ -3071,7 +3070,7 @@ static int ucc_geth_start_xmit(struct sk_buff *skb, struct net_device *dev)
 
 	/* set up the buffer descriptor */
 	out_be32(&((struct qe_bd __iomem *)bd)->buf,
-		      dma_map_single(&ugeth->dev->dev, skb->data,
+		      dma_map_single(ugeth->dev, skb->data,
 			      skb->len, DMA_TO_DEVICE));
 
 	/* printk(KERN_DEBUG"skb->data is 0x%x\n",skb->data); */
@@ -3127,7 +3126,7 @@ static int ucc_geth_rx(struct ucc_geth_private *ugeth, u8 rxQ, int rx_work_limit
 
 	ugeth_vdbg("%s: IN", __func__);
 
-	dev = ugeth->dev;
+	dev = ugeth->ndev;
 
 	/* collect received buffers */
 	bd = ugeth->rxBd[rxQ];
@@ -3161,7 +3160,7 @@ static int ucc_geth_rx(struct ucc_geth_private *ugeth, u8 rxQ, int rx_work_limit
 			skb_put(skb, length);
 
 			/* Tell the skb what kind of packet this is */
-			skb->protocol = eth_type_trans(skb, ugeth->dev);
+			skb->protocol = eth_type_trans(skb, ugeth->ndev);
 
 			dev->stats.rx_bytes += length;
 			/* Send the packet up the stack */
@@ -3432,7 +3431,7 @@ static int ucc_geth_close(struct net_device *dev)
 
 	ucc_geth_stop(ugeth);
 
-	free_irq(ugeth->ug_info->uf_info.irq, ugeth->dev);
+	free_irq(ugeth->ug_info->uf_info.irq, ugeth->ndev);
 
 	netif_stop_queue(dev);
 
@@ -3446,7 +3445,7 @@ static void ucc_geth_timeout_work(struct work_struct *work)
 	struct net_device *dev;
 
 	ugeth = container_of(work, struct ucc_geth_private, timeout_work);
-	dev = ugeth->dev;
+	dev = ugeth->ndev;
 
 	ugeth_vdbg("%s: IN", __func__);
 
@@ -3756,7 +3755,8 @@ static int ucc_geth_probe(struct of_device* ofdev, const struct of_device_id *ma
 		memcpy(dev->dev_addr, mac_addr, 6);
 
 	ugeth->ug_info = ug_info;
-	ugeth->dev = dev;
+	ugeth->dev = device;
+	ugeth->ndev = dev;
 	ugeth->node = np;
 
 	return 0;
diff --git a/drivers/net/ucc_geth.h b/drivers/net/ucc_geth.h
index e3a25e64a652..2f8ee7c87efe 100644
--- a/drivers/net/ucc_geth.h
+++ b/drivers/net/ucc_geth.h
@@ -20,7 +20,6 @@
 
 #include <linux/kernel.h>
 #include <linux/list.h>
-#include <linux/fsl_devices.h>
 
 #include <asm/immap_qe.h>
 #include <asm/qe.h>
@@ -1129,7 +1128,8 @@ struct ucc_geth_info {
 struct ucc_geth_private {
 	struct ucc_geth_info *ug_info;
 	struct ucc_fast_private *uccf;
-	struct net_device *dev;
+	struct device *dev;
+	struct net_device *ndev;
 	struct napi_struct napi;
 	struct work_struct timeout_work;
 	struct ucc_geth __iomem *ug_regs;
diff --git a/drivers/net/ucc_geth_ethtool.c b/drivers/net/ucc_geth_ethtool.c
index a755bea559b9..6fcb500257bc 100644
--- a/drivers/net/ucc_geth_ethtool.c
+++ b/drivers/net/ucc_geth_ethtool.c
@@ -28,7 +28,6 @@
 #include <linux/mm.h>
 #include <linux/delay.h>
 #include <linux/dma-mapping.h>
-#include <linux/fsl_devices.h>
 #include <linux/ethtool.h>
 #include <linux/mii.h>
 #include <linux/phy.h>
diff --git a/drivers/net/usb/hso.c b/drivers/net/usb/hso.c
index cde423c6d040..f84b78d94c40 100644
--- a/drivers/net/usb/hso.c
+++ b/drivers/net/usb/hso.c
@@ -5,6 +5,7 @@
  *  Copyright (C) 2008 Option International
  *                     Filip Aben <f.aben@option.com>
  *                     Denis Joseph Barrow <d.barow@option.com>
+ *                     Jan Dumon <j.dumon@option.com>
  *  Copyright (C) 2007 Andrew Bird (Sphere Systems Ltd)
  *  			<ajb@spheresystems.co.uk>
  *  Copyright (C) 2008 Greg Kroah-Hartman <gregkh@suse.de>
@@ -462,9 +463,16 @@ static const struct usb_device_id hso_ids[] = {
 	{USB_DEVICE(0x0af0, 0x7701)},
 	{USB_DEVICE(0x0af0, 0x7801)},
 	{USB_DEVICE(0x0af0, 0x7901)},
-	{USB_DEVICE(0x0af0, 0x7361)},
-	{USB_DEVICE(0x0af0, 0xd057)},
+	{USB_DEVICE(0x0af0, 0x8200)},
+	{USB_DEVICE(0x0af0, 0x8201)},
+	{USB_DEVICE(0x0af0, 0xd035)},
 	{USB_DEVICE(0x0af0, 0xd055)},
+	{USB_DEVICE(0x0af0, 0xd155)},
+	{USB_DEVICE(0x0af0, 0xd255)},
+	{USB_DEVICE(0x0af0, 0xd057)},
+	{USB_DEVICE(0x0af0, 0xd157)},
+	{USB_DEVICE(0x0af0, 0xd257)},
+	{USB_DEVICE(0x0af0, 0xd357)},
 	{}
 };
 MODULE_DEVICE_TABLE(usb, hso_ids);
@@ -2410,20 +2418,22 @@ static void hso_free_net_device(struct hso_device *hso_dev)
 	if (!hso_net)
 		return;
 
+	remove_net_device(hso_net->parent);
+
+	if (hso_net->net) {
+		unregister_netdev(hso_net->net);
+		free_netdev(hso_net->net);
+	}
+
 	/* start freeing */
 	for (i = 0; i < MUX_BULK_RX_BUF_COUNT; i++) {
 		usb_free_urb(hso_net->mux_bulk_rx_urb_pool[i]);
 		kfree(hso_net->mux_bulk_rx_buf_pool[i]);
+		hso_net->mux_bulk_rx_buf_pool[i] = NULL;
 	}
 	usb_free_urb(hso_net->mux_bulk_tx_urb);
 	kfree(hso_net->mux_bulk_tx_buf);
-
-	remove_net_device(hso_net->parent);
-
-	if (hso_net->net) {
-		unregister_netdev(hso_net->net);
-		free_netdev(hso_net->net);
-	}
+	hso_net->mux_bulk_tx_buf = NULL;
 
 	kfree(hso_dev);
 }
@@ -2526,14 +2536,15 @@ static void hso_create_rfkill(struct hso_device *hso_dev,
 }
 
 /* Creates our network device */
-static struct hso_device *hso_create_net_device(struct usb_interface *interface)
+static struct hso_device *hso_create_net_device(struct usb_interface *interface,
+						int port_spec)
 {
 	int result, i;
 	struct net_device *net;
 	struct hso_net *hso_net;
 	struct hso_device *hso_dev;
 
-	hso_dev = hso_create_device(interface, HSO_INTF_MUX | HSO_PORT_NETWORK);
+	hso_dev = hso_create_device(interface, port_spec);
 	if (!hso_dev)
 		return NULL;
 
@@ -2613,12 +2624,12 @@ static void hso_free_tiomget(struct hso_serial *serial)
 {
 	struct hso_tiocmget *tiocmget = serial->tiocmget;
 	if (tiocmget) {
-		kfree(tiocmget);
 		if (tiocmget->urb) {
 			usb_free_urb(tiocmget->urb);
 			tiocmget->urb = NULL;
 		}
 		serial->tiocmget = NULL;
+		kfree(tiocmget);
 
 	}
 }
@@ -2933,7 +2944,8 @@ static int hso_probe(struct usb_interface *interface,
 		if ((port_spec & HSO_PORT_MASK) == HSO_PORT_NETWORK) {
 			/* Create the network device */
 			if (!disable_net) {
-				hso_dev = hso_create_net_device(interface);
+				hso_dev = hso_create_net_device(interface,
+								port_spec);
 				if (!hso_dev)
 					goto exit;
 				tmp_dev = hso_dev;
@@ -2965,7 +2977,7 @@ static int hso_probe(struct usb_interface *interface,
 		/* It's a regular bulk interface */
 		if (((port_spec & HSO_PORT_MASK) == HSO_PORT_NETWORK)
 		    && !disable_net)
-			hso_dev = hso_create_net_device(interface);
+			hso_dev = hso_create_net_device(interface, port_spec);
 		else
 			hso_dev =
 			    hso_create_bulk_serial_device(interface, port_spec);
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index 7cb10a0a5316..3d0d0b0b37c5 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -36,7 +36,6 @@
  * Run test procedures
  * Fix bugs from previous two steps
  * Snoop other OSs for any tricks we're not doing
- * SMP locking
  * Reduce arbitrary timeouts
  * Smart multicast support
  * Temporary MAC change support
@@ -796,7 +795,7 @@ static int kaweth_start_xmit(struct sk_buff *skb, struct net_device *net)
 
 	int res;
 
-	spin_lock(&kaweth->device_lock);
+	spin_lock_irq(&kaweth->device_lock);
 
 	kaweth_async_set_rx_mode(kaweth);
 	netif_stop_queue(net);
@@ -814,7 +813,7 @@ static int kaweth_start_xmit(struct sk_buff *skb, struct net_device *net)
 		if (!copied_skb) {
 			kaweth->stats.tx_errors++;
 			netif_start_queue(net);
-			spin_unlock(&kaweth->device_lock);
+			spin_unlock_irq(&kaweth->device_lock);
 			return 0;
 		}
 	}
@@ -848,7 +847,7 @@ skip:
 		net->trans_start = jiffies;
 	}
 
-	spin_unlock(&kaweth->device_lock);
+	spin_unlock_irq(&kaweth->device_lock);
 
 	return 0;
 }
diff --git a/drivers/net/vxge/Makefile b/drivers/net/vxge/Makefile
new file mode 100644
index 000000000000..8992ca26b277
--- /dev/null
+++ b/drivers/net/vxge/Makefile
@@ -0,0 +1,7 @@
+#
+# Makefile for Neterion Inc's X3100 Series 10 GbE PCIe # I/O
+# Virtualized Server Adapter linux driver
+
+obj-$(CONFIG_VXGE) += vxge.o
+
+vxge-objs := vxge-config.o vxge-traffic.o vxge-ethtool.o vxge-main.o
diff --git a/drivers/net/vxge/vxge-config.c b/drivers/net/vxge/vxge-config.c
new file mode 100644
index 000000000000..6b41c884a337
--- /dev/null
+++ b/drivers/net/vxge/vxge-config.c
@@ -0,0 +1,5264 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-config.c: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *                Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#include <linux/vmalloc.h>
+#include <linux/etherdevice.h>
+#include <linux/pci.h>
+#include <linux/pci_hotplug.h>
+
+#include "vxge-traffic.h"
+#include "vxge-config.h"
+
+/*
+ * __vxge_hw_channel_allocate - Allocate memory for channel
+ * This function allocates required memory for the channel and various arrays
+ * in the channel
+ */
+struct __vxge_hw_channel*
+__vxge_hw_channel_allocate(struct __vxge_hw_vpath_handle *vph,
+			   enum __vxge_hw_channel_type type,
+	u32 length, u32 per_dtr_space, void *userdata)
+{
+	struct __vxge_hw_channel *channel;
+	struct __vxge_hw_device *hldev;
+	int size = 0;
+	u32 vp_id;
+
+	hldev = vph->vpath->hldev;
+	vp_id = vph->vpath->vp_id;
+
+	switch (type) {
+	case VXGE_HW_CHANNEL_TYPE_FIFO:
+		size = sizeof(struct __vxge_hw_fifo);
+		break;
+	case VXGE_HW_CHANNEL_TYPE_RING:
+		size = sizeof(struct __vxge_hw_ring);
+		break;
+	default:
+		break;
+	}
+
+	channel = kzalloc(size, GFP_KERNEL);
+	if (channel == NULL)
+		goto exit0;
+	INIT_LIST_HEAD(&channel->item);
+
+	channel->common_reg = hldev->common_reg;
+	channel->first_vp_id = hldev->first_vp_id;
+	channel->type = type;
+	channel->devh = hldev;
+	channel->vph = vph;
+	channel->userdata = userdata;
+	channel->per_dtr_space = per_dtr_space;
+	channel->length = length;
+	channel->vp_id = vp_id;
+
+	channel->work_arr = kzalloc(sizeof(void *)*length, GFP_KERNEL);
+	if (channel->work_arr == NULL)
+		goto exit1;
+
+	channel->free_arr = kzalloc(sizeof(void *)*length, GFP_KERNEL);
+	if (channel->free_arr == NULL)
+		goto exit1;
+	channel->free_ptr = length;
+
+	channel->reserve_arr = kzalloc(sizeof(void *)*length, GFP_KERNEL);
+	if (channel->reserve_arr == NULL)
+		goto exit1;
+	channel->reserve_ptr = length;
+	channel->reserve_top = 0;
+
+	channel->orig_arr = kzalloc(sizeof(void *)*length, GFP_KERNEL);
+	if (channel->orig_arr == NULL)
+		goto exit1;
+
+	return channel;
+exit1:
+	__vxge_hw_channel_free(channel);
+
+exit0:
+	return NULL;
+}
+
+/*
+ * __vxge_hw_channel_free - Free memory allocated for channel
+ * This function deallocates memory from the channel and various arrays
+ * in the channel
+ */
+void __vxge_hw_channel_free(struct __vxge_hw_channel *channel)
+{
+	kfree(channel->work_arr);
+	kfree(channel->free_arr);
+	kfree(channel->reserve_arr);
+	kfree(channel->orig_arr);
+	kfree(channel);
+}
+
+/*
+ * __vxge_hw_channel_initialize - Initialize a channel
+ * This function initializes a channel by properly setting the
+ * various references
+ */
+enum vxge_hw_status
+__vxge_hw_channel_initialize(struct __vxge_hw_channel *channel)
+{
+	u32 i;
+	struct __vxge_hw_virtualpath *vpath;
+
+	vpath = channel->vph->vpath;
+
+	if ((channel->reserve_arr != NULL) && (channel->orig_arr != NULL)) {
+		for (i = 0; i < channel->length; i++)
+			channel->orig_arr[i] = channel->reserve_arr[i];
+	}
+
+	switch (channel->type) {
+	case VXGE_HW_CHANNEL_TYPE_FIFO:
+		vpath->fifoh = (struct __vxge_hw_fifo *)channel;
+		channel->stats = &((struct __vxge_hw_fifo *)
+				channel)->stats->common_stats;
+		break;
+	case VXGE_HW_CHANNEL_TYPE_RING:
+		vpath->ringh = (struct __vxge_hw_ring *)channel;
+		channel->stats = &((struct __vxge_hw_ring *)
+				channel)->stats->common_stats;
+		break;
+	default:
+		break;
+	}
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_channel_reset - Resets a channel
+ * This function resets a channel by properly setting the various references
+ */
+enum vxge_hw_status
+__vxge_hw_channel_reset(struct __vxge_hw_channel *channel)
+{
+	u32 i;
+
+	for (i = 0; i < channel->length; i++) {
+		if (channel->reserve_arr != NULL)
+			channel->reserve_arr[i] = channel->orig_arr[i];
+		if (channel->free_arr != NULL)
+			channel->free_arr[i] = NULL;
+		if (channel->work_arr != NULL)
+			channel->work_arr[i] = NULL;
+	}
+	channel->free_ptr = channel->length;
+	channel->reserve_ptr = channel->length;
+	channel->reserve_top = 0;
+	channel->post_index = 0;
+	channel->compl_index = 0;
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_device_pci_e_init
+ * Initialize certain PCI/PCI-X configuration registers
+ * with recommended values. Save config space for future hw resets.
+ */
+void
+__vxge_hw_device_pci_e_init(struct __vxge_hw_device *hldev)
+{
+	u16 cmd = 0;
+
+	/* Set the PErr Repconse bit and SERR in PCI command register. */
+	pci_read_config_word(hldev->pdev, PCI_COMMAND, &cmd);
+	cmd |= 0x140;
+	pci_write_config_word(hldev->pdev, PCI_COMMAND, cmd);
+
+	pci_save_state(hldev->pdev);
+
+	return;
+}
+
+/*
+ * __vxge_hw_device_register_poll
+ * Will poll certain register for specified amount of time.
+ * Will poll until masked bit is not cleared.
+ */
+enum vxge_hw_status
+__vxge_hw_device_register_poll(void __iomem *reg, u64 mask, u32 max_millis)
+{
+	u64 val64;
+	u32 i = 0;
+	enum vxge_hw_status ret = VXGE_HW_FAIL;
+
+	udelay(10);
+
+	do {
+		val64 = readq(reg);
+		if (!(val64 & mask))
+			return VXGE_HW_OK;
+		udelay(100);
+	} while (++i <= 9);
+
+	i = 0;
+	do {
+		val64 = readq(reg);
+		if (!(val64 & mask))
+			return VXGE_HW_OK;
+		mdelay(1);
+	} while (++i <= max_millis);
+
+	return ret;
+}
+
+ /* __vxge_hw_device_vpath_reset_in_prog_check - Check if vpath reset
+ * in progress
+ * This routine checks the vpath reset in progress register is turned zero
+ */
+enum vxge_hw_status
+__vxge_hw_device_vpath_reset_in_prog_check(u64 __iomem *vpath_rst_in_prog)
+{
+	enum vxge_hw_status status;
+	status = __vxge_hw_device_register_poll(vpath_rst_in_prog,
+			VXGE_HW_VPATH_RST_IN_PROG_VPATH_RST_IN_PROG(0x1ffff),
+			VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+	return status;
+}
+
+/*
+ * __vxge_hw_device_toc_get
+ * This routine sets the swapper and reads the toc pointer and returns the
+ * memory mapped address of the toc
+ */
+struct vxge_hw_toc_reg __iomem *
+__vxge_hw_device_toc_get(void __iomem *bar0)
+{
+	u64 val64;
+	struct vxge_hw_toc_reg __iomem *toc = NULL;
+	enum vxge_hw_status status;
+
+	struct vxge_hw_legacy_reg __iomem *legacy_reg =
+		(struct vxge_hw_legacy_reg __iomem *)bar0;
+
+	status = __vxge_hw_legacy_swapper_set(legacy_reg);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 =	readq(&legacy_reg->toc_first_pointer);
+	toc = (struct vxge_hw_toc_reg __iomem *)(bar0+val64);
+exit:
+	return toc;
+}
+
+/*
+ * __vxge_hw_device_reg_addr_get
+ * This routine sets the swapper and reads the toc pointer and initializes the
+ * register location pointers in the device object. It waits until the ric is
+ * completed initializing registers.
+ */
+enum vxge_hw_status
+__vxge_hw_device_reg_addr_get(struct __vxge_hw_device *hldev)
+{
+	u64 val64;
+	u32 i;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	hldev->legacy_reg = (struct vxge_hw_legacy_reg __iomem *)hldev->bar0;
+
+	hldev->toc_reg = __vxge_hw_device_toc_get(hldev->bar0);
+	if (hldev->toc_reg  == NULL) {
+		status = VXGE_HW_FAIL;
+		goto exit;
+	}
+
+	val64 = readq(&hldev->toc_reg->toc_common_pointer);
+	hldev->common_reg =
+	(struct vxge_hw_common_reg __iomem *)(hldev->bar0 + val64);
+
+	val64 = readq(&hldev->toc_reg->toc_mrpcim_pointer);
+	hldev->mrpcim_reg =
+		(struct vxge_hw_mrpcim_reg __iomem *)(hldev->bar0 + val64);
+
+	for (i = 0; i < VXGE_HW_TITAN_SRPCIM_REG_SPACES; i++) {
+		val64 = readq(&hldev->toc_reg->toc_srpcim_pointer[i]);
+		hldev->srpcim_reg[i] =
+			(struct vxge_hw_srpcim_reg __iomem *)
+				(hldev->bar0 + val64);
+	}
+
+	for (i = 0; i < VXGE_HW_TITAN_VPMGMT_REG_SPACES; i++) {
+		val64 = readq(&hldev->toc_reg->toc_vpmgmt_pointer[i]);
+		hldev->vpmgmt_reg[i] =
+		(struct vxge_hw_vpmgmt_reg __iomem *)(hldev->bar0 + val64);
+	}
+
+	for (i = 0; i < VXGE_HW_TITAN_VPATH_REG_SPACES; i++) {
+		val64 = readq(&hldev->toc_reg->toc_vpath_pointer[i]);
+		hldev->vpath_reg[i] =
+			(struct vxge_hw_vpath_reg __iomem *)
+				(hldev->bar0 + val64);
+	}
+
+	val64 = readq(&hldev->toc_reg->toc_kdfc);
+
+	switch (VXGE_HW_TOC_GET_KDFC_INITIAL_BIR(val64)) {
+	case 0:
+		hldev->kdfc = (u8 __iomem *)(hldev->bar0 +
+			VXGE_HW_TOC_GET_KDFC_INITIAL_OFFSET(val64));
+		break;
+	case 2:
+		hldev->kdfc = (u8 __iomem *)(hldev->bar1 +
+			VXGE_HW_TOC_GET_KDFC_INITIAL_OFFSET(val64));
+		break;
+	case 4:
+		hldev->kdfc = (u8 __iomem *)(hldev->bar2 +
+			VXGE_HW_TOC_GET_KDFC_INITIAL_OFFSET(val64));
+		break;
+	default:
+		break;
+	}
+
+	status = __vxge_hw_device_vpath_reset_in_prog_check(
+			(u64 __iomem *)&hldev->common_reg->vpath_rst_in_prog);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_device_id_get
+ * This routine returns sets the device id and revision numbers into the device
+ * structure
+ */
+void __vxge_hw_device_id_get(struct __vxge_hw_device *hldev)
+{
+	u64 val64;
+
+	val64 = readq(&hldev->common_reg->titan_asic_id);
+	hldev->device_id =
+		(u16)VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_DEVICE_ID(val64);
+
+	hldev->major_revision =
+		(u8)VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_MAJOR_REVISION(val64);
+
+	hldev->minor_revision =
+		(u8)VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_MINOR_REVISION(val64);
+
+	return;
+}
+
+/*
+ * __vxge_hw_device_access_rights_get: Get Access Rights of the driver
+ * This routine returns the Access Rights of the driver
+ */
+static u32
+__vxge_hw_device_access_rights_get(u32 host_type, u32 func_id)
+{
+	u32 access_rights = VXGE_HW_DEVICE_ACCESS_RIGHT_VPATH;
+
+	switch (host_type) {
+	case VXGE_HW_NO_MR_NO_SR_NORMAL_FUNCTION:
+		if (func_id == 0) {
+			access_rights |= VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM |
+					VXGE_HW_DEVICE_ACCESS_RIGHT_SRPCIM;
+		}
+		break;
+	case VXGE_HW_MR_NO_SR_VH0_BASE_FUNCTION:
+		access_rights |= VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM |
+				VXGE_HW_DEVICE_ACCESS_RIGHT_SRPCIM;
+		break;
+	case VXGE_HW_NO_MR_SR_VH0_FUNCTION0:
+		access_rights |= VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM |
+				VXGE_HW_DEVICE_ACCESS_RIGHT_SRPCIM;
+		break;
+	case VXGE_HW_NO_MR_SR_VH0_VIRTUAL_FUNCTION:
+	case VXGE_HW_SR_VH_VIRTUAL_FUNCTION:
+	case VXGE_HW_MR_SR_VH0_INVALID_CONFIG:
+		break;
+	case VXGE_HW_SR_VH_FUNCTION0:
+	case VXGE_HW_VH_NORMAL_FUNCTION:
+		access_rights |= VXGE_HW_DEVICE_ACCESS_RIGHT_SRPCIM;
+		break;
+	}
+
+	return access_rights;
+}
+/*
+ * __vxge_hw_device_host_info_get
+ * This routine returns the host type assignments
+ */
+void __vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev)
+{
+	u64 val64;
+	u32 i;
+
+	val64 = readq(&hldev->common_reg->host_type_assignments);
+
+	hldev->host_type =
+	   (u32)VXGE_HW_HOST_TYPE_ASSIGNMENTS_GET_HOST_TYPE_ASSIGNMENTS(val64);
+
+	hldev->vpath_assignments = readq(&hldev->common_reg->vpath_assignments);
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!(hldev->vpath_assignments & vxge_mBIT(i)))
+			continue;
+
+		hldev->func_id =
+			__vxge_hw_vpath_func_id_get(i, hldev->vpmgmt_reg[i]);
+
+		hldev->access_rights = __vxge_hw_device_access_rights_get(
+			hldev->host_type, hldev->func_id);
+
+		hldev->first_vp_id = i;
+		break;
+	}
+
+	return;
+}
+
+/*
+ * __vxge_hw_verify_pci_e_info - Validate the pci-e link parameters such as
+ * link width and signalling rate.
+ */
+static enum vxge_hw_status
+__vxge_hw_verify_pci_e_info(struct __vxge_hw_device *hldev)
+{
+	int exp_cap;
+	u16 lnk;
+
+	/* Get the negotiated link width and speed from PCI config space */
+	exp_cap = pci_find_capability(hldev->pdev, PCI_CAP_ID_EXP);
+	pci_read_config_word(hldev->pdev, exp_cap + PCI_EXP_LNKSTA, &lnk);
+
+	if ((lnk & PCI_EXP_LNKSTA_CLS) != 1)
+		return VXGE_HW_ERR_INVALID_PCI_INFO;
+
+	switch ((lnk & PCI_EXP_LNKSTA_NLW) >> 4) {
+	case PCIE_LNK_WIDTH_RESRV:
+	case PCIE_LNK_X1:
+	case PCIE_LNK_X2:
+	case PCIE_LNK_X4:
+	case PCIE_LNK_X8:
+		break;
+	default:
+		return VXGE_HW_ERR_INVALID_PCI_INFO;
+	}
+
+	return VXGE_HW_OK;
+}
+
+static enum vxge_hw_status
+__vxge_hw_device_is_privilaged(struct __vxge_hw_device *hldev)
+{
+	if ((hldev->host_type == VXGE_HW_NO_MR_NO_SR_NORMAL_FUNCTION ||
+	hldev->host_type == VXGE_HW_MR_NO_SR_VH0_BASE_FUNCTION ||
+	hldev->host_type == VXGE_HW_NO_MR_SR_VH0_FUNCTION0) &&
+	(hldev->func_id == 0))
+		return VXGE_HW_OK;
+	else
+		return VXGE_HW_ERR_PRIVILAGED_OPEARATION;
+}
+
+/*
+ * vxge_hw_wrr_rebalance - Rebalance the RX_WRR and KDFC_WRR calandars.
+ * Rebalance the RX_WRR and KDFC_WRR calandars.
+ */
+static enum
+vxge_hw_status vxge_hw_wrr_rebalance(struct __vxge_hw_device *hldev)
+{
+	u64 val64;
+	u32 wrr_states[VXGE_HW_WEIGHTED_RR_SERVICE_STATES];
+	u32 i, j, how_often = 1;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	status = __vxge_hw_device_is_privilaged(hldev);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	/* Reset the priorities assigned to the WRR arbitration
+	phases for the receive traffic */
+	for (i = 0; i < VXGE_HW_WRR_RING_COUNT; i++)
+		writeq(0, ((&hldev->mrpcim_reg->rx_w_round_robin_0) + i));
+
+	/* Reset the transmit FIFO servicing calendar for FIFOs */
+	for (i = 0; i < VXGE_HW_WRR_FIFO_COUNT; i++) {
+		writeq(0, ((&hldev->mrpcim_reg->kdfc_w_round_robin_0) + i));
+		writeq(0, ((&hldev->mrpcim_reg->kdfc_w_round_robin_20) + i));
+	}
+
+	/* Assign WRR priority  0 for all FIFOs */
+	for (i = 1; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		writeq(VXGE_HW_KDFC_FIFO_0_CTRL_WRR_NUMBER(0),
+				((&hldev->mrpcim_reg->kdfc_fifo_0_ctrl)  + i));
+
+		writeq(VXGE_HW_KDFC_FIFO_17_CTRL_WRR_NUMBER(0),
+			((&hldev->mrpcim_reg->kdfc_fifo_17_ctrl) + i));
+	}
+
+	/* Reset to service non-offload doorbells */
+	writeq(0, &hldev->mrpcim_reg->kdfc_entry_type_sel_0);
+	writeq(0, &hldev->mrpcim_reg->kdfc_entry_type_sel_1);
+
+	/* Set priority 0 to all receive queues */
+	writeq(0, &hldev->mrpcim_reg->rx_queue_priority_0);
+	writeq(0, &hldev->mrpcim_reg->rx_queue_priority_1);
+	writeq(0, &hldev->mrpcim_reg->rx_queue_priority_2);
+
+	/* Initialize all the slots as unused */
+	for (i = 0; i < VXGE_HW_WEIGHTED_RR_SERVICE_STATES; i++)
+		wrr_states[i] = -1;
+
+	/* Prepare the Fifo service states */
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!hldev->config.vp_config[i].min_bandwidth)
+			continue;
+
+		how_often = VXGE_HW_VPATH_BANDWIDTH_MAX /
+				hldev->config.vp_config[i].min_bandwidth;
+		if (how_often) {
+
+			for (j = 0; j < VXGE_HW_WRR_FIFO_SERVICE_STATES;) {
+				if (wrr_states[j] == -1) {
+					wrr_states[j] = i;
+					/* Make sure each fifo is serviced
+					 * atleast once */
+					if (i == j)
+						j += VXGE_HW_MAX_VIRTUAL_PATHS;
+					else
+						j += how_often;
+				} else
+					j++;
+			}
+		}
+	}
+
+	/* Fill the unused slots with 0 */
+	for (j = 0; j < VXGE_HW_WEIGHTED_RR_SERVICE_STATES; j++) {
+		if (wrr_states[j] == -1)
+			wrr_states[j] = 0;
+	}
+
+	/* Assign WRR priority number for FIFOs */
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		writeq(VXGE_HW_KDFC_FIFO_0_CTRL_WRR_NUMBER(i),
+				((&hldev->mrpcim_reg->kdfc_fifo_0_ctrl) + i));
+
+		writeq(VXGE_HW_KDFC_FIFO_17_CTRL_WRR_NUMBER(i),
+			((&hldev->mrpcim_reg->kdfc_fifo_17_ctrl) + i));
+	}
+
+	/* Modify the servicing algorithm applied to the 3 types of doorbells.
+	i.e, none-offload, message and offload */
+	writeq(VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_0(0) |
+				VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_1(0) |
+				VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_2(0) |
+				VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_3(0) |
+				VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_4(1) |
+				VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_5(0) |
+				VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_6(0) |
+				VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_7(0),
+				&hldev->mrpcim_reg->kdfc_entry_type_sel_0);
+
+	writeq(VXGE_HW_KDFC_ENTRY_TYPE_SEL_1_NUMBER_8(1),
+				&hldev->mrpcim_reg->kdfc_entry_type_sel_1);
+
+	for (i = 0, j = 0; i < VXGE_HW_WRR_FIFO_COUNT; i++) {
+
+		val64 = VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_0(wrr_states[j++]);
+		val64 |= VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_1(wrr_states[j++]);
+		val64 |= VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_2(wrr_states[j++]);
+		val64 |= VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_3(wrr_states[j++]);
+		val64 |= VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_4(wrr_states[j++]);
+		val64 |= VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_5(wrr_states[j++]);
+		val64 |= VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_6(wrr_states[j++]);
+		val64 |= VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_7(wrr_states[j++]);
+
+		writeq(val64, (&hldev->mrpcim_reg->kdfc_w_round_robin_0 + i));
+		writeq(val64, (&hldev->mrpcim_reg->kdfc_w_round_robin_20 + i));
+	}
+
+	/* Set up the priorities assigned to receive queues */
+	writeq(VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_0(0) |
+			VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_1(1) |
+			VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_2(2) |
+			VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_3(3) |
+			VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_4(4) |
+			VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_5(5) |
+			VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_6(6) |
+			VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_7(7),
+			&hldev->mrpcim_reg->rx_queue_priority_0);
+
+	writeq(VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_8(8) |
+			VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_9(9) |
+			VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_10(10) |
+			VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_11(11) |
+			VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_12(12) |
+			VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_13(13) |
+			VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_14(14) |
+			VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_15(15),
+			&hldev->mrpcim_reg->rx_queue_priority_1);
+
+	writeq(VXGE_HW_RX_QUEUE_PRIORITY_2_RX_Q_NUMBER_16(16),
+				&hldev->mrpcim_reg->rx_queue_priority_2);
+
+	/* Initialize all the slots as unused */
+	for (i = 0; i < VXGE_HW_WEIGHTED_RR_SERVICE_STATES; i++)
+		wrr_states[i] = -1;
+
+	/* Prepare the Ring service states */
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!hldev->config.vp_config[i].min_bandwidth)
+			continue;
+
+		how_often = VXGE_HW_VPATH_BANDWIDTH_MAX /
+				hldev->config.vp_config[i].min_bandwidth;
+
+		if (how_often) {
+			for (j = 0; j < VXGE_HW_WRR_RING_SERVICE_STATES;) {
+				if (wrr_states[j] == -1) {
+					wrr_states[j] = i;
+					/* Make sure each ring is
+					 * serviced atleast once */
+					if (i == j)
+						j += VXGE_HW_MAX_VIRTUAL_PATHS;
+					else
+						j += how_often;
+				} else
+					j++;
+			}
+		}
+	}
+
+	/* Fill the unused slots with 0 */
+	for (j = 0; j < VXGE_HW_WEIGHTED_RR_SERVICE_STATES; j++) {
+		if (wrr_states[j] == -1)
+			wrr_states[j] = 0;
+	}
+
+	for (i = 0, j = 0; i < VXGE_HW_WRR_RING_COUNT; i++) {
+		val64 =  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_0(
+				wrr_states[j++]);
+		val64 |=  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_1(
+				wrr_states[j++]);
+		val64 |=  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_2(
+				wrr_states[j++]);
+		val64 |=  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_3(
+				wrr_states[j++]);
+		val64 |=  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_4(
+				wrr_states[j++]);
+		val64 |=  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_5(
+				wrr_states[j++]);
+		val64 |=  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_6(
+				wrr_states[j++]);
+		val64 |=  VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_7(
+				wrr_states[j++]);
+
+		writeq(val64, ((&hldev->mrpcim_reg->rx_w_round_robin_0) + i));
+	}
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_device_initialize
+ * Initialize Titan-V hardware.
+ */
+enum vxge_hw_status __vxge_hw_device_initialize(struct __vxge_hw_device *hldev)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	/* Validate the pci-e link width and speed */
+	status = __vxge_hw_verify_pci_e_info(hldev);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	vxge_hw_wrr_rebalance(hldev);
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_device_hw_info_get - Get the hw information
+ * Returns the vpath mask that has the bits set for each vpath allocated
+ * for the driver, FW version information and the first mac addresse for
+ * each vpath
+ */
+enum vxge_hw_status __devinit
+vxge_hw_device_hw_info_get(void __iomem *bar0,
+			   struct vxge_hw_device_hw_info *hw_info)
+{
+	u32 i;
+	u64 val64;
+	struct vxge_hw_toc_reg __iomem *toc;
+	struct vxge_hw_mrpcim_reg __iomem *mrpcim_reg;
+	struct vxge_hw_common_reg __iomem *common_reg;
+	struct vxge_hw_vpath_reg __iomem *vpath_reg;
+	struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg;
+	enum vxge_hw_status status;
+
+	memset(hw_info, 0, sizeof(struct vxge_hw_device_hw_info));
+
+	toc = __vxge_hw_device_toc_get(bar0);
+	if (toc == NULL) {
+		status = VXGE_HW_ERR_CRITICAL;
+		goto exit;
+	}
+
+	val64 = readq(&toc->toc_common_pointer);
+	common_reg = (struct vxge_hw_common_reg __iomem *)(bar0 + val64);
+
+	status = __vxge_hw_device_vpath_reset_in_prog_check(
+		(u64 __iomem *)&common_reg->vpath_rst_in_prog);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	hw_info->vpath_mask = readq(&common_reg->vpath_assignments);
+
+	val64 = readq(&common_reg->host_type_assignments);
+
+	hw_info->host_type =
+	   (u32)VXGE_HW_HOST_TYPE_ASSIGNMENTS_GET_HOST_TYPE_ASSIGNMENTS(val64);
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!((hw_info->vpath_mask) & vxge_mBIT(i)))
+			continue;
+
+		val64 = readq(&toc->toc_vpmgmt_pointer[i]);
+
+		vpmgmt_reg = (struct vxge_hw_vpmgmt_reg __iomem *)
+				(bar0 + val64);
+
+		hw_info->func_id = __vxge_hw_vpath_func_id_get(i, vpmgmt_reg);
+		if (__vxge_hw_device_access_rights_get(hw_info->host_type,
+			hw_info->func_id) &
+			VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM) {
+
+			val64 = readq(&toc->toc_mrpcim_pointer);
+
+			mrpcim_reg = (struct vxge_hw_mrpcim_reg __iomem *)
+					(bar0 + val64);
+
+			writeq(0, &mrpcim_reg->xgmac_gen_fw_memo_mask);
+			wmb();
+		}
+
+		val64 = readq(&toc->toc_vpath_pointer[i]);
+
+		vpath_reg = (struct vxge_hw_vpath_reg __iomem *)(bar0 + val64);
+
+		hw_info->function_mode =
+			__vxge_hw_vpath_pci_func_mode_get(i, vpath_reg);
+
+		status = __vxge_hw_vpath_fw_ver_get(i, vpath_reg, hw_info);
+		if (status != VXGE_HW_OK)
+			goto exit;
+
+		status = __vxge_hw_vpath_card_info_get(i, vpath_reg, hw_info);
+		if (status != VXGE_HW_OK)
+			goto exit;
+
+		break;
+	}
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!((hw_info->vpath_mask) & vxge_mBIT(i)))
+			continue;
+
+		val64 = readq(&toc->toc_vpath_pointer[i]);
+		vpath_reg = (struct vxge_hw_vpath_reg __iomem *)(bar0 + val64);
+
+		status =  __vxge_hw_vpath_addr_get(i, vpath_reg,
+				hw_info->mac_addrs[i],
+				hw_info->mac_addr_masks[i]);
+		if (status != VXGE_HW_OK)
+			goto exit;
+	}
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_device_initialize - Initialize Titan device.
+ * Initialize Titan device. Note that all the arguments of this public API
+ * are 'IN', including @hldev. Driver cooperates with
+ * OS to find new Titan device, locate its PCI and memory spaces.
+ *
+ * When done, the driver allocates sizeof(struct __vxge_hw_device) bytes for HW
+ * to enable the latter to perform Titan hardware initialization.
+ */
+enum vxge_hw_status __devinit
+vxge_hw_device_initialize(
+	struct __vxge_hw_device **devh,
+	struct vxge_hw_device_attr *attr,
+	struct vxge_hw_device_config *device_config)
+{
+	u32 i;
+	u32 nblocks = 0;
+	struct __vxge_hw_device *hldev = NULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	status = __vxge_hw_device_config_check(device_config);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	hldev = (struct __vxge_hw_device *)
+			vmalloc(sizeof(struct __vxge_hw_device));
+	if (hldev == NULL) {
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto exit;
+	}
+
+	memset(hldev, 0, sizeof(struct __vxge_hw_device));
+	hldev->magic = VXGE_HW_DEVICE_MAGIC;
+
+	vxge_hw_device_debug_set(hldev, VXGE_ERR, VXGE_COMPONENT_ALL);
+
+	/* apply config */
+	memcpy(&hldev->config, device_config,
+		sizeof(struct vxge_hw_device_config));
+
+	hldev->bar0 = attr->bar0;
+	hldev->bar1 = attr->bar1;
+	hldev->bar2 = attr->bar2;
+	hldev->pdev = attr->pdev;
+
+	hldev->uld_callbacks.link_up = attr->uld_callbacks.link_up;
+	hldev->uld_callbacks.link_down = attr->uld_callbacks.link_down;
+	hldev->uld_callbacks.crit_err = attr->uld_callbacks.crit_err;
+
+	__vxge_hw_device_pci_e_init(hldev);
+
+	status = __vxge_hw_device_reg_addr_get(hldev);
+	if (status != VXGE_HW_OK)
+		goto exit;
+	__vxge_hw_device_id_get(hldev);
+
+	__vxge_hw_device_host_info_get(hldev);
+
+	/* Incrementing for stats blocks */
+	nblocks++;
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!(hldev->vpath_assignments & vxge_mBIT(i)))
+			continue;
+
+		if (device_config->vp_config[i].ring.enable ==
+			VXGE_HW_RING_ENABLE)
+			nblocks += device_config->vp_config[i].ring.ring_blocks;
+
+		if (device_config->vp_config[i].fifo.enable ==
+			VXGE_HW_FIFO_ENABLE)
+			nblocks += device_config->vp_config[i].fifo.fifo_blocks;
+		nblocks++;
+	}
+
+	if (__vxge_hw_blockpool_create(hldev,
+		&hldev->block_pool,
+		device_config->dma_blockpool_initial + nblocks,
+		device_config->dma_blockpool_max + nblocks) != VXGE_HW_OK) {
+
+		vxge_hw_device_terminate(hldev);
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto exit;
+	}
+
+	status = __vxge_hw_device_initialize(hldev);
+
+	if (status != VXGE_HW_OK) {
+		vxge_hw_device_terminate(hldev);
+		goto exit;
+	}
+
+	*devh = hldev;
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_device_terminate - Terminate Titan device.
+ * Terminate HW device.
+ */
+void
+vxge_hw_device_terminate(struct __vxge_hw_device *hldev)
+{
+	vxge_assert(hldev->magic == VXGE_HW_DEVICE_MAGIC);
+
+	hldev->magic = VXGE_HW_DEVICE_DEAD;
+	__vxge_hw_blockpool_destroy(&hldev->block_pool);
+	vfree(hldev);
+}
+
+/*
+ * vxge_hw_device_stats_get - Get the device hw statistics.
+ * Returns the vpath h/w stats for the device.
+ */
+enum vxge_hw_status
+vxge_hw_device_stats_get(struct __vxge_hw_device *hldev,
+			struct vxge_hw_device_stats_hw_info *hw_stats)
+{
+	u32 i;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!(hldev->vpaths_deployed & vxge_mBIT(i)) ||
+			(hldev->virtual_paths[i].vp_open ==
+				VXGE_HW_VP_NOT_OPEN))
+			continue;
+
+		memcpy(hldev->virtual_paths[i].hw_stats_sav,
+				hldev->virtual_paths[i].hw_stats,
+				sizeof(struct vxge_hw_vpath_stats_hw_info));
+
+		status = __vxge_hw_vpath_stats_get(
+			&hldev->virtual_paths[i],
+			hldev->virtual_paths[i].hw_stats);
+	}
+
+	memcpy(hw_stats, &hldev->stats.hw_dev_info_stats,
+			sizeof(struct vxge_hw_device_stats_hw_info));
+
+	return status;
+}
+
+/*
+ * vxge_hw_driver_stats_get - Get the device sw statistics.
+ * Returns the vpath s/w stats for the device.
+ */
+enum vxge_hw_status vxge_hw_driver_stats_get(
+			struct __vxge_hw_device *hldev,
+			struct vxge_hw_device_stats_sw_info *sw_stats)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	memcpy(sw_stats, &hldev->stats.sw_dev_info_stats,
+		sizeof(struct vxge_hw_device_stats_sw_info));
+
+	return status;
+}
+
+/*
+ * vxge_hw_mrpcim_stats_access - Access the statistics from the given location
+ *                           and offset and perform an operation
+ * Get the statistics from the given location and offset.
+ */
+enum vxge_hw_status
+vxge_hw_mrpcim_stats_access(struct __vxge_hw_device *hldev,
+			    u32 operation, u32 location, u32 offset, u64 *stat)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	status = __vxge_hw_device_is_privilaged(hldev);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = VXGE_HW_XMAC_STATS_SYS_CMD_OP(operation) |
+		VXGE_HW_XMAC_STATS_SYS_CMD_STROBE |
+		VXGE_HW_XMAC_STATS_SYS_CMD_LOC_SEL(location) |
+		VXGE_HW_XMAC_STATS_SYS_CMD_OFFSET_SEL(offset);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&hldev->mrpcim_reg->xmac_stats_sys_cmd,
+				VXGE_HW_XMAC_STATS_SYS_CMD_STROBE,
+				hldev->config.device_poll_millis);
+
+	if ((status == VXGE_HW_OK) && (operation == VXGE_HW_STATS_OP_READ))
+		*stat = readq(&hldev->mrpcim_reg->xmac_stats_sys_data);
+	else
+		*stat = 0;
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_device_xmac_aggr_stats_get - Get the Statistics on aggregate port
+ * Get the Statistics on aggregate port
+ */
+enum vxge_hw_status
+vxge_hw_device_xmac_aggr_stats_get(struct __vxge_hw_device *hldev, u32 port,
+				   struct vxge_hw_xmac_aggr_stats *aggr_stats)
+{
+	u64 *val64;
+	int i;
+	u32 offset = VXGE_HW_STATS_AGGRn_OFFSET;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	val64 = (u64 *)aggr_stats;
+
+	status = __vxge_hw_device_is_privilaged(hldev);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	for (i = 0; i < sizeof(struct vxge_hw_xmac_aggr_stats) / 8; i++) {
+		status = vxge_hw_mrpcim_stats_access(hldev,
+					VXGE_HW_STATS_OP_READ,
+					VXGE_HW_STATS_LOC_AGGR,
+					((offset + (104 * port)) >> 3), val64);
+		if (status != VXGE_HW_OK)
+			goto exit;
+
+		offset += 8;
+		val64++;
+	}
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_device_xmac_port_stats_get - Get the Statistics on a port
+ * Get the Statistics on port
+ */
+enum vxge_hw_status
+vxge_hw_device_xmac_port_stats_get(struct __vxge_hw_device *hldev, u32 port,
+				   struct vxge_hw_xmac_port_stats *port_stats)
+{
+	u64 *val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	int i;
+	u32 offset = 0x0;
+	val64 = (u64 *) port_stats;
+
+	status = __vxge_hw_device_is_privilaged(hldev);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	for (i = 0; i < sizeof(struct vxge_hw_xmac_port_stats) / 8; i++) {
+		status = vxge_hw_mrpcim_stats_access(hldev,
+					VXGE_HW_STATS_OP_READ,
+					VXGE_HW_STATS_LOC_AGGR,
+					((offset + (608 * port)) >> 3), val64);
+		if (status != VXGE_HW_OK)
+			goto exit;
+
+		offset += 8;
+		val64++;
+	}
+
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_device_xmac_stats_get - Get the XMAC Statistics
+ * Get the XMAC Statistics
+ */
+enum vxge_hw_status
+vxge_hw_device_xmac_stats_get(struct __vxge_hw_device *hldev,
+			      struct vxge_hw_xmac_stats *xmac_stats)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	u32 i;
+
+	status = vxge_hw_device_xmac_aggr_stats_get(hldev,
+					0, &xmac_stats->aggr_stats[0]);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	status = vxge_hw_device_xmac_aggr_stats_get(hldev,
+				1, &xmac_stats->aggr_stats[1]);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	for (i = 0; i <= VXGE_HW_MAC_MAX_MAC_PORT_ID; i++) {
+
+		status = vxge_hw_device_xmac_port_stats_get(hldev,
+					i, &xmac_stats->port_stats[i]);
+		if (status != VXGE_HW_OK)
+			goto exit;
+	}
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!(hldev->vpaths_deployed & vxge_mBIT(i)))
+			continue;
+
+		status = __vxge_hw_vpath_xmac_tx_stats_get(
+					&hldev->virtual_paths[i],
+					&xmac_stats->vpath_tx_stats[i]);
+		if (status != VXGE_HW_OK)
+			goto exit;
+
+		status = __vxge_hw_vpath_xmac_rx_stats_get(
+					&hldev->virtual_paths[i],
+					&xmac_stats->vpath_rx_stats[i]);
+		if (status != VXGE_HW_OK)
+			goto exit;
+	}
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_device_debug_set - Set the debug module, level and timestamp
+ * This routine is used to dynamically change the debug output
+ */
+void vxge_hw_device_debug_set(struct __vxge_hw_device *hldev,
+			      enum vxge_debug_level level, u32 mask)
+{
+	if (hldev == NULL)
+		return;
+
+#if defined(VXGE_DEBUG_TRACE_MASK) || \
+	defined(VXGE_DEBUG_ERR_MASK)
+	hldev->debug_module_mask = mask;
+	hldev->debug_level = level;
+#endif
+
+#if defined(VXGE_DEBUG_ERR_MASK)
+	hldev->level_err = level & VXGE_ERR;
+#endif
+
+#if defined(VXGE_DEBUG_TRACE_MASK)
+	hldev->level_trace = level & VXGE_TRACE;
+#endif
+}
+
+/*
+ * vxge_hw_device_error_level_get - Get the error level
+ * This routine returns the current error level set
+ */
+u32 vxge_hw_device_error_level_get(struct __vxge_hw_device *hldev)
+{
+#if defined(VXGE_DEBUG_ERR_MASK)
+	if (hldev == NULL)
+		return VXGE_ERR;
+	else
+		return hldev->level_err;
+#else
+	return 0;
+#endif
+}
+
+/*
+ * vxge_hw_device_trace_level_get - Get the trace level
+ * This routine returns the current trace level set
+ */
+u32 vxge_hw_device_trace_level_get(struct __vxge_hw_device *hldev)
+{
+#if defined(VXGE_DEBUG_TRACE_MASK)
+	if (hldev == NULL)
+		return VXGE_TRACE;
+	else
+		return hldev->level_trace;
+#else
+	return 0;
+#endif
+}
+/*
+ * vxge_hw_device_debug_mask_get - Get the debug mask
+ * This routine returns the current debug mask set
+ */
+u32 vxge_hw_device_debug_mask_get(struct __vxge_hw_device *hldev)
+{
+#if defined(VXGE_DEBUG_TRACE_MASK) || defined(VXGE_DEBUG_ERR_MASK)
+	if (hldev == NULL)
+		return 0;
+	return hldev->debug_module_mask;
+#else
+	return 0;
+#endif
+}
+
+/*
+ * vxge_hw_getpause_data -Pause frame frame generation and reception.
+ * Returns the Pause frame generation and reception capability of the NIC.
+ */
+enum vxge_hw_status vxge_hw_device_getpause_data(struct __vxge_hw_device *hldev,
+						 u32 port, u32 *tx, u32 *rx)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((hldev == NULL) || (hldev->magic != VXGE_HW_DEVICE_MAGIC)) {
+		status = VXGE_HW_ERR_INVALID_DEVICE;
+		goto exit;
+	}
+
+	if (port > VXGE_HW_MAC_MAX_MAC_PORT_ID) {
+		status = VXGE_HW_ERR_INVALID_PORT;
+		goto exit;
+	}
+
+	if (!(hldev->access_rights & VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM)) {
+		status = VXGE_HW_ERR_PRIVILAGED_OPEARATION;
+		goto exit;
+	}
+
+	val64 = readq(&hldev->mrpcim_reg->rxmac_pause_cfg_port[port]);
+	if (val64 & VXGE_HW_RXMAC_PAUSE_CFG_PORT_GEN_EN)
+		*tx = 1;
+	if (val64 & VXGE_HW_RXMAC_PAUSE_CFG_PORT_RCV_EN)
+		*rx = 1;
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_device_setpause_data -  set/reset pause frame generation.
+ * It can be used to set or reset Pause frame generation or reception
+ * support of the NIC.
+ */
+
+enum vxge_hw_status vxge_hw_device_setpause_data(struct __vxge_hw_device *hldev,
+						 u32 port, u32 tx, u32 rx)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((hldev == NULL) || (hldev->magic != VXGE_HW_DEVICE_MAGIC)) {
+		status = VXGE_HW_ERR_INVALID_DEVICE;
+		goto exit;
+	}
+
+	if (port > VXGE_HW_MAC_MAX_MAC_PORT_ID) {
+		status = VXGE_HW_ERR_INVALID_PORT;
+		goto exit;
+	}
+
+	status = __vxge_hw_device_is_privilaged(hldev);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&hldev->mrpcim_reg->rxmac_pause_cfg_port[port]);
+	if (tx)
+		val64 |= VXGE_HW_RXMAC_PAUSE_CFG_PORT_GEN_EN;
+	else
+		val64 &= ~VXGE_HW_RXMAC_PAUSE_CFG_PORT_GEN_EN;
+	if (rx)
+		val64 |= VXGE_HW_RXMAC_PAUSE_CFG_PORT_RCV_EN;
+	else
+		val64 &= ~VXGE_HW_RXMAC_PAUSE_CFG_PORT_RCV_EN;
+
+	writeq(val64, &hldev->mrpcim_reg->rxmac_pause_cfg_port[port]);
+exit:
+	return status;
+}
+
+u16 vxge_hw_device_link_width_get(struct __vxge_hw_device *hldev)
+{
+	int link_width, exp_cap;
+	u16 lnk;
+
+	exp_cap = pci_find_capability(hldev->pdev, PCI_CAP_ID_EXP);
+	pci_read_config_word(hldev->pdev, exp_cap + PCI_EXP_LNKSTA, &lnk);
+	link_width = (lnk & VXGE_HW_PCI_EXP_LNKCAP_LNK_WIDTH) >> 4;
+	return link_width;
+}
+
+/*
+ * __vxge_hw_ring_block_memblock_idx - Return the memblock index
+ * This function returns the index of memory block
+ */
+static inline u32
+__vxge_hw_ring_block_memblock_idx(u8 *block)
+{
+	return (u32)*((u64 *)(block + VXGE_HW_RING_MEMBLOCK_IDX_OFFSET));
+}
+
+/*
+ * __vxge_hw_ring_block_memblock_idx_set - Sets the memblock index
+ * This function sets index to a memory block
+ */
+static inline void
+__vxge_hw_ring_block_memblock_idx_set(u8 *block, u32 memblock_idx)
+{
+	*((u64 *)(block + VXGE_HW_RING_MEMBLOCK_IDX_OFFSET)) = memblock_idx;
+}
+
+/*
+ * __vxge_hw_ring_block_next_pointer_set - Sets the next block pointer
+ * in RxD block
+ * Sets the next block pointer in RxD block
+ */
+static inline void
+__vxge_hw_ring_block_next_pointer_set(u8 *block, dma_addr_t dma_next)
+{
+	*((u64 *)(block + VXGE_HW_RING_NEXT_BLOCK_POINTER_OFFSET)) = dma_next;
+}
+
+/*
+ * __vxge_hw_ring_first_block_address_get - Returns the dma address of the
+ *             first block
+ * Returns the dma address of the first RxD block
+ */
+u64 __vxge_hw_ring_first_block_address_get(struct __vxge_hw_ring *ring)
+{
+	struct vxge_hw_mempool_dma *dma_object;
+
+	dma_object = ring->mempool->memblocks_dma_arr;
+	vxge_assert(dma_object != NULL);
+
+	return dma_object->addr;
+}
+
+/*
+ * __vxge_hw_ring_item_dma_addr - Return the dma address of an item
+ * This function returns the dma address of a given item
+ */
+static dma_addr_t __vxge_hw_ring_item_dma_addr(struct vxge_hw_mempool *mempoolh,
+					       void *item)
+{
+	u32 memblock_idx;
+	void *memblock;
+	struct vxge_hw_mempool_dma *memblock_dma_object;
+	ptrdiff_t dma_item_offset;
+
+	/* get owner memblock index */
+	memblock_idx = __vxge_hw_ring_block_memblock_idx(item);
+
+	/* get owner memblock by memblock index */
+	memblock = mempoolh->memblocks_arr[memblock_idx];
+
+	/* get memblock DMA object by memblock index */
+	memblock_dma_object = mempoolh->memblocks_dma_arr + memblock_idx;
+
+	/* calculate offset in the memblock of this item */
+	dma_item_offset = (u8 *)item - (u8 *)memblock;
+
+	return memblock_dma_object->addr + dma_item_offset;
+}
+
+/*
+ * __vxge_hw_ring_rxdblock_link - Link the RxD blocks
+ * This function returns the dma address of a given item
+ */
+static void __vxge_hw_ring_rxdblock_link(struct vxge_hw_mempool *mempoolh,
+					 struct __vxge_hw_ring *ring, u32 from,
+					 u32 to)
+{
+	u8 *to_item , *from_item;
+	dma_addr_t to_dma;
+
+	/* get "from" RxD block */
+	from_item = mempoolh->items_arr[from];
+	vxge_assert(from_item);
+
+	/* get "to" RxD block */
+	to_item = mempoolh->items_arr[to];
+	vxge_assert(to_item);
+
+	/* return address of the beginning of previous RxD block */
+	to_dma = __vxge_hw_ring_item_dma_addr(mempoolh, to_item);
+
+	/* set next pointer for this RxD block to point on
+	 * previous item's DMA start address */
+	__vxge_hw_ring_block_next_pointer_set(from_item, to_dma);
+}
+
+/*
+ * __vxge_hw_ring_mempool_item_alloc - Allocate List blocks for RxD
+ * block callback
+ * This function is callback passed to __vxge_hw_mempool_create to create memory
+ * pool for RxD block
+ */
+static void
+__vxge_hw_ring_mempool_item_alloc(struct vxge_hw_mempool *mempoolh,
+				  u32 memblock_index,
+				  struct vxge_hw_mempool_dma *dma_object,
+				  u32 index, u32 is_last)
+{
+	u32 i;
+	void *item = mempoolh->items_arr[index];
+	struct __vxge_hw_ring *ring =
+		(struct __vxge_hw_ring *)mempoolh->userdata;
+
+	/* format rxds array */
+	for (i = 0; i < ring->rxds_per_block; i++) {
+		void *rxdblock_priv;
+		void *uld_priv;
+		struct vxge_hw_ring_rxd_1 *rxdp;
+
+		u32 reserve_index = ring->channel.reserve_ptr -
+				(index * ring->rxds_per_block + i + 1);
+		u32 memblock_item_idx;
+
+		ring->channel.reserve_arr[reserve_index] = ((u8 *)item) +
+						i * ring->rxd_size;
+
+		/* Note: memblock_item_idx is index of the item within
+		 *       the memblock. For instance, in case of three RxD-blocks
+		 *       per memblock this value can be 0, 1 or 2. */
+		rxdblock_priv = __vxge_hw_mempool_item_priv(mempoolh,
+					memblock_index, item,
+					&memblock_item_idx);
+
+		rxdp = (struct vxge_hw_ring_rxd_1 *)
+				ring->channel.reserve_arr[reserve_index];
+
+		uld_priv = ((u8 *)rxdblock_priv + ring->rxd_priv_size * i);
+
+		/* pre-format Host_Control */
+		rxdp->host_control = (u64)(size_t)uld_priv;
+	}
+
+	__vxge_hw_ring_block_memblock_idx_set(item, memblock_index);
+
+	if (is_last) {
+		/* link last one with first one */
+		__vxge_hw_ring_rxdblock_link(mempoolh, ring, index, 0);
+	}
+
+	if (index > 0) {
+		/* link this RxD block with previous one */
+		__vxge_hw_ring_rxdblock_link(mempoolh, ring, index - 1, index);
+	}
+
+	return;
+}
+
+/*
+ * __vxge_hw_ring_initial_replenish - Initial replenish of RxDs
+ * This function replenishes the RxDs from reserve array to work array
+ */
+enum vxge_hw_status
+vxge_hw_ring_replenish(struct __vxge_hw_ring *ring, u16 min_flag)
+{
+	void *rxd;
+	int i = 0;
+	struct __vxge_hw_channel *channel;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	channel = &ring->channel;
+
+	while (vxge_hw_channel_dtr_count(channel) > 0) {
+
+		status = vxge_hw_ring_rxd_reserve(ring, &rxd);
+
+		vxge_assert(status == VXGE_HW_OK);
+
+		if (ring->rxd_init) {
+			status = ring->rxd_init(rxd, channel->userdata);
+			if (status != VXGE_HW_OK) {
+				vxge_hw_ring_rxd_free(ring, rxd);
+				goto exit;
+			}
+		}
+
+		vxge_hw_ring_rxd_post(ring, rxd);
+		if (min_flag) {
+			i++;
+			if (i == VXGE_HW_RING_MIN_BUFF_ALLOCATION)
+				break;
+		}
+	}
+	status = VXGE_HW_OK;
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_ring_create - Create a Ring
+ * This function creates Ring and initializes it.
+ *
+ */
+enum vxge_hw_status
+__vxge_hw_ring_create(struct __vxge_hw_vpath_handle *vp,
+		      struct vxge_hw_ring_attr *attr)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_ring *ring;
+	u32 ring_length;
+	struct vxge_hw_ring_config *config;
+	struct __vxge_hw_device *hldev;
+	u32 vp_id;
+	struct vxge_hw_mempool_cbs ring_mp_callback;
+
+	if ((vp == NULL) || (attr == NULL)) {
+		status = VXGE_HW_FAIL;
+		goto exit;
+	}
+
+	hldev = vp->vpath->hldev;
+	vp_id = vp->vpath->vp_id;
+
+	config = &hldev->config.vp_config[vp_id].ring;
+
+	ring_length = config->ring_blocks *
+			vxge_hw_ring_rxds_per_block_get(config->buffer_mode);
+
+	ring = (struct __vxge_hw_ring *)__vxge_hw_channel_allocate(vp,
+						VXGE_HW_CHANNEL_TYPE_RING,
+						ring_length,
+						attr->per_rxd_space,
+						attr->userdata);
+
+	if (ring == NULL) {
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto exit;
+	}
+
+	vp->vpath->ringh = ring;
+	ring->vp_id = vp_id;
+	ring->vp_reg = vp->vpath->vp_reg;
+	ring->common_reg = hldev->common_reg;
+	ring->stats = &vp->vpath->sw_stats->ring_stats;
+	ring->config = config;
+	ring->callback = attr->callback;
+	ring->rxd_init = attr->rxd_init;
+	ring->rxd_term = attr->rxd_term;
+	ring->buffer_mode = config->buffer_mode;
+	ring->rxds_limit = config->rxds_limit;
+
+	ring->rxd_size = vxge_hw_ring_rxd_size_get(config->buffer_mode);
+	ring->rxd_priv_size =
+		sizeof(struct __vxge_hw_ring_rxd_priv) + attr->per_rxd_space;
+	ring->per_rxd_space = attr->per_rxd_space;
+
+	ring->rxd_priv_size =
+		((ring->rxd_priv_size + VXGE_CACHE_LINE_SIZE - 1) /
+		VXGE_CACHE_LINE_SIZE) * VXGE_CACHE_LINE_SIZE;
+
+	/* how many RxDs can fit into one block. Depends on configured
+	 * buffer_mode. */
+	ring->rxds_per_block =
+		vxge_hw_ring_rxds_per_block_get(config->buffer_mode);
+
+	/* calculate actual RxD block private size */
+	ring->rxdblock_priv_size = ring->rxd_priv_size * ring->rxds_per_block;
+	ring_mp_callback.item_func_alloc = __vxge_hw_ring_mempool_item_alloc;
+	ring->mempool = __vxge_hw_mempool_create(hldev,
+				VXGE_HW_BLOCK_SIZE,
+				VXGE_HW_BLOCK_SIZE,
+				ring->rxdblock_priv_size,
+				ring->config->ring_blocks,
+				ring->config->ring_blocks,
+				&ring_mp_callback,
+				ring);
+
+	if (ring->mempool == NULL) {
+		__vxge_hw_ring_delete(vp);
+		return VXGE_HW_ERR_OUT_OF_MEMORY;
+	}
+
+	status = __vxge_hw_channel_initialize(&ring->channel);
+	if (status != VXGE_HW_OK) {
+		__vxge_hw_ring_delete(vp);
+		goto exit;
+	}
+
+	/* Note:
+	 * Specifying rxd_init callback means two things:
+	 * 1) rxds need to be initialized by driver at channel-open time;
+	 * 2) rxds need to be posted at channel-open time
+	 *    (that's what the initial_replenish() below does)
+	 * Currently we don't have a case when the 1) is done without the 2).
+	 */
+	if (ring->rxd_init) {
+		status = vxge_hw_ring_replenish(ring, 1);
+		if (status != VXGE_HW_OK) {
+			__vxge_hw_ring_delete(vp);
+			goto exit;
+		}
+	}
+
+	/* initial replenish will increment the counter in its post() routine,
+	 * we have to reset it */
+	ring->stats->common_stats.usage_cnt = 0;
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_ring_abort - Returns the RxD
+ * This function terminates the RxDs of ring
+ */
+enum vxge_hw_status __vxge_hw_ring_abort(struct __vxge_hw_ring *ring)
+{
+	void *rxdh;
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	for (;;) {
+		vxge_hw_channel_dtr_try_complete(channel, &rxdh);
+
+		if (rxdh == NULL)
+			break;
+
+		vxge_hw_channel_dtr_complete(channel);
+
+		if (ring->rxd_term)
+			ring->rxd_term(rxdh, VXGE_HW_RXD_STATE_POSTED,
+				channel->userdata);
+
+		vxge_hw_channel_dtr_free(channel, rxdh);
+	}
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_ring_reset - Resets the ring
+ * This function resets the ring during vpath reset operation
+ */
+enum vxge_hw_status __vxge_hw_ring_reset(struct __vxge_hw_ring *ring)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	__vxge_hw_ring_abort(ring);
+
+	status = __vxge_hw_channel_reset(channel);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	if (ring->rxd_init) {
+		status = vxge_hw_ring_replenish(ring, 1);
+		if (status != VXGE_HW_OK)
+			goto exit;
+	}
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_ring_delete - Removes the ring
+ * This function freeup the memory pool and removes the ring
+ */
+enum vxge_hw_status __vxge_hw_ring_delete(struct __vxge_hw_vpath_handle *vp)
+{
+	struct __vxge_hw_ring *ring = vp->vpath->ringh;
+
+	__vxge_hw_ring_abort(ring);
+
+	if (ring->mempool)
+		__vxge_hw_mempool_destroy(ring->mempool);
+
+	vp->vpath->ringh = NULL;
+	__vxge_hw_channel_free(&ring->channel);
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_mempool_grow
+ * Will resize mempool up to %num_allocate value.
+ */
+enum vxge_hw_status
+__vxge_hw_mempool_grow(struct vxge_hw_mempool *mempool, u32 num_allocate,
+		       u32 *num_allocated)
+{
+	u32 i, first_time = mempool->memblocks_allocated == 0 ? 1 : 0;
+	u32 n_items = mempool->items_per_memblock;
+	u32 start_block_idx = mempool->memblocks_allocated;
+	u32 end_block_idx = mempool->memblocks_allocated + num_allocate;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	*num_allocated = 0;
+
+	if (end_block_idx > mempool->memblocks_max) {
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto exit;
+	}
+
+	for (i = start_block_idx; i < end_block_idx; i++) {
+		u32 j;
+		u32 is_last = ((end_block_idx - 1) == i);
+		struct vxge_hw_mempool_dma *dma_object =
+			mempool->memblocks_dma_arr + i;
+		void *the_memblock;
+
+		/* allocate memblock's private part. Each DMA memblock
+		 * has a space allocated for item's private usage upon
+		 * mempool's user request. Each time mempool grows, it will
+		 * allocate new memblock and its private part at once.
+		 * This helps to minimize memory usage a lot. */
+		mempool->memblocks_priv_arr[i] =
+				vmalloc(mempool->items_priv_size * n_items);
+		if (mempool->memblocks_priv_arr[i] == NULL) {
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto exit;
+		}
+
+		memset(mempool->memblocks_priv_arr[i], 0,
+			     mempool->items_priv_size * n_items);
+
+		/* allocate DMA-capable memblock */
+		mempool->memblocks_arr[i] =
+			__vxge_hw_blockpool_malloc(mempool->devh,
+				mempool->memblock_size, dma_object);
+		if (mempool->memblocks_arr[i] == NULL) {
+			vfree(mempool->memblocks_priv_arr[i]);
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto exit;
+		}
+
+		(*num_allocated)++;
+		mempool->memblocks_allocated++;
+
+		memset(mempool->memblocks_arr[i], 0, mempool->memblock_size);
+
+		the_memblock = mempool->memblocks_arr[i];
+
+		/* fill the items hash array */
+		for (j = 0; j < n_items; j++) {
+			u32 index = i * n_items + j;
+
+			if (first_time && index >= mempool->items_initial)
+				break;
+
+			mempool->items_arr[index] =
+				((char *)the_memblock + j*mempool->item_size);
+
+			/* let caller to do more job on each item */
+			if (mempool->item_func_alloc != NULL)
+				mempool->item_func_alloc(mempool, i,
+					dma_object, index, is_last);
+
+			mempool->items_current = index + 1;
+		}
+
+		if (first_time && mempool->items_current ==
+					mempool->items_initial)
+			break;
+	}
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_mempool_create
+ * This function will create memory pool object. Pool may grow but will
+ * never shrink. Pool consists of number of dynamically allocated blocks
+ * with size enough to hold %items_initial number of items. Memory is
+ * DMA-able but client must map/unmap before interoperating with the device.
+ */
+struct vxge_hw_mempool*
+__vxge_hw_mempool_create(
+	struct __vxge_hw_device *devh,
+	u32 memblock_size,
+	u32 item_size,
+	u32 items_priv_size,
+	u32 items_initial,
+	u32 items_max,
+	struct vxge_hw_mempool_cbs *mp_callback,
+	void *userdata)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	u32 memblocks_to_allocate;
+	struct vxge_hw_mempool *mempool = NULL;
+	u32 allocated;
+
+	if (memblock_size < item_size) {
+		status = VXGE_HW_FAIL;
+		goto exit;
+	}
+
+	mempool = (struct vxge_hw_mempool *)
+			vmalloc(sizeof(struct vxge_hw_mempool));
+	if (mempool == NULL) {
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto exit;
+	}
+	memset(mempool, 0, sizeof(struct vxge_hw_mempool));
+
+	mempool->devh			= devh;
+	mempool->memblock_size		= memblock_size;
+	mempool->items_max		= items_max;
+	mempool->items_initial		= items_initial;
+	mempool->item_size		= item_size;
+	mempool->items_priv_size	= items_priv_size;
+	mempool->item_func_alloc	= mp_callback->item_func_alloc;
+	mempool->userdata		= userdata;
+
+	mempool->memblocks_allocated = 0;
+
+	mempool->items_per_memblock = memblock_size / item_size;
+
+	mempool->memblocks_max = (items_max + mempool->items_per_memblock - 1) /
+					mempool->items_per_memblock;
+
+	/* allocate array of memblocks */
+	mempool->memblocks_arr =
+		(void **) vmalloc(sizeof(void *) * mempool->memblocks_max);
+	if (mempool->memblocks_arr == NULL) {
+		__vxge_hw_mempool_destroy(mempool);
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		mempool = NULL;
+		goto exit;
+	}
+	memset(mempool->memblocks_arr, 0,
+		sizeof(void *) * mempool->memblocks_max);
+
+	/* allocate array of private parts of items per memblocks */
+	mempool->memblocks_priv_arr =
+		(void **) vmalloc(sizeof(void *) * mempool->memblocks_max);
+	if (mempool->memblocks_priv_arr == NULL) {
+		__vxge_hw_mempool_destroy(mempool);
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		mempool = NULL;
+		goto exit;
+	}
+	memset(mempool->memblocks_priv_arr, 0,
+		    sizeof(void *) * mempool->memblocks_max);
+
+	/* allocate array of memblocks DMA objects */
+	mempool->memblocks_dma_arr = (struct vxge_hw_mempool_dma *)
+		vmalloc(sizeof(struct vxge_hw_mempool_dma) *
+			mempool->memblocks_max);
+
+	if (mempool->memblocks_dma_arr == NULL) {
+		__vxge_hw_mempool_destroy(mempool);
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		mempool = NULL;
+		goto exit;
+	}
+	memset(mempool->memblocks_dma_arr, 0,
+			sizeof(struct vxge_hw_mempool_dma) *
+			mempool->memblocks_max);
+
+	/* allocate hash array of items */
+	mempool->items_arr =
+		(void **) vmalloc(sizeof(void *) * mempool->items_max);
+	if (mempool->items_arr == NULL) {
+		__vxge_hw_mempool_destroy(mempool);
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		mempool = NULL;
+		goto exit;
+	}
+	memset(mempool->items_arr, 0, sizeof(void *) * mempool->items_max);
+
+	/* calculate initial number of memblocks */
+	memblocks_to_allocate = (mempool->items_initial +
+				 mempool->items_per_memblock - 1) /
+						mempool->items_per_memblock;
+
+	/* pre-allocate the mempool */
+	status = __vxge_hw_mempool_grow(mempool, memblocks_to_allocate,
+					&allocated);
+	if (status != VXGE_HW_OK) {
+		__vxge_hw_mempool_destroy(mempool);
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		mempool = NULL;
+		goto exit;
+	}
+
+exit:
+	return mempool;
+}
+
+/*
+ * vxge_hw_mempool_destroy
+ */
+void __vxge_hw_mempool_destroy(struct vxge_hw_mempool *mempool)
+{
+	u32 i, j;
+	struct __vxge_hw_device *devh = mempool->devh;
+
+	for (i = 0; i < mempool->memblocks_allocated; i++) {
+		struct vxge_hw_mempool_dma *dma_object;
+
+		vxge_assert(mempool->memblocks_arr[i]);
+		vxge_assert(mempool->memblocks_dma_arr + i);
+
+		dma_object = mempool->memblocks_dma_arr + i;
+
+		for (j = 0; j < mempool->items_per_memblock; j++) {
+			u32 index = i * mempool->items_per_memblock + j;
+
+			/* to skip last partially filled(if any) memblock */
+			if (index >= mempool->items_current)
+				break;
+		}
+
+		vfree(mempool->memblocks_priv_arr[i]);
+
+		__vxge_hw_blockpool_free(devh, mempool->memblocks_arr[i],
+				mempool->memblock_size, dma_object);
+	}
+
+	if (mempool->items_arr)
+		vfree(mempool->items_arr);
+
+	if (mempool->memblocks_dma_arr)
+		vfree(mempool->memblocks_dma_arr);
+
+	if (mempool->memblocks_priv_arr)
+		vfree(mempool->memblocks_priv_arr);
+
+	if (mempool->memblocks_arr)
+		vfree(mempool->memblocks_arr);
+
+	vfree(mempool);
+}
+
+/*
+ * __vxge_hw_device_fifo_config_check - Check fifo configuration.
+ * Check the fifo configuration
+ */
+enum vxge_hw_status
+__vxge_hw_device_fifo_config_check(struct vxge_hw_fifo_config *fifo_config)
+{
+	if ((fifo_config->fifo_blocks < VXGE_HW_MIN_FIFO_BLOCKS) ||
+	     (fifo_config->fifo_blocks > VXGE_HW_MAX_FIFO_BLOCKS))
+		return VXGE_HW_BADCFG_FIFO_BLOCKS;
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_device_vpath_config_check - Check vpath configuration.
+ * Check the vpath configuration
+ */
+enum vxge_hw_status
+__vxge_hw_device_vpath_config_check(struct vxge_hw_vp_config *vp_config)
+{
+	enum vxge_hw_status status;
+
+	if ((vp_config->min_bandwidth < VXGE_HW_VPATH_BANDWIDTH_MIN) ||
+		(vp_config->min_bandwidth >
+					VXGE_HW_VPATH_BANDWIDTH_MAX))
+		return VXGE_HW_BADCFG_VPATH_MIN_BANDWIDTH;
+
+	status = __vxge_hw_device_fifo_config_check(&vp_config->fifo);
+	if (status != VXGE_HW_OK)
+		return status;
+
+	if ((vp_config->mtu != VXGE_HW_VPATH_USE_FLASH_DEFAULT_INITIAL_MTU) &&
+		((vp_config->mtu < VXGE_HW_VPATH_MIN_INITIAL_MTU) ||
+		(vp_config->mtu > VXGE_HW_VPATH_MAX_INITIAL_MTU)))
+		return VXGE_HW_BADCFG_VPATH_MTU;
+
+	if ((vp_config->rpa_strip_vlan_tag !=
+		VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_USE_FLASH_DEFAULT) &&
+		(vp_config->rpa_strip_vlan_tag !=
+		VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_ENABLE) &&
+		(vp_config->rpa_strip_vlan_tag !=
+		VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_DISABLE))
+		return VXGE_HW_BADCFG_VPATH_RPA_STRIP_VLAN_TAG;
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_device_config_check - Check device configuration.
+ * Check the device configuration
+ */
+enum vxge_hw_status
+__vxge_hw_device_config_check(struct vxge_hw_device_config *new_config)
+{
+	u32 i;
+	enum vxge_hw_status status;
+
+	if ((new_config->intr_mode != VXGE_HW_INTR_MODE_IRQLINE) &&
+	   (new_config->intr_mode != VXGE_HW_INTR_MODE_MSIX) &&
+	   (new_config->intr_mode != VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) &&
+	   (new_config->intr_mode != VXGE_HW_INTR_MODE_DEF))
+		return VXGE_HW_BADCFG_INTR_MODE;
+
+	if ((new_config->rts_mac_en != VXGE_HW_RTS_MAC_DISABLE) &&
+	   (new_config->rts_mac_en != VXGE_HW_RTS_MAC_ENABLE))
+		return VXGE_HW_BADCFG_RTS_MAC_EN;
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		status = __vxge_hw_device_vpath_config_check(
+				&new_config->vp_config[i]);
+		if (status != VXGE_HW_OK)
+			return status;
+	}
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * vxge_hw_device_config_default_get - Initialize device config with defaults.
+ * Initialize Titan device config with default values.
+ */
+enum vxge_hw_status __devinit
+vxge_hw_device_config_default_get(struct vxge_hw_device_config *device_config)
+{
+	u32 i;
+
+	device_config->dma_blockpool_initial =
+					VXGE_HW_INITIAL_DMA_BLOCK_POOL_SIZE;
+	device_config->dma_blockpool_max = VXGE_HW_MAX_DMA_BLOCK_POOL_SIZE;
+	device_config->intr_mode = VXGE_HW_INTR_MODE_DEF;
+	device_config->rth_en = VXGE_HW_RTH_DEFAULT;
+	device_config->rth_it_type = VXGE_HW_RTH_IT_TYPE_DEFAULT;
+	device_config->device_poll_millis =  VXGE_HW_DEF_DEVICE_POLL_MILLIS;
+	device_config->rts_mac_en =  VXGE_HW_RTS_MAC_DEFAULT;
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		device_config->vp_config[i].vp_id = i;
+
+		device_config->vp_config[i].min_bandwidth =
+				VXGE_HW_VPATH_BANDWIDTH_DEFAULT;
+
+		device_config->vp_config[i].ring.enable = VXGE_HW_RING_DEFAULT;
+
+		device_config->vp_config[i].ring.ring_blocks =
+				VXGE_HW_DEF_RING_BLOCKS;
+
+		device_config->vp_config[i].ring.buffer_mode =
+				VXGE_HW_RING_RXD_BUFFER_MODE_DEFAULT;
+
+		device_config->vp_config[i].ring.scatter_mode =
+				VXGE_HW_RING_SCATTER_MODE_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].ring.rxds_limit =
+				VXGE_HW_DEF_RING_RXDS_LIMIT;
+
+		device_config->vp_config[i].fifo.enable = VXGE_HW_FIFO_ENABLE;
+
+		device_config->vp_config[i].fifo.fifo_blocks =
+				VXGE_HW_MIN_FIFO_BLOCKS;
+
+		device_config->vp_config[i].fifo.max_frags =
+				VXGE_HW_MAX_FIFO_FRAGS;
+
+		device_config->vp_config[i].fifo.memblock_size =
+				VXGE_HW_DEF_FIFO_MEMBLOCK_SIZE;
+
+		device_config->vp_config[i].fifo.alignment_size =
+				VXGE_HW_DEF_FIFO_ALIGNMENT_SIZE;
+
+		device_config->vp_config[i].fifo.intr =
+				VXGE_HW_FIFO_QUEUE_INTR_DEFAULT;
+
+		device_config->vp_config[i].fifo.no_snoop_bits =
+				VXGE_HW_FIFO_NO_SNOOP_DEFAULT;
+		device_config->vp_config[i].tti.intr_enable =
+				VXGE_HW_TIM_INTR_DEFAULT;
+
+		device_config->vp_config[i].tti.btimer_val =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.timer_ac_en =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.timer_ci_en =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.timer_ri_en =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.rtimer_val =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.util_sel =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.ltimer_val =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.urange_a =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.uec_a =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.urange_b =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.uec_b =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.urange_c =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.uec_c =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].tti.uec_d =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.intr_enable =
+				VXGE_HW_TIM_INTR_DEFAULT;
+
+		device_config->vp_config[i].rti.btimer_val =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.timer_ac_en =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.timer_ci_en =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.timer_ri_en =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.rtimer_val =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.util_sel =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.ltimer_val =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.urange_a =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.uec_a =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.urange_b =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.uec_b =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.urange_c =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.uec_c =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].rti.uec_d =
+				VXGE_HW_USE_FLASH_DEFAULT;
+
+		device_config->vp_config[i].mtu =
+				VXGE_HW_VPATH_USE_FLASH_DEFAULT_INITIAL_MTU;
+
+		device_config->vp_config[i].rpa_strip_vlan_tag =
+			VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_USE_FLASH_DEFAULT;
+	}
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * _hw_legacy_swapper_set - Set the swapper bits for the legacy secion.
+ * Set the swapper bits appropriately for the lagacy section.
+ */
+enum vxge_hw_status
+__vxge_hw_legacy_swapper_set(struct vxge_hw_legacy_reg __iomem *legacy_reg)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	val64 = readq(&legacy_reg->toc_swapper_fb);
+
+	wmb();
+
+	switch (val64) {
+
+	case VXGE_HW_SWAPPER_INITIAL_VALUE:
+		return status;
+
+	case VXGE_HW_SWAPPER_BYTE_SWAPPED_BIT_FLIPPED:
+		writeq(VXGE_HW_SWAPPER_READ_BYTE_SWAP_ENABLE,
+			&legacy_reg->pifm_rd_swap_en);
+		writeq(VXGE_HW_SWAPPER_READ_BIT_FLAP_ENABLE,
+			&legacy_reg->pifm_rd_flip_en);
+		writeq(VXGE_HW_SWAPPER_WRITE_BYTE_SWAP_ENABLE,
+			&legacy_reg->pifm_wr_swap_en);
+		writeq(VXGE_HW_SWAPPER_WRITE_BIT_FLAP_ENABLE,
+			&legacy_reg->pifm_wr_flip_en);
+		break;
+
+	case VXGE_HW_SWAPPER_BYTE_SWAPPED:
+		writeq(VXGE_HW_SWAPPER_READ_BYTE_SWAP_ENABLE,
+			&legacy_reg->pifm_rd_swap_en);
+		writeq(VXGE_HW_SWAPPER_WRITE_BYTE_SWAP_ENABLE,
+			&legacy_reg->pifm_wr_swap_en);
+		break;
+
+	case VXGE_HW_SWAPPER_BIT_FLIPPED:
+		writeq(VXGE_HW_SWAPPER_READ_BIT_FLAP_ENABLE,
+			&legacy_reg->pifm_rd_flip_en);
+		writeq(VXGE_HW_SWAPPER_WRITE_BIT_FLAP_ENABLE,
+			&legacy_reg->pifm_wr_flip_en);
+		break;
+	}
+
+	wmb();
+
+	val64 = readq(&legacy_reg->toc_swapper_fb);
+
+	if (val64 != VXGE_HW_SWAPPER_INITIAL_VALUE)
+		status = VXGE_HW_ERR_SWAPPER_CTRL;
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_swapper_set - Set the swapper bits for the vpath.
+ * Set the swapper bits appropriately for the vpath.
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_swapper_set(struct vxge_hw_vpath_reg __iomem *vpath_reg)
+{
+#ifndef __BIG_ENDIAN
+	u64 val64;
+
+	val64 = readq(&vpath_reg->vpath_general_cfg1);
+	wmb();
+	val64 |= VXGE_HW_VPATH_GENERAL_CFG1_CTL_BYTE_SWAPEN;
+	writeq(val64, &vpath_reg->vpath_general_cfg1);
+	wmb();
+#endif
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_kdfc_swapper_set - Set the swapper bits for the kdfc.
+ * Set the swapper bits appropriately for the vpath.
+ */
+enum vxge_hw_status
+__vxge_hw_kdfc_swapper_set(
+	struct vxge_hw_legacy_reg __iomem *legacy_reg,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg)
+{
+	u64 val64;
+
+	val64 = readq(&legacy_reg->pifm_wr_swap_en);
+
+	if (val64 == VXGE_HW_SWAPPER_WRITE_BYTE_SWAP_ENABLE) {
+		val64 = readq(&vpath_reg->kdfcctl_cfg0);
+		wmb();
+
+		val64 |= VXGE_HW_KDFCCTL_CFG0_BYTE_SWAPEN_FIFO0	|
+			VXGE_HW_KDFCCTL_CFG0_BYTE_SWAPEN_FIFO1	|
+			VXGE_HW_KDFCCTL_CFG0_BYTE_SWAPEN_FIFO2;
+
+		writeq(val64, &vpath_reg->kdfcctl_cfg0);
+		wmb();
+	}
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * vxge_hw_mgmt_device_config - Retrieve device configuration.
+ * Get device configuration. Permits to retrieve at run-time configuration
+ * values that were used to initialize and configure the device.
+ */
+enum vxge_hw_status
+vxge_hw_mgmt_device_config(struct __vxge_hw_device *hldev,
+			   struct vxge_hw_device_config *dev_config, int size)
+{
+
+	if ((hldev == NULL) || (hldev->magic != VXGE_HW_DEVICE_MAGIC))
+		return VXGE_HW_ERR_INVALID_DEVICE;
+
+	if (size != sizeof(struct vxge_hw_device_config))
+		return VXGE_HW_ERR_VERSION_CONFLICT;
+
+	memcpy(dev_config, &hldev->config,
+		sizeof(struct vxge_hw_device_config));
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * vxge_hw_mgmt_reg_read - Read Titan register.
+ */
+enum vxge_hw_status
+vxge_hw_mgmt_reg_read(struct __vxge_hw_device *hldev,
+		      enum vxge_hw_mgmt_reg_type type,
+		      u32 index, u32 offset, u64 *value)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((hldev == NULL) || (hldev->magic != VXGE_HW_DEVICE_MAGIC)) {
+		status = VXGE_HW_ERR_INVALID_DEVICE;
+		goto exit;
+	}
+
+	switch (type) {
+	case vxge_hw_mgmt_reg_type_legacy:
+		if (offset > sizeof(struct vxge_hw_legacy_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		*value = readq((void __iomem *)hldev->legacy_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_toc:
+		if (offset > sizeof(struct vxge_hw_toc_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		*value = readq((void __iomem *)hldev->toc_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_common:
+		if (offset > sizeof(struct vxge_hw_common_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		*value = readq((void __iomem *)hldev->common_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_mrpcim:
+		if (!(hldev->access_rights &
+			VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM)) {
+			status = VXGE_HW_ERR_PRIVILAGED_OPEARATION;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_mrpcim_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		*value = readq((void __iomem *)hldev->mrpcim_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_srpcim:
+		if (!(hldev->access_rights &
+			VXGE_HW_DEVICE_ACCESS_RIGHT_SRPCIM)) {
+			status = VXGE_HW_ERR_PRIVILAGED_OPEARATION;
+			break;
+		}
+		if (index > VXGE_HW_TITAN_SRPCIM_REG_SPACES - 1) {
+			status = VXGE_HW_ERR_INVALID_INDEX;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_srpcim_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		*value = readq((void __iomem *)hldev->srpcim_reg[index] +
+				offset);
+		break;
+	case vxge_hw_mgmt_reg_type_vpmgmt:
+		if ((index > VXGE_HW_TITAN_VPMGMT_REG_SPACES - 1) ||
+			(!(hldev->vpath_assignments & vxge_mBIT(index)))) {
+			status = VXGE_HW_ERR_INVALID_INDEX;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_vpmgmt_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		*value = readq((void __iomem *)hldev->vpmgmt_reg[index] +
+				offset);
+		break;
+	case vxge_hw_mgmt_reg_type_vpath:
+		if ((index > VXGE_HW_TITAN_VPATH_REG_SPACES - 1) ||
+			(!(hldev->vpath_assignments & vxge_mBIT(index)))) {
+			status = VXGE_HW_ERR_INVALID_INDEX;
+			break;
+		}
+		if (index > VXGE_HW_TITAN_VPATH_REG_SPACES - 1) {
+			status = VXGE_HW_ERR_INVALID_INDEX;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_vpath_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		*value = readq((void __iomem *)hldev->vpath_reg[index] +
+				offset);
+		break;
+	default:
+		status = VXGE_HW_ERR_INVALID_TYPE;
+		break;
+	}
+
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_mgmt_reg_Write - Write Titan register.
+ */
+enum vxge_hw_status
+vxge_hw_mgmt_reg_write(struct __vxge_hw_device *hldev,
+		      enum vxge_hw_mgmt_reg_type type,
+		      u32 index, u32 offset, u64 value)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((hldev == NULL) || (hldev->magic != VXGE_HW_DEVICE_MAGIC)) {
+		status = VXGE_HW_ERR_INVALID_DEVICE;
+		goto exit;
+	}
+
+	switch (type) {
+	case vxge_hw_mgmt_reg_type_legacy:
+		if (offset > sizeof(struct vxge_hw_legacy_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		writeq(value, (void __iomem *)hldev->legacy_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_toc:
+		if (offset > sizeof(struct vxge_hw_toc_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		writeq(value, (void __iomem *)hldev->toc_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_common:
+		if (offset > sizeof(struct vxge_hw_common_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		writeq(value, (void __iomem *)hldev->common_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_mrpcim:
+		if (!(hldev->access_rights &
+			VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM)) {
+			status = VXGE_HW_ERR_PRIVILAGED_OPEARATION;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_mrpcim_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		writeq(value, (void __iomem *)hldev->mrpcim_reg + offset);
+		break;
+	case vxge_hw_mgmt_reg_type_srpcim:
+		if (!(hldev->access_rights &
+			VXGE_HW_DEVICE_ACCESS_RIGHT_SRPCIM)) {
+			status = VXGE_HW_ERR_PRIVILAGED_OPEARATION;
+			break;
+		}
+		if (index > VXGE_HW_TITAN_SRPCIM_REG_SPACES - 1) {
+			status = VXGE_HW_ERR_INVALID_INDEX;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_srpcim_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		writeq(value, (void __iomem *)hldev->srpcim_reg[index] +
+			offset);
+
+		break;
+	case vxge_hw_mgmt_reg_type_vpmgmt:
+		if ((index > VXGE_HW_TITAN_VPMGMT_REG_SPACES - 1) ||
+			(!(hldev->vpath_assignments & vxge_mBIT(index)))) {
+			status = VXGE_HW_ERR_INVALID_INDEX;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_vpmgmt_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		writeq(value, (void __iomem *)hldev->vpmgmt_reg[index] +
+			offset);
+		break;
+	case vxge_hw_mgmt_reg_type_vpath:
+		if ((index > VXGE_HW_TITAN_VPATH_REG_SPACES-1) ||
+			(!(hldev->vpath_assignments & vxge_mBIT(index)))) {
+			status = VXGE_HW_ERR_INVALID_INDEX;
+			break;
+		}
+		if (offset > sizeof(struct vxge_hw_vpath_reg) - 8) {
+			status = VXGE_HW_ERR_INVALID_OFFSET;
+			break;
+		}
+		writeq(value, (void __iomem *)hldev->vpath_reg[index] +
+			offset);
+		break;
+	default:
+		status = VXGE_HW_ERR_INVALID_TYPE;
+		break;
+	}
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_fifo_mempool_item_alloc - Allocate List blocks for TxD
+ * list callback
+ * This function is callback passed to __vxge_hw_mempool_create to create memory
+ * pool for TxD list
+ */
+static void
+__vxge_hw_fifo_mempool_item_alloc(
+	struct vxge_hw_mempool *mempoolh,
+	u32 memblock_index, struct vxge_hw_mempool_dma *dma_object,
+	u32 index, u32 is_last)
+{
+	u32 memblock_item_idx;
+	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
+	struct vxge_hw_fifo_txd *txdp =
+		(struct vxge_hw_fifo_txd *)mempoolh->items_arr[index];
+	struct __vxge_hw_fifo *fifo =
+			(struct __vxge_hw_fifo *)mempoolh->userdata;
+	void *memblock = mempoolh->memblocks_arr[memblock_index];
+
+	vxge_assert(txdp);
+
+	txdp->host_control = (u64) (size_t)
+	__vxge_hw_mempool_item_priv(mempoolh, memblock_index, txdp,
+					&memblock_item_idx);
+
+	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdp);
+
+	vxge_assert(txdl_priv);
+
+	fifo->channel.reserve_arr[fifo->channel.reserve_ptr - 1 - index] = txdp;
+
+	/* pre-format HW's TxDL's private */
+	txdl_priv->dma_offset = (char *)txdp - (char *)memblock;
+	txdl_priv->dma_addr = dma_object->addr + txdl_priv->dma_offset;
+	txdl_priv->dma_handle = dma_object->handle;
+	txdl_priv->memblock   = memblock;
+	txdl_priv->first_txdp = txdp;
+	txdl_priv->next_txdl_priv = NULL;
+	txdl_priv->alloc_frags = 0;
+
+	return;
+}
+
+/*
+ * __vxge_hw_fifo_create - Create a FIFO
+ * This function creates FIFO and initializes it.
+ */
+enum vxge_hw_status
+__vxge_hw_fifo_create(struct __vxge_hw_vpath_handle *vp,
+		      struct vxge_hw_fifo_attr *attr)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_fifo *fifo;
+	struct vxge_hw_fifo_config *config;
+	u32 txdl_size, txdl_per_memblock;
+	struct vxge_hw_mempool_cbs fifo_mp_callback;
+	struct __vxge_hw_virtualpath *vpath;
+
+	if ((vp == NULL) || (attr == NULL)) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+	vpath = vp->vpath;
+	config = &vpath->hldev->config.vp_config[vpath->vp_id].fifo;
+
+	txdl_size = config->max_frags * sizeof(struct vxge_hw_fifo_txd);
+
+	txdl_per_memblock = config->memblock_size / txdl_size;
+
+	fifo = (struct __vxge_hw_fifo *)__vxge_hw_channel_allocate(vp,
+					VXGE_HW_CHANNEL_TYPE_FIFO,
+					config->fifo_blocks * txdl_per_memblock,
+					attr->per_txdl_space, attr->userdata);
+
+	if (fifo == NULL) {
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto exit;
+	}
+
+	vpath->fifoh = fifo;
+	fifo->nofl_db = vpath->nofl_db;
+
+	fifo->vp_id = vpath->vp_id;
+	fifo->vp_reg = vpath->vp_reg;
+	fifo->stats = &vpath->sw_stats->fifo_stats;
+
+	fifo->config = config;
+
+	/* apply "interrupts per txdl" attribute */
+	fifo->interrupt_type = VXGE_HW_FIFO_TXD_INT_TYPE_UTILZ;
+
+	if (fifo->config->intr)
+		fifo->interrupt_type = VXGE_HW_FIFO_TXD_INT_TYPE_PER_LIST;
+
+	fifo->no_snoop_bits = config->no_snoop_bits;
+
+	/*
+	 * FIFO memory management strategy:
+	 *
+	 * TxDL split into three independent parts:
+	 *	- set of TxD's
+	 *	- TxD HW private part
+	 *	- driver private part
+	 *
+	 * Adaptative memory allocation used. i.e. Memory allocated on
+	 * demand with the size which will fit into one memory block.
+	 * One memory block may contain more than one TxDL.
+	 *
+	 * During "reserve" operations more memory can be allocated on demand
+	 * for example due to FIFO full condition.
+	 *
+	 * Pool of memory memblocks never shrinks except in __vxge_hw_fifo_close
+	 * routine which will essentially stop the channel and free resources.
+	 */
+
+	/* TxDL common private size == TxDL private  +  driver private */
+	fifo->priv_size =
+		sizeof(struct __vxge_hw_fifo_txdl_priv) + attr->per_txdl_space;
+	fifo->priv_size = ((fifo->priv_size  +  VXGE_CACHE_LINE_SIZE - 1) /
+			VXGE_CACHE_LINE_SIZE) * VXGE_CACHE_LINE_SIZE;
+
+	fifo->per_txdl_space = attr->per_txdl_space;
+
+	/* recompute txdl size to be cacheline aligned */
+	fifo->txdl_size = txdl_size;
+	fifo->txdl_per_memblock = txdl_per_memblock;
+
+	fifo->txdl_term = attr->txdl_term;
+	fifo->callback = attr->callback;
+
+	if (fifo->txdl_per_memblock == 0) {
+		__vxge_hw_fifo_delete(vp);
+		status = VXGE_HW_ERR_INVALID_BLOCK_SIZE;
+		goto exit;
+	}
+
+	fifo_mp_callback.item_func_alloc = __vxge_hw_fifo_mempool_item_alloc;
+
+	fifo->mempool =
+		__vxge_hw_mempool_create(vpath->hldev,
+			fifo->config->memblock_size,
+			fifo->txdl_size,
+			fifo->priv_size,
+			(fifo->config->fifo_blocks * fifo->txdl_per_memblock),
+			(fifo->config->fifo_blocks * fifo->txdl_per_memblock),
+			&fifo_mp_callback,
+			fifo);
+
+	if (fifo->mempool == NULL) {
+		__vxge_hw_fifo_delete(vp);
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto exit;
+	}
+
+	status = __vxge_hw_channel_initialize(&fifo->channel);
+	if (status != VXGE_HW_OK) {
+		__vxge_hw_fifo_delete(vp);
+		goto exit;
+	}
+
+	vxge_assert(fifo->channel.reserve_ptr);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_fifo_abort - Returns the TxD
+ * This function terminates the TxDs of fifo
+ */
+enum vxge_hw_status __vxge_hw_fifo_abort(struct __vxge_hw_fifo *fifo)
+{
+	void *txdlh;
+
+	for (;;) {
+		vxge_hw_channel_dtr_try_complete(&fifo->channel, &txdlh);
+
+		if (txdlh == NULL)
+			break;
+
+		vxge_hw_channel_dtr_complete(&fifo->channel);
+
+		if (fifo->txdl_term) {
+			fifo->txdl_term(txdlh,
+			VXGE_HW_TXDL_STATE_POSTED,
+			fifo->channel.userdata);
+		}
+
+		vxge_hw_channel_dtr_free(&fifo->channel, txdlh);
+	}
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_fifo_reset - Resets the fifo
+ * This function resets the fifo during vpath reset operation
+ */
+enum vxge_hw_status __vxge_hw_fifo_reset(struct __vxge_hw_fifo *fifo)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	__vxge_hw_fifo_abort(fifo);
+	status = __vxge_hw_channel_reset(&fifo->channel);
+
+	return status;
+}
+
+/*
+ * __vxge_hw_fifo_delete - Removes the FIFO
+ * This function freeup the memory pool and removes the FIFO
+ */
+enum vxge_hw_status __vxge_hw_fifo_delete(struct __vxge_hw_vpath_handle *vp)
+{
+	struct __vxge_hw_fifo *fifo = vp->vpath->fifoh;
+
+	__vxge_hw_fifo_abort(fifo);
+
+	if (fifo->mempool)
+		__vxge_hw_mempool_destroy(fifo->mempool);
+
+	vp->vpath->fifoh = NULL;
+
+	__vxge_hw_channel_free(&fifo->channel);
+
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_vpath_pci_read - Read the content of given address
+ *                          in pci config space.
+ * Read from the vpath pci config space.
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_pci_read(struct __vxge_hw_virtualpath *vpath,
+			 u32 phy_func_0, u32 offset, u32 *val)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_hw_vpath_reg __iomem *vp_reg = vpath->vp_reg;
+
+	val64 =	VXGE_HW_PCI_CONFIG_ACCESS_CFG1_ADDRESS(offset);
+
+	if (phy_func_0)
+		val64 |= VXGE_HW_PCI_CONFIG_ACCESS_CFG1_SEL_FUNC0;
+
+	writeq(val64, &vp_reg->pci_config_access_cfg1);
+	wmb();
+	writeq(VXGE_HW_PCI_CONFIG_ACCESS_CFG2_REQ,
+			&vp_reg->pci_config_access_cfg2);
+	wmb();
+
+	status = __vxge_hw_device_register_poll(
+			&vp_reg->pci_config_access_cfg2,
+			VXGE_HW_INTR_MASK_ALL, VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&vp_reg->pci_config_access_status);
+
+	if (val64 & VXGE_HW_PCI_CONFIG_ACCESS_STATUS_ACCESS_ERR) {
+		status = VXGE_HW_FAIL;
+		*val = 0;
+	} else
+		*val = (u32)vxge_bVALn(val64, 32, 32);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_func_id_get - Get the function id of the vpath.
+ * Returns the function number of the vpath.
+ */
+u32
+__vxge_hw_vpath_func_id_get(u32 vp_id,
+	struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg)
+{
+	u64 val64;
+
+	val64 = readq(&vpmgmt_reg->vpath_to_func_map_cfg1);
+
+	return
+	 (u32)VXGE_HW_VPATH_TO_FUNC_MAP_CFG1_GET_VPATH_TO_FUNC_MAP_CFG1(val64);
+}
+
+/*
+ * __vxge_hw_read_rts_ds - Program RTS steering critieria
+ */
+static inline void
+__vxge_hw_read_rts_ds(struct vxge_hw_vpath_reg __iomem *vpath_reg,
+		      u64 dta_struct_sel)
+{
+	writeq(0, &vpath_reg->rts_access_steer_ctrl);
+	wmb();
+	writeq(dta_struct_sel, &vpath_reg->rts_access_steer_data0);
+	writeq(0, &vpath_reg->rts_access_steer_data1);
+	wmb();
+	return;
+}
+
+
+/*
+ * __vxge_hw_vpath_card_info_get - Get the serial numbers,
+ * part number and product description.
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_card_info_get(
+	u32 vp_id,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg,
+	struct vxge_hw_device_hw_info *hw_info)
+{
+	u32 i, j;
+	u64 val64;
+	u64 data1 = 0ULL;
+	u64 data2 = 0ULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	u8 *serial_number = hw_info->serial_number;
+	u8 *part_number = hw_info->part_number;
+	u8 *product_desc = hw_info->product_desc;
+
+	__vxge_hw_read_rts_ds(vpath_reg,
+		VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_SERIAL_NUMBER);
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vpath_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+	if (status != VXGE_HW_OK)
+		return status;
+
+	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
+
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+		data1 = readq(&vpath_reg->rts_access_steer_data0);
+		((u64 *)serial_number)[0] = be64_to_cpu(data1);
+
+		data2 = readq(&vpath_reg->rts_access_steer_data1);
+		((u64 *)serial_number)[1] = be64_to_cpu(data2);
+		status = VXGE_HW_OK;
+	} else
+		*serial_number = 0;
+
+	__vxge_hw_read_rts_ds(vpath_reg,
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PART_NUMBER);
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vpath_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+	if (status != VXGE_HW_OK)
+		return status;
+
+	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
+
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+
+		data1 = readq(&vpath_reg->rts_access_steer_data0);
+		((u64 *)part_number)[0] = be64_to_cpu(data1);
+
+		data2 = readq(&vpath_reg->rts_access_steer_data1);
+		((u64 *)part_number)[1] = be64_to_cpu(data2);
+
+		status = VXGE_HW_OK;
+
+	} else
+		*part_number = 0;
+
+	j = 0;
+
+	for (i = VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_0;
+	     i <= VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_3; i++) {
+
+		__vxge_hw_read_rts_ds(vpath_reg, i);
+
+		val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+
+		status = __vxge_hw_pio_mem_write64(val64,
+				&vpath_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+		if (status != VXGE_HW_OK)
+			return status;
+
+		val64 = readq(&vpath_reg->rts_access_steer_ctrl);
+
+		if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+
+			data1 = readq(&vpath_reg->rts_access_steer_data0);
+			((u64 *)product_desc)[j++] = be64_to_cpu(data1);
+
+			data2 = readq(&vpath_reg->rts_access_steer_data1);
+			((u64 *)product_desc)[j++] = be64_to_cpu(data2);
+
+			status = VXGE_HW_OK;
+		} else
+			*product_desc = 0;
+	}
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_fw_ver_get - Get the fw version
+ * Returns FW Version
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_fw_ver_get(
+	u32 vp_id,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg,
+	struct vxge_hw_device_hw_info *hw_info)
+{
+	u64 val64;
+	u64 data1 = 0ULL;
+	u64 data2 = 0ULL;
+	struct vxge_hw_device_version *fw_version = &hw_info->fw_version;
+	struct vxge_hw_device_date *fw_date = &hw_info->fw_date;
+	struct vxge_hw_device_version *flash_version = &hw_info->flash_version;
+	struct vxge_hw_device_date *flash_date = &hw_info->flash_date;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vpath_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
+
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+
+		data1 = readq(&vpath_reg->rts_access_steer_data0);
+		data2 = readq(&vpath_reg->rts_access_steer_data1);
+
+		fw_date->day =
+			(u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_DAY(
+						data1);
+		fw_date->month =
+			(u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MONTH(
+						data1);
+		fw_date->year =
+			(u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_YEAR(
+						data1);
+
+		snprintf(fw_date->date, VXGE_HW_FW_STRLEN, "%2.2d/%2.2d/%4.4d",
+			fw_date->month, fw_date->day, fw_date->year);
+
+		fw_version->major =
+		    (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(data1);
+		fw_version->minor =
+		    (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(data1);
+		fw_version->build =
+		    (u32)VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(data1);
+
+		snprintf(fw_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d",
+		    fw_version->major, fw_version->minor, fw_version->build);
+
+		flash_date->day =
+		  (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_DAY(data2);
+		flash_date->month =
+		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MONTH(data2);
+		flash_date->year =
+		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_YEAR(data2);
+
+		snprintf(flash_date->date, VXGE_HW_FW_STRLEN,
+			"%2.2d/%2.2d/%4.4d",
+			flash_date->month, flash_date->day, flash_date->year);
+
+		flash_version->major =
+		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MAJOR(data2);
+		flash_version->minor =
+		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MINOR(data2);
+		flash_version->build =
+		 (u32)VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(data2);
+
+		snprintf(flash_version->version, VXGE_HW_FW_STRLEN, "%d.%d.%d",
+			flash_version->major, flash_version->minor,
+			flash_version->build);
+
+		status = VXGE_HW_OK;
+
+	} else
+		status = VXGE_HW_FAIL;
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_pci_func_mode_get - Get the pci mode
+ * Returns pci function mode
+ */
+u64
+__vxge_hw_vpath_pci_func_mode_get(
+	u32  vp_id,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg)
+{
+	u64 val64;
+	u64 data1 = 0ULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	__vxge_hw_read_rts_ds(vpath_reg,
+		VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PCI_MODE);
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vpath_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
+
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+		data1 = readq(&vpath_reg->rts_access_steer_data0);
+		status = VXGE_HW_OK;
+	} else {
+		data1 = 0;
+		status = VXGE_HW_FAIL;
+	}
+exit:
+	return data1;
+}
+
+/**
+ * vxge_hw_device_flick_link_led - Flick (blink) link LED.
+ * @hldev: HW device.
+ * @on_off: TRUE if flickering to be on, FALSE to be off
+ *
+ * Flicker the link LED.
+ */
+enum vxge_hw_status
+vxge_hw_device_flick_link_led(struct __vxge_hw_device *hldev,
+			       u64 on_off)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	if (hldev == NULL) {
+		status = VXGE_HW_ERR_INVALID_DEVICE;
+		goto exit;
+	}
+
+	vp_reg = hldev->vpath_reg[hldev->first_vp_id];
+
+	writeq(0, &vp_reg->rts_access_steer_ctrl);
+	wmb();
+	writeq(on_off, &vp_reg->rts_access_steer_data0);
+	writeq(0, &vp_reg->rts_access_steer_data1);
+	wmb();
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LED_CONTROL) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vp_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_rts_table_get - Get the entries from RTS access tables
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_rts_table_get(
+	struct __vxge_hw_vpath_handle *vp,
+	u32 action, u32 rts_table, u32 offset, u64 *data1, u64 *data2)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+	vp_reg = vpath->vp_reg;
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(rts_table) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset);
+
+	if ((rts_table ==
+		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT) ||
+	    (rts_table ==
+		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT) ||
+	    (rts_table ==
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK) ||
+	    (rts_table ==
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY)) {
+		val64 = val64 |	VXGE_HW_RTS_ACCESS_STEER_CTRL_TABLE_SEL;
+	}
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vp_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				vpath->hldev->config.device_poll_millis);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&vp_reg->rts_access_steer_ctrl);
+
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+
+		*data1 = readq(&vp_reg->rts_access_steer_data0);
+
+		if ((rts_table ==
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) ||
+		(rts_table ==
+		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) {
+			*data2 = readq(&vp_reg->rts_access_steer_data1);
+		}
+		status = VXGE_HW_OK;
+	} else
+		status = VXGE_HW_FAIL;
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_rts_table_set - Set the entries of RTS access tables
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_rts_table_set(
+	struct __vxge_hw_vpath_handle *vp, u32 action, u32 rts_table,
+	u32 offset, u64 data1, u64 data2)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+	vp_reg = vpath->vp_reg;
+
+	writeq(data1, &vp_reg->rts_access_steer_data0);
+	wmb();
+
+	if ((rts_table == VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) ||
+	    (rts_table ==
+		VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT)) {
+		writeq(data2, &vp_reg->rts_access_steer_data1);
+		wmb();
+	}
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(action) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(rts_table) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(offset);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vp_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				vpath->hldev->config.device_poll_millis);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&vp_reg->rts_access_steer_ctrl);
+
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS)
+		status = VXGE_HW_OK;
+	else
+		status = VXGE_HW_FAIL;
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_addr_get - Get the hw address entry for this vpath
+ *               from MAC address table.
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_addr_get(
+	u32 vp_id, struct vxge_hw_vpath_reg __iomem *vpath_reg,
+	u8 (macaddr)[ETH_ALEN], u8 (macaddr_mask)[ETH_ALEN])
+{
+	u32 i;
+	u64 val64;
+	u64 data1 = 0ULL;
+	u64 data2 = 0ULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	val64 = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA) |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE |
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(0);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vpath_reg->rts_access_steer_ctrl,
+				VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE,
+				VXGE_HW_DEF_DEVICE_POLL_MILLIS);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&vpath_reg->rts_access_steer_ctrl);
+
+	if (val64 & VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS) {
+
+		data1 = readq(&vpath_reg->rts_access_steer_data0);
+		data2 = readq(&vpath_reg->rts_access_steer_data1);
+
+		data1 = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(data1);
+		data2 = VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK(
+							data2);
+
+		for (i = ETH_ALEN; i > 0; i--) {
+			macaddr[i-1] = (u8)(data1 & 0xFF);
+			data1 >>= 8;
+
+			macaddr_mask[i-1] = (u8)(data2 & 0xFF);
+			data2 >>= 8;
+		}
+		status = VXGE_HW_OK;
+	} else
+		status = VXGE_HW_FAIL;
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_vpath_rts_rth_set - Set/configure RTS hashing.
+ */
+enum vxge_hw_status vxge_hw_vpath_rts_rth_set(
+			struct __vxge_hw_vpath_handle *vp,
+			enum vxge_hw_rth_algoritms algorithm,
+			struct vxge_hw_rth_hash_types *hash_type,
+			u16 bucket_size)
+{
+	u64 data0, data1;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_rts_table_get(vp,
+		     VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY,
+		     VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG,
+			0, &data0, &data1);
+
+	data0 &= ~(VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_BUCKET_SIZE(0xf) |
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL(0x3));
+
+	data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_EN |
+	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_BUCKET_SIZE(bucket_size) |
+	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL(algorithm);
+
+	if (hash_type->hash_type_tcpipv4_en)
+		data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_TCP_IPV4_EN;
+
+	if (hash_type->hash_type_ipv4_en)
+		data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_IPV4_EN;
+
+	if (hash_type->hash_type_tcpipv6_en)
+		data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_TCP_IPV6_EN;
+
+	if (hash_type->hash_type_ipv6_en)
+		data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_IPV6_EN;
+
+	if (hash_type->hash_type_tcpipv6ex_en)
+		data0 |=
+		VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_TCP_IPV6_EX_EN;
+
+	if (hash_type->hash_type_ipv6ex_en)
+		data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_IPV6_EX_EN;
+
+	if (VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_ACTIVE_TABLE(data0))
+		data0 &= ~VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ACTIVE_TABLE;
+	else
+		data0 |= VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ACTIVE_TABLE;
+
+	status = __vxge_hw_vpath_rts_table_set(vp,
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_WRITE_ENTRY,
+		VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG,
+		0, data0, 0);
+exit:
+	return status;
+}
+
+static void
+vxge_hw_rts_rth_data0_data1_get(u32 j, u64 *data0, u64 *data1,
+				u16 flag, u8 *itable)
+{
+	switch (flag) {
+	case 1:
+		*data0 = VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_NUM(j)|
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_ENTRY_EN |
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_DATA(
+			itable[j]);
+	case 2:
+		*data0 |=
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_NUM(j)|
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_ENTRY_EN |
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_DATA(
+			itable[j]);
+	case 3:
+		*data1 = VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_NUM(j)|
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_ENTRY_EN |
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_DATA(
+			itable[j]);
+	case 4:
+		*data1 |=
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_NUM(j)|
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_ENTRY_EN |
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_DATA(
+			itable[j]);
+	default:
+		return;
+	}
+}
+/*
+ * vxge_hw_vpath_rts_rth_itable_set - Set/configure indirection table (IT).
+ */
+enum vxge_hw_status vxge_hw_vpath_rts_rth_itable_set(
+			struct __vxge_hw_vpath_handle **vpath_handles,
+			u32 vpath_count,
+			u8 *mtable,
+			u8 *itable,
+			u32 itable_size)
+{
+	u32 i, j, action, rts_table;
+	u64 data0;
+	u64 data1;
+	u32 max_entries;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_vpath_handle *vp = vpath_handles[0];
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	max_entries = (((u32)1) << itable_size);
+
+	if (vp->vpath->hldev->config.rth_it_type
+				== VXGE_HW_RTH_IT_TYPE_SOLO_IT) {
+		action = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_WRITE_ENTRY;
+		rts_table =
+			VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT;
+
+		for (j = 0; j < max_entries; j++) {
+
+			data1 = 0;
+
+			data0 =
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_SOLO_IT_BUCKET_DATA(
+				itable[j]);
+
+			status = __vxge_hw_vpath_rts_table_set(vpath_handles[0],
+				action, rts_table, j, data0, data1);
+
+			if (status != VXGE_HW_OK)
+				goto exit;
+		}
+
+		for (j = 0; j < max_entries; j++) {
+
+			data1 = 0;
+
+			data0 =
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_SOLO_IT_ENTRY_EN |
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_SOLO_IT_BUCKET_DATA(
+				itable[j]);
+
+			status = __vxge_hw_vpath_rts_table_set(
+				vpath_handles[mtable[itable[j]]], action,
+				rts_table, j, data0, data1);
+
+			if (status != VXGE_HW_OK)
+				goto exit;
+		}
+	} else {
+		action = VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_WRITE_ENTRY;
+		rts_table =
+			VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT;
+		for (i = 0; i < vpath_count; i++) {
+
+			for (j = 0; j < max_entries;) {
+
+				data0 = 0;
+				data1 = 0;
+
+				while (j < max_entries) {
+					if (mtable[itable[j]] != i) {
+						j++;
+						continue;
+					}
+					vxge_hw_rts_rth_data0_data1_get(j,
+						&data0, &data1, 1, itable);
+					j++;
+					break;
+				}
+
+				while (j < max_entries) {
+					if (mtable[itable[j]] != i) {
+						j++;
+						continue;
+					}
+					vxge_hw_rts_rth_data0_data1_get(j,
+						&data0, &data1, 2, itable);
+					j++;
+					break;
+				}
+
+				while (j < max_entries) {
+					if (mtable[itable[j]] != i) {
+						j++;
+						continue;
+					}
+					vxge_hw_rts_rth_data0_data1_get(j,
+						&data0, &data1, 3, itable);
+					j++;
+					break;
+				}
+
+				while (j < max_entries) {
+					if (mtable[itable[j]] != i) {
+						j++;
+						continue;
+					}
+					vxge_hw_rts_rth_data0_data1_get(j,
+						&data0, &data1, 4, itable);
+					j++;
+					break;
+				}
+
+				if (data0 != 0) {
+					status = __vxge_hw_vpath_rts_table_set(
+							vpath_handles[i],
+							action, rts_table,
+							0, data0, data1);
+
+					if (status != VXGE_HW_OK)
+						goto exit;
+				}
+			}
+		}
+	}
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_check_leak - Check for memory leak
+ * @ringh: Handle to the ring object used for receive
+ *
+ * If PRC_RXD_DOORBELL_VPn.NEW_QW_CNT is larger or equal to
+ * PRC_CFG6_VPn.RXD_SPAT then a leak has occurred.
+ * Returns: VXGE_HW_FAIL, if leak has occurred.
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_check_leak(struct __vxge_hw_ring *ring)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	u64 rxd_new_count, rxd_spat;
+
+	if (ring == NULL)
+		return status;
+
+	rxd_new_count = readl(&ring->vp_reg->prc_rxd_doorbell);
+	rxd_spat = readq(&ring->vp_reg->prc_cfg6);
+	rxd_spat = VXGE_HW_PRC_CFG6_RXD_SPAT(rxd_spat);
+
+	if (rxd_new_count >= rxd_spat)
+		status = VXGE_HW_FAIL;
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_mgmt_read
+ * This routine reads the vpath_mgmt registers
+ */
+static enum vxge_hw_status
+__vxge_hw_vpath_mgmt_read(
+	struct __vxge_hw_device *hldev,
+	struct __vxge_hw_virtualpath *vpath)
+{
+	u32 i, mtu = 0, max_pyld = 0;
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	for (i = 0; i < VXGE_HW_MAC_MAX_MAC_PORT_ID; i++) {
+
+		val64 = readq(&vpath->vpmgmt_reg->
+				rxmac_cfg0_port_vpmgmt_clone[i]);
+		max_pyld =
+			(u32)
+			VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_GET_MAX_PYLD_LEN
+			(val64);
+		if (mtu < max_pyld)
+			mtu = max_pyld;
+	}
+
+	vpath->max_mtu = mtu + VXGE_HW_MAC_HEADER_MAX_SIZE;
+
+	val64 = readq(&vpath->vpmgmt_reg->xmac_vsport_choices_vp);
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		if (val64 & vxge_mBIT(i))
+			vpath->vsport_number = i;
+	}
+
+	val64 = readq(&vpath->vpmgmt_reg->xgmac_gen_status_vpmgmt_clone);
+
+	if (val64 & VXGE_HW_XGMAC_GEN_STATUS_VPMGMT_CLONE_XMACJ_NTWK_OK)
+		VXGE_HW_DEVICE_LINK_STATE_SET(vpath->hldev, VXGE_HW_LINK_UP);
+	else
+		VXGE_HW_DEVICE_LINK_STATE_SET(vpath->hldev, VXGE_HW_LINK_DOWN);
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_reset_check - Check if resetting the vpath completed
+ * This routine checks the vpath_rst_in_prog register to see if
+ * adapter completed the reset process for the vpath
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_reset_check(struct __vxge_hw_virtualpath *vpath)
+{
+	enum vxge_hw_status status;
+
+	status = __vxge_hw_device_register_poll(
+			&vpath->hldev->common_reg->vpath_rst_in_prog,
+			VXGE_HW_VPATH_RST_IN_PROG_VPATH_RST_IN_PROG(
+				1 << (16 - vpath->vp_id)),
+			vpath->hldev->config.device_poll_millis);
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_reset
+ * This routine resets the vpath on the device
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_reset(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	val64 = VXGE_HW_CMN_RSTHDLR_CFG0_SW_RESET_VPATH(1 << (16 - vp_id));
+
+	__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(val64, 0, 32),
+				&hldev->common_reg->cmn_rsthdlr_cfg0);
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_sw_reset
+ * This routine resets the vpath structures
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_sw_reset(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_virtualpath *vpath;
+
+	vpath = (struct __vxge_hw_virtualpath *)&hldev->virtual_paths[vp_id];
+
+	if (vpath->ringh) {
+		status = __vxge_hw_ring_reset(vpath->ringh);
+		if (status != VXGE_HW_OK)
+			goto exit;
+	}
+
+	if (vpath->fifoh)
+		status = __vxge_hw_fifo_reset(vpath->fifoh);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_prc_configure
+ * This routine configures the prc registers of virtual path using the config
+ * passed
+ */
+void
+__vxge_hw_vpath_prc_configure(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	struct vxge_hw_vp_config *vp_config;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	vpath = &hldev->virtual_paths[vp_id];
+	vp_reg = vpath->vp_reg;
+	vp_config = vpath->vp_config;
+
+	if (vp_config->ring.enable == VXGE_HW_RING_DISABLE)
+		return;
+
+	val64 = readq(&vp_reg->prc_cfg1);
+	val64 |= VXGE_HW_PRC_CFG1_RTI_TINT_DISABLE;
+	writeq(val64, &vp_reg->prc_cfg1);
+
+	val64 = readq(&vpath->vp_reg->prc_cfg6);
+	val64 |= VXGE_HW_PRC_CFG6_DOORBELL_MODE_EN;
+	writeq(val64, &vpath->vp_reg->prc_cfg6);
+
+	val64 = readq(&vp_reg->prc_cfg7);
+
+	if (vpath->vp_config->ring.scatter_mode !=
+		VXGE_HW_RING_SCATTER_MODE_USE_FLASH_DEFAULT) {
+
+		val64 &= ~VXGE_HW_PRC_CFG7_SCATTER_MODE(0x3);
+
+		switch (vpath->vp_config->ring.scatter_mode) {
+		case VXGE_HW_RING_SCATTER_MODE_A:
+			val64 |= VXGE_HW_PRC_CFG7_SCATTER_MODE(
+					VXGE_HW_PRC_CFG7_SCATTER_MODE_A);
+			break;
+		case VXGE_HW_RING_SCATTER_MODE_B:
+			val64 |= VXGE_HW_PRC_CFG7_SCATTER_MODE(
+					VXGE_HW_PRC_CFG7_SCATTER_MODE_B);
+			break;
+		case VXGE_HW_RING_SCATTER_MODE_C:
+			val64 |= VXGE_HW_PRC_CFG7_SCATTER_MODE(
+					VXGE_HW_PRC_CFG7_SCATTER_MODE_C);
+			break;
+		}
+	}
+
+	writeq(val64, &vp_reg->prc_cfg7);
+
+	writeq(VXGE_HW_PRC_CFG5_RXD0_ADD(
+				__vxge_hw_ring_first_block_address_get(
+					vpath->ringh) >> 3), &vp_reg->prc_cfg5);
+
+	val64 = readq(&vp_reg->prc_cfg4);
+	val64 |= VXGE_HW_PRC_CFG4_IN_SVC;
+	val64 &= ~VXGE_HW_PRC_CFG4_RING_MODE(0x3);
+
+	val64 |= VXGE_HW_PRC_CFG4_RING_MODE(
+			VXGE_HW_PRC_CFG4_RING_MODE_ONE_BUFFER);
+
+	if (hldev->config.rth_en == VXGE_HW_RTH_DISABLE)
+		val64 |= VXGE_HW_PRC_CFG4_RTH_DISABLE;
+	else
+		val64 &= ~VXGE_HW_PRC_CFG4_RTH_DISABLE;
+
+	writeq(val64, &vp_reg->prc_cfg4);
+	return;
+}
+
+/*
+ * __vxge_hw_vpath_kdfc_configure
+ * This routine configures the kdfc registers of virtual path using the
+ * config passed
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_kdfc_configure(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	u64 val64;
+	u64 vpath_stride;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_virtualpath *vpath;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	vpath = &hldev->virtual_paths[vp_id];
+	vp_reg = vpath->vp_reg;
+	status = __vxge_hw_kdfc_swapper_set(hldev->legacy_reg, vp_reg);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	val64 = readq(&vp_reg->kdfc_drbl_triplet_total);
+
+	vpath->max_kdfc_db =
+		(u32)VXGE_HW_KDFC_DRBL_TRIPLET_TOTAL_GET_KDFC_MAX_SIZE(
+			val64+1)/2;
+
+	if (vpath->vp_config->fifo.enable == VXGE_HW_FIFO_ENABLE) {
+
+		vpath->max_nofl_db = vpath->max_kdfc_db;
+
+		if (vpath->max_nofl_db <
+			((vpath->vp_config->fifo.memblock_size /
+			(vpath->vp_config->fifo.max_frags *
+			sizeof(struct vxge_hw_fifo_txd))) *
+			vpath->vp_config->fifo.fifo_blocks)) {
+
+			return VXGE_HW_BADCFG_FIFO_BLOCKS;
+		}
+		val64 = VXGE_HW_KDFC_FIFO_TRPL_PARTITION_LENGTH_0(
+				(vpath->max_nofl_db*2)-1);
+	}
+
+	writeq(val64, &vp_reg->kdfc_fifo_trpl_partition);
+
+	writeq(VXGE_HW_KDFC_FIFO_TRPL_CTRL_TRIPLET_ENABLE,
+		&vp_reg->kdfc_fifo_trpl_ctrl);
+
+	val64 = readq(&vp_reg->kdfc_trpl_fifo_0_ctrl);
+
+	val64 &= ~(VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_MODE(0x3) |
+		   VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_SELECT(0xFF));
+
+	val64 |= VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_MODE(
+		 VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_MODE_NON_OFFLOAD_ONLY) |
+#ifndef __BIG_ENDIAN
+		 VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_SWAP_EN |
+#endif
+		 VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_SELECT(0);
+
+	writeq(val64, &vp_reg->kdfc_trpl_fifo_0_ctrl);
+	writeq((u64)0, &vp_reg->kdfc_trpl_fifo_0_wb_address);
+	wmb();
+	vpath_stride = readq(&hldev->toc_reg->toc_kdfc_vpath_stride);
+
+	vpath->nofl_db =
+		(struct __vxge_hw_non_offload_db_wrapper __iomem *)
+		(hldev->kdfc + (vp_id *
+		VXGE_HW_TOC_KDFC_VPATH_STRIDE_GET_TOC_KDFC_VPATH_STRIDE(
+					vpath_stride)));
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_mac_configure
+ * This routine configures the mac of virtual path using the config passed
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_mac_configure(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_virtualpath *vpath;
+	struct vxge_hw_vp_config *vp_config;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	vpath = &hldev->virtual_paths[vp_id];
+	vp_reg = vpath->vp_reg;
+	vp_config = vpath->vp_config;
+
+	writeq(VXGE_HW_XMAC_VSPORT_CHOICE_VSPORT_NUMBER(
+			vpath->vsport_number), &vp_reg->xmac_vsport_choice);
+
+	if (vp_config->ring.enable == VXGE_HW_RING_ENABLE) {
+
+		val64 = readq(&vp_reg->xmac_rpa_vcfg);
+
+		if (vp_config->rpa_strip_vlan_tag !=
+			VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_USE_FLASH_DEFAULT) {
+			if (vp_config->rpa_strip_vlan_tag)
+				val64 |= VXGE_HW_XMAC_RPA_VCFG_STRIP_VLAN_TAG;
+			else
+				val64 &= ~VXGE_HW_XMAC_RPA_VCFG_STRIP_VLAN_TAG;
+		}
+
+		writeq(val64, &vp_reg->xmac_rpa_vcfg);
+		val64 = readq(&vp_reg->rxmac_vcfg0);
+
+		if (vp_config->mtu !=
+				VXGE_HW_VPATH_USE_FLASH_DEFAULT_INITIAL_MTU) {
+			val64 &= ~VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(0x3fff);
+			if ((vp_config->mtu  +
+				VXGE_HW_MAC_HEADER_MAX_SIZE) < vpath->max_mtu)
+				val64 |= VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(
+					vp_config->mtu  +
+					VXGE_HW_MAC_HEADER_MAX_SIZE);
+			else
+				val64 |= VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(
+					vpath->max_mtu);
+		}
+
+		writeq(val64, &vp_reg->rxmac_vcfg0);
+
+		val64 = readq(&vp_reg->rxmac_vcfg1);
+
+		val64 &= ~(VXGE_HW_RXMAC_VCFG1_RTS_RTH_MULTI_IT_BD_MODE(0x3) |
+			VXGE_HW_RXMAC_VCFG1_RTS_RTH_MULTI_IT_EN_MODE);
+
+		if (hldev->config.rth_it_type ==
+				VXGE_HW_RTH_IT_TYPE_MULTI_IT) {
+			val64 |= VXGE_HW_RXMAC_VCFG1_RTS_RTH_MULTI_IT_BD_MODE(
+				0x2) |
+				VXGE_HW_RXMAC_VCFG1_RTS_RTH_MULTI_IT_EN_MODE;
+		}
+
+		writeq(val64, &vp_reg->rxmac_vcfg1);
+	}
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_tim_configure
+ * This routine configures the tim registers of virtual path using the config
+ * passed
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_tim_configure(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_virtualpath *vpath;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+	struct vxge_hw_vp_config *config;
+
+	vpath = &hldev->virtual_paths[vp_id];
+	vp_reg = vpath->vp_reg;
+	config = vpath->vp_config;
+
+	writeq((u64)0, &vp_reg->tim_dest_addr);
+	writeq((u64)0, &vp_reg->tim_vpath_map);
+	writeq((u64)0, &vp_reg->tim_bitmap);
+	writeq((u64)0, &vp_reg->tim_remap);
+
+	if (config->ring.enable == VXGE_HW_RING_ENABLE)
+		writeq(VXGE_HW_TIM_RING_ASSN_INT_NUM(
+			(vp_id * VXGE_HW_MAX_INTR_PER_VP) +
+			VXGE_HW_VPATH_INTR_RX), &vp_reg->tim_ring_assn);
+
+	val64 = readq(&vp_reg->tim_pci_cfg);
+	val64 |= VXGE_HW_TIM_PCI_CFG_ADD_PAD;
+	writeq(val64, &vp_reg->tim_pci_cfg);
+
+	if (config->fifo.enable == VXGE_HW_FIFO_ENABLE) {
+
+		val64 = readq(&vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]);
+
+		if (config->tti.btimer_val != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_BTIMER_VAL(
+				0x3ffffff);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_BTIMER_VAL(
+					config->tti.btimer_val);
+		}
+
+		val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_BITMP_EN;
+
+		if (config->tti.timer_ac_en != VXGE_HW_USE_FLASH_DEFAULT) {
+			if (config->tti.timer_ac_en)
+				val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_AC;
+			else
+				val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_TIMER_AC;
+		}
+
+		if (config->tti.timer_ci_en != VXGE_HW_USE_FLASH_DEFAULT) {
+			if (config->tti.timer_ci_en)
+				val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI;
+			else
+				val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI;
+		}
+
+		if (config->tti.urange_a != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_URNG_A(0x3f);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_URNG_A(
+					config->tti.urange_a);
+		}
+
+		if (config->tti.urange_b != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_URNG_B(0x3f);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_URNG_B(
+					config->tti.urange_b);
+		}
+
+		if (config->tti.urange_c != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_URNG_C(0x3f);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_URNG_C(
+					config->tti.urange_c);
+		}
+
+		writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_TX]);
+		val64 = readq(&vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_TX]);
+
+		if (config->tti.uec_a != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_A(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_A(
+						config->tti.uec_a);
+		}
+
+		if (config->tti.uec_b != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_B(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_B(
+						config->tti.uec_b);
+		}
+
+		if (config->tti.uec_c != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_C(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_C(
+						config->tti.uec_c);
+		}
+
+		if (config->tti.uec_d != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_D(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_D(
+						config->tti.uec_d);
+		}
+
+		writeq(val64, &vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_TX]);
+		val64 = readq(&vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_TX]);
+
+		if (config->tti.timer_ri_en != VXGE_HW_USE_FLASH_DEFAULT) {
+			if (config->tti.timer_ri_en)
+				val64 |= VXGE_HW_TIM_CFG3_INT_NUM_TIMER_RI;
+			else
+				val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_TIMER_RI;
+		}
+
+		if (config->tti.rtimer_val != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(
+					0x3ffffff);
+			val64 |= VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(
+					config->tti.rtimer_val);
+		}
+
+		if (config->tti.util_sel != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_UTIL_SEL(0x3f);
+			val64 |= VXGE_HW_TIM_CFG3_INT_NUM_UTIL_SEL(
+					config->tti.util_sel);
+		}
+
+		if (config->tti.ltimer_val != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_LTIMER_VAL(
+					0x3ffffff);
+			val64 |= VXGE_HW_TIM_CFG3_INT_NUM_LTIMER_VAL(
+					config->tti.ltimer_val);
+		}
+
+		writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_TX]);
+	}
+
+	if (config->ring.enable == VXGE_HW_RING_ENABLE) {
+
+		val64 = readq(&vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_RX]);
+
+		if (config->rti.btimer_val != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_BTIMER_VAL(
+					0x3ffffff);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_BTIMER_VAL(
+					config->rti.btimer_val);
+		}
+
+		val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_BITMP_EN;
+
+		if (config->rti.timer_ac_en != VXGE_HW_USE_FLASH_DEFAULT) {
+			if (config->rti.timer_ac_en)
+				val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_AC;
+			else
+				val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_TIMER_AC;
+		}
+
+		if (config->rti.timer_ci_en != VXGE_HW_USE_FLASH_DEFAULT) {
+			if (config->rti.timer_ci_en)
+				val64 |= VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI;
+			else
+				val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI;
+		}
+
+		if (config->rti.urange_a != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_URNG_A(0x3f);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_URNG_A(
+					config->rti.urange_a);
+		}
+
+		if (config->rti.urange_b != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_URNG_B(0x3f);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_URNG_B(
+					config->rti.urange_b);
+		}
+
+		if (config->rti.urange_c != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG1_INT_NUM_URNG_C(0x3f);
+			val64 |= VXGE_HW_TIM_CFG1_INT_NUM_URNG_C(
+					config->rti.urange_c);
+		}
+
+		writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_RX]);
+		val64 = readq(&vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_RX]);
+
+		if (config->rti.uec_a != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_A(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_A(
+						config->rti.uec_a);
+		}
+
+		if (config->rti.uec_b != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_B(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_B(
+						config->rti.uec_b);
+		}
+
+		if (config->rti.uec_c != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_C(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_C(
+						config->rti.uec_c);
+		}
+
+		if (config->rti.uec_d != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG2_INT_NUM_UEC_D(0xffff);
+			val64 |= VXGE_HW_TIM_CFG2_INT_NUM_UEC_D(
+						config->rti.uec_d);
+		}
+
+		writeq(val64, &vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_RX]);
+		val64 = readq(&vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_RX]);
+
+		if (config->rti.timer_ri_en != VXGE_HW_USE_FLASH_DEFAULT) {
+			if (config->rti.timer_ri_en)
+				val64 |= VXGE_HW_TIM_CFG3_INT_NUM_TIMER_RI;
+			else
+				val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_TIMER_RI;
+		}
+
+		if (config->rti.rtimer_val != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(
+					0x3ffffff);
+			val64 |= VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(
+					config->rti.rtimer_val);
+		}
+
+		if (config->rti.util_sel != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_UTIL_SEL(0x3f);
+			val64 |= VXGE_HW_TIM_CFG3_INT_NUM_UTIL_SEL(
+					config->rti.util_sel);
+		}
+
+		if (config->rti.ltimer_val != VXGE_HW_USE_FLASH_DEFAULT) {
+			val64 &= ~VXGE_HW_TIM_CFG3_INT_NUM_LTIMER_VAL(
+					0x3ffffff);
+			val64 |= VXGE_HW_TIM_CFG3_INT_NUM_LTIMER_VAL(
+					config->rti.ltimer_val);
+		}
+
+		writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_RX]);
+	}
+
+	val64 = 0;
+	writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_EINTA]);
+	writeq(val64, &vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_EINTA]);
+	writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_EINTA]);
+	writeq(val64, &vp_reg->tim_cfg1_int_num[VXGE_HW_VPATH_INTR_BMAP]);
+	writeq(val64, &vp_reg->tim_cfg2_int_num[VXGE_HW_VPATH_INTR_BMAP]);
+	writeq(val64, &vp_reg->tim_cfg3_int_num[VXGE_HW_VPATH_INTR_BMAP]);
+
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_initialize
+ * This routine is the final phase of init which initializes the
+ * registers of the vpath using the configuration passed.
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_initialize(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	u64 val64;
+	u32 val32;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_virtualpath *vpath;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	vpath = &hldev->virtual_paths[vp_id];
+
+	if (!(hldev->vpath_assignments & vxge_mBIT(vp_id))) {
+		status = VXGE_HW_ERR_VPATH_NOT_AVAILABLE;
+		goto exit;
+	}
+	vp_reg = vpath->vp_reg;
+
+	status =  __vxge_hw_vpath_swapper_set(vpath->vp_reg);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	status =  __vxge_hw_vpath_mac_configure(hldev, vp_id);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	status =  __vxge_hw_vpath_kdfc_configure(hldev, vp_id);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	status = __vxge_hw_vpath_tim_configure(hldev, vp_id);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	writeq(0, &vp_reg->gendma_int);
+
+	val64 = readq(&vp_reg->rtdma_rd_optimization_ctrl);
+
+	/* Get MRRS value from device control */
+	status  = __vxge_hw_vpath_pci_read(vpath, 1, 0x78, &val32);
+
+	if (status == VXGE_HW_OK) {
+		val32 = (val32 & VXGE_HW_PCI_EXP_DEVCTL_READRQ) >> 12;
+		val64 &=
+		    ~(VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_FILL_THRESH(7));
+		val64 |=
+		    VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_FILL_THRESH(val32);
+
+		val64 |= VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_WAIT_FOR_SPACE;
+	}
+
+	val64 &= ~(VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_ADDR_BDRY(7));
+	val64 |=
+	    VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_ADDR_BDRY(
+		    VXGE_HW_MAX_PAYLOAD_SIZE_512);
+
+	val64 |= VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_ADDR_BDRY_EN;
+	writeq(val64, &vp_reg->rtdma_rd_optimization_ctrl);
+
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vp_initialize - Initialize Virtual Path structure
+ * This routine is the initial phase of init which resets the vpath and
+ * initializes the software support structures.
+ */
+enum vxge_hw_status
+__vxge_hw_vp_initialize(struct __vxge_hw_device *hldev, u32 vp_id,
+			struct vxge_hw_vp_config *config)
+{
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (!(hldev->vpath_assignments & vxge_mBIT(vp_id))) {
+		status = VXGE_HW_ERR_VPATH_NOT_AVAILABLE;
+		goto exit;
+	}
+
+	vpath = &hldev->virtual_paths[vp_id];
+
+	vpath->vp_id = vp_id;
+	vpath->vp_open = VXGE_HW_VP_OPEN;
+	vpath->hldev = hldev;
+	vpath->vp_config = config;
+	vpath->vp_reg = hldev->vpath_reg[vp_id];
+	vpath->vpmgmt_reg = hldev->vpmgmt_reg[vp_id];
+
+	__vxge_hw_vpath_reset(hldev, vp_id);
+
+	status = __vxge_hw_vpath_reset_check(vpath);
+
+	if (status != VXGE_HW_OK) {
+		memset(vpath, 0, sizeof(struct __vxge_hw_virtualpath));
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_mgmt_read(hldev, vpath);
+
+	if (status != VXGE_HW_OK) {
+		memset(vpath, 0, sizeof(struct __vxge_hw_virtualpath));
+		goto exit;
+	}
+
+	INIT_LIST_HEAD(&vpath->vpath_handles);
+
+	vpath->sw_stats = &hldev->stats.sw_dev_info_stats.vpath_info[vp_id];
+
+	VXGE_HW_DEVICE_TIM_INT_MASK_SET(hldev->tim_int_mask0,
+		hldev->tim_int_mask1, vp_id);
+
+	status = __vxge_hw_vpath_initialize(hldev, vp_id);
+
+	if (status != VXGE_HW_OK)
+		__vxge_hw_vp_terminate(hldev, vp_id);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vp_terminate - Terminate Virtual Path structure
+ * This routine closes all channels it opened and freeup memory
+ */
+void
+__vxge_hw_vp_terminate(struct __vxge_hw_device *hldev, u32 vp_id)
+{
+	struct __vxge_hw_virtualpath *vpath;
+
+	vpath = &hldev->virtual_paths[vp_id];
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN)
+		goto exit;
+
+	VXGE_HW_DEVICE_TIM_INT_MASK_RESET(vpath->hldev->tim_int_mask0,
+		vpath->hldev->tim_int_mask1, vpath->vp_id);
+	hldev->stats.hw_dev_info_stats.vpath_info[vpath->vp_id] = NULL;
+
+	memset(vpath, 0, sizeof(struct __vxge_hw_virtualpath));
+exit:
+	return;
+}
+
+/*
+ * vxge_hw_vpath_mtu_set - Set MTU.
+ * Set new MTU value. Example, to use jumbo frames:
+ * vxge_hw_vpath_mtu_set(my_device, 9600);
+ */
+enum vxge_hw_status
+vxge_hw_vpath_mtu_set(struct __vxge_hw_vpath_handle *vp, u32 new_mtu)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_virtualpath *vpath;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+	vpath = vp->vpath;
+
+	new_mtu += VXGE_HW_MAC_HEADER_MAX_SIZE;
+
+	if ((new_mtu < VXGE_HW_MIN_MTU) || (new_mtu > vpath->max_mtu))
+		status = VXGE_HW_ERR_INVALID_MTU_SIZE;
+
+	val64 = readq(&vpath->vp_reg->rxmac_vcfg0);
+
+	val64 &= ~VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(0x3fff);
+	val64 |= VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(new_mtu);
+
+	writeq(val64, &vpath->vp_reg->rxmac_vcfg0);
+
+	vpath->vp_config->mtu = new_mtu - VXGE_HW_MAC_HEADER_MAX_SIZE;
+
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_vpath_open - Open a virtual path on a given adapter
+ * This function is used to open access to virtual path of an
+ * adapter for offload, GRO operations. This function returns
+ * synchronously.
+ */
+enum vxge_hw_status
+vxge_hw_vpath_open(struct __vxge_hw_device *hldev,
+		   struct vxge_hw_vpath_attr *attr,
+		   struct __vxge_hw_vpath_handle **vpath_handle)
+{
+	struct __vxge_hw_virtualpath *vpath;
+	struct __vxge_hw_vpath_handle *vp;
+	enum vxge_hw_status status;
+
+	vpath = &hldev->virtual_paths[attr->vp_id];
+
+	if (vpath->vp_open == VXGE_HW_VP_OPEN) {
+		status = VXGE_HW_ERR_INVALID_STATE;
+		goto vpath_open_exit1;
+	}
+
+	status = __vxge_hw_vp_initialize(hldev, attr->vp_id,
+			&hldev->config.vp_config[attr->vp_id]);
+
+	if (status != VXGE_HW_OK)
+		goto vpath_open_exit1;
+
+	vp = (struct __vxge_hw_vpath_handle *)
+		vmalloc(sizeof(struct __vxge_hw_vpath_handle));
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto vpath_open_exit2;
+	}
+
+	memset(vp, 0, sizeof(struct __vxge_hw_vpath_handle));
+
+	vp->vpath = vpath;
+
+	if (vpath->vp_config->fifo.enable == VXGE_HW_FIFO_ENABLE) {
+		status = __vxge_hw_fifo_create(vp, &attr->fifo_attr);
+		if (status != VXGE_HW_OK)
+			goto vpath_open_exit6;
+	}
+
+	if (vpath->vp_config->ring.enable == VXGE_HW_RING_ENABLE) {
+		status = __vxge_hw_ring_create(vp, &attr->ring_attr);
+		if (status != VXGE_HW_OK)
+			goto vpath_open_exit7;
+
+		__vxge_hw_vpath_prc_configure(hldev, attr->vp_id);
+	}
+
+	vpath->fifoh->tx_intr_num =
+		(attr->vp_id * VXGE_HW_MAX_INTR_PER_VP)  +
+			VXGE_HW_VPATH_INTR_TX;
+
+	vpath->stats_block = __vxge_hw_blockpool_block_allocate(hldev,
+				VXGE_HW_BLOCK_SIZE);
+
+	if (vpath->stats_block == NULL) {
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+		goto vpath_open_exit8;
+	}
+
+	vpath->hw_stats = (struct vxge_hw_vpath_stats_hw_info *)vpath->
+			stats_block->memblock;
+	memset(vpath->hw_stats, 0,
+		sizeof(struct vxge_hw_vpath_stats_hw_info));
+
+	hldev->stats.hw_dev_info_stats.vpath_info[attr->vp_id] =
+						vpath->hw_stats;
+
+	vpath->hw_stats_sav =
+		&hldev->stats.hw_dev_info_stats.vpath_info_sav[attr->vp_id];
+	memset(vpath->hw_stats_sav, 0,
+			sizeof(struct vxge_hw_vpath_stats_hw_info));
+
+	writeq(vpath->stats_block->dma_addr, &vpath->vp_reg->stats_cfg);
+
+	status = vxge_hw_vpath_stats_enable(vp);
+	if (status != VXGE_HW_OK)
+		goto vpath_open_exit8;
+
+	list_add(&vp->item, &vpath->vpath_handles);
+
+	hldev->vpaths_deployed |= vxge_mBIT(vpath->vp_id);
+
+	*vpath_handle = vp;
+
+	attr->fifo_attr.userdata = vpath->fifoh;
+	attr->ring_attr.userdata = vpath->ringh;
+
+	return VXGE_HW_OK;
+
+vpath_open_exit8:
+	if (vpath->ringh != NULL)
+		__vxge_hw_ring_delete(vp);
+vpath_open_exit7:
+	if (vpath->fifoh != NULL)
+		__vxge_hw_fifo_delete(vp);
+vpath_open_exit6:
+	vfree(vp);
+vpath_open_exit2:
+	__vxge_hw_vp_terminate(hldev, attr->vp_id);
+vpath_open_exit1:
+
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_rx_doorbell_post - Close the handle got from previous vpath
+ * (vpath) open
+ * @vp: Handle got from previous vpath open
+ *
+ * This function is used to close access to virtual path opened
+ * earlier.
+ */
+void
+vxge_hw_vpath_rx_doorbell_init(struct __vxge_hw_vpath_handle *vp)
+{
+	struct __vxge_hw_virtualpath *vpath = NULL;
+	u64 new_count, val64, val164;
+	struct __vxge_hw_ring *ring;
+
+	vpath = vp->vpath;
+	ring = vpath->ringh;
+
+	new_count = readq(&vpath->vp_reg->rxdmem_size);
+	new_count &= 0x1fff;
+	val164 = (VXGE_HW_RXDMEM_SIZE_PRC_RXDMEM_SIZE(new_count));
+
+	writeq(VXGE_HW_PRC_RXD_DOORBELL_NEW_QW_CNT(val164),
+		&vpath->vp_reg->prc_rxd_doorbell);
+	readl(&vpath->vp_reg->prc_rxd_doorbell);
+
+	val164 /= 2;
+	val64 = readq(&vpath->vp_reg->prc_cfg6);
+	val64 = VXGE_HW_PRC_CFG6_RXD_SPAT(val64);
+	val64 &= 0x1ff;
+
+	/*
+	 * Each RxD is of 4 qwords
+	 */
+	new_count -= (val64 + 1);
+	val64 = min(val164, new_count) / 4;
+
+	ring->rxds_limit = min(ring->rxds_limit, val64);
+	if (ring->rxds_limit < 4)
+		ring->rxds_limit = 4;
+}
+
+/*
+ * vxge_hw_vpath_close - Close the handle got from previous vpath (vpath) open
+ * This function is used to close access to virtual path opened
+ * earlier.
+ */
+enum vxge_hw_status vxge_hw_vpath_close(struct __vxge_hw_vpath_handle *vp)
+{
+	struct __vxge_hw_virtualpath *vpath = NULL;
+	struct __vxge_hw_device *devh = NULL;
+	u32 vp_id = vp->vpath->vp_id;
+	u32 is_empty = TRUE;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	vpath = vp->vpath;
+	devh = vpath->hldev;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto vpath_close_exit;
+	}
+
+	list_del(&vp->item);
+
+	if (!list_empty(&vpath->vpath_handles)) {
+		list_add(&vp->item, &vpath->vpath_handles);
+		is_empty = FALSE;
+	}
+
+	if (!is_empty) {
+		status = VXGE_HW_FAIL;
+		goto vpath_close_exit;
+	}
+
+	devh->vpaths_deployed &= ~vxge_mBIT(vp_id);
+
+	if (vpath->ringh != NULL)
+		__vxge_hw_ring_delete(vp);
+
+	if (vpath->fifoh != NULL)
+		__vxge_hw_fifo_delete(vp);
+
+	if (vpath->stats_block != NULL)
+		__vxge_hw_blockpool_block_free(devh, vpath->stats_block);
+
+	vfree(vp);
+
+	__vxge_hw_vp_terminate(devh, vp_id);
+
+	vpath->vp_open = VXGE_HW_VP_NOT_OPEN;
+
+vpath_close_exit:
+	return status;
+}
+
+/*
+ * vxge_hw_vpath_reset - Resets vpath
+ * This function is used to request a reset of vpath
+ */
+enum vxge_hw_status vxge_hw_vpath_reset(struct __vxge_hw_vpath_handle *vp)
+{
+	enum vxge_hw_status status;
+	u32 vp_id;
+	struct __vxge_hw_virtualpath *vpath = vp->vpath;
+
+	vp_id = vpath->vp_id;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_reset(vpath->hldev, vp_id);
+	if (status == VXGE_HW_OK)
+		vpath->sw_stats->soft_reset_cnt++;
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_vpath_recover_from_reset - Poll for reset complete and re-initialize.
+ * This function poll's for the vpath reset completion and re initializes
+ * the vpath.
+ */
+enum vxge_hw_status
+vxge_hw_vpath_recover_from_reset(struct __vxge_hw_vpath_handle *vp)
+{
+	struct __vxge_hw_virtualpath *vpath = NULL;
+	enum vxge_hw_status status;
+	struct __vxge_hw_device *hldev;
+	u32 vp_id;
+
+	vp_id = vp->vpath->vp_id;
+	vpath = vp->vpath;
+	hldev = vpath->hldev;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_reset_check(vpath);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	status = __vxge_hw_vpath_sw_reset(hldev, vp_id);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	status = __vxge_hw_vpath_initialize(hldev, vp_id);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	if (vpath->ringh != NULL)
+		__vxge_hw_vpath_prc_configure(hldev, vp_id);
+
+	memset(vpath->hw_stats, 0,
+		sizeof(struct vxge_hw_vpath_stats_hw_info));
+
+	memset(vpath->hw_stats_sav, 0,
+		sizeof(struct vxge_hw_vpath_stats_hw_info));
+
+	writeq(vpath->stats_block->dma_addr,
+		&vpath->vp_reg->stats_cfg);
+
+	status = vxge_hw_vpath_stats_enable(vp);
+
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_vpath_enable - Enable vpath.
+ * This routine clears the vpath reset thereby enabling a vpath
+ * to start forwarding frames and generating interrupts.
+ */
+void
+vxge_hw_vpath_enable(struct __vxge_hw_vpath_handle *vp)
+{
+	struct __vxge_hw_device *hldev;
+	u64 val64;
+
+	hldev = vp->vpath->hldev;
+
+	val64 = VXGE_HW_CMN_RSTHDLR_CFG1_CLR_VPATH_RESET(
+		1 << (16 - vp->vpath->vp_id));
+
+	__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(val64, 0, 32),
+		&hldev->common_reg->cmn_rsthdlr_cfg1);
+}
+
+/*
+ * vxge_hw_vpath_stats_enable - Enable vpath h/wstatistics.
+ * Enable the DMA vpath statistics. The function is to be called to re-enable
+ * the adapter to update stats into the host memory
+ */
+enum vxge_hw_status
+vxge_hw_vpath_stats_enable(struct __vxge_hw_vpath_handle *vp)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_virtualpath *vpath;
+
+	vpath = vp->vpath;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+
+	memcpy(vpath->hw_stats_sav, vpath->hw_stats,
+			sizeof(struct vxge_hw_vpath_stats_hw_info));
+
+	status = __vxge_hw_vpath_stats_get(vpath, vpath->hw_stats);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_stats_access - Get the statistics from the given location
+ *                           and offset and perform an operation
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_stats_access(struct __vxge_hw_virtualpath *vpath,
+			     u32 operation, u32 offset, u64 *stat)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto vpath_stats_access_exit;
+	}
+
+	vp_reg = vpath->vp_reg;
+
+	val64 =  VXGE_HW_XMAC_STATS_ACCESS_CMD_OP(operation) |
+		 VXGE_HW_XMAC_STATS_ACCESS_CMD_STROBE |
+		 VXGE_HW_XMAC_STATS_ACCESS_CMD_OFFSET_SEL(offset);
+
+	status = __vxge_hw_pio_mem_write64(val64,
+				&vp_reg->xmac_stats_access_cmd,
+				VXGE_HW_XMAC_STATS_ACCESS_CMD_STROBE,
+				vpath->hldev->config.device_poll_millis);
+
+	if ((status == VXGE_HW_OK) && (operation == VXGE_HW_STATS_OP_READ))
+		*stat = readq(&vp_reg->xmac_stats_access_data);
+	else
+		*stat = 0;
+
+vpath_stats_access_exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_xmac_tx_stats_get - Get the TX Statistics of a vpath
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_xmac_tx_stats_get(
+	struct __vxge_hw_virtualpath *vpath,
+	struct vxge_hw_xmac_vpath_tx_stats *vpath_tx_stats)
+{
+	u64 *val64;
+	int i;
+	u32 offset = VXGE_HW_STATS_VPATH_TX_OFFSET;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	val64 = (u64 *) vpath_tx_stats;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+
+	for (i = 0; i < sizeof(struct vxge_hw_xmac_vpath_tx_stats) / 8; i++) {
+		status = __vxge_hw_vpath_stats_access(vpath,
+					VXGE_HW_STATS_OP_READ,
+					offset, val64);
+		if (status != VXGE_HW_OK)
+			goto exit;
+		offset++;
+		val64++;
+	}
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_xmac_rx_stats_get - Get the RX Statistics of a vpath
+ */
+enum vxge_hw_status
+__vxge_hw_vpath_xmac_rx_stats_get(struct __vxge_hw_virtualpath *vpath,
+			struct vxge_hw_xmac_vpath_rx_stats *vpath_rx_stats)
+{
+	u64 *val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	int i;
+	u32 offset = VXGE_HW_STATS_VPATH_RX_OFFSET;
+	val64 = (u64 *) vpath_rx_stats;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+	for (i = 0; i < sizeof(struct vxge_hw_xmac_vpath_rx_stats) / 8; i++) {
+		status = __vxge_hw_vpath_stats_access(vpath,
+					VXGE_HW_STATS_OP_READ,
+					offset >> 3, val64);
+		if (status != VXGE_HW_OK)
+			goto exit;
+
+		offset += 8;
+		val64++;
+	}
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_stats_get - Get the vpath hw statistics.
+ */
+enum vxge_hw_status __vxge_hw_vpath_stats_get(
+			struct __vxge_hw_virtualpath *vpath,
+			struct vxge_hw_vpath_stats_hw_info *hw_stats)
+{
+	u64 val64;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+	vp_reg = vpath->vp_reg;
+
+	val64 = readq(&vp_reg->vpath_debug_stats0);
+	hw_stats->ini_num_mwr_sent =
+		(u32)VXGE_HW_VPATH_DEBUG_STATS0_GET_INI_NUM_MWR_SENT(val64);
+
+	val64 = readq(&vp_reg->vpath_debug_stats1);
+	hw_stats->ini_num_mrd_sent =
+		(u32)VXGE_HW_VPATH_DEBUG_STATS1_GET_INI_NUM_MRD_SENT(val64);
+
+	val64 = readq(&vp_reg->vpath_debug_stats2);
+	hw_stats->ini_num_cpl_rcvd =
+		(u32)VXGE_HW_VPATH_DEBUG_STATS2_GET_INI_NUM_CPL_RCVD(val64);
+
+	val64 = readq(&vp_reg->vpath_debug_stats3);
+	hw_stats->ini_num_mwr_byte_sent =
+		VXGE_HW_VPATH_DEBUG_STATS3_GET_INI_NUM_MWR_BYTE_SENT(val64);
+
+	val64 = readq(&vp_reg->vpath_debug_stats4);
+	hw_stats->ini_num_cpl_byte_rcvd =
+		VXGE_HW_VPATH_DEBUG_STATS4_GET_INI_NUM_CPL_BYTE_RCVD(val64);
+
+	val64 = readq(&vp_reg->vpath_debug_stats5);
+	hw_stats->wrcrdtarb_xoff =
+		(u32)VXGE_HW_VPATH_DEBUG_STATS5_GET_WRCRDTARB_XOFF(val64);
+
+	val64 = readq(&vp_reg->vpath_debug_stats6);
+	hw_stats->rdcrdtarb_xoff =
+		(u32)VXGE_HW_VPATH_DEBUG_STATS6_GET_RDCRDTARB_XOFF(val64);
+
+	val64 = readq(&vp_reg->vpath_genstats_count01);
+	hw_stats->vpath_genstats_count0 =
+	(u32)VXGE_HW_VPATH_GENSTATS_COUNT01_GET_PPIF_VPATH_GENSTATS_COUNT0(
+		val64);
+
+	val64 = readq(&vp_reg->vpath_genstats_count01);
+	hw_stats->vpath_genstats_count1 =
+	(u32)VXGE_HW_VPATH_GENSTATS_COUNT01_GET_PPIF_VPATH_GENSTATS_COUNT1(
+		val64);
+
+	val64 = readq(&vp_reg->vpath_genstats_count23);
+	hw_stats->vpath_genstats_count2 =
+	(u32)VXGE_HW_VPATH_GENSTATS_COUNT23_GET_PPIF_VPATH_GENSTATS_COUNT2(
+		val64);
+
+	val64 = readq(&vp_reg->vpath_genstats_count01);
+	hw_stats->vpath_genstats_count3 =
+	(u32)VXGE_HW_VPATH_GENSTATS_COUNT23_GET_PPIF_VPATH_GENSTATS_COUNT3(
+		val64);
+
+	val64 = readq(&vp_reg->vpath_genstats_count4);
+	hw_stats->vpath_genstats_count4 =
+	(u32)VXGE_HW_VPATH_GENSTATS_COUNT4_GET_PPIF_VPATH_GENSTATS_COUNT4(
+		val64);
+
+	val64 = readq(&vp_reg->vpath_genstats_count5);
+	hw_stats->vpath_genstats_count5 =
+	(u32)VXGE_HW_VPATH_GENSTATS_COUNT5_GET_PPIF_VPATH_GENSTATS_COUNT5(
+		val64);
+
+	status = __vxge_hw_vpath_xmac_tx_stats_get(vpath, &hw_stats->tx_stats);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	status = __vxge_hw_vpath_xmac_rx_stats_get(vpath, &hw_stats->rx_stats);
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	VXGE_HW_VPATH_STATS_PIO_READ(
+		VXGE_HW_STATS_VPATH_PROG_EVENT_VNUM0_OFFSET);
+
+	hw_stats->prog_event_vnum0 =
+			(u32)VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM0(val64);
+
+	hw_stats->prog_event_vnum1 =
+			(u32)VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM1(val64);
+
+	VXGE_HW_VPATH_STATS_PIO_READ(
+		VXGE_HW_STATS_VPATH_PROG_EVENT_VNUM2_OFFSET);
+
+	hw_stats->prog_event_vnum2 =
+			(u32)VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM2(val64);
+
+	hw_stats->prog_event_vnum3 =
+			(u32)VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM3(val64);
+
+	val64 = readq(&vp_reg->rx_multi_cast_stats);
+	hw_stats->rx_multi_cast_frame_discard =
+		(u16)VXGE_HW_RX_MULTI_CAST_STATS_GET_FRAME_DISCARD(val64);
+
+	val64 = readq(&vp_reg->rx_frm_transferred);
+	hw_stats->rx_frm_transferred =
+		(u32)VXGE_HW_RX_FRM_TRANSFERRED_GET_RX_FRM_TRANSFERRED(val64);
+
+	val64 = readq(&vp_reg->rxd_returned);
+	hw_stats->rxd_returned =
+		(u16)VXGE_HW_RXD_RETURNED_GET_RXD_RETURNED(val64);
+
+	val64 = readq(&vp_reg->dbg_stats_rx_mpa);
+	hw_stats->rx_mpa_len_fail_frms =
+		(u16)VXGE_HW_DBG_STATS_GET_RX_MPA_LEN_FAIL_FRMS(val64);
+	hw_stats->rx_mpa_mrk_fail_frms =
+		(u16)VXGE_HW_DBG_STATS_GET_RX_MPA_MRK_FAIL_FRMS(val64);
+	hw_stats->rx_mpa_crc_fail_frms =
+		(u16)VXGE_HW_DBG_STATS_GET_RX_MPA_CRC_FAIL_FRMS(val64);
+
+	val64 = readq(&vp_reg->dbg_stats_rx_fau);
+	hw_stats->rx_permitted_frms =
+		(u16)VXGE_HW_DBG_STATS_GET_RX_FAU_RX_PERMITTED_FRMS(val64);
+	hw_stats->rx_vp_reset_discarded_frms =
+	(u16)VXGE_HW_DBG_STATS_GET_RX_FAU_RX_VP_RESET_DISCARDED_FRMS(val64);
+	hw_stats->rx_wol_frms =
+		(u16)VXGE_HW_DBG_STATS_GET_RX_FAU_RX_WOL_FRMS(val64);
+
+	val64 = readq(&vp_reg->tx_vp_reset_discarded_frms);
+	hw_stats->tx_vp_reset_discarded_frms =
+	(u16)VXGE_HW_TX_VP_RESET_DISCARDED_FRMS_GET_TX_VP_RESET_DISCARDED_FRMS(
+		val64);
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_blockpool_create - Create block pool
+ */
+
+enum vxge_hw_status
+__vxge_hw_blockpool_create(struct __vxge_hw_device *hldev,
+			   struct __vxge_hw_blockpool *blockpool,
+			   u32 pool_size,
+			   u32 pool_max)
+{
+	u32 i;
+	struct __vxge_hw_blockpool_entry *entry = NULL;
+	void *memblock;
+	dma_addr_t dma_addr;
+	struct pci_dev *dma_handle;
+	struct pci_dev *acc_handle;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (blockpool == NULL) {
+		status = VXGE_HW_FAIL;
+		goto blockpool_create_exit;
+	}
+
+	blockpool->hldev = hldev;
+	blockpool->block_size = VXGE_HW_BLOCK_SIZE;
+	blockpool->pool_size = 0;
+	blockpool->pool_max = pool_max;
+	blockpool->req_out = 0;
+
+	INIT_LIST_HEAD(&blockpool->free_block_list);
+	INIT_LIST_HEAD(&blockpool->free_entry_list);
+
+	for (i = 0; i < pool_size + pool_max; i++) {
+		entry = kzalloc(sizeof(struct __vxge_hw_blockpool_entry),
+				GFP_KERNEL);
+		if (entry == NULL) {
+			__vxge_hw_blockpool_destroy(blockpool);
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto blockpool_create_exit;
+		}
+		list_add(&entry->item, &blockpool->free_entry_list);
+	}
+
+	for (i = 0; i < pool_size; i++) {
+
+		memblock = vxge_os_dma_malloc(
+				hldev->pdev,
+				VXGE_HW_BLOCK_SIZE,
+				&dma_handle,
+				&acc_handle);
+
+		if (memblock == NULL) {
+			__vxge_hw_blockpool_destroy(blockpool);
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto blockpool_create_exit;
+		}
+
+		dma_addr = pci_map_single(hldev->pdev, memblock,
+				VXGE_HW_BLOCK_SIZE, PCI_DMA_BIDIRECTIONAL);
+
+		if (unlikely(pci_dma_mapping_error(hldev->pdev,
+				dma_addr))) {
+
+			vxge_os_dma_free(hldev->pdev, memblock, &acc_handle);
+			__vxge_hw_blockpool_destroy(blockpool);
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto blockpool_create_exit;
+		}
+
+		if (!list_empty(&blockpool->free_entry_list))
+			entry = (struct __vxge_hw_blockpool_entry *)
+				list_first_entry(&blockpool->free_entry_list,
+					struct __vxge_hw_blockpool_entry,
+					item);
+
+		if (entry == NULL)
+			entry =
+			    kzalloc(sizeof(struct __vxge_hw_blockpool_entry),
+					GFP_KERNEL);
+		if (entry != NULL) {
+			list_del(&entry->item);
+			entry->length = VXGE_HW_BLOCK_SIZE;
+			entry->memblock = memblock;
+			entry->dma_addr = dma_addr;
+			entry->acc_handle = acc_handle;
+			entry->dma_handle = dma_handle;
+			list_add(&entry->item,
+					  &blockpool->free_block_list);
+			blockpool->pool_size++;
+		} else {
+			__vxge_hw_blockpool_destroy(blockpool);
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto blockpool_create_exit;
+		}
+	}
+
+blockpool_create_exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_blockpool_destroy - Deallocates the block pool
+ */
+
+void __vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool *blockpool)
+{
+
+	struct __vxge_hw_device *hldev;
+	struct list_head *p, *n;
+	u16 ret;
+
+	if (blockpool == NULL) {
+		ret = 1;
+		goto exit;
+	}
+
+	hldev = blockpool->hldev;
+
+	list_for_each_safe(p, n, &blockpool->free_block_list) {
+
+		pci_unmap_single(hldev->pdev,
+			((struct __vxge_hw_blockpool_entry *)p)->dma_addr,
+			((struct __vxge_hw_blockpool_entry *)p)->length,
+			PCI_DMA_BIDIRECTIONAL);
+
+		vxge_os_dma_free(hldev->pdev,
+			((struct __vxge_hw_blockpool_entry *)p)->memblock,
+			&((struct __vxge_hw_blockpool_entry *) p)->acc_handle);
+
+		list_del(
+			&((struct __vxge_hw_blockpool_entry *)p)->item);
+		kfree(p);
+		blockpool->pool_size--;
+	}
+
+	list_for_each_safe(p, n, &blockpool->free_entry_list) {
+		list_del(
+			&((struct __vxge_hw_blockpool_entry *)p)->item);
+		kfree((void *)p);
+	}
+	ret = 0;
+exit:
+	return;
+}
+
+/*
+ * __vxge_hw_blockpool_blocks_add - Request additional blocks
+ */
+static
+void __vxge_hw_blockpool_blocks_add(struct __vxge_hw_blockpool *blockpool)
+{
+	u32 nreq = 0, i;
+
+	if ((blockpool->pool_size  +  blockpool->req_out) <
+		VXGE_HW_MIN_DMA_BLOCK_POOL_SIZE) {
+		nreq = VXGE_HW_INCR_DMA_BLOCK_POOL_SIZE;
+		blockpool->req_out += nreq;
+	}
+
+	for (i = 0; i < nreq; i++)
+		vxge_os_dma_malloc_async(
+			((struct __vxge_hw_device *)blockpool->hldev)->pdev,
+			blockpool->hldev, VXGE_HW_BLOCK_SIZE);
+}
+
+/*
+ * __vxge_hw_blockpool_blocks_remove - Free additional blocks
+ */
+static
+void __vxge_hw_blockpool_blocks_remove(struct __vxge_hw_blockpool *blockpool)
+{
+	struct list_head *p, *n;
+
+	list_for_each_safe(p, n, &blockpool->free_block_list) {
+
+		if (blockpool->pool_size < blockpool->pool_max)
+			break;
+
+		pci_unmap_single(
+			((struct __vxge_hw_device *)blockpool->hldev)->pdev,
+			((struct __vxge_hw_blockpool_entry *)p)->dma_addr,
+			((struct __vxge_hw_blockpool_entry *)p)->length,
+			PCI_DMA_BIDIRECTIONAL);
+
+		vxge_os_dma_free(
+			((struct __vxge_hw_device *)blockpool->hldev)->pdev,
+			((struct __vxge_hw_blockpool_entry *)p)->memblock,
+			&((struct __vxge_hw_blockpool_entry *)p)->acc_handle);
+
+		list_del(&((struct __vxge_hw_blockpool_entry *)p)->item);
+
+		list_add(p, &blockpool->free_entry_list);
+
+		blockpool->pool_size--;
+
+	}
+}
+
+/*
+ * vxge_hw_blockpool_block_add - callback for vxge_os_dma_malloc_async
+ * Adds a block to block pool
+ */
+void vxge_hw_blockpool_block_add(
+			struct __vxge_hw_device *devh,
+			void *block_addr,
+			u32 length,
+			struct pci_dev *dma_h,
+			struct pci_dev *acc_handle)
+{
+	struct __vxge_hw_blockpool  *blockpool;
+	struct __vxge_hw_blockpool_entry  *entry = NULL;
+	dma_addr_t dma_addr;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	u32 req_out;
+
+	blockpool = &devh->block_pool;
+
+	if (block_addr == NULL) {
+		blockpool->req_out--;
+		status = VXGE_HW_FAIL;
+		goto exit;
+	}
+
+	dma_addr = pci_map_single(devh->pdev, block_addr, length,
+				PCI_DMA_BIDIRECTIONAL);
+
+	if (unlikely(pci_dma_mapping_error(devh->pdev, dma_addr))) {
+
+		vxge_os_dma_free(devh->pdev, block_addr, &acc_handle);
+		blockpool->req_out--;
+		status = VXGE_HW_FAIL;
+		goto exit;
+	}
+
+
+	if (!list_empty(&blockpool->free_entry_list))
+		entry = (struct __vxge_hw_blockpool_entry *)
+			list_first_entry(&blockpool->free_entry_list,
+				struct __vxge_hw_blockpool_entry,
+				item);
+
+	if (entry == NULL)
+		entry = (struct __vxge_hw_blockpool_entry *)
+			vmalloc(sizeof(struct __vxge_hw_blockpool_entry));
+	else
+		list_del(&entry->item);
+
+	if (entry != NULL) {
+		entry->length = length;
+		entry->memblock = block_addr;
+		entry->dma_addr = dma_addr;
+		entry->acc_handle = acc_handle;
+		entry->dma_handle = dma_h;
+		list_add(&entry->item, &blockpool->free_block_list);
+		blockpool->pool_size++;
+		status = VXGE_HW_OK;
+	} else
+		status = VXGE_HW_ERR_OUT_OF_MEMORY;
+
+	blockpool->req_out--;
+
+	req_out = blockpool->req_out;
+exit:
+	return;
+}
+
+/*
+ * __vxge_hw_blockpool_malloc - Allocate a memory block from pool
+ * Allocates a block of memory of given size, either from block pool
+ * or by calling vxge_os_dma_malloc()
+ */
+void *
+__vxge_hw_blockpool_malloc(struct __vxge_hw_device *devh, u32 size,
+				struct vxge_hw_mempool_dma *dma_object)
+{
+	struct __vxge_hw_blockpool_entry *entry = NULL;
+	struct __vxge_hw_blockpool  *blockpool;
+	void *memblock = NULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	blockpool = &devh->block_pool;
+
+	if (size != blockpool->block_size) {
+
+		memblock = vxge_os_dma_malloc(devh->pdev, size,
+						&dma_object->handle,
+						&dma_object->acc_handle);
+
+		if (memblock == NULL) {
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto exit;
+		}
+
+		dma_object->addr = pci_map_single(devh->pdev, memblock, size,
+					PCI_DMA_BIDIRECTIONAL);
+
+		if (unlikely(pci_dma_mapping_error(devh->pdev,
+				dma_object->addr))) {
+			vxge_os_dma_free(devh->pdev, memblock,
+				&dma_object->acc_handle);
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+			goto exit;
+		}
+
+	} else {
+
+		if (!list_empty(&blockpool->free_block_list))
+			entry = (struct __vxge_hw_blockpool_entry *)
+				list_first_entry(&blockpool->free_block_list,
+					struct __vxge_hw_blockpool_entry,
+					item);
+
+		if (entry != NULL) {
+			list_del(&entry->item);
+			dma_object->addr = entry->dma_addr;
+			dma_object->handle = entry->dma_handle;
+			dma_object->acc_handle = entry->acc_handle;
+			memblock = entry->memblock;
+
+			list_add(&entry->item,
+				&blockpool->free_entry_list);
+			blockpool->pool_size--;
+		}
+
+		if (memblock != NULL)
+			__vxge_hw_blockpool_blocks_add(blockpool);
+	}
+exit:
+	return memblock;
+}
+
+/*
+ * __vxge_hw_blockpool_free - Frees the memory allcoated with
+				__vxge_hw_blockpool_malloc
+ */
+void
+__vxge_hw_blockpool_free(struct __vxge_hw_device *devh,
+			void *memblock, u32 size,
+			struct vxge_hw_mempool_dma *dma_object)
+{
+	struct __vxge_hw_blockpool_entry *entry = NULL;
+	struct __vxge_hw_blockpool  *blockpool;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	blockpool = &devh->block_pool;
+
+	if (size != blockpool->block_size) {
+		pci_unmap_single(devh->pdev, dma_object->addr, size,
+			PCI_DMA_BIDIRECTIONAL);
+		vxge_os_dma_free(devh->pdev, memblock, &dma_object->acc_handle);
+	} else {
+
+		if (!list_empty(&blockpool->free_entry_list))
+			entry = (struct __vxge_hw_blockpool_entry *)
+				list_first_entry(&blockpool->free_entry_list,
+					struct __vxge_hw_blockpool_entry,
+					item);
+
+		if (entry == NULL)
+			entry = (struct __vxge_hw_blockpool_entry *)
+				vmalloc(sizeof(
+					struct __vxge_hw_blockpool_entry));
+		else
+			list_del(&entry->item);
+
+		if (entry != NULL) {
+			entry->length = size;
+			entry->memblock = memblock;
+			entry->dma_addr = dma_object->addr;
+			entry->acc_handle = dma_object->acc_handle;
+			entry->dma_handle = dma_object->handle;
+			list_add(&entry->item,
+					&blockpool->free_block_list);
+			blockpool->pool_size++;
+			status = VXGE_HW_OK;
+		} else
+			status = VXGE_HW_ERR_OUT_OF_MEMORY;
+
+		if (status == VXGE_HW_OK)
+			__vxge_hw_blockpool_blocks_remove(blockpool);
+	}
+
+	return;
+}
+
+/*
+ * __vxge_hw_blockpool_block_allocate - Allocates a block from block pool
+ * This function allocates a block from block pool or from the system
+ */
+struct __vxge_hw_blockpool_entry *
+__vxge_hw_blockpool_block_allocate(struct __vxge_hw_device *devh, u32 size)
+{
+	struct __vxge_hw_blockpool_entry *entry = NULL;
+	struct __vxge_hw_blockpool  *blockpool;
+
+	blockpool = &devh->block_pool;
+
+	if (size == blockpool->block_size) {
+
+		if (!list_empty(&blockpool->free_block_list))
+			entry = (struct __vxge_hw_blockpool_entry *)
+				list_first_entry(&blockpool->free_block_list,
+					struct __vxge_hw_blockpool_entry,
+					item);
+
+		if (entry != NULL) {
+			list_del(&entry->item);
+			blockpool->pool_size--;
+		}
+	}
+
+	if (entry != NULL)
+		__vxge_hw_blockpool_blocks_add(blockpool);
+
+	return entry;
+}
+
+/*
+ * __vxge_hw_blockpool_block_free - Frees a block from block pool
+ * @devh: Hal device
+ * @entry: Entry of block to be freed
+ *
+ * This function frees a block from block pool
+ */
+void
+__vxge_hw_blockpool_block_free(struct __vxge_hw_device *devh,
+			struct __vxge_hw_blockpool_entry *entry)
+{
+	struct __vxge_hw_blockpool  *blockpool;
+
+	blockpool = &devh->block_pool;
+
+	if (entry->length == blockpool->block_size) {
+		list_add(&entry->item, &blockpool->free_block_list);
+		blockpool->pool_size++;
+	}
+
+	__vxge_hw_blockpool_blocks_remove(blockpool);
+
+	return;
+}
diff --git a/drivers/net/vxge/vxge-config.h b/drivers/net/vxge/vxge-config.h
new file mode 100644
index 000000000000..afbdf6f4d224
--- /dev/null
+++ b/drivers/net/vxge/vxge-config.h
@@ -0,0 +1,2259 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-config.h: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *                Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#ifndef VXGE_CONFIG_H
+#define VXGE_CONFIG_H
+#include <linux/list.h>
+
+#ifndef VXGE_CACHE_LINE_SIZE
+#define VXGE_CACHE_LINE_SIZE 128
+#endif
+
+#define vxge_os_vaprintf(level, mask, fmt, ...) { \
+	char buff[255]; \
+		snprintf(buff, 255, fmt, __VA_ARGS__); \
+		printk(buff); \
+		printk("\n"); \
+}
+
+#ifndef VXGE_ALIGN
+#define VXGE_ALIGN(adrs, size) \
+	(((size) - (((u64)adrs) & ((size)-1))) & ((size)-1))
+#endif
+
+#define VXGE_HW_MIN_MTU				68
+#define VXGE_HW_MAX_MTU				9600
+#define VXGE_HW_DEFAULT_MTU			1500
+
+#ifdef VXGE_DEBUG_ASSERT
+
+/**
+ * vxge_assert
+ * @test: C-condition to check
+ * @fmt: printf like format string
+ *
+ * This function implements traditional assert. By default assertions
+ * are enabled. It can be disabled by undefining VXGE_DEBUG_ASSERT macro in
+ * compilation
+ * time.
+ */
+#define vxge_assert(test) { \
+	if (!(test)) \
+		vxge_os_bug("bad cond: "#test" at %s:%d\n", \
+				__FILE__, __LINE__); }
+#else
+#define vxge_assert(test)
+#endif /* end of VXGE_DEBUG_ASSERT */
+
+/**
+ * enum enum vxge_debug_level
+ * @VXGE_NONE: debug disabled
+ * @VXGE_ERR: all errors going to be logged out
+ * @VXGE_TRACE: all errors plus all kind of verbose tracing print outs
+ *                 going to be logged out. Very noisy.
+ *
+ * This enumeration going to be used to switch between different
+ * debug levels during runtime if DEBUG macro defined during
+ * compilation. If DEBUG macro not defined than code will be
+ * compiled out.
+ */
+enum vxge_debug_level {
+	VXGE_NONE   = 0,
+	VXGE_TRACE  = 1,
+	VXGE_ERR    = 2
+};
+
+#define NULL_VPID					0xFFFFFFFF
+#ifdef CONFIG_VXGE_DEBUG_TRACE_ALL
+#define VXGE_DEBUG_MODULE_MASK  0xffffffff
+#define VXGE_DEBUG_TRACE_MASK   0xffffffff
+#define VXGE_DEBUG_ERR_MASK     0xffffffff
+#define VXGE_DEBUG_MASK         0x000001ff
+#else
+#define VXGE_DEBUG_MODULE_MASK  0x20000000
+#define VXGE_DEBUG_TRACE_MASK   0x20000000
+#define VXGE_DEBUG_ERR_MASK     0x20000000
+#define VXGE_DEBUG_MASK         0x00000001
+#endif
+
+/*
+ * @VXGE_COMPONENT_LL: do debug for vxge link layer module
+ * @VXGE_COMPONENT_ALL: activate debug for all modules with no exceptions
+ *
+ * This enumeration going to be used to distinguish modules
+ * or libraries during compilation and runtime.  Makefile must declare
+ * VXGE_DEBUG_MODULE_MASK macro and set it to proper value.
+ */
+#define	VXGE_COMPONENT_LL				0x20000000
+#define	VXGE_COMPONENT_ALL				0xffffffff
+
+#define VXGE_HW_BASE_INF	100
+#define VXGE_HW_BASE_ERR	200
+#define VXGE_HW_BASE_BADCFG	300
+
+enum vxge_hw_status {
+	VXGE_HW_OK				  = 0,
+	VXGE_HW_FAIL				  = 1,
+	VXGE_HW_PENDING				  = 2,
+	VXGE_HW_COMPLETIONS_REMAIN		  = 3,
+
+	VXGE_HW_INF_NO_MORE_COMPLETED_DESCRIPTORS = VXGE_HW_BASE_INF + 1,
+	VXGE_HW_INF_OUT_OF_DESCRIPTORS		  = VXGE_HW_BASE_INF + 2,
+
+	VXGE_HW_ERR_INVALID_HANDLE		  = VXGE_HW_BASE_ERR + 1,
+	VXGE_HW_ERR_OUT_OF_MEMORY		  = VXGE_HW_BASE_ERR + 2,
+	VXGE_HW_ERR_VPATH_NOT_AVAILABLE	  	  = VXGE_HW_BASE_ERR + 3,
+	VXGE_HW_ERR_VPATH_NOT_OPEN		  = VXGE_HW_BASE_ERR + 4,
+	VXGE_HW_ERR_WRONG_IRQ			  = VXGE_HW_BASE_ERR + 5,
+	VXGE_HW_ERR_SWAPPER_CTRL		  = VXGE_HW_BASE_ERR + 6,
+	VXGE_HW_ERR_INVALID_MTU_SIZE		  = VXGE_HW_BASE_ERR + 7,
+	VXGE_HW_ERR_INVALID_INDEX		  = VXGE_HW_BASE_ERR + 8,
+	VXGE_HW_ERR_INVALID_TYPE		  = VXGE_HW_BASE_ERR + 9,
+	VXGE_HW_ERR_INVALID_OFFSET		  = VXGE_HW_BASE_ERR + 10,
+	VXGE_HW_ERR_INVALID_DEVICE		  = VXGE_HW_BASE_ERR + 11,
+	VXGE_HW_ERR_VERSION_CONFLICT		  = VXGE_HW_BASE_ERR + 12,
+	VXGE_HW_ERR_INVALID_PCI_INFO		  = VXGE_HW_BASE_ERR + 13,
+	VXGE_HW_ERR_INVALID_TCODE 		  = VXGE_HW_BASE_ERR + 14,
+	VXGE_HW_ERR_INVALID_BLOCK_SIZE		  = VXGE_HW_BASE_ERR + 15,
+	VXGE_HW_ERR_INVALID_STATE		  = VXGE_HW_BASE_ERR + 16,
+	VXGE_HW_ERR_PRIVILAGED_OPEARATION	  = VXGE_HW_BASE_ERR + 17,
+	VXGE_HW_ERR_INVALID_PORT 		  = VXGE_HW_BASE_ERR + 18,
+	VXGE_HW_ERR_FIFO		 	  = VXGE_HW_BASE_ERR + 19,
+	VXGE_HW_ERR_VPATH			  = VXGE_HW_BASE_ERR + 20,
+	VXGE_HW_ERR_CRITICAL			  = VXGE_HW_BASE_ERR + 21,
+	VXGE_HW_ERR_SLOT_FREEZE 		  = VXGE_HW_BASE_ERR + 22,
+
+	VXGE_HW_BADCFG_RING_INDICATE_MAX_PKTS	  = VXGE_HW_BASE_BADCFG + 1,
+	VXGE_HW_BADCFG_FIFO_BLOCKS		  = VXGE_HW_BASE_BADCFG + 2,
+	VXGE_HW_BADCFG_VPATH_MTU		  = VXGE_HW_BASE_BADCFG + 3,
+	VXGE_HW_BADCFG_VPATH_RPA_STRIP_VLAN_TAG	  = VXGE_HW_BASE_BADCFG + 4,
+	VXGE_HW_BADCFG_VPATH_MIN_BANDWIDTH	  = VXGE_HW_BASE_BADCFG + 5,
+	VXGE_HW_BADCFG_INTR_MODE		  = VXGE_HW_BASE_BADCFG + 6,
+	VXGE_HW_BADCFG_RTS_MAC_EN		  = VXGE_HW_BASE_BADCFG + 7,
+
+	VXGE_HW_EOF_TRACE_BUF			  = -1
+};
+
+/**
+ * enum enum vxge_hw_device_link_state - Link state enumeration.
+ * @VXGE_HW_LINK_NONE: Invalid link state.
+ * @VXGE_HW_LINK_DOWN: Link is down.
+ * @VXGE_HW_LINK_UP: Link is up.
+ *
+ */
+enum vxge_hw_device_link_state {
+	VXGE_HW_LINK_NONE,
+	VXGE_HW_LINK_DOWN,
+	VXGE_HW_LINK_UP
+};
+
+/**
+ * struct vxge_hw_device_date - Date Format
+ * @day: Day
+ * @month: Month
+ * @year: Year
+ * @date: Date in string format
+ *
+ * Structure for returning date
+ */
+
+#define VXGE_HW_FW_STRLEN	32
+struct vxge_hw_device_date {
+	u32     day;
+	u32     month;
+	u32     year;
+	char    date[VXGE_HW_FW_STRLEN];
+};
+
+struct vxge_hw_device_version {
+	u32     major;
+	u32     minor;
+	u32     build;
+	char    version[VXGE_HW_FW_STRLEN];
+};
+
+u64
+__vxge_hw_vpath_pci_func_mode_get(
+	u32 vp_id,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg);
+
+/**
+ * struct vxge_hw_fifo_config - Configuration of fifo.
+ * @enable: Is this fifo to be commissioned
+ * @fifo_blocks: Numbers of TxDL (that is, lists of Tx descriptors)
+ * 		blocks per queue.
+ * @max_frags: Max number of Tx buffers per TxDL (that is, per single
+ *             transmit operation).
+ *             No more than 256 transmit buffers can be specified.
+ * @memblock_size: Fifo descriptors are allocated in blocks of @mem_block_size
+ *             bytes. Setting @memblock_size to page size ensures
+ *             by-page allocation of descriptors. 128K bytes is the
+ *             maximum supported block size.
+ * @alignment_size: per Tx fragment DMA-able memory used to align transmit data
+ *             (e.g., to align on a cache line).
+ * @intr: Boolean. Use 1 to generate interrupt for each completed TxDL.
+ *             Use 0 otherwise.
+ * @no_snoop_bits: If non-zero, specifies no-snoop PCI operation,
+ *             which generally improves latency of the host bridge operation
+ *             (see PCI specification). For valid values please refer
+ *             to struct vxge_hw_fifo_config{} in the driver sources.
+ * Configuration of all Titan fifos.
+ * Note: Valid (min, max) range for each attribute is specified in the body of
+ * the struct vxge_hw_fifo_config{} structure.
+ */
+struct vxge_hw_fifo_config {
+	u32				enable;
+#define VXGE_HW_FIFO_ENABLE				1
+#define VXGE_HW_FIFO_DISABLE				0
+
+	u32				fifo_blocks;
+#define VXGE_HW_MIN_FIFO_BLOCKS				2
+#define VXGE_HW_MAX_FIFO_BLOCKS				128
+
+	u32				max_frags;
+#define VXGE_HW_MIN_FIFO_FRAGS				1
+#define VXGE_HW_MAX_FIFO_FRAGS				256
+
+	u32				memblock_size;
+#define VXGE_HW_MIN_FIFO_MEMBLOCK_SIZE			VXGE_HW_BLOCK_SIZE
+#define VXGE_HW_MAX_FIFO_MEMBLOCK_SIZE			131072
+#define VXGE_HW_DEF_FIFO_MEMBLOCK_SIZE			8096
+
+	u32		                alignment_size;
+#define VXGE_HW_MIN_FIFO_ALIGNMENT_SIZE		0
+#define VXGE_HW_MAX_FIFO_ALIGNMENT_SIZE		65536
+#define VXGE_HW_DEF_FIFO_ALIGNMENT_SIZE		VXGE_CACHE_LINE_SIZE
+
+	u32		                intr;
+#define VXGE_HW_FIFO_QUEUE_INTR_ENABLE			1
+#define VXGE_HW_FIFO_QUEUE_INTR_DISABLE			0
+#define VXGE_HW_FIFO_QUEUE_INTR_DEFAULT			0
+
+	u32				no_snoop_bits;
+#define VXGE_HW_FIFO_NO_SNOOP_DISABLED			0
+#define VXGE_HW_FIFO_NO_SNOOP_TXD			1
+#define VXGE_HW_FIFO_NO_SNOOP_FRM			2
+#define VXGE_HW_FIFO_NO_SNOOP_ALL			3
+#define VXGE_HW_FIFO_NO_SNOOP_DEFAULT			0
+
+};
+/**
+ * struct vxge_hw_ring_config - Ring configurations.
+ * @enable: Is this ring to be commissioned
+ * @ring_blocks: Numbers of RxD blocks in the ring
+ * @buffer_mode: Receive buffer mode (1, 2, 3, or 5); for details please refer
+ *             to Titan User Guide.
+ * @scatter_mode: Titan supports two receive scatter modes: A and B.
+ *             For details please refer to Titan User Guide.
+ * @rx_timer_val: The number of 32ns periods that would be counted between two
+ *             timer interrupts.
+ * @greedy_return: If Set it forces the device to return absolutely all RxD
+ *             that are consumed and still on board when a timer interrupt
+ *             triggers. If Clear, then if the device has already returned
+ *             RxD before current timer interrupt trigerred and after the
+ *             previous timer interrupt triggered, then the device is not
+ *             forced to returned the rest of the consumed RxD that it has
+ *             on board which account for a byte count less than the one
+ *             programmed into PRC_CFG6.RXD_CRXDT field
+ * @rx_timer_ci: TBD
+ * @backoff_interval_us: Time (in microseconds), after which Titan
+ *             tries to download RxDs posted by the host.
+ *             Note that the "backoff" does not happen if host posts receive
+ *             descriptors in the timely fashion.
+ * Ring configuration.
+ */
+struct vxge_hw_ring_config {
+	u32				enable;
+#define VXGE_HW_RING_ENABLE					1
+#define VXGE_HW_RING_DISABLE					0
+#define VXGE_HW_RING_DEFAULT					1
+
+	u32				ring_blocks;
+#define VXGE_HW_MIN_RING_BLOCKS				1
+#define VXGE_HW_MAX_RING_BLOCKS				128
+#define VXGE_HW_DEF_RING_BLOCKS				2
+
+	u32				buffer_mode;
+#define VXGE_HW_RING_RXD_BUFFER_MODE_1				1
+#define VXGE_HW_RING_RXD_BUFFER_MODE_3				3
+#define VXGE_HW_RING_RXD_BUFFER_MODE_5				5
+#define VXGE_HW_RING_RXD_BUFFER_MODE_DEFAULT			1
+
+	u32				scatter_mode;
+#define VXGE_HW_RING_SCATTER_MODE_A				0
+#define VXGE_HW_RING_SCATTER_MODE_B				1
+#define VXGE_HW_RING_SCATTER_MODE_C				2
+#define VXGE_HW_RING_SCATTER_MODE_USE_FLASH_DEFAULT		0xffffffff
+
+	u64				rxds_limit;
+#define VXGE_HW_DEF_RING_RXDS_LIMIT				44
+};
+
+/**
+ * struct vxge_hw_vp_config - Configuration of virtual path
+ * @vp_id: Virtual Path Id
+ * @min_bandwidth: Minimum Guaranteed bandwidth
+ * @ring: See struct vxge_hw_ring_config{}.
+ * @fifo: See struct vxge_hw_fifo_config{}.
+ * @tti: Configuration of interrupt associated with Transmit.
+ *             see struct vxge_hw_tim_intr_config();
+ * @rti: Configuration of interrupt associated with Receive.
+ *              see struct vxge_hw_tim_intr_config();
+ * @mtu: mtu size used on this port.
+ * @rpa_strip_vlan_tag: Strip VLAN Tag enable/disable. Instructs the device to
+ *             remove the VLAN tag from all received tagged frames that are not
+ *             replicated at the internal L2 switch.
+ *             0 - Do not strip the VLAN tag.
+ *             1 - Strip the VLAN tag. Regardless of this setting, VLAN tags are
+ *                 always placed into the RxDMA descriptor.
+ *
+ * This structure is used by the driver to pass the configuration parameters to
+ * configure Virtual Path.
+ */
+struct vxge_hw_vp_config {
+	u32				vp_id;
+
+#define	VXGE_HW_VPATH_PRIORITY_MIN			0
+#define	VXGE_HW_VPATH_PRIORITY_MAX			16
+#define	VXGE_HW_VPATH_PRIORITY_DEFAULT			0
+
+	u32				min_bandwidth;
+#define	VXGE_HW_VPATH_BANDWIDTH_MIN			0
+#define	VXGE_HW_VPATH_BANDWIDTH_MAX			100
+#define	VXGE_HW_VPATH_BANDWIDTH_DEFAULT			0
+
+	struct vxge_hw_ring_config		ring;
+	struct vxge_hw_fifo_config		fifo;
+	struct vxge_hw_tim_intr_config	tti;
+	struct vxge_hw_tim_intr_config	rti;
+
+	u32				mtu;
+#define VXGE_HW_VPATH_MIN_INITIAL_MTU			VXGE_HW_MIN_MTU
+#define VXGE_HW_VPATH_MAX_INITIAL_MTU			VXGE_HW_MAX_MTU
+#define VXGE_HW_VPATH_USE_FLASH_DEFAULT_INITIAL_MTU	0xffffffff
+
+	u32				rpa_strip_vlan_tag;
+#define VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_ENABLE			1
+#define VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_DISABLE		0
+#define VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_USE_FLASH_DEFAULT	0xffffffff
+
+};
+/**
+ * struct vxge_hw_device_config - Device configuration.
+ * @dma_blockpool_initial: Initial size of DMA Pool
+ * @dma_blockpool_max: Maximum blocks in DMA pool
+ * @intr_mode: Line, or MSI-X interrupt.
+ *
+ * @rth_en: Enable Receive Traffic Hashing(RTH) using IT(Indirection Table).
+ * @rth_it_type: RTH IT table programming type
+ * @rts_mac_en: Enable Receive Traffic Steering using MAC destination address
+ * @vp_config: Configuration for virtual paths
+ * @device_poll_millis: Specify the interval (in mulliseconds)
+ * 			to wait for register reads
+ *
+ * Titan configuration.
+ * Contains per-device configuration parameters, including:
+ * - stats sampling interval, etc.
+ *
+ * In addition, struct vxge_hw_device_config{} includes "subordinate"
+ * configurations, including:
+ * - fifos and rings;
+ * - MAC (done at firmware level).
+ *
+ * See Titan User Guide for more details.
+ * Note: Valid (min, max) range for each attribute is specified in the body of
+ * the struct vxge_hw_device_config{} structure. Please refer to the
+ * corresponding include file.
+ * See also: struct vxge_hw_tim_intr_config{}.
+ */
+struct vxge_hw_device_config {
+	u32				dma_blockpool_initial;
+	u32				dma_blockpool_max;
+#define VXGE_HW_MIN_DMA_BLOCK_POOL_SIZE			0
+#define VXGE_HW_INITIAL_DMA_BLOCK_POOL_SIZE		0
+#define VXGE_HW_INCR_DMA_BLOCK_POOL_SIZE		4
+#define VXGE_HW_MAX_DMA_BLOCK_POOL_SIZE			4096
+
+#define        VXGE_HW_MAX_PAYLOAD_SIZE_512		2
+
+	u32				intr_mode;
+#define VXGE_HW_INTR_MODE_IRQLINE			0
+#define VXGE_HW_INTR_MODE_MSIX				1
+#define VXGE_HW_INTR_MODE_MSIX_ONE_SHOT			2
+
+#define VXGE_HW_INTR_MODE_DEF				0
+
+	u32				rth_en;
+#define VXGE_HW_RTH_DISABLE				0
+#define VXGE_HW_RTH_ENABLE				1
+#define VXGE_HW_RTH_DEFAULT				0
+
+	u32				rth_it_type;
+#define VXGE_HW_RTH_IT_TYPE_SOLO_IT			0
+#define VXGE_HW_RTH_IT_TYPE_MULTI_IT			1
+#define VXGE_HW_RTH_IT_TYPE_DEFAULT			0
+
+	u32				rts_mac_en;
+#define VXGE_HW_RTS_MAC_DISABLE			0
+#define VXGE_HW_RTS_MAC_ENABLE			1
+#define VXGE_HW_RTS_MAC_DEFAULT			0
+
+	struct vxge_hw_vp_config	vp_config[VXGE_HW_MAX_VIRTUAL_PATHS];
+
+	u32				device_poll_millis;
+#define VXGE_HW_MIN_DEVICE_POLL_MILLIS			1
+#define VXGE_HW_MAX_DEVICE_POLL_MILLIS			100000
+#define VXGE_HW_DEF_DEVICE_POLL_MILLIS			1000
+
+};
+
+/**
+ * function vxge_uld_link_up_f - Link-Up callback provided by driver.
+ * @devh: HW device handle.
+ * Link-up notification callback provided by the driver.
+ * This is one of the per-driver callbacks, see struct vxge_hw_uld_cbs{}.
+ *
+ * See also: struct vxge_hw_uld_cbs{}, vxge_uld_link_down_f{},
+ * vxge_hw_driver_initialize().
+ */
+
+/**
+ * function vxge_uld_link_down_f - Link-Down callback provided by
+ * driver.
+ * @devh: HW device handle.
+ *
+ * Link-Down notification callback provided by the driver.
+ * This is one of the per-driver callbacks, see struct vxge_hw_uld_cbs{}.
+ *
+ * See also: struct vxge_hw_uld_cbs{}, vxge_uld_link_up_f{},
+ * vxge_hw_driver_initialize().
+ */
+
+/**
+ * function vxge_uld_crit_err_f - Critical Error notification callback.
+ * @devh: HW device handle.
+ * (typically - at HW device iinitialization time).
+ * @type: Enumerated hw error, e.g.: double ECC.
+ * @serr_data: Titan status.
+ * @ext_data: Extended data. The contents depends on the @type.
+ *
+ * Link-Down notification callback provided by the driver.
+ * This is one of the per-driver callbacks, see struct vxge_hw_uld_cbs{}.
+ *
+ * See also: struct vxge_hw_uld_cbs{}, enum vxge_hw_event{},
+ * vxge_hw_driver_initialize().
+ */
+
+/**
+ * struct vxge_hw_uld_cbs - driver "slow-path" callbacks.
+ * @link_up: See vxge_uld_link_up_f{}.
+ * @link_down: See vxge_uld_link_down_f{}.
+ * @crit_err: See vxge_uld_crit_err_f{}.
+ *
+ * Driver slow-path (per-driver) callbacks.
+ * Implemented by driver and provided to HW via
+ * vxge_hw_driver_initialize().
+ * Note that these callbacks are not mandatory: HW will not invoke
+ * a callback if NULL is specified.
+ *
+ * See also: vxge_hw_driver_initialize().
+ */
+struct vxge_hw_uld_cbs {
+
+	void (*link_up)(struct __vxge_hw_device *devh);
+	void (*link_down)(struct __vxge_hw_device *devh);
+	void (*crit_err)(struct __vxge_hw_device *devh,
+			enum vxge_hw_event type, u64 ext_data);
+};
+
+/*
+ * struct __vxge_hw_blockpool_entry - Block private data structure
+ * @item: List header used to link.
+ * @length: Length of the block
+ * @memblock: Virtual address block
+ * @dma_addr: DMA Address of the block.
+ * @dma_handle: DMA handle of the block.
+ * @acc_handle: DMA acc handle
+ *
+ * Block is allocated with a header to put the blocks into list.
+ *
+ */
+struct __vxge_hw_blockpool_entry {
+	struct list_head	item;
+	u32			length;
+	void			*memblock;
+	dma_addr_t		dma_addr;
+	struct pci_dev 		*dma_handle;
+	struct pci_dev 		*acc_handle;
+};
+
+/*
+ * struct __vxge_hw_blockpool - Block Pool
+ * @hldev: HW device
+ * @block_size: size of each block.
+ * @Pool_size: Number of blocks in the pool
+ * @pool_max: Maximum number of blocks above which to free additional blocks
+ * @req_out: Number of block requests with OS out standing
+ * @free_block_list: List of free blocks
+ *
+ * Block pool contains the DMA blocks preallocated.
+ *
+ */
+struct __vxge_hw_blockpool {
+	struct __vxge_hw_device *hldev;
+	u32				block_size;
+	u32				pool_size;
+	u32				pool_max;
+	u32				req_out;
+	struct list_head		free_block_list;
+	struct list_head		free_entry_list;
+};
+
+/*
+ * enum enum __vxge_hw_channel_type - Enumerated channel types.
+ * @VXGE_HW_CHANNEL_TYPE_UNKNOWN: Unknown channel.
+ * @VXGE_HW_CHANNEL_TYPE_FIFO: fifo.
+ * @VXGE_HW_CHANNEL_TYPE_RING: ring.
+ * @VXGE_HW_CHANNEL_TYPE_MAX: Maximum number of HW-supported
+ * (and recognized) channel types. Currently: 2.
+ *
+ * Enumerated channel types. Currently there are only two link-layer
+ * channels - Titan fifo and Titan ring. In the future the list will grow.
+ */
+enum __vxge_hw_channel_type {
+	VXGE_HW_CHANNEL_TYPE_UNKNOWN			= 0,
+	VXGE_HW_CHANNEL_TYPE_FIFO			= 1,
+	VXGE_HW_CHANNEL_TYPE_RING			= 2,
+	VXGE_HW_CHANNEL_TYPE_MAX			= 3
+};
+
+/*
+ * struct __vxge_hw_channel
+ * @item: List item; used to maintain a list of open channels.
+ * @type: Channel type. See enum vxge_hw_channel_type{}.
+ * @devh: Device handle. HW device object that contains _this_ channel.
+ * @vph: Virtual path handle. Virtual Path Object that contains _this_ channel.
+ * @length: Channel length. Currently allocated number of descriptors.
+ *          The channel length "grows" when more descriptors get allocated.
+ *          See _hw_mempool_grow.
+ * @reserve_arr: Reserve array. Contains descriptors that can be reserved
+ *               by driver for the subsequent send or receive operation.
+ *               See vxge_hw_fifo_txdl_reserve(),
+ *               vxge_hw_ring_rxd_reserve().
+ * @reserve_ptr: Current pointer in the resrve array
+ * @reserve_top: Reserve top gives the maximum number of dtrs available in
+ *          reserve array.
+ * @work_arr: Work array. Contains descriptors posted to the channel.
+ *            Note that at any point in time @work_arr contains 3 types of
+ *            descriptors:
+ *            1) posted but not yet consumed by Titan device;
+ *            2) consumed but not yet completed;
+ *            3) completed but not yet freed
+ *            (via vxge_hw_fifo_txdl_free() or vxge_hw_ring_rxd_free())
+ * @post_index: Post index. At any point in time points on the
+ *              position in the channel, which'll contain next to-be-posted
+ *              descriptor.
+ * @compl_index: Completion index. At any point in time points on the
+ *               position in the channel, which will contain next
+ *               to-be-completed descriptor.
+ * @free_arr: Free array. Contains completed descriptors that were freed
+ *            (i.e., handed over back to HW) by driver.
+ *            See vxge_hw_fifo_txdl_free(), vxge_hw_ring_rxd_free().
+ * @free_ptr: current pointer in free array
+ * @per_dtr_space: Per-descriptor space (in bytes) that channel user can utilize
+ *                 to store per-operation control information.
+ * @stats: Pointer to common statistics
+ * @userdata: Per-channel opaque (void*) user-defined context, which may be
+ *            driver object, ULP connection, etc.
+ *            Once channel is open, @userdata is passed back to user via
+ *            vxge_hw_channel_callback_f.
+ *
+ * HW channel object.
+ *
+ * See also: enum vxge_hw_channel_type{}, enum vxge_hw_channel_flag
+ */
+struct __vxge_hw_channel {
+	struct list_head		item;
+	enum __vxge_hw_channel_type	type;
+	struct __vxge_hw_device 	*devh;
+	struct __vxge_hw_vpath_handle 	*vph;
+	u32			length;
+	u32			vp_id;
+	void		**reserve_arr;
+	u32			reserve_ptr;
+	u32			reserve_top;
+	void		**work_arr;
+	u32			post_index ____cacheline_aligned;
+	u32			compl_index ____cacheline_aligned;
+	void		**free_arr;
+	u32			free_ptr;
+	void		**orig_arr;
+	u32			per_dtr_space;
+	void		*userdata;
+	struct vxge_hw_common_reg	__iomem *common_reg;
+	u32			first_vp_id;
+	struct vxge_hw_vpath_stats_sw_common_info *stats;
+
+} ____cacheline_aligned;
+
+/*
+ * struct __vxge_hw_virtualpath - Virtual Path
+ *
+ * @vp_id: Virtual path id
+ * @vp_open: This flag specifies if vxge_hw_vp_open is called from LL Driver
+ * @hldev: Hal device
+ * @vp_config: Virtual Path Config
+ * @vp_reg: VPATH Register map address in BAR0
+ * @vpmgmt_reg: VPATH_MGMT register map address
+ * @max_mtu: Max mtu that can be supported
+ * @vsport_number: vsport attached to this vpath
+ * @max_kdfc_db: Maximum kernel mode doorbells
+ * @max_nofl_db: Maximum non offload doorbells
+ * @tx_intr_num: Interrupt Number associated with the TX
+
+ * @ringh: Ring Queue
+ * @fifoh: FIFO Queue
+ * @vpath_handles: Virtual Path handles list
+ * @stats_block: Memory for DMAing stats
+ * @stats: Vpath statistics
+ *
+ * Virtual path structure to encapsulate the data related to a virtual path.
+ * Virtual paths are allocated by the HW upon getting configuration from the
+ * driver and inserted into the list of virtual paths.
+ */
+struct __vxge_hw_virtualpath {
+	u32				vp_id;
+
+	u32				vp_open;
+#define VXGE_HW_VP_NOT_OPEN	0
+#define	VXGE_HW_VP_OPEN		1
+
+	struct __vxge_hw_device		*hldev;
+	struct vxge_hw_vp_config	*vp_config;
+	struct vxge_hw_vpath_reg	__iomem *vp_reg;
+	struct vxge_hw_vpmgmt_reg	__iomem *vpmgmt_reg;
+	struct __vxge_hw_non_offload_db_wrapper	__iomem *nofl_db;
+
+	u32				max_mtu;
+	u32				vsport_number;
+	u32				max_kdfc_db;
+	u32				max_nofl_db;
+
+	struct __vxge_hw_ring *____cacheline_aligned ringh;
+	struct __vxge_hw_fifo *____cacheline_aligned fifoh;
+	struct list_head		vpath_handles;
+	struct __vxge_hw_blockpool_entry		*stats_block;
+	struct vxge_hw_vpath_stats_hw_info	*hw_stats;
+	struct vxge_hw_vpath_stats_hw_info	*hw_stats_sav;
+	struct vxge_hw_vpath_stats_sw_info	*sw_stats;
+};
+
+/*
+ * struct __vxge_hw_vpath_handle - List item to store callback information
+ * @item: List head to keep the item in linked list
+ * @vpath: Virtual path to which this item belongs
+ *
+ * This structure is used to store the callback information.
+ */
+struct __vxge_hw_vpath_handle{
+	struct list_head	item;
+	struct __vxge_hw_virtualpath	*vpath;
+};
+
+/*
+ * struct __vxge_hw_device
+ *
+ * HW device object.
+ */
+/**
+ * struct __vxge_hw_device  - Hal device object
+ * @magic: Magic Number
+ * @device_id: PCI Device Id of the adapter
+ * @major_revision: PCI Device major revision
+ * @minor_revision: PCI Device minor revision
+ * @bar0: BAR0 virtual address.
+ * @bar1: BAR1 virtual address.
+ * @bar2: BAR2 virtual address.
+ * @pdev: Physical device handle
+ * @config: Confguration passed by the LL driver at initialization
+ * @link_state: Link state
+ *
+ * HW device object. Represents Titan adapter
+ */
+struct __vxge_hw_device {
+	u32				magic;
+#define VXGE_HW_DEVICE_MAGIC		0x12345678
+#define VXGE_HW_DEVICE_DEAD		0xDEADDEAD
+	u16				device_id;
+	u8				major_revision;
+	u8				minor_revision;
+	void __iomem			*bar0;
+	void __iomem			*bar1;
+	void __iomem			*bar2;
+	struct pci_dev			*pdev;
+	struct net_device		*ndev;
+	struct vxge_hw_device_config	config;
+	enum vxge_hw_device_link_state	link_state;
+
+	struct vxge_hw_uld_cbs		uld_callbacks;
+
+	u32				host_type;
+	u32				func_id;
+	u32				access_rights;
+#define VXGE_HW_DEVICE_ACCESS_RIGHT_VPATH      0x1
+#define VXGE_HW_DEVICE_ACCESS_RIGHT_SRPCIM     0x2
+#define VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM     0x4
+	struct vxge_hw_legacy_reg	__iomem *legacy_reg;
+	struct vxge_hw_toc_reg		__iomem *toc_reg;
+	struct vxge_hw_common_reg	__iomem *common_reg;
+	struct vxge_hw_mrpcim_reg	__iomem *mrpcim_reg;
+	struct vxge_hw_srpcim_reg	__iomem *srpcim_reg \
+					[VXGE_HW_TITAN_SRPCIM_REG_SPACES];
+	struct vxge_hw_vpmgmt_reg	__iomem *vpmgmt_reg \
+					[VXGE_HW_TITAN_VPMGMT_REG_SPACES];
+	struct vxge_hw_vpath_reg	__iomem *vpath_reg \
+					[VXGE_HW_TITAN_VPATH_REG_SPACES];
+	u8				__iomem *kdfc;
+	u8				__iomem *usdc;
+	struct __vxge_hw_virtualpath	virtual_paths \
+					[VXGE_HW_MAX_VIRTUAL_PATHS];
+	u64				vpath_assignments;
+	u64				vpaths_deployed;
+	u32				first_vp_id;
+	u64				tim_int_mask0[4];
+	u32				tim_int_mask1[4];
+
+	struct __vxge_hw_blockpool	block_pool;
+	struct vxge_hw_device_stats	stats;
+	u32				debug_module_mask;
+	u32				debug_level;
+	u32				level_err;
+	u32				level_trace;
+};
+
+#define VXGE_HW_INFO_LEN	64
+/**
+ * struct vxge_hw_device_hw_info - Device information
+ * @host_type: Host Type
+ * @func_id: Function Id
+ * @vpath_mask: vpath bit mask
+ * @fw_version: Firmware version
+ * @fw_date: Firmware Date
+ * @flash_version: Firmware version
+ * @flash_date: Firmware Date
+ * @mac_addrs: Mac addresses for each vpath
+ * @mac_addr_masks: Mac address masks for each vpath
+ *
+ * Returns the vpath mask that has the bits set for each vpath allocated
+ * for the driver and the first mac address for each vpath
+ */
+struct vxge_hw_device_hw_info {
+	u32		host_type;
+#define VXGE_HW_NO_MR_NO_SR_NORMAL_FUNCTION			0
+#define VXGE_HW_MR_NO_SR_VH0_BASE_FUNCTION			1
+#define VXGE_HW_NO_MR_SR_VH0_FUNCTION0				2
+#define VXGE_HW_NO_MR_SR_VH0_VIRTUAL_FUNCTION			3
+#define VXGE_HW_MR_SR_VH0_INVALID_CONFIG			4
+#define VXGE_HW_SR_VH_FUNCTION0					5
+#define VXGE_HW_SR_VH_VIRTUAL_FUNCTION				6
+#define VXGE_HW_VH_NORMAL_FUNCTION				7
+	u64		function_mode;
+#define VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION			0
+#define VXGE_HW_FUNCTION_MODE_SINGLE_FUNCTION			1
+#define VXGE_HW_FUNCTION_MODE_SRIOV				2
+#define VXGE_HW_FUNCTION_MODE_MRIOV				3
+	u32		func_id;
+	u64		vpath_mask;
+	struct vxge_hw_device_version fw_version;
+	struct vxge_hw_device_date    fw_date;
+	struct vxge_hw_device_version flash_version;
+	struct vxge_hw_device_date    flash_date;
+	u8		serial_number[VXGE_HW_INFO_LEN];
+	u8		part_number[VXGE_HW_INFO_LEN];
+	u8		product_desc[VXGE_HW_INFO_LEN];
+	u8 (mac_addrs)[VXGE_HW_MAX_VIRTUAL_PATHS][ETH_ALEN];
+	u8 (mac_addr_masks)[VXGE_HW_MAX_VIRTUAL_PATHS][ETH_ALEN];
+};
+
+/**
+ * struct vxge_hw_device_attr - Device memory spaces.
+ * @bar0: BAR0 virtual address.
+ * @bar1: BAR1 virtual address.
+ * @bar2: BAR2 virtual address.
+ * @pdev: PCI device object.
+ *
+ * Device memory spaces. Includes configuration, BAR0, BAR1, etc. per device
+ * mapped memories. Also, includes a pointer to OS-specific PCI device object.
+ */
+struct vxge_hw_device_attr {
+	void __iomem		*bar0;
+	void __iomem		*bar1;
+	void __iomem		*bar2;
+	struct pci_dev 		*pdev;
+	struct vxge_hw_uld_cbs	uld_callbacks;
+};
+
+#define VXGE_HW_DEVICE_LINK_STATE_SET(hldev, ls)	(hldev->link_state = ls)
+
+#define VXGE_HW_DEVICE_TIM_INT_MASK_SET(m0, m1, i) {	\
+	if (i < 16) {				\
+		m0[0] |= vxge_vBIT(0x8, (i*4), 4);	\
+		m0[1] |= vxge_vBIT(0x4, (i*4), 4);	\
+	}			       		\
+	else {					\
+		m1[0] = 0x80000000;		\
+		m1[1] = 0x40000000;		\
+	}					\
+}
+
+#define VXGE_HW_DEVICE_TIM_INT_MASK_RESET(m0, m1, i) {	\
+	if (i < 16) {					\
+		m0[0] &= ~vxge_vBIT(0x8, (i*4), 4);		\
+		m0[1] &= ~vxge_vBIT(0x4, (i*4), 4);		\
+	}						\
+	else {						\
+		m1[0] = 0;				\
+		m1[1] = 0;				\
+	}						\
+}
+
+#define VXGE_HW_DEVICE_STATS_PIO_READ(loc, offset) {		\
+	status = vxge_hw_mrpcim_stats_access(hldev, \
+				VXGE_HW_STATS_OP_READ, \
+				loc, \
+				offset, \
+				&val64);			\
+								\
+	if (status != VXGE_HW_OK)				\
+		return status;						\
+}
+
+#define VXGE_HW_VPATH_STATS_PIO_READ(offset) {				\
+	status = __vxge_hw_vpath_stats_access(vpath, \
+			VXGE_HW_STATS_OP_READ, \
+			offset, \
+			&val64);					\
+	if (status != VXGE_HW_OK)					\
+		return status;						\
+}
+
+/*
+ * struct __vxge_hw_ring - Ring channel.
+ * @channel: Channel "base" of this ring, the common part of all HW
+ *           channels.
+ * @mempool: Memory pool, the pool from which descriptors get allocated.
+ *           (See vxge_hw_mm.h).
+ * @config: Ring configuration, part of device configuration
+ *          (see struct vxge_hw_device_config{}).
+ * @ring_length: Length of the ring
+ * @buffer_mode: 1, 3, or 5. The value specifies a receive buffer mode,
+ *          as per Titan User Guide.
+ * @rxd_size: RxD sizes for 1-, 3- or 5- buffer modes. As per Titan spec,
+ *            1-buffer mode descriptor is 32 byte long, etc.
+ * @rxd_priv_size: Per RxD size reserved (by HW) for driver to keep
+ *                 per-descriptor data (e.g., DMA handle for Solaris)
+ * @per_rxd_space: Per rxd space requested by driver
+ * @rxds_per_block: Number of descriptors per hardware-defined RxD
+ *                  block. Depends on the (1-, 3-, 5-) buffer mode.
+ * @rxdblock_priv_size: Reserved at the end of each RxD block. HW internal
+ *                      usage. Not to confuse with @rxd_priv_size.
+ * @cmpl_cnt: Completion counter. Is reset to zero upon entering the ISR.
+ * @callback: Channel completion callback. HW invokes the callback when there
+ *            are new completions on that channel. In many implementations
+ *            the @callback executes in the hw interrupt context.
+ * @rxd_init: Channel's descriptor-initialize callback.
+ *            See vxge_hw_ring_rxd_init_f{}.
+ *            If not NULL, HW invokes the callback when opening
+ *            the ring.
+ * @rxd_term: Channel's descriptor-terminate callback. If not NULL,
+ *          HW invokes the callback when closing the corresponding channel.
+ *          See also vxge_hw_channel_rxd_term_f{}.
+ * @stats: Statistics for ring
+ * Ring channel.
+ *
+ * Note: The structure is cache line aligned to better utilize
+ *       CPU cache performance.
+ */
+struct __vxge_hw_ring {
+	struct __vxge_hw_channel		channel;
+	struct vxge_hw_mempool			*mempool;
+	struct vxge_hw_vpath_reg		__iomem	*vp_reg;
+	struct vxge_hw_common_reg		__iomem	*common_reg;
+	u32					ring_length;
+	u32					buffer_mode;
+	u32					rxd_size;
+	u32					rxd_priv_size;
+	u32					per_rxd_space;
+	u32					rxds_per_block;
+	u32					rxdblock_priv_size;
+	u32					cmpl_cnt;
+	u32					vp_id;
+	u32					doorbell_cnt;
+	u32					total_db_cnt;
+	u64					rxds_limit;
+
+	enum vxge_hw_status (*callback)(
+			struct __vxge_hw_ring *ringh,
+			void *rxdh,
+			u8 t_code,
+			void *userdata);
+
+	enum vxge_hw_status (*rxd_init)(
+			void *rxdh,
+			void *userdata);
+
+	void (*rxd_term)(
+			void *rxdh,
+			enum vxge_hw_rxd_state state,
+			void *userdata);
+
+	struct vxge_hw_vpath_stats_sw_ring_info *stats	____cacheline_aligned;
+	struct vxge_hw_ring_config		*config;
+} ____cacheline_aligned;
+
+/**
+ * enum enum vxge_hw_txdl_state - Descriptor (TXDL) state.
+ * @VXGE_HW_TXDL_STATE_NONE: Invalid state.
+ * @VXGE_HW_TXDL_STATE_AVAIL: Descriptor is available for reservation.
+ * @VXGE_HW_TXDL_STATE_POSTED: Descriptor is posted for processing by the
+ * device.
+ * @VXGE_HW_TXDL_STATE_FREED: Descriptor is free and can be reused for
+ * filling-in and posting later.
+ *
+ * Titan/HW descriptor states.
+ *
+ */
+enum vxge_hw_txdl_state {
+	VXGE_HW_TXDL_STATE_NONE	= 0,
+	VXGE_HW_TXDL_STATE_AVAIL	= 1,
+	VXGE_HW_TXDL_STATE_POSTED	= 2,
+	VXGE_HW_TXDL_STATE_FREED	= 3
+};
+/*
+ * struct __vxge_hw_fifo - Fifo.
+ * @channel: Channel "base" of this fifo, the common part of all HW
+ *             channels.
+ * @mempool: Memory pool, from which descriptors get allocated.
+ * @config: Fifo configuration, part of device configuration
+ *             (see struct vxge_hw_device_config{}).
+ * @interrupt_type: Interrupt type to be used
+ * @no_snoop_bits: See struct vxge_hw_fifo_config{}.
+ * @txdl_per_memblock: Number of TxDLs (TxD lists) per memblock.
+ *             on TxDL please refer to Titan UG.
+ * @txdl_size: Configured TxDL size (i.e., number of TxDs in a list), plus
+ *             per-TxDL HW private space (struct __vxge_hw_fifo_txdl_priv).
+ * @priv_size: Per-Tx descriptor space reserved for driver
+ *             usage.
+ * @per_txdl_space: Per txdl private space for the driver
+ * @callback: Fifo completion callback. HW invokes the callback when there
+ *             are new completions on that fifo. In many implementations
+ *             the @callback executes in the hw interrupt context.
+ * @txdl_term: Fifo's descriptor-terminate callback. If not NULL,
+ *             HW invokes the callback when closing the corresponding fifo.
+ *             See also vxge_hw_fifo_txdl_term_f{}.
+ * @stats: Statistics of this fifo
+ *
+ * Fifo channel.
+ * Note: The structure is cache line aligned.
+ */
+struct __vxge_hw_fifo {
+	struct __vxge_hw_channel		channel;
+	struct vxge_hw_mempool			*mempool;
+	struct vxge_hw_fifo_config		*config;
+	struct vxge_hw_vpath_reg		__iomem *vp_reg;
+	struct __vxge_hw_non_offload_db_wrapper	__iomem *nofl_db;
+	u64					interrupt_type;
+	u32					no_snoop_bits;
+	u32					txdl_per_memblock;
+	u32					txdl_size;
+	u32					priv_size;
+	u32					per_txdl_space;
+	u32					vp_id;
+	u32					tx_intr_num;
+
+	enum vxge_hw_status (*callback)(
+			struct __vxge_hw_fifo *fifo_handle,
+			void *txdlh,
+			enum vxge_hw_fifo_tcode t_code,
+			void *userdata,
+			void **skb_ptr);
+
+	void (*txdl_term)(
+			void *txdlh,
+			enum vxge_hw_txdl_state state,
+			void *userdata);
+
+	struct vxge_hw_vpath_stats_sw_fifo_info *stats ____cacheline_aligned;
+} ____cacheline_aligned;
+
+/*
+ * struct __vxge_hw_fifo_txdl_priv - Transmit descriptor HW-private data.
+ * @dma_addr: DMA (mapped) address of _this_ descriptor.
+ * @dma_handle: DMA handle used to map the descriptor onto device.
+ * @dma_offset: Descriptor's offset in the memory block. HW allocates
+ *	 descriptors in memory blocks (see struct vxge_hw_fifo_config{})
+ *             Each memblock is a contiguous block of DMA-able memory.
+ * @frags: Total number of fragments (that is, contiguous data buffers)
+ * carried by this TxDL.
+ * @align_vaddr_start: Aligned virtual address start
+ * @align_vaddr: Virtual address of the per-TxDL area in memory used for
+ *             alignement. Used to place one or more mis-aligned fragments
+ * @align_dma_addr: DMA address translated from the @align_vaddr.
+ * @align_dma_handle: DMA handle that corresponds to @align_dma_addr.
+ * @align_dma_acch: DMA access handle corresponds to @align_dma_addr.
+ * @align_dma_offset: The current offset into the @align_vaddr area.
+ * Grows while filling the descriptor, gets reset.
+ * @align_used_frags: Number of fragments used.
+ * @alloc_frags: Total number of fragments allocated.
+ * @unused: TODO
+ * @next_txdl_priv: (TODO).
+ * @first_txdp: (TODO).
+ * @linked_txdl_priv: Pointer to any linked TxDL for creating contiguous
+ *             TxDL list.
+ * @txdlh: Corresponding txdlh to this TxDL.
+ * @memblock: Pointer to the TxDL memory block or memory page.
+ *             on the next send operation.
+ * @dma_object: DMA address and handle of the memory block that contains
+ *             the descriptor. This member is used only in the "checked"
+ *             version of the HW (to enforce certain assertions);
+ *             otherwise it gets compiled out.
+ * @allocated: True if the descriptor is reserved, 0 otherwise. Internal usage.
+ *
+ * Per-transmit decsriptor HW-private data. HW uses the space to keep DMA
+ * information associated with the descriptor. Note that driver can ask HW
+ * to allocate additional per-descriptor space for its own (driver-specific)
+ * purposes.
+ *
+ * See also: struct vxge_hw_ring_rxd_priv{}.
+ */
+struct __vxge_hw_fifo_txdl_priv {
+	dma_addr_t		dma_addr;
+	struct pci_dev	*dma_handle;
+	ptrdiff_t		dma_offset;
+	u32				frags;
+	u8				*align_vaddr_start;
+	u8				*align_vaddr;
+	dma_addr_t		align_dma_addr;
+	struct pci_dev 	*align_dma_handle;
+	struct pci_dev	*align_dma_acch;
+	ptrdiff_t		align_dma_offset;
+	u32				align_used_frags;
+	u32				alloc_frags;
+	u32				unused;
+	struct __vxge_hw_fifo_txdl_priv	*next_txdl_priv;
+	struct vxge_hw_fifo_txd		*first_txdp;
+	void			*memblock;
+};
+
+/*
+ * struct __vxge_hw_non_offload_db_wrapper - Non-offload Doorbell Wrapper
+ * @control_0: Bits 0 to 7 - Doorbell type.
+ *             Bits 8 to 31 - Reserved.
+ *             Bits 32 to 39 - The highest TxD in this TxDL.
+ *             Bits 40 to 47 - Reserved.
+	*	       Bits 48 to 55 - Reserved.
+ *             Bits 56 to 63 - No snoop flags.
+ * @txdl_ptr:  The starting location of the TxDL in host memory.
+ *
+ * Created by the host and written to the adapter via PIO to a Kernel Doorbell
+ * FIFO. All non-offload doorbell wrapper fields must be written by the host as
+ * part of a doorbell write. Consumed by the adapter but is not written by the
+ * adapter.
+ */
+struct __vxge_hw_non_offload_db_wrapper {
+	u64		control_0;
+#define	VXGE_HW_NODBW_GET_TYPE(ctrl0)			vxge_bVALn(ctrl0, 0, 8)
+#define VXGE_HW_NODBW_TYPE(val) vxge_vBIT(val, 0, 8)
+#define	VXGE_HW_NODBW_TYPE_NODBW				0
+
+#define	VXGE_HW_NODBW_GET_LAST_TXD_NUMBER(ctrl0)	vxge_bVALn(ctrl0, 32, 8)
+#define VXGE_HW_NODBW_LAST_TXD_NUMBER(val) vxge_vBIT(val, 32, 8)
+
+#define	VXGE_HW_NODBW_GET_NO_SNOOP(ctrl0)		vxge_bVALn(ctrl0, 56, 8)
+#define VXGE_HW_NODBW_LIST_NO_SNOOP(val) vxge_vBIT(val, 56, 8)
+#define	VXGE_HW_NODBW_LIST_NO_SNOOP_TXD_READ_TXD0_WRITE		0x2
+#define	VXGE_HW_NODBW_LIST_NO_SNOOP_TX_FRAME_DATA_READ		0x1
+
+	u64		txdl_ptr;
+};
+
+/*
+ * TX Descriptor
+ */
+
+/**
+ * struct vxge_hw_fifo_txd - Transmit Descriptor
+ * @control_0: Bits 0 to 6 - Reserved.
+ *             Bit 7 - List Ownership. This field should be initialized
+ *             to '1' by the driver before the transmit list pointer is
+ *             written to the adapter. This field will be set to '0' by the
+ *             adapter once it has completed transmitting the frame or frames in
+ *             the list. Note - This field is only valid in TxD0. Additionally,
+ *             for multi-list sequences, the driver should not release any
+ *             buffers until the ownership of the last list in the multi-list
+ *             sequence has been returned to the host.
+ *             Bits 8 to 11 - Reserved
+ *             Bits 12 to 15 - Transfer_Code. This field is only valid in
+ *             TxD0. It is used to describe the status of the transmit data
+ *             buffer transfer. This field is always overwritten by the
+ *             adapter, so this field may be initialized to any value.
+ *             Bits 16 to 17 - Host steering. This field allows the host to
+ *             override the selection of the physical transmit port.
+ *             Attention:
+ *             Normal sounds as if learned from the switch rather than from
+ *             the aggregation algorythms.
+ *             00: Normal. Use Destination/MAC Address
+ *             lookup to determine the transmit port.
+ *             01: Send on physical Port1.
+ *             10: Send on physical Port0.
+	*	       11: Send on both ports.
+ *             Bits 18 to 21 - Reserved
+ *             Bits 22 to 23 - Gather_Code. This field is set by the host and
+ *             is used to describe how individual buffers comprise a frame.
+ *             10: First descriptor of a frame.
+ *             00: Middle of a multi-descriptor frame.
+ *             01: Last descriptor of a frame.
+ *             11: First and last descriptor of a frame (the entire frame
+ *             resides in a single buffer).
+ *             For multi-descriptor frames, the only valid gather code sequence
+ *             is {10, [00], 01}. In other words, the descriptors must be placed
+ *             in the list in the correct order.
+ *             Bits 24 to 27 - Reserved
+ *             Bits 28 to 29 - LSO_Frm_Encap. LSO Frame Encapsulation
+ *             definition. Only valid in TxD0. This field allows the host to
+ *             indicate the Ethernet encapsulation of an outbound LSO packet.
+ *             00 - classic mode (best guess)
+ *             01 - LLC
+ *             10 - SNAP
+ *             11 - DIX
+ *             If "classic mode" is selected, the adapter will attempt to
+ *             decode the frame's Ethernet encapsulation by examining the L/T
+ *             field as follows:
+ *             <= 0x05DC LLC/SNAP encoding; must examine DSAP/SSAP to determine
+ *             if packet is IPv4 or IPv6.
+ *             0x8870 Jumbo-SNAP encoding.
+ *             0x0800 IPv4 DIX encoding
+ *             0x86DD IPv6 DIX encoding
+ *             others illegal encapsulation
+ *             Bits 30 - LSO_ Flag. Large Send Offload (LSO) flag.
+ *             Set to 1 to perform segmentation offload for TCP/UDP.
+ *             This field is valid only in TxD0.
+ *             Bits 31 to 33 - Reserved.
+ *             Bits 34 to 47 - LSO_MSS. TCP/UDP LSO Maximum Segment Size
+ *             This field is meaningful only when LSO_Control is non-zero.
+ *             When LSO_Control is set to TCP_LSO, the single (possibly large)
+ *             TCP segment described by this TxDL will be sent as a series of
+ *             TCP segments each of which contains no more than LSO_MSS
+ *             payload bytes.
+ *             When LSO_Control is set to UDP_LSO, the single (possibly large)
+ *             UDP datagram described by this TxDL will be sent as a series of
+ *             UDP datagrams each of which contains no more than LSO_MSS
+ *             payload bytes.
+ *             All outgoing frames from this TxDL will have LSO_MSS bytes of UDP
+ *             or TCP payload, with the exception of the last, which will have
+ *             <= LSO_MSS bytes of payload.
+ *             Bits 48 to 63 - Buffer_Size. Number of valid bytes in the
+ *             buffer to be read by the adapter. This field is written by the
+ *             host. A value of 0 is illegal.
+ *	       Bits 32 to 63 - This value is written by the adapter upon
+ *	       completion of a UDP or TCP LSO operation and indicates the number
+ *             of UDP or TCP payload bytes that were transmitted. 0x0000 will be
+ *             returned for any non-LSO operation.
+ * @control_1: Bits 0 to 4 - Reserved.
+ *             Bit 5 - Tx_CKO_IPv4 Set to a '1' to enable IPv4 header checksum
+ *             offload. This field is only valid in the first TxD of a frame.
+ *             Bit 6 - Tx_CKO_TCP Set to a '1' to enable TCP checksum offload.
+ *             This field is only valid in the first TxD of a frame (the TxD's
+ *             gather code must be 10 or 11). The driver should only set this
+ *             bit if it can guarantee that TCP is present.
+ *             Bit 7 - Tx_CKO_UDP Set to a '1' to enable UDP checksum offload.
+ *             This field is only valid in the first TxD of a frame (the TxD's
+ *             gather code must be 10 or 11). The driver should only set this
+ *             bit if it can guarantee that UDP is present.
+ *             Bits 8 to 14 - Reserved.
+ *             Bit 15 - Tx_VLAN_Enable VLAN tag insertion flag. Set to a '1' to
+ *             instruct the adapter to insert the VLAN tag specified by the
+ *             Tx_VLAN_Tag field. This field is only valid in the first TxD of
+ *             a frame.
+ *             Bits 16 to 31 - Tx_VLAN_Tag. Variable portion of the VLAN tag
+ *             to be inserted into the frame by the adapter (the first two bytes
+ *             of a VLAN tag are always 0x8100). This field is only valid if the
+ *             Tx_VLAN_Enable field is set to '1'.
+ *             Bits 32 to 33 - Reserved.
+ *             Bits 34 to 39 - Tx_Int_Number. Indicates which Tx interrupt
+ *             number the frame associated with. This field is written by the
+ *             host. It is only valid in the first TxD of a frame.
+ *             Bits 40 to 42 - Reserved.
+ *             Bit 43 - Set to 1 to exclude the frame from bandwidth metering
+ *             functions. This field is valid only in the first TxD
+ *             of a frame.
+ *             Bits 44 to 45 - Reserved.
+ *             Bit 46 - Tx_Int_Per_List Set to a '1' to instruct the adapter to
+ *             generate an interrupt as soon as all of the frames in the list
+ *             have been transmitted. In order to have per-frame interrupts,
+ *             the driver should place a maximum of one frame per list. This
+ *             field is only valid in the first TxD of a frame.
+ *             Bit 47 - Tx_Int_Utilization Set to a '1' to instruct the adapter
+ *             to count the frame toward the utilization interrupt specified in
+ *             the Tx_Int_Number field. This field is only valid in the first
+ *             TxD of a frame.
+ *             Bits 48 to 63 - Reserved.
+ * @buffer_pointer: Buffer start address.
+ * @host_control: Host_Control.Opaque 64bit data stored by driver inside the
+ *            Titan descriptor prior to posting the latter on the fifo
+ *            via vxge_hw_fifo_txdl_post().The %host_control is returned as is
+ *            to the driver with each completed descriptor.
+ *
+ * Transmit descriptor (TxD).Fifo descriptor contains configured number
+ * (list) of TxDs. * For more details please refer to Titan User Guide,
+ * Section 5.4.2 "Transmit Descriptor (TxD) Format".
+ */
+struct vxge_hw_fifo_txd {
+	u64 control_0;
+#define VXGE_HW_FIFO_TXD_LIST_OWN_ADAPTER		vxge_mBIT(7)
+
+#define VXGE_HW_FIFO_TXD_T_CODE_GET(ctrl0)		vxge_bVALn(ctrl0, 12, 4)
+#define VXGE_HW_FIFO_TXD_T_CODE(val) 			vxge_vBIT(val, 12, 4)
+#define VXGE_HW_FIFO_TXD_T_CODE_UNUSED		VXGE_HW_FIFO_T_CODE_UNUSED
+
+
+#define VXGE_HW_FIFO_TXD_GATHER_CODE(val) 		vxge_vBIT(val, 22, 2)
+#define VXGE_HW_FIFO_TXD_GATHER_CODE_FIRST	VXGE_HW_FIFO_GATHER_CODE_FIRST
+#define VXGE_HW_FIFO_TXD_GATHER_CODE_LAST	VXGE_HW_FIFO_GATHER_CODE_LAST
+
+
+#define VXGE_HW_FIFO_TXD_LSO_EN				vxge_mBIT(30)
+
+#define VXGE_HW_FIFO_TXD_LSO_MSS(val) 			vxge_vBIT(val, 34, 14)
+
+#define VXGE_HW_FIFO_TXD_BUFFER_SIZE(val) 		vxge_vBIT(val, 48, 16)
+
+	u64 control_1;
+#define VXGE_HW_FIFO_TXD_TX_CKO_IPV4_EN			vxge_mBIT(5)
+#define VXGE_HW_FIFO_TXD_TX_CKO_TCP_EN			vxge_mBIT(6)
+#define VXGE_HW_FIFO_TXD_TX_CKO_UDP_EN			vxge_mBIT(7)
+#define VXGE_HW_FIFO_TXD_VLAN_ENABLE			vxge_mBIT(15)
+
+#define VXGE_HW_FIFO_TXD_VLAN_TAG(val) 			vxge_vBIT(val, 16, 16)
+
+#define VXGE_HW_FIFO_TXD_INT_NUMBER(val) 		vxge_vBIT(val, 34, 6)
+
+#define VXGE_HW_FIFO_TXD_INT_TYPE_PER_LIST		vxge_mBIT(46)
+#define VXGE_HW_FIFO_TXD_INT_TYPE_UTILZ			vxge_mBIT(47)
+
+	u64 buffer_pointer;
+
+	u64 host_control;
+};
+
+/**
+ * struct vxge_hw_ring_rxd_1 - One buffer mode RxD for ring
+ * @host_control: This field is exclusively for host use and is "readonly"
+ *             from the adapter's perspective.
+ * @control_0:Bits 0 to 6 - RTH_Bucket get
+ *	      Bit 7 - Own Descriptor ownership bit. This bit is set to 1
+ *            by the host, and is set to 0 by the adapter.
+ *	      0 - Host owns RxD and buffer.
+ *	      1 - The adapter owns RxD and buffer.
+ *	      Bit 8 - Fast_Path_Eligible When set, indicates that the
+ *            received frame meets all of the criteria for fast path processing.
+ *            The required criteria are as follows:
+ *            !SYN &
+ *            (Transfer_Code == "Transfer OK") &
+ *            (!Is_IP_Fragment) &
+ *            ((Is_IPv4 & computed_L3_checksum == 0xFFFF) |
+ *            (Is_IPv6)) &
+ *            ((Is_TCP & computed_L4_checksum == 0xFFFF) |
+ *            (Is_UDP & (computed_L4_checksum == 0xFFFF |
+ *            computed _L4_checksum == 0x0000)))
+ *            (same meaning for all RxD buffer modes)
+ *	      Bit 9 - L3 Checksum Correct
+ *	      Bit 10 - L4 Checksum Correct
+ *	      Bit 11 - Reserved
+ *	      Bit 12 to 15 - This field is written by the adapter. It is
+ *            used to report the status of the frame transfer to the host.
+ *	      0x0 - Transfer OK
+ *	      0x4 - RDA Failure During Transfer
+ *	      0x5 - Unparseable Packet, such as unknown IPv6 header.
+ *	      0x6 - Frame integrity error (FCS or ECC).
+ *	      0x7 - Buffer Size Error. The provided buffer(s) were not
+ *                  appropriately sized and data loss occurred.
+ *	      0x8 - Internal ECC Error. RxD corrupted.
+ *	      0x9 - IPv4 Checksum error
+ *	      0xA - TCP/UDP Checksum error
+ *	      0xF - Unknown Error or Multiple Error. Indicates an
+ *               unknown problem or that more than one of transfer codes is set.
+ *	      Bit 16 - SYN The adapter sets this field to indicate that
+ *                the incoming frame contained a TCP segment with its SYN bit
+ *	          set and its ACK bit NOT set. (same meaning for all RxD buffer
+ *                modes)
+ *	      Bit 17 - Is ICMP
+ *	      Bit 18 - RTH_SPDM_HIT Set to 1 if there was a match in the
+ *                Socket Pair Direct Match Table and the frame was steered based
+ *                on SPDM.
+ *	      Bit 19 - RTH_IT_HIT Set to 1 if there was a match in the
+ *            Indirection Table and the frame was steered based on hash
+ *            indirection.
+ *	      Bit 20 to 23 - RTH_HASH_TYPE Indicates the function (hash
+ *	          type) that was used to calculate the hash.
+ *	      Bit 19 - IS_VLAN Set to '1' if the frame was/is VLAN
+ *	          tagged.
+ *	      Bit 25 to 26 - ETHER_ENCAP Reflects the Ethernet encapsulation
+ *                of the received frame.
+ *	      0x0 - Ethernet DIX
+ *	      0x1 - LLC
+ *	      0x2 - SNAP (includes Jumbo-SNAP)
+ *	      0x3 - IPX
+ *	      Bit 27 - IS_IPV4 Set to '1' if the frame contains an IPv4	packet.
+ *	      Bit 28 - IS_IPV6 Set to '1' if the frame contains an IPv6 packet.
+ *	      Bit 29 - IS_IP_FRAG Set to '1' if the frame contains a fragmented
+ *            IP packet.
+ *	      Bit 30 - IS_TCP Set to '1' if the frame contains a TCP segment.
+ *	      Bit 31 - IS_UDP Set to '1' if the frame contains a UDP message.
+ *	      Bit 32 to 47 - L3_Checksum[0:15] The IPv4 checksum value 	that
+ *            arrived with the frame. If the resulting computed IPv4 header
+ *            checksum for the frame did not produce the expected 0xFFFF value,
+ *            then the transfer code would be set to 0x9.
+ *	      Bit 48 to 63 - L4_Checksum[0:15] The TCP/UDP checksum value that
+ *            arrived with the frame. If the resulting computed TCP/UDP checksum
+ *            for the frame did not produce the expected 0xFFFF value, then the
+ *            transfer code would be set to 0xA.
+ * @control_1:Bits 0 to 1 - Reserved
+ *            Bits 2 to 15 - Buffer0_Size.This field is set by the host and
+ *            eventually overwritten by the adapter. The host writes the
+ *            available buffer size in bytes when it passes the descriptor to
+ *            the adapter. When a frame is delivered the host, the adapter
+ *            populates this field with the number of bytes written into the
+ *            buffer. The largest supported buffer is 16, 383 bytes.
+ *	      Bit 16 to 47 - RTH Hash Value 32-bit RTH hash value. Only valid if
+ *	      RTH_HASH_TYPE (Control_0, bits 20:23) is nonzero.
+ *	      Bit 48 to 63 - VLAN_Tag[0:15] The contents of the variable portion
+ *            of the VLAN tag, if one was detected by the adapter. This field is
+ *            populated even if VLAN-tag stripping is enabled.
+ * @buffer0_ptr: Pointer to buffer. This field is populated by the driver.
+ *
+ * One buffer mode RxD for ring structure
+ */
+struct vxge_hw_ring_rxd_1 {
+	u64 host_control;
+	u64 control_0;
+#define VXGE_HW_RING_RXD_RTH_BUCKET_GET(ctrl0)		vxge_bVALn(ctrl0, 0, 7)
+
+#define VXGE_HW_RING_RXD_LIST_OWN_ADAPTER		vxge_mBIT(7)
+
+#define VXGE_HW_RING_RXD_FAST_PATH_ELIGIBLE_GET(ctrl0)	vxge_bVALn(ctrl0, 8, 1)
+
+#define VXGE_HW_RING_RXD_L3_CKSUM_CORRECT_GET(ctrl0)	vxge_bVALn(ctrl0, 9, 1)
+
+#define VXGE_HW_RING_RXD_L4_CKSUM_CORRECT_GET(ctrl0)	vxge_bVALn(ctrl0, 10, 1)
+
+#define VXGE_HW_RING_RXD_T_CODE_GET(ctrl0)		vxge_bVALn(ctrl0, 12, 4)
+#define VXGE_HW_RING_RXD_T_CODE(val) 			vxge_vBIT(val, 12, 4)
+
+#define VXGE_HW_RING_RXD_T_CODE_UNUSED		VXGE_HW_RING_T_CODE_UNUSED
+
+#define VXGE_HW_RING_RXD_SYN_GET(ctrl0)		vxge_bVALn(ctrl0, 16, 1)
+
+#define VXGE_HW_RING_RXD_IS_ICMP_GET(ctrl0)		vxge_bVALn(ctrl0, 17, 1)
+
+#define VXGE_HW_RING_RXD_RTH_SPDM_HIT_GET(ctrl0)	vxge_bVALn(ctrl0, 18, 1)
+
+#define VXGE_HW_RING_RXD_RTH_IT_HIT_GET(ctrl0)		vxge_bVALn(ctrl0, 19, 1)
+
+#define VXGE_HW_RING_RXD_RTH_HASH_TYPE_GET(ctrl0)	vxge_bVALn(ctrl0, 20, 4)
+
+#define VXGE_HW_RING_RXD_IS_VLAN_GET(ctrl0)		vxge_bVALn(ctrl0, 24, 1)
+
+#define VXGE_HW_RING_RXD_ETHER_ENCAP_GET(ctrl0)		vxge_bVALn(ctrl0, 25, 2)
+
+#define VXGE_HW_RING_RXD_FRAME_PROTO_GET(ctrl0)		vxge_bVALn(ctrl0, 27, 5)
+
+#define VXGE_HW_RING_RXD_L3_CKSUM_GET(ctrl0)	vxge_bVALn(ctrl0, 32, 16)
+
+#define VXGE_HW_RING_RXD_L4_CKSUM_GET(ctrl0)	vxge_bVALn(ctrl0, 48, 16)
+
+	u64 control_1;
+
+#define VXGE_HW_RING_RXD_1_BUFFER0_SIZE_GET(ctrl1)	vxge_bVALn(ctrl1, 2, 14)
+#define VXGE_HW_RING_RXD_1_BUFFER0_SIZE(val) vxge_vBIT(val, 2, 14)
+#define VXGE_HW_RING_RXD_1_BUFFER0_SIZE_MASK		vxge_vBIT(0x3FFF, 2, 14)
+
+#define VXGE_HW_RING_RXD_1_RTH_HASH_VAL_GET(ctrl1)    vxge_bVALn(ctrl1, 16, 32)
+
+#define VXGE_HW_RING_RXD_VLAN_TAG_GET(ctrl1)	vxge_bVALn(ctrl1, 48, 16)
+
+	u64 buffer0_ptr;
+};
+
+enum vxge_hw_rth_algoritms {
+	RTH_ALG_JENKINS = 0,
+	RTH_ALG_MS_RSS	= 1,
+	RTH_ALG_CRC32C	= 2
+};
+
+/**
+ * struct vxge_hw_rth_hash_types - RTH hash types.
+ * @hash_type_tcpipv4_en: Enables RTH field type HashTypeTcpIPv4
+ * @hash_type_ipv4_en: Enables RTH field type HashTypeIPv4
+ * @hash_type_tcpipv6_en: Enables RTH field type HashTypeTcpIPv6
+ * @hash_type_ipv6_en: Enables RTH field type HashTypeIPv6
+ * @hash_type_tcpipv6ex_en: Enables RTH field type HashTypeTcpIPv6Ex
+ * @hash_type_ipv6ex_en: Enables RTH field type HashTypeIPv6Ex
+ *
+ * Used to pass RTH hash types to rts_rts_set.
+ *
+ * See also: vxge_hw_vpath_rts_rth_set(), vxge_hw_vpath_rts_rth_get().
+ */
+struct vxge_hw_rth_hash_types {
+	u8 hash_type_tcpipv4_en;
+	u8 hash_type_ipv4_en;
+	u8 hash_type_tcpipv6_en;
+	u8 hash_type_ipv6_en;
+	u8 hash_type_tcpipv6ex_en;
+	u8 hash_type_ipv6ex_en;
+};
+
+u32
+vxge_hw_device_debug_mask_get(struct __vxge_hw_device *devh);
+
+void vxge_hw_device_debug_set(
+	struct __vxge_hw_device *devh,
+	enum vxge_debug_level level,
+	u32 mask);
+
+u32
+vxge_hw_device_error_level_get(struct __vxge_hw_device *devh);
+
+u32
+vxge_hw_device_trace_level_get(struct __vxge_hw_device *devh);
+
+u32
+vxge_hw_device_debug_mask_get(struct __vxge_hw_device *devh);
+
+/**
+ * vxge_hw_ring_rxd_size_get	- Get the size of ring descriptor.
+ * @buf_mode: Buffer mode (1, 3 or 5)
+ *
+ * This function returns the size of RxD for given buffer mode
+ */
+static inline u32 vxge_hw_ring_rxd_size_get(u32 buf_mode)
+{
+	return sizeof(struct vxge_hw_ring_rxd_1);
+}
+
+/**
+ * vxge_hw_ring_rxds_per_block_get - Get the number of rxds per block.
+ * @buf_mode: Buffer mode (1 buffer mode only)
+ *
+ * This function returns the number of RxD for RxD block for given buffer mode
+ */
+static inline u32 vxge_hw_ring_rxds_per_block_get(u32 buf_mode)
+{
+	return (u32)((VXGE_HW_BLOCK_SIZE-16) /
+		sizeof(struct vxge_hw_ring_rxd_1));
+}
+
+/**
+ * vxge_hw_ring_rxd_1b_set - Prepare 1-buffer-mode descriptor.
+ * @rxdh: Descriptor handle.
+ * @dma_pointer: DMA address of	a single receive buffer	this descriptor
+ * should carry. Note that by the time vxge_hw_ring_rxd_1b_set is called,
+ * the receive buffer should be already mapped to the device
+ * @size: Size of the receive @dma_pointer buffer.
+ *
+ * Prepare 1-buffer-mode Rx	descriptor for posting
+ * (via	vxge_hw_ring_rxd_post()).
+ *
+ * This	inline helper-function does not	return any parameters and always
+ * succeeds.
+ *
+ */
+static inline
+void vxge_hw_ring_rxd_1b_set(
+	void *rxdh,
+	dma_addr_t dma_pointer,
+	u32 size)
+{
+	struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh;
+	rxdp->buffer0_ptr = dma_pointer;
+	rxdp->control_1	&= ~VXGE_HW_RING_RXD_1_BUFFER0_SIZE_MASK;
+	rxdp->control_1	|= VXGE_HW_RING_RXD_1_BUFFER0_SIZE(size);
+}
+
+/**
+ * vxge_hw_ring_rxd_1b_get - Get data from the completed 1-buf
+ * descriptor.
+ * @vpath_handle: Virtual Path handle.
+ * @rxdh: Descriptor handle.
+ * @dma_pointer: DMA address of	a single receive buffer	this descriptor
+ * carries. Returned by HW.
+ * @pkt_length:	Length (in bytes) of the data in the buffer pointed by
+ *
+ * Retrieve protocol data from the completed 1-buffer-mode Rx descriptor.
+ * This	inline helper-function uses completed descriptor to populate receive
+ * buffer pointer and other "out" parameters. The function always succeeds.
+ *
+ */
+static inline
+void vxge_hw_ring_rxd_1b_get(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh,
+	u32 *pkt_length)
+{
+	struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh;
+
+	*pkt_length =
+		(u32)VXGE_HW_RING_RXD_1_BUFFER0_SIZE_GET(rxdp->control_1);
+}
+
+/**
+ * vxge_hw_ring_rxd_1b_info_get - Get extended information associated with
+ * a completed receive descriptor for 1b mode.
+ * @vpath_handle: Virtual Path handle.
+ * @rxdh: Descriptor handle.
+ * @rxd_info: Descriptor information
+ *
+ * Retrieve extended information associated with a completed receive descriptor.
+ *
+ */
+static inline
+void vxge_hw_ring_rxd_1b_info_get(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh,
+	struct vxge_hw_ring_rxd_info *rxd_info)
+{
+
+	struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh;
+	rxd_info->syn_flag =
+		(u32)VXGE_HW_RING_RXD_SYN_GET(rxdp->control_0);
+	rxd_info->is_icmp =
+		(u32)VXGE_HW_RING_RXD_IS_ICMP_GET(rxdp->control_0);
+	rxd_info->fast_path_eligible =
+		(u32)VXGE_HW_RING_RXD_FAST_PATH_ELIGIBLE_GET(rxdp->control_0);
+	rxd_info->l3_cksum_valid =
+		(u32)VXGE_HW_RING_RXD_L3_CKSUM_CORRECT_GET(rxdp->control_0);
+	rxd_info->l3_cksum =
+		(u32)VXGE_HW_RING_RXD_L3_CKSUM_GET(rxdp->control_0);
+	rxd_info->l4_cksum_valid =
+		(u32)VXGE_HW_RING_RXD_L4_CKSUM_CORRECT_GET(rxdp->control_0);
+	rxd_info->l4_cksum =
+		(u32)VXGE_HW_RING_RXD_L4_CKSUM_GET(rxdp->control_0);;
+	rxd_info->frame =
+		(u32)VXGE_HW_RING_RXD_ETHER_ENCAP_GET(rxdp->control_0);
+	rxd_info->proto =
+		(u32)VXGE_HW_RING_RXD_FRAME_PROTO_GET(rxdp->control_0);
+	rxd_info->is_vlan =
+		(u32)VXGE_HW_RING_RXD_IS_VLAN_GET(rxdp->control_0);
+	rxd_info->vlan =
+		(u32)VXGE_HW_RING_RXD_VLAN_TAG_GET(rxdp->control_1);
+	rxd_info->rth_bucket =
+		(u32)VXGE_HW_RING_RXD_RTH_BUCKET_GET(rxdp->control_0);
+	rxd_info->rth_it_hit =
+		(u32)VXGE_HW_RING_RXD_RTH_IT_HIT_GET(rxdp->control_0);
+	rxd_info->rth_spdm_hit =
+		(u32)VXGE_HW_RING_RXD_RTH_SPDM_HIT_GET(rxdp->control_0);
+	rxd_info->rth_hash_type =
+		(u32)VXGE_HW_RING_RXD_RTH_HASH_TYPE_GET(rxdp->control_0);
+	rxd_info->rth_value =
+		(u32)VXGE_HW_RING_RXD_1_RTH_HASH_VAL_GET(rxdp->control_1);
+}
+
+/**
+ * vxge_hw_ring_rxd_private_get - Get driver private per-descriptor data
+ *                      of 1b mode 3b mode ring.
+ * @rxdh: Descriptor handle.
+ *
+ * Returns: private driver	info associated	with the descriptor.
+ * driver requests	per-descriptor space via vxge_hw_ring_attr.
+ *
+ */
+static inline void *vxge_hw_ring_rxd_private_get(void *rxdh)
+{
+	struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh;
+	return (void *)(size_t)rxdp->host_control;
+}
+
+/**
+ * vxge_hw_fifo_txdl_cksum_set_bits - Offload checksum.
+ * @txdlh: Descriptor handle.
+ * @cksum_bits: Specifies which checksums are to be offloaded: IPv4,
+ *              and/or TCP and/or UDP.
+ *
+ * Ask Titan to calculate IPv4 & transport checksums for _this_ transmit
+ * descriptor.
+ * This API is part of the preparation of the transmit descriptor for posting
+ * (via vxge_hw_fifo_txdl_post()). The related "preparation" APIs include
+ * vxge_hw_fifo_txdl_mss_set(), vxge_hw_fifo_txdl_buffer_set_aligned(),
+ * and vxge_hw_fifo_txdl_buffer_set().
+ * All these APIs fill in the fields of the fifo descriptor,
+ * in accordance with the Titan specification.
+ *
+ */
+static inline void vxge_hw_fifo_txdl_cksum_set_bits(void *txdlh, u64 cksum_bits)
+{
+	struct vxge_hw_fifo_txd *txdp = (struct vxge_hw_fifo_txd *)txdlh;
+	txdp->control_1 |= cksum_bits;
+}
+
+/**
+ * vxge_hw_fifo_txdl_mss_set - Set MSS.
+ * @txdlh: Descriptor handle.
+ * @mss: MSS size for _this_ TCP connection. Passed by TCP stack down to the
+ *       driver, which in turn inserts the MSS into the @txdlh.
+ *
+ * This API is part of the preparation of the transmit descriptor for posting
+ * (via vxge_hw_fifo_txdl_post()). The related "preparation" APIs include
+ * vxge_hw_fifo_txdl_buffer_set(), vxge_hw_fifo_txdl_buffer_set_aligned(),
+ * and vxge_hw_fifo_txdl_cksum_set_bits().
+ * All these APIs fill in the fields of the fifo descriptor,
+ * in accordance with the Titan specification.
+ *
+ */
+static inline void vxge_hw_fifo_txdl_mss_set(void *txdlh, int mss)
+{
+	struct vxge_hw_fifo_txd *txdp = (struct vxge_hw_fifo_txd *)txdlh;
+
+	txdp->control_0 |= VXGE_HW_FIFO_TXD_LSO_EN;
+	txdp->control_0 |= VXGE_HW_FIFO_TXD_LSO_MSS(mss);
+}
+
+/**
+ * vxge_hw_fifo_txdl_vlan_set - Set VLAN tag.
+ * @txdlh: Descriptor handle.
+ * @vlan_tag: 16bit VLAN tag.
+ *
+ * Insert VLAN tag into specified transmit descriptor.
+ * The actual insertion of the tag into outgoing frame is done by the hardware.
+ */
+static inline void vxge_hw_fifo_txdl_vlan_set(void *txdlh, u16 vlan_tag)
+{
+	struct vxge_hw_fifo_txd *txdp = (struct vxge_hw_fifo_txd *)txdlh;
+
+	txdp->control_1 |= VXGE_HW_FIFO_TXD_VLAN_ENABLE;
+	txdp->control_1 |= VXGE_HW_FIFO_TXD_VLAN_TAG(vlan_tag);
+}
+
+/**
+ * vxge_hw_fifo_txdl_private_get - Retrieve per-descriptor private data.
+ * @txdlh: Descriptor handle.
+ *
+ * Retrieve per-descriptor private data.
+ * Note that driver requests per-descriptor space via
+ * struct vxge_hw_fifo_attr passed to
+ * vxge_hw_vpath_open().
+ *
+ * Returns: private driver data associated with the descriptor.
+ */
+static inline void *vxge_hw_fifo_txdl_private_get(void *txdlh)
+{
+	struct vxge_hw_fifo_txd *txdp  = (struct vxge_hw_fifo_txd *)txdlh;
+
+	return (void *)(size_t)txdp->host_control;
+}
+
+/**
+ * struct vxge_hw_ring_attr - Ring open "template".
+ * @callback: Ring completion callback. HW invokes the callback when there
+ *            are new completions on that ring. In many implementations
+ *            the @callback executes in the hw interrupt context.
+ * @rxd_init: Ring's descriptor-initialize callback.
+ *            See vxge_hw_ring_rxd_init_f{}.
+ *            If not NULL, HW invokes the callback when opening
+ *            the ring.
+ * @rxd_term: Ring's descriptor-terminate callback. If not NULL,
+ *          HW invokes the callback when closing the corresponding ring.
+ *          See also vxge_hw_ring_rxd_term_f{}.
+ * @userdata: User-defined "context" of _that_ ring. Passed back to the
+ *            user as one of the @callback, @rxd_init, and @rxd_term arguments.
+ * @per_rxd_space: If specified (i.e., greater than zero): extra space
+ *              reserved by HW per each receive descriptor.
+ *              Can be used to store
+ *              and retrieve on completion, information specific
+ *              to the driver.
+ *
+ * Ring open "template". User fills the structure with ring
+ * attributes and passes it to vxge_hw_vpath_open().
+ */
+struct vxge_hw_ring_attr {
+	enum vxge_hw_status (*callback)(
+			struct __vxge_hw_ring *ringh,
+			void *rxdh,
+			u8 t_code,
+			void *userdata);
+
+	enum vxge_hw_status (*rxd_init)(
+			void *rxdh,
+			void *userdata);
+
+	void (*rxd_term)(
+			void *rxdh,
+			enum vxge_hw_rxd_state state,
+			void *userdata);
+
+	void		*userdata;
+	u32		per_rxd_space;
+};
+
+/**
+ * function vxge_hw_fifo_callback_f - FIFO callback.
+ * @vpath_handle: Virtual path whose Fifo "containing" 1 or more completed
+ *             descriptors.
+ * @txdlh: First completed descriptor.
+ * @txdl_priv: Pointer to per txdl space allocated
+ * @t_code: Transfer code, as per Titan User Guide.
+ *          Returned by HW.
+ * @host_control: Opaque 64bit data stored by driver inside the Titan
+ *            descriptor prior to posting the latter on the fifo
+ *            via vxge_hw_fifo_txdl_post(). The @host_control is returned
+ *            as is to the driver with each completed descriptor.
+ * @userdata: Opaque per-fifo data specified at fifo open
+ *            time, via vxge_hw_vpath_open().
+ *
+ * Fifo completion callback (type declaration). A single per-fifo
+ * callback is specified at fifo open time, via
+ * vxge_hw_vpath_open(). Typically gets called as part of the processing
+ * of the Interrupt Service Routine.
+ *
+ * Fifo callback gets called by HW if, and only if, there is at least
+ * one new completion on a given fifo. Upon processing the first @txdlh driver
+ * is _supposed_ to continue consuming completions using:
+ *    - vxge_hw_fifo_txdl_next_completed()
+ *
+ * Note that failure to process new completions in a timely fashion
+ * leads to VXGE_HW_INF_OUT_OF_DESCRIPTORS condition.
+ *
+ * Non-zero @t_code means failure to process transmit descriptor.
+ *
+ * In the "transmit" case the failure could happen, for instance, when the
+ * link is down, in which case Titan completes the descriptor because it
+ * is not able to send the data out.
+ *
+ * For details please refer to Titan User Guide.
+ *
+ * See also: vxge_hw_fifo_txdl_next_completed(), vxge_hw_fifo_txdl_term_f{}.
+ */
+/**
+ * function vxge_hw_fifo_txdl_term_f - Terminate descriptor callback.
+ * @txdlh: First completed descriptor.
+ * @txdl_priv: Pointer to per txdl space allocated
+ * @state: One of the enum vxge_hw_txdl_state{} enumerated states.
+ * @userdata: Per-fifo user data (a.k.a. context) specified at
+ * fifo open time, via vxge_hw_vpath_open().
+ *
+ * Terminate descriptor callback. Unless NULL is specified in the
+ * struct vxge_hw_fifo_attr{} structure passed to vxge_hw_vpath_open()),
+ * HW invokes the callback as part of closing fifo, prior to
+ * de-allocating the ring and associated data structures
+ * (including descriptors).
+ * driver should utilize the callback to (for instance) unmap
+ * and free DMA data buffers associated with the posted (state =
+ * VXGE_HW_TXDL_STATE_POSTED) descriptors,
+ * as well as other relevant cleanup functions.
+ *
+ * See also: struct vxge_hw_fifo_attr{}
+ */
+/**
+ * struct vxge_hw_fifo_attr - Fifo open "template".
+ * @callback: Fifo completion callback. HW invokes the callback when there
+ *            are new completions on that fifo. In many implementations
+ *            the @callback executes in the hw interrupt context.
+ * @txdl_term: Fifo's descriptor-terminate callback. If not NULL,
+ *          HW invokes the callback when closing the corresponding fifo.
+ *          See also vxge_hw_fifo_txdl_term_f{}.
+ * @userdata: User-defined "context" of _that_ fifo. Passed back to the
+ *            user as one of the @callback, and @txdl_term arguments.
+ * @per_txdl_space: If specified (i.e., greater than zero): extra space
+ *              reserved by HW per each transmit descriptor. Can be used to
+ *              store, and retrieve on completion, information specific
+ *              to the driver.
+ *
+ * Fifo open "template". User fills the structure with fifo
+ * attributes and passes it to vxge_hw_vpath_open().
+ */
+struct vxge_hw_fifo_attr {
+
+	enum vxge_hw_status (*callback)(
+			struct __vxge_hw_fifo *fifo_handle,
+			void *txdlh,
+			enum vxge_hw_fifo_tcode t_code,
+			void *userdata,
+			void **skb_ptr);
+
+	void (*txdl_term)(
+			void *txdlh,
+			enum vxge_hw_txdl_state state,
+			void *userdata);
+
+	void		*userdata;
+	u32		per_txdl_space;
+};
+
+/**
+ * struct vxge_hw_vpath_attr - Attributes of virtual path
+ * @vp_id: Identifier of Virtual Path
+ * @ring_attr: Attributes of ring for non-offload receive
+ * @fifo_attr: Attributes of fifo for non-offload transmit
+ *
+ * Attributes of virtual path.  This structure is passed as parameter
+ * to the vxge_hw_vpath_open() routine to set the attributes of ring and fifo.
+ */
+struct vxge_hw_vpath_attr {
+	u32				vp_id;
+	struct vxge_hw_ring_attr	ring_attr;
+	struct vxge_hw_fifo_attr	fifo_attr;
+};
+
+enum vxge_hw_status
+__vxge_hw_blockpool_create(struct __vxge_hw_device *hldev,
+			struct __vxge_hw_blockpool  *blockpool,
+			u32 pool_size,
+			u32 pool_max);
+
+void
+__vxge_hw_blockpool_destroy(struct __vxge_hw_blockpool  *blockpool);
+
+struct __vxge_hw_blockpool_entry *
+__vxge_hw_blockpool_block_allocate(struct __vxge_hw_device *hldev,
+			u32 size);
+
+void
+__vxge_hw_blockpool_block_free(struct __vxge_hw_device *hldev,
+			struct __vxge_hw_blockpool_entry *entry);
+
+void *
+__vxge_hw_blockpool_malloc(struct __vxge_hw_device *hldev,
+			u32 size,
+			struct vxge_hw_mempool_dma *dma_object);
+
+void
+__vxge_hw_blockpool_free(struct __vxge_hw_device *hldev,
+			void *memblock,
+			u32 size,
+			struct vxge_hw_mempool_dma *dma_object);
+
+enum vxge_hw_status
+__vxge_hw_device_fifo_config_check(struct vxge_hw_fifo_config *fifo_config);
+
+enum vxge_hw_status
+__vxge_hw_device_config_check(struct vxge_hw_device_config *new_config);
+
+enum vxge_hw_status
+vxge_hw_mgmt_device_config(struct __vxge_hw_device *devh,
+		struct vxge_hw_device_config	*dev_config, int size);
+
+enum vxge_hw_status __devinit vxge_hw_device_hw_info_get(
+	void __iomem *bar0,
+	struct vxge_hw_device_hw_info *hw_info);
+
+enum vxge_hw_status
+__vxge_hw_vpath_fw_ver_get(
+	u32	vp_id,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg,
+	struct vxge_hw_device_hw_info *hw_info);
+
+enum vxge_hw_status
+__vxge_hw_vpath_card_info_get(
+	u32 vp_id,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg,
+	struct vxge_hw_device_hw_info *hw_info);
+
+enum vxge_hw_status __devinit vxge_hw_device_config_default_get(
+	struct vxge_hw_device_config *device_config);
+
+/**
+ * vxge_hw_device_link_state_get - Get link state.
+ * @devh: HW device handle.
+ *
+ * Get link state.
+ * Returns: link state.
+ */
+static inline
+enum vxge_hw_device_link_state vxge_hw_device_link_state_get(
+	struct __vxge_hw_device *devh)
+{
+	return devh->link_state;
+}
+
+void vxge_hw_device_terminate(struct __vxge_hw_device *devh);
+
+const u8 *
+vxge_hw_device_serial_number_get(struct __vxge_hw_device *devh);
+
+u16 vxge_hw_device_link_width_get(struct __vxge_hw_device *devh);
+
+const u8 *
+vxge_hw_device_product_name_get(struct __vxge_hw_device *devh);
+
+enum vxge_hw_status __devinit vxge_hw_device_initialize(
+	struct __vxge_hw_device **devh,
+	struct vxge_hw_device_attr *attr,
+	struct vxge_hw_device_config *device_config);
+
+enum vxge_hw_status vxge_hw_device_getpause_data(
+	 struct __vxge_hw_device *devh,
+	 u32 port,
+	 u32 *tx,
+	 u32 *rx);
+
+enum vxge_hw_status vxge_hw_device_setpause_data(
+	struct __vxge_hw_device *devh,
+	u32 port,
+	u32 tx,
+	u32 rx);
+
+static inline void *vxge_os_dma_malloc(struct pci_dev *pdev,
+			unsigned long size,
+			struct pci_dev **p_dmah,
+			struct pci_dev **p_dma_acch)
+{
+	gfp_t flags;
+	void *vaddr;
+	unsigned long misaligned = 0;
+	*p_dma_acch = *p_dmah = NULL;
+
+	if (in_interrupt())
+		flags = GFP_ATOMIC | GFP_DMA;
+	else
+		flags = GFP_KERNEL | GFP_DMA;
+
+	size += VXGE_CACHE_LINE_SIZE;
+
+	vaddr = kmalloc((size), flags);
+	if (vaddr == NULL)
+		return vaddr;
+	misaligned = (unsigned long)VXGE_ALIGN(*((u64 *)&vaddr),
+				VXGE_CACHE_LINE_SIZE);
+	*(unsigned long *)p_dma_acch = misaligned;
+	vaddr = (void *)((u8 *)vaddr + misaligned);
+	return vaddr;
+}
+
+extern void vxge_hw_blockpool_block_add(
+			struct __vxge_hw_device *devh,
+			void *block_addr,
+			u32 length,
+			struct pci_dev *dma_h,
+			struct pci_dev *acc_handle);
+
+static inline void vxge_os_dma_malloc_async(struct pci_dev *pdev, void *devh,
+					unsigned long size)
+{
+	gfp_t flags;
+	void *vaddr;
+
+	if (in_interrupt())
+		flags = GFP_ATOMIC | GFP_DMA;
+	else
+		flags = GFP_KERNEL | GFP_DMA;
+
+	vaddr = kmalloc((size), flags);
+
+	vxge_hw_blockpool_block_add(devh, vaddr, size, pdev, pdev);
+}
+
+static inline void vxge_os_dma_free(struct pci_dev *pdev, const void *vaddr,
+			struct pci_dev **p_dma_acch)
+{
+	unsigned long misaligned = *(unsigned long *)p_dma_acch;
+	u8 *tmp = (u8 *)vaddr;
+	tmp -= misaligned;
+	kfree((void *)tmp);
+}
+
+/*
+ * __vxge_hw_mempool_item_priv - will return pointer on per item private space
+ */
+static inline void*
+__vxge_hw_mempool_item_priv(
+	struct vxge_hw_mempool *mempool,
+	u32 memblock_idx,
+	void *item,
+	u32 *memblock_item_idx)
+{
+	ptrdiff_t offset;
+	void *memblock = mempool->memblocks_arr[memblock_idx];
+
+
+	offset = (u32)((u8 *)item - (u8 *)memblock);
+	vxge_assert(offset >= 0 && (u32)offset < mempool->memblock_size);
+
+	(*memblock_item_idx) = (u32) offset / mempool->item_size;
+	vxge_assert((*memblock_item_idx) < mempool->items_per_memblock);
+
+	return (u8 *)mempool->memblocks_priv_arr[memblock_idx] +
+			    (*memblock_item_idx) * mempool->items_priv_size;
+}
+
+enum vxge_hw_status
+__vxge_hw_mempool_grow(
+	struct vxge_hw_mempool *mempool,
+	u32 num_allocate,
+	u32 *num_allocated);
+
+struct vxge_hw_mempool*
+__vxge_hw_mempool_create(
+	struct __vxge_hw_device *devh,
+	u32 memblock_size,
+	u32 item_size,
+	u32 private_size,
+	u32 items_initial,
+	u32 items_max,
+	struct vxge_hw_mempool_cbs *mp_callback,
+	void *userdata);
+
+struct __vxge_hw_channel*
+__vxge_hw_channel_allocate(struct __vxge_hw_vpath_handle *vph,
+			enum __vxge_hw_channel_type type, u32 length,
+			u32 per_dtr_space, void *userdata);
+
+void
+__vxge_hw_channel_free(
+	struct __vxge_hw_channel *channel);
+
+enum vxge_hw_status
+__vxge_hw_channel_initialize(
+	struct __vxge_hw_channel *channel);
+
+enum vxge_hw_status
+__vxge_hw_channel_reset(
+	struct __vxge_hw_channel *channel);
+
+/*
+ * __vxge_hw_fifo_txdl_priv - Return the max fragments allocated
+ * for the fifo.
+ * @fifo: Fifo
+ * @txdp: Poniter to a TxD
+ */
+static inline struct __vxge_hw_fifo_txdl_priv *
+__vxge_hw_fifo_txdl_priv(
+	struct __vxge_hw_fifo *fifo,
+	struct vxge_hw_fifo_txd *txdp)
+{
+	return (struct __vxge_hw_fifo_txdl_priv *)
+			(((char *)((ulong)txdp->host_control)) +
+				fifo->per_txdl_space);
+}
+
+enum vxge_hw_status vxge_hw_vpath_open(
+	struct __vxge_hw_device *devh,
+	struct vxge_hw_vpath_attr *attr,
+	struct __vxge_hw_vpath_handle **vpath_handle);
+
+enum vxge_hw_status
+__vxge_hw_device_vpath_reset_in_prog_check(u64 __iomem *vpath_rst_in_prog);
+
+enum vxge_hw_status vxge_hw_vpath_close(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status
+vxge_hw_vpath_reset(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status
+vxge_hw_vpath_recover_from_reset(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+void
+vxge_hw_vpath_enable(struct __vxge_hw_vpath_handle *vp);
+
+enum vxge_hw_status
+vxge_hw_vpath_check_leak(struct __vxge_hw_ring *ringh);
+
+enum vxge_hw_status vxge_hw_vpath_mtu_set(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u32 new_mtu);
+
+enum vxge_hw_status vxge_hw_vpath_stats_enable(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status
+__vxge_hw_vpath_stats_access(
+	struct __vxge_hw_virtualpath	*vpath,
+	u32			operation,
+	u32			offset,
+	u64			*stat);
+
+enum vxge_hw_status
+__vxge_hw_vpath_xmac_tx_stats_get(
+	struct __vxge_hw_virtualpath	*vpath,
+	struct vxge_hw_xmac_vpath_tx_stats *vpath_tx_stats);
+
+enum vxge_hw_status
+__vxge_hw_vpath_xmac_rx_stats_get(
+	struct __vxge_hw_virtualpath	*vpath,
+	struct vxge_hw_xmac_vpath_rx_stats *vpath_rx_stats);
+
+enum vxge_hw_status
+__vxge_hw_vpath_stats_get(
+	struct __vxge_hw_virtualpath *vpath,
+	struct vxge_hw_vpath_stats_hw_info *hw_stats);
+
+void
+vxge_hw_vpath_rx_doorbell_init(struct __vxge_hw_vpath_handle *vp);
+
+enum vxge_hw_status
+__vxge_hw_device_vpath_config_check(struct vxge_hw_vp_config *vp_config);
+
+void
+__vxge_hw_device_pci_e_init(struct __vxge_hw_device *hldev);
+
+enum vxge_hw_status
+__vxge_hw_legacy_swapper_set(struct vxge_hw_legacy_reg __iomem *legacy_reg);
+
+enum vxge_hw_status
+__vxge_hw_vpath_swapper_set(struct vxge_hw_vpath_reg __iomem *vpath_reg);
+
+enum vxge_hw_status
+__vxge_hw_kdfc_swapper_set(struct vxge_hw_legacy_reg __iomem *legacy_reg,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg);
+
+enum vxge_hw_status
+__vxge_hw_device_register_poll(
+	void __iomem	*reg,
+	u64 mask, u32 max_millis);
+
+#ifndef readq
+static inline u64 readq(void __iomem *addr)
+{
+	u64 ret = 0;
+	ret = readl(addr + 4);
+	ret <<= 32;
+	ret |= readl(addr);
+
+	return ret;
+}
+#endif
+
+#ifndef writeq
+static inline void writeq(u64 val, void __iomem *addr)
+{
+	writel((u32) (val), addr);
+	writel((u32) (val >> 32), (addr + 4));
+}
+#endif
+
+static inline void __vxge_hw_pio_mem_write32_upper(u32 val, void __iomem *addr)
+{
+	writel(val, addr + 4);
+}
+
+static inline void __vxge_hw_pio_mem_write32_lower(u32 val, void __iomem *addr)
+{
+	writel(val, addr);
+}
+
+static inline enum vxge_hw_status
+__vxge_hw_pio_mem_write64(u64 val64, void __iomem *addr,
+			  u64 mask, u32 max_millis)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	__vxge_hw_pio_mem_write32_lower((u32)vxge_bVALn(val64, 32, 32), addr);
+	wmb();
+	__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(val64, 0, 32), addr);
+	wmb();
+
+	status = __vxge_hw_device_register_poll(addr, mask, max_millis);
+	return status;
+}
+
+struct vxge_hw_toc_reg __iomem *
+__vxge_hw_device_toc_get(void __iomem *bar0);
+
+enum vxge_hw_status
+__vxge_hw_device_reg_addr_get(struct __vxge_hw_device *hldev);
+
+void
+__vxge_hw_device_id_get(struct __vxge_hw_device *hldev);
+
+void
+__vxge_hw_device_host_info_get(struct __vxge_hw_device *hldev);
+
+enum vxge_hw_status
+vxge_hw_device_flick_link_led(struct __vxge_hw_device *devh, u64 on_off);
+
+enum vxge_hw_status
+__vxge_hw_device_initialize(struct __vxge_hw_device *hldev);
+
+enum vxge_hw_status
+__vxge_hw_vpath_pci_read(
+	struct __vxge_hw_virtualpath	*vpath,
+	u32			phy_func_0,
+	u32			offset,
+	u32			*val);
+
+enum vxge_hw_status
+__vxge_hw_vpath_addr_get(
+	u32 vp_id,
+	struct vxge_hw_vpath_reg __iomem *vpath_reg,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN]);
+
+u32
+__vxge_hw_vpath_func_id_get(
+	u32 vp_id, struct vxge_hw_vpmgmt_reg __iomem *vpmgmt_reg);
+
+enum vxge_hw_status
+__vxge_hw_vpath_reset_check(struct __vxge_hw_virtualpath *vpath);
+
+/**
+ * vxge_debug
+ * @level: level of debug verbosity.
+ * @mask: mask for the debug
+ * @buf: Circular buffer for tracing
+ * @fmt: printf like format string
+ *
+ * Provides logging facilities. Can be customized on per-module
+ * basis or/and with debug levels. Input parameters, except
+ * module and level, are the same as posix printf. This function
+ * may be compiled out if DEBUG macro was never defined.
+ * See also: enum vxge_debug_level{}.
+ */
+
+#define vxge_trace_aux(level, mask, fmt, ...) \
+{\
+		vxge_os_vaprintf(level, mask, fmt, __VA_ARGS__);\
+}
+
+#define vxge_debug(module, level, mask, fmt, ...) { \
+if ((level >= VXGE_TRACE && ((module & VXGE_DEBUG_TRACE_MASK) == module)) || \
+	(level >= VXGE_ERR && ((module & VXGE_DEBUG_ERR_MASK) == module))) {\
+	if ((mask & VXGE_DEBUG_MASK) == mask)\
+		vxge_trace_aux(level, mask, fmt, __VA_ARGS__); \
+} \
+}
+
+#if (VXGE_COMPONENT_LL & VXGE_DEBUG_MODULE_MASK)
+#define vxge_debug_ll(level, mask, fmt, ...) \
+{\
+	vxge_debug(VXGE_COMPONENT_LL, level, mask, fmt, __VA_ARGS__);\
+}
+
+#else
+#define vxge_debug_ll(level, mask, fmt, ...)
+#endif
+
+enum vxge_hw_status vxge_hw_vpath_rts_rth_itable_set(
+			struct __vxge_hw_vpath_handle **vpath_handles,
+			u32 vpath_count,
+			u8 *mtable,
+			u8 *itable,
+			u32 itable_size);
+
+enum vxge_hw_status vxge_hw_vpath_rts_rth_set(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	enum vxge_hw_rth_algoritms algorithm,
+	struct vxge_hw_rth_hash_types *hash_type,
+	u16 bucket_size);
+
+#endif
diff --git a/drivers/net/vxge/vxge-ethtool.c b/drivers/net/vxge/vxge-ethtool.c
new file mode 100644
index 000000000000..c6736b972635
--- /dev/null
+++ b/drivers/net/vxge/vxge-ethtool.c
@@ -0,0 +1,1148 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-ethtool.c: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *                 Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#include<linux/ethtool.h>
+#include <linux/pci.h>
+#include <linux/etherdevice.h>
+
+#include "vxge-ethtool.h"
+
+/**
+ * vxge_ethtool_sset - Sets different link parameters.
+ * @dev: device pointer.
+ * @info: pointer to the structure with parameters given by ethtool to set
+ * link information.
+ *
+ * The function sets different link parameters provided by the user onto
+ * the NIC.
+ * Return value:
+ * 0 on success.
+ */
+
+static int vxge_ethtool_sset(struct net_device *dev, struct ethtool_cmd *info)
+{
+	/* We currently only support 10Gb/FULL */
+	if ((info->autoneg == AUTONEG_ENABLE) ||
+	    (info->speed != SPEED_10000) || (info->duplex != DUPLEX_FULL))
+		return -EINVAL;
+
+	return 0;
+}
+
+/**
+ * vxge_ethtool_gset - Return link specific information.
+ * @dev: device pointer.
+ * @info: pointer to the structure with parameters given by ethtool
+ * to return link information.
+ *
+ * Returns link specific information like speed, duplex etc.. to ethtool.
+ * Return value :
+ * return 0 on success.
+ */
+static int vxge_ethtool_gset(struct net_device *dev, struct ethtool_cmd *info)
+{
+	info->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE);
+	info->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE);
+	info->port = PORT_FIBRE;
+
+	info->transceiver = XCVR_EXTERNAL;
+
+	if (netif_carrier_ok(dev)) {
+		info->speed = SPEED_10000;
+		info->duplex = DUPLEX_FULL;
+	} else {
+		info->speed = -1;
+		info->duplex = -1;
+	}
+
+	info->autoneg = AUTONEG_DISABLE;
+	return 0;
+}
+
+/**
+ * vxge_ethtool_gdrvinfo - Returns driver specific information.
+ * @dev: device pointer.
+ * @info: pointer to the structure with parameters given by ethtool to
+ * return driver information.
+ *
+ * Returns driver specefic information like name, version etc.. to ethtool.
+ */
+static void vxge_ethtool_gdrvinfo(struct net_device *dev,
+			struct ethtool_drvinfo *info)
+{
+	struct vxgedev *vdev;
+	vdev = (struct vxgedev *)netdev_priv(dev);
+	strlcpy(info->driver, VXGE_DRIVER_NAME, sizeof(VXGE_DRIVER_NAME));
+	strlcpy(info->version, DRV_VERSION, sizeof(DRV_VERSION));
+	strlcpy(info->fw_version, vdev->fw_version, VXGE_HW_FW_STRLEN);
+	strlcpy(info->bus_info, pci_name(vdev->pdev), sizeof(info->bus_info));
+	info->regdump_len = sizeof(struct vxge_hw_vpath_reg)
+				* vdev->no_of_vpath;
+
+	info->n_stats = STAT_LEN;
+}
+
+/**
+ * vxge_ethtool_gregs - dumps the entire space of Titan into the buffer.
+ * @dev: device pointer.
+ * @regs: pointer to the structure with parameters given by ethtool for
+ * dumping the registers.
+ * @reg_space: The input argumnet into which all the registers are dumped.
+ *
+ * Dumps the vpath register space of Titan NIC into the user given
+ * buffer area.
+ */
+static void vxge_ethtool_gregs(struct net_device *dev,
+			struct ethtool_regs *regs, void *space)
+{
+	int index, offset;
+	enum vxge_hw_status status;
+	u64 reg;
+	u8 *reg_space = (u8 *) space;
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	struct __vxge_hw_device  *hldev = (struct __vxge_hw_device *)
+					pci_get_drvdata(vdev->pdev);
+
+	regs->len = sizeof(struct vxge_hw_vpath_reg) * vdev->no_of_vpath;
+	regs->version = vdev->pdev->subsystem_device;
+	for (index = 0; index < vdev->no_of_vpath; index++) {
+		for (offset = 0; offset < sizeof(struct vxge_hw_vpath_reg);
+				offset += 8) {
+			status = vxge_hw_mgmt_reg_read(hldev,
+					vxge_hw_mgmt_reg_type_vpath,
+					vdev->vpaths[index].device_id,
+					offset, &reg);
+			if (status != VXGE_HW_OK) {
+				vxge_debug_init(VXGE_ERR,
+					"%s:%d Getting reg dump Failed",
+						__func__, __LINE__);
+				return;
+			}
+
+			memcpy((reg_space + offset), &reg, 8);
+		}
+	}
+}
+
+/**
+ * vxge_ethtool_idnic - To physically identify the nic on the system.
+ * @dev : device pointer.
+ * @id : pointer to the structure with identification parameters given by
+ * ethtool.
+ *
+ * Used to physically identify the NIC on the system.
+ * The Link LED will blink for a time specified by the user.
+ * Return value:
+ * 0 on success
+ */
+static int vxge_ethtool_idnic(struct net_device *dev, u32 data)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	struct __vxge_hw_device  *hldev = (struct __vxge_hw_device  *)
+			pci_get_drvdata(vdev->pdev);
+
+	vxge_hw_device_flick_link_led(hldev, VXGE_FLICKER_ON);
+	msleep_interruptible(data ? (data * HZ) : VXGE_MAX_FLICKER_TIME);
+	vxge_hw_device_flick_link_led(hldev, VXGE_FLICKER_OFF);
+
+	return 0;
+}
+
+/**
+ * vxge_ethtool_getpause_data - Pause frame frame generation and reception.
+ * @dev : device pointer.
+ * @ep : pointer to the structure with pause parameters given by ethtool.
+ * Description:
+ * Returns the Pause frame generation and reception capability of the NIC.
+ * Return value:
+ *  void
+ */
+static void vxge_ethtool_getpause_data(struct net_device *dev,
+					struct ethtool_pauseparam *ep)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	struct __vxge_hw_device  *hldev = (struct __vxge_hw_device  *)
+			pci_get_drvdata(vdev->pdev);
+
+	vxge_hw_device_getpause_data(hldev, 0, &ep->tx_pause, &ep->rx_pause);
+}
+
+/**
+ * vxge_ethtool_setpause_data -  set/reset pause frame generation.
+ * @dev : device pointer.
+ * @ep : pointer to the structure with pause parameters given by ethtool.
+ * Description:
+ * It can be used to set or reset Pause frame generation or reception
+ * support of the NIC.
+ * Return value:
+ * int, returns 0 on Success
+ */
+static int vxge_ethtool_setpause_data(struct net_device *dev,
+					struct ethtool_pauseparam *ep)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	struct __vxge_hw_device  *hldev = (struct __vxge_hw_device  *)
+			pci_get_drvdata(vdev->pdev);
+
+	vxge_hw_device_setpause_data(hldev, 0, ep->tx_pause, ep->rx_pause);
+
+	vdev->config.tx_pause_enable = ep->tx_pause;
+	vdev->config.rx_pause_enable = ep->rx_pause;
+
+	return 0;
+}
+
+static void vxge_get_ethtool_stats(struct net_device *dev,
+				   struct ethtool_stats *estats, u64 *tmp_stats)
+{
+	int j, k;
+	enum vxge_hw_status status;
+	enum vxge_hw_status swstatus;
+	struct vxge_vpath *vpath = NULL;
+
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	struct __vxge_hw_device  *hldev = vdev->devh;
+	struct vxge_hw_xmac_stats *xmac_stats;
+	struct vxge_hw_device_stats_sw_info *sw_stats;
+	struct vxge_hw_device_stats_hw_info *hw_stats;
+
+	u64 *ptr = tmp_stats;
+
+	memset(tmp_stats, 0,
+		vxge_ethtool_get_sset_count(dev, ETH_SS_STATS) * sizeof(u64));
+
+	xmac_stats = kzalloc(sizeof(struct vxge_hw_xmac_stats), GFP_KERNEL);
+	if (xmac_stats == NULL) {
+		vxge_debug_init(VXGE_ERR,
+			"%s : %d Memory Allocation failed for xmac_stats",
+				 __func__, __LINE__);
+		return;
+	}
+
+	sw_stats = kzalloc(sizeof(struct vxge_hw_device_stats_sw_info),
+				GFP_KERNEL);
+	if (sw_stats == NULL) {
+		kfree(xmac_stats);
+		vxge_debug_init(VXGE_ERR,
+			"%s : %d Memory Allocation failed for sw_stats",
+			__func__, __LINE__);
+		return;
+	}
+
+	hw_stats = kzalloc(sizeof(struct vxge_hw_device_stats_hw_info),
+				GFP_KERNEL);
+	if (hw_stats == NULL) {
+		kfree(xmac_stats);
+		kfree(sw_stats);
+		vxge_debug_init(VXGE_ERR,
+			"%s : %d Memory Allocation failed for hw_stats",
+			__func__, __LINE__);
+		return;
+	}
+
+	*ptr++ = 0;
+	status = vxge_hw_device_xmac_stats_get(hldev, xmac_stats);
+	if (status != VXGE_HW_OK) {
+		if (status != VXGE_HW_ERR_PRIVILAGED_OPEARATION) {
+			vxge_debug_init(VXGE_ERR,
+				"%s : %d Failure in getting xmac stats",
+				__func__, __LINE__);
+		}
+	}
+	swstatus = vxge_hw_driver_stats_get(hldev, sw_stats);
+	if (swstatus != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"%s : %d Failure in getting sw stats",
+			__func__, __LINE__);
+	}
+
+	status = vxge_hw_device_stats_get(hldev, hw_stats);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"%s : %d hw_stats_get error", __func__, __LINE__);
+	}
+
+	for (k = 0; k < vdev->no_of_vpath; k++) {
+		struct vxge_hw_vpath_stats_hw_info *vpath_info;
+
+		vpath = &vdev->vpaths[k];
+		j = vpath->device_id;
+		vpath_info = hw_stats->vpath_info[j];
+		if (!vpath_info) {
+			memset(ptr, 0, (VXGE_HW_VPATH_TX_STATS_LEN +
+				VXGE_HW_VPATH_RX_STATS_LEN) * sizeof(u64));
+			ptr += (VXGE_HW_VPATH_TX_STATS_LEN +
+				VXGE_HW_VPATH_RX_STATS_LEN);
+			continue;
+		}
+
+		*ptr++ = vpath_info->tx_stats.tx_ttl_eth_frms;
+		*ptr++ = vpath_info->tx_stats.tx_ttl_eth_octets;
+		*ptr++ = vpath_info->tx_stats.tx_data_octets;
+		*ptr++ = vpath_info->tx_stats.tx_mcast_frms;
+		*ptr++ = vpath_info->tx_stats.tx_bcast_frms;
+		*ptr++ = vpath_info->tx_stats.tx_ucast_frms;
+		*ptr++ = vpath_info->tx_stats.tx_tagged_frms;
+		*ptr++ = vpath_info->tx_stats.tx_vld_ip;
+		*ptr++ = vpath_info->tx_stats.tx_vld_ip_octets;
+		*ptr++ = vpath_info->tx_stats.tx_icmp;
+		*ptr++ = vpath_info->tx_stats.tx_tcp;
+		*ptr++ = vpath_info->tx_stats.tx_rst_tcp;
+		*ptr++ = vpath_info->tx_stats.tx_udp;
+		*ptr++ = vpath_info->tx_stats.tx_unknown_protocol;
+		*ptr++ = vpath_info->tx_stats.tx_lost_ip;
+		*ptr++ = vpath_info->tx_stats.tx_parse_error;
+		*ptr++ = vpath_info->tx_stats.tx_tcp_offload;
+		*ptr++ = vpath_info->tx_stats.tx_retx_tcp_offload;
+		*ptr++ = vpath_info->tx_stats.tx_lost_ip_offload;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_eth_frms;
+		*ptr++ = vpath_info->rx_stats.rx_vld_frms;
+		*ptr++ = vpath_info->rx_stats.rx_offload_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_eth_octets;
+		*ptr++ = vpath_info->rx_stats.rx_data_octets;
+		*ptr++ = vpath_info->rx_stats.rx_offload_octets;
+		*ptr++ = vpath_info->rx_stats.rx_vld_mcast_frms;
+		*ptr++ = vpath_info->rx_stats.rx_vld_bcast_frms;
+		*ptr++ = vpath_info->rx_stats.rx_accepted_ucast_frms;
+		*ptr++ = vpath_info->rx_stats.rx_accepted_nucast_frms;
+		*ptr++ = vpath_info->rx_stats.rx_tagged_frms;
+		*ptr++ = vpath_info->rx_stats.rx_long_frms;
+		*ptr++ = vpath_info->rx_stats.rx_usized_frms;
+		*ptr++ = vpath_info->rx_stats.rx_osized_frms;
+		*ptr++ = vpath_info->rx_stats.rx_frag_frms;
+		*ptr++ = vpath_info->rx_stats.rx_jabber_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_64_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_65_127_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_128_255_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_256_511_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_512_1023_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_1024_1518_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_1519_4095_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_4096_8191_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_8192_max_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ttl_gt_max_frms;
+		*ptr++ = vpath_info->rx_stats.rx_ip;
+		*ptr++ = vpath_info->rx_stats.rx_accepted_ip;
+		*ptr++ = vpath_info->rx_stats.rx_ip_octets;
+		*ptr++ = vpath_info->rx_stats.rx_err_ip;
+		*ptr++ = vpath_info->rx_stats.rx_icmp;
+		*ptr++ = vpath_info->rx_stats.rx_tcp;
+		*ptr++ = vpath_info->rx_stats.rx_udp;
+		*ptr++ = vpath_info->rx_stats.rx_err_tcp;
+		*ptr++ = vpath_info->rx_stats.rx_lost_frms;
+		*ptr++ = vpath_info->rx_stats.rx_lost_ip;
+		*ptr++ = vpath_info->rx_stats.rx_lost_ip_offload;
+		*ptr++ = vpath_info->rx_stats.rx_various_discard;
+		*ptr++ = vpath_info->rx_stats.rx_sleep_discard;
+		*ptr++ = vpath_info->rx_stats.rx_red_discard;
+		*ptr++ = vpath_info->rx_stats.rx_queue_full_discard;
+		*ptr++ = vpath_info->rx_stats.rx_mpa_ok_frms;
+	}
+	*ptr++ = 0;
+	for (k = 0; k < vdev->max_config_port; k++) {
+		*ptr++ = xmac_stats->aggr_stats[k].tx_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].tx_data_octets;
+		*ptr++ = xmac_stats->aggr_stats[k].tx_mcast_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].tx_bcast_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].tx_discarded_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].tx_errored_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].rx_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].rx_data_octets;
+		*ptr++ = xmac_stats->aggr_stats[k].rx_mcast_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].rx_bcast_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].rx_discarded_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].rx_errored_frms;
+		*ptr++ = xmac_stats->aggr_stats[k].rx_unknown_slow_proto_frms;
+	}
+	*ptr++ = 0;
+	for (k = 0; k < vdev->max_config_port; k++) {
+		*ptr++ = xmac_stats->port_stats[k].tx_ttl_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_ttl_octets;
+		*ptr++ = xmac_stats->port_stats[k].tx_data_octets;
+		*ptr++ = xmac_stats->port_stats[k].tx_mcast_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_bcast_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_ucast_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_tagged_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_vld_ip;
+		*ptr++ = xmac_stats->port_stats[k].tx_vld_ip_octets;
+		*ptr++ = xmac_stats->port_stats[k].tx_icmp;
+		*ptr++ = xmac_stats->port_stats[k].tx_tcp;
+		*ptr++ = xmac_stats->port_stats[k].tx_rst_tcp;
+		*ptr++ = xmac_stats->port_stats[k].tx_udp;
+		*ptr++ = xmac_stats->port_stats[k].tx_parse_error;
+		*ptr++ = xmac_stats->port_stats[k].tx_unknown_protocol;
+		*ptr++ = xmac_stats->port_stats[k].tx_pause_ctrl_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_marker_pdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_lacpdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_drop_ip;
+		*ptr++ = xmac_stats->port_stats[k].tx_marker_resp_pdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_xgmii_char2_match;
+		*ptr++ = xmac_stats->port_stats[k].tx_xgmii_char1_match;
+		*ptr++ = xmac_stats->port_stats[k].tx_xgmii_column2_match;
+		*ptr++ = xmac_stats->port_stats[k].tx_xgmii_column1_match;
+		*ptr++ = xmac_stats->port_stats[k].tx_any_err_frms;
+		*ptr++ = xmac_stats->port_stats[k].tx_drop_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_vld_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_offload_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_octets;
+		*ptr++ = xmac_stats->port_stats[k].rx_data_octets;
+		*ptr++ = xmac_stats->port_stats[k].rx_offload_octets;
+		*ptr++ = xmac_stats->port_stats[k].rx_vld_mcast_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_vld_bcast_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_accepted_ucast_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_accepted_nucast_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_tagged_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_long_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_usized_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_osized_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_frag_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_jabber_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_64_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_65_127_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_128_255_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_256_511_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_512_1023_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_1024_1518_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_1519_4095_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_4096_8191_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_8192_max_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ttl_gt_max_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_ip;
+		*ptr++ = xmac_stats->port_stats[k].rx_accepted_ip;
+		*ptr++ = xmac_stats->port_stats[k].rx_ip_octets;
+		*ptr++ = xmac_stats->port_stats[k].rx_err_ip;
+		*ptr++ = xmac_stats->port_stats[k].rx_icmp;
+		*ptr++ = xmac_stats->port_stats[k].rx_tcp;
+		*ptr++ = xmac_stats->port_stats[k].rx_udp;
+		*ptr++ = xmac_stats->port_stats[k].rx_err_tcp;
+		*ptr++ = xmac_stats->port_stats[k].rx_pause_count;
+		*ptr++ = xmac_stats->port_stats[k].rx_pause_ctrl_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_unsup_ctrl_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_fcs_err_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_in_rng_len_err_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_out_rng_len_err_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_drop_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_discarded_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_drop_ip;
+		*ptr++ = xmac_stats->port_stats[k].rx_drop_udp;
+		*ptr++ = xmac_stats->port_stats[k].rx_marker_pdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_lacpdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_unknown_pdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_marker_resp_pdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_fcs_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_illegal_pdu_frms;
+		*ptr++ = xmac_stats->port_stats[k].rx_switch_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_len_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_rpa_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_l2_mgmt_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_rts_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_trash_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_buff_full_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_red_discard;
+		*ptr++ = xmac_stats->port_stats[k].rx_xgmii_ctrl_err_cnt;
+		*ptr++ = xmac_stats->port_stats[k].rx_xgmii_data_err_cnt;
+		*ptr++ = xmac_stats->port_stats[k].rx_xgmii_char1_match;
+		*ptr++ = xmac_stats->port_stats[k].rx_xgmii_err_sym;
+		*ptr++ = xmac_stats->port_stats[k].rx_xgmii_column1_match;
+		*ptr++ = xmac_stats->port_stats[k].rx_xgmii_char2_match;
+		*ptr++ = xmac_stats->port_stats[k].rx_local_fault;
+		*ptr++ = xmac_stats->port_stats[k].rx_xgmii_column2_match;
+		*ptr++ = xmac_stats->port_stats[k].rx_jettison;
+		*ptr++ = xmac_stats->port_stats[k].rx_remote_fault;
+	}
+
+	*ptr++ = 0;
+	for (k = 0; k < vdev->no_of_vpath; k++) {
+		struct vxge_hw_vpath_stats_sw_info *vpath_info;
+
+		vpath = &vdev->vpaths[k];
+		j = vpath->device_id;
+		vpath_info = (struct vxge_hw_vpath_stats_sw_info *)
+				&sw_stats->vpath_info[j];
+		*ptr++ = vpath_info->soft_reset_cnt;
+		*ptr++ = vpath_info->error_stats.unknown_alarms;
+		*ptr++ = vpath_info->error_stats.network_sustained_fault;
+		*ptr++ = vpath_info->error_stats.network_sustained_ok;
+		*ptr++ = vpath_info->error_stats.kdfcctl_fifo0_overwrite;
+		*ptr++ = vpath_info->error_stats.kdfcctl_fifo0_poison;
+		*ptr++ = vpath_info->error_stats.kdfcctl_fifo0_dma_error;
+		*ptr++ = vpath_info->error_stats.dblgen_fifo0_overflow;
+		*ptr++ = vpath_info->error_stats.statsb_pif_chain_error;
+		*ptr++ = vpath_info->error_stats.statsb_drop_timeout;
+		*ptr++ = vpath_info->error_stats.target_illegal_access;
+		*ptr++ = vpath_info->error_stats.ini_serr_det;
+		*ptr++ = vpath_info->error_stats.prc_ring_bumps;
+		*ptr++ = vpath_info->error_stats.prc_rxdcm_sc_err;
+		*ptr++ = vpath_info->error_stats.prc_rxdcm_sc_abort;
+		*ptr++ = vpath_info->error_stats.prc_quanta_size_err;
+		*ptr++ = vpath_info->ring_stats.common_stats.full_cnt;
+		*ptr++ = vpath_info->ring_stats.common_stats.usage_cnt;
+		*ptr++ = vpath_info->ring_stats.common_stats.usage_max;
+		*ptr++ = vpath_info->ring_stats.common_stats.
+					reserve_free_swaps_cnt;
+		*ptr++ = vpath_info->ring_stats.common_stats.total_compl_cnt;
+		for (j = 0; j < VXGE_HW_DTR_MAX_T_CODE; j++)
+			*ptr++ = vpath_info->ring_stats.rxd_t_code_err_cnt[j];
+		*ptr++ = vpath_info->fifo_stats.common_stats.full_cnt;
+		*ptr++ = vpath_info->fifo_stats.common_stats.usage_cnt;
+		*ptr++ = vpath_info->fifo_stats.common_stats.usage_max;
+		*ptr++ = vpath_info->fifo_stats.common_stats.
+						reserve_free_swaps_cnt;
+		*ptr++ = vpath_info->fifo_stats.common_stats.total_compl_cnt;
+		*ptr++ = vpath_info->fifo_stats.total_posts;
+		*ptr++ = vpath_info->fifo_stats.total_buffers;
+		for (j = 0; j < VXGE_HW_DTR_MAX_T_CODE; j++)
+			*ptr++ = vpath_info->fifo_stats.txd_t_code_err_cnt[j];
+	}
+
+	*ptr++ = 0;
+	for (k = 0; k < vdev->no_of_vpath; k++) {
+		struct vxge_hw_vpath_stats_hw_info *vpath_info;
+		vpath = &vdev->vpaths[k];
+		j = vpath->device_id;
+		vpath_info = hw_stats->vpath_info[j];
+		if (!vpath_info) {
+			memset(ptr, 0, VXGE_HW_VPATH_STATS_LEN * sizeof(u64));
+			ptr += VXGE_HW_VPATH_STATS_LEN;
+			continue;
+		}
+		*ptr++ = vpath_info->ini_num_mwr_sent;
+		*ptr++ = vpath_info->ini_num_mrd_sent;
+		*ptr++ = vpath_info->ini_num_cpl_rcvd;
+		*ptr++ = vpath_info->ini_num_mwr_byte_sent;
+		*ptr++ = vpath_info->ini_num_cpl_byte_rcvd;
+		*ptr++ = vpath_info->wrcrdtarb_xoff;
+		*ptr++ = vpath_info->rdcrdtarb_xoff;
+		*ptr++ = vpath_info->vpath_genstats_count0;
+		*ptr++ = vpath_info->vpath_genstats_count1;
+		*ptr++ = vpath_info->vpath_genstats_count2;
+		*ptr++ = vpath_info->vpath_genstats_count3;
+		*ptr++ = vpath_info->vpath_genstats_count4;
+		*ptr++ = vpath_info->vpath_genstats_count5;
+		*ptr++ = vpath_info->prog_event_vnum0;
+		*ptr++ = vpath_info->prog_event_vnum1;
+		*ptr++ = vpath_info->prog_event_vnum2;
+		*ptr++ = vpath_info->prog_event_vnum3;
+		*ptr++ = vpath_info->rx_multi_cast_frame_discard;
+		*ptr++ = vpath_info->rx_frm_transferred;
+		*ptr++ = vpath_info->rxd_returned;
+		*ptr++ = vpath_info->rx_mpa_len_fail_frms;
+		*ptr++ = vpath_info->rx_mpa_mrk_fail_frms;
+		*ptr++ = vpath_info->rx_mpa_crc_fail_frms;
+		*ptr++ = vpath_info->rx_permitted_frms;
+		*ptr++ = vpath_info->rx_vp_reset_discarded_frms;
+		*ptr++ = vpath_info->rx_wol_frms;
+		*ptr++ = vpath_info->tx_vp_reset_discarded_frms;
+	}
+
+	*ptr++ = 0;
+	*ptr++ = vdev->stats.vpaths_open;
+	*ptr++ = vdev->stats.vpath_open_fail;
+	*ptr++ = vdev->stats.link_up;
+	*ptr++ = vdev->stats.link_down;
+
+	for (k = 0; k < vdev->no_of_vpath; k++) {
+		*ptr += vdev->vpaths[k].fifo.stats.tx_frms;
+		*(ptr + 1) += vdev->vpaths[k].fifo.stats.tx_errors;
+		*(ptr + 2) += vdev->vpaths[k].fifo.stats.tx_bytes;
+		*(ptr + 3) += vdev->vpaths[k].fifo.stats.txd_not_free;
+		*(ptr + 4) += vdev->vpaths[k].fifo.stats.txd_out_of_desc;
+		*(ptr + 5) += vdev->vpaths[k].ring.stats.rx_frms;
+		*(ptr + 6) += vdev->vpaths[k].ring.stats.rx_errors;
+		*(ptr + 7) += vdev->vpaths[k].ring.stats.rx_bytes;
+		*(ptr + 8) += vdev->vpaths[k].ring.stats.rx_mcast;
+		*(ptr + 9) += vdev->vpaths[k].fifo.stats.pci_map_fail +
+				vdev->vpaths[k].ring.stats.pci_map_fail;
+		*(ptr + 10) += vdev->vpaths[k].ring.stats.skb_alloc_fail;
+	}
+
+	ptr += 12;
+
+	kfree(xmac_stats);
+	kfree(sw_stats);
+	kfree(hw_stats);
+}
+
+static void vxge_ethtool_get_strings(struct net_device *dev,
+			      u32 stringset, u8 *data)
+{
+	int stat_size = 0;
+	int i, j;
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	switch (stringset) {
+	case ETH_SS_STATS:
+		vxge_add_string("VPATH STATISTICS%s\t\t\t",
+			&stat_size, data, "");
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			vxge_add_string("tx_ttl_eth_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_ttl_eth_octects_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_data_octects_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_mcast_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_bcast_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_ucast_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_tagged_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_vld_ip_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_vld_ip_octects_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_icmp_%d\t\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_tcp_%d\t\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_rst_tcp_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_udp_%d\t\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_unknown_proto_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_lost_ip_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_parse_error_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_tcp_offload_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_retx_tcp_offload_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_lost_ip_offload_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_eth_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_vld_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_offload_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_eth_octects_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_data_octects_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_offload_octects_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_vld_mcast_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_vld_bcast_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_accepted_ucast_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_accepted_nucast_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_tagged_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_long_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_usized_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_osized_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_frag_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_jabber_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_64_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_65_127_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_128_255_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_256_511_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_512_1023_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_1024_1518_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_1519_4095_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_4096_8191_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_8192_max_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ttl_gt_max_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ip%d\t\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_accepted_ip_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_ip_octects_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_err_ip_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_icmp_%d\t\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_tcp_%d\t\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_udp_%d\t\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_err_tcp_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_lost_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_lost_ip_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_lost_ip_offload_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_various_discard_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_sleep_discard_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_red_discard_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_queue_full_discard_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_mpa_ok_frms_%d\t\t\t",
+					&stat_size, data, i);
+		}
+
+		vxge_add_string("\nAGGR STATISTICS%s\t\t\t\t",
+			&stat_size, data, "");
+		for (i = 0; i < vdev->max_config_port; i++) {
+			vxge_add_string("tx_frms_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_data_octects_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_mcast_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_bcast_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_discarded_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_errored_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_frms_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_data_octects_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_mcast_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_bcast_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_discarded_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_errored_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_unknown_slow_proto_frms_%d\t",
+				&stat_size, data, i);
+		}
+
+		vxge_add_string("\nPORT STATISTICS%s\t\t\t\t",
+			&stat_size, data, "");
+		for (i = 0; i < vdev->max_config_port; i++) {
+			vxge_add_string("tx_ttl_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_ttl_octects_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_data_octects_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_mcast_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_bcast_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_ucast_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_tagged_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_vld_ip_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_vld_ip_octects_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_icmp_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_tcp_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_rst_tcp_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_udp_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_parse_error_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_unknown_protocol_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_pause_ctrl_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_marker_pdu_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_lacpdu_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_drop_ip_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_marker_resp_pdu_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_xgmii_char2_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_xgmii_char1_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_xgmii_column2_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_xgmii_column1_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_any_err_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("tx_drop_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_vld_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_offload_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_octects_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_data_octects_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_offload_octects_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_vld_mcast_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_vld_bcast_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_accepted_ucast_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_accepted_nucast_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_tagged_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_long_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_usized_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_osized_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_frag_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_jabber_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_64_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_65_127_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_128_255_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_256_511_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_512_1023_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_1024_1518_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_1519_4095_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_4096_8191_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_8192_max_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ttl_gt_max_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ip_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_accepted_ip_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_ip_octets_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_err_ip_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_icmp_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_tcp_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_udp_%d\t\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_err_tcp_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_pause_count_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_pause_ctrl_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_unsup_ctrl_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_fcs_err_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_in_rng_len_err_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_out_rng_len_err_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_drop_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_discard_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_drop_ip_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_drop_udp_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_marker_pdu_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_lacpdu_frms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_unknown_pdu_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_marker_resp_pdu_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_fcs_discard_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_illegal_pdu_frms_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_switch_discard_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_len_discard_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_rpa_discard_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_l2_mgmt_discard_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_rts_discard_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_trash_discard_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_buff_full_discard_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_red_discard_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_xgmii_ctrl_err_cnt_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_xgmii_data_err_cnt_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_xgmii_char1_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_xgmii_err_sym_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_xgmii_column1_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_xgmii_char2_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_local_fault_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_xgmii_column2_match_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_jettison_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("rx_remote_fault_%d\t\t\t",
+				&stat_size, data, i);
+		}
+
+		vxge_add_string("\n SOFTWARE STATISTICS%s\t\t\t",
+			&stat_size, data, "");
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			vxge_add_string("soft_reset_cnt_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("unknown_alarms_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("network_sustained_fault_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("network_sustained_ok_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("kdfcctl_fifo0_overwrite_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("kdfcctl_fifo0_poison_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("kdfcctl_fifo0_dma_error_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("dblgen_fifo0_overflow_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("statsb_pif_chain_error_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("statsb_drop_timeout_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("target_illegal_access_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("ini_serr_det_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("prc_ring_bumps_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("prc_rxdcm_sc_err_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("prc_rxdcm_sc_abort_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("prc_quanta_size_err_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("ring_full_cnt_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("ring_usage_cnt_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("ring_usage_max_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("ring_reserve_free_swaps_cnt_%d\t",
+				&stat_size, data, i);
+			vxge_add_string("ring_total_compl_cnt_%d\t\t",
+				&stat_size, data, i);
+			for (j = 0; j < VXGE_HW_DTR_MAX_T_CODE; j++)
+				vxge_add_string("rxd_t_code_err_cnt%d_%d\t\t",
+					&stat_size, data, j, i);
+			vxge_add_string("fifo_full_cnt_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("fifo_usage_cnt_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("fifo_usage_max_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("fifo_reserve_free_swaps_cnt_%d\t",
+				&stat_size, data, i);
+			vxge_add_string("fifo_total_compl_cnt_%d\t\t",
+				&stat_size, data, i);
+			vxge_add_string("fifo_total_posts_%d\t\t\t",
+				&stat_size, data, i);
+			vxge_add_string("fifo_total_buffers_%d\t\t",
+				&stat_size, data, i);
+			for (j = 0; j < VXGE_HW_DTR_MAX_T_CODE; j++)
+				vxge_add_string("txd_t_code_err_cnt%d_%d\t\t",
+					&stat_size, data, j, i);
+		}
+
+		vxge_add_string("\n HARDWARE STATISTICS%s\t\t\t",
+				&stat_size, data, "");
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			vxge_add_string("ini_num_mwr_sent_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("ini_num_mrd_sent_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("ini_num_cpl_rcvd_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("ini_num_mwr_byte_sent_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("ini_num_cpl_byte_rcvd_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("wrcrdtarb_xoff_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rdcrdtarb_xoff_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("vpath_genstats_count0_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("vpath_genstats_count1_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("vpath_genstats_count2_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("vpath_genstats_count3_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("vpath_genstats_count4_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("vpath_genstats_count5_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("prog_event_vnum0_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("prog_event_vnum1_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("prog_event_vnum2_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("prog_event_vnum3_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_multi_cast_frame_discard_%d\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_frm_transferred_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rxd_returned_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_mpa_len_fail_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_mpa_mrk_fail_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_mpa_crc_fail_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_permitted_frms_%d\t\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_vp_reset_discarded_frms_%d\t",
+					&stat_size, data, i);
+			vxge_add_string("rx_wol_frms_%d\t\t\t",
+					&stat_size, data, i);
+			vxge_add_string("tx_vp_reset_discarded_frms_%d\t",
+					&stat_size, data, i);
+		}
+
+		memcpy(data + stat_size, &ethtool_driver_stats_keys,
+			sizeof(ethtool_driver_stats_keys));
+	}
+}
+
+static int vxge_ethtool_get_regs_len(struct net_device *dev)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+
+	return sizeof(struct vxge_hw_vpath_reg) * vdev->no_of_vpath;
+}
+
+static u32 vxge_get_rx_csum(struct net_device *dev)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+
+	return vdev->rx_csum;
+}
+
+static int vxge_set_rx_csum(struct net_device *dev, u32 data)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+
+	if (data)
+		vdev->rx_csum = 1;
+	else
+		vdev->rx_csum = 0;
+
+	return 0;
+}
+
+static int vxge_ethtool_op_set_tso(struct net_device *dev, u32 data)
+{
+	if (data)
+		dev->features |= (NETIF_F_TSO | NETIF_F_TSO6);
+	else
+		dev->features &= ~(NETIF_F_TSO | NETIF_F_TSO6);
+
+	return 0;
+}
+
+static int vxge_ethtool_get_sset_count(struct net_device *dev, int sset)
+{
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+
+	switch (sset) {
+	case ETH_SS_STATS:
+		return VXGE_TITLE_LEN +
+			(vdev->no_of_vpath * VXGE_HW_VPATH_STATS_LEN) +
+			(vdev->max_config_port * VXGE_HW_AGGR_STATS_LEN) +
+			(vdev->max_config_port * VXGE_HW_PORT_STATS_LEN) +
+			(vdev->no_of_vpath * VXGE_HW_VPATH_TX_STATS_LEN) +
+			(vdev->no_of_vpath * VXGE_HW_VPATH_RX_STATS_LEN) +
+			(vdev->no_of_vpath * VXGE_SW_STATS_LEN) +
+			DRIVER_STAT_LEN;
+	default:
+		return -EOPNOTSUPP;
+	}
+}
+
+static const struct ethtool_ops vxge_ethtool_ops = {
+	.get_settings		= vxge_ethtool_gset,
+	.set_settings		= vxge_ethtool_sset,
+	.get_drvinfo		= vxge_ethtool_gdrvinfo,
+	.get_regs_len		= vxge_ethtool_get_regs_len,
+	.get_regs		= vxge_ethtool_gregs,
+	.get_link		= ethtool_op_get_link,
+	.get_pauseparam		= vxge_ethtool_getpause_data,
+	.set_pauseparam		= vxge_ethtool_setpause_data,
+	.get_rx_csum		= vxge_get_rx_csum,
+	.set_rx_csum		= vxge_set_rx_csum,
+	.get_tx_csum		= ethtool_op_get_tx_csum,
+	.set_tx_csum		= ethtool_op_set_tx_hw_csum,
+	.get_sg			= ethtool_op_get_sg,
+	.set_sg			= ethtool_op_set_sg,
+	.get_tso		= ethtool_op_get_tso,
+	.set_tso		= vxge_ethtool_op_set_tso,
+	.get_strings		= vxge_ethtool_get_strings,
+	.phys_id		= vxge_ethtool_idnic,
+	.get_sset_count		= vxge_ethtool_get_sset_count,
+	.get_ethtool_stats	= vxge_get_ethtool_stats,
+};
+
+void initialize_ethtool_ops(struct net_device *ndev)
+{
+	SET_ETHTOOL_OPS(ndev, &vxge_ethtool_ops);
+}
diff --git a/drivers/net/vxge/vxge-ethtool.h b/drivers/net/vxge/vxge-ethtool.h
new file mode 100644
index 000000000000..1c3df0a34acc
--- /dev/null
+++ b/drivers/net/vxge/vxge-ethtool.h
@@ -0,0 +1,67 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-ethtool.h: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *                 Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#ifndef _VXGE_ETHTOOL_H
+#define _VXGE_ETHTOOL_H
+
+#include "vxge-main.h"
+
+/* Ethtool related variables and Macros. */
+static int vxge_ethtool_get_sset_count(struct net_device *dev, int sset);
+
+static char ethtool_driver_stats_keys[][ETH_GSTRING_LEN] = {
+	{"\n DRIVER STATISTICS"},
+	{"vpaths_opened"},
+	{"vpath_open_fail_cnt"},
+	{"link_up_cnt"},
+	{"link_down_cnt"},
+	{"tx_frms"},
+	{"tx_errors"},
+	{"tx_bytes"},
+	{"txd_not_free"},
+	{"txd_out_of_desc"},
+	{"rx_frms"},
+	{"rx_errors"},
+	{"rx_bytes"},
+	{"rx_mcast"},
+	{"pci_map_fail_cnt"},
+	{"skb_alloc_fail_cnt"}
+};
+
+#define VXGE_TITLE_LEN			5
+#define VXGE_HW_VPATH_STATS_LEN 	27
+#define VXGE_HW_AGGR_STATS_LEN  	13
+#define VXGE_HW_PORT_STATS_LEN  	94
+#define VXGE_HW_VPATH_TX_STATS_LEN	19
+#define VXGE_HW_VPATH_RX_STATS_LEN	42
+#define VXGE_SW_STATS_LEN		60
+#define VXGE_HW_STATS_LEN	(VXGE_HW_VPATH_STATS_LEN +\
+				VXGE_HW_AGGR_STATS_LEN +\
+				VXGE_HW_PORT_STATS_LEN +\
+				VXGE_HW_VPATH_TX_STATS_LEN +\
+				VXGE_HW_VPATH_RX_STATS_LEN)
+
+#define DRIVER_STAT_LEN (sizeof(ethtool_driver_stats_keys)/ETH_GSTRING_LEN)
+#define STAT_LEN (VXGE_HW_STATS_LEN + DRIVER_STAT_LEN + VXGE_SW_STATS_LEN)
+
+/* Maximum flicker time of adapter LED */
+#define VXGE_MAX_FLICKER_TIME (60 * HZ) /* 60 seconds */
+#define VXGE_FLICKER_ON		1
+#define VXGE_FLICKER_OFF	0
+
+#define vxge_add_string(fmt, size, buf, ...) {\
+	snprintf(buf + *size, ETH_GSTRING_LEN, fmt, __VA_ARGS__); \
+	*size += ETH_GSTRING_LEN; \
+}
+
+#endif /*_VXGE_ETHTOOL_H*/
diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c
new file mode 100644
index 000000000000..61ef16118157
--- /dev/null
+++ b/drivers/net/vxge/vxge-main.c
@@ -0,0 +1,4502 @@
+/******************************************************************************
+* This software may be used and distributed according to the terms of
+* the GNU General Public License (GPL), incorporated herein by reference.
+* Drivers based on or derived from this code fall under the GPL and must
+* retain the authorship, copyright and license notice.  This file is not
+* a complete program and may only be used when the entire operating
+* system is licensed under the GPL.
+* See the file COPYING in this distribution for more information.
+*
+* vxge-main.c: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+*              Virtualized Server Adapter.
+* Copyright(c) 2002-2009 Neterion Inc.
+*
+* The module loadable parameters that are supported by the driver and a brief
+* explanation of all the variables:
+* vlan_tag_strip:
+*	Strip VLAN Tag enable/disable. Instructs the device to remove
+*	the VLAN tag from all received tagged frames that are not
+*	replicated at the internal L2 switch.
+*		0 - Do not strip the VLAN tag.
+*		1 - Strip the VLAN tag.
+*
+* addr_learn_en:
+*	Enable learning the mac address of the guest OS interface in
+*	a virtualization environment.
+*		0 - DISABLE
+*		1 - ENABLE
+*
+* max_config_port:
+*	Maximum number of port to be supported.
+*		MIN -1 and MAX - 2
+*
+* max_config_vpath:
+*	This configures the maximum no of VPATH configures for each
+* 	device function.
+*		MIN - 1 and MAX - 17
+*
+* max_config_dev:
+*	This configures maximum no of Device function to be enabled.
+*		MIN - 1 and MAX - 17
+*
+******************************************************************************/
+
+#include <linux/if_vlan.h>
+#include <linux/pci.h>
+#include <net/ip.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include "vxge-main.h"
+#include "vxge-reg.h"
+
+MODULE_LICENSE("Dual BSD/GPL");
+MODULE_DESCRIPTION("Neterion's X3100 Series 10GbE PCIe I/O"
+	"Virtualized Server Adapter");
+
+static struct pci_device_id vxge_id_table[] __devinitdata = {
+	{PCI_VENDOR_ID_S2IO, PCI_DEVICE_ID_TITAN_WIN, PCI_ANY_ID,
+	PCI_ANY_ID},
+	{PCI_VENDOR_ID_S2IO, PCI_DEVICE_ID_TITAN_UNI, PCI_ANY_ID,
+	PCI_ANY_ID},
+	{0}
+};
+
+MODULE_DEVICE_TABLE(pci, vxge_id_table);
+
+VXGE_MODULE_PARAM_INT(vlan_tag_strip, VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_ENABLE);
+VXGE_MODULE_PARAM_INT(addr_learn_en, VXGE_HW_MAC_ADDR_LEARN_DEFAULT);
+VXGE_MODULE_PARAM_INT(max_config_port, VXGE_MAX_CONFIG_PORT);
+VXGE_MODULE_PARAM_INT(max_config_vpath, VXGE_USE_DEFAULT);
+VXGE_MODULE_PARAM_INT(max_mac_vpath, VXGE_MAX_MAC_ADDR_COUNT);
+VXGE_MODULE_PARAM_INT(max_config_dev, VXGE_MAX_CONFIG_DEV);
+
+static u16 vpath_selector[VXGE_HW_MAX_VIRTUAL_PATHS] =
+		{0, 1, 3, 3, 7, 7, 7, 7, 15, 15, 15, 15, 15, 15, 15, 15, 31};
+static unsigned int bw_percentage[VXGE_HW_MAX_VIRTUAL_PATHS] =
+	{[0 ...(VXGE_HW_MAX_VIRTUAL_PATHS - 1)] = 0xFF};
+module_param_array(bw_percentage, uint, NULL, 0);
+
+static struct vxge_drv_config *driver_config;
+
+static inline int is_vxge_card_up(struct vxgedev *vdev)
+{
+	return test_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+}
+
+static inline void VXGE_COMPLETE_VPATH_TX(struct vxge_fifo *fifo)
+{
+	unsigned long flags = 0;
+	struct sk_buff *skb_ptr = NULL;
+	struct sk_buff **temp, *head, *skb;
+
+	if (spin_trylock_irqsave(&fifo->tx_lock, flags)) {
+		vxge_hw_vpath_poll_tx(fifo->handle, (void **)&skb_ptr);
+		spin_unlock_irqrestore(&fifo->tx_lock, flags);
+	}
+	/* free SKBs */
+	head = skb_ptr;
+	while (head) {
+		skb = head;
+		temp = (struct sk_buff **)&skb->cb;
+		head = *temp;
+		*temp = NULL;
+		dev_kfree_skb_irq(skb);
+	}
+}
+
+static inline void VXGE_COMPLETE_ALL_TX(struct vxgedev *vdev)
+{
+	int i;
+
+	/* Complete all transmits */
+	for (i = 0; i < vdev->no_of_vpath; i++)
+		VXGE_COMPLETE_VPATH_TX(&vdev->vpaths[i].fifo);
+}
+
+static inline void VXGE_COMPLETE_ALL_RX(struct vxgedev *vdev)
+{
+	int i;
+	struct vxge_ring *ring;
+
+	/* Complete all receives*/
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		ring = &vdev->vpaths[i].ring;
+		vxge_hw_vpath_poll_rx(ring->handle);
+	}
+}
+
+/*
+ * MultiQ manipulation helper functions
+ */
+void vxge_stop_all_tx_queue(struct vxgedev *vdev)
+{
+	int i;
+	struct net_device *dev = vdev->ndev;
+
+	if (vdev->config.tx_steering_type != TX_MULTIQ_STEERING) {
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			vdev->vpaths[i].fifo.queue_state = VPATH_QUEUE_STOP;
+	}
+	netif_tx_stop_all_queues(dev);
+}
+
+void vxge_stop_tx_queue(struct vxge_fifo *fifo)
+{
+	struct net_device *dev = fifo->ndev;
+
+	struct netdev_queue *txq = NULL;
+	if (fifo->tx_steering_type == TX_MULTIQ_STEERING)
+		txq = netdev_get_tx_queue(dev, fifo->driver_id);
+	else {
+		txq = netdev_get_tx_queue(dev, 0);
+		fifo->queue_state = VPATH_QUEUE_STOP;
+	}
+
+	netif_tx_stop_queue(txq);
+}
+
+void vxge_start_all_tx_queue(struct vxgedev *vdev)
+{
+	int i;
+	struct net_device *dev = vdev->ndev;
+
+	if (vdev->config.tx_steering_type != TX_MULTIQ_STEERING) {
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			vdev->vpaths[i].fifo.queue_state = VPATH_QUEUE_START;
+	}
+	netif_tx_start_all_queues(dev);
+}
+
+static void vxge_wake_all_tx_queue(struct vxgedev *vdev)
+{
+	int i;
+	struct net_device *dev = vdev->ndev;
+
+	if (vdev->config.tx_steering_type != TX_MULTIQ_STEERING) {
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			vdev->vpaths[i].fifo.queue_state = VPATH_QUEUE_START;
+	}
+	netif_tx_wake_all_queues(dev);
+}
+
+void vxge_wake_tx_queue(struct vxge_fifo *fifo, struct sk_buff *skb)
+{
+	struct net_device *dev = fifo->ndev;
+
+	int vpath_no = fifo->driver_id;
+	struct netdev_queue *txq = NULL;
+	if (fifo->tx_steering_type == TX_MULTIQ_STEERING) {
+		txq = netdev_get_tx_queue(dev, vpath_no);
+		if (netif_tx_queue_stopped(txq))
+			netif_tx_wake_queue(txq);
+	} else {
+		txq = netdev_get_tx_queue(dev, 0);
+		if (fifo->queue_state == VPATH_QUEUE_STOP)
+			if (netif_tx_queue_stopped(txq)) {
+				fifo->queue_state = VPATH_QUEUE_START;
+				netif_tx_wake_queue(txq);
+			}
+	}
+}
+
+/*
+ * vxge_callback_link_up
+ *
+ * This function is called during interrupt context to notify link up state
+ * change.
+ */
+void
+vxge_callback_link_up(struct __vxge_hw_device *hldev)
+{
+	struct net_device *dev = hldev->ndev;
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+		vdev->ndev->name, __func__, __LINE__);
+	printk(KERN_NOTICE "%s: Link Up\n", vdev->ndev->name);
+	vdev->stats.link_up++;
+
+	netif_carrier_on(vdev->ndev);
+	vxge_wake_all_tx_queue(vdev);
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d Exiting...", vdev->ndev->name, __func__, __LINE__);
+}
+
+/*
+ * vxge_callback_link_down
+ *
+ * This function is called during interrupt context to notify link down state
+ * change.
+ */
+void
+vxge_callback_link_down(struct __vxge_hw_device *hldev)
+{
+	struct net_device *dev = hldev->ndev;
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d", vdev->ndev->name, __func__, __LINE__);
+	printk(KERN_NOTICE "%s: Link Down\n", vdev->ndev->name);
+
+	vdev->stats.link_down++;
+	netif_carrier_off(vdev->ndev);
+	vxge_stop_all_tx_queue(vdev);
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d Exiting...", vdev->ndev->name, __func__, __LINE__);
+}
+
+/*
+ * vxge_rx_alloc
+ *
+ * Allocate SKB.
+ */
+static struct sk_buff*
+vxge_rx_alloc(void *dtrh, struct vxge_ring *ring, const int skb_size)
+{
+	struct net_device    *dev;
+	struct sk_buff       *skb;
+	struct vxge_rx_priv *rx_priv;
+
+	dev = ring->ndev;
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+		ring->ndev->name, __func__, __LINE__);
+
+	rx_priv = vxge_hw_ring_rxd_private_get(dtrh);
+
+	/* try to allocate skb first. this one may fail */
+	skb = netdev_alloc_skb(dev, skb_size +
+	VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);
+	if (skb == NULL) {
+		vxge_debug_mem(VXGE_ERR,
+			"%s: out of memory to allocate SKB", dev->name);
+		ring->stats.skb_alloc_fail++;
+		return NULL;
+	}
+
+	vxge_debug_mem(VXGE_TRACE,
+		"%s: %s:%d  Skb : 0x%p", ring->ndev->name,
+		__func__, __LINE__, skb);
+
+	skb_reserve(skb, VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);
+
+	rx_priv->skb = skb;
+	rx_priv->data_size = skb_size;
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);
+
+	return skb;
+}
+
+/*
+ * vxge_rx_map
+ */
+static int vxge_rx_map(void *dtrh, struct vxge_ring *ring)
+{
+	struct vxge_rx_priv *rx_priv;
+	dma_addr_t dma_addr;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+		ring->ndev->name, __func__, __LINE__);
+	rx_priv = vxge_hw_ring_rxd_private_get(dtrh);
+
+	dma_addr = pci_map_single(ring->pdev, rx_priv->skb->data,
+				rx_priv->data_size, PCI_DMA_FROMDEVICE);
+
+	if (dma_addr == 0) {
+		ring->stats.pci_map_fail++;
+		return -EIO;
+	}
+	vxge_debug_mem(VXGE_TRACE,
+		"%s: %s:%d  1 buffer mode dma_addr = 0x%llx",
+		ring->ndev->name, __func__, __LINE__,
+		(unsigned long long)dma_addr);
+	vxge_hw_ring_rxd_1b_set(dtrh, dma_addr, rx_priv->data_size);
+
+	rx_priv->data_dma = dma_addr;
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);
+
+	return 0;
+}
+
+/*
+ * vxge_rx_initial_replenish
+ * Allocation of RxD as an initial replenish procedure.
+ */
+static enum vxge_hw_status
+vxge_rx_initial_replenish(void *dtrh, void *userdata)
+{
+	struct vxge_ring *ring = (struct vxge_ring *)userdata;
+	struct vxge_rx_priv *rx_priv;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+		ring->ndev->name, __func__, __LINE__);
+	if (vxge_rx_alloc(dtrh, ring,
+			  VXGE_LL_MAX_FRAME_SIZE(ring->ndev)) == NULL)
+		return VXGE_HW_FAIL;
+
+	if (vxge_rx_map(dtrh, ring)) {
+		rx_priv = vxge_hw_ring_rxd_private_get(dtrh);
+		dev_kfree_skb(rx_priv->skb);
+
+		return VXGE_HW_FAIL;
+	}
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);
+
+	return VXGE_HW_OK;
+}
+
+static inline void
+vxge_rx_complete(struct vxge_ring *ring, struct sk_buff *skb, u16 vlan,
+		 int pkt_length, struct vxge_hw_ring_rxd_info *ext_info)
+{
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+			ring->ndev->name, __func__, __LINE__);
+	skb_record_rx_queue(skb, ring->driver_id);
+	skb->protocol = eth_type_trans(skb, ring->ndev);
+
+	ring->stats.rx_frms++;
+	ring->stats.rx_bytes += pkt_length;
+
+	if (skb->pkt_type == PACKET_MULTICAST)
+		ring->stats.rx_mcast++;
+
+	vxge_debug_rx(VXGE_TRACE,
+		"%s: %s:%d  skb protocol = %d",
+		ring->ndev->name, __func__, __LINE__, skb->protocol);
+
+	if (ring->gro_enable) {
+		if (ring->vlgrp && ext_info->vlan &&
+			(ring->vlan_tag_strip ==
+				VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_ENABLE))
+			vlan_gro_receive(&ring->napi, ring->vlgrp,
+					ext_info->vlan, skb);
+		else
+			napi_gro_receive(&ring->napi, skb);
+	} else {
+		if (ring->vlgrp && vlan &&
+			(ring->vlan_tag_strip ==
+				VXGE_HW_VPATH_RPA_STRIP_VLAN_TAG_ENABLE))
+			vlan_hwaccel_receive_skb(skb, ring->vlgrp, vlan);
+		else
+			netif_receive_skb(skb);
+	}
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d Exiting...", ring->ndev->name, __func__, __LINE__);
+}
+
+static inline void vxge_re_pre_post(void *dtr, struct vxge_ring *ring,
+				    struct vxge_rx_priv *rx_priv)
+{
+	pci_dma_sync_single_for_device(ring->pdev,
+		rx_priv->data_dma, rx_priv->data_size, PCI_DMA_FROMDEVICE);
+
+	vxge_hw_ring_rxd_1b_set(dtr, rx_priv->data_dma, rx_priv->data_size);
+	vxge_hw_ring_rxd_pre_post(ring->handle, dtr);
+}
+
+static inline void vxge_post(int *dtr_cnt, void **first_dtr,
+			     void *post_dtr, struct __vxge_hw_ring *ringh)
+{
+	int dtr_count = *dtr_cnt;
+	if ((*dtr_cnt % VXGE_HW_RXSYNC_FREQ_CNT) == 0) {
+		if (*first_dtr)
+			vxge_hw_ring_rxd_post_post_wmb(ringh, *first_dtr);
+		*first_dtr = post_dtr;
+	} else
+		vxge_hw_ring_rxd_post_post(ringh, post_dtr);
+	dtr_count++;
+	*dtr_cnt = dtr_count;
+}
+
+/*
+ * vxge_rx_1b_compl
+ *
+ * If the interrupt is because of a received frame or if the receive ring
+ * contains fresh as yet un-processed frames, this function is called.
+ */
+enum vxge_hw_status
+vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr,
+		 u8 t_code, void *userdata)
+{
+	struct vxge_ring *ring = (struct vxge_ring *)userdata;
+	struct  net_device *dev = ring->ndev;
+	unsigned int dma_sizes;
+	void *first_dtr = NULL;
+	int dtr_cnt = 0;
+	int data_size;
+	dma_addr_t data_dma;
+	int pkt_length;
+	struct sk_buff *skb;
+	struct vxge_rx_priv *rx_priv;
+	struct vxge_hw_ring_rxd_info ext_info;
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+		ring->ndev->name, __func__, __LINE__);
+	ring->pkts_processed = 0;
+
+	vxge_hw_ring_replenish(ringh, 0);
+
+	do {
+		rx_priv = vxge_hw_ring_rxd_private_get(dtr);
+		skb = rx_priv->skb;
+		data_size = rx_priv->data_size;
+		data_dma = rx_priv->data_dma;
+
+		vxge_debug_rx(VXGE_TRACE,
+			"%s: %s:%d  skb = 0x%p",
+			ring->ndev->name, __func__, __LINE__, skb);
+
+		vxge_hw_ring_rxd_1b_get(ringh, dtr, &dma_sizes);
+		pkt_length = dma_sizes;
+
+		vxge_debug_rx(VXGE_TRACE,
+			"%s: %s:%d  Packet Length = %d",
+			ring->ndev->name, __func__, __LINE__, pkt_length);
+
+		vxge_hw_ring_rxd_1b_info_get(ringh, dtr, &ext_info);
+
+		/* check skb validity */
+		vxge_assert(skb);
+
+		prefetch((char *)skb + L1_CACHE_BYTES);
+		if (unlikely(t_code)) {
+
+			if (vxge_hw_ring_handle_tcode(ringh, dtr, t_code) !=
+				VXGE_HW_OK) {
+
+				ring->stats.rx_errors++;
+				vxge_debug_rx(VXGE_TRACE,
+					"%s: %s :%d Rx T_code is %d",
+					ring->ndev->name, __func__,
+					__LINE__, t_code);
+
+				/* If the t_code is not supported and if the
+				 * t_code is other than 0x5 (unparseable packet
+				 * such as unknown UPV6 header), Drop it !!!
+				 */
+				vxge_re_pre_post(dtr, ring, rx_priv);
+
+				vxge_post(&dtr_cnt, &first_dtr, dtr, ringh);
+				ring->stats.rx_dropped++;
+				continue;
+			}
+		}
+
+		if (pkt_length > VXGE_LL_RX_COPY_THRESHOLD) {
+
+			if (vxge_rx_alloc(dtr, ring, data_size) != NULL) {
+
+				if (!vxge_rx_map(dtr, ring)) {
+					skb_put(skb, pkt_length);
+
+					pci_unmap_single(ring->pdev, data_dma,
+						data_size, PCI_DMA_FROMDEVICE);
+
+					vxge_hw_ring_rxd_pre_post(ringh, dtr);
+					vxge_post(&dtr_cnt, &first_dtr, dtr,
+						ringh);
+				} else {
+					dev_kfree_skb(rx_priv->skb);
+					rx_priv->skb = skb;
+					rx_priv->data_size = data_size;
+					vxge_re_pre_post(dtr, ring, rx_priv);
+
+					vxge_post(&dtr_cnt, &first_dtr, dtr,
+						ringh);
+					ring->stats.rx_dropped++;
+					break;
+				}
+			} else {
+				vxge_re_pre_post(dtr, ring, rx_priv);
+
+				vxge_post(&dtr_cnt, &first_dtr, dtr, ringh);
+				ring->stats.rx_dropped++;
+				break;
+			}
+		} else {
+			struct sk_buff *skb_up;
+
+			skb_up = netdev_alloc_skb(dev, pkt_length +
+				VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);
+			if (skb_up != NULL) {
+				skb_reserve(skb_up,
+				    VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN);
+
+				pci_dma_sync_single_for_cpu(ring->pdev,
+					data_dma, data_size,
+					PCI_DMA_FROMDEVICE);
+
+				vxge_debug_mem(VXGE_TRACE,
+					"%s: %s:%d  skb_up = %p",
+					ring->ndev->name, __func__,
+					__LINE__, skb);
+				memcpy(skb_up->data, skb->data, pkt_length);
+
+				vxge_re_pre_post(dtr, ring, rx_priv);
+
+				vxge_post(&dtr_cnt, &first_dtr, dtr,
+					ringh);
+				/* will netif_rx small SKB instead */
+				skb = skb_up;
+				skb_put(skb, pkt_length);
+			} else {
+				vxge_re_pre_post(dtr, ring, rx_priv);
+
+				vxge_post(&dtr_cnt, &first_dtr, dtr, ringh);
+				vxge_debug_rx(VXGE_ERR,
+					"%s: vxge_rx_1b_compl: out of "
+					"memory", dev->name);
+				ring->stats.skb_alloc_fail++;
+				break;
+			}
+		}
+
+		if ((ext_info.proto & VXGE_HW_FRAME_PROTO_TCP_OR_UDP) &&
+		    !(ext_info.proto & VXGE_HW_FRAME_PROTO_IP_FRAG) &&
+		    ring->rx_csum && /* Offload Rx side CSUM */
+		    ext_info.l3_cksum == VXGE_HW_L3_CKSUM_OK &&
+		    ext_info.l4_cksum == VXGE_HW_L4_CKSUM_OK)
+			skb->ip_summed = CHECKSUM_UNNECESSARY;
+		else
+			skb->ip_summed = CHECKSUM_NONE;
+
+		vxge_rx_complete(ring, skb, ext_info.vlan,
+			pkt_length, &ext_info);
+
+		ring->budget--;
+		ring->pkts_processed++;
+		if (!ring->budget)
+			break;
+
+	} while (vxge_hw_ring_rxd_next_completed(ringh, &dtr,
+		&t_code) == VXGE_HW_OK);
+
+	if (first_dtr)
+		vxge_hw_ring_rxd_post_post_wmb(ringh, first_dtr);
+
+	dev->last_rx = jiffies;
+
+	vxge_debug_entryexit(VXGE_TRACE,
+				"%s:%d  Exiting...",
+				__func__, __LINE__);
+	return VXGE_HW_OK;
+}
+
+/*
+ * vxge_xmit_compl
+ *
+ * If an interrupt was raised to indicate DMA complete of the Tx packet,
+ * this function is called. It identifies the last TxD whose buffer was
+ * freed and frees all skbs whose data have already DMA'ed into the NICs
+ * internal memory.
+ */
+enum vxge_hw_status
+vxge_xmit_compl(struct __vxge_hw_fifo *fifo_hw, void *dtr,
+		enum vxge_hw_fifo_tcode t_code, void *userdata,
+		void **skb_ptr)
+{
+	struct vxge_fifo *fifo = (struct vxge_fifo *)userdata;
+	struct sk_buff *skb, *head = NULL;
+	struct sk_buff **temp;
+	int pkt_cnt = 0;
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d Entered....", __func__, __LINE__);
+
+	do {
+		int frg_cnt;
+		skb_frag_t *frag;
+		int i = 0, j;
+		struct vxge_tx_priv *txd_priv =
+			vxge_hw_fifo_txdl_private_get(dtr);
+
+		skb = txd_priv->skb;
+		frg_cnt = skb_shinfo(skb)->nr_frags;
+		frag = &skb_shinfo(skb)->frags[0];
+
+		vxge_debug_tx(VXGE_TRACE,
+				"%s: %s:%d fifo_hw = %p dtr = %p "
+				"tcode = 0x%x", fifo->ndev->name, __func__,
+				__LINE__, fifo_hw, dtr, t_code);
+		/* check skb validity */
+		vxge_assert(skb);
+		vxge_debug_tx(VXGE_TRACE,
+			"%s: %s:%d skb = %p itxd_priv = %p frg_cnt = %d",
+			fifo->ndev->name, __func__, __LINE__,
+			skb, txd_priv, frg_cnt);
+		if (unlikely(t_code)) {
+			fifo->stats.tx_errors++;
+			vxge_debug_tx(VXGE_ERR,
+				"%s: tx: dtr %p completed due to "
+				"error t_code %01x", fifo->ndev->name,
+				dtr, t_code);
+			vxge_hw_fifo_handle_tcode(fifo_hw, dtr, t_code);
+		}
+
+		/*  for unfragmented skb */
+		pci_unmap_single(fifo->pdev, txd_priv->dma_buffers[i++],
+				skb_headlen(skb), PCI_DMA_TODEVICE);
+
+		for (j = 0; j < frg_cnt; j++) {
+			pci_unmap_page(fifo->pdev,
+					txd_priv->dma_buffers[i++],
+					frag->size, PCI_DMA_TODEVICE);
+			frag += 1;
+		}
+
+		vxge_hw_fifo_txdl_free(fifo_hw, dtr);
+
+		/* Updating the statistics block */
+		fifo->stats.tx_frms++;
+		fifo->stats.tx_bytes += skb->len;
+
+		temp = (struct sk_buff **)&skb->cb;
+		*temp = head;
+		head = skb;
+
+		pkt_cnt++;
+		if (pkt_cnt > fifo->indicate_max_pkts)
+			break;
+
+	} while (vxge_hw_fifo_txdl_next_completed(fifo_hw,
+				&dtr, &t_code) == VXGE_HW_OK);
+
+	vxge_wake_tx_queue(fifo, skb);
+
+	if (skb_ptr)
+		*skb_ptr = (void *) head;
+
+	vxge_debug_entryexit(VXGE_TRACE,
+				"%s: %s:%d  Exiting...",
+				fifo->ndev->name, __func__, __LINE__);
+	return VXGE_HW_OK;
+}
+
+/* select a vpath to trasmit the packet */
+static u32 vxge_get_vpath_no(struct vxgedev *vdev, struct sk_buff *skb,
+	int *do_lock)
+{
+	u16 queue_len, counter = 0;
+	if (skb->protocol == htons(ETH_P_IP)) {
+		struct iphdr *ip;
+		struct tcphdr *th;
+
+		ip = ip_hdr(skb);
+
+		if ((ip->frag_off & htons(IP_OFFSET|IP_MF)) == 0) {
+			th = (struct tcphdr *)(((unsigned char *)ip) +
+					ip->ihl*4);
+
+			queue_len = vdev->no_of_vpath;
+			counter = (ntohs(th->source) +
+				ntohs(th->dest)) &
+				vdev->vpath_selector[queue_len - 1];
+			if (counter >= queue_len)
+				counter = queue_len - 1;
+
+			if (ip->protocol == IPPROTO_UDP) {
+#ifdef NETIF_F_LLTX
+				*do_lock = 0;
+#endif
+			}
+		}
+	}
+	return counter;
+}
+
+static enum vxge_hw_status vxge_search_mac_addr_in_list(
+	struct vxge_vpath *vpath, u64 del_mac)
+{
+	struct list_head *entry, *next;
+	list_for_each_safe(entry, next, &vpath->mac_addr_list) {
+		if (((struct vxge_mac_addrs *)entry)->macaddr == del_mac)
+			return TRUE;
+	}
+	return FALSE;
+}
+
+static int vxge_learn_mac(struct vxgedev *vdev, u8 *mac_header)
+{
+	struct macInfo mac_info;
+	u8 *mac_address = NULL;
+	u64 mac_addr = 0, vpath_vector = 0;
+	int vpath_idx = 0;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_vpath *vpath = NULL;
+	struct __vxge_hw_device *hldev;
+
+	hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev);
+
+	mac_address = (u8 *)&mac_addr;
+	memcpy(mac_address, mac_header, ETH_ALEN);
+
+	/* Is this mac address already in the list? */
+	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
+		vpath = &vdev->vpaths[vpath_idx];
+		if (vxge_search_mac_addr_in_list(vpath, mac_addr))
+			return vpath_idx;
+	}
+
+	memset(&mac_info, 0, sizeof(struct macInfo));
+	memcpy(mac_info.macaddr, mac_header, ETH_ALEN);
+
+	/* Any vpath has room to add mac address to its da table? */
+	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
+		vpath = &vdev->vpaths[vpath_idx];
+		if (vpath->mac_addr_cnt < vpath->max_mac_addr_cnt) {
+			/* Add this mac address to this vpath */
+			mac_info.vpath_no = vpath_idx;
+			mac_info.state = VXGE_LL_MAC_ADDR_IN_DA_TABLE;
+			status = vxge_add_mac_addr(vdev, &mac_info);
+			if (status != VXGE_HW_OK)
+				return -EPERM;
+			return vpath_idx;
+		}
+	}
+
+	mac_info.state = VXGE_LL_MAC_ADDR_IN_LIST;
+	vpath_idx = 0;
+	mac_info.vpath_no = vpath_idx;
+	/* Is the first vpath already selected as catch-basin ? */
+	vpath = &vdev->vpaths[vpath_idx];
+	if (vpath->mac_addr_cnt > vpath->max_mac_addr_cnt) {
+		/* Add this mac address to this vpath */
+		if (FALSE == vxge_mac_list_add(vpath, &mac_info))
+			return -EPERM;
+		return vpath_idx;
+	}
+
+	/* Select first vpath as catch-basin */
+	vpath_vector = vxge_mBIT(vpath->device_id);
+	status = vxge_hw_mgmt_reg_write(vpath->vdev->devh,
+				vxge_hw_mgmt_reg_type_mrpcim,
+				0,
+				(ulong)offsetof(
+					struct vxge_hw_mrpcim_reg,
+					rts_mgr_cbasin_cfg),
+				vpath_vector);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_tx(VXGE_ERR,
+			"%s: Unable to set the vpath-%d in catch-basin mode",
+			VXGE_DRIVER_NAME, vpath->device_id);
+		return -EPERM;
+	}
+
+	if (FALSE == vxge_mac_list_add(vpath, &mac_info))
+		return -EPERM;
+
+	return vpath_idx;
+}
+
+/**
+ * vxge_xmit
+ * @skb : the socket buffer containing the Tx data.
+ * @dev : device pointer.
+ *
+ * This function is the Tx entry point of the driver. Neterion NIC supports
+ * certain protocol assist features on Tx side, namely  CSO, S/G, LSO.
+ * NOTE: when device cant queue the pkt, just the trans_start variable will
+ * not be upadted.
+*/
+static int
+vxge_xmit(struct sk_buff *skb, struct net_device *dev)
+{
+	struct vxge_fifo *fifo = NULL;
+	void *dtr_priv;
+	void *dtr = NULL;
+	struct vxgedev *vdev = NULL;
+	enum vxge_hw_status status;
+	int frg_cnt, first_frg_len;
+	skb_frag_t *frag;
+	int i = 0, j = 0, avail;
+	u64 dma_pointer;
+	struct vxge_tx_priv *txdl_priv = NULL;
+	struct __vxge_hw_fifo *fifo_hw;
+	u32 max_mss = 0x0;
+	int offload_type;
+	unsigned long flags = 0;
+	int vpath_no = 0;
+	int do_spin_tx_lock = 1;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+			dev->name, __func__, __LINE__);
+
+	/* A buffer with no data will be dropped */
+	if (unlikely(skb->len <= 0)) {
+		vxge_debug_tx(VXGE_ERR,
+			"%s: Buffer has no data..", dev->name);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+
+	if (unlikely(!is_vxge_card_up(vdev))) {
+		vxge_debug_tx(VXGE_ERR,
+			"%s: vdev not initialized", dev->name);
+		dev_kfree_skb(skb);
+		return NETDEV_TX_OK;
+	}
+
+	if (vdev->config.addr_learn_en) {
+		vpath_no = vxge_learn_mac(vdev, skb->data + ETH_ALEN);
+		if (vpath_no == -EPERM) {
+			vxge_debug_tx(VXGE_ERR,
+				"%s: Failed to store the mac address",
+				dev->name);
+			dev_kfree_skb(skb);
+			return NETDEV_TX_OK;
+		}
+	}
+
+	if (vdev->config.tx_steering_type == TX_MULTIQ_STEERING)
+		vpath_no = skb_get_queue_mapping(skb);
+	else if (vdev->config.tx_steering_type == TX_PORT_STEERING)
+		vpath_no = vxge_get_vpath_no(vdev, skb, &do_spin_tx_lock);
+
+	vxge_debug_tx(VXGE_TRACE, "%s: vpath_no= %d", dev->name, vpath_no);
+
+	if (vpath_no >= vdev->no_of_vpath)
+		vpath_no = 0;
+
+	fifo = &vdev->vpaths[vpath_no].fifo;
+	fifo_hw = fifo->handle;
+
+	if (do_spin_tx_lock)
+		spin_lock_irqsave(&fifo->tx_lock, flags);
+	else {
+		if (unlikely(!spin_trylock_irqsave(&fifo->tx_lock, flags)))
+			return NETDEV_TX_LOCKED;
+	}
+
+	if (vdev->config.tx_steering_type == TX_MULTIQ_STEERING) {
+		if (netif_subqueue_stopped(dev, skb)) {
+			spin_unlock_irqrestore(&fifo->tx_lock, flags);
+			return NETDEV_TX_BUSY;
+		}
+	} else if (unlikely(fifo->queue_state == VPATH_QUEUE_STOP)) {
+		if (netif_queue_stopped(dev)) {
+			spin_unlock_irqrestore(&fifo->tx_lock, flags);
+			return NETDEV_TX_BUSY;
+		}
+	}
+	avail = vxge_hw_fifo_free_txdl_count_get(fifo_hw);
+	if (avail == 0) {
+		vxge_debug_tx(VXGE_ERR,
+			"%s: No free TXDs available", dev->name);
+		fifo->stats.txd_not_free++;
+		vxge_stop_tx_queue(fifo);
+		goto _exit2;
+	}
+
+	status = vxge_hw_fifo_txdl_reserve(fifo_hw, &dtr, &dtr_priv);
+	if (unlikely(status != VXGE_HW_OK)) {
+		vxge_debug_tx(VXGE_ERR,
+		   "%s: Out of descriptors .", dev->name);
+		fifo->stats.txd_out_of_desc++;
+		vxge_stop_tx_queue(fifo);
+		goto _exit2;
+	}
+
+	vxge_debug_tx(VXGE_TRACE,
+		"%s: %s:%d fifo_hw = %p dtr = %p dtr_priv = %p",
+		dev->name, __func__, __LINE__,
+		fifo_hw, dtr, dtr_priv);
+
+	if (vdev->vlgrp && vlan_tx_tag_present(skb)) {
+		u16 vlan_tag = vlan_tx_tag_get(skb);
+		vxge_hw_fifo_txdl_vlan_set(dtr, vlan_tag);
+	}
+
+	first_frg_len = skb_headlen(skb);
+
+	dma_pointer = pci_map_single(fifo->pdev, skb->data, first_frg_len,
+				PCI_DMA_TODEVICE);
+
+	if (unlikely(pci_dma_mapping_error(fifo->pdev, dma_pointer))) {
+		vxge_hw_fifo_txdl_free(fifo_hw, dtr);
+		vxge_stop_tx_queue(fifo);
+		fifo->stats.pci_map_fail++;
+		goto _exit2;
+	}
+
+	txdl_priv = vxge_hw_fifo_txdl_private_get(dtr);
+	txdl_priv->skb = skb;
+	txdl_priv->dma_buffers[j] = dma_pointer;
+
+	frg_cnt = skb_shinfo(skb)->nr_frags;
+	vxge_debug_tx(VXGE_TRACE,
+			"%s: %s:%d skb = %p txdl_priv = %p "
+			"frag_cnt = %d dma_pointer = 0x%llx", dev->name,
+			__func__, __LINE__, skb, txdl_priv,
+			frg_cnt, (unsigned long long)dma_pointer);
+
+	vxge_hw_fifo_txdl_buffer_set(fifo_hw, dtr, j++, dma_pointer,
+		first_frg_len);
+
+	frag = &skb_shinfo(skb)->frags[0];
+	for (i = 0; i < frg_cnt; i++) {
+		/* ignore 0 length fragment */
+		if (!frag->size)
+			continue;
+
+		dma_pointer =
+			(u64)pci_map_page(fifo->pdev, frag->page,
+				frag->page_offset, frag->size,
+				PCI_DMA_TODEVICE);
+
+		if (unlikely(pci_dma_mapping_error(fifo->pdev, dma_pointer)))
+			goto _exit0;
+		vxge_debug_tx(VXGE_TRACE,
+			"%s: %s:%d frag = %d dma_pointer = 0x%llx",
+				dev->name, __func__, __LINE__, i,
+				(unsigned long long)dma_pointer);
+
+		txdl_priv->dma_buffers[j] = dma_pointer;
+		vxge_hw_fifo_txdl_buffer_set(fifo_hw, dtr, j++, dma_pointer,
+					frag->size);
+		frag += 1;
+	}
+
+	offload_type = vxge_offload_type(skb);
+
+	if (offload_type & (SKB_GSO_TCPV4 | SKB_GSO_TCPV6)) {
+
+		int mss = vxge_tcp_mss(skb);
+		if (mss) {
+			max_mss = dev->mtu + ETH_HLEN -
+				VXGE_HW_TCPIP_HEADER_MAX_SIZE;
+			if (mss > max_mss)
+				mss = max_mss;
+			vxge_debug_tx(VXGE_TRACE,
+				"%s: %s:%d mss = %d",
+				dev->name, __func__, __LINE__, mss);
+			vxge_hw_fifo_txdl_mss_set(dtr, mss);
+		} else {
+			vxge_assert(skb->len <=
+				dev->mtu + VXGE_HW_MAC_HEADER_MAX_SIZE);
+			vxge_assert(0);
+			goto _exit1;
+		}
+	}
+
+	if (skb->ip_summed == CHECKSUM_PARTIAL)
+		vxge_hw_fifo_txdl_cksum_set_bits(dtr,
+					VXGE_HW_FIFO_TXD_TX_CKO_IPV4_EN |
+					VXGE_HW_FIFO_TXD_TX_CKO_TCP_EN |
+					VXGE_HW_FIFO_TXD_TX_CKO_UDP_EN);
+
+	vxge_hw_fifo_txdl_post(fifo_hw, dtr);
+	dev->trans_start = jiffies;
+	spin_unlock_irqrestore(&fifo->tx_lock, flags);
+
+	VXGE_COMPLETE_VPATH_TX(fifo);
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d  Exiting...",
+		dev->name, __func__, __LINE__);
+	return 0;
+
+_exit0:
+	vxge_debug_tx(VXGE_TRACE, "%s: pci_map_page failed", dev->name);
+
+_exit1:
+	j = 0;
+	frag = &skb_shinfo(skb)->frags[0];
+
+	pci_unmap_single(fifo->pdev, txdl_priv->dma_buffers[j++],
+			skb_headlen(skb), PCI_DMA_TODEVICE);
+
+	for (; j < i; j++) {
+		pci_unmap_page(fifo->pdev, txdl_priv->dma_buffers[j],
+			frag->size, PCI_DMA_TODEVICE);
+		frag += 1;
+	}
+
+	vxge_hw_fifo_txdl_free(fifo_hw, dtr);
+_exit2:
+	dev_kfree_skb(skb);
+	spin_unlock_irqrestore(&fifo->tx_lock, flags);
+	VXGE_COMPLETE_VPATH_TX(fifo);
+
+	return 0;
+}
+
+/*
+ * vxge_rx_term
+ *
+ * Function will be called by hw function to abort all outstanding receive
+ * descriptors.
+ */
+static void
+vxge_rx_term(void *dtrh, enum vxge_hw_rxd_state state, void *userdata)
+{
+	struct vxge_ring *ring = (struct vxge_ring *)userdata;
+	struct vxge_rx_priv *rx_priv =
+		vxge_hw_ring_rxd_private_get(dtrh);
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+			ring->ndev->name, __func__, __LINE__);
+	if (state != VXGE_HW_RXD_STATE_POSTED)
+		return;
+
+	pci_unmap_single(ring->pdev, rx_priv->data_dma,
+		rx_priv->data_size, PCI_DMA_FROMDEVICE);
+
+	dev_kfree_skb(rx_priv->skb);
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d  Exiting...",
+		ring->ndev->name, __func__, __LINE__);
+}
+
+/*
+ * vxge_tx_term
+ *
+ * Function will be called to abort all outstanding tx descriptors
+ */
+static void
+vxge_tx_term(void *dtrh, enum vxge_hw_txdl_state state, void *userdata)
+{
+	struct vxge_fifo *fifo = (struct vxge_fifo *)userdata;
+	skb_frag_t *frag;
+	int i = 0, j, frg_cnt;
+	struct vxge_tx_priv *txd_priv = vxge_hw_fifo_txdl_private_get(dtrh);
+	struct sk_buff *skb = txd_priv->skb;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	if (state != VXGE_HW_TXDL_STATE_POSTED)
+		return;
+
+	/* check skb validity */
+	vxge_assert(skb);
+	frg_cnt = skb_shinfo(skb)->nr_frags;
+	frag = &skb_shinfo(skb)->frags[0];
+
+	/*  for unfragmented skb */
+	pci_unmap_single(fifo->pdev, txd_priv->dma_buffers[i++],
+		skb_headlen(skb), PCI_DMA_TODEVICE);
+
+	for (j = 0; j < frg_cnt; j++) {
+		pci_unmap_page(fifo->pdev, txd_priv->dma_buffers[i++],
+			       frag->size, PCI_DMA_TODEVICE);
+		frag += 1;
+	}
+
+	dev_kfree_skb(skb);
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d  Exiting...", __func__, __LINE__);
+}
+
+/**
+ * vxge_set_multicast
+ * @dev: pointer to the device structure
+ *
+ * Entry point for multicast address enable/disable
+ * This function is a driver entry point which gets called by the kernel
+ * whenever multicast addresses must be enabled/disabled. This also gets
+ * called to set/reset promiscuous mode. Depending on the deivce flag, we
+ * determine, if multicast address must be enabled or if promiscuous mode
+ * is to be disabled etc.
+ */
+static void vxge_set_multicast(struct net_device *dev)
+{
+	struct dev_mc_list *mclist;
+	struct vxgedev *vdev;
+	int i, mcast_cnt = 0;
+	struct __vxge_hw_device  *hldev;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct macInfo mac_info;
+	int vpath_idx = 0;
+	struct vxge_mac_addrs *mac_entry;
+	struct list_head *list_head;
+	struct list_head *entry, *next;
+	u8 *mac_address = NULL;
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d", __func__, __LINE__);
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+	hldev = (struct __vxge_hw_device  *)vdev->devh;
+
+	if (unlikely(!is_vxge_card_up(vdev)))
+		return;
+
+	if ((dev->flags & IFF_ALLMULTI) && (!vdev->all_multi_flg)) {
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			vxge_assert(vdev->vpaths[i].is_open);
+			status = vxge_hw_vpath_mcast_enable(
+						vdev->vpaths[i].handle);
+			vdev->all_multi_flg = 1;
+		}
+	} else if ((dev->flags & IFF_ALLMULTI) && (vdev->all_multi_flg)) {
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			vxge_assert(vdev->vpaths[i].is_open);
+			status = vxge_hw_vpath_mcast_disable(
+						vdev->vpaths[i].handle);
+			vdev->all_multi_flg = 1;
+		}
+	}
+
+	if (status != VXGE_HW_OK)
+		vxge_debug_init(VXGE_ERR,
+			"failed to %s multicast, status %d",
+			dev->flags & IFF_ALLMULTI ?
+			"enable" : "disable", status);
+
+	if (!vdev->config.addr_learn_en) {
+		if (dev->flags & IFF_PROMISC) {
+			for (i = 0; i < vdev->no_of_vpath; i++) {
+				vxge_assert(vdev->vpaths[i].is_open);
+				status = vxge_hw_vpath_promisc_enable(
+						vdev->vpaths[i].handle);
+			}
+		} else {
+			for (i = 0; i < vdev->no_of_vpath; i++) {
+				vxge_assert(vdev->vpaths[i].is_open);
+				status = vxge_hw_vpath_promisc_disable(
+						vdev->vpaths[i].handle);
+			}
+		}
+	}
+
+	memset(&mac_info, 0, sizeof(struct macInfo));
+	/* Update individual M_CAST address list */
+	if ((!vdev->all_multi_flg) && dev->mc_count) {
+
+		mcast_cnt = vdev->vpaths[0].mcast_addr_cnt;
+		list_head = &vdev->vpaths[0].mac_addr_list;
+		if ((dev->mc_count +
+			(vdev->vpaths[0].mac_addr_cnt - mcast_cnt)) >
+				vdev->vpaths[0].max_mac_addr_cnt)
+			goto _set_all_mcast;
+
+		/* Delete previous MC's */
+		for (i = 0; i < mcast_cnt; i++) {
+			if (!list_empty(list_head))
+				mac_entry = (struct vxge_mac_addrs *)
+					list_first_entry(list_head,
+						struct vxge_mac_addrs,
+						item);
+
+			list_for_each_safe(entry, next, list_head) {
+
+				mac_entry = (struct vxge_mac_addrs *) entry;
+				/* Copy the mac address to delete */
+				mac_address = (u8 *)&mac_entry->macaddr;
+				memcpy(mac_info.macaddr, mac_address, ETH_ALEN);
+
+				/* Is this a multicast address */
+				if (0x01 & mac_info.macaddr[0]) {
+					for (vpath_idx = 0; vpath_idx <
+						vdev->no_of_vpath;
+						vpath_idx++) {
+						mac_info.vpath_no = vpath_idx;
+						status = vxge_del_mac_addr(
+								vdev,
+								&mac_info);
+					}
+				}
+			}
+		}
+
+		/* Add new ones */
+		for (i = 0, mclist = dev->mc_list; i < dev->mc_count;
+			i++, mclist = mclist->next) {
+
+			memcpy(mac_info.macaddr, mclist->dmi_addr, ETH_ALEN);
+			for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath;
+					vpath_idx++) {
+				mac_info.vpath_no = vpath_idx;
+				mac_info.state = VXGE_LL_MAC_ADDR_IN_DA_TABLE;
+				status = vxge_add_mac_addr(vdev, &mac_info);
+				if (status != VXGE_HW_OK) {
+					vxge_debug_init(VXGE_ERR,
+						"%s:%d Setting individual"
+						"multicast address failed",
+						__func__, __LINE__);
+					goto _set_all_mcast;
+				}
+			}
+		}
+
+		return;
+_set_all_mcast:
+		mcast_cnt = vdev->vpaths[0].mcast_addr_cnt;
+		/* Delete previous MC's */
+		for (i = 0; i < mcast_cnt; i++) {
+
+			list_for_each_safe(entry, next, list_head) {
+
+				mac_entry = (struct vxge_mac_addrs *) entry;
+				/* Copy the mac address to delete */
+				mac_address = (u8 *)&mac_entry->macaddr;
+				memcpy(mac_info.macaddr, mac_address, ETH_ALEN);
+
+				/* Is this a multicast address */
+				if (0x01 & mac_info.macaddr[0])
+					break;
+			}
+
+			for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath;
+					vpath_idx++) {
+				mac_info.vpath_no = vpath_idx;
+				status = vxge_del_mac_addr(vdev, &mac_info);
+			}
+		}
+
+		/* Enable all multicast */
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			vxge_assert(vdev->vpaths[i].is_open);
+			status = vxge_hw_vpath_mcast_enable(
+						vdev->vpaths[i].handle);
+			if (status != VXGE_HW_OK) {
+				vxge_debug_init(VXGE_ERR,
+					"%s:%d Enabling all multicasts failed",
+					 __func__, __LINE__);
+			}
+			vdev->all_multi_flg = 1;
+		}
+		dev->flags |= IFF_ALLMULTI;
+	}
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d  Exiting...", __func__, __LINE__);
+}
+
+/**
+ * vxge_set_mac_addr
+ * @dev: pointer to the device structure
+ *
+ * Update entry "0" (default MAC addr)
+ */
+static int vxge_set_mac_addr(struct net_device *dev, void *p)
+{
+	struct sockaddr *addr = p;
+	struct vxgedev *vdev;
+	struct __vxge_hw_device  *hldev;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct macInfo mac_info_new, mac_info_old;
+	int vpath_idx = 0;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+	hldev = vdev->devh;
+
+	if (!is_valid_ether_addr(addr->sa_data))
+		return -EINVAL;
+
+	memset(&mac_info_new, 0, sizeof(struct macInfo));
+	memset(&mac_info_old, 0, sizeof(struct macInfo));
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d  Exiting...",
+		__func__, __LINE__);
+
+	/* Get the old address */
+	memcpy(mac_info_old.macaddr, dev->dev_addr, dev->addr_len);
+
+	/* Copy the new address */
+	memcpy(mac_info_new.macaddr, addr->sa_data, dev->addr_len);
+
+	/* First delete the old mac address from all the vpaths
+	as we can't specify the index while adding new mac address */
+	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
+		struct vxge_vpath *vpath = &vdev->vpaths[vpath_idx];
+		if (!vpath->is_open) {
+			/* This can happen when this interface is added/removed
+			to the bonding interface. Delete this station address
+			from the linked list */
+			vxge_mac_list_del(vpath, &mac_info_old);
+
+			/* Add this new address to the linked list
+			for later restoring */
+			vxge_mac_list_add(vpath, &mac_info_new);
+
+			continue;
+		}
+		/* Delete the station address */
+		mac_info_old.vpath_no = vpath_idx;
+		status = vxge_del_mac_addr(vdev, &mac_info_old);
+	}
+
+	if (unlikely(!is_vxge_card_up(vdev))) {
+		memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+		return VXGE_HW_OK;
+	}
+
+	/* Set this mac address to all the vpaths */
+	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++) {
+		mac_info_new.vpath_no = vpath_idx;
+		mac_info_new.state = VXGE_LL_MAC_ADDR_IN_DA_TABLE;
+		status = vxge_add_mac_addr(vdev, &mac_info_new);
+		if (status != VXGE_HW_OK)
+			return -EINVAL;
+	}
+
+	memcpy(dev->dev_addr, addr->sa_data, dev->addr_len);
+
+	return status;
+}
+
+/*
+ * vxge_vpath_intr_enable
+ * @vdev: pointer to vdev
+ * @vp_id: vpath for which to enable the interrupts
+ *
+ * Enables the interrupts for the vpath
+*/
+void vxge_vpath_intr_enable(struct vxgedev *vdev, int vp_id)
+{
+	struct vxge_vpath *vpath = &vdev->vpaths[vp_id];
+	int msix_id, alarm_msix_id;
+	int tim_msix_id[4] = {[0 ...3] = 0};
+
+	vxge_hw_vpath_intr_enable(vpath->handle);
+
+	if (vdev->config.intr_type == INTA)
+		vxge_hw_vpath_inta_unmask_tx_rx(vpath->handle);
+	else {
+		msix_id = vp_id * VXGE_HW_VPATH_MSIX_ACTIVE;
+		alarm_msix_id =
+			VXGE_HW_VPATH_MSIX_ACTIVE * vdev->no_of_vpath - 2;
+
+		tim_msix_id[0] = msix_id;
+		tim_msix_id[1] = msix_id + 1;
+		vxge_hw_vpath_msix_set(vpath->handle, tim_msix_id,
+			alarm_msix_id);
+
+		vxge_hw_vpath_msix_unmask(vpath->handle, msix_id);
+		vxge_hw_vpath_msix_unmask(vpath->handle, msix_id + 1);
+
+		/* enable the alarm vector */
+		vxge_hw_vpath_msix_unmask(vpath->handle, alarm_msix_id);
+	}
+}
+
+/*
+ * vxge_vpath_intr_disable
+ * @vdev: pointer to vdev
+ * @vp_id: vpath for which to disable the interrupts
+ *
+ * Disables the interrupts for the vpath
+*/
+void vxge_vpath_intr_disable(struct vxgedev *vdev, int vp_id)
+{
+	struct vxge_vpath *vpath = &vdev->vpaths[vp_id];
+	int msix_id;
+
+	vxge_hw_vpath_intr_disable(vpath->handle);
+
+	if (vdev->config.intr_type == INTA)
+		vxge_hw_vpath_inta_mask_tx_rx(vpath->handle);
+	else {
+		msix_id = vp_id * VXGE_HW_VPATH_MSIX_ACTIVE;
+		vxge_hw_vpath_msix_mask(vpath->handle, msix_id);
+		vxge_hw_vpath_msix_mask(vpath->handle, msix_id + 1);
+
+		/* disable the alarm vector */
+		msix_id = VXGE_HW_VPATH_MSIX_ACTIVE * vdev->no_of_vpath - 2;
+		vxge_hw_vpath_msix_mask(vpath->handle, msix_id);
+	}
+}
+
+/*
+ * vxge_reset_vpath
+ * @vdev: pointer to vdev
+ * @vp_id: vpath to reset
+ *
+ * Resets the vpath
+*/
+static int vxge_reset_vpath(struct vxgedev *vdev, int vp_id)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	int ret = 0;
+
+	/* check if device is down already */
+	if (unlikely(!is_vxge_card_up(vdev)))
+		return 0;
+
+	/* is device reset already scheduled */
+	if (test_bit(__VXGE_STATE_RESET_CARD, &vdev->state))
+		return 0;
+
+	if (vdev->vpaths[vp_id].handle) {
+		if (vxge_hw_vpath_reset(vdev->vpaths[vp_id].handle)
+				== VXGE_HW_OK) {
+			if (is_vxge_card_up(vdev) &&
+				vxge_hw_vpath_recover_from_reset(
+					vdev->vpaths[vp_id].handle)
+					!= VXGE_HW_OK) {
+				vxge_debug_init(VXGE_ERR,
+					"vxge_hw_vpath_recover_from_reset"
+					"failed for vpath:%d", vp_id);
+				return status;
+			}
+		} else {
+			vxge_debug_init(VXGE_ERR,
+				"vxge_hw_vpath_reset failed for"
+				"vpath:%d", vp_id);
+				return status;
+		}
+	} else
+		return VXGE_HW_FAIL;
+
+	vxge_restore_vpath_mac_addr(&vdev->vpaths[vp_id]);
+	vxge_restore_vpath_vid_table(&vdev->vpaths[vp_id]);
+
+	/* Enable all broadcast */
+	vxge_hw_vpath_bcast_enable(vdev->vpaths[vp_id].handle);
+
+	/* Enable the interrupts */
+	vxge_vpath_intr_enable(vdev, vp_id);
+
+	smp_wmb();
+
+	/* Enable the flow of traffic through the vpath */
+	vxge_hw_vpath_enable(vdev->vpaths[vp_id].handle);
+
+	smp_wmb();
+	vxge_hw_vpath_rx_doorbell_init(vdev->vpaths[vp_id].handle);
+	vdev->vpaths[vp_id].ring.last_status = VXGE_HW_OK;
+
+	/* Vpath reset done */
+	clear_bit(vp_id, &vdev->vp_reset);
+
+	/* Start the vpath queue */
+	vxge_wake_tx_queue(&vdev->vpaths[vp_id].fifo, NULL);
+
+	return ret;
+}
+
+static int do_vxge_reset(struct vxgedev *vdev, int event)
+{
+	enum vxge_hw_status status;
+	int ret = 0, vp_id, i;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_START_RESET)) {
+		/* check if device is down already */
+		if (unlikely(!is_vxge_card_up(vdev)))
+			return 0;
+
+		/* is reset already scheduled */
+		if (test_and_set_bit(__VXGE_STATE_RESET_CARD, &vdev->state))
+			return 0;
+	}
+
+	if (event == VXGE_LL_FULL_RESET) {
+		/* wait for all the vpath reset to complete */
+		for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
+			while (test_bit(vp_id, &vdev->vp_reset))
+				msleep(50);
+		}
+
+		/* if execution mode is set to debug, don't reset the adapter */
+		if (unlikely(vdev->exec_mode)) {
+			vxge_debug_init(VXGE_ERR,
+				"%s: execution mode is debug, returning..",
+				vdev->ndev->name);
+		clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+		vxge_stop_all_tx_queue(vdev);
+		return 0;
+		}
+	}
+
+	if (event == VXGE_LL_FULL_RESET) {
+		vxge_hw_device_intr_disable(vdev->devh);
+
+		switch (vdev->cric_err_event) {
+		case VXGE_HW_EVENT_UNKNOWN:
+			vxge_stop_all_tx_queue(vdev);
+			vxge_debug_init(VXGE_ERR,
+				"fatal: %s: Disabling device due to"
+				"unknown error",
+				vdev->ndev->name);
+			ret = -EPERM;
+			goto out;
+		case VXGE_HW_EVENT_RESET_START:
+			break;
+		case VXGE_HW_EVENT_RESET_COMPLETE:
+		case VXGE_HW_EVENT_LINK_DOWN:
+		case VXGE_HW_EVENT_LINK_UP:
+		case VXGE_HW_EVENT_ALARM_CLEARED:
+		case VXGE_HW_EVENT_ECCERR:
+		case VXGE_HW_EVENT_MRPCIM_ECCERR:
+			ret = -EPERM;
+			goto out;
+		case VXGE_HW_EVENT_FIFO_ERR:
+		case VXGE_HW_EVENT_VPATH_ERR:
+			break;
+		case VXGE_HW_EVENT_CRITICAL_ERR:
+			vxge_stop_all_tx_queue(vdev);
+			vxge_debug_init(VXGE_ERR,
+				"fatal: %s: Disabling device due to"
+				"serious error",
+				vdev->ndev->name);
+			/* SOP or device reset required */
+			/* This event is not currently used */
+			ret = -EPERM;
+			goto out;
+		case VXGE_HW_EVENT_SERR:
+			vxge_stop_all_tx_queue(vdev);
+			vxge_debug_init(VXGE_ERR,
+				"fatal: %s: Disabling device due to"
+				"serious error",
+				vdev->ndev->name);
+			ret = -EPERM;
+			goto out;
+		case VXGE_HW_EVENT_SRPCIM_SERR:
+		case VXGE_HW_EVENT_MRPCIM_SERR:
+			ret = -EPERM;
+			goto out;
+		case VXGE_HW_EVENT_SLOT_FREEZE:
+			vxge_stop_all_tx_queue(vdev);
+			vxge_debug_init(VXGE_ERR,
+				"fatal: %s: Disabling device due to"
+				"slot freeze",
+				vdev->ndev->name);
+			ret = -EPERM;
+			goto out;
+		default:
+			break;
+
+		}
+	}
+
+	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_START_RESET))
+		vxge_stop_all_tx_queue(vdev);
+
+	if (event == VXGE_LL_FULL_RESET) {
+		status = vxge_reset_all_vpaths(vdev);
+		if (status != VXGE_HW_OK) {
+			vxge_debug_init(VXGE_ERR,
+				"fatal: %s: can not reset vpaths",
+				vdev->ndev->name);
+			ret = -EPERM;
+			goto out;
+		}
+	}
+
+	if (event == VXGE_LL_COMPL_RESET) {
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			if (vdev->vpaths[i].handle) {
+				if (vxge_hw_vpath_recover_from_reset(
+					vdev->vpaths[i].handle)
+						!= VXGE_HW_OK) {
+					vxge_debug_init(VXGE_ERR,
+						"vxge_hw_vpath_recover_"
+						"from_reset failed for vpath: "
+						"%d", i);
+					ret = -EPERM;
+					goto out;
+				}
+				} else {
+					vxge_debug_init(VXGE_ERR,
+					"vxge_hw_vpath_reset failed for "
+						"vpath:%d", i);
+					ret = -EPERM;
+					goto out;
+				}
+	}
+
+	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_COMPL_RESET)) {
+		/* Reprogram the DA table with populated mac addresses */
+		for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
+			vxge_restore_vpath_mac_addr(&vdev->vpaths[vp_id]);
+			vxge_restore_vpath_vid_table(&vdev->vpaths[vp_id]);
+		}
+
+		/* enable vpath interrupts */
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			vxge_vpath_intr_enable(vdev, i);
+
+		vxge_hw_device_intr_enable(vdev->devh);
+
+		smp_wmb();
+
+		/* Indicate card up */
+		set_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+
+		/* Get the traffic to flow through the vpaths */
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			vxge_hw_vpath_enable(vdev->vpaths[i].handle);
+			smp_wmb();
+			vxge_hw_vpath_rx_doorbell_init(vdev->vpaths[i].handle);
+		}
+
+		vxge_wake_all_tx_queue(vdev);
+	}
+
+out:
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d  Exiting...", __func__, __LINE__);
+
+	/* Indicate reset done */
+	if ((event == VXGE_LL_FULL_RESET) || (event == VXGE_LL_COMPL_RESET))
+		clear_bit(__VXGE_STATE_RESET_CARD, &vdev->state);
+	return ret;
+}
+
+/*
+ * vxge_reset
+ * @vdev: pointer to ll device
+ *
+ * driver may reset the chip on events of serr, eccerr, etc
+ */
+int vxge_reset(struct vxgedev *vdev)
+{
+	do_vxge_reset(vdev, VXGE_LL_FULL_RESET);
+	return 0;
+}
+
+/**
+ * vxge_poll - Receive handler when Receive Polling is used.
+ * @dev: pointer to the device structure.
+ * @budget: Number of packets budgeted to be processed in this iteration.
+ *
+ * This function comes into picture only if Receive side is being handled
+ * through polling (called NAPI in linux). It mostly does what the normal
+ * Rx interrupt handler does in terms of descriptor and packet processing
+ * but not in an interrupt context. Also it will process a specified number
+ * of packets at most in one iteration. This value is passed down by the
+ * kernel as the function argument 'budget'.
+ */
+static int vxge_poll_msix(struct napi_struct *napi, int budget)
+{
+	struct vxge_ring *ring =
+		container_of(napi, struct vxge_ring, napi);
+	int budget_org = budget;
+	ring->budget = budget;
+
+	vxge_hw_vpath_poll_rx(ring->handle);
+
+	if (ring->pkts_processed < budget_org) {
+		napi_complete(napi);
+		/* Re enable the Rx interrupts for the vpath */
+		vxge_hw_channel_msix_unmask(
+				(struct __vxge_hw_channel *)ring->handle,
+				ring->rx_vector_no);
+	}
+
+	return ring->pkts_processed;
+}
+
+static int vxge_poll_inta(struct napi_struct *napi, int budget)
+{
+	struct vxgedev *vdev = container_of(napi, struct vxgedev, napi);
+	int pkts_processed = 0;
+	int i;
+	int budget_org = budget;
+	struct vxge_ring *ring;
+
+	struct __vxge_hw_device  *hldev = (struct __vxge_hw_device *)
+		pci_get_drvdata(vdev->pdev);
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		ring = &vdev->vpaths[i].ring;
+		ring->budget = budget;
+		vxge_hw_vpath_poll_rx(ring->handle);
+		pkts_processed += ring->pkts_processed;
+		budget -= ring->pkts_processed;
+		if (budget <= 0)
+			break;
+	}
+
+	VXGE_COMPLETE_ALL_TX(vdev);
+
+	if (pkts_processed < budget_org) {
+		napi_complete(napi);
+		/* Re enable the Rx interrupts for the ring */
+		vxge_hw_device_unmask_all(hldev);
+		vxge_hw_device_flush_io(hldev);
+	}
+
+	return pkts_processed;
+}
+
+#ifdef CONFIG_NET_POLL_CONTROLLER
+/**
+ * vxge_netpoll - netpoll event handler entry point
+ * @dev : pointer to the device structure.
+ * Description:
+ *      This function will be called by upper layer to check for events on the
+ * interface in situations where interrupts are disabled. It is used for
+ * specific in-kernel networking tasks, such as remote consoles and kernel
+ * debugging over the network (example netdump in RedHat).
+ */
+static void vxge_netpoll(struct net_device *dev)
+{
+	struct __vxge_hw_device  *hldev;
+	struct vxgedev *vdev;
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+	hldev = (struct __vxge_hw_device  *)pci_get_drvdata(vdev->pdev);
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	if (pci_channel_offline(vdev->pdev))
+		return;
+
+	disable_irq(dev->irq);
+	vxge_hw_device_clear_tx_rx(hldev);
+
+	vxge_hw_device_clear_tx_rx(hldev);
+	VXGE_COMPLETE_ALL_RX(vdev);
+	VXGE_COMPLETE_ALL_TX(vdev);
+
+	enable_irq(dev->irq);
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d  Exiting...", __func__, __LINE__);
+	return;
+}
+#endif
+
+/* RTH configuration */
+static enum vxge_hw_status vxge_rth_configure(struct vxgedev *vdev)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_hw_rth_hash_types hash_types;
+	u8 itable[256] = {0}; /* indirection table */
+	u8 mtable[256] = {0}; /* CPU to vpath mapping  */
+	int index;
+
+	/*
+	 * Filling
+	 * 	- itable with bucket numbers
+	 * 	- mtable with bucket-to-vpath mapping
+	 */
+	for (index = 0; index < (1 << vdev->config.rth_bkt_sz); index++) {
+		itable[index] = index;
+		mtable[index] = index % vdev->no_of_vpath;
+	}
+
+	/* Fill RTH hash types */
+	hash_types.hash_type_tcpipv4_en   = vdev->config.rth_hash_type_tcpipv4;
+	hash_types.hash_type_ipv4_en      = vdev->config.rth_hash_type_ipv4;
+	hash_types.hash_type_tcpipv6_en   = vdev->config.rth_hash_type_tcpipv6;
+	hash_types.hash_type_ipv6_en      = vdev->config.rth_hash_type_ipv6;
+	hash_types.hash_type_tcpipv6ex_en =
+					vdev->config.rth_hash_type_tcpipv6ex;
+	hash_types.hash_type_ipv6ex_en    = vdev->config.rth_hash_type_ipv6ex;
+
+	/* set indirection table, bucket-to-vpath mapping */
+	status = vxge_hw_vpath_rts_rth_itable_set(vdev->vp_handles,
+						vdev->no_of_vpath,
+						mtable, itable,
+						vdev->config.rth_bkt_sz);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"RTH indirection table configuration failed "
+			"for vpath:%d", vdev->vpaths[0].device_id);
+		return status;
+	}
+
+	/*
+	* Because the itable_set() method uses the active_table field
+	* for the target virtual path the RTH config should be updated
+	* for all VPATHs. The h/w only uses the lowest numbered VPATH
+	* when steering frames.
+	*/
+	 for (index = 0; index < vdev->no_of_vpath; index++) {
+		status = vxge_hw_vpath_rts_rth_set(
+				vdev->vpaths[index].handle,
+				vdev->config.rth_algorithm,
+				&hash_types,
+				vdev->config.rth_bkt_sz);
+
+		 if (status != VXGE_HW_OK) {
+			vxge_debug_init(VXGE_ERR,
+				"RTH configuration failed for vpath:%d",
+				vdev->vpaths[index].device_id);
+			return status;
+		 }
+	 }
+
+	return status;
+}
+
+int vxge_mac_list_add(struct vxge_vpath *vpath, struct macInfo *mac)
+{
+	struct vxge_mac_addrs *new_mac_entry;
+	u8 *mac_address = NULL;
+
+	if (vpath->mac_addr_cnt >= VXGE_MAX_LEARN_MAC_ADDR_CNT)
+		return TRUE;
+
+	new_mac_entry = kzalloc(sizeof(struct vxge_mac_addrs), GFP_ATOMIC);
+	if (!new_mac_entry) {
+		vxge_debug_mem(VXGE_ERR,
+			"%s: memory allocation failed",
+			VXGE_DRIVER_NAME);
+		return FALSE;
+	}
+
+	list_add(&new_mac_entry->item, &vpath->mac_addr_list);
+
+	/* Copy the new mac address to the list */
+	mac_address = (u8 *)&new_mac_entry->macaddr;
+	memcpy(mac_address, mac->macaddr, ETH_ALEN);
+
+	new_mac_entry->state = mac->state;
+	vpath->mac_addr_cnt++;
+
+	/* Is this a multicast address */
+	if (0x01 & mac->macaddr[0])
+		vpath->mcast_addr_cnt++;
+
+	return TRUE;
+}
+
+/* Add a mac address to DA table */
+enum vxge_hw_status vxge_add_mac_addr(struct vxgedev *vdev, struct macInfo *mac)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_vpath *vpath;
+	enum vxge_hw_vpath_mac_addr_add_mode duplicate_mode;
+
+	if (0x01 & mac->macaddr[0]) /* multicast address */
+		duplicate_mode = VXGE_HW_VPATH_MAC_ADDR_ADD_DUPLICATE;
+	else
+		duplicate_mode = VXGE_HW_VPATH_MAC_ADDR_REPLACE_DUPLICATE;
+
+	vpath = &vdev->vpaths[mac->vpath_no];
+	status = vxge_hw_vpath_mac_addr_add(vpath->handle, mac->macaddr,
+						mac->macmask, duplicate_mode);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"DA config add entry failed for vpath:%d",
+			vpath->device_id);
+	} else
+		if (FALSE == vxge_mac_list_add(vpath, mac))
+			status = -EPERM;
+
+	return status;
+}
+
+int vxge_mac_list_del(struct vxge_vpath *vpath, struct macInfo *mac)
+{
+	struct list_head *entry, *next;
+	u64 del_mac = 0;
+	u8 *mac_address = (u8 *) (&del_mac);
+
+	/* Copy the mac address to delete from the list */
+	memcpy(mac_address, mac->macaddr, ETH_ALEN);
+
+	list_for_each_safe(entry, next, &vpath->mac_addr_list) {
+		if (((struct vxge_mac_addrs *)entry)->macaddr == del_mac) {
+			list_del(entry);
+			kfree((struct vxge_mac_addrs *)entry);
+			vpath->mac_addr_cnt--;
+
+			/* Is this a multicast address */
+			if (0x01 & mac->macaddr[0])
+				vpath->mcast_addr_cnt--;
+			return TRUE;
+		}
+	}
+
+	return FALSE;
+}
+/* delete a mac address from DA table */
+enum vxge_hw_status vxge_del_mac_addr(struct vxgedev *vdev, struct macInfo *mac)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_vpath *vpath;
+
+	vpath = &vdev->vpaths[mac->vpath_no];
+	status = vxge_hw_vpath_mac_addr_delete(vpath->handle, mac->macaddr,
+						mac->macmask);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"DA config delete entry failed for vpath:%d",
+			vpath->device_id);
+	} else
+		vxge_mac_list_del(vpath, mac);
+	return status;
+}
+
+/* list all mac addresses from DA table */
+enum vxge_hw_status
+static vxge_search_mac_addr_in_da_table(struct vxge_vpath *vpath,
+					struct macInfo *mac)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	unsigned char macmask[ETH_ALEN];
+	unsigned char macaddr[ETH_ALEN];
+
+	status = vxge_hw_vpath_mac_addr_get(vpath->handle,
+				macaddr, macmask);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"DA config list entry failed for vpath:%d",
+			vpath->device_id);
+		return status;
+	}
+
+	while (memcmp(mac->macaddr, macaddr, ETH_ALEN)) {
+
+		status = vxge_hw_vpath_mac_addr_get_next(vpath->handle,
+				macaddr, macmask);
+		if (status != VXGE_HW_OK)
+			break;
+	}
+
+	return status;
+}
+
+/* Store all vlan ids from the list to the vid table */
+enum vxge_hw_status vxge_restore_vpath_vid_table(struct vxge_vpath *vpath)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxgedev *vdev = vpath->vdev;
+	u16 vid;
+
+	if (vdev->vlgrp && vpath->is_open) {
+
+		for (vid = 0; vid < VLAN_GROUP_ARRAY_LEN; vid++) {
+			if (!vlan_group_get_device(vdev->vlgrp, vid))
+				continue;
+			/* Add these vlan to the vid table */
+			status = vxge_hw_vpath_vid_add(vpath->handle, vid);
+		}
+	}
+
+	return status;
+}
+
+/* Store all mac addresses from the list to the DA table */
+enum vxge_hw_status vxge_restore_vpath_mac_addr(struct vxge_vpath *vpath)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct macInfo mac_info;
+	u8 *mac_address = NULL;
+	struct list_head *entry, *next;
+
+	memset(&mac_info, 0, sizeof(struct macInfo));
+
+	if (vpath->is_open) {
+
+		list_for_each_safe(entry, next, &vpath->mac_addr_list) {
+			mac_address =
+				(u8 *)&
+				((struct vxge_mac_addrs *)entry)->macaddr;
+			memcpy(mac_info.macaddr, mac_address, ETH_ALEN);
+			((struct vxge_mac_addrs *)entry)->state =
+				VXGE_LL_MAC_ADDR_IN_DA_TABLE;
+			/* does this mac address already exist in da table? */
+			status = vxge_search_mac_addr_in_da_table(vpath,
+				&mac_info);
+			if (status != VXGE_HW_OK) {
+				/* Add this mac address to the DA table */
+				status = vxge_hw_vpath_mac_addr_add(
+					vpath->handle, mac_info.macaddr,
+					mac_info.macmask,
+				    VXGE_HW_VPATH_MAC_ADDR_ADD_DUPLICATE);
+				if (status != VXGE_HW_OK) {
+					vxge_debug_init(VXGE_ERR,
+					    "DA add entry failed for vpath:%d",
+					    vpath->device_id);
+					((struct vxge_mac_addrs *)entry)->state
+						= VXGE_LL_MAC_ADDR_IN_LIST;
+				}
+			}
+		}
+	}
+
+	return status;
+}
+
+/* reset vpaths */
+enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev)
+{
+	int i;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	for (i = 0; i < vdev->no_of_vpath; i++)
+		if (vdev->vpaths[i].handle) {
+			if (vxge_hw_vpath_reset(vdev->vpaths[i].handle)
+					== VXGE_HW_OK) {
+				if (is_vxge_card_up(vdev) &&
+					vxge_hw_vpath_recover_from_reset(
+						vdev->vpaths[i].handle)
+						!= VXGE_HW_OK) {
+					vxge_debug_init(VXGE_ERR,
+						"vxge_hw_vpath_recover_"
+						"from_reset failed for vpath: "
+						"%d", i);
+					return status;
+				}
+			} else {
+				vxge_debug_init(VXGE_ERR,
+					"vxge_hw_vpath_reset failed for "
+					"vpath:%d", i);
+					return status;
+			}
+		}
+	return status;
+}
+
+/* close vpaths */
+void vxge_close_vpaths(struct vxgedev *vdev, int index)
+{
+	int i;
+	for (i = index; i < vdev->no_of_vpath; i++) {
+		if (vdev->vpaths[i].handle && vdev->vpaths[i].is_open) {
+			vxge_hw_vpath_close(vdev->vpaths[i].handle);
+			vdev->stats.vpaths_open--;
+		}
+		vdev->vpaths[i].is_open = 0;
+		vdev->vpaths[i].handle  = NULL;
+	}
+}
+
+/* open vpaths */
+int vxge_open_vpaths(struct vxgedev *vdev)
+{
+	enum vxge_hw_status status;
+	int i;
+	u32 vp_id = 0;
+	struct vxge_hw_vpath_attr attr;
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		vxge_assert(vdev->vpaths[i].is_configured);
+		attr.vp_id = vdev->vpaths[i].device_id;
+		attr.fifo_attr.callback = vxge_xmit_compl;
+		attr.fifo_attr.txdl_term = vxge_tx_term;
+		attr.fifo_attr.per_txdl_space = sizeof(struct vxge_tx_priv);
+		attr.fifo_attr.userdata = (void *)&vdev->vpaths[i].fifo;
+
+		attr.ring_attr.callback = vxge_rx_1b_compl;
+		attr.ring_attr.rxd_init = vxge_rx_initial_replenish;
+		attr.ring_attr.rxd_term = vxge_rx_term;
+		attr.ring_attr.per_rxd_space = sizeof(struct vxge_rx_priv);
+		attr.ring_attr.userdata = (void *)&vdev->vpaths[i].ring;
+
+		vdev->vpaths[i].ring.ndev = vdev->ndev;
+		vdev->vpaths[i].ring.pdev = vdev->pdev;
+		status = vxge_hw_vpath_open(vdev->devh, &attr,
+				&(vdev->vpaths[i].handle));
+		if (status == VXGE_HW_OK) {
+			vdev->vpaths[i].fifo.handle =
+			    (struct __vxge_hw_fifo *)attr.fifo_attr.userdata;
+			vdev->vpaths[i].ring.handle =
+			    (struct __vxge_hw_ring *)attr.ring_attr.userdata;
+			vdev->vpaths[i].fifo.tx_steering_type =
+				vdev->config.tx_steering_type;
+			vdev->vpaths[i].fifo.ndev = vdev->ndev;
+			vdev->vpaths[i].fifo.pdev = vdev->pdev;
+			vdev->vpaths[i].fifo.indicate_max_pkts =
+				vdev->config.fifo_indicate_max_pkts;
+			vdev->vpaths[i].ring.rx_vector_no = 0;
+			vdev->vpaths[i].ring.rx_csum = vdev->rx_csum;
+			vdev->vpaths[i].is_open = 1;
+			vdev->vp_handles[i] = vdev->vpaths[i].handle;
+			vdev->vpaths[i].ring.gro_enable =
+						vdev->config.gro_enable;
+			vdev->vpaths[i].ring.vlan_tag_strip =
+						vdev->vlan_tag_strip;
+			vdev->stats.vpaths_open++;
+		} else {
+			vdev->stats.vpath_open_fail++;
+			vxge_debug_init(VXGE_ERR,
+				"%s: vpath: %d failed to open "
+				"with status: %d",
+			    vdev->ndev->name, vdev->vpaths[i].device_id,
+				status);
+			vxge_close_vpaths(vdev, 0);
+			return -EPERM;
+		}
+
+		vp_id =
+		  ((struct __vxge_hw_vpath_handle *)vdev->vpaths[i].handle)->
+		  vpath->vp_id;
+		vdev->vpaths_deployed |= vxge_mBIT(vp_id);
+	}
+	return VXGE_HW_OK;
+}
+
+/*
+ *  vxge_isr_napi
+ *  @irq: the irq of the device.
+ *  @dev_id: a void pointer to the hldev structure of the Titan device
+ *  @ptregs: pointer to the registers pushed on the stack.
+ *
+ *  This function is the ISR handler of the device when napi is enabled. It
+ *  identifies the reason for the interrupt and calls the relevant service
+ *  routines.
+ */
+static irqreturn_t vxge_isr_napi(int irq, void *dev_id)
+{
+	struct __vxge_hw_device  *hldev = (struct __vxge_hw_device  *)dev_id;
+	struct vxgedev *vdev;
+	struct net_device *dev;
+	u64 reason;
+	enum vxge_hw_status status;
+
+	vxge_debug_intr(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	dev = hldev->ndev;
+	vdev = netdev_priv(dev);
+
+	if (pci_channel_offline(vdev->pdev))
+		return IRQ_NONE;
+
+	if (unlikely(!is_vxge_card_up(vdev)))
+		return IRQ_NONE;
+
+	status = vxge_hw_device_begin_irq(hldev, vdev->exec_mode,
+			&reason);
+	if (status == VXGE_HW_OK) {
+		vxge_hw_device_mask_all(hldev);
+
+		if (reason &
+			VXGE_HW_TITAN_GENERAL_INT_STATUS_VPATH_TRAFFIC_INT(
+			vdev->vpaths_deployed >>
+			(64 - VXGE_HW_MAX_VIRTUAL_PATHS))) {
+
+			vxge_hw_device_clear_tx_rx(hldev);
+			napi_schedule(&vdev->napi);
+			vxge_debug_intr(VXGE_TRACE,
+				"%s:%d  Exiting...", __func__, __LINE__);
+			return IRQ_HANDLED;
+		} else
+			vxge_hw_device_unmask_all(hldev);
+	} else if (unlikely((status == VXGE_HW_ERR_VPATH) ||
+		(status == VXGE_HW_ERR_CRITICAL) ||
+		(status == VXGE_HW_ERR_FIFO))) {
+		vxge_hw_device_mask_all(hldev);
+		vxge_hw_device_flush_io(hldev);
+		return IRQ_HANDLED;
+	} else if (unlikely(status == VXGE_HW_ERR_SLOT_FREEZE))
+		return IRQ_HANDLED;
+
+	vxge_debug_intr(VXGE_TRACE, "%s:%d  Exiting...", __func__, __LINE__);
+	return IRQ_NONE;
+}
+
+#ifdef CONFIG_PCI_MSI
+
+static irqreturn_t
+vxge_tx_msix_handle(int irq, void *dev_id)
+{
+	struct vxge_fifo *fifo = (struct vxge_fifo *)dev_id;
+
+	VXGE_COMPLETE_VPATH_TX(fifo);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t
+vxge_rx_msix_napi_handle(int irq, void *dev_id)
+{
+	struct vxge_ring *ring = (struct vxge_ring *)dev_id;
+
+	/* MSIX_IDX for Rx is 1 */
+	vxge_hw_channel_msix_mask((struct __vxge_hw_channel *)ring->handle,
+					ring->rx_vector_no);
+
+	napi_schedule(&ring->napi);
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t
+vxge_alarm_msix_handle(int irq, void *dev_id)
+{
+	int i;
+	enum vxge_hw_status status;
+	struct vxge_vpath *vpath = (struct vxge_vpath *)dev_id;
+	struct vxgedev *vdev = vpath->vdev;
+	int alarm_msix_id =
+		VXGE_HW_VPATH_MSIX_ACTIVE * vdev->no_of_vpath - 2;
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		vxge_hw_vpath_msix_mask(vdev->vpaths[i].handle,
+			alarm_msix_id);
+
+		status = vxge_hw_vpath_alarm_process(vdev->vpaths[i].handle,
+			vdev->exec_mode);
+		if (status == VXGE_HW_OK) {
+
+			vxge_hw_vpath_msix_unmask(vdev->vpaths[i].handle,
+				alarm_msix_id);
+			continue;
+		}
+		vxge_debug_intr(VXGE_ERR,
+			"%s: vxge_hw_vpath_alarm_process failed %x ",
+			VXGE_DRIVER_NAME, status);
+	}
+	return IRQ_HANDLED;
+}
+
+static int vxge_alloc_msix(struct vxgedev *vdev)
+{
+	int j, i, ret = 0;
+	int intr_cnt = 0;
+	int alarm_msix_id = 0, msix_intr_vect = 0;
+	vdev->intr_cnt = 0;
+
+	/* Tx/Rx MSIX Vectors count */
+	vdev->intr_cnt = vdev->no_of_vpath * 2;
+
+	/* Alarm MSIX Vectors count */
+	vdev->intr_cnt++;
+
+	intr_cnt = (vdev->max_vpath_supported * 2) + 1;
+	vdev->entries = kzalloc(intr_cnt * sizeof(struct msix_entry),
+						GFP_KERNEL);
+	if (!vdev->entries) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: memory allocation failed",
+			VXGE_DRIVER_NAME);
+		return  -ENOMEM;
+	}
+
+	vdev->vxge_entries = kzalloc(intr_cnt * sizeof(struct vxge_msix_entry),
+							GFP_KERNEL);
+	if (!vdev->vxge_entries) {
+		vxge_debug_init(VXGE_ERR, "%s: memory allocation failed",
+			VXGE_DRIVER_NAME);
+		kfree(vdev->entries);
+		return -ENOMEM;
+	}
+
+	/* Last vector in the list is used for alarm */
+	alarm_msix_id = VXGE_HW_VPATH_MSIX_ACTIVE * vdev->no_of_vpath - 2;
+	for (i = 0, j = 0; i < vdev->max_vpath_supported; i++) {
+
+		msix_intr_vect = i * VXGE_HW_VPATH_MSIX_ACTIVE;
+
+		/* Initialize the fifo vector */
+		vdev->entries[j].entry = msix_intr_vect;
+		vdev->vxge_entries[j].entry = msix_intr_vect;
+		vdev->vxge_entries[j].in_use = 0;
+		j++;
+
+		/* Initialize the ring vector */
+		vdev->entries[j].entry = msix_intr_vect + 1;
+		vdev->vxge_entries[j].entry = msix_intr_vect + 1;
+		vdev->vxge_entries[j].in_use = 0;
+		j++;
+	}
+
+	/* Initialize the alarm vector */
+	vdev->entries[j].entry = alarm_msix_id;
+	vdev->vxge_entries[j].entry = alarm_msix_id;
+	vdev->vxge_entries[j].in_use = 0;
+
+	ret = pci_enable_msix(vdev->pdev, vdev->entries, intr_cnt);
+	/* if driver request exceeeds available irq's, request with a small
+	 * number.
+	*/
+	if (ret > 0) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: MSI-X enable failed for %d vectors, available: %d",
+			VXGE_DRIVER_NAME, intr_cnt, ret);
+		vdev->max_vpath_supported = vdev->no_of_vpath;
+		intr_cnt = (vdev->max_vpath_supported * 2) + 1;
+
+		/* Reset the alarm vector setting */
+		vdev->entries[j].entry = 0;
+		vdev->vxge_entries[j].entry = 0;
+
+		/* Initialize the alarm vector with new setting */
+		vdev->entries[intr_cnt - 1].entry = alarm_msix_id;
+		vdev->vxge_entries[intr_cnt - 1].entry = alarm_msix_id;
+		vdev->vxge_entries[intr_cnt - 1].in_use = 0;
+
+		ret = pci_enable_msix(vdev->pdev, vdev->entries, intr_cnt);
+		if (!ret)
+			vxge_debug_init(VXGE_ERR,
+				"%s: MSI-X enabled for %d vectors",
+				VXGE_DRIVER_NAME, intr_cnt);
+	}
+
+	if (ret) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: MSI-X enable failed for %d vectors, ret: %d",
+			VXGE_DRIVER_NAME, intr_cnt, ret);
+		kfree(vdev->entries);
+		kfree(vdev->vxge_entries);
+		vdev->entries = NULL;
+		vdev->vxge_entries = NULL;
+		return -ENODEV;
+	}
+	return 0;
+}
+
+static int vxge_enable_msix(struct vxgedev *vdev)
+{
+
+	int i, ret = 0;
+	enum vxge_hw_status status;
+	/* 0 - Tx, 1 - Rx  */
+	int tim_msix_id[4];
+	int alarm_msix_id = 0, msix_intr_vect = 0;;
+	vdev->intr_cnt = 0;
+
+	/* allocate msix vectors */
+	ret = vxge_alloc_msix(vdev);
+	if (!ret) {
+		/* Last vector in the list is used for alarm */
+		alarm_msix_id =
+			VXGE_HW_VPATH_MSIX_ACTIVE * vdev->no_of_vpath - 2;
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+
+			/* If fifo or ring are not enabled
+			   the MSIX vector for that should be set to 0
+			   Hence initializeing this array to all 0s.
+			*/
+			memset(tim_msix_id, 0, sizeof(tim_msix_id));
+			msix_intr_vect = i * VXGE_HW_VPATH_MSIX_ACTIVE;
+			tim_msix_id[0] = msix_intr_vect;
+
+			tim_msix_id[1] = msix_intr_vect + 1;
+			vdev->vpaths[i].ring.rx_vector_no = tim_msix_id[1];
+
+			status = vxge_hw_vpath_msix_set(
+						vdev->vpaths[i].handle,
+						tim_msix_id, alarm_msix_id);
+			if (status != VXGE_HW_OK) {
+				vxge_debug_init(VXGE_ERR,
+					"vxge_hw_vpath_msix_set "
+					"failed with status : %x", status);
+				kfree(vdev->entries);
+				kfree(vdev->vxge_entries);
+				pci_disable_msix(vdev->pdev);
+				return -ENODEV;
+			}
+		}
+	}
+
+	return ret;
+}
+
+static void vxge_rem_msix_isr(struct vxgedev *vdev)
+{
+	int intr_cnt;
+
+	for (intr_cnt = 0; intr_cnt < (vdev->max_vpath_supported * 2 + 1);
+		intr_cnt++) {
+		if (vdev->vxge_entries[intr_cnt].in_use) {
+			synchronize_irq(vdev->entries[intr_cnt].vector);
+			free_irq(vdev->entries[intr_cnt].vector,
+				vdev->vxge_entries[intr_cnt].arg);
+			vdev->vxge_entries[intr_cnt].in_use = 0;
+		}
+	}
+
+	kfree(vdev->entries);
+	kfree(vdev->vxge_entries);
+	vdev->entries = NULL;
+	vdev->vxge_entries = NULL;
+
+	if (vdev->config.intr_type == MSI_X)
+		pci_disable_msix(vdev->pdev);
+}
+#endif
+
+static void vxge_rem_isr(struct vxgedev *vdev)
+{
+	struct __vxge_hw_device  *hldev;
+	hldev = (struct __vxge_hw_device  *) pci_get_drvdata(vdev->pdev);
+
+#ifdef CONFIG_PCI_MSI
+	if (vdev->config.intr_type == MSI_X) {
+		vxge_rem_msix_isr(vdev);
+	} else
+#endif
+	if (vdev->config.intr_type == INTA) {
+			synchronize_irq(vdev->pdev->irq);
+			free_irq(vdev->pdev->irq, hldev);
+	}
+}
+
+static int vxge_add_isr(struct vxgedev *vdev)
+{
+	int ret = 0;
+	struct __vxge_hw_device  *hldev =
+		(struct __vxge_hw_device  *) pci_get_drvdata(vdev->pdev);
+#ifdef CONFIG_PCI_MSI
+	int vp_idx = 0, intr_idx = 0, intr_cnt = 0, msix_idx = 0, irq_req = 0;
+	u64 function_mode = vdev->config.device_hw_info.function_mode;
+	int pci_fun = PCI_FUNC(vdev->pdev->devfn);
+
+	if (vdev->config.intr_type == MSI_X)
+		ret = vxge_enable_msix(vdev);
+
+	if (ret) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: Enabling MSI-X Failed", VXGE_DRIVER_NAME);
+		if ((function_mode == VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION) &&
+			test_and_set_bit(__VXGE_STATE_CARD_UP,
+				&driver_config->inta_dev_open))
+			return VXGE_HW_FAIL;
+		else {
+			vxge_debug_init(VXGE_ERR,
+				"%s: Defaulting to INTA", VXGE_DRIVER_NAME);
+			vdev->config.intr_type = INTA;
+			vxge_hw_device_set_intr_type(vdev->devh,
+				VXGE_HW_INTR_MODE_IRQLINE);
+			vxge_close_vpaths(vdev, 1);
+			vdev->no_of_vpath = 1;
+			vdev->stats.vpaths_open = 1;
+		}
+	}
+
+	if (vdev->config.intr_type == MSI_X) {
+		for (intr_idx = 0;
+		     intr_idx < (vdev->no_of_vpath *
+			VXGE_HW_VPATH_MSIX_ACTIVE); intr_idx++) {
+
+			msix_idx = intr_idx % VXGE_HW_VPATH_MSIX_ACTIVE;
+			irq_req = 0;
+
+			switch (msix_idx) {
+			case 0:
+				snprintf(vdev->desc[intr_cnt], VXGE_INTR_STRLEN,
+					"%s:vxge fn: %d vpath: %d Tx MSI-X: %d",
+					vdev->ndev->name, pci_fun, vp_idx,
+					vdev->entries[intr_cnt].entry);
+				ret = request_irq(
+				    vdev->entries[intr_cnt].vector,
+					vxge_tx_msix_handle, 0,
+					vdev->desc[intr_cnt],
+					&vdev->vpaths[vp_idx].fifo);
+					vdev->vxge_entries[intr_cnt].arg =
+						&vdev->vpaths[vp_idx].fifo;
+				irq_req = 1;
+				break;
+			case 1:
+				snprintf(vdev->desc[intr_cnt], VXGE_INTR_STRLEN,
+					"%s:vxge fn: %d vpath: %d Rx MSI-X: %d",
+					vdev->ndev->name, pci_fun, vp_idx,
+					vdev->entries[intr_cnt].entry);
+				ret = request_irq(
+				    vdev->entries[intr_cnt].vector,
+					vxge_rx_msix_napi_handle,
+					0,
+					vdev->desc[intr_cnt],
+					&vdev->vpaths[vp_idx].ring);
+					vdev->vxge_entries[intr_cnt].arg =
+						&vdev->vpaths[vp_idx].ring;
+				irq_req = 1;
+				break;
+			}
+
+			if (ret) {
+				vxge_debug_init(VXGE_ERR,
+					"%s: MSIX - %d  Registration failed",
+					vdev->ndev->name, intr_cnt);
+				vxge_rem_msix_isr(vdev);
+				if ((function_mode ==
+					VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION) &&
+					test_and_set_bit(__VXGE_STATE_CARD_UP,
+						&driver_config->inta_dev_open))
+					return VXGE_HW_FAIL;
+				else {
+					vxge_hw_device_set_intr_type(
+						vdev->devh,
+						VXGE_HW_INTR_MODE_IRQLINE);
+						vdev->config.intr_type = INTA;
+					vxge_debug_init(VXGE_ERR,
+						"%s: Defaulting to INTA"
+						, vdev->ndev->name);
+					vxge_close_vpaths(vdev, 1);
+					vdev->no_of_vpath = 1;
+					vdev->stats.vpaths_open = 1;
+					goto INTA_MODE;
+				}
+			}
+
+			if (irq_req) {
+				/* We requested for this msix interrupt */
+				vdev->vxge_entries[intr_cnt].in_use = 1;
+				vxge_hw_vpath_msix_unmask(
+					vdev->vpaths[vp_idx].handle,
+					intr_idx);
+				intr_cnt++;
+			}
+
+			/* Point to next vpath handler */
+			if (((intr_idx + 1) % VXGE_HW_VPATH_MSIX_ACTIVE == 0)
+				&& (vp_idx < (vdev->no_of_vpath - 1)))
+					vp_idx++;
+		}
+
+		intr_cnt = vdev->max_vpath_supported * 2;
+		snprintf(vdev->desc[intr_cnt], VXGE_INTR_STRLEN,
+			"%s:vxge Alarm fn: %d MSI-X: %d",
+			vdev->ndev->name, pci_fun,
+			vdev->entries[intr_cnt].entry);
+		/* For Alarm interrupts */
+		ret = request_irq(vdev->entries[intr_cnt].vector,
+					vxge_alarm_msix_handle, 0,
+					vdev->desc[intr_cnt],
+					&vdev->vpaths[vp_idx]);
+		if (ret) {
+			vxge_debug_init(VXGE_ERR,
+				"%s: MSIX - %d Registration failed",
+				vdev->ndev->name, intr_cnt);
+			vxge_rem_msix_isr(vdev);
+			if ((function_mode ==
+				VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION) &&
+				test_and_set_bit(__VXGE_STATE_CARD_UP,
+						&driver_config->inta_dev_open))
+				return VXGE_HW_FAIL;
+			else {
+				vxge_hw_device_set_intr_type(vdev->devh,
+						VXGE_HW_INTR_MODE_IRQLINE);
+				vdev->config.intr_type = INTA;
+				vxge_debug_init(VXGE_ERR,
+					"%s: Defaulting to INTA",
+					vdev->ndev->name);
+				vxge_close_vpaths(vdev, 1);
+				vdev->no_of_vpath = 1;
+				vdev->stats.vpaths_open = 1;
+				goto INTA_MODE;
+			}
+		}
+
+		vxge_hw_vpath_msix_unmask(vdev->vpaths[vp_idx].handle,
+					intr_idx - 2);
+		vdev->vxge_entries[intr_cnt].in_use = 1;
+		vdev->vxge_entries[intr_cnt].arg = &vdev->vpaths[vp_idx];
+	}
+INTA_MODE:
+#endif
+	snprintf(vdev->desc[0], VXGE_INTR_STRLEN, "%s:vxge", vdev->ndev->name);
+
+	if (vdev->config.intr_type == INTA) {
+		ret = request_irq((int) vdev->pdev->irq,
+			vxge_isr_napi,
+			IRQF_SHARED, vdev->desc[0], hldev);
+		if (ret) {
+			vxge_debug_init(VXGE_ERR,
+				"%s %s-%d: ISR registration failed",
+				VXGE_DRIVER_NAME, "IRQ", vdev->pdev->irq);
+			return -ENODEV;
+		}
+		vxge_debug_init(VXGE_TRACE,
+			"new %s-%d line allocated",
+			"IRQ", vdev->pdev->irq);
+	}
+
+	return VXGE_HW_OK;
+}
+
+static void vxge_poll_vp_reset(unsigned long data)
+{
+	struct vxgedev *vdev = (struct vxgedev *)data;
+	int i, j = 0;
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		if (test_bit(i, &vdev->vp_reset)) {
+			vxge_reset_vpath(vdev, i);
+			j++;
+		}
+	}
+	if (j && (vdev->config.intr_type != MSI_X)) {
+		vxge_hw_device_unmask_all(vdev->devh);
+		vxge_hw_device_flush_io(vdev->devh);
+	}
+
+	mod_timer(&vdev->vp_reset_timer, jiffies + HZ / 2);
+}
+
+static void vxge_poll_vp_lockup(unsigned long data)
+{
+	struct vxgedev *vdev = (struct vxgedev *)data;
+	int i;
+	struct vxge_ring *ring;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		ring = &vdev->vpaths[i].ring;
+		/* Did this vpath received any packets */
+		if (ring->stats.prev_rx_frms == ring->stats.rx_frms) {
+			status = vxge_hw_vpath_check_leak(ring->handle);
+
+			/* Did it received any packets last time */
+			if ((VXGE_HW_FAIL == status) &&
+				(VXGE_HW_FAIL == ring->last_status)) {
+
+				/* schedule vpath reset */
+				if (!test_and_set_bit(i, &vdev->vp_reset)) {
+
+					/* disable interrupts for this vpath */
+					vxge_vpath_intr_disable(vdev, i);
+
+					/* stop the queue for this vpath */
+					vxge_stop_tx_queue(&vdev->vpaths[i].
+								fifo);
+					continue;
+				}
+			}
+		}
+		ring->stats.prev_rx_frms = ring->stats.rx_frms;
+		ring->last_status = status;
+	}
+
+	/* Check every 1 milli second */
+	mod_timer(&vdev->vp_lockup_timer, jiffies + HZ / 1000);
+}
+
+/**
+ * vxge_open
+ * @dev: pointer to the device structure.
+ *
+ * This function is the open entry point of the driver. It mainly calls a
+ * function to allocate Rx buffers and inserts them into the buffer
+ * descriptors and then enables the Rx part of the NIC.
+ * Return value: '0' on success and an appropriate (-)ve integer as
+ * defined in errno.h file on failure.
+ */
+int
+vxge_open(struct net_device *dev)
+{
+	enum vxge_hw_status status;
+	struct vxgedev *vdev;
+	struct __vxge_hw_device *hldev;
+	int ret = 0;
+	int i;
+	u64 val64, function_mode;
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d", dev->name, __func__, __LINE__);
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+	hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev);
+	function_mode = vdev->config.device_hw_info.function_mode;
+
+	/* make sure you have link off by default every time Nic is
+	 * initialized */
+	netif_carrier_off(dev);
+
+	/* Check for another device already opn with INTA */
+	if ((function_mode == VXGE_HW_FUNCTION_MODE_MULTI_FUNCTION) &&
+		test_bit(__VXGE_STATE_CARD_UP, &driver_config->inta_dev_open)) {
+		ret = -EPERM;
+		goto out0;
+	}
+
+	/* Open VPATHs */
+	status = vxge_open_vpaths(vdev);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: fatal: Vpath open failed", vdev->ndev->name);
+		ret = -EPERM;
+		goto out0;
+	}
+
+	vdev->mtu = dev->mtu;
+
+	status = vxge_add_isr(vdev);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: fatal: ISR add failed", dev->name);
+		ret = -EPERM;
+		goto out1;
+	}
+
+
+	if (vdev->config.intr_type != MSI_X) {
+		netif_napi_add(dev, &vdev->napi, vxge_poll_inta,
+			vdev->config.napi_weight);
+		napi_enable(&vdev->napi);
+	} else {
+		for (i = 0; i < vdev->no_of_vpath; i++) {
+			netif_napi_add(dev, &vdev->vpaths[i].ring.napi,
+			    vxge_poll_msix, vdev->config.napi_weight);
+			napi_enable(&vdev->vpaths[i].ring.napi);
+		}
+	}
+
+	/* configure RTH */
+	if (vdev->config.rth_steering) {
+		status = vxge_rth_configure(vdev);
+		if (status != VXGE_HW_OK) {
+			vxge_debug_init(VXGE_ERR,
+				"%s: fatal: RTH configuration failed",
+				dev->name);
+			ret = -EPERM;
+			goto out2;
+		}
+	}
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		/* set initial mtu before enabling the device */
+		status = vxge_hw_vpath_mtu_set(vdev->vpaths[i].handle,
+						vdev->mtu);
+		if (status != VXGE_HW_OK) {
+			vxge_debug_init(VXGE_ERR,
+				"%s: fatal: can not set new MTU", dev->name);
+			ret = -EPERM;
+			goto out2;
+		}
+	}
+
+	VXGE_DEVICE_DEBUG_LEVEL_SET(VXGE_TRACE, VXGE_COMPONENT_LL, vdev);
+	vxge_debug_init(vdev->level_trace,
+		"%s: MTU is %d", vdev->ndev->name, vdev->mtu);
+	VXGE_DEVICE_DEBUG_LEVEL_SET(VXGE_ERR, VXGE_COMPONENT_LL, vdev);
+
+	/* Reprogram the DA table with populated mac addresses */
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		vxge_restore_vpath_mac_addr(&vdev->vpaths[i]);
+		vxge_restore_vpath_vid_table(&vdev->vpaths[i]);
+	}
+
+	/* Enable vpath to sniff all unicast/multicast traffic that not
+	 * addressed to them. We allow promiscous mode for PF only
+	 */
+
+	val64 = 0;
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
+		val64 |= VXGE_HW_RXMAC_AUTHORIZE_ALL_ADDR_VP(i);
+
+	vxge_hw_mgmt_reg_write(vdev->devh,
+		vxge_hw_mgmt_reg_type_mrpcim,
+		0,
+		(ulong)offsetof(struct vxge_hw_mrpcim_reg,
+			rxmac_authorize_all_addr),
+		val64);
+
+	vxge_hw_mgmt_reg_write(vdev->devh,
+		vxge_hw_mgmt_reg_type_mrpcim,
+		0,
+		(ulong)offsetof(struct vxge_hw_mrpcim_reg,
+			rxmac_authorize_all_vid),
+		val64);
+
+	vxge_set_multicast(dev);
+
+	/* Enabling Bcast and mcast for all vpath */
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		status = vxge_hw_vpath_bcast_enable(vdev->vpaths[i].handle);
+		if (status != VXGE_HW_OK)
+			vxge_debug_init(VXGE_ERR,
+				"%s : Can not enable bcast for vpath "
+				"id %d", dev->name, i);
+		if (vdev->config.addr_learn_en) {
+			status =
+			    vxge_hw_vpath_mcast_enable(vdev->vpaths[i].handle);
+			if (status != VXGE_HW_OK)
+				vxge_debug_init(VXGE_ERR,
+					"%s : Can not enable mcast for vpath "
+					"id %d", dev->name, i);
+		}
+	}
+
+	vxge_hw_device_setpause_data(vdev->devh, 0,
+		vdev->config.tx_pause_enable,
+		vdev->config.rx_pause_enable);
+
+	if (vdev->vp_reset_timer.function == NULL)
+		vxge_os_timer(vdev->vp_reset_timer,
+			vxge_poll_vp_reset, vdev, (HZ/2));
+
+	if (vdev->vp_lockup_timer.function == NULL)
+		vxge_os_timer(vdev->vp_lockup_timer,
+			vxge_poll_vp_lockup, vdev, (HZ/2));
+
+	set_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+
+	smp_wmb();
+
+	if (vxge_hw_device_link_state_get(vdev->devh) == VXGE_HW_LINK_UP) {
+		netif_carrier_on(vdev->ndev);
+		printk(KERN_NOTICE "%s: Link Up\n", vdev->ndev->name);
+		vdev->stats.link_up++;
+	}
+
+	vxge_hw_device_intr_enable(vdev->devh);
+
+	smp_wmb();
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		vxge_hw_vpath_enable(vdev->vpaths[i].handle);
+		smp_wmb();
+		vxge_hw_vpath_rx_doorbell_init(vdev->vpaths[i].handle);
+	}
+
+	vxge_start_all_tx_queue(vdev);
+	goto out0;
+
+out2:
+	vxge_rem_isr(vdev);
+
+	/* Disable napi */
+	if (vdev->config.intr_type != MSI_X)
+		napi_disable(&vdev->napi);
+	else {
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			napi_disable(&vdev->vpaths[i].ring.napi);
+	}
+
+out1:
+	vxge_close_vpaths(vdev, 0);
+out0:
+	vxge_debug_entryexit(VXGE_TRACE,
+				"%s: %s:%d  Exiting...",
+				dev->name, __func__, __LINE__);
+	return ret;
+}
+
+/* Loop throught the mac address list and delete all the entries */
+void vxge_free_mac_add_list(struct vxge_vpath *vpath)
+{
+
+	struct list_head *entry, *next;
+	if (list_empty(&vpath->mac_addr_list))
+		return;
+
+	list_for_each_safe(entry, next, &vpath->mac_addr_list) {
+		list_del(entry);
+		kfree((struct vxge_mac_addrs *)entry);
+	}
+}
+
+static void vxge_napi_del_all(struct vxgedev *vdev)
+{
+	int i;
+	if (vdev->config.intr_type != MSI_X)
+		netif_napi_del(&vdev->napi);
+	else {
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			netif_napi_del(&vdev->vpaths[i].ring.napi);
+	}
+	return;
+}
+
+int do_vxge_close(struct net_device *dev, int do_io)
+{
+	enum vxge_hw_status status;
+	struct vxgedev *vdev;
+	struct __vxge_hw_device *hldev;
+	int i;
+	u64 val64, vpath_vector;
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d",
+		dev->name, __func__, __LINE__);
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+	hldev = (struct __vxge_hw_device *) pci_get_drvdata(vdev->pdev);
+
+	/* If vxge_handle_crit_err task is executing,
+	 * wait till it completes. */
+	while (test_and_set_bit(__VXGE_STATE_RESET_CARD, &vdev->state))
+		msleep(50);
+
+	clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+	if (do_io) {
+		/* Put the vpath back in normal mode */
+		vpath_vector = vxge_mBIT(vdev->vpaths[0].device_id);
+		status = vxge_hw_mgmt_reg_read(vdev->devh,
+				vxge_hw_mgmt_reg_type_mrpcim,
+				0,
+				(ulong)offsetof(
+					struct vxge_hw_mrpcim_reg,
+					rts_mgr_cbasin_cfg),
+				&val64);
+
+		if (status == VXGE_HW_OK) {
+			val64 &= ~vpath_vector;
+			status = vxge_hw_mgmt_reg_write(vdev->devh,
+					vxge_hw_mgmt_reg_type_mrpcim,
+					0,
+					(ulong)offsetof(
+						struct vxge_hw_mrpcim_reg,
+						rts_mgr_cbasin_cfg),
+					val64);
+		}
+
+		/* Remove the function 0 from promiscous mode */
+		vxge_hw_mgmt_reg_write(vdev->devh,
+			vxge_hw_mgmt_reg_type_mrpcim,
+			0,
+			(ulong)offsetof(struct vxge_hw_mrpcim_reg,
+				rxmac_authorize_all_addr),
+			0);
+
+		vxge_hw_mgmt_reg_write(vdev->devh,
+			vxge_hw_mgmt_reg_type_mrpcim,
+			0,
+			(ulong)offsetof(struct vxge_hw_mrpcim_reg,
+				rxmac_authorize_all_vid),
+			0);
+
+		smp_wmb();
+	}
+	del_timer_sync(&vdev->vp_lockup_timer);
+
+	del_timer_sync(&vdev->vp_reset_timer);
+
+	/* Disable napi */
+	if (vdev->config.intr_type != MSI_X)
+		napi_disable(&vdev->napi);
+	else {
+		for (i = 0; i < vdev->no_of_vpath; i++)
+			napi_disable(&vdev->vpaths[i].ring.napi);
+	}
+
+	netif_carrier_off(vdev->ndev);
+	printk(KERN_NOTICE "%s: Link Down\n", vdev->ndev->name);
+	vxge_stop_all_tx_queue(vdev);
+
+	/* Note that at this point xmit() is stopped by upper layer */
+	if (do_io)
+		vxge_hw_device_intr_disable(vdev->devh);
+
+	mdelay(1000);
+
+	vxge_rem_isr(vdev);
+
+	vxge_napi_del_all(vdev);
+
+	if (do_io)
+		vxge_reset_all_vpaths(vdev);
+
+	vxge_close_vpaths(vdev, 0);
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s: %s:%d  Exiting...", dev->name, __func__, __LINE__);
+
+	clear_bit(__VXGE_STATE_CARD_UP, &driver_config->inta_dev_open);
+	clear_bit(__VXGE_STATE_RESET_CARD, &vdev->state);
+
+	return 0;
+}
+
+/**
+ * vxge_close
+ * @dev: device pointer.
+ *
+ * This is the stop entry point of the driver. It needs to undo exactly
+ * whatever was done by the open entry point, thus it's usually referred to
+ * as the close function.Among other things this function mainly stops the
+ * Rx side of the NIC and frees all the Rx buffers in the Rx rings.
+ * Return value: '0' on success and an appropriate (-)ve integer as
+ * defined in errno.h file on failure.
+ */
+int
+vxge_close(struct net_device *dev)
+{
+	do_vxge_close(dev, 1);
+	return 0;
+}
+
+/**
+ * vxge_change_mtu
+ * @dev: net device pointer.
+ * @new_mtu :the new MTU size for the device.
+ *
+ * A driver entry point to change MTU size for the device. Before changing
+ * the MTU the device must be stopped.
+ */
+static int vxge_change_mtu(struct net_device *dev, int new_mtu)
+{
+	struct vxgedev *vdev = netdev_priv(dev);
+
+	vxge_debug_entryexit(vdev->level_trace,
+		"%s:%d", __func__, __LINE__);
+	if ((new_mtu < VXGE_HW_MIN_MTU) || (new_mtu > VXGE_HW_MAX_MTU)) {
+		vxge_debug_init(vdev->level_err,
+			"%s: mtu size is invalid", dev->name);
+		return -EPERM;
+	}
+
+	/* check if device is down already */
+	if (unlikely(!is_vxge_card_up(vdev))) {
+		/* just store new value, will use later on open() */
+		dev->mtu = new_mtu;
+		vxge_debug_init(vdev->level_err,
+			"%s", "device is down on MTU change");
+		return 0;
+	}
+
+	vxge_debug_init(vdev->level_trace,
+		"trying to apply new MTU %d", new_mtu);
+
+	if (vxge_close(dev))
+		return -EIO;
+
+	dev->mtu = new_mtu;
+	vdev->mtu = new_mtu;
+
+	if (vxge_open(dev))
+		return -EIO;
+
+	vxge_debug_init(vdev->level_trace,
+		"%s: MTU changed to %d", vdev->ndev->name, new_mtu);
+
+	vxge_debug_entryexit(vdev->level_trace,
+		"%s:%d  Exiting...", __func__, __LINE__);
+
+	return 0;
+}
+
+/**
+ * vxge_get_stats
+ * @dev: pointer to the device structure
+ *
+ * Updates the device statistics structure. This function updates the device
+ * statistics structure in the net_device structure and returns a pointer
+ * to the same.
+ */
+static struct net_device_stats *
+vxge_get_stats(struct net_device *dev)
+{
+	struct vxgedev *vdev;
+	struct net_device_stats *net_stats;
+	int k;
+
+	vdev = netdev_priv(dev);
+
+	net_stats = &vdev->stats.net_stats;
+
+	memset(net_stats, 0, sizeof(struct net_device_stats));
+
+	for (k = 0; k < vdev->no_of_vpath; k++) {
+		net_stats->rx_packets += vdev->vpaths[k].ring.stats.rx_frms;
+		net_stats->rx_bytes += vdev->vpaths[k].ring.stats.rx_bytes;
+		net_stats->rx_errors += vdev->vpaths[k].ring.stats.rx_errors;
+		net_stats->multicast += vdev->vpaths[k].ring.stats.rx_mcast;
+		net_stats->rx_dropped +=
+			vdev->vpaths[k].ring.stats.rx_dropped;
+
+		net_stats->tx_packets += vdev->vpaths[k].fifo.stats.tx_frms;
+		net_stats->tx_bytes += vdev->vpaths[k].fifo.stats.tx_bytes;
+		net_stats->tx_errors += vdev->vpaths[k].fifo.stats.tx_errors;
+	}
+
+	return net_stats;
+}
+
+/**
+ * vxge_ioctl
+ * @dev: Device pointer.
+ * @ifr: An IOCTL specific structure, that can contain a pointer to
+ *       a proprietary structure used to pass information to the driver.
+ * @cmd: This is used to distinguish between the different commands that
+ *       can be passed to the IOCTL functions.
+ *
+ * Entry point for the Ioctl.
+ */
+static int vxge_ioctl(struct net_device *dev, struct ifreq *rq, int cmd)
+{
+	return -EOPNOTSUPP;
+}
+
+/**
+ * vxge_tx_watchdog
+ * @dev: pointer to net device structure
+ *
+ * Watchdog for transmit side.
+ * This function is triggered if the Tx Queue is stopped
+ * for a pre-defined amount of time when the Interface is still up.
+ */
+static void
+vxge_tx_watchdog(struct net_device *dev)
+{
+	struct vxgedev *vdev;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+
+	vdev->cric_err_event = VXGE_HW_EVENT_RESET_START;
+
+	vxge_reset(vdev);
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d  Exiting...", __func__, __LINE__);
+}
+
+/**
+ * vxge_vlan_rx_register
+ * @dev: net device pointer.
+ * @grp: vlan group
+ *
+ * Vlan group registration
+ */
+static void
+vxge_vlan_rx_register(struct net_device *dev, struct vlan_group *grp)
+{
+	struct vxgedev *vdev;
+	struct vxge_vpath *vpath;
+	int vp;
+	u64 vid;
+	enum vxge_hw_status status;
+	int i;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+
+	vpath = &vdev->vpaths[0];
+	if ((NULL == grp) && (vpath->is_open)) {
+		/* Get the first vlan */
+		status = vxge_hw_vpath_vid_get(vpath->handle, &vid);
+
+		while (status == VXGE_HW_OK) {
+
+			/* Delete this vlan from the vid table */
+			for (vp = 0; vp < vdev->no_of_vpath; vp++) {
+				vpath = &vdev->vpaths[vp];
+				if (!vpath->is_open)
+					continue;
+
+				vxge_hw_vpath_vid_delete(vpath->handle, vid);
+			}
+
+			/* Get the next vlan to be deleted */
+			vpath = &vdev->vpaths[0];
+			status = vxge_hw_vpath_vid_get(vpath->handle, &vid);
+		}
+	}
+
+	vdev->vlgrp = grp;
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		if (vdev->vpaths[i].is_configured)
+			vdev->vpaths[i].ring.vlgrp = grp;
+	}
+
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d  Exiting...", __func__, __LINE__);
+}
+
+/**
+ * vxge_vlan_rx_add_vid
+ * @dev: net device pointer.
+ * @vid: vid
+ *
+ * Add the vlan id to the devices vlan id table
+ */
+static void
+vxge_vlan_rx_add_vid(struct net_device *dev, unsigned short vid)
+{
+	struct vxgedev *vdev;
+	struct vxge_vpath *vpath;
+	int vp_id;
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+
+	/* Add these vlan to the vid table */
+	for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
+		vpath = &vdev->vpaths[vp_id];
+		if (!vpath->is_open)
+			continue;
+		vxge_hw_vpath_vid_add(vpath->handle, vid);
+	}
+}
+
+/**
+ * vxge_vlan_rx_add_vid
+ * @dev: net device pointer.
+ * @vid: vid
+ *
+ * Remove the vlan id from the device's vlan id table
+ */
+static void
+vxge_vlan_rx_kill_vid(struct net_device *dev, unsigned short vid)
+{
+	struct vxgedev *vdev;
+	struct vxge_vpath *vpath;
+	int vp_id;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+
+	vdev = (struct vxgedev *)netdev_priv(dev);
+
+	vlan_group_set_device(vdev->vlgrp, vid, NULL);
+
+	/* Delete this vlan from the vid table */
+	for (vp_id = 0; vp_id < vdev->no_of_vpath; vp_id++) {
+		vpath = &vdev->vpaths[vp_id];
+		if (!vpath->is_open)
+			continue;
+		vxge_hw_vpath_vid_delete(vpath->handle, vid);
+	}
+	vxge_debug_entryexit(VXGE_TRACE,
+		"%s:%d  Exiting...", __func__, __LINE__);
+}
+
+static const struct net_device_ops vxge_netdev_ops = {
+	.ndo_open               = vxge_open,
+	.ndo_stop               = vxge_close,
+	.ndo_get_stats          = vxge_get_stats,
+	.ndo_start_xmit         = vxge_xmit,
+	.ndo_validate_addr      = eth_validate_addr,
+	.ndo_set_multicast_list = vxge_set_multicast,
+
+	.ndo_do_ioctl           = vxge_ioctl,
+
+	.ndo_set_mac_address    = vxge_set_mac_addr,
+	.ndo_change_mtu         = vxge_change_mtu,
+	.ndo_vlan_rx_register   = vxge_vlan_rx_register,
+	.ndo_vlan_rx_kill_vid   = vxge_vlan_rx_kill_vid,
+	.ndo_vlan_rx_add_vid	= vxge_vlan_rx_add_vid,
+
+	.ndo_tx_timeout         = vxge_tx_watchdog,
+#ifdef CONFIG_NET_POLL_CONTROLLER
+	.ndo_poll_controller    = vxge_netpoll,
+#endif
+};
+
+int __devinit vxge_device_register(struct __vxge_hw_device *hldev,
+				   struct vxge_config *config,
+				   int high_dma, int no_of_vpath,
+				   struct vxgedev **vdev_out)
+{
+	struct net_device *ndev;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxgedev *vdev;
+	int i, ret = 0, no_of_queue = 1;
+	u64 stat;
+
+	*vdev_out = NULL;
+	if (config->tx_steering_type == TX_MULTIQ_STEERING)
+		no_of_queue = no_of_vpath;
+
+	ndev = alloc_etherdev_mq(sizeof(struct vxgedev),
+			no_of_queue);
+	if (ndev == NULL) {
+		vxge_debug_init(
+			vxge_hw_device_trace_level_get(hldev),
+		"%s : device allocation failed", __func__);
+		ret = -ENODEV;
+		goto _out0;
+	}
+
+	vxge_debug_entryexit(
+		vxge_hw_device_trace_level_get(hldev),
+		"%s: %s:%d  Entering...",
+		ndev->name, __func__, __LINE__);
+
+	vdev = netdev_priv(ndev);
+	memset(vdev, 0, sizeof(struct vxgedev));
+
+	vdev->ndev = ndev;
+	vdev->devh = hldev;
+	vdev->pdev = hldev->pdev;
+	memcpy(&vdev->config, config, sizeof(struct vxge_config));
+	vdev->rx_csum = 1;	/* Enable Rx CSUM by default. */
+
+	SET_NETDEV_DEV(ndev, &vdev->pdev->dev);
+
+	ndev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_RX |
+				NETIF_F_HW_VLAN_FILTER;
+	/*  Driver entry points */
+	ndev->irq = vdev->pdev->irq;
+	ndev->base_addr = (unsigned long) hldev->bar0;
+
+	ndev->netdev_ops = &vxge_netdev_ops;
+
+	ndev->watchdog_timeo = VXGE_LL_WATCH_DOG_TIMEOUT;
+
+	initialize_ethtool_ops(ndev);
+
+	/* Allocate memory for vpath */
+	vdev->vpaths = kzalloc((sizeof(struct vxge_vpath)) *
+				no_of_vpath, GFP_KERNEL);
+	if (!vdev->vpaths) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: vpath memory allocation failed",
+			vdev->ndev->name);
+		ret = -ENODEV;
+		goto _out1;
+	}
+
+	ndev->features |= NETIF_F_SG;
+
+	ndev->features |= NETIF_F_HW_CSUM;
+	vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
+		"%s : checksuming enabled", __func__);
+
+	if (high_dma) {
+		ndev->features |= NETIF_F_HIGHDMA;
+		vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
+			"%s : using High DMA", __func__);
+	}
+
+	ndev->features |= NETIF_F_TSO | NETIF_F_TSO6;
+
+	if (vdev->config.gro_enable)
+		ndev->features |= NETIF_F_GRO;
+
+	if (vdev->config.tx_steering_type == TX_MULTIQ_STEERING)
+		ndev->real_num_tx_queues = no_of_vpath;
+
+#ifdef NETIF_F_LLTX
+	ndev->features |= NETIF_F_LLTX;
+#endif
+
+	for (i = 0; i < no_of_vpath; i++)
+		spin_lock_init(&vdev->vpaths[i].fifo.tx_lock);
+
+	if (register_netdev(ndev)) {
+		vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
+			"%s: %s : device registration failed!",
+			ndev->name, __func__);
+		ret = -ENODEV;
+		goto _out2;
+	}
+
+	/*  Set the factory defined MAC address initially */
+	ndev->addr_len = ETH_ALEN;
+
+	/* Make Link state as off at this point, when the Link change
+	 * interrupt comes the state will be automatically changed to
+	 * the right state.
+	 */
+	netif_carrier_off(ndev);
+
+	vxge_debug_init(vxge_hw_device_trace_level_get(hldev),
+		"%s: Ethernet device registered",
+		ndev->name);
+
+	*vdev_out = vdev;
+
+	/* Resetting the Device stats */
+	status = vxge_hw_mrpcim_stats_access(
+				hldev,
+				VXGE_HW_STATS_OP_CLEAR_ALL_STATS,
+				0,
+				0,
+				&stat);
+
+	if (status == VXGE_HW_ERR_PRIVILAGED_OPEARATION)
+		vxge_debug_init(
+			vxge_hw_device_trace_level_get(hldev),
+			"%s: device stats clear returns"
+			"VXGE_HW_ERR_PRIVILAGED_OPEARATION", ndev->name);
+
+	vxge_debug_entryexit(vxge_hw_device_trace_level_get(hldev),
+		"%s: %s:%d  Exiting...",
+		ndev->name, __func__, __LINE__);
+
+	return ret;
+_out2:
+	kfree(vdev->vpaths);
+_out1:
+	free_netdev(ndev);
+_out0:
+	return ret;
+}
+
+/*
+ * vxge_device_unregister
+ *
+ * This function will unregister and free network device
+ */
+void
+vxge_device_unregister(struct __vxge_hw_device *hldev)
+{
+	struct vxgedev *vdev;
+	struct net_device *dev;
+	char buf[IFNAMSIZ];
+#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \
+	(VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK))
+	u32 level_trace;
+#endif
+
+	dev = hldev->ndev;
+	vdev = netdev_priv(dev);
+#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \
+	(VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK))
+	level_trace = vdev->level_trace;
+#endif
+	vxge_debug_entryexit(level_trace,
+		"%s: %s:%d", vdev->ndev->name, __func__, __LINE__);
+
+	memcpy(buf, vdev->ndev->name, IFNAMSIZ);
+
+	/* in 2.6 will call stop() if device is up */
+	unregister_netdev(dev);
+
+	flush_scheduled_work();
+
+	vxge_debug_init(level_trace, "%s: ethernet device unregistered", buf);
+	vxge_debug_entryexit(level_trace,
+		"%s: %s:%d  Exiting...", buf, __func__, __LINE__);
+}
+
+/*
+ * vxge_callback_crit_err
+ *
+ * This function is called by the alarm handler in interrupt context.
+ * Driver must analyze it based on the event type.
+ */
+static void
+vxge_callback_crit_err(struct __vxge_hw_device *hldev,
+			enum vxge_hw_event type, u64 vp_id)
+{
+	struct net_device *dev = hldev->ndev;
+	struct vxgedev *vdev = (struct vxgedev *)netdev_priv(dev);
+	int vpath_idx;
+
+	vxge_debug_entryexit(vdev->level_trace,
+		"%s: %s:%d", vdev->ndev->name, __func__, __LINE__);
+
+	/* Note: This event type should be used for device wide
+	 * indications only - Serious errors, Slot freeze and critical errors
+	 */
+	vdev->cric_err_event = type;
+
+	for (vpath_idx = 0; vpath_idx < vdev->no_of_vpath; vpath_idx++)
+		if (vdev->vpaths[vpath_idx].device_id == vp_id)
+			break;
+
+	if (!test_bit(__VXGE_STATE_RESET_CARD, &vdev->state)) {
+		if (type == VXGE_HW_EVENT_SLOT_FREEZE) {
+			vxge_debug_init(VXGE_ERR,
+				"%s: Slot is frozen", vdev->ndev->name);
+		} else if (type == VXGE_HW_EVENT_SERR) {
+			vxge_debug_init(VXGE_ERR,
+				"%s: Encountered Serious Error",
+				vdev->ndev->name);
+		} else if (type == VXGE_HW_EVENT_CRITICAL_ERR)
+			vxge_debug_init(VXGE_ERR,
+				"%s: Encountered Critical Error",
+				vdev->ndev->name);
+	}
+
+	if ((type == VXGE_HW_EVENT_SERR) ||
+		(type == VXGE_HW_EVENT_SLOT_FREEZE)) {
+		if (unlikely(vdev->exec_mode))
+			clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+	} else if (type == VXGE_HW_EVENT_CRITICAL_ERR) {
+		vxge_hw_device_mask_all(hldev);
+		if (unlikely(vdev->exec_mode))
+			clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+	} else if ((type == VXGE_HW_EVENT_FIFO_ERR) ||
+		  (type == VXGE_HW_EVENT_VPATH_ERR)) {
+
+		if (unlikely(vdev->exec_mode))
+			clear_bit(__VXGE_STATE_CARD_UP, &vdev->state);
+		else {
+			/* check if this vpath is already set for reset */
+			if (!test_and_set_bit(vpath_idx, &vdev->vp_reset)) {
+
+				/* disable interrupts for this vpath */
+				vxge_vpath_intr_disable(vdev, vpath_idx);
+
+				/* stop the queue for this vpath */
+				vxge_stop_tx_queue(&vdev->vpaths[vpath_idx].
+							fifo);
+			}
+		}
+	}
+
+	vxge_debug_entryexit(vdev->level_trace,
+		"%s: %s:%d  Exiting...",
+		vdev->ndev->name, __func__, __LINE__);
+}
+
+static void verify_bandwidth(void)
+{
+	int i, band_width, total = 0, equal_priority = 0;
+
+	/* 1. If user enters 0 for some fifo, give equal priority to all */
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		if (bw_percentage[i] == 0) {
+			equal_priority = 1;
+			break;
+		}
+	}
+
+	if (!equal_priority) {
+		/* 2. If sum exceeds 100, give equal priority to all */
+		for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+			if (bw_percentage[i] == 0xFF)
+				break;
+
+			total += bw_percentage[i];
+			if (total > VXGE_HW_VPATH_BANDWIDTH_MAX) {
+				equal_priority = 1;
+				break;
+			}
+		}
+	}
+
+	if (!equal_priority) {
+		/* Is all the bandwidth consumed? */
+		if (total < VXGE_HW_VPATH_BANDWIDTH_MAX) {
+			if (i < VXGE_HW_MAX_VIRTUAL_PATHS) {
+				/* Split rest of bw equally among next VPs*/
+				band_width =
+				  (VXGE_HW_VPATH_BANDWIDTH_MAX  - total) /
+					(VXGE_HW_MAX_VIRTUAL_PATHS - i);
+				if (band_width < 2) /* min of 2% */
+					equal_priority = 1;
+				else {
+					for (; i < VXGE_HW_MAX_VIRTUAL_PATHS;
+						i++)
+						bw_percentage[i] =
+							band_width;
+				}
+			}
+		} else if (i < VXGE_HW_MAX_VIRTUAL_PATHS)
+			equal_priority = 1;
+	}
+
+	if (equal_priority) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: Assigning equal bandwidth to all the vpaths",
+			VXGE_DRIVER_NAME);
+		bw_percentage[0] = VXGE_HW_VPATH_BANDWIDTH_MAX /
+					VXGE_HW_MAX_VIRTUAL_PATHS;
+		for (i = 1; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
+			bw_percentage[i] = bw_percentage[0];
+	}
+
+	return;
+}
+
+/*
+ * Vpath configuration
+ */
+static int __devinit vxge_config_vpaths(
+			struct vxge_hw_device_config *device_config,
+			u64 vpath_mask, struct vxge_config *config_param)
+{
+	int i, no_of_vpaths = 0, default_no_vpath = 0, temp;
+	u32 txdl_size, txdl_per_memblock;
+
+	temp = driver_config->vpath_per_dev;
+	if ((driver_config->vpath_per_dev == VXGE_USE_DEFAULT) &&
+		(max_config_dev == VXGE_MAX_CONFIG_DEV)) {
+		/* No more CPU. Return vpath number as zero.*/
+		if (driver_config->g_no_cpus == -1)
+			return 0;
+
+		if (!driver_config->g_no_cpus)
+			driver_config->g_no_cpus = num_online_cpus();
+
+		driver_config->vpath_per_dev = driver_config->g_no_cpus >> 1;
+		if (!driver_config->vpath_per_dev)
+			driver_config->vpath_per_dev = 1;
+
+		for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
+			if (!vxge_bVALn(vpath_mask, i, 1))
+				continue;
+			else
+				default_no_vpath++;
+		if (default_no_vpath < driver_config->vpath_per_dev)
+			driver_config->vpath_per_dev = default_no_vpath;
+
+		driver_config->g_no_cpus = driver_config->g_no_cpus -
+				(driver_config->vpath_per_dev * 2);
+		if (driver_config->g_no_cpus <= 0)
+			driver_config->g_no_cpus = -1;
+	}
+
+	if (driver_config->vpath_per_dev == 1) {
+		vxge_debug_ll_config(VXGE_TRACE,
+			"%s: Disable tx and rx steering, "
+			"as single vpath is configured", VXGE_DRIVER_NAME);
+		config_param->rth_steering = NO_STEERING;
+		config_param->tx_steering_type = NO_STEERING;
+		device_config->rth_en = 0;
+	}
+
+	/* configure bandwidth */
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++)
+		device_config->vp_config[i].min_bandwidth = bw_percentage[i];
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		device_config->vp_config[i].vp_id = i;
+		device_config->vp_config[i].mtu = VXGE_HW_DEFAULT_MTU;
+		if (no_of_vpaths < driver_config->vpath_per_dev) {
+			if (!vxge_bVALn(vpath_mask, i, 1)) {
+				vxge_debug_ll_config(VXGE_TRACE,
+					"%s: vpath: %d is not available",
+					VXGE_DRIVER_NAME, i);
+				continue;
+			} else {
+				vxge_debug_ll_config(VXGE_TRACE,
+					"%s: vpath: %d available",
+					VXGE_DRIVER_NAME, i);
+				no_of_vpaths++;
+			}
+		} else {
+			vxge_debug_ll_config(VXGE_TRACE,
+				"%s: vpath: %d is not configured, "
+				"max_config_vpath exceeded",
+				VXGE_DRIVER_NAME, i);
+			break;
+		}
+
+		/* Configure Tx fifo's */
+		device_config->vp_config[i].fifo.enable =
+						VXGE_HW_FIFO_ENABLE;
+		device_config->vp_config[i].fifo.max_frags =
+				MAX_SKB_FRAGS;
+		device_config->vp_config[i].fifo.memblock_size =
+			VXGE_HW_MIN_FIFO_MEMBLOCK_SIZE;
+
+		txdl_size = MAX_SKB_FRAGS * sizeof(struct vxge_hw_fifo_txd);
+		txdl_per_memblock = VXGE_HW_MIN_FIFO_MEMBLOCK_SIZE / txdl_size;
+
+		device_config->vp_config[i].fifo.fifo_blocks =
+			((VXGE_DEF_FIFO_LENGTH - 1) / txdl_per_memblock) + 1;
+
+		device_config->vp_config[i].fifo.intr =
+				VXGE_HW_FIFO_QUEUE_INTR_DISABLE;
+
+		/* Configure tti properties */
+		device_config->vp_config[i].tti.intr_enable =
+					VXGE_HW_TIM_INTR_ENABLE;
+
+		device_config->vp_config[i].tti.btimer_val =
+			(VXGE_TTI_BTIMER_VAL * 1000) / 272;
+
+		device_config->vp_config[i].tti.timer_ac_en =
+				VXGE_HW_TIM_TIMER_AC_ENABLE;
+
+		/* For msi-x with napi (each vector
+		has a handler of its own) -
+		Set CI to OFF for all vpaths */
+		device_config->vp_config[i].tti.timer_ci_en =
+			VXGE_HW_TIM_TIMER_CI_DISABLE;
+
+		device_config->vp_config[i].tti.timer_ri_en =
+				VXGE_HW_TIM_TIMER_RI_DISABLE;
+
+		device_config->vp_config[i].tti.util_sel =
+			VXGE_HW_TIM_UTIL_SEL_LEGACY_TX_NET_UTIL;
+
+		device_config->vp_config[i].tti.ltimer_val =
+			(VXGE_TTI_LTIMER_VAL * 1000) / 272;
+
+		device_config->vp_config[i].tti.rtimer_val =
+			(VXGE_TTI_RTIMER_VAL * 1000) / 272;
+
+		device_config->vp_config[i].tti.urange_a = TTI_TX_URANGE_A;
+		device_config->vp_config[i].tti.urange_b = TTI_TX_URANGE_B;
+		device_config->vp_config[i].tti.urange_c = TTI_TX_URANGE_C;
+		device_config->vp_config[i].tti.uec_a = TTI_TX_UFC_A;
+		device_config->vp_config[i].tti.uec_b = TTI_TX_UFC_B;
+		device_config->vp_config[i].tti.uec_c = TTI_TX_UFC_C;
+		device_config->vp_config[i].tti.uec_d = TTI_TX_UFC_D;
+
+		/* Configure Rx rings */
+		device_config->vp_config[i].ring.enable  =
+						VXGE_HW_RING_ENABLE;
+
+		device_config->vp_config[i].ring.ring_blocks  =
+						VXGE_HW_DEF_RING_BLOCKS;
+		device_config->vp_config[i].ring.buffer_mode =
+			VXGE_HW_RING_RXD_BUFFER_MODE_1;
+		device_config->vp_config[i].ring.rxds_limit  =
+				VXGE_HW_DEF_RING_RXDS_LIMIT;
+		device_config->vp_config[i].ring.scatter_mode =
+					VXGE_HW_RING_SCATTER_MODE_A;
+
+		/* Configure rti properties */
+		device_config->vp_config[i].rti.intr_enable =
+					VXGE_HW_TIM_INTR_ENABLE;
+
+		device_config->vp_config[i].rti.btimer_val =
+			(VXGE_RTI_BTIMER_VAL * 1000)/272;
+
+		device_config->vp_config[i].rti.timer_ac_en =
+						VXGE_HW_TIM_TIMER_AC_ENABLE;
+
+		device_config->vp_config[i].rti.timer_ci_en =
+						VXGE_HW_TIM_TIMER_CI_DISABLE;
+
+		device_config->vp_config[i].rti.timer_ri_en =
+						VXGE_HW_TIM_TIMER_RI_DISABLE;
+
+		device_config->vp_config[i].rti.util_sel =
+				VXGE_HW_TIM_UTIL_SEL_LEGACY_RX_NET_UTIL;
+
+		device_config->vp_config[i].rti.urange_a =
+						RTI_RX_URANGE_A;
+		device_config->vp_config[i].rti.urange_b =
+						RTI_RX_URANGE_B;
+		device_config->vp_config[i].rti.urange_c =
+						RTI_RX_URANGE_C;
+		device_config->vp_config[i].rti.uec_a = RTI_RX_UFC_A;
+		device_config->vp_config[i].rti.uec_b = RTI_RX_UFC_B;
+		device_config->vp_config[i].rti.uec_c = RTI_RX_UFC_C;
+		device_config->vp_config[i].rti.uec_d = RTI_RX_UFC_D;
+
+		device_config->vp_config[i].rti.rtimer_val =
+			(VXGE_RTI_RTIMER_VAL * 1000) / 272;
+
+		device_config->vp_config[i].rti.ltimer_val =
+			(VXGE_RTI_LTIMER_VAL * 1000) / 272;
+
+		device_config->vp_config[i].rpa_strip_vlan_tag =
+			vlan_tag_strip;
+	}
+
+	driver_config->vpath_per_dev = temp;
+	return no_of_vpaths;
+}
+
+/* initialize device configuratrions */
+static void __devinit vxge_device_config_init(
+				struct vxge_hw_device_config *device_config,
+				int *intr_type)
+{
+	/* Used for CQRQ/SRQ. */
+	device_config->dma_blockpool_initial =
+			VXGE_HW_INITIAL_DMA_BLOCK_POOL_SIZE;
+
+	device_config->dma_blockpool_max =
+			VXGE_HW_MAX_DMA_BLOCK_POOL_SIZE;
+
+	if (max_mac_vpath > VXGE_MAX_MAC_ADDR_COUNT)
+		max_mac_vpath = VXGE_MAX_MAC_ADDR_COUNT;
+
+#ifndef CONFIG_PCI_MSI
+	vxge_debug_init(VXGE_ERR,
+		"%s: This Kernel does not support "
+		"MSI-X. Defaulting to INTA", VXGE_DRIVER_NAME);
+	*intr_type = INTA;
+#endif
+
+	/* Configure whether MSI-X or IRQL. */
+	switch (*intr_type) {
+	case INTA:
+		device_config->intr_mode = VXGE_HW_INTR_MODE_IRQLINE;
+		break;
+
+	case MSI_X:
+		device_config->intr_mode = VXGE_HW_INTR_MODE_MSIX;
+		break;
+	}
+	/* Timer period between device poll */
+	device_config->device_poll_millis = VXGE_TIMER_DELAY;
+
+	/* Configure mac based steering. */
+	device_config->rts_mac_en = addr_learn_en;
+
+	/* Configure Vpaths */
+	device_config->rth_it_type = VXGE_HW_RTH_IT_TYPE_MULTI_IT;
+
+	vxge_debug_ll_config(VXGE_TRACE, "%s : Device Config Params ",
+			__func__);
+	vxge_debug_ll_config(VXGE_TRACE, "dma_blockpool_initial : %d",
+			device_config->dma_blockpool_initial);
+	vxge_debug_ll_config(VXGE_TRACE, "dma_blockpool_max : %d",
+			device_config->dma_blockpool_max);
+	vxge_debug_ll_config(VXGE_TRACE, "intr_mode : %d",
+			device_config->intr_mode);
+	vxge_debug_ll_config(VXGE_TRACE, "device_poll_millis : %d",
+			device_config->device_poll_millis);
+	vxge_debug_ll_config(VXGE_TRACE, "rts_mac_en : %d",
+			device_config->rts_mac_en);
+	vxge_debug_ll_config(VXGE_TRACE, "rth_en : %d",
+			device_config->rth_en);
+	vxge_debug_ll_config(VXGE_TRACE, "rth_it_type : %d",
+			device_config->rth_it_type);
+}
+
+static void __devinit vxge_print_parm(struct vxgedev *vdev, u64 vpath_mask)
+{
+	int i;
+
+	vxge_debug_init(VXGE_TRACE,
+		"%s: %d Vpath(s) opened",
+		vdev->ndev->name, vdev->no_of_vpath);
+
+	switch (vdev->config.intr_type) {
+	case INTA:
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Interrupt type INTA", vdev->ndev->name);
+		break;
+
+	case MSI_X:
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Interrupt type MSI-X", vdev->ndev->name);
+		break;
+	}
+
+	if (vdev->config.rth_steering) {
+		vxge_debug_init(VXGE_TRACE,
+			"%s: RTH steering enabled for TCP_IPV4",
+			vdev->ndev->name);
+	} else {
+		vxge_debug_init(VXGE_TRACE,
+			"%s: RTH steering disabled", vdev->ndev->name);
+	}
+
+	switch (vdev->config.tx_steering_type) {
+	case NO_STEERING:
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Tx steering disabled", vdev->ndev->name);
+		break;
+	case TX_PRIORITY_STEERING:
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Unsupported tx steering option",
+			vdev->ndev->name);
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Tx steering disabled", vdev->ndev->name);
+		vdev->config.tx_steering_type = 0;
+		break;
+	case TX_VLAN_STEERING:
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Unsupported tx steering option",
+			vdev->ndev->name);
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Tx steering disabled", vdev->ndev->name);
+		vdev->config.tx_steering_type = 0;
+		break;
+	case TX_MULTIQ_STEERING:
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Tx multiqueue steering enabled",
+			vdev->ndev->name);
+		break;
+	case TX_PORT_STEERING:
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Tx port steering enabled",
+			vdev->ndev->name);
+		break;
+	default:
+		vxge_debug_init(VXGE_ERR,
+			"%s: Unsupported tx steering type",
+			vdev->ndev->name);
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Tx steering disabled", vdev->ndev->name);
+		vdev->config.tx_steering_type = 0;
+	}
+
+	if (vdev->config.gro_enable) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: Generic receive offload enabled",
+			vdev->ndev->name);
+	} else
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Generic receive offload disabled",
+			vdev->ndev->name);
+
+	if (vdev->config.addr_learn_en)
+		vxge_debug_init(VXGE_TRACE,
+			"%s: MAC Address learning enabled", vdev->ndev->name);
+
+	vxge_debug_init(VXGE_TRACE,
+		"%s: Rx doorbell mode enabled", vdev->ndev->name);
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		if (!vxge_bVALn(vpath_mask, i, 1))
+			continue;
+		vxge_debug_ll_config(VXGE_TRACE,
+			"%s: MTU size - %d", vdev->ndev->name,
+			((struct __vxge_hw_device  *)(vdev->devh))->
+				config.vp_config[i].mtu);
+		vxge_debug_init(VXGE_TRACE,
+			"%s: VLAN tag stripping %s", vdev->ndev->name,
+			((struct __vxge_hw_device  *)(vdev->devh))->
+				config.vp_config[i].rpa_strip_vlan_tag
+			? "Enabled" : "Disabled");
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Ring blocks : %d", vdev->ndev->name,
+			((struct __vxge_hw_device  *)(vdev->devh))->
+				config.vp_config[i].ring.ring_blocks);
+		vxge_debug_init(VXGE_TRACE,
+			"%s: Fifo blocks : %d", vdev->ndev->name,
+			((struct __vxge_hw_device  *)(vdev->devh))->
+				config.vp_config[i].fifo.fifo_blocks);
+		vxge_debug_ll_config(VXGE_TRACE,
+			"%s: Max frags : %d", vdev->ndev->name,
+			((struct __vxge_hw_device  *)(vdev->devh))->
+				config.vp_config[i].fifo.max_frags);
+		break;
+	}
+}
+
+#ifdef CONFIG_PM
+/**
+ * vxge_pm_suspend - vxge power management suspend entry point
+ *
+ */
+static int vxge_pm_suspend(struct pci_dev *pdev, pm_message_t state)
+{
+	return -ENOSYS;
+}
+/**
+ * vxge_pm_resume - vxge power management resume entry point
+ *
+ */
+static int vxge_pm_resume(struct pci_dev *pdev)
+{
+	return -ENOSYS;
+}
+
+#endif
+
+/**
+ * vxge_io_error_detected - called when PCI error is detected
+ * @pdev: Pointer to PCI device
+ * @state: The current pci connection state
+ *
+ * This function is called after a PCI bus error affecting
+ * this device has been detected.
+ */
+static pci_ers_result_t vxge_io_error_detected(struct pci_dev *pdev,
+						pci_channel_state_t state)
+{
+	struct __vxge_hw_device  *hldev =
+		(struct __vxge_hw_device  *) pci_get_drvdata(pdev);
+	struct net_device *netdev = hldev->ndev;
+
+	netif_device_detach(netdev);
+
+	if (netif_running(netdev)) {
+		/* Bring down the card, while avoiding PCI I/O */
+		do_vxge_close(netdev, 0);
+	}
+
+	pci_disable_device(pdev);
+
+	return PCI_ERS_RESULT_NEED_RESET;
+}
+
+/**
+ * vxge_io_slot_reset - called after the pci bus has been reset.
+ * @pdev: Pointer to PCI device
+ *
+ * Restart the card from scratch, as if from a cold-boot.
+ * At this point, the card has exprienced a hard reset,
+ * followed by fixups by BIOS, and has its config space
+ * set up identically to what it was at cold boot.
+ */
+static pci_ers_result_t vxge_io_slot_reset(struct pci_dev *pdev)
+{
+	struct __vxge_hw_device  *hldev =
+		(struct __vxge_hw_device  *) pci_get_drvdata(pdev);
+	struct net_device *netdev = hldev->ndev;
+
+	struct vxgedev *vdev = netdev_priv(netdev);
+
+	if (pci_enable_device(pdev)) {
+		printk(KERN_ERR "%s: "
+			"Cannot re-enable device after reset\n",
+			VXGE_DRIVER_NAME);
+		return PCI_ERS_RESULT_DISCONNECT;
+	}
+
+	pci_set_master(pdev);
+	vxge_reset(vdev);
+
+	return PCI_ERS_RESULT_RECOVERED;
+}
+
+/**
+ * vxge_io_resume - called when traffic can start flowing again.
+ * @pdev: Pointer to PCI device
+ *
+ * This callback is called when the error recovery driver tells
+ * us that its OK to resume normal operation.
+ */
+static void vxge_io_resume(struct pci_dev *pdev)
+{
+	struct __vxge_hw_device  *hldev =
+		(struct __vxge_hw_device  *) pci_get_drvdata(pdev);
+	struct net_device *netdev = hldev->ndev;
+
+	if (netif_running(netdev)) {
+		if (vxge_open(netdev)) {
+			printk(KERN_ERR "%s: "
+				"Can't bring device back up after reset\n",
+				VXGE_DRIVER_NAME);
+			return;
+		}
+	}
+
+	netif_device_attach(netdev);
+}
+
+/**
+ * vxge_probe
+ * @pdev : structure containing the PCI related information of the device.
+ * @pre: List of PCI devices supported by the driver listed in vxge_id_table.
+ * Description:
+ * This function is called when a new PCI device gets detected and initializes
+ * it.
+ * Return value:
+ * returns 0 on success and negative on failure.
+ *
+ */
+static int __devinit
+vxge_probe(struct pci_dev *pdev, const struct pci_device_id *pre)
+{
+	struct __vxge_hw_device  *hldev;
+	enum vxge_hw_status status;
+	int ret;
+	int high_dma = 0;
+	u64 vpath_mask = 0;
+	struct vxgedev *vdev;
+	struct vxge_config ll_config;
+	struct vxge_hw_device_config *device_config = NULL;
+	struct vxge_hw_device_attr attr;
+	int i, j, no_of_vpath = 0, max_vpath_supported = 0;
+	u8 *macaddr;
+	struct vxge_mac_addrs *entry;
+	static int bus = -1, device = -1;
+	u8 new_device = 0;
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s:%d", __func__, __LINE__);
+	attr.pdev = pdev;
+
+	if (bus != pdev->bus->number)
+		new_device = 1;
+	if (device != PCI_SLOT(pdev->devfn))
+		new_device = 1;
+
+	bus = pdev->bus->number;
+	device = PCI_SLOT(pdev->devfn);
+
+	if (new_device) {
+		if (driver_config->config_dev_cnt &&
+		   (driver_config->config_dev_cnt !=
+			driver_config->total_dev_cnt))
+			vxge_debug_init(VXGE_ERR,
+				"%s: Configured %d of %d devices",
+				VXGE_DRIVER_NAME,
+				driver_config->config_dev_cnt,
+				driver_config->total_dev_cnt);
+		driver_config->config_dev_cnt = 0;
+		driver_config->total_dev_cnt = 0;
+		driver_config->g_no_cpus = 0;
+		driver_config->vpath_per_dev = max_config_vpath;
+	}
+
+	driver_config->total_dev_cnt++;
+	if (++driver_config->config_dev_cnt > max_config_dev) {
+		ret = 0;
+		goto _exit0;
+	}
+
+	device_config = kzalloc(sizeof(struct vxge_hw_device_config),
+		GFP_KERNEL);
+	if (!device_config) {
+		ret = -ENOMEM;
+		vxge_debug_init(VXGE_ERR,
+			"device_config : malloc failed %s %d",
+			__FILE__, __LINE__);
+		goto _exit0;
+	}
+
+	memset(&ll_config, 0, sizeof(struct vxge_config));
+	ll_config.tx_steering_type = TX_MULTIQ_STEERING;
+	ll_config.intr_type = MSI_X;
+	ll_config.napi_weight = NEW_NAPI_WEIGHT;
+	ll_config.rth_steering = RTH_STEERING;
+
+	/* get the default configuration parameters */
+	vxge_hw_device_config_default_get(device_config);
+
+	/* initialize configuration parameters */
+	vxge_device_config_init(device_config, &ll_config.intr_type);
+
+	ret = pci_enable_device(pdev);
+	if (ret) {
+		vxge_debug_init(VXGE_ERR,
+			"%s : can not enable PCI device", __func__);
+		goto _exit0;
+	}
+
+	if (!pci_set_dma_mask(pdev, 0xffffffffffffffffULL)) {
+		vxge_debug_ll_config(VXGE_TRACE,
+			"%s : using 64bit DMA", __func__);
+
+		high_dma = 1;
+
+		if (pci_set_consistent_dma_mask(pdev,
+						0xffffffffffffffffULL)) {
+			vxge_debug_init(VXGE_ERR,
+				"%s : unable to obtain 64bit DMA for "
+				"consistent allocations", __func__);
+			ret = -ENOMEM;
+			goto _exit1;
+		}
+	} else if (!pci_set_dma_mask(pdev, 0xffffffffUL)) {
+		vxge_debug_ll_config(VXGE_TRACE,
+			"%s : using 32bit DMA", __func__);
+	} else {
+		ret = -ENOMEM;
+		goto _exit1;
+	}
+
+	if (pci_request_regions(pdev, VXGE_DRIVER_NAME)) {
+		vxge_debug_init(VXGE_ERR,
+			"%s : request regions failed", __func__);
+		ret = -ENODEV;
+		goto _exit1;
+	}
+
+	pci_set_master(pdev);
+
+	attr.bar0 = pci_ioremap_bar(pdev, 0);
+	if (!attr.bar0) {
+		vxge_debug_init(VXGE_ERR,
+			"%s : cannot remap io memory bar0", __func__);
+		ret = -ENODEV;
+		goto _exit2;
+	}
+	vxge_debug_ll_config(VXGE_TRACE,
+		"pci ioremap bar0: %p:0x%llx",
+		attr.bar0,
+		(unsigned long long)pci_resource_start(pdev, 0));
+
+	attr.bar1 = pci_ioremap_bar(pdev, 2);
+	if (!attr.bar1) {
+		vxge_debug_init(VXGE_ERR,
+			"%s : cannot remap io memory bar2", __func__);
+		ret = -ENODEV;
+		goto _exit3;
+	}
+	vxge_debug_ll_config(VXGE_TRACE,
+		"pci ioremap bar1: %p:0x%llx",
+		attr.bar1,
+		(unsigned long long)pci_resource_start(pdev, 2));
+
+	status = vxge_hw_device_hw_info_get(attr.bar0,
+			&ll_config.device_hw_info);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"%s: Reading of hardware info failed."
+			"Please try upgrading the firmware.", VXGE_DRIVER_NAME);
+		ret = -EINVAL;
+		goto _exit4;
+	}
+
+	if (ll_config.device_hw_info.fw_version.major !=
+		VXGE_DRIVER_VERSION_MAJOR) {
+		vxge_debug_init(VXGE_ERR,
+			"FW Ver.(maj): %d not driver's expected version: %d",
+			ll_config.device_hw_info.fw_version.major,
+			VXGE_DRIVER_VERSION_MAJOR);
+		ret = -EINVAL;
+		goto _exit4;
+	}
+
+	vpath_mask = ll_config.device_hw_info.vpath_mask;
+	if (vpath_mask == 0) {
+		vxge_debug_ll_config(VXGE_TRACE,
+			"%s: No vpaths available in device", VXGE_DRIVER_NAME);
+		ret = -EINVAL;
+		goto _exit4;
+	}
+
+	vxge_debug_ll_config(VXGE_TRACE,
+		"%s:%d  Vpath mask = %llx", __func__, __LINE__,
+		(unsigned long long)vpath_mask);
+
+	/* Check how many vpaths are available */
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		if (!((vpath_mask) & vxge_mBIT(i)))
+			continue;
+		max_vpath_supported++;
+	}
+
+	/*
+	 * Configure vpaths and get driver configured number of vpaths
+	 * which is less than or equal to the maximum vpaths per function.
+	 */
+	no_of_vpath = vxge_config_vpaths(device_config, vpath_mask, &ll_config);
+	if (!no_of_vpath) {
+		vxge_debug_ll_config(VXGE_ERR,
+			"%s: No more vpaths to configure", VXGE_DRIVER_NAME);
+		ret = 0;
+		goto _exit4;
+	}
+
+	/* Setting driver callbacks */
+	attr.uld_callbacks.link_up = vxge_callback_link_up;
+	attr.uld_callbacks.link_down = vxge_callback_link_down;
+	attr.uld_callbacks.crit_err = vxge_callback_crit_err;
+
+	status = vxge_hw_device_initialize(&hldev, &attr, device_config);
+	if (status != VXGE_HW_OK) {
+		vxge_debug_init(VXGE_ERR,
+			"Failed to initialize device (%d)", status);
+			ret = -EINVAL;
+			goto _exit4;
+	}
+
+	vxge_hw_device_debug_set(hldev, VXGE_ERR, VXGE_COMPONENT_LL);
+
+	/* set private device info */
+	pci_set_drvdata(pdev, hldev);
+
+	ll_config.gro_enable = VXGE_GRO_ALWAYS_AGGREGATE;
+	ll_config.fifo_indicate_max_pkts = VXGE_FIFO_INDICATE_MAX_PKTS;
+	ll_config.addr_learn_en = addr_learn_en;
+	ll_config.rth_algorithm = RTH_ALG_JENKINS;
+	ll_config.rth_hash_type_tcpipv4 = VXGE_HW_RING_HASH_TYPE_TCP_IPV4;
+	ll_config.rth_hash_type_ipv4 = VXGE_HW_RING_HASH_TYPE_NONE;
+	ll_config.rth_hash_type_tcpipv6 = VXGE_HW_RING_HASH_TYPE_NONE;
+	ll_config.rth_hash_type_ipv6 = VXGE_HW_RING_HASH_TYPE_NONE;
+	ll_config.rth_hash_type_tcpipv6ex = VXGE_HW_RING_HASH_TYPE_NONE;
+	ll_config.rth_hash_type_ipv6ex = VXGE_HW_RING_HASH_TYPE_NONE;
+	ll_config.rth_bkt_sz = RTH_BUCKET_SIZE;
+	ll_config.tx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;
+	ll_config.rx_pause_enable = VXGE_PAUSE_CTRL_ENABLE;
+
+	if (vxge_device_register(hldev, &ll_config, high_dma, no_of_vpath,
+		&vdev)) {
+		ret = -EINVAL;
+		goto _exit5;
+	}
+
+	vxge_hw_device_debug_set(hldev, VXGE_TRACE, VXGE_COMPONENT_LL);
+	VXGE_COPY_DEBUG_INFO_TO_LL(vdev, vxge_hw_device_error_level_get(hldev),
+		vxge_hw_device_trace_level_get(hldev));
+
+	/* set private HW device info */
+	hldev->ndev = vdev->ndev;
+	vdev->mtu = VXGE_HW_DEFAULT_MTU;
+	vdev->bar0 = attr.bar0;
+	vdev->bar1 = attr.bar1;
+	vdev->max_vpath_supported = max_vpath_supported;
+	vdev->no_of_vpath = no_of_vpath;
+
+	/* Virtual Path count */
+	for (i = 0, j = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+		if (!vxge_bVALn(vpath_mask, i, 1))
+			continue;
+		if (j >= vdev->no_of_vpath)
+			break;
+
+		vdev->vpaths[j].is_configured = 1;
+		vdev->vpaths[j].device_id = i;
+		vdev->vpaths[j].fifo.driver_id = j;
+		vdev->vpaths[j].ring.driver_id = j;
+		vdev->vpaths[j].vdev = vdev;
+		vdev->vpaths[j].max_mac_addr_cnt = max_mac_vpath;
+		memcpy((u8 *)vdev->vpaths[j].macaddr,
+				(u8 *)ll_config.device_hw_info.mac_addrs[i],
+				ETH_ALEN);
+
+		/* Initialize the mac address list header */
+		INIT_LIST_HEAD(&vdev->vpaths[j].mac_addr_list);
+
+		vdev->vpaths[j].mac_addr_cnt = 0;
+		vdev->vpaths[j].mcast_addr_cnt = 0;
+		j++;
+	}
+	vdev->exec_mode = VXGE_EXEC_MODE_DISABLE;
+	vdev->max_config_port = max_config_port;
+
+	vdev->vlan_tag_strip = vlan_tag_strip;
+
+	/* map the hashing selector table to the configured vpaths */
+	for (i = 0; i < vdev->no_of_vpath; i++)
+		vdev->vpath_selector[i] = vpath_selector[i];
+
+	macaddr = (u8 *)vdev->vpaths[0].macaddr;
+
+	ll_config.device_hw_info.serial_number[VXGE_HW_INFO_LEN - 1] = '\0';
+	ll_config.device_hw_info.product_desc[VXGE_HW_INFO_LEN - 1] = '\0';
+	ll_config.device_hw_info.part_number[VXGE_HW_INFO_LEN - 1] = '\0';
+
+	vxge_debug_init(VXGE_TRACE, "%s: SERIAL NUMBER: %s",
+		vdev->ndev->name, ll_config.device_hw_info.serial_number);
+
+	vxge_debug_init(VXGE_TRACE, "%s: PART NUMBER: %s",
+		vdev->ndev->name, ll_config.device_hw_info.part_number);
+
+	vxge_debug_init(VXGE_TRACE, "%s: Neterion %s Server Adapter",
+		vdev->ndev->name, ll_config.device_hw_info.product_desc);
+
+	vxge_debug_init(VXGE_TRACE,
+		"%s: MAC ADDR: %02X:%02X:%02X:%02X:%02X:%02X",
+		vdev->ndev->name, macaddr[0], macaddr[1], macaddr[2],
+		macaddr[3], macaddr[4], macaddr[5]);
+
+	vxge_debug_init(VXGE_TRACE, "%s: Link Width x%d",
+		vdev->ndev->name, vxge_hw_device_link_width_get(hldev));
+
+	vxge_debug_init(VXGE_TRACE,
+		"%s: Firmware version : %s Date : %s", vdev->ndev->name,
+		ll_config.device_hw_info.fw_version.version,
+		ll_config.device_hw_info.fw_date.date);
+
+	vxge_print_parm(vdev, vpath_mask);
+
+	/* Store the fw version for ethttool option */
+	strcpy(vdev->fw_version, ll_config.device_hw_info.fw_version.version);
+	memcpy(vdev->ndev->dev_addr, (u8 *)vdev->vpaths[0].macaddr, ETH_ALEN);
+	memcpy(vdev->ndev->perm_addr, vdev->ndev->dev_addr, ETH_ALEN);
+
+	/* Copy the station mac address to the list */
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		entry =	(struct vxge_mac_addrs *)
+				kzalloc(sizeof(struct vxge_mac_addrs),
+					GFP_KERNEL);
+		if (NULL == entry) {
+			vxge_debug_init(VXGE_ERR,
+				"%s: mac_addr_list : memory allocation failed",
+				vdev->ndev->name);
+			ret = -EPERM;
+			goto _exit6;
+		}
+		macaddr = (u8 *)&entry->macaddr;
+		memcpy(macaddr, vdev->ndev->dev_addr, ETH_ALEN);
+		list_add(&entry->item, &vdev->vpaths[i].mac_addr_list);
+		vdev->vpaths[i].mac_addr_cnt = 1;
+	}
+
+	vxge_debug_entryexit(VXGE_TRACE, "%s: %s:%d  Exiting...",
+		vdev->ndev->name, __func__, __LINE__);
+
+	vxge_hw_device_debug_set(hldev, VXGE_ERR, VXGE_COMPONENT_LL);
+	VXGE_COPY_DEBUG_INFO_TO_LL(vdev, vxge_hw_device_error_level_get(hldev),
+		vxge_hw_device_trace_level_get(hldev));
+
+	return 0;
+
+_exit6:
+	for (i = 0; i < vdev->no_of_vpath; i++)
+		vxge_free_mac_add_list(&vdev->vpaths[i]);
+
+	vxge_device_unregister(hldev);
+_exit5:
+	vxge_hw_device_terminate(hldev);
+_exit4:
+	iounmap(attr.bar1);
+_exit3:
+	iounmap(attr.bar0);
+_exit2:
+	pci_release_regions(pdev);
+_exit1:
+	pci_disable_device(pdev);
+_exit0:
+	kfree(device_config);
+	driver_config->config_dev_cnt--;
+	pci_set_drvdata(pdev, NULL);
+	return ret;
+}
+
+/**
+ * vxge_rem_nic - Free the PCI device
+ * @pdev: structure containing the PCI related information of the device.
+ * Description: This function is called by the Pci subsystem to release a
+ * PCI device and free up all resource held up by the device.
+ */
+static void __devexit
+vxge_remove(struct pci_dev *pdev)
+{
+	struct __vxge_hw_device  *hldev;
+	struct vxgedev *vdev = NULL;
+	struct net_device *dev;
+	int i = 0;
+#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \
+	(VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK))
+	u32 level_trace;
+#endif
+
+	hldev = (struct __vxge_hw_device  *) pci_get_drvdata(pdev);
+
+	if (hldev == NULL)
+		return;
+	dev = hldev->ndev;
+	vdev = netdev_priv(dev);
+
+#if ((VXGE_DEBUG_INIT & VXGE_DEBUG_MASK) || \
+	(VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK))
+	level_trace = vdev->level_trace;
+#endif
+	vxge_debug_entryexit(level_trace,
+		"%s:%d", __func__, __LINE__);
+
+	vxge_debug_init(level_trace,
+		"%s : removing PCI device...", __func__);
+	vxge_device_unregister(hldev);
+
+	for (i = 0; i < vdev->no_of_vpath; i++) {
+		vxge_free_mac_add_list(&vdev->vpaths[i]);
+		vdev->vpaths[i].mcast_addr_cnt = 0;
+		vdev->vpaths[i].mac_addr_cnt = 0;
+	}
+
+	kfree(vdev->vpaths);
+
+	iounmap(vdev->bar0);
+	iounmap(vdev->bar1);
+
+	/* we are safe to free it now */
+	free_netdev(dev);
+
+	vxge_debug_init(level_trace,
+		"%s:%d  Device unregistered", __func__, __LINE__);
+
+	vxge_hw_device_terminate(hldev);
+
+	pci_disable_device(pdev);
+	pci_release_regions(pdev);
+	pci_set_drvdata(pdev, NULL);
+	vxge_debug_entryexit(level_trace,
+		"%s:%d  Exiting...", __func__, __LINE__);
+}
+
+static struct pci_error_handlers vxge_err_handler = {
+	.error_detected = vxge_io_error_detected,
+	.slot_reset = vxge_io_slot_reset,
+	.resume = vxge_io_resume,
+};
+
+static struct pci_driver vxge_driver = {
+	.name = VXGE_DRIVER_NAME,
+	.id_table = vxge_id_table,
+	.probe = vxge_probe,
+	.remove = __devexit_p(vxge_remove),
+#ifdef CONFIG_PM
+	.suspend = vxge_pm_suspend,
+	.resume = vxge_pm_resume,
+#endif
+	.err_handler = &vxge_err_handler,
+};
+
+static int __init
+vxge_starter(void)
+{
+	int ret = 0;
+	char version[32];
+	snprintf(version, 32, "%s", DRV_VERSION);
+
+	printk(KERN_CRIT "%s: Copyright(c) 2002-2009 Neterion Inc\n",
+		VXGE_DRIVER_NAME);
+	printk(KERN_CRIT "%s: Driver version: %s\n",
+			VXGE_DRIVER_NAME, version);
+
+	verify_bandwidth();
+
+	driver_config = kzalloc(sizeof(struct vxge_drv_config), GFP_KERNEL);
+	if (!driver_config)
+		return -ENOMEM;
+
+	ret = pci_register_driver(&vxge_driver);
+
+	if (driver_config->config_dev_cnt &&
+	   (driver_config->config_dev_cnt != driver_config->total_dev_cnt))
+		vxge_debug_init(VXGE_ERR,
+			"%s: Configured %d of %d devices",
+			VXGE_DRIVER_NAME, driver_config->config_dev_cnt,
+			driver_config->total_dev_cnt);
+
+	if (ret)
+		kfree(driver_config);
+
+	return ret;
+}
+
+static void __exit
+vxge_closer(void)
+{
+	pci_unregister_driver(&vxge_driver);
+	kfree(driver_config);
+}
+module_init(vxge_starter);
+module_exit(vxge_closer);
diff --git a/drivers/net/vxge/vxge-main.h b/drivers/net/vxge/vxge-main.h
new file mode 100644
index 000000000000..9704b2bd4320
--- /dev/null
+++ b/drivers/net/vxge/vxge-main.h
@@ -0,0 +1,557 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-main.h: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *              Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#ifndef VXGE_MAIN_H
+#define VXGE_MAIN_H
+
+#include "vxge-traffic.h"
+#include "vxge-config.h"
+#include "vxge-version.h"
+#include <linux/list.h>
+
+#define VXGE_DRIVER_NAME		"vxge"
+#define VXGE_DRIVER_VENDOR		"Neterion, Inc"
+#define VXGE_DRIVER_VERSION_MAJOR 0
+
+#define DRV_VERSION	VXGE_VERSION_MAJOR"."VXGE_VERSION_MINOR"."\
+	VXGE_VERSION_FIX"."VXGE_VERSION_BUILD"-"\
+	VXGE_VERSION_FOR
+
+#define PCI_DEVICE_ID_TITAN_WIN		0x5733
+#define PCI_DEVICE_ID_TITAN_UNI		0x5833
+#define	VXGE_USE_DEFAULT		0xffffffff
+#define VXGE_HW_VPATH_MSIX_ACTIVE	4
+#define VXGE_HW_RXSYNC_FREQ_CNT		4
+#define VXGE_LL_WATCH_DOG_TIMEOUT	(15 * HZ)
+#define VXGE_LL_RX_COPY_THRESHOLD	256
+#define VXGE_DEF_FIFO_LENGTH		84
+
+#define NO_STEERING		0
+#define PORT_STEERING		0x1
+#define RTH_STEERING		0x2
+#define RX_TOS_STEERING		0x3
+#define RX_VLAN_STEERING	0x4
+#define RTH_BUCKET_SIZE		4
+
+#define	TX_PRIORITY_STEERING	1
+#define	TX_VLAN_STEERING	2
+#define	TX_PORT_STEERING	3
+#define	TX_MULTIQ_STEERING	4
+
+#define VXGE_HW_MAC_ADDR_LEARN_DEFAULT VXGE_HW_RTS_MAC_DISABLE
+
+#define VXGE_TTI_BTIMER_VAL 250000
+
+#define VXGE_TTI_LTIMER_VAL 1000
+#define VXGE_TTI_RTIMER_VAL 0
+#define VXGE_RTI_BTIMER_VAL 250
+#define VXGE_RTI_LTIMER_VAL 100
+#define VXGE_RTI_RTIMER_VAL 0
+#define VXGE_FIFO_INDICATE_MAX_PKTS VXGE_DEF_FIFO_LENGTH
+#define VXGE_ISR_POLLING_CNT 	8
+#define VXGE_MAX_CONFIG_DEV	0xFF
+#define VXGE_EXEC_MODE_DISABLE	0
+#define VXGE_EXEC_MODE_ENABLE	1
+#define VXGE_MAX_CONFIG_PORT	1
+#define VXGE_ALL_VID_DISABLE	0
+#define VXGE_ALL_VID_ENABLE	1
+#define VXGE_PAUSE_CTRL_DISABLE	0
+#define VXGE_PAUSE_CTRL_ENABLE	1
+
+#define TTI_TX_URANGE_A	5
+#define TTI_TX_URANGE_B	15
+#define TTI_TX_URANGE_C	40
+#define TTI_TX_UFC_A	5
+#define TTI_TX_UFC_B	40
+#define TTI_TX_UFC_C	60
+#define TTI_TX_UFC_D	100
+
+#define RTI_RX_URANGE_A	5
+#define RTI_RX_URANGE_B	15
+#define RTI_RX_URANGE_C	40
+#define RTI_RX_UFC_A	1
+#define RTI_RX_UFC_B	5
+#define RTI_RX_UFC_C	10
+#define RTI_RX_UFC_D	15
+
+/* Milli secs timer period */
+#define VXGE_TIMER_DELAY		10000
+
+#define VXGE_LL_MAX_FRAME_SIZE(dev) ((dev)->mtu + VXGE_HW_MAC_HEADER_MAX_SIZE)
+
+enum vxge_reset_event {
+	/* reset events */
+	VXGE_LL_VPATH_RESET	= 0,
+	VXGE_LL_DEVICE_RESET	= 1,
+	VXGE_LL_FULL_RESET	= 2,
+	VXGE_LL_START_RESET	= 3,
+	VXGE_LL_COMPL_RESET	= 4
+};
+/* These flags represent the devices temporary state */
+enum vxge_device_state_t {
+__VXGE_STATE_RESET_CARD = 0,
+__VXGE_STATE_CARD_UP
+};
+
+enum vxge_mac_addr_state {
+	/* mac address states */
+	VXGE_LL_MAC_ADDR_IN_LIST        = 0,
+	VXGE_LL_MAC_ADDR_IN_DA_TABLE    = 1
+};
+
+struct vxge_drv_config {
+	int config_dev_cnt;
+	int total_dev_cnt;
+	unsigned long inta_dev_open;
+	int g_no_cpus;
+	unsigned int vpath_per_dev;
+};
+
+struct macInfo {
+	unsigned char macaddr[ETH_ALEN];
+	unsigned char macmask[ETH_ALEN];
+	unsigned int vpath_no;
+	enum vxge_mac_addr_state state;
+};
+
+struct vxge_config {
+	int		tx_pause_enable;
+	int		rx_pause_enable;
+
+#define	NEW_NAPI_WEIGHT	64
+	int		napi_weight;
+#define VXGE_GRO_DONOT_AGGREGATE		0
+#define VXGE_GRO_ALWAYS_AGGREGATE		1
+	int		gro_enable;
+	int		intr_type;
+#define INTA	0
+#define MSI	1
+#define MSI_X	2
+
+	int		addr_learn_en;
+
+	int		rth_steering;
+	int		rth_algorithm;
+	int		rth_hash_type_tcpipv4;
+	int		rth_hash_type_ipv4;
+	int		rth_hash_type_tcpipv6;
+	int		rth_hash_type_ipv6;
+	int		rth_hash_type_tcpipv6ex;
+	int		rth_hash_type_ipv6ex;
+	int		rth_bkt_sz;
+	int		rth_jhash_golden_ratio;
+	int		tx_steering_type;
+	int 	fifo_indicate_max_pkts;
+	struct vxge_hw_device_hw_info device_hw_info;
+};
+
+struct vxge_msix_entry {
+	/* Mimicing the msix_entry struct of Kernel. */
+	u16 vector;
+	u16 entry;
+	u16 in_use;
+	void *arg;
+};
+
+/* Software Statistics */
+
+struct vxge_sw_stats {
+	/* Network Stats (interface stats) */
+	struct net_device_stats net_stats;
+
+	/* Tx */
+	u64 tx_frms;
+	u64 tx_errors;
+	u64 tx_bytes;
+	u64 txd_not_free;
+	u64 txd_out_of_desc;
+
+	/* Virtual Path */
+	u64 vpaths_open;
+	u64 vpath_open_fail;
+
+	/* Rx */
+	u64 rx_frms;
+	u64 rx_errors;
+	u64 rx_bytes;
+	u64 rx_mcast;
+
+	/* Misc. */
+	u64 link_up;
+	u64 link_down;
+	u64 pci_map_fail;
+	u64 skb_alloc_fail;
+};
+
+struct vxge_mac_addrs {
+	struct list_head item;
+	u64 macaddr;
+	u64 macmask;
+	enum vxge_mac_addr_state state;
+};
+
+struct vxgedev;
+
+struct vxge_fifo_stats {
+	u64 tx_frms;
+	u64 tx_errors;
+	u64 tx_bytes;
+	u64 txd_not_free;
+	u64 txd_out_of_desc;
+	u64 pci_map_fail;
+};
+
+struct vxge_fifo {
+	struct net_device	*ndev;
+	struct pci_dev		*pdev;
+	struct __vxge_hw_fifo *handle;
+
+	/* The vpath id maintained in the driver -
+	 * 0 to 'maximum_vpaths_in_function - 1'
+	 */
+	int driver_id;
+	int tx_steering_type;
+	int indicate_max_pkts;
+	spinlock_t tx_lock;
+	/* flag used to maintain queue state when MULTIQ is not enabled */
+#define VPATH_QUEUE_START       0
+#define VPATH_QUEUE_STOP        1
+	int queue_state;
+
+	/* Tx stats */
+	struct vxge_fifo_stats stats;
+} ____cacheline_aligned;
+
+struct vxge_ring_stats {
+	u64 prev_rx_frms;
+	u64 rx_frms;
+	u64 rx_errors;
+	u64 rx_dropped;
+	u64 rx_bytes;
+	u64 rx_mcast;
+	u64 pci_map_fail;
+	u64 skb_alloc_fail;
+};
+
+struct vxge_ring {
+	struct net_device	*ndev;
+	struct pci_dev		*pdev;
+	struct __vxge_hw_ring	*handle;
+	/* The vpath id maintained in the driver -
+	 * 0 to 'maximum_vpaths_in_function - 1'
+	 */
+	int driver_id;
+
+	 /* copy of the flag indicating whether rx_csum is to be used */
+	u32 rx_csum;
+
+	int pkts_processed;
+	int budget;
+	int gro_enable;
+
+	struct napi_struct napi;
+
+#define VXGE_MAX_MAC_ADDR_COUNT		30
+
+	int vlan_tag_strip;
+	struct vlan_group *vlgrp;
+	int rx_vector_no;
+	enum vxge_hw_status last_status;
+
+	/* Rx stats */
+	struct vxge_ring_stats stats;
+} ____cacheline_aligned;
+
+struct vxge_vpath {
+
+	struct vxge_fifo fifo;
+	struct vxge_ring ring;
+
+	struct __vxge_hw_vpath_handle *handle;
+
+	/* Actual vpath id for this vpath in the device - 0 to 16 */
+	int device_id;
+	int max_mac_addr_cnt;
+	int is_configured;
+	int is_open;
+	struct vxgedev *vdev;
+	u8 (macaddr)[ETH_ALEN];
+	u8 (macmask)[ETH_ALEN];
+
+#define VXGE_MAX_LEARN_MAC_ADDR_CNT	2048
+	/* mac addresses currently programmed into NIC */
+	u16 mac_addr_cnt;
+	u16 mcast_addr_cnt;
+	struct list_head mac_addr_list;
+
+	u32 level_err;
+	u32 level_trace;
+};
+#define VXGE_COPY_DEBUG_INFO_TO_LL(vdev, err, trace) {	\
+	for (i = 0; i < vdev->no_of_vpath; i++) {		\
+		vdev->vpaths[i].level_err = err;		\
+		vdev->vpaths[i].level_trace = trace;		\
+	}							\
+	vdev->level_err = err;					\
+	vdev->level_trace = trace;				\
+}
+
+struct vxgedev {
+	struct net_device	*ndev;
+	struct pci_dev		*pdev;
+	struct __vxge_hw_device *devh;
+	struct vlan_group	*vlgrp;
+	int vlan_tag_strip;
+	struct vxge_config	config;
+	unsigned long	state;
+
+	/* Indicates which vpath to reset */
+	unsigned long  vp_reset;
+
+	/* Timer used for polling vpath resets */
+	struct timer_list vp_reset_timer;
+
+	/* Timer used for polling vpath lockup */
+	struct timer_list vp_lockup_timer;
+
+	/*
+	 * Flags to track whether device is in All Multicast
+	 * or in promiscuous mode.
+	 */
+	u16		all_multi_flg;
+
+	 /* A flag indicating whether rx_csum is to be used or not. */
+	u32	rx_csum;
+
+	struct vxge_msix_entry *vxge_entries;
+	struct msix_entry *entries;
+	/*
+	 * 4 for each vpath * 17;
+	 * total is 68
+	 */
+#define	VXGE_MAX_REQUESTED_MSIX	68
+#define VXGE_INTR_STRLEN 80
+	char desc[VXGE_MAX_REQUESTED_MSIX][VXGE_INTR_STRLEN];
+
+	enum vxge_hw_event cric_err_event;
+
+	int max_vpath_supported;
+	int no_of_vpath;
+
+	struct napi_struct napi;
+	/* A debug option, when enabled and if error condition occurs,
+	 * the driver will do following steps:
+	 * - mask all interrupts
+	 * - Not clear the source of the alarm
+	 * - gracefully stop all I/O
+	 * A diagnostic dump of register and stats at this point
+	 * reveals very useful information.
+	 */
+	int exec_mode;
+	int max_config_port;
+	struct vxge_vpath	*vpaths;
+
+	struct __vxge_hw_vpath_handle *vp_handles[VXGE_HW_MAX_VIRTUAL_PATHS];
+	void __iomem *bar0;
+	void __iomem *bar1;
+	struct vxge_sw_stats	stats;
+	int		mtu;
+	/* Below variables are used for vpath selection to transmit a packet */
+	u8 		vpath_selector[VXGE_HW_MAX_VIRTUAL_PATHS];
+	u64		vpaths_deployed;
+
+	u32 		intr_cnt;
+	u32 		level_err;
+	u32 		level_trace;
+	char		fw_version[VXGE_HW_FW_STRLEN];
+};
+
+struct vxge_rx_priv {
+	struct sk_buff		*skb;
+	dma_addr_t		data_dma;
+	dma_addr_t		data_size;
+};
+
+struct vxge_tx_priv {
+	struct sk_buff		*skb;
+	dma_addr_t		dma_buffers[MAX_SKB_FRAGS+1];
+};
+
+#define VXGE_MODULE_PARAM_INT(p, val) \
+	static int p = val; \
+	module_param(p, int, 0)
+
+#define vxge_os_bug(fmt...)		{ printk(fmt); BUG(); }
+
+#define vxge_os_timer(timer, handle, arg, exp) do { \
+		init_timer(&timer); \
+		timer.function = handle; \
+		timer.data = (unsigned long) arg; \
+		mod_timer(&timer, (jiffies + exp)); \
+	} while (0);
+
+int __devinit vxge_device_register(struct __vxge_hw_device *devh,
+				    struct vxge_config *config,
+				    int high_dma, int no_of_vpath,
+				    struct vxgedev **vdev);
+
+void vxge_device_unregister(struct __vxge_hw_device *devh);
+
+void vxge_vpath_intr_enable(struct vxgedev *vdev, int vp_id);
+
+void vxge_vpath_intr_disable(struct vxgedev *vdev, int vp_id);
+
+void vxge_callback_link_up(struct __vxge_hw_device *devh);
+
+void vxge_callback_link_down(struct __vxge_hw_device *devh);
+
+enum vxge_hw_status vxge_add_mac_addr(struct vxgedev *vdev,
+	struct macInfo *mac);
+
+int vxge_mac_list_del(struct vxge_vpath *vpath, struct macInfo *mac);
+
+int vxge_reset(struct vxgedev *vdev);
+
+enum vxge_hw_status
+vxge_rx_1b_compl(struct __vxge_hw_ring *ringh, void *dtr,
+	u8 t_code, void *userdata);
+
+enum vxge_hw_status
+vxge_xmit_compl(struct __vxge_hw_fifo *fifo_hw, void *dtr,
+	enum vxge_hw_fifo_tcode t_code, void *userdata, void **skb_ptr);
+
+int vxge_close(struct net_device *dev);
+
+int vxge_open(struct net_device *dev);
+
+void vxge_close_vpaths(struct vxgedev *vdev, int index);
+
+int vxge_open_vpaths(struct vxgedev *vdev);
+
+enum vxge_hw_status vxge_reset_all_vpaths(struct vxgedev *vdev);
+
+void vxge_stop_all_tx_queue(struct vxgedev *vdev);
+
+void vxge_stop_tx_queue(struct vxge_fifo *fifo);
+
+void vxge_start_all_tx_queue(struct vxgedev *vdev);
+
+void vxge_wake_tx_queue(struct vxge_fifo *fifo, struct sk_buff *skb);
+
+enum vxge_hw_status vxge_add_mac_addr(struct vxgedev *vdev,
+	struct macInfo *mac);
+
+enum vxge_hw_status vxge_del_mac_addr(struct vxgedev *vdev,
+	struct macInfo *mac);
+
+int vxge_mac_list_add(struct vxge_vpath *vpath,
+	struct macInfo *mac);
+
+void vxge_free_mac_add_list(struct vxge_vpath *vpath);
+
+enum vxge_hw_status vxge_restore_vpath_mac_addr(struct vxge_vpath *vpath);
+
+enum vxge_hw_status vxge_restore_vpath_vid_table(struct vxge_vpath *vpath);
+
+int do_vxge_close(struct net_device *dev, int do_io);
+extern void initialize_ethtool_ops(struct net_device *ndev);
+/**
+ * #define VXGE_DEBUG_INIT: debug for initialization functions
+ * #define VXGE_DEBUG_TX	 : debug transmit related functions
+ * #define VXGE_DEBUG_RX  : debug recevice related functions
+ * #define VXGE_DEBUG_MEM : debug memory module
+ * #define VXGE_DEBUG_LOCK: debug locks
+ * #define VXGE_DEBUG_SEM : debug semaphore
+ * #define VXGE_DEBUG_ENTRYEXIT: debug functions by adding entry exit statements
+*/
+#define VXGE_DEBUG_INIT		0x00000001
+#define VXGE_DEBUG_TX		0x00000002
+#define VXGE_DEBUG_RX		0x00000004
+#define VXGE_DEBUG_MEM		0x00000008
+#define VXGE_DEBUG_LOCK		0x00000010
+#define VXGE_DEBUG_SEM		0x00000020
+#define VXGE_DEBUG_ENTRYEXIT	0x00000040
+#define VXGE_DEBUG_INTR		0x00000080
+#define VXGE_DEBUG_LL_CONFIG	0x00000100
+
+/* Debug tracing for VXGE driver */
+#ifndef VXGE_DEBUG_MASK
+#define VXGE_DEBUG_MASK	0x0
+#endif
+
+#if (VXGE_DEBUG_LL_CONFIG & VXGE_DEBUG_MASK)
+#define vxge_debug_ll_config(level, fmt, ...) \
+	vxge_debug_ll(level, VXGE_DEBUG_LL_CONFIG, fmt, __VA_ARGS__)
+#else
+#define vxge_debug_ll_config(level, fmt, ...)
+#endif
+
+#if (VXGE_DEBUG_INIT & VXGE_DEBUG_MASK)
+#define vxge_debug_init(level, fmt, ...) \
+	vxge_debug_ll(level, VXGE_DEBUG_INIT, fmt, __VA_ARGS__)
+#else
+#define vxge_debug_init(level, fmt, ...)
+#endif
+
+#if (VXGE_DEBUG_TX & VXGE_DEBUG_MASK)
+#define vxge_debug_tx(level, fmt, ...) \
+	vxge_debug_ll(level, VXGE_DEBUG_TX, fmt, __VA_ARGS__)
+#else
+#define vxge_debug_tx(level, fmt, ...)
+#endif
+
+#if (VXGE_DEBUG_RX & VXGE_DEBUG_MASK)
+#define vxge_debug_rx(level, fmt, ...) \
+	vxge_debug_ll(level, VXGE_DEBUG_RX, fmt, __VA_ARGS__)
+#else
+#define vxge_debug_rx(level, fmt, ...)
+#endif
+
+#if (VXGE_DEBUG_MEM & VXGE_DEBUG_MASK)
+#define vxge_debug_mem(level, fmt, ...) \
+	vxge_debug_ll(level, VXGE_DEBUG_MEM, fmt, __VA_ARGS__)
+#else
+#define vxge_debug_mem(level, fmt, ...)
+#endif
+
+#if (VXGE_DEBUG_ENTRYEXIT & VXGE_DEBUG_MASK)
+#define vxge_debug_entryexit(level, fmt, ...) \
+	vxge_debug_ll(level, VXGE_DEBUG_ENTRYEXIT, fmt, __VA_ARGS__)
+#else
+#define vxge_debug_entryexit(level, fmt, ...)
+#endif
+
+#if (VXGE_DEBUG_INTR & VXGE_DEBUG_MASK)
+#define vxge_debug_intr(level, fmt, ...) \
+	vxge_debug_ll(level, VXGE_DEBUG_INTR, fmt, __VA_ARGS__)
+#else
+#define vxge_debug_intr(level, fmt, ...)
+#endif
+
+#define VXGE_DEVICE_DEBUG_LEVEL_SET(level, mask, vdev) {\
+	vxge_hw_device_debug_set((struct __vxge_hw_device  *)vdev->devh, \
+		level, mask);\
+	VXGE_COPY_DEBUG_INFO_TO_LL(vdev, \
+		vxge_hw_device_error_level_get((struct __vxge_hw_device  *) \
+			vdev->devh), \
+		vxge_hw_device_trace_level_get((struct __vxge_hw_device  *) \
+			vdev->devh));\
+}
+
+#ifdef NETIF_F_GSO
+#define vxge_tcp_mss(skb) (skb_shinfo(skb)->gso_size)
+#define vxge_udp_mss(skb) (skb_shinfo(skb)->gso_size)
+#define vxge_offload_type(skb) (skb_shinfo(skb)->gso_type)
+#endif
+
+#endif
diff --git a/drivers/net/vxge/vxge-reg.h b/drivers/net/vxge/vxge-reg.h
new file mode 100644
index 000000000000..10f4da32929f
--- /dev/null
+++ b/drivers/net/vxge/vxge-reg.h
@@ -0,0 +1,4608 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-reg.h: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O Virtualized
+ *             Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#ifndef VXGE_REG_H
+#define VXGE_REG_H
+
+/*
+ * vxge_mBIT(loc) - set bit at offset
+ */
+#define vxge_mBIT(loc)		(0x8000000000000000ULL >> (loc))
+
+/*
+ * vxge_vBIT(val, loc, sz) - set bits at offset
+ */
+#define vxge_vBIT(val, loc, sz)	(((u64)(val)) << (64-(loc)-(sz)))
+#define vxge_vBIT32(val, loc, sz)	(((u32)(val)) << (32-(loc)-(sz)))
+
+/*
+ * vxge_bVALn(bits, loc, n) - Get the value of n bits at location
+ */
+#define vxge_bVALn(bits, loc, n) \
+	((((u64)bits) >> (64-(loc+n))) & ((0x1ULL << n) - 1))
+
+#define	VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_DEVICE_ID(bits) \
+							vxge_bVALn(bits, 0, 16)
+#define	VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_MAJOR_REVISION(bits) \
+							vxge_bVALn(bits, 48, 8)
+#define	VXGE_HW_TITAN_ASIC_ID_GET_INITIAL_MINOR_REVISION(bits) \
+							vxge_bVALn(bits, 56, 8)
+
+#define	VXGE_HW_VPATH_TO_FUNC_MAP_CFG1_GET_VPATH_TO_FUNC_MAP_CFG1(bits) \
+							vxge_bVALn(bits, 3, 5)
+#define	VXGE_HW_HOST_TYPE_ASSIGNMENTS_GET_HOST_TYPE_ASSIGNMENTS(bits) \
+							vxge_bVALn(bits, 5, 3)
+#define VXGE_HW_PF_SW_RESET_COMMAND				0xA5
+
+#define VXGE_HW_TITAN_PCICFGMGMT_REG_SPACES		17
+#define VXGE_HW_TITAN_SRPCIM_REG_SPACES			17
+#define VXGE_HW_TITAN_VPMGMT_REG_SPACES			17
+#define VXGE_HW_TITAN_VPATH_REG_SPACES			17
+
+#define VXGE_HW_ASIC_MODE_RESERVED				0
+#define VXGE_HW_ASIC_MODE_NO_IOV				1
+#define VXGE_HW_ASIC_MODE_SR_IOV				2
+#define VXGE_HW_ASIC_MODE_MR_IOV				3
+
+#define	VXGE_HW_TXMAC_GEN_CFG1_TMAC_PERMA_STOP_EN		vxge_mBIT(3)
+#define	VXGE_HW_TXMAC_GEN_CFG1_BLOCK_BCAST_TO_WIRE		vxge_mBIT(19)
+#define	VXGE_HW_TXMAC_GEN_CFG1_BLOCK_BCAST_TO_SWITCH	vxge_mBIT(23)
+#define	VXGE_HW_TXMAC_GEN_CFG1_HOST_APPEND_FCS			vxge_mBIT(31)
+
+#define	VXGE_HW_VPATH_IS_FIRST_GET_VPATH_IS_FIRST(bits)	vxge_bVALn(bits, 3, 1)
+
+#define	VXGE_HW_TIM_VPATH_ASSIGNMENT_GET_BMAP_ROOT(bits) \
+						vxge_bVALn(bits, 0, 32)
+
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_GET_MAX_PYLD_LEN(bits) \
+							vxge_bVALn(bits, 50, 14)
+
+#define	VXGE_HW_XMAC_VSPORT_CHOICES_VP_GET_VSPORT_VECTOR(bits) \
+							vxge_bVALn(bits, 0, 17)
+
+#define	VXGE_HW_XMAC_VPATH_TO_VSPORT_VPMGMT_CLONE_GET_VSPORT_NUMBER(bits) \
+							vxge_bVALn(bits, 3, 5)
+
+#define	VXGE_HW_KDFC_DRBL_TRIPLET_TOTAL_GET_KDFC_MAX_SIZE(bits) \
+							vxge_bVALn(bits, 17, 15)
+
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_MODE_LEGACY_MODE			0
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_MODE_NON_OFFLOAD_ONLY		1
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_MODE_MULTI_OP_MODE		2
+
+#define VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_MODE_MESSAGES_ONLY		0
+#define VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_MODE_MULTI_OP_MODE		1
+
+#define	VXGE_HW_TOC_GET_KDFC_INITIAL_OFFSET(val) \
+				(val&~VXGE_HW_TOC_KDFC_INITIAL_BIR(7))
+#define	VXGE_HW_TOC_GET_KDFC_INITIAL_BIR(val) \
+				vxge_bVALn(val, 61, 3)
+#define	VXGE_HW_TOC_GET_USDC_INITIAL_OFFSET(val) \
+				(val&~VXGE_HW_TOC_USDC_INITIAL_BIR(7))
+#define	VXGE_HW_TOC_GET_USDC_INITIAL_BIR(val) \
+				vxge_bVALn(val, 61, 3)
+
+#define	VXGE_HW_TOC_KDFC_VPATH_STRIDE_GET_TOC_KDFC_VPATH_STRIDE(bits)	bits
+#define	VXGE_HW_TOC_KDFC_FIFO_STRIDE_GET_TOC_KDFC_FIFO_STRIDE(bits)	bits
+
+#define	VXGE_HW_KDFC_TRPL_FIFO_OFFSET_GET_KDFC_RCTR0(bits) \
+						vxge_bVALn(bits, 1, 15)
+#define	VXGE_HW_KDFC_TRPL_FIFO_OFFSET_GET_KDFC_RCTR1(bits) \
+						vxge_bVALn(bits, 17, 15)
+#define	VXGE_HW_KDFC_TRPL_FIFO_OFFSET_GET_KDFC_RCTR2(bits) \
+						vxge_bVALn(bits, 33, 15)
+
+#define VXGE_HW_KDFC_TRPL_FIFO_OFFSET_KDFC_VAPTH_NUM(val) vxge_vBIT(val, 42, 5)
+#define VXGE_HW_KDFC_TRPL_FIFO_OFFSET_KDFC_FIFO_NUM(val) vxge_vBIT(val, 47, 2)
+#define VXGE_HW_KDFC_TRPL_FIFO_OFFSET_KDFC_FIFO_OFFSET(val) \
+					vxge_vBIT(val, 49, 15)
+
+#define VXGE_HW_PRC_CFG4_RING_MODE_ONE_BUFFER			0
+#define VXGE_HW_PRC_CFG4_RING_MODE_THREE_BUFFER			1
+#define VXGE_HW_PRC_CFG4_RING_MODE_FIVE_BUFFER			2
+
+#define VXGE_HW_PRC_CFG7_SCATTER_MODE_A				0
+#define VXGE_HW_PRC_CFG7_SCATTER_MODE_B				2
+#define VXGE_HW_PRC_CFG7_SCATTER_MODE_C				1
+
+#define VXGE_HW_RTS_MGR_STEER_CTRL_WE_READ                             0
+#define VXGE_HW_RTS_MGR_STEER_CTRL_WE_WRITE                            1
+
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_DA                  0
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_VID                 1
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_ETYPE               2
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_PN                  3
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_RANGE_PN            4
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG         5
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT         6
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_RTH_JHASH_CFG       7
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK            8
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY             9
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_QOS                 10
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_DS                  11
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT        12
+#define VXGE_HW_RTS_MGR_STEER_CTRL_DATA_STRUCT_SEL_FW_VERSION          13
+
+#define VXGE_HW_RTS_MGR_STEER_DATA0_GET_DA_MAC_ADDR(bits) \
+							vxge_bVALn(bits, 0, 48)
+#define VXGE_HW_RTS_MGR_STEER_DATA0_DA_MAC_ADDR(val) vxge_vBIT(val, 0, 48)
+
+#define VXGE_HW_RTS_MGR_STEER_DATA1_GET_DA_MAC_ADDR_MASK(bits) \
+							vxge_bVALn(bits, 0, 48)
+#define VXGE_HW_RTS_MGR_STEER_DATA1_DA_MAC_ADDR_MASK(val) vxge_vBIT(val, 0, 48)
+#define VXGE_HW_RTS_MGR_STEER_DATA1_DA_MAC_ADDR_ADD_PRIVILEGED_MODE \
+								vxge_mBIT(54)
+#define VXGE_HW_RTS_MGR_STEER_DATA1_GET_DA_MAC_ADDR_ADD_VPATH(bits) \
+							vxge_bVALn(bits, 55, 5)
+#define VXGE_HW_RTS_MGR_STEER_DATA1_DA_MAC_ADDR_ADD_VPATH(val) \
+							vxge_vBIT(val, 55, 5)
+#define VXGE_HW_RTS_MGR_STEER_DATA1_GET_DA_MAC_ADDR_ADD_MODE(bits) \
+							vxge_bVALn(bits, 62, 2)
+#define VXGE_HW_RTS_MGR_STEER_DATA1_DA_MAC_ADDR_MODE(val) vxge_vBIT(val, 62, 2)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_ADD_ENTRY			0
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_DELETE_ENTRY		1
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY		2
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_NEXT_ENTRY		3
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_ENTRY			0
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_WRITE_ENTRY		1
+#define VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_READ_MEMO_ENTRY		3
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LED_CONTROL		4
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_ALL_CLEAR			172
+
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA		0
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_VID		1
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_ETYPE		2
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_PN		3
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_GEN_CFG	5
+#define	VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_SOLO_IT	6
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_JHASH_CFG	7
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MASK		8
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_RTH_KEY		9
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_QOS		10
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DS		11
+#define	VXGE_HW_RTS_ACS_STEER_CTRL_DATA_STRUCT_SEL_RTH_MULTI_IT	12
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_FW_MEMO		13
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(bits) \
+							vxge_bVALn(bits, 0, 48)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_DA_MAC_ADDR(val) vxge_vBIT(val, 0, 48)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_VLAN_ID(bits) vxge_bVALn(bits, 0, 12)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_VLAN_ID(val) vxge_vBIT(val, 0, 12)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_ETYPE(bits)	vxge_bVALn(bits, 0, 11)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_ETYPE(val) vxge_vBIT(val, 0, 16)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_PN_SRC_DEST_SEL(bits) \
+							vxge_bVALn(bits, 3, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_PN_SRC_DEST_SEL		vxge_mBIT(3)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_PN_TCP_UDP_SEL(bits) \
+							vxge_bVALn(bits, 7, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_PN_TCP_UDP_SEL		vxge_mBIT(7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_PN_PORT_NUM(bits) \
+							vxge_bVALn(bits, 8, 16)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_PN_PORT_NUM(val) vxge_vBIT(val, 8, 16)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_RTH_EN(bits) \
+							vxge_bVALn(bits, 3, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_EN		vxge_mBIT(3)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_BUCKET_SIZE(bits) \
+							vxge_bVALn(bits, 4, 4)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_BUCKET_SIZE(val) \
+							vxge_vBIT(val, 4, 4)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_ALG_SEL(bits) \
+							vxge_bVALn(bits, 10, 2)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL(val) \
+							vxge_vBIT(val, 10, 2)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL_JENKINS	0
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL_MS_RSS	1
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ALG_SEL_CRC32C	2
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_RTH_TCP_IPV4_EN(bits) \
+							vxge_bVALn(bits, 15, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_TCP_IPV4_EN	vxge_mBIT(15)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_RTH_IPV4_EN(bits) \
+							vxge_bVALn(bits, 19, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_IPV4_EN	vxge_mBIT(19)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_RTH_TCP_IPV6_EN(bits) \
+							vxge_bVALn(bits, 23, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_TCP_IPV6_EN	vxge_mBIT(23)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_RTH_IPV6_EN(bits) \
+							vxge_bVALn(bits, 27, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_IPV6_EN	vxge_mBIT(27)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_RTH_TCP_IPV6_EX_EN(bits) \
+							vxge_bVALn(bits, 31, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_TCP_IPV6_EX_EN vxge_mBIT(31)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_RTH_IPV6_EX_EN(bits) \
+							vxge_bVALn(bits, 35, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_RTH_IPV6_EX_EN	vxge_mBIT(35)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_ACTIVE_TABLE(bits) \
+							vxge_bVALn(bits, 39, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_ACTIVE_TABLE	vxge_mBIT(39)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_GEN_REPL_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 43, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_GEN_REPL_ENTRY_EN	vxge_mBIT(43)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_SOLO_IT_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 3, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_SOLO_IT_ENTRY_EN	vxge_mBIT(3)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_SOLO_IT_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 9, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_SOLO_IT_BUCKET_DATA(val) \
+							vxge_vBIT(val, 9, 7)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_ITEM0_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 0, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_NUM(val) \
+							vxge_vBIT(val, 0, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_ITEM0_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 8, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_ENTRY_EN	vxge_mBIT(8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_ITEM0_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 9, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM0_BUCKET_DATA(val) \
+							vxge_vBIT(val, 9, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_ITEM1_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 16, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_NUM(val) \
+							vxge_vBIT(val, 16, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_ITEM1_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 24, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_ENTRY_EN	vxge_mBIT(24)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_ITEM1_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 25, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_ITEM1_BUCKET_DATA(val) \
+							vxge_vBIT(val, 25, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM0_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 0, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_NUM(val) \
+							vxge_vBIT(val, 0, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM0_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 8, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_ENTRY_EN	vxge_mBIT(8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM0_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 9, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM0_BUCKET_DATA(val) \
+							vxge_vBIT(val, 9, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM1_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 16, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_NUM(val) \
+							vxge_vBIT(val, 16, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM1_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 24, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_ENTRY_EN	vxge_mBIT(24)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM1_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 25, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM1_BUCKET_DATA(val) \
+							vxge_vBIT(val, 25, 7)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_JHASH_CFG_GOLDEN_RATIO(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_JHASH_CFG_GOLDEN_RATIO(val) \
+							vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_JHASH_CFG_INIT_VALUE(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_JHASH_CFG_INIT_VALUE(val) \
+							vxge_vBIT(val, 32, 32)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_MASK_IPV6_SA_MASK(bits) \
+							vxge_bVALn(bits, 0, 16)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_MASK_IPV6_SA_MASK(val) \
+							vxge_vBIT(val, 0, 16)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_MASK_IPV6_DA_MASK(bits) \
+							vxge_bVALn(bits, 16, 16)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_MASK_IPV6_DA_MASK(val) \
+							vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_MASK_IPV4_SA_MASK(bits) \
+							vxge_bVALn(bits, 32, 4)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_MASK_IPV4_SA_MASK(val) \
+							vxge_vBIT(val, 32, 4)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_MASK_IPV4_DA_MASK(bits) \
+							vxge_bVALn(bits, 36, 4)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_MASK_IPV4_DA_MASK(val) \
+							vxge_vBIT(val, 36, 4)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_MASK_L4SP_MASK(bits) \
+							vxge_bVALn(bits, 40, 2)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_MASK_L4SP_MASK(val) \
+							vxge_vBIT(val, 40, 2)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_MASK_L4DP_MASK(bits) \
+							vxge_bVALn(bits, 42, 2)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_MASK_L4DP_MASK(val) \
+							vxge_vBIT(val, 42, 2)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_RTH_KEY_KEY(bits) \
+							vxge_bVALn(bits, 0, 64)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_RTH_KEY_KEY vxge_vBIT(val, 0, 64)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_QOS_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 3, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_QOS_ENTRY_EN		vxge_mBIT(3)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DS_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 3, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_DS_ENTRY_EN		vxge_mBIT(3)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK(bits) \
+							vxge_bVALn(bits, 0, 48)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_DA_MAC_ADDR_MASK(val) \
+							vxge_vBIT(val, 0, 48)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_DA_MAC_ADDR_MODE(val) \
+							vxge_vBIT(val, 62, 2)
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM4_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 0, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM4_BUCKET_NUM(val) \
+							vxge_vBIT(val, 0, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM4_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 8, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM4_ENTRY_EN	vxge_mBIT(8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM4_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 9, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM4_BUCKET_DATA(val) \
+							vxge_vBIT(val, 9, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM5_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 16, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM5_BUCKET_NUM(val) \
+							vxge_vBIT(val, 16, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM5_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 24, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM5_ENTRY_EN	vxge_mBIT(24)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM5_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 25, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM5_BUCKET_DATA(val) \
+							vxge_vBIT(val, 25, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM6_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 32, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM6_BUCKET_NUM(val) \
+							vxge_vBIT(val, 32, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM6_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 40, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM6_ENTRY_EN	vxge_mBIT(40)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM6_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 41, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM6_BUCKET_DATA(val) \
+							vxge_vBIT(val, 41, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM7_BUCKET_NUM(bits) \
+							vxge_bVALn(bits, 48, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM7_BUCKET_NUM(val) \
+							vxge_vBIT(val, 48, 8)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM7_ENTRY_EN(bits) \
+							vxge_bVALn(bits, 56, 1)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM7_ENTRY_EN	vxge_mBIT(56)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_RTH_ITEM7_BUCKET_DATA(bits) \
+							vxge_bVALn(bits, 57, 7)
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA1_RTH_ITEM7_BUCKET_DATA(val) \
+							vxge_vBIT(val, 57, 7)
+
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PART_NUMBER           0
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_SERIAL_NUMBER         1
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_VERSION               2
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_PCI_MODE              3
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_0                4
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_1                5
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_2                6
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_MEMO_ITEM_DESC_3                7
+
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_LED_CONTROL_ON			1
+#define	VXGE_HW_RTS_ACCESS_STEER_DATA0_LED_CONTROL_OFF			0
+
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_DAY(bits) \
+							vxge_bVALn(bits, 0, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_FW_VER_DAY(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MONTH(bits) \
+							vxge_bVALn(bits, 8, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_FW_VER_MONTH(val) vxge_vBIT(val, 8, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_YEAR(bits) \
+						vxge_bVALn(bits, 16, 16)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_FW_VER_YEAR(val) \
+							vxge_vBIT(val, 16, 16)
+
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MAJOR(bits) \
+						vxge_bVALn(bits, 32, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_FW_VER_MAJOR vxge_vBIT(val, 32, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_MINOR(bits) \
+						vxge_bVALn(bits, 40, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_FW_VER_MINOR vxge_vBIT(val, 40, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_FW_VER_BUILD(bits) \
+						vxge_bVALn(bits, 48, 16)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_FW_VER_BUILD vxge_vBIT(val, 48, 16)
+
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_DAY(bits) \
+						vxge_bVALn(bits, 0, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_DAY(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MONTH(bits) \
+							vxge_bVALn(bits, 8, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_MONTH(val) vxge_vBIT(val, 8, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_YEAR(bits) \
+							vxge_bVALn(bits, 16, 16)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_YEAR(val) \
+							vxge_vBIT(val, 16, 16)
+
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MAJOR(bits) \
+							vxge_bVALn(bits, 32, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_MAJOR vxge_vBIT(val, 32, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_MINOR(bits) \
+							vxge_bVALn(bits, 40, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_MINOR vxge_vBIT(val, 40, 8)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_FLASH_VER_BUILD(bits) \
+							vxge_bVALn(bits, 48, 16)
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_FLASH_VER_BUILD vxge_vBIT(val, 48, 16)
+
+#define	VXGE_HW_SRPCIM_TO_VPATH_ALARM_REG_GET_PPIF_SRPCIM_TO_VPATH_ALARM(bits)\
+							vxge_bVALn(bits, 0, 18)
+
+#define	VXGE_HW_RX_MULTI_CAST_STATS_GET_FRAME_DISCARD(bits) \
+							vxge_bVALn(bits, 48, 16)
+#define	VXGE_HW_RX_FRM_TRANSFERRED_GET_RX_FRM_TRANSFERRED(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_RXD_RETURNED_GET_RXD_RETURNED(bits)	vxge_bVALn(bits, 48, 16)
+#define	VXGE_HW_VPATH_DEBUG_STATS0_GET_INI_NUM_MWR_SENT(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_VPATH_DEBUG_STATS1_GET_INI_NUM_MRD_SENT(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_VPATH_DEBUG_STATS2_GET_INI_NUM_CPL_RCVD(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_VPATH_DEBUG_STATS3_GET_INI_NUM_MWR_BYTE_SENT(bits)	(bits)
+#define	VXGE_HW_VPATH_DEBUG_STATS4_GET_INI_NUM_CPL_BYTE_RCVD(bits)	(bits)
+#define	VXGE_HW_VPATH_DEBUG_STATS5_GET_WRCRDTARB_XOFF(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_VPATH_DEBUG_STATS6_GET_RDCRDTARB_XOFF(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT01_GET_PPIF_VPATH_GENSTATS_COUNT1(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT01_GET_PPIF_VPATH_GENSTATS_COUNT0(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT23_GET_PPIF_VPATH_GENSTATS_COUNT3(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT23_GET_PPIF_VPATH_GENSTATS_COUNT2(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT4_GET_PPIF_VPATH_GENSTATS_COUNT4(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT5_GET_PPIF_VPATH_GENSTATS_COUNT5(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_TX_VP_RESET_DISCARDED_FRMS_GET_TX_VP_RESET_DISCARDED_FRMS(bits\
+) vxge_bVALn(bits, 48, 16)
+#define	VXGE_HW_DBG_STATS_GET_RX_MPA_CRC_FAIL_FRMS(bits) vxge_bVALn(bits, 0, 16)
+#define	VXGE_HW_DBG_STATS_GET_RX_MPA_MRK_FAIL_FRMS(bits) \
+							vxge_bVALn(bits, 16, 16)
+#define	VXGE_HW_DBG_STATS_GET_RX_MPA_LEN_FAIL_FRMS(bits) \
+							vxge_bVALn(bits, 32, 16)
+#define	VXGE_HW_DBG_STATS_GET_RX_FAU_RX_WOL_FRMS(bits)	vxge_bVALn(bits, 0, 16)
+#define	VXGE_HW_DBG_STATS_GET_RX_FAU_RX_VP_RESET_DISCARDED_FRMS(bits) \
+							vxge_bVALn(bits, 16, 16)
+#define	VXGE_HW_DBG_STATS_GET_RX_FAU_RX_PERMITTED_FRMS(bits) \
+							vxge_bVALn(bits, 32, 16)
+
+#define	VXGE_HW_MRPCIM_DEBUG_STATS0_GET_INI_WR_DROP(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_MRPCIM_DEBUG_STATS0_GET_INI_RD_DROP(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_MRPCIM_DEBUG_STATS1_GET_VPLANE_WRCRDTARB_PH_CRDT_DEPLETED(bits\
+) vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_MRPCIM_DEBUG_STATS2_GET_VPLANE_WRCRDTARB_PD_CRDT_DEPLETED(bits\
+) vxge_bVALn(bits, 32, 32)
+#define \
+VXGE_HW_MRPCIM_DEBUG_STATS3_GET_VPLANE_RDCRDTARB_NPH_CRDT_DEPLETED(bits) \
+	vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_MRPCIM_DEBUG_STATS4_GET_INI_WR_VPIN_DROP(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_MRPCIM_DEBUG_STATS4_GET_INI_RD_VPIN_DROP(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_GENSTATS_COUNT01_GET_GENSTATS_COUNT1(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_GENSTATS_COUNT01_GET_GENSTATS_COUNT0(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_GENSTATS_COUNT23_GET_GENSTATS_COUNT3(bits) \
+							vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_GENSTATS_COUNT23_GET_GENSTATS_COUNT2(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_GENSTATS_COUNT4_GET_GENSTATS_COUNT4(bits) \
+							vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_GENSTATS_COUNT5_GET_GENSTATS_COUNT5(bits) \
+							vxge_bVALn(bits, 32, 32)
+
+#define	VXGE_HW_DEBUG_STATS0_GET_RSTDROP_MSG(bits)	vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_DEBUG_STATS0_GET_RSTDROP_CPL(bits)	vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_DEBUG_STATS1_GET_RSTDROP_CLIENT0(bits)	vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_DEBUG_STATS1_GET_RSTDROP_CLIENT1(bits)	vxge_bVALn(bits, 32, 32)
+#define	VXGE_HW_DEBUG_STATS2_GET_RSTDROP_CLIENT2(bits)	vxge_bVALn(bits, 0, 32)
+#define	VXGE_HW_DEBUG_STATS3_GET_VPLANE_DEPL_PH(bits)	vxge_bVALn(bits, 0, 16)
+#define	VXGE_HW_DEBUG_STATS3_GET_VPLANE_DEPL_NPH(bits)	vxge_bVALn(bits, 16, 16)
+#define	VXGE_HW_DEBUG_STATS3_GET_VPLANE_DEPL_CPLH(bits)	vxge_bVALn(bits, 32, 16)
+#define	VXGE_HW_DEBUG_STATS4_GET_VPLANE_DEPL_PD(bits)	vxge_bVALn(bits, 0, 16)
+#define	VXGE_HW_DEBUG_STATS4_GET_VPLANE_DEPL_NPD(bits)	bVAL(bits, 16, 16)
+#define	VXGE_HW_DEBUG_STATS4_GET_VPLANE_DEPL_CPLD(bits)	vxge_bVALn(bits, 32, 16)
+
+#define	VXGE_HW_DBG_STATS_TPA_TX_PATH_GET_TX_PERMITTED_FRMS(bits) \
+							vxge_bVALn(bits, 32, 32)
+
+#define	VXGE_HW_DBG_STAT_TX_ANY_FRMS_GET_PORT0_TX_ANY_FRMS(bits) \
+							vxge_bVALn(bits, 0, 8)
+#define	VXGE_HW_DBG_STAT_TX_ANY_FRMS_GET_PORT1_TX_ANY_FRMS(bits) \
+							vxge_bVALn(bits, 8, 8)
+#define	VXGE_HW_DBG_STAT_TX_ANY_FRMS_GET_PORT2_TX_ANY_FRMS(bits) \
+							vxge_bVALn(bits, 16, 8)
+
+#define	VXGE_HW_DBG_STAT_RX_ANY_FRMS_GET_PORT0_RX_ANY_FRMS(bits) \
+							vxge_bVALn(bits, 0, 8)
+#define	VXGE_HW_DBG_STAT_RX_ANY_FRMS_GET_PORT1_RX_ANY_FRMS(bits) \
+							vxge_bVALn(bits, 8, 8)
+#define	VXGE_HW_DBG_STAT_RX_ANY_FRMS_GET_PORT2_RX_ANY_FRMS(bits) \
+							vxge_bVALn(bits, 16, 8)
+
+#define VXGE_HW_CONFIG_PRIV_H
+
+#define VXGE_HW_SWAPPER_INITIAL_VALUE			0x0123456789abcdefULL
+#define VXGE_HW_SWAPPER_BYTE_SWAPPED			0xefcdab8967452301ULL
+#define VXGE_HW_SWAPPER_BIT_FLIPPED			0x80c4a2e691d5b3f7ULL
+#define VXGE_HW_SWAPPER_BYTE_SWAPPED_BIT_FLIPPED	0xf7b3d591e6a2c480ULL
+
+#define VXGE_HW_SWAPPER_READ_BYTE_SWAP_ENABLE		0xFFFFFFFFFFFFFFFFULL
+#define VXGE_HW_SWAPPER_READ_BYTE_SWAP_DISABLE		0x0000000000000000ULL
+
+#define VXGE_HW_SWAPPER_READ_BIT_FLAP_ENABLE		0xFFFFFFFFFFFFFFFFULL
+#define VXGE_HW_SWAPPER_READ_BIT_FLAP_DISABLE		0x0000000000000000ULL
+
+#define VXGE_HW_SWAPPER_WRITE_BYTE_SWAP_ENABLE		0xFFFFFFFFFFFFFFFFULL
+#define VXGE_HW_SWAPPER_WRITE_BYTE_SWAP_DISABLE		0x0000000000000000ULL
+
+#define VXGE_HW_SWAPPER_WRITE_BIT_FLAP_ENABLE		0xFFFFFFFFFFFFFFFFULL
+#define VXGE_HW_SWAPPER_WRITE_BIT_FLAP_DISABLE		0x0000000000000000ULL
+
+/*
+ * The registers are memory mapped and are native big-endian byte order. The
+ * little-endian hosts are handled by enabling hardware byte-swapping for
+ * register and dma operations.
+ */
+struct vxge_hw_legacy_reg {
+
+	u8	unused00010[0x00010];
+
+/*0x00010*/	u64	toc_swapper_fb;
+#define VXGE_HW_TOC_SWAPPER_FB_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+/*0x00018*/	u64	pifm_rd_swap_en;
+#define VXGE_HW_PIFM_RD_SWAP_EN_PIFM_RD_SWAP_EN(val) vxge_vBIT(val, 0, 64)
+/*0x00020*/	u64	pifm_rd_flip_en;
+#define VXGE_HW_PIFM_RD_FLIP_EN_PIFM_RD_FLIP_EN(val) vxge_vBIT(val, 0, 64)
+/*0x00028*/	u64	pifm_wr_swap_en;
+#define VXGE_HW_PIFM_WR_SWAP_EN_PIFM_WR_SWAP_EN(val) vxge_vBIT(val, 0, 64)
+/*0x00030*/	u64	pifm_wr_flip_en;
+#define VXGE_HW_PIFM_WR_FLIP_EN_PIFM_WR_FLIP_EN(val) vxge_vBIT(val, 0, 64)
+/*0x00038*/	u64	toc_first_pointer;
+#define VXGE_HW_TOC_FIRST_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+/*0x00040*/	u64	host_access_en;
+#define VXGE_HW_HOST_ACCESS_EN_HOST_ACCESS_EN(val) vxge_vBIT(val, 0, 64)
+
+} __packed;
+
+struct vxge_hw_toc_reg {
+
+	u8	unused00050[0x00050];
+
+/*0x00050*/	u64	toc_common_pointer;
+#define VXGE_HW_TOC_COMMON_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+/*0x00058*/	u64	toc_memrepair_pointer;
+#define VXGE_HW_TOC_MEMREPAIR_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+/*0x00060*/	u64	toc_pcicfgmgmt_pointer[17];
+#define VXGE_HW_TOC_PCICFGMGMT_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+	u8	unused001e0[0x001e0-0x000e8];
+
+/*0x001e0*/	u64	toc_mrpcim_pointer;
+#define VXGE_HW_TOC_MRPCIM_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+/*0x001e8*/	u64	toc_srpcim_pointer[17];
+#define VXGE_HW_TOC_SRPCIM_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+	u8	unused00278[0x00278-0x00270];
+
+/*0x00278*/	u64	toc_vpmgmt_pointer[17];
+#define VXGE_HW_TOC_VPMGMT_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+	u8	unused00390[0x00390-0x00300];
+
+/*0x00390*/	u64	toc_vpath_pointer[17];
+#define VXGE_HW_TOC_VPATH_POINTER_INITIAL_VAL(val) vxge_vBIT(val, 0, 64)
+	u8	unused004a0[0x004a0-0x00418];
+
+/*0x004a0*/	u64	toc_kdfc;
+#define VXGE_HW_TOC_KDFC_INITIAL_OFFSET(val) vxge_vBIT(val, 0, 61)
+#define VXGE_HW_TOC_KDFC_INITIAL_BIR(val) vxge_vBIT(val, 61, 3)
+/*0x004a8*/	u64	toc_usdc;
+#define VXGE_HW_TOC_USDC_INITIAL_OFFSET(val) vxge_vBIT(val, 0, 61)
+#define VXGE_HW_TOC_USDC_INITIAL_BIR(val) vxge_vBIT(val, 61, 3)
+/*0x004b0*/	u64	toc_kdfc_vpath_stride;
+#define	VXGE_HW_TOC_KDFC_VPATH_STRIDE_INITIAL_TOC_KDFC_VPATH_STRIDE(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x004b8*/	u64	toc_kdfc_fifo_stride;
+#define	VXGE_HW_TOC_KDFC_FIFO_STRIDE_INITIAL_TOC_KDFC_FIFO_STRIDE(val) \
+							vxge_vBIT(val, 0, 64)
+
+} __packed;
+
+struct vxge_hw_common_reg {
+
+	u8	unused00a00[0x00a00];
+
+/*0x00a00*/	u64	prc_status1;
+#define VXGE_HW_PRC_STATUS1_PRC_VP_QUIESCENT(n)	vxge_mBIT(n)
+/*0x00a08*/	u64	rxdcm_reset_in_progress;
+#define VXGE_HW_RXDCM_RESET_IN_PROGRESS_PRC_VP(n)	vxge_mBIT(n)
+/*0x00a10*/	u64	replicq_flush_in_progress;
+#define VXGE_HW_REPLICQ_FLUSH_IN_PROGRESS_NOA_VP(n)	vxge_mBIT(n)
+/*0x00a18*/	u64	rxpe_cmds_reset_in_progress;
+#define VXGE_HW_RXPE_CMDS_RESET_IN_PROGRESS_NOA_VP(n)	vxge_mBIT(n)
+/*0x00a20*/	u64	mxp_cmds_reset_in_progress;
+#define VXGE_HW_MXP_CMDS_RESET_IN_PROGRESS_NOA_VP(n)	vxge_mBIT(n)
+/*0x00a28*/	u64	noffload_reset_in_progress;
+#define VXGE_HW_NOFFLOAD_RESET_IN_PROGRESS_PRC_VP(n)	vxge_mBIT(n)
+/*0x00a30*/	u64	rd_req_in_progress;
+#define VXGE_HW_RD_REQ_IN_PROGRESS_VP(n)	vxge_mBIT(n)
+/*0x00a38*/	u64	rd_req_outstanding;
+#define VXGE_HW_RD_REQ_OUTSTANDING_VP(n)	vxge_mBIT(n)
+/*0x00a40*/	u64	kdfc_reset_in_progress;
+#define VXGE_HW_KDFC_RESET_IN_PROGRESS_NOA_VP(n)	vxge_mBIT(n)
+	u8	unused00b00[0x00b00-0x00a48];
+
+/*0x00b00*/	u64	one_cfg_vp;
+#define VXGE_HW_ONE_CFG_VP_RDY(n)	vxge_mBIT(n)
+/*0x00b08*/	u64	one_common;
+#define VXGE_HW_ONE_COMMON_PET_VPATH_RESET_IN_PROGRESS(n)	vxge_mBIT(n)
+	u8	unused00b80[0x00b80-0x00b10];
+
+/*0x00b80*/	u64	tim_int_en;
+#define VXGE_HW_TIM_INT_EN_TIM_VP(n)	vxge_mBIT(n)
+/*0x00b88*/	u64	tim_set_int_en;
+#define VXGE_HW_TIM_SET_INT_EN_VP(n)	vxge_mBIT(n)
+/*0x00b90*/	u64	tim_clr_int_en;
+#define VXGE_HW_TIM_CLR_INT_EN_VP(n)	vxge_mBIT(n)
+/*0x00b98*/	u64	tim_mask_int_during_reset;
+#define VXGE_HW_TIM_MASK_INT_DURING_RESET_VPATH(n)	vxge_mBIT(n)
+/*0x00ba0*/	u64	tim_reset_in_progress;
+#define VXGE_HW_TIM_RESET_IN_PROGRESS_TIM_VPATH(n)	vxge_mBIT(n)
+/*0x00ba8*/	u64	tim_outstanding_bmap;
+#define VXGE_HW_TIM_OUTSTANDING_BMAP_TIM_VPATH(n)	vxge_mBIT(n)
+	u8	unused00c00[0x00c00-0x00bb0];
+
+/*0x00c00*/	u64	msg_reset_in_progress;
+#define VXGE_HW_MSG_RESET_IN_PROGRESS_MSG_COMPOSITE(val) vxge_vBIT(val, 0, 17)
+/*0x00c08*/	u64	msg_mxp_mr_ready;
+#define VXGE_HW_MSG_MXP_MR_READY_MP_BOOTED(n)	vxge_mBIT(n)
+/*0x00c10*/	u64	msg_uxp_mr_ready;
+#define VXGE_HW_MSG_UXP_MR_READY_UP_BOOTED(n)	vxge_mBIT(n)
+/*0x00c18*/	u64	msg_dmq_noni_rtl_prefetch;
+#define VXGE_HW_MSG_DMQ_NONI_RTL_PREFETCH_BYPASS_ENABLE(n)	vxge_mBIT(n)
+/*0x00c20*/	u64	msg_umq_rtl_bwr;
+#define VXGE_HW_MSG_UMQ_RTL_BWR_PREFETCH_DISABLE(n)	vxge_mBIT(n)
+	u8	unused00d00[0x00d00-0x00c28];
+
+/*0x00d00*/	u64	cmn_rsthdlr_cfg0;
+#define VXGE_HW_CMN_RSTHDLR_CFG0_SW_RESET_VPATH(val) vxge_vBIT(val, 0, 17)
+/*0x00d08*/	u64	cmn_rsthdlr_cfg1;
+#define VXGE_HW_CMN_RSTHDLR_CFG1_CLR_VPATH_RESET(val) vxge_vBIT(val, 0, 17)
+/*0x00d10*/	u64	cmn_rsthdlr_cfg2;
+#define VXGE_HW_CMN_RSTHDLR_CFG2_SW_RESET_FIFO0(val) vxge_vBIT(val, 0, 17)
+/*0x00d18*/	u64	cmn_rsthdlr_cfg3;
+#define VXGE_HW_CMN_RSTHDLR_CFG3_SW_RESET_FIFO1(val) vxge_vBIT(val, 0, 17)
+/*0x00d20*/	u64	cmn_rsthdlr_cfg4;
+#define VXGE_HW_CMN_RSTHDLR_CFG4_SW_RESET_FIFO2(val) vxge_vBIT(val, 0, 17)
+	u8	unused00d40[0x00d40-0x00d28];
+
+/*0x00d40*/	u64	cmn_rsthdlr_cfg8;
+#define VXGE_HW_CMN_RSTHDLR_CFG8_INCR_VPATH_INST_NUM(val) vxge_vBIT(val, 0, 17)
+/*0x00d48*/	u64	stats_cfg0;
+#define VXGE_HW_STATS_CFG0_STATS_ENABLE(val) vxge_vBIT(val, 0, 17)
+	u8	unused00da8[0x00da8-0x00d50];
+
+/*0x00da8*/	u64	clear_msix_mask_vect[4];
+#define VXGE_HW_CLEAR_MSIX_MASK_VECT_CLEAR_MSIX_MASK_VECT(val) \
+						vxge_vBIT(val, 0, 17)
+/*0x00dc8*/	u64	set_msix_mask_vect[4];
+#define VXGE_HW_SET_MSIX_MASK_VECT_SET_MSIX_MASK_VECT(val) vxge_vBIT(val, 0, 17)
+/*0x00de8*/	u64	clear_msix_mask_all_vect;
+#define	VXGE_HW_CLEAR_MSIX_MASK_ALL_VECT_CLEAR_MSIX_MASK_ALL_VECT(val)	\
+							vxge_vBIT(val, 0, 17)
+/*0x00df0*/	u64	set_msix_mask_all_vect;
+#define	VXGE_HW_SET_MSIX_MASK_ALL_VECT_SET_MSIX_MASK_ALL_VECT(val) \
+							vxge_vBIT(val, 0, 17)
+/*0x00df8*/	u64	mask_vector[4];
+#define VXGE_HW_MASK_VECTOR_MASK_VECTOR(val) vxge_vBIT(val, 0, 17)
+/*0x00e18*/	u64	msix_pending_vector[4];
+#define VXGE_HW_MSIX_PENDING_VECTOR_MSIX_PENDING_VECTOR(val) \
+							vxge_vBIT(val, 0, 17)
+/*0x00e38*/	u64	clr_msix_one_shot_vec[4];
+#define	VXGE_HW_CLR_MSIX_ONE_SHOT_VEC_CLR_MSIX_ONE_SHOT_VEC(val) \
+							vxge_vBIT(val, 0, 17)
+/*0x00e58*/	u64	titan_asic_id;
+#define VXGE_HW_TITAN_ASIC_ID_INITIAL_DEVICE_ID(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_TITAN_ASIC_ID_INITIAL_MAJOR_REVISION(val) vxge_vBIT(val, 48, 8)
+#define VXGE_HW_TITAN_ASIC_ID_INITIAL_MINOR_REVISION(val) vxge_vBIT(val, 56, 8)
+/*0x00e60*/	u64	titan_general_int_status;
+#define	VXGE_HW_TITAN_GENERAL_INT_STATUS_MRPCIM_ALARM_INT	vxge_mBIT(0)
+#define	VXGE_HW_TITAN_GENERAL_INT_STATUS_SRPCIM_ALARM_INT	vxge_mBIT(1)
+#define	VXGE_HW_TITAN_GENERAL_INT_STATUS_VPATH_ALARM_INT	vxge_mBIT(2)
+#define	VXGE_HW_TITAN_GENERAL_INT_STATUS_VPATH_TRAFFIC_INT(val) \
+							vxge_vBIT(val, 3, 17)
+	u8	unused00e70[0x00e70-0x00e68];
+
+/*0x00e70*/	u64	titan_mask_all_int;
+#define	VXGE_HW_TITAN_MASK_ALL_INT_ALARM	vxge_mBIT(7)
+#define	VXGE_HW_TITAN_MASK_ALL_INT_TRAFFIC	vxge_mBIT(15)
+	u8	unused00e80[0x00e80-0x00e78];
+
+/*0x00e80*/	u64	tim_int_status0;
+#define VXGE_HW_TIM_INT_STATUS0_TIM_INT_STATUS0(val) vxge_vBIT(val, 0, 64)
+/*0x00e88*/	u64	tim_int_mask0;
+#define VXGE_HW_TIM_INT_MASK0_TIM_INT_MASK0(val) vxge_vBIT(val, 0, 64)
+/*0x00e90*/	u64	tim_int_status1;
+#define VXGE_HW_TIM_INT_STATUS1_TIM_INT_STATUS1(val) vxge_vBIT(val, 0, 4)
+/*0x00e98*/	u64	tim_int_mask1;
+#define VXGE_HW_TIM_INT_MASK1_TIM_INT_MASK1(val) vxge_vBIT(val, 0, 4)
+/*0x00ea0*/	u64	rti_int_status;
+#define VXGE_HW_RTI_INT_STATUS_RTI_INT_STATUS(val) vxge_vBIT(val, 0, 17)
+/*0x00ea8*/	u64	rti_int_mask;
+#define VXGE_HW_RTI_INT_MASK_RTI_INT_MASK(val) vxge_vBIT(val, 0, 17)
+/*0x00eb0*/	u64	adapter_status;
+#define	VXGE_HW_ADAPTER_STATUS_RTDMA_RTDMA_READY	vxge_mBIT(0)
+#define	VXGE_HW_ADAPTER_STATUS_WRDMA_WRDMA_READY	vxge_mBIT(1)
+#define	VXGE_HW_ADAPTER_STATUS_KDFC_KDFC_READY	vxge_mBIT(2)
+#define	VXGE_HW_ADAPTER_STATUS_TPA_TMAC_BUF_EMPTY	vxge_mBIT(3)
+#define	VXGE_HW_ADAPTER_STATUS_RDCTL_PIC_QUIESCENT	vxge_mBIT(4)
+#define	VXGE_HW_ADAPTER_STATUS_XGMAC_NETWORK_FAULT	vxge_mBIT(5)
+#define	VXGE_HW_ADAPTER_STATUS_ROCRC_OFFLOAD_QUIESCENT	vxge_mBIT(6)
+#define	VXGE_HW_ADAPTER_STATUS_G3IF_FB_G3IF_FB_GDDR3_READY	vxge_mBIT(7)
+#define	VXGE_HW_ADAPTER_STATUS_G3IF_CM_G3IF_CM_GDDR3_READY	vxge_mBIT(8)
+#define	VXGE_HW_ADAPTER_STATUS_RIC_RIC_RUNNING	vxge_mBIT(9)
+#define	VXGE_HW_ADAPTER_STATUS_CMG_C_PLL_IN_LOCK	vxge_mBIT(10)
+#define	VXGE_HW_ADAPTER_STATUS_XGMAC_X_PLL_IN_LOCK	vxge_mBIT(11)
+#define	VXGE_HW_ADAPTER_STATUS_FBIF_M_PLL_IN_LOCK	vxge_mBIT(12)
+#define VXGE_HW_ADAPTER_STATUS_PCC_PCC_IDLE(val) vxge_vBIT(val, 24, 8)
+#define VXGE_HW_ADAPTER_STATUS_ROCRC_RC_PRC_QUIESCENT(val) vxge_vBIT(val, 44, 8)
+/*0x00eb8*/	u64	gen_ctrl;
+#define	VXGE_HW_GEN_CTRL_SPI_MRPCIM_WR_DIS	vxge_mBIT(0)
+#define	VXGE_HW_GEN_CTRL_SPI_MRPCIM_RD_DIS	vxge_mBIT(1)
+#define	VXGE_HW_GEN_CTRL_SPI_SRPCIM_WR_DIS	vxge_mBIT(2)
+#define	VXGE_HW_GEN_CTRL_SPI_SRPCIM_RD_DIS	vxge_mBIT(3)
+#define	VXGE_HW_GEN_CTRL_SPI_DEBUG_DIS	vxge_mBIT(4)
+#define	VXGE_HW_GEN_CTRL_SPI_APP_LTSSM_TIMER_DIS	vxge_mBIT(5)
+#define VXGE_HW_GEN_CTRL_SPI_NOT_USED(val) vxge_vBIT(val, 6, 4)
+	u8	unused00ed0[0x00ed0-0x00ec0];
+
+/*0x00ed0*/	u64	adapter_ready;
+#define	VXGE_HW_ADAPTER_READY_ADAPTER_READY	vxge_mBIT(63)
+/*0x00ed8*/	u64	outstanding_read;
+#define VXGE_HW_OUTSTANDING_READ_OUTSTANDING_READ(val) vxge_vBIT(val, 0, 17)
+/*0x00ee0*/	u64	vpath_rst_in_prog;
+#define VXGE_HW_VPATH_RST_IN_PROG_VPATH_RST_IN_PROG(val) vxge_vBIT(val, 0, 17)
+/*0x00ee8*/	u64	vpath_reg_modified;
+#define VXGE_HW_VPATH_REG_MODIFIED_VPATH_REG_MODIFIED(val) vxge_vBIT(val, 0, 17)
+	u8	unused00fc0[0x00fc0-0x00ef0];
+
+/*0x00fc0*/	u64	cp_reset_in_progress;
+#define VXGE_HW_CP_RESET_IN_PROGRESS_CP_VPATH(n)	vxge_mBIT(n)
+	u8	unused01080[0x01080-0x00fc8];
+
+/*0x01080*/	u64	xgmac_ready;
+#define VXGE_HW_XGMAC_READY_XMACJ_READY(val) vxge_vBIT(val, 0, 17)
+	u8	unused010c0[0x010c0-0x01088];
+
+/*0x010c0*/	u64	fbif_ready;
+#define VXGE_HW_FBIF_READY_FAU_READY(val) vxge_vBIT(val, 0, 17)
+	u8	unused01100[0x01100-0x010c8];
+
+/*0x01100*/	u64	vplane_assignments;
+#define VXGE_HW_VPLANE_ASSIGNMENTS_VPLANE_ASSIGNMENTS(val) vxge_vBIT(val, 3, 5)
+/*0x01108*/	u64	vpath_assignments;
+#define VXGE_HW_VPATH_ASSIGNMENTS_VPATH_ASSIGNMENTS(val) vxge_vBIT(val, 0, 17)
+/*0x01110*/	u64	resource_assignments;
+#define VXGE_HW_RESOURCE_ASSIGNMENTS_RESOURCE_ASSIGNMENTS(val) \
+						vxge_vBIT(val, 0, 17)
+/*0x01118*/	u64	host_type_assignments;
+#define	VXGE_HW_HOST_TYPE_ASSIGNMENTS_HOST_TYPE_ASSIGNMENTS(val) \
+							vxge_vBIT(val, 5, 3)
+	u8	unused01128[0x01128-0x01120];
+
+/*0x01128*/	u64	max_resource_assignments;
+#define VXGE_HW_MAX_RESOURCE_ASSIGNMENTS_PCI_MAX_VPLANE(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_MAX_RESOURCE_ASSIGNMENTS_PCI_MAX_VPATHS(val) \
+						vxge_vBIT(val, 11, 5)
+/*0x01130*/	u64	pf_vpath_assignments;
+#define VXGE_HW_PF_VPATH_ASSIGNMENTS_PF_VPATH_ASSIGNMENTS(val) \
+						vxge_vBIT(val, 0, 17)
+	u8	unused01200[0x01200-0x01138];
+
+/*0x01200*/	u64	rts_access_icmp;
+#define VXGE_HW_RTS_ACCESS_ICMP_EN(val) vxge_vBIT(val, 0, 17)
+/*0x01208*/	u64	rts_access_tcpsyn;
+#define VXGE_HW_RTS_ACCESS_TCPSYN_EN(val) vxge_vBIT(val, 0, 17)
+/*0x01210*/	u64	rts_access_zl4pyld;
+#define VXGE_HW_RTS_ACCESS_ZL4PYLD_EN(val) vxge_vBIT(val, 0, 17)
+/*0x01218*/	u64	rts_access_l4prtcl_tcp;
+#define VXGE_HW_RTS_ACCESS_L4PRTCL_TCP_EN(val) vxge_vBIT(val, 0, 17)
+/*0x01220*/	u64	rts_access_l4prtcl_udp;
+#define VXGE_HW_RTS_ACCESS_L4PRTCL_UDP_EN(val) vxge_vBIT(val, 0, 17)
+/*0x01228*/	u64	rts_access_l4prtcl_flex;
+#define VXGE_HW_RTS_ACCESS_L4PRTCL_FLEX_EN(val) vxge_vBIT(val, 0, 17)
+/*0x01230*/	u64	rts_access_ipfrag;
+#define VXGE_HW_RTS_ACCESS_IPFRAG_EN(val) vxge_vBIT(val, 0, 17)
+
+} __packed;
+
+struct vxge_hw_memrepair_reg {
+	u64	unused1;
+	u64	unused2;
+} __packed;
+
+struct vxge_hw_pcicfgmgmt_reg {
+
+/*0x00000*/	u64	resource_no;
+#define	VXGE_HW_RESOURCE_NO_PFN_OR_VF	BIT(3)
+/*0x00008*/	u64	bargrp_pf_or_vf_bar0_mask;
+#define	VXGE_HW_BARGRP_PF_OR_VF_BAR0_MASK_BARGRP_PF_OR_VF_BAR0_MASK(val) \
+							vxge_vBIT(val, 2, 6)
+/*0x00010*/	u64	bargrp_pf_or_vf_bar1_mask;
+#define	VXGE_HW_BARGRP_PF_OR_VF_BAR1_MASK_BARGRP_PF_OR_VF_BAR1_MASK(val) \
+							vxge_vBIT(val, 2, 6)
+/*0x00018*/	u64	bargrp_pf_or_vf_bar2_mask;
+#define	VXGE_HW_BARGRP_PF_OR_VF_BAR2_MASK_BARGRP_PF_OR_VF_BAR2_MASK(val) \
+							vxge_vBIT(val, 2, 6)
+/*0x00020*/	u64	msixgrp_no;
+#define VXGE_HW_MSIXGRP_NO_TABLE_SIZE(val) vxge_vBIT(val, 5, 11)
+
+} __packed;
+
+struct vxge_hw_mrpcim_reg {
+/*0x00000*/	u64	g3fbct_int_status;
+#define	VXGE_HW_G3FBCT_INT_STATUS_ERR_G3IF_INT	vxge_mBIT(0)
+/*0x00008*/	u64	g3fbct_int_mask;
+/*0x00010*/	u64	g3fbct_err_reg;
+#define	VXGE_HW_G3FBCT_ERR_REG_G3IF_SM_ERR	vxge_mBIT(4)
+#define	VXGE_HW_G3FBCT_ERR_REG_G3IF_GDDR3_DECC	vxge_mBIT(5)
+#define	VXGE_HW_G3FBCT_ERR_REG_G3IF_GDDR3_U_DECC	vxge_mBIT(6)
+#define	VXGE_HW_G3FBCT_ERR_REG_G3IF_CTRL_FIFO_DECC	vxge_mBIT(7)
+#define	VXGE_HW_G3FBCT_ERR_REG_G3IF_GDDR3_SECC	vxge_mBIT(29)
+#define	VXGE_HW_G3FBCT_ERR_REG_G3IF_GDDR3_U_SECC	vxge_mBIT(30)
+#define	VXGE_HW_G3FBCT_ERR_REG_G3IF_CTRL_FIFO_SECC	vxge_mBIT(31)
+/*0x00018*/	u64	g3fbct_err_mask;
+/*0x00020*/	u64	g3fbct_err_alarm;
+
+	u8	unused00a00[0x00a00-0x00028];
+
+/*0x00a00*/	u64	wrdma_int_status;
+#define	VXGE_HW_WRDMA_INT_STATUS_RC_ALARM_RC_INT	vxge_mBIT(0)
+#define	VXGE_HW_WRDMA_INT_STATUS_RXDRM_SM_ERR_RXDRM_INT	vxge_mBIT(1)
+#define	VXGE_HW_WRDMA_INT_STATUS_RXDCM_SM_ERR_RXDCM_SM_INT	vxge_mBIT(2)
+#define	VXGE_HW_WRDMA_INT_STATUS_RXDWM_SM_ERR_RXDWM_INT	vxge_mBIT(3)
+#define	VXGE_HW_WRDMA_INT_STATUS_RDA_ERR_RDA_INT	vxge_mBIT(6)
+#define	VXGE_HW_WRDMA_INT_STATUS_RDA_ECC_DB_RDA_ECC_DB_INT	vxge_mBIT(8)
+#define	VXGE_HW_WRDMA_INT_STATUS_RDA_ECC_SG_RDA_ECC_SG_INT	vxge_mBIT(9)
+#define	VXGE_HW_WRDMA_INT_STATUS_FRF_ALARM_FRF_INT	vxge_mBIT(12)
+#define	VXGE_HW_WRDMA_INT_STATUS_ROCRC_ALARM_ROCRC_INT	vxge_mBIT(13)
+#define	VXGE_HW_WRDMA_INT_STATUS_WDE0_ALARM_WDE0_INT	vxge_mBIT(14)
+#define	VXGE_HW_WRDMA_INT_STATUS_WDE1_ALARM_WDE1_INT	vxge_mBIT(15)
+#define	VXGE_HW_WRDMA_INT_STATUS_WDE2_ALARM_WDE2_INT	vxge_mBIT(16)
+#define	VXGE_HW_WRDMA_INT_STATUS_WDE3_ALARM_WDE3_INT	vxge_mBIT(17)
+/*0x00a08*/	u64	wrdma_int_mask;
+/*0x00a10*/	u64	rc_alarm_reg;
+#define	VXGE_HW_RC_ALARM_REG_FTC_SM_ERR	vxge_mBIT(0)
+#define	VXGE_HW_RC_ALARM_REG_FTC_SM_PHASE_ERR	vxge_mBIT(1)
+#define	VXGE_HW_RC_ALARM_REG_BTDWM_SM_ERR	vxge_mBIT(2)
+#define	VXGE_HW_RC_ALARM_REG_BTC_SM_ERR	vxge_mBIT(3)
+#define	VXGE_HW_RC_ALARM_REG_BTDCM_SM_ERR	vxge_mBIT(4)
+#define	VXGE_HW_RC_ALARM_REG_BTDRM_SM_ERR	vxge_mBIT(5)
+#define	VXGE_HW_RC_ALARM_REG_RMM_RXD_RC_ECC_DB_ERR	vxge_mBIT(6)
+#define	VXGE_HW_RC_ALARM_REG_RMM_RXD_RC_ECC_SG_ERR	vxge_mBIT(7)
+#define	VXGE_HW_RC_ALARM_REG_RHS_RXD_RHS_ECC_DB_ERR	vxge_mBIT(8)
+#define	VXGE_HW_RC_ALARM_REG_RHS_RXD_RHS_ECC_SG_ERR	vxge_mBIT(9)
+#define	VXGE_HW_RC_ALARM_REG_RMM_SM_ERR	vxge_mBIT(10)
+#define	VXGE_HW_RC_ALARM_REG_BTC_VPATH_MISMATCH_ERR	vxge_mBIT(12)
+/*0x00a18*/	u64	rc_alarm_mask;
+/*0x00a20*/	u64	rc_alarm_alarm;
+/*0x00a28*/	u64	rxdrm_sm_err_reg;
+#define VXGE_HW_RXDRM_SM_ERR_REG_PRC_VP(n)	vxge_mBIT(n)
+/*0x00a30*/	u64	rxdrm_sm_err_mask;
+/*0x00a38*/	u64	rxdrm_sm_err_alarm;
+/*0x00a40*/	u64	rxdcm_sm_err_reg;
+#define VXGE_HW_RXDCM_SM_ERR_REG_PRC_VP(n)	vxge_mBIT(n)
+/*0x00a48*/	u64	rxdcm_sm_err_mask;
+/*0x00a50*/	u64	rxdcm_sm_err_alarm;
+/*0x00a58*/	u64	rxdwm_sm_err_reg;
+#define VXGE_HW_RXDWM_SM_ERR_REG_PRC_VP(n)	vxge_mBIT(n)
+/*0x00a60*/	u64	rxdwm_sm_err_mask;
+/*0x00a68*/	u64	rxdwm_sm_err_alarm;
+/*0x00a70*/	u64	rda_err_reg;
+#define	VXGE_HW_RDA_ERR_REG_RDA_SM0_ERR_ALARM	vxge_mBIT(0)
+#define	VXGE_HW_RDA_ERR_REG_RDA_MISC_ERR	vxge_mBIT(1)
+#define	VXGE_HW_RDA_ERR_REG_RDA_PCIX_ERR	vxge_mBIT(2)
+#define	VXGE_HW_RDA_ERR_REG_RDA_RXD_ECC_DB_ERR	vxge_mBIT(3)
+#define	VXGE_HW_RDA_ERR_REG_RDA_FRM_ECC_DB_ERR	vxge_mBIT(4)
+#define	VXGE_HW_RDA_ERR_REG_RDA_UQM_ECC_DB_ERR	vxge_mBIT(5)
+#define	VXGE_HW_RDA_ERR_REG_RDA_IMM_ECC_DB_ERR	vxge_mBIT(6)
+#define	VXGE_HW_RDA_ERR_REG_RDA_TIM_ECC_DB_ERR	vxge_mBIT(7)
+/*0x00a78*/	u64	rda_err_mask;
+/*0x00a80*/	u64	rda_err_alarm;
+/*0x00a88*/	u64	rda_ecc_db_reg;
+#define VXGE_HW_RDA_ECC_DB_REG_RDA_RXD_ERR(n)	vxge_mBIT(n)
+/*0x00a90*/	u64	rda_ecc_db_mask;
+/*0x00a98*/	u64	rda_ecc_db_alarm;
+/*0x00aa0*/	u64	rda_ecc_sg_reg;
+#define VXGE_HW_RDA_ECC_SG_REG_RDA_RXD_ERR(n)	vxge_mBIT(n)
+/*0x00aa8*/	u64	rda_ecc_sg_mask;
+/*0x00ab0*/	u64	rda_ecc_sg_alarm;
+/*0x00ab8*/	u64	rqa_err_reg;
+#define	VXGE_HW_RQA_ERR_REG_RQA_SM_ERR_ALARM	vxge_mBIT(0)
+/*0x00ac0*/	u64	rqa_err_mask;
+/*0x00ac8*/	u64	rqa_err_alarm;
+/*0x00ad0*/	u64	frf_alarm_reg;
+#define VXGE_HW_FRF_ALARM_REG_PRC_VP_FRF_SM_ERR(n)	vxge_mBIT(n)
+/*0x00ad8*/	u64	frf_alarm_mask;
+/*0x00ae0*/	u64	frf_alarm_alarm;
+/*0x00ae8*/	u64	rocrc_alarm_reg;
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_QCC_BYP_ECC_DB	vxge_mBIT(0)
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_QCC_BYP_ECC_SG	vxge_mBIT(1)
+#define	VXGE_HW_ROCRC_ALARM_REG_NOA_NMA_SM_ERR	vxge_mBIT(2)
+#define	VXGE_HW_ROCRC_ALARM_REG_NOA_IMMM_ECC_DB	vxge_mBIT(3)
+#define	VXGE_HW_ROCRC_ALARM_REG_NOA_IMMM_ECC_SG	vxge_mBIT(4)
+#define	VXGE_HW_ROCRC_ALARM_REG_UDQ_UMQM_ECC_DB	vxge_mBIT(5)
+#define	VXGE_HW_ROCRC_ALARM_REG_UDQ_UMQM_ECC_SG	vxge_mBIT(6)
+#define	VXGE_HW_ROCRC_ALARM_REG_NOA_RCBM_ECC_DB	vxge_mBIT(11)
+#define	VXGE_HW_ROCRC_ALARM_REG_NOA_RCBM_ECC_SG	vxge_mBIT(12)
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_MULTI_EGB_RSVD_ERR	vxge_mBIT(13)
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_MULTI_EGB_OWN_ERR	vxge_mBIT(14)
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_MULTI_BYP_OWN_ERR	vxge_mBIT(15)
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_OWN_NOT_ASSIGNED_ERR	vxge_mBIT(16)
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_OWN_RSVD_SYNC_ERR	vxge_mBIT(17)
+#define	VXGE_HW_ROCRC_ALARM_REG_QCQ_LOST_EGB_ERR	vxge_mBIT(18)
+#define	VXGE_HW_ROCRC_ALARM_REG_RCQ_BYPQ0_OVERFLOW	vxge_mBIT(19)
+#define	VXGE_HW_ROCRC_ALARM_REG_RCQ_BYPQ1_OVERFLOW	vxge_mBIT(20)
+#define	VXGE_HW_ROCRC_ALARM_REG_RCQ_BYPQ2_OVERFLOW	vxge_mBIT(21)
+#define	VXGE_HW_ROCRC_ALARM_REG_NOA_WCT_CMD_FIFO_ERR	vxge_mBIT(22)
+/*0x00af0*/	u64	rocrc_alarm_mask;
+/*0x00af8*/	u64	rocrc_alarm_alarm;
+/*0x00b00*/	u64	wde0_alarm_reg;
+#define	VXGE_HW_WDE0_ALARM_REG_WDE0_DCC_SM_ERR	vxge_mBIT(0)
+#define	VXGE_HW_WDE0_ALARM_REG_WDE0_PRM_SM_ERR	vxge_mBIT(1)
+#define	VXGE_HW_WDE0_ALARM_REG_WDE0_CP_SM_ERR	vxge_mBIT(2)
+#define	VXGE_HW_WDE0_ALARM_REG_WDE0_CP_CMD_ERR	vxge_mBIT(3)
+#define	VXGE_HW_WDE0_ALARM_REG_WDE0_PCR_SM_ERR	vxge_mBIT(4)
+/*0x00b08*/	u64	wde0_alarm_mask;
+/*0x00b10*/	u64	wde0_alarm_alarm;
+/*0x00b18*/	u64	wde1_alarm_reg;
+#define	VXGE_HW_WDE1_ALARM_REG_WDE1_DCC_SM_ERR	vxge_mBIT(0)
+#define	VXGE_HW_WDE1_ALARM_REG_WDE1_PRM_SM_ERR	vxge_mBIT(1)
+#define	VXGE_HW_WDE1_ALARM_REG_WDE1_CP_SM_ERR	vxge_mBIT(2)
+#define	VXGE_HW_WDE1_ALARM_REG_WDE1_CP_CMD_ERR	vxge_mBIT(3)
+#define	VXGE_HW_WDE1_ALARM_REG_WDE1_PCR_SM_ERR	vxge_mBIT(4)
+/*0x00b20*/	u64	wde1_alarm_mask;
+/*0x00b28*/	u64	wde1_alarm_alarm;
+/*0x00b30*/	u64	wde2_alarm_reg;
+#define	VXGE_HW_WDE2_ALARM_REG_WDE2_DCC_SM_ERR	vxge_mBIT(0)
+#define	VXGE_HW_WDE2_ALARM_REG_WDE2_PRM_SM_ERR	vxge_mBIT(1)
+#define	VXGE_HW_WDE2_ALARM_REG_WDE2_CP_SM_ERR	vxge_mBIT(2)
+#define	VXGE_HW_WDE2_ALARM_REG_WDE2_CP_CMD_ERR	vxge_mBIT(3)
+#define	VXGE_HW_WDE2_ALARM_REG_WDE2_PCR_SM_ERR	vxge_mBIT(4)
+/*0x00b38*/	u64	wde2_alarm_mask;
+/*0x00b40*/	u64	wde2_alarm_alarm;
+/*0x00b48*/	u64	wde3_alarm_reg;
+#define	VXGE_HW_WDE3_ALARM_REG_WDE3_DCC_SM_ERR	vxge_mBIT(0)
+#define	VXGE_HW_WDE3_ALARM_REG_WDE3_PRM_SM_ERR	vxge_mBIT(1)
+#define	VXGE_HW_WDE3_ALARM_REG_WDE3_CP_SM_ERR	vxge_mBIT(2)
+#define	VXGE_HW_WDE3_ALARM_REG_WDE3_CP_CMD_ERR	vxge_mBIT(3)
+#define	VXGE_HW_WDE3_ALARM_REG_WDE3_PCR_SM_ERR	vxge_mBIT(4)
+/*0x00b50*/	u64	wde3_alarm_mask;
+/*0x00b58*/	u64	wde3_alarm_alarm;
+
+	u8	unused00be8[0x00be8-0x00b60];
+
+/*0x00be8*/	u64	rx_w_round_robin_0;
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_0(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_1(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_2(val) vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_3(val) vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_4(val) vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_5(val) vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_6(val) vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_0_RX_W_PRIORITY_SS_7(val) vxge_vBIT(val, 59, 5)
+/*0x00bf0*/	u64	rx_w_round_robin_1;
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_8(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_9(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_10(val) \
+						vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_11(val) \
+						vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_12(val) \
+						vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_13(val) \
+						vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_14(val) \
+						vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_1_RX_W_PRIORITY_SS_15(val) \
+						vxge_vBIT(val, 59, 5)
+/*0x00bf8*/	u64	rx_w_round_robin_2;
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_16(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_17(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_18(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_19(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_20(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_21(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_22(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_2_RX_W_PRIORITY_SS_23(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c00*/	u64	rx_w_round_robin_3;
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_24(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_25(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_26(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_27(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_28(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_29(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_30(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_3_RX_W_PRIORITY_SS_31(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c08*/	u64	rx_w_round_robin_4;
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_32(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_33(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_34(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_35(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_36(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_37(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_38(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_4_RX_W_PRIORITY_SS_39(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c10*/	u64	rx_w_round_robin_5;
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_40(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_41(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_42(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_43(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_44(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_45(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_46(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_5_RX_W_PRIORITY_SS_47(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c18*/	u64	rx_w_round_robin_6;
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_48(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_49(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_50(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_51(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_52(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_53(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_54(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_6_RX_W_PRIORITY_SS_55(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c20*/	u64	rx_w_round_robin_7;
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_56(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_57(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_58(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_59(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_60(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_61(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_62(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_7_RX_W_PRIORITY_SS_63(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c28*/	u64	rx_w_round_robin_8;
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_64(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_65(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_66(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_67(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_68(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_69(val) \
+						vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_70(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_8_RX_W_PRIORITY_SS_71(val) \
+						vxge_vBIT(val, 59, 5)
+/*0x00c30*/	u64	rx_w_round_robin_9;
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_72(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_73(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_74(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_75(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_76(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_77(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_78(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_9_RX_W_PRIORITY_SS_79(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c38*/	u64	rx_w_round_robin_10;
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_80(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_81(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_82(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_83(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_84(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_85(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_86(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_10_RX_W_PRIORITY_SS_87(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c40*/	u64	rx_w_round_robin_11;
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_88(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_89(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_90(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_91(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_92(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_93(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_94(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_11_RX_W_PRIORITY_SS_95(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c48*/	u64	rx_w_round_robin_12;
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_96(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_97(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_98(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_99(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_100(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_101(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_102(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_12_RX_W_PRIORITY_SS_103(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c50*/	u64	rx_w_round_robin_13;
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_104(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_105(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_106(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_107(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_108(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_109(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_110(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_13_RX_W_PRIORITY_SS_111(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c58*/	u64	rx_w_round_robin_14;
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_112(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_113(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_114(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_115(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_116(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_117(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_118(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_14_RX_W_PRIORITY_SS_119(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c60*/	u64	rx_w_round_robin_15;
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_120(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_121(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_122(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_123(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_124(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_125(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_126(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_15_RX_W_PRIORITY_SS_127(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c68*/	u64	rx_w_round_robin_16;
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_128(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_129(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_130(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_131(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_132(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_133(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_134(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_16_RX_W_PRIORITY_SS_135(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c70*/	u64	rx_w_round_robin_17;
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_136(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_137(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_138(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_139(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_140(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_141(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_142(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_17_RX_W_PRIORITY_SS_143(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c78*/	u64	rx_w_round_robin_18;
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_144(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_145(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_146(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_147(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_148(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_149(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_150(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_18_RX_W_PRIORITY_SS_151(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c80*/	u64	rx_w_round_robin_19;
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_152(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_153(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_154(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_155(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_156(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_157(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_158(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_19_RX_W_PRIORITY_SS_159(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c88*/	u64	rx_w_round_robin_20;
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_160(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_161(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_162(val) \
+							vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_163(val) \
+							vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_164(val) \
+							vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_165(val) \
+							vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_166(val) \
+							vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_20_RX_W_PRIORITY_SS_167(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00c90*/	u64	rx_w_round_robin_21;
+#define VXGE_HW_RX_W_ROUND_ROBIN_21_RX_W_PRIORITY_SS_168(val) \
+							vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_21_RX_W_PRIORITY_SS_169(val) \
+							vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_W_ROUND_ROBIN_21_RX_W_PRIORITY_SS_170(val) \
+							vxge_vBIT(val, 19, 5)
+
+#define VXGE_HW_WRR_RING_SERVICE_STATES			171
+#define VXGE_HW_WRR_RING_COUNT				22
+
+/*0x00c98*/	u64	rx_queue_priority_0;
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_0(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_1(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_2(val) vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_3(val) vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_4(val) vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_5(val) vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_6(val) vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_0_RX_Q_NUMBER_7(val) vxge_vBIT(val, 59, 5)
+/*0x00ca0*/	u64	rx_queue_priority_1;
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_8(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_9(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_10(val) vxge_vBIT(val, 19, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_11(val) vxge_vBIT(val, 27, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_12(val) vxge_vBIT(val, 35, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_13(val) vxge_vBIT(val, 43, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_14(val) vxge_vBIT(val, 51, 5)
+#define VXGE_HW_RX_QUEUE_PRIORITY_1_RX_Q_NUMBER_15(val) vxge_vBIT(val, 59, 5)
+/*0x00ca8*/	u64	rx_queue_priority_2;
+#define VXGE_HW_RX_QUEUE_PRIORITY_2_RX_Q_NUMBER_16(val) vxge_vBIT(val, 3, 5)
+	u8	unused00cc8[0x00cc8-0x00cb0];
+
+/*0x00cc8*/	u64	replication_queue_priority;
+#define	VXGE_HW_REPLICATION_QUEUE_PRIORITY_REPLICATION_QUEUE_PRIORITY(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00cd0*/	u64	rx_queue_select;
+#define VXGE_HW_RX_QUEUE_SELECT_NUMBER(n)	vxge_mBIT(n)
+#define	VXGE_HW_RX_QUEUE_SELECT_ENABLE_CODE	vxge_mBIT(15)
+#define	VXGE_HW_RX_QUEUE_SELECT_ENABLE_HIERARCHICAL_PRTY	vxge_mBIT(23)
+/*0x00cd8*/	u64	rqa_vpbp_ctrl;
+#define	VXGE_HW_RQA_VPBP_CTRL_WR_XON_DIS	vxge_mBIT(15)
+#define	VXGE_HW_RQA_VPBP_CTRL_ROCRC_DIS	vxge_mBIT(23)
+#define	VXGE_HW_RQA_VPBP_CTRL_TXPE_DIS	vxge_mBIT(31)
+/*0x00ce0*/	u64	rx_multi_cast_ctrl;
+#define	VXGE_HW_RX_MULTI_CAST_CTRL_TIME_OUT_DIS	vxge_mBIT(0)
+#define	VXGE_HW_RX_MULTI_CAST_CTRL_FRM_DROP_DIS	vxge_mBIT(1)
+#define VXGE_HW_RX_MULTI_CAST_CTRL_NO_RXD_TIME_OUT_CNT(val) \
+							vxge_vBIT(val, 2, 30)
+#define VXGE_HW_RX_MULTI_CAST_CTRL_TIME_OUT_CNT(val) vxge_vBIT(val, 32, 32)
+/*0x00ce8*/	u64	wde_prm_ctrl;
+#define VXGE_HW_WDE_PRM_CTRL_SPAV_THRESHOLD(val) vxge_vBIT(val, 2, 10)
+#define VXGE_HW_WDE_PRM_CTRL_SPLIT_THRESHOLD(val) vxge_vBIT(val, 18, 14)
+#define	VXGE_HW_WDE_PRM_CTRL_SPLIT_ON_1ST_ROW	vxge_mBIT(32)
+#define	VXGE_HW_WDE_PRM_CTRL_SPLIT_ON_ROW_BNDRY	vxge_mBIT(33)
+#define VXGE_HW_WDE_PRM_CTRL_FB_ROW_SIZE(val) vxge_vBIT(val, 46, 2)
+/*0x00cf0*/	u64	noa_ctrl;
+#define VXGE_HW_NOA_CTRL_FRM_PRTY_QUOTA(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_NOA_CTRL_NON_FRM_PRTY_QUOTA(val) vxge_vBIT(val, 11, 5)
+#define	VXGE_HW_NOA_CTRL_IGNORE_KDFC_IF_STATUS	vxge_mBIT(16)
+#define VXGE_HW_NOA_CTRL_MAX_JOB_CNT_FOR_WDE0(val) vxge_vBIT(val, 37, 4)
+#define VXGE_HW_NOA_CTRL_MAX_JOB_CNT_FOR_WDE1(val) vxge_vBIT(val, 45, 4)
+#define VXGE_HW_NOA_CTRL_MAX_JOB_CNT_FOR_WDE2(val) vxge_vBIT(val, 53, 4)
+#define VXGE_HW_NOA_CTRL_MAX_JOB_CNT_FOR_WDE3(val) vxge_vBIT(val, 60, 4)
+/*0x00cf8*/	u64	phase_cfg;
+#define	VXGE_HW_PHASE_CFG_QCC_WR_PHASE_EN	vxge_mBIT(0)
+#define	VXGE_HW_PHASE_CFG_QCC_RD_PHASE_EN	vxge_mBIT(3)
+#define	VXGE_HW_PHASE_CFG_IMMM_WR_PHASE_EN	vxge_mBIT(7)
+#define	VXGE_HW_PHASE_CFG_IMMM_RD_PHASE_EN	vxge_mBIT(11)
+#define	VXGE_HW_PHASE_CFG_UMQM_WR_PHASE_EN	vxge_mBIT(15)
+#define	VXGE_HW_PHASE_CFG_UMQM_RD_PHASE_EN	vxge_mBIT(19)
+#define	VXGE_HW_PHASE_CFG_RCBM_WR_PHASE_EN	vxge_mBIT(23)
+#define	VXGE_HW_PHASE_CFG_RCBM_RD_PHASE_EN	vxge_mBIT(27)
+#define	VXGE_HW_PHASE_CFG_RXD_RC_WR_PHASE_EN	vxge_mBIT(31)
+#define	VXGE_HW_PHASE_CFG_RXD_RC_RD_PHASE_EN	vxge_mBIT(35)
+#define	VXGE_HW_PHASE_CFG_RXD_RHS_WR_PHASE_EN	vxge_mBIT(39)
+#define	VXGE_HW_PHASE_CFG_RXD_RHS_RD_PHASE_EN	vxge_mBIT(43)
+/*0x00d00*/	u64	rcq_bypq_cfg;
+#define VXGE_HW_RCQ_BYPQ_CFG_OVERFLOW_THRESHOLD(val) vxge_vBIT(val, 10, 22)
+#define VXGE_HW_RCQ_BYPQ_CFG_BYP_ON_THRESHOLD(val) vxge_vBIT(val, 39, 9)
+#define VXGE_HW_RCQ_BYPQ_CFG_BYP_OFF_THRESHOLD(val) vxge_vBIT(val, 55, 9)
+	u8	unused00e00[0x00e00-0x00d08];
+
+/*0x00e00*/	u64	doorbell_int_status;
+#define	VXGE_HW_DOORBELL_INT_STATUS_KDFC_ERR_REG_TXDMA_KDFC_INT	vxge_mBIT(7)
+#define	VXGE_HW_DOORBELL_INT_STATUS_USDC_ERR_REG_TXDMA_USDC_INT	vxge_mBIT(15)
+/*0x00e08*/	u64	doorbell_int_mask;
+/*0x00e10*/	u64	kdfc_err_reg;
+#define	VXGE_HW_KDFC_ERR_REG_KDFC_KDFC_ECC_SG_ERR	vxge_mBIT(7)
+#define	VXGE_HW_KDFC_ERR_REG_KDFC_KDFC_ECC_DB_ERR	vxge_mBIT(15)
+#define	VXGE_HW_KDFC_ERR_REG_KDFC_KDFC_SM_ERR_ALARM	vxge_mBIT(23)
+#define	VXGE_HW_KDFC_ERR_REG_KDFC_KDFC_MISC_ERR_1	vxge_mBIT(32)
+#define	VXGE_HW_KDFC_ERR_REG_KDFC_KDFC_PCIX_ERR	vxge_mBIT(39)
+/*0x00e18*/	u64	kdfc_err_mask;
+/*0x00e20*/	u64	kdfc_err_reg_alarm;
+#define	VXGE_HW_KDFC_ERR_REG_ALARM_KDFC_KDFC_ECC_SG_ERR	vxge_mBIT(7)
+#define	VXGE_HW_KDFC_ERR_REG_ALARM_KDFC_KDFC_ECC_DB_ERR	vxge_mBIT(15)
+#define	VXGE_HW_KDFC_ERR_REG_ALARM_KDFC_KDFC_SM_ERR_ALARM	vxge_mBIT(23)
+#define	VXGE_HW_KDFC_ERR_REG_ALARM_KDFC_KDFC_MISC_ERR_1	vxge_mBIT(32)
+#define	VXGE_HW_KDFC_ERR_REG_ALARM_KDFC_KDFC_PCIX_ERR	vxge_mBIT(39)
+	u8	unused00e40[0x00e40-0x00e28];
+/*0x00e40*/	u64	kdfc_vp_partition_0;
+#define	VXGE_HW_KDFC_VP_PARTITION_0_ENABLE	vxge_mBIT(0)
+#define VXGE_HW_KDFC_VP_PARTITION_0_NUMBER_0(val) vxge_vBIT(val, 5, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_0_LENGTH_0(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_0_NUMBER_1(val) vxge_vBIT(val, 37, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_0_LENGTH_1(val) vxge_vBIT(val, 49, 15)
+/*0x00e48*/	u64	kdfc_vp_partition_1;
+#define VXGE_HW_KDFC_VP_PARTITION_1_NUMBER_2(val) vxge_vBIT(val, 5, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_1_LENGTH_2(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_1_NUMBER_3(val) vxge_vBIT(val, 37, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_1_LENGTH_3(val) vxge_vBIT(val, 49, 15)
+/*0x00e50*/	u64	kdfc_vp_partition_2;
+#define VXGE_HW_KDFC_VP_PARTITION_2_NUMBER_4(val) vxge_vBIT(val, 5, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_2_LENGTH_4(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_2_NUMBER_5(val) vxge_vBIT(val, 37, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_2_LENGTH_5(val) vxge_vBIT(val, 49, 15)
+/*0x00e58*/	u64	kdfc_vp_partition_3;
+#define VXGE_HW_KDFC_VP_PARTITION_3_NUMBER_6(val) vxge_vBIT(val, 5, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_3_LENGTH_6(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_3_NUMBER_7(val) vxge_vBIT(val, 37, 3)
+#define VXGE_HW_KDFC_VP_PARTITION_3_LENGTH_7(val) vxge_vBIT(val, 49, 15)
+/*0x00e60*/	u64	kdfc_vp_partition_4;
+#define VXGE_HW_KDFC_VP_PARTITION_4_LENGTH_8(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_4_LENGTH_9(val) vxge_vBIT(val, 49, 15)
+/*0x00e68*/	u64	kdfc_vp_partition_5;
+#define VXGE_HW_KDFC_VP_PARTITION_5_LENGTH_10(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_5_LENGTH_11(val) vxge_vBIT(val, 49, 15)
+/*0x00e70*/	u64	kdfc_vp_partition_6;
+#define VXGE_HW_KDFC_VP_PARTITION_6_LENGTH_12(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_6_LENGTH_13(val) vxge_vBIT(val, 49, 15)
+/*0x00e78*/	u64	kdfc_vp_partition_7;
+#define VXGE_HW_KDFC_VP_PARTITION_7_LENGTH_14(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_VP_PARTITION_7_LENGTH_15(val) vxge_vBIT(val, 49, 15)
+/*0x00e80*/	u64	kdfc_vp_partition_8;
+#define VXGE_HW_KDFC_VP_PARTITION_8_LENGTH_16(val) vxge_vBIT(val, 17, 15)
+/*0x00e88*/	u64	kdfc_w_round_robin_0;
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_0(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_1(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_2(val) vxge_vBIT(val, 19, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_3(val) vxge_vBIT(val, 27, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_4(val) vxge_vBIT(val, 35, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_5(val) vxge_vBIT(val, 43, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_6(val) vxge_vBIT(val, 51, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_0_NUMBER_7(val) vxge_vBIT(val, 59, 5)
+
+	u8	unused0f28[0x0f28-0x0e90];
+
+/*0x00f28*/	u64	kdfc_w_round_robin_20;
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_0(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_1(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_2(val) vxge_vBIT(val, 19, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_3(val) vxge_vBIT(val, 27, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_4(val) vxge_vBIT(val, 35, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_5(val) vxge_vBIT(val, 43, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_6(val) vxge_vBIT(val, 51, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_20_NUMBER_7(val) vxge_vBIT(val, 59, 5)
+
+#define VXGE_HW_WRR_FIFO_COUNT				20
+
+	u8	unused0fc8[0x0fc8-0x0f30];
+
+/*0x00fc8*/	u64	kdfc_w_round_robin_40;
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_0(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_1(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_2(val) vxge_vBIT(val, 19, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_3(val) vxge_vBIT(val, 27, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_4(val) vxge_vBIT(val, 35, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_5(val) vxge_vBIT(val, 43, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_6(val) vxge_vBIT(val, 51, 5)
+#define VXGE_HW_KDFC_W_ROUND_ROBIN_40_NUMBER_7(val) vxge_vBIT(val, 59, 5)
+
+	u8	unused1068[0x01068-0x0fd0];
+
+/*0x01068*/	u64	kdfc_entry_type_sel_0;
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_0(val) vxge_vBIT(val, 6, 2)
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_1(val) vxge_vBIT(val, 14, 2)
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_2(val) vxge_vBIT(val, 22, 2)
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_3(val) vxge_vBIT(val, 30, 2)
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_4(val) vxge_vBIT(val, 38, 2)
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_5(val) vxge_vBIT(val, 46, 2)
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_6(val) vxge_vBIT(val, 54, 2)
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_0_NUMBER_7(val) vxge_vBIT(val, 62, 2)
+/*0x01070*/	u64	kdfc_entry_type_sel_1;
+#define VXGE_HW_KDFC_ENTRY_TYPE_SEL_1_NUMBER_8(val) vxge_vBIT(val, 6, 2)
+/*0x01078*/	u64	kdfc_fifo_0_ctrl;
+#define VXGE_HW_KDFC_FIFO_0_CTRL_WRR_NUMBER(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_WEIGHTED_RR_SERVICE_STATES		176
+#define VXGE_HW_WRR_FIFO_SERVICE_STATES			153
+
+	u8	unused1100[0x01100-0x1080];
+
+/*0x01100*/	u64	kdfc_fifo_17_ctrl;
+#define VXGE_HW_KDFC_FIFO_17_CTRL_WRR_NUMBER(val) vxge_vBIT(val, 3, 5)
+
+	u8	unused1600[0x01600-0x1108];
+
+/*0x01600*/	u64	rxmac_int_status;
+#define	VXGE_HW_RXMAC_INT_STATUS_RXMAC_GEN_ERR_RXMAC_GEN_INT	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_INT_STATUS_RXMAC_ECC_ERR_RXMAC_ECC_INT	vxge_mBIT(7)
+#define	VXGE_HW_RXMAC_INT_STATUS_RXMAC_VARIOUS_ERR_RXMAC_VARIOUS_INT \
+								vxge_mBIT(11)
+/*0x01608*/	u64	rxmac_int_mask;
+	u8	unused01618[0x01618-0x01610];
+
+/*0x01618*/	u64	rxmac_gen_err_reg;
+/*0x01620*/	u64	rxmac_gen_err_mask;
+/*0x01628*/	u64	rxmac_gen_err_alarm;
+/*0x01630*/	u64	rxmac_ecc_err_reg;
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RMAC_PORT0_RMAC_RTS_PART_SG_ERR(val) \
+							vxge_vBIT(val, 0, 4)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RMAC_PORT0_RMAC_RTS_PART_DB_ERR(val) \
+							vxge_vBIT(val, 4, 4)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RMAC_PORT1_RMAC_RTS_PART_SG_ERR(val) \
+							vxge_vBIT(val, 8, 4)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RMAC_PORT1_RMAC_RTS_PART_DB_ERR(val) \
+							vxge_vBIT(val, 12, 4)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RMAC_PORT2_RMAC_RTS_PART_SG_ERR(val) \
+							vxge_vBIT(val, 16, 4)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RMAC_PORT2_RMAC_RTS_PART_DB_ERR(val) \
+							vxge_vBIT(val, 20, 4)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_DA_LKP_PRT0_SG_ERR(val) \
+							vxge_vBIT(val, 24, 2)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_DA_LKP_PRT0_DB_ERR(val) \
+							vxge_vBIT(val, 26, 2)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_DA_LKP_PRT1_SG_ERR(val) \
+							vxge_vBIT(val, 28, 2)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_DA_LKP_PRT1_DB_ERR(val) \
+							vxge_vBIT(val, 30, 2)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_VID_LKP_SG_ERR	vxge_mBIT(32)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_VID_LKP_DB_ERR	vxge_mBIT(33)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_PN_LKP_PRT0_SG_ERR	vxge_mBIT(34)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_PN_LKP_PRT0_DB_ERR	vxge_mBIT(35)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_PN_LKP_PRT1_SG_ERR	vxge_mBIT(36)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_PN_LKP_PRT1_DB_ERR	vxge_mBIT(37)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_PN_LKP_PRT2_SG_ERR	vxge_mBIT(38)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_PN_LKP_PRT2_DB_ERR	vxge_mBIT(39)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_RTH_MASK_SG_ERR(val) \
+							vxge_vBIT(val, 40, 7)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_RTH_MASK_DB_ERR(val) \
+							vxge_vBIT(val, 47, 7)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_RTH_LKP_SG_ERR(val) \
+							vxge_vBIT(val, 54, 3)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_RTH_LKP_DB_ERR(val) \
+							vxge_vBIT(val, 57, 3)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_DS_LKP_SG_ERR \
+							vxge_mBIT(60)
+#define	VXGE_HW_RXMAC_ECC_ERR_REG_RTSJ_RMAC_DS_LKP_DB_ERR \
+							vxge_mBIT(61)
+/*0x01638*/	u64	rxmac_ecc_err_mask;
+/*0x01640*/	u64	rxmac_ecc_err_alarm;
+/*0x01648*/	u64	rxmac_various_err_reg;
+#define	VXGE_HW_RXMAC_VARIOUS_ERR_REG_RMAC_RMAC_PORT0_FSM_ERR	vxge_mBIT(0)
+#define	VXGE_HW_RXMAC_VARIOUS_ERR_REG_RMAC_RMAC_PORT1_FSM_ERR	vxge_mBIT(1)
+#define	VXGE_HW_RXMAC_VARIOUS_ERR_REG_RMAC_RMAC_PORT2_FSM_ERR	vxge_mBIT(2)
+#define	VXGE_HW_RXMAC_VARIOUS_ERR_REG_RMACJ_RMACJ_FSM_ERR	vxge_mBIT(3)
+/*0x01650*/	u64	rxmac_various_err_mask;
+/*0x01658*/	u64	rxmac_various_err_alarm;
+/*0x01660*/	u64	rxmac_gen_cfg;
+#define	VXGE_HW_RXMAC_GEN_CFG_SCALE_RMAC_UTIL	vxge_mBIT(11)
+/*0x01668*/	u64	rxmac_authorize_all_addr;
+#define VXGE_HW_RXMAC_AUTHORIZE_ALL_ADDR_VP(n)	vxge_mBIT(n)
+/*0x01670*/	u64	rxmac_authorize_all_vid;
+#define VXGE_HW_RXMAC_AUTHORIZE_ALL_VID_VP(n)	vxge_mBIT(n)
+	u8	unused016c0[0x016c0-0x01678];
+
+/*0x016c0*/	u64	rxmac_red_rate_repl_queue;
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_CRATE_THR0(val) vxge_vBIT(val, 0, 4)
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_CRATE_THR1(val) vxge_vBIT(val, 4, 4)
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_CRATE_THR2(val) vxge_vBIT(val, 8, 4)
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_CRATE_THR3(val) vxge_vBIT(val, 12, 4)
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_FRATE_THR0(val) vxge_vBIT(val, 16, 4)
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_FRATE_THR1(val) vxge_vBIT(val, 20, 4)
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_FRATE_THR2(val) vxge_vBIT(val, 24, 4)
+#define VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_FRATE_THR3(val) vxge_vBIT(val, 28, 4)
+#define	VXGE_HW_RXMAC_RED_RATE_REPL_QUEUE_TRICKLE_EN	vxge_mBIT(35)
+	u8	unused016e0[0x016e0-0x016c8];
+
+/*0x016e0*/	u64	rxmac_cfg0_port[3];
+#define	VXGE_HW_RXMAC_CFG0_PORT_RMAC_EN	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_CFG0_PORT_STRIP_FCS	vxge_mBIT(7)
+#define	VXGE_HW_RXMAC_CFG0_PORT_DISCARD_PFRM	vxge_mBIT(11)
+#define	VXGE_HW_RXMAC_CFG0_PORT_IGNORE_FCS_ERR	vxge_mBIT(15)
+#define	VXGE_HW_RXMAC_CFG0_PORT_IGNORE_LONG_ERR	vxge_mBIT(19)
+#define	VXGE_HW_RXMAC_CFG0_PORT_IGNORE_USIZED_ERR	vxge_mBIT(23)
+#define	VXGE_HW_RXMAC_CFG0_PORT_IGNORE_LEN_MISMATCH	vxge_mBIT(27)
+#define VXGE_HW_RXMAC_CFG0_PORT_MAX_PYLD_LEN(val) vxge_vBIT(val, 50, 14)
+	u8	unused01710[0x01710-0x016f8];
+
+/*0x01710*/	u64	rxmac_cfg2_port[3];
+#define	VXGE_HW_RXMAC_CFG2_PORT_PROM_EN	vxge_mBIT(3)
+/*0x01728*/	u64	rxmac_pause_cfg_port[3];
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_GEN_EN	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_RCV_EN	vxge_mBIT(7)
+#define VXGE_HW_RXMAC_PAUSE_CFG_PORT_ACCEL_SEND(val) vxge_vBIT(val, 9, 3)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_DUAL_THR	vxge_mBIT(15)
+#define VXGE_HW_RXMAC_PAUSE_CFG_PORT_HIGH_PTIME(val) vxge_vBIT(val, 20, 16)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_IGNORE_PF_FCS_ERR	vxge_mBIT(39)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_IGNORE_PF_LEN_ERR	vxge_mBIT(43)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_LIMITER_EN	vxge_mBIT(47)
+#define VXGE_HW_RXMAC_PAUSE_CFG_PORT_MAX_LIMIT(val) vxge_vBIT(val, 48, 8)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_PERMIT_RATEMGMT_CTRL	vxge_mBIT(59)
+	u8	unused01758[0x01758-0x01740];
+
+/*0x01758*/	u64	rxmac_red_cfg0_port[3];
+#define VXGE_HW_RXMAC_RED_CFG0_PORT_RED_EN_VP(n)	vxge_mBIT(n)
+/*0x01770*/	u64	rxmac_red_cfg1_port[3];
+#define	VXGE_HW_RXMAC_RED_CFG1_PORT_FINE_EN	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_RED_CFG1_PORT_RED_EN_REPL_QUEUE	vxge_mBIT(11)
+/*0x01788*/	u64	rxmac_red_cfg2_port[3];
+#define VXGE_HW_RXMAC_RED_CFG2_PORT_TRICKLE_EN_VP(n)	vxge_mBIT(n)
+/*0x017a0*/	u64	rxmac_link_util_port[3];
+#define	VXGE_HW_RXMAC_LINK_UTIL_PORT_RMAC_RMAC_UTILIZATION(val) \
+							vxge_vBIT(val, 1, 7)
+#define VXGE_HW_RXMAC_LINK_UTIL_PORT_RMAC_UTIL_CFG(val) vxge_vBIT(val, 8, 4)
+#define VXGE_HW_RXMAC_LINK_UTIL_PORT_RMAC_RMAC_FRAC_UTIL(val) \
+							vxge_vBIT(val, 12, 4)
+#define VXGE_HW_RXMAC_LINK_UTIL_PORT_RMAC_PKT_WEIGHT(val) vxge_vBIT(val, 16, 4)
+#define	VXGE_HW_RXMAC_LINK_UTIL_PORT_RMAC_RMAC_SCALE_FACTOR	vxge_mBIT(23)
+	u8	unused017d0[0x017d0-0x017b8];
+
+/*0x017d0*/	u64	rxmac_status_port[3];
+#define	VXGE_HW_RXMAC_STATUS_PORT_RMAC_RX_FRM_RCVD	vxge_mBIT(3)
+	u8	unused01800[0x01800-0x017e8];
+
+/*0x01800*/	u64	rxmac_rx_pa_cfg0;
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_IGNORE_FRAME_ERR	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_SUPPORT_SNAP_AB_N	vxge_mBIT(7)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_SEARCH_FOR_HAO	vxge_mBIT(18)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_SUPPORT_MOBILE_IPV6_HDRS	vxge_mBIT(19)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_IPV6_STOP_SEARCHING	vxge_mBIT(23)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_NO_PS_IF_UNKNOWN	vxge_mBIT(27)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_SEARCH_FOR_ETYPE	vxge_mBIT(35)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_TOSS_ANY_FRM_IF_L3_CSUM_ERR	vxge_mBIT(39)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_TOSS_OFFLD_FRM_IF_L3_CSUM_ERR	vxge_mBIT(43)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_TOSS_ANY_FRM_IF_L4_CSUM_ERR	vxge_mBIT(47)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_TOSS_OFFLD_FRM_IF_L4_CSUM_ERR	vxge_mBIT(51)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_TOSS_ANY_FRM_IF_RPA_ERR	vxge_mBIT(55)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_TOSS_OFFLD_FRM_IF_RPA_ERR	vxge_mBIT(59)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_JUMBO_SNAP_EN	vxge_mBIT(63)
+/*0x01808*/	u64	rxmac_rx_pa_cfg1;
+#define	VXGE_HW_RXMAC_RX_PA_CFG1_REPL_IPV4_TCP_INCL_PH	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_RX_PA_CFG1_REPL_IPV6_TCP_INCL_PH	vxge_mBIT(7)
+#define	VXGE_HW_RXMAC_RX_PA_CFG1_REPL_IPV4_UDP_INCL_PH	vxge_mBIT(11)
+#define	VXGE_HW_RXMAC_RX_PA_CFG1_REPL_IPV6_UDP_INCL_PH	vxge_mBIT(15)
+#define	VXGE_HW_RXMAC_RX_PA_CFG1_REPL_L4_INCL_CF	vxge_mBIT(19)
+#define	VXGE_HW_RXMAC_RX_PA_CFG1_REPL_STRIP_VLAN_TAG	vxge_mBIT(23)
+	u8	unused01828[0x01828-0x01810];
+
+/*0x01828*/	u64	rts_mgr_cfg0;
+#define	VXGE_HW_RTS_MGR_CFG0_RTS_DP_SP_PRIORITY	vxge_mBIT(3)
+#define VXGE_HW_RTS_MGR_CFG0_FLEX_L4PRTCL_VALUE(val) vxge_vBIT(val, 24, 8)
+#define	VXGE_HW_RTS_MGR_CFG0_ICMP_TRASH	vxge_mBIT(35)
+#define	VXGE_HW_RTS_MGR_CFG0_TCPSYN_TRASH	vxge_mBIT(39)
+#define	VXGE_HW_RTS_MGR_CFG0_ZL4PYLD_TRASH	vxge_mBIT(43)
+#define	VXGE_HW_RTS_MGR_CFG0_L4PRTCL_TCP_TRASH	vxge_mBIT(47)
+#define	VXGE_HW_RTS_MGR_CFG0_L4PRTCL_UDP_TRASH	vxge_mBIT(51)
+#define	VXGE_HW_RTS_MGR_CFG0_L4PRTCL_FLEX_TRASH	vxge_mBIT(55)
+#define	VXGE_HW_RTS_MGR_CFG0_IPFRAG_TRASH	vxge_mBIT(59)
+/*0x01830*/	u64	rts_mgr_cfg1;
+#define	VXGE_HW_RTS_MGR_CFG1_DA_ACTIVE_TABLE	vxge_mBIT(3)
+#define	VXGE_HW_RTS_MGR_CFG1_PN_ACTIVE_TABLE	vxge_mBIT(7)
+/*0x01838*/	u64	rts_mgr_criteria_priority;
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_ETYPE(val) vxge_vBIT(val, 5, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_ICMP_TCPSYN(val) vxge_vBIT(val, 9, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_L4PN(val) vxge_vBIT(val, 13, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_RANGE_L4PN(val) vxge_vBIT(val, 17, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_RTH_IT(val) vxge_vBIT(val, 21, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_DS(val) vxge_vBIT(val, 25, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_QOS(val) vxge_vBIT(val, 29, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_ZL4PYLD(val) vxge_vBIT(val, 33, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_L4PRTCL(val) vxge_vBIT(val, 37, 3)
+/*0x01840*/	u64	rts_mgr_da_pause_cfg;
+#define VXGE_HW_RTS_MGR_DA_PAUSE_CFG_VPATH_VECTOR(val) vxge_vBIT(val, 0, 17)
+/*0x01848*/	u64	rts_mgr_da_slow_proto_cfg;
+#define VXGE_HW_RTS_MGR_DA_SLOW_PROTO_CFG_VPATH_VECTOR(val) \
+							vxge_vBIT(val, 0, 17)
+	u8	unused01890[0x01890-0x01850];
+/*0x01890*/     u64     rts_mgr_cbasin_cfg;
+	u8	unused01968[0x01968-0x01898];
+
+/*0x01968*/	u64	dbg_stat_rx_any_frms;
+#define VXGE_HW_DBG_STAT_RX_ANY_FRMS_PORT0_RX_ANY_FRMS(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_DBG_STAT_RX_ANY_FRMS_PORT1_RX_ANY_FRMS(val) vxge_vBIT(val, 8, 8)
+#define VXGE_HW_DBG_STAT_RX_ANY_FRMS_PORT2_RX_ANY_FRMS(val) \
+							vxge_vBIT(val, 16, 8)
+	u8	unused01a00[0x01a00-0x01970];
+
+/*0x01a00*/	u64	rxmac_red_rate_vp[17];
+#define VXGE_HW_RXMAC_RED_RATE_VP_CRATE_THR0(val) vxge_vBIT(val, 0, 4)
+#define VXGE_HW_RXMAC_RED_RATE_VP_CRATE_THR1(val) vxge_vBIT(val, 4, 4)
+#define VXGE_HW_RXMAC_RED_RATE_VP_CRATE_THR2(val) vxge_vBIT(val, 8, 4)
+#define VXGE_HW_RXMAC_RED_RATE_VP_CRATE_THR3(val) vxge_vBIT(val, 12, 4)
+#define VXGE_HW_RXMAC_RED_RATE_VP_FRATE_THR0(val) vxge_vBIT(val, 16, 4)
+#define VXGE_HW_RXMAC_RED_RATE_VP_FRATE_THR1(val) vxge_vBIT(val, 20, 4)
+#define VXGE_HW_RXMAC_RED_RATE_VP_FRATE_THR2(val) vxge_vBIT(val, 24, 4)
+#define VXGE_HW_RXMAC_RED_RATE_VP_FRATE_THR3(val) vxge_vBIT(val, 28, 4)
+	u8	unused01e00[0x01e00-0x01a88];
+
+/*0x01e00*/	u64	xgmac_int_status;
+#define	VXGE_HW_XGMAC_INT_STATUS_XMAC_GEN_ERR_XMAC_GEN_INT	vxge_mBIT(3)
+#define	VXGE_HW_XGMAC_INT_STATUS_XMAC_LINK_ERR_PORT0_XMAC_LINK_INT_PORT0 \
+								vxge_mBIT(7)
+#define	VXGE_HW_XGMAC_INT_STATUS_XMAC_LINK_ERR_PORT1_XMAC_LINK_INT_PORT1 \
+								vxge_mBIT(11)
+#define	VXGE_HW_XGMAC_INT_STATUS_XGXS_GEN_ERR_XGXS_GEN_INT	vxge_mBIT(15)
+#define	VXGE_HW_XGMAC_INT_STATUS_ASIC_NTWK_ERR_ASIC_NTWK_INT	vxge_mBIT(19)
+#define	VXGE_HW_XGMAC_INT_STATUS_ASIC_GPIO_ERR_ASIC_GPIO_INT	vxge_mBIT(23)
+/*0x01e08*/	u64	xgmac_int_mask;
+/*0x01e10*/	u64	xmac_gen_err_reg;
+#define	VXGE_HW_XMAC_GEN_ERR_REG_LAGC_LAG_PORT0_ACTOR_CHURN_DETECTED \
+								vxge_mBIT(7)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_LAGC_LAG_PORT0_PARTNER_CHURN_DETECTED \
+								vxge_mBIT(11)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_LAGC_LAG_PORT0_RECEIVED_LACPDU	vxge_mBIT(15)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_LAGC_LAG_PORT1_ACTOR_CHURN_DETECTED \
+								vxge_mBIT(19)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_LAGC_LAG_PORT1_PARTNER_CHURN_DETECTED \
+								vxge_mBIT(23)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_LAGC_LAG_PORT1_RECEIVED_LACPDU	vxge_mBIT(27)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XLCM_LAG_FAILOVER_DETECTED	vxge_mBIT(31)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE0_SG_ERR(val) \
+							vxge_vBIT(val, 40, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE0_DB_ERR(val) \
+							vxge_vBIT(val, 42, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE1_SG_ERR(val) \
+							vxge_vBIT(val, 44, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE1_DB_ERR(val) \
+							vxge_vBIT(val, 46, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE2_SG_ERR(val) \
+							vxge_vBIT(val, 48, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE2_DB_ERR(val) \
+							vxge_vBIT(val, 50, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE3_SG_ERR(val) \
+							vxge_vBIT(val, 52, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE3_DB_ERR(val) \
+							vxge_vBIT(val, 54, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE4_SG_ERR(val) \
+							vxge_vBIT(val, 56, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XSTATS_RMAC_STATS_TILE4_DB_ERR(val) \
+							vxge_vBIT(val, 58, 2)
+#define	VXGE_HW_XMAC_GEN_ERR_REG_XMACJ_XMAC_FSM_ERR	vxge_mBIT(63)
+/*0x01e18*/	u64	xmac_gen_err_mask;
+/*0x01e20*/	u64	xmac_gen_err_alarm;
+/*0x01e28*/	u64	xmac_link_err_port_reg[2];
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_PORT_DOWN	vxge_mBIT(3)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_PORT_UP	vxge_mBIT(7)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_PORT_WENT_DOWN	vxge_mBIT(11)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_PORT_WENT_UP	vxge_mBIT(15)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_PORT_REAFFIRMED_FAULT \
+								vxge_mBIT(19)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_PORT_REAFFIRMED_OK	vxge_mBIT(23)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_LINK_DOWN	vxge_mBIT(27)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMACJ_LINK_UP	vxge_mBIT(31)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_RATEMGMT_RATE_CHANGE	vxge_mBIT(35)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_RATEMGMT_LASI_INV	vxge_mBIT(39)
+#define	VXGE_HW_XMAC_LINK_ERR_PORT_REG_XMDIO_MDIO_MGR_ACCESS_COMPLETE \
+								vxge_mBIT(47)
+/*0x01e30*/	u64	xmac_link_err_port_mask[2];
+/*0x01e38*/	u64	xmac_link_err_port_alarm[2];
+/*0x01e58*/	u64	xgxs_gen_err_reg;
+#define	VXGE_HW_XGXS_GEN_ERR_REG_XGXS_XGXS_FSM_ERR	vxge_mBIT(63)
+/*0x01e60*/	u64	xgxs_gen_err_mask;
+/*0x01e68*/	u64	xgxs_gen_err_alarm;
+/*0x01e70*/	u64	asic_ntwk_err_reg;
+#define	VXGE_HW_ASIC_NTWK_ERR_REG_XMACJ_NTWK_DOWN	vxge_mBIT(3)
+#define	VXGE_HW_ASIC_NTWK_ERR_REG_XMACJ_NTWK_UP	vxge_mBIT(7)
+#define	VXGE_HW_ASIC_NTWK_ERR_REG_XMACJ_NTWK_WENT_DOWN	vxge_mBIT(11)
+#define	VXGE_HW_ASIC_NTWK_ERR_REG_XMACJ_NTWK_WENT_UP	vxge_mBIT(15)
+#define	VXGE_HW_ASIC_NTWK_ERR_REG_XMACJ_NTWK_REAFFIRMED_FAULT	vxge_mBIT(19)
+#define	VXGE_HW_ASIC_NTWK_ERR_REG_XMACJ_NTWK_REAFFIRMED_OK	vxge_mBIT(23)
+/*0x01e78*/	u64	asic_ntwk_err_mask;
+/*0x01e80*/	u64	asic_ntwk_err_alarm;
+/*0x01e88*/	u64	asic_gpio_err_reg;
+#define VXGE_HW_ASIC_GPIO_ERR_REG_XMACJ_GPIO_INT(n)	vxge_mBIT(n)
+/*0x01e90*/	u64	asic_gpio_err_mask;
+/*0x01e98*/	u64	asic_gpio_err_alarm;
+/*0x01ea0*/	u64	xgmac_gen_status;
+#define	VXGE_HW_XGMAC_GEN_STATUS_XMACJ_NTWK_OK	vxge_mBIT(3)
+#define	VXGE_HW_XGMAC_GEN_STATUS_XMACJ_NTWK_DATA_RATE	vxge_mBIT(11)
+/*0x01ea8*/	u64	xgmac_gen_fw_memo_status;
+#define	VXGE_HW_XGMAC_GEN_FW_MEMO_STATUS_XMACJ_EVENTS_PENDING(val) \
+							vxge_vBIT(val, 0, 17)
+/*0x01eb0*/	u64	xgmac_gen_fw_memo_mask;
+#define VXGE_HW_XGMAC_GEN_FW_MEMO_MASK_MASK(val) vxge_vBIT(val, 0, 64)
+/*0x01eb8*/	u64	xgmac_gen_fw_vpath_to_vsport_status;
+#define	VXGE_HW_XGMAC_GEN_FW_VPATH_TO_VSPORT_STATUS_XMACJ_EVENTS_PENDING(val) \
+						vxge_vBIT(val, 0, 17)
+/*0x01ec0*/	u64	xgmac_main_cfg_port[2];
+#define	VXGE_HW_XGMAC_MAIN_CFG_PORT_PORT_EN	vxge_mBIT(3)
+	u8	unused01f40[0x01f40-0x01ed0];
+
+/*0x01f40*/	u64	xmac_gen_cfg;
+#define VXGE_HW_XMAC_GEN_CFG_RATEMGMT_MAC_RATE_SEL(val) vxge_vBIT(val, 2, 2)
+#define	VXGE_HW_XMAC_GEN_CFG_TX_HEAD_DROP_WHEN_FAULT	vxge_mBIT(7)
+#define	VXGE_HW_XMAC_GEN_CFG_FAULT_BEHAVIOUR	vxge_mBIT(27)
+#define VXGE_HW_XMAC_GEN_CFG_PERIOD_NTWK_UP(val) vxge_vBIT(val, 28, 4)
+#define VXGE_HW_XMAC_GEN_CFG_PERIOD_NTWK_DOWN(val) vxge_vBIT(val, 32, 4)
+/*0x01f48*/	u64	xmac_timestamp;
+#define	VXGE_HW_XMAC_TIMESTAMP_EN	vxge_mBIT(3)
+#define VXGE_HW_XMAC_TIMESTAMP_USE_LINK_ID(val) vxge_vBIT(val, 6, 2)
+#define VXGE_HW_XMAC_TIMESTAMP_INTERVAL(val) vxge_vBIT(val, 12, 4)
+#define	VXGE_HW_XMAC_TIMESTAMP_TIMER_RESTART	vxge_mBIT(19)
+#define VXGE_HW_XMAC_TIMESTAMP_XMACJ_ROLLOVER_CNT(val) vxge_vBIT(val, 32, 16)
+/*0x01f50*/	u64	xmac_stats_gen_cfg;
+#define VXGE_HW_XMAC_STATS_GEN_CFG_PRTAGGR_CUM_TIMER(val) vxge_vBIT(val, 4, 4)
+#define VXGE_HW_XMAC_STATS_GEN_CFG_VPATH_CUM_TIMER(val) vxge_vBIT(val, 8, 4)
+#define	VXGE_HW_XMAC_STATS_GEN_CFG_VLAN_HANDLING	vxge_mBIT(15)
+/*0x01f58*/	u64	xmac_stats_sys_cmd;
+#define VXGE_HW_XMAC_STATS_SYS_CMD_OP(val) vxge_vBIT(val, 5, 3)
+#define	VXGE_HW_XMAC_STATS_SYS_CMD_STROBE	vxge_mBIT(15)
+#define VXGE_HW_XMAC_STATS_SYS_CMD_LOC_SEL(val) vxge_vBIT(val, 27, 5)
+#define VXGE_HW_XMAC_STATS_SYS_CMD_OFFSET_SEL(val) vxge_vBIT(val, 32, 8)
+/*0x01f60*/	u64	xmac_stats_sys_data;
+#define VXGE_HW_XMAC_STATS_SYS_DATA_XSMGR_DATA(val) vxge_vBIT(val, 0, 64)
+	u8	unused01f80[0x01f80-0x01f68];
+
+/*0x01f80*/	u64	asic_ntwk_ctrl;
+#define	VXGE_HW_ASIC_NTWK_CTRL_REQ_TEST_NTWK	vxge_mBIT(3)
+#define	VXGE_HW_ASIC_NTWK_CTRL_PORT0_REQ_TEST_PORT	vxge_mBIT(11)
+#define	VXGE_HW_ASIC_NTWK_CTRL_PORT1_REQ_TEST_PORT	vxge_mBIT(15)
+/*0x01f88*/	u64	asic_ntwk_cfg_show_port_info;
+#define VXGE_HW_ASIC_NTWK_CFG_SHOW_PORT_INFO_VP(n)	vxge_mBIT(n)
+/*0x01f90*/	u64	asic_ntwk_cfg_port_num;
+#define VXGE_HW_ASIC_NTWK_CFG_PORT_NUM_VP(n)	vxge_mBIT(n)
+/*0x01f98*/	u64	xmac_cfg_port[3];
+#define	VXGE_HW_XMAC_CFG_PORT_XGMII_LOOPBACK	vxge_mBIT(3)
+#define	VXGE_HW_XMAC_CFG_PORT_XGMII_REVERSE_LOOPBACK	vxge_mBIT(7)
+#define	VXGE_HW_XMAC_CFG_PORT_XGMII_TX_BEHAV	vxge_mBIT(11)
+#define	VXGE_HW_XMAC_CFG_PORT_XGMII_RX_BEHAV	vxge_mBIT(15)
+/*0x01fb0*/	u64	xmac_station_addr_port[2];
+#define VXGE_HW_XMAC_STATION_ADDR_PORT_MAC_ADDR(val) vxge_vBIT(val, 0, 48)
+	u8	unused02020[0x02020-0x01fc0];
+
+/*0x02020*/	u64	lag_cfg;
+#define	VXGE_HW_LAG_CFG_EN	vxge_mBIT(3)
+#define VXGE_HW_LAG_CFG_MODE(val) vxge_vBIT(val, 6, 2)
+#define	VXGE_HW_LAG_CFG_TX_DISCARD_BEHAV	vxge_mBIT(11)
+#define	VXGE_HW_LAG_CFG_RX_DISCARD_BEHAV	vxge_mBIT(15)
+#define	VXGE_HW_LAG_CFG_PREF_INDIV_PORT_NUM	vxge_mBIT(19)
+/*0x02028*/	u64	lag_status;
+#define	VXGE_HW_LAG_STATUS_XLCM_WAITING_TO_FAILBACK	vxge_mBIT(3)
+#define VXGE_HW_LAG_STATUS_XLCM_TIMER_VAL_COLD_FAILOVER(val) \
+							vxge_vBIT(val, 8, 8)
+/*0x02030*/	u64	lag_active_passive_cfg;
+#define	VXGE_HW_LAG_ACTIVE_PASSIVE_CFG_HOT_STANDBY	vxge_mBIT(3)
+#define	VXGE_HW_LAG_ACTIVE_PASSIVE_CFG_LACP_DECIDES	vxge_mBIT(7)
+#define	VXGE_HW_LAG_ACTIVE_PASSIVE_CFG_PREF_ACTIVE_PORT_NUM	vxge_mBIT(11)
+#define	VXGE_HW_LAG_ACTIVE_PASSIVE_CFG_AUTO_FAILBACK	vxge_mBIT(15)
+#define	VXGE_HW_LAG_ACTIVE_PASSIVE_CFG_FAILBACK_EN	vxge_mBIT(19)
+#define	VXGE_HW_LAG_ACTIVE_PASSIVE_CFG_COLD_FAILOVER_TIMEOUT(val) \
+							vxge_vBIT(val, 32, 16)
+	u8	unused02040[0x02040-0x02038];
+
+/*0x02040*/	u64	lag_lacp_cfg;
+#define	VXGE_HW_LAG_LACP_CFG_EN	vxge_mBIT(3)
+#define	VXGE_HW_LAG_LACP_CFG_LACP_BEGIN	vxge_mBIT(7)
+#define	VXGE_HW_LAG_LACP_CFG_DISCARD_LACP	vxge_mBIT(11)
+#define	VXGE_HW_LAG_LACP_CFG_LIBERAL_LEN_CHK	vxge_mBIT(15)
+/*0x02048*/	u64	lag_timer_cfg_1;
+#define VXGE_HW_LAG_TIMER_CFG_1_FAST_PER(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_LAG_TIMER_CFG_1_SLOW_PER(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_LAG_TIMER_CFG_1_SHORT_TIMEOUT(val) vxge_vBIT(val, 32, 16)
+#define VXGE_HW_LAG_TIMER_CFG_1_LONG_TIMEOUT(val) vxge_vBIT(val, 48, 16)
+/*0x02050*/	u64	lag_timer_cfg_2;
+#define VXGE_HW_LAG_TIMER_CFG_2_CHURN_DET(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_LAG_TIMER_CFG_2_AGGR_WAIT(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_LAG_TIMER_CFG_2_SHORT_TIMER_SCALE(val) vxge_vBIT(val, 32, 16)
+#define VXGE_HW_LAG_TIMER_CFG_2_LONG_TIMER_SCALE(val)  vxge_vBIT(val, 48, 16)
+/*0x02058*/	u64	lag_sys_id;
+#define VXGE_HW_LAG_SYS_ID_ADDR(val) vxge_vBIT(val, 0, 48)
+#define	VXGE_HW_LAG_SYS_ID_USE_PORT_ADDR	vxge_mBIT(51)
+#define	VXGE_HW_LAG_SYS_ID_ADDR_SEL	vxge_mBIT(55)
+/*0x02060*/	u64	lag_sys_cfg;
+#define VXGE_HW_LAG_SYS_CFG_SYS_PRI(val) vxge_vBIT(val, 0, 16)
+	u8	unused02070[0x02070-0x02068];
+
+/*0x02070*/	u64	lag_aggr_addr_cfg[2];
+#define VXGE_HW_LAG_AGGR_ADDR_CFG_ADDR(val) vxge_vBIT(val, 0, 48)
+#define	VXGE_HW_LAG_AGGR_ADDR_CFG_USE_PORT_ADDR	vxge_mBIT(51)
+#define	VXGE_HW_LAG_AGGR_ADDR_CFG_ADDR_SEL	vxge_mBIT(55)
+/*0x02080*/	u64	lag_aggr_id_cfg[2];
+#define VXGE_HW_LAG_AGGR_ID_CFG_ID(val) vxge_vBIT(val, 0, 16)
+/*0x02090*/	u64	lag_aggr_admin_key[2];
+#define VXGE_HW_LAG_AGGR_ADMIN_KEY_KEY(val) vxge_vBIT(val, 0, 16)
+/*0x020a0*/	u64	lag_aggr_alt_admin_key;
+#define VXGE_HW_LAG_AGGR_ALT_ADMIN_KEY_KEY(val) vxge_vBIT(val, 0, 16)
+#define	VXGE_HW_LAG_AGGR_ALT_ADMIN_KEY_ALT_AGGR	vxge_mBIT(19)
+/*0x020a8*/	u64	lag_aggr_oper_key[2];
+#define VXGE_HW_LAG_AGGR_OPER_KEY_LAGC_KEY(val) vxge_vBIT(val, 0, 16)
+/*0x020b8*/	u64	lag_aggr_partner_sys_id[2];
+#define VXGE_HW_LAG_AGGR_PARTNER_SYS_ID_LAGC_ADDR(val) vxge_vBIT(val, 0, 48)
+/*0x020c8*/	u64	lag_aggr_partner_info[2];
+#define VXGE_HW_LAG_AGGR_PARTNER_INFO_LAGC_SYS_PRI(val) vxge_vBIT(val, 0, 16)
+#define	VXGE_HW_LAG_AGGR_PARTNER_INFO_LAGC_OPER_KEY(val) \
+						vxge_vBIT(val, 16, 16)
+/*0x020d8*/	u64	lag_aggr_state[2];
+#define	VXGE_HW_LAG_AGGR_STATE_LAGC_TX	vxge_mBIT(3)
+#define	VXGE_HW_LAG_AGGR_STATE_LAGC_RX	vxge_mBIT(7)
+#define	VXGE_HW_LAG_AGGR_STATE_LAGC_READY	vxge_mBIT(11)
+#define	VXGE_HW_LAG_AGGR_STATE_LAGC_INDIVIDUAL	vxge_mBIT(15)
+	u8	unused020f0[0x020f0-0x020e8];
+
+/*0x020f0*/	u64	lag_port_cfg[2];
+#define	VXGE_HW_LAG_PORT_CFG_EN	vxge_mBIT(3)
+#define	VXGE_HW_LAG_PORT_CFG_DISCARD_SLOW_PROTO	vxge_mBIT(7)
+#define	VXGE_HW_LAG_PORT_CFG_HOST_CHOSEN_AGGR	vxge_mBIT(11)
+#define	VXGE_HW_LAG_PORT_CFG_DISCARD_UNKNOWN_SLOW_PROTO	vxge_mBIT(15)
+/*0x02100*/	u64	lag_port_actor_admin_cfg[2];
+#define VXGE_HW_LAG_PORT_ACTOR_ADMIN_CFG_PORT_NUM(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_LAG_PORT_ACTOR_ADMIN_CFG_PORT_PRI(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_LAG_PORT_ACTOR_ADMIN_CFG_KEY_10G(val) vxge_vBIT(val, 32, 16)
+#define VXGE_HW_LAG_PORT_ACTOR_ADMIN_CFG_KEY_1G(val) vxge_vBIT(val, 48, 16)
+/*0x02110*/	u64	lag_port_actor_admin_state[2];
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_LACP_ACTIVITY	vxge_mBIT(3)
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_LACP_TIMEOUT	vxge_mBIT(7)
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_AGGREGATION	vxge_mBIT(11)
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_SYNCHRONIZATION	vxge_mBIT(15)
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_COLLECTING	vxge_mBIT(19)
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_DISTRIBUTING	vxge_mBIT(23)
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_DEFAULTED	vxge_mBIT(27)
+#define	VXGE_HW_LAG_PORT_ACTOR_ADMIN_STATE_EXPIRED	vxge_mBIT(31)
+/*0x02120*/	u64	lag_port_partner_admin_sys_id[2];
+#define VXGE_HW_LAG_PORT_PARTNER_ADMIN_SYS_ID_ADDR(val) vxge_vBIT(val, 0, 48)
+/*0x02130*/	u64	lag_port_partner_admin_cfg[2];
+#define VXGE_HW_LAG_PORT_PARTNER_ADMIN_CFG_SYS_PRI(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_LAG_PORT_PARTNER_ADMIN_CFG_KEY(val) vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_CFG_PORT_NUM(val) \
+							vxge_vBIT(val, 32, 16)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_CFG_PORT_PRI(val) \
+							vxge_vBIT(val, 48, 16)
+/*0x02140*/	u64	lag_port_partner_admin_state[2];
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_LACP_ACTIVITY	vxge_mBIT(3)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_LACP_TIMEOUT	vxge_mBIT(7)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_AGGREGATION	vxge_mBIT(11)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_SYNCHRONIZATION	vxge_mBIT(15)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_COLLECTING	vxge_mBIT(19)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_DISTRIBUTING	vxge_mBIT(23)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_DEFAULTED	vxge_mBIT(27)
+#define	VXGE_HW_LAG_PORT_PARTNER_ADMIN_STATE_EXPIRED	vxge_mBIT(31)
+/*0x02150*/	u64	lag_port_to_aggr[2];
+#define VXGE_HW_LAG_PORT_TO_AGGR_LAGC_AGGR_ID(val) vxge_vBIT(val, 0, 16)
+#define	VXGE_HW_LAG_PORT_TO_AGGR_LAGC_AGGR_VLD_ID	vxge_mBIT(19)
+/*0x02160*/	u64	lag_port_actor_oper_key[2];
+#define VXGE_HW_LAG_PORT_ACTOR_OPER_KEY_LAGC_KEY(val) vxge_vBIT(val, 0, 16)
+/*0x02170*/	u64	lag_port_actor_oper_state[2];
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_LACP_ACTIVITY	vxge_mBIT(3)
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_LACP_TIMEOUT	vxge_mBIT(7)
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_AGGREGATION	vxge_mBIT(11)
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_SYNCHRONIZATION	vxge_mBIT(15)
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_COLLECTING	vxge_mBIT(19)
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_DISTRIBUTING	vxge_mBIT(23)
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_DEFAULTED	vxge_mBIT(27)
+#define	VXGE_HW_LAG_PORT_ACTOR_OPER_STATE_LAGC_EXPIRED	vxge_mBIT(31)
+/*0x02180*/	u64	lag_port_partner_oper_sys_id[2];
+#define VXGE_HW_LAG_PORT_PARTNER_OPER_SYS_ID_LAGC_ADDR(val) \
+						vxge_vBIT(val, 0, 48)
+/*0x02190*/	u64	lag_port_partner_oper_info[2];
+#define VXGE_HW_LAG_PORT_PARTNER_OPER_INFO_LAGC_SYS_PRI(val) \
+						vxge_vBIT(val, 0, 16)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_INFO_LAGC_KEY(val) \
+						vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_INFO_LAGC_PORT_NUM(val) \
+						vxge_vBIT(val, 32, 16)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_INFO_LAGC_PORT_PRI(val) \
+						vxge_vBIT(val, 48, 16)
+/*0x021a0*/	u64	lag_port_partner_oper_state[2];
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_LACP_ACTIVITY	vxge_mBIT(3)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_LACP_TIMEOUT	vxge_mBIT(7)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_AGGREGATION	vxge_mBIT(11)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_SYNCHRONIZATION \
+								vxge_mBIT(15)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_COLLECTING	vxge_mBIT(19)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_DISTRIBUTING	vxge_mBIT(23)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_DEFAULTED	vxge_mBIT(27)
+#define	VXGE_HW_LAG_PORT_PARTNER_OPER_STATE_LAGC_EXPIRED	vxge_mBIT(31)
+/*0x021b0*/	u64	lag_port_state_vars[2];
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_READY	vxge_mBIT(3)
+#define VXGE_HW_LAG_PORT_STATE_VARS_LAGC_SELECTED(val) vxge_vBIT(val, 6, 2)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_AGGR_NUM	vxge_mBIT(11)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_PORT_MOVED	vxge_mBIT(15)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_PORT_ENABLED	vxge_mBIT(18)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_PORT_DISABLED	vxge_mBIT(19)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_NTT	vxge_mBIT(23)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_ACTOR_CHURN	vxge_mBIT(27)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_PARTNER_CHURN	vxge_mBIT(31)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_ACTOR_INFO_LEN_MISMATCH \
+								vxge_mBIT(32)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_PARTNER_INFO_LEN_MISMATCH \
+								vxge_mBIT(33)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_COLL_INFO_LEN_MISMATCH	vxge_mBIT(34)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_TERM_INFO_LEN_MISMATCH	vxge_mBIT(35)
+#define VXGE_HW_LAG_PORT_STATE_VARS_LAGC_RX_FSM_STATE(val) vxge_vBIT(val, 37, 3)
+#define VXGE_HW_LAG_PORT_STATE_VARS_LAGC_MUX_FSM_STATE(val) \
+							vxge_vBIT(val, 41, 3)
+#define VXGE_HW_LAG_PORT_STATE_VARS_LAGC_MUX_REASON(val) vxge_vBIT(val, 44, 4)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_ACTOR_CHURN_STATE	vxge_mBIT(54)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_PARTNER_CHURN_STATE	vxge_mBIT(55)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_ACTOR_CHURN_COUNT(val) \
+							vxge_vBIT(val, 56, 4)
+#define	VXGE_HW_LAG_PORT_STATE_VARS_LAGC_PARTNER_CHURN_COUNT(val) \
+							vxge_vBIT(val, 60, 4)
+/*0x021c0*/	u64	lag_port_timer_cntr[2];
+#define VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_CURRENT_WHILE(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_PERIODIC_WHILE(val) \
+							vxge_vBIT(val, 8, 8)
+#define VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_WAIT_WHILE(val) vxge_vBIT(val, 16, 8)
+#define VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_TX_LACP(val) vxge_vBIT(val, 24, 8)
+#define	VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_ACTOR_SYNC_TRANSITION_COUNT(val) \
+							vxge_vBIT(val, 32, 8)
+#define	VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_PARTNER_SYNC_TRANSITION_COUNT(val) \
+							vxge_vBIT(val, 40, 8)
+#define	VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_ACTOR_CHANGE_COUNT(val) \
+							vxge_vBIT(val, 48, 8)
+#define	VXGE_HW_LAG_PORT_TIMER_CNTR_LAGC_PARTNER_CHANGE_COUNT(val) \
+							vxge_vBIT(val, 56, 8)
+	u8	unused02208[0x02700-0x021d0];
+
+/*0x02700*/	u64	rtdma_int_status;
+#define	VXGE_HW_RTDMA_INT_STATUS_PDA_ALARM_PDA_INT	vxge_mBIT(1)
+#define	VXGE_HW_RTDMA_INT_STATUS_PCC_ERROR_PCC_INT	vxge_mBIT(2)
+#define	VXGE_HW_RTDMA_INT_STATUS_LSO_ERROR_LSO_INT	vxge_mBIT(4)
+#define	VXGE_HW_RTDMA_INT_STATUS_SM_ERROR_SM_INT	vxge_mBIT(5)
+/*0x02708*/	u64	rtdma_int_mask;
+/*0x02710*/	u64	pda_alarm_reg;
+#define	VXGE_HW_PDA_ALARM_REG_PDA_HSC_FIFO_ERR	vxge_mBIT(0)
+#define	VXGE_HW_PDA_ALARM_REG_PDA_SM_ERR	vxge_mBIT(1)
+/*0x02718*/	u64	pda_alarm_mask;
+/*0x02720*/	u64	pda_alarm_alarm;
+/*0x02728*/	u64	pcc_error_reg;
+#define VXGE_HW_PCC_ERROR_REG_PCC_PCC_FRM_BUF_SBE(n)	vxge_mBIT(n)
+#define VXGE_HW_PCC_ERROR_REG_PCC_PCC_TXDO_SBE(n)	vxge_mBIT(n)
+#define VXGE_HW_PCC_ERROR_REG_PCC_PCC_FRM_BUF_DBE(n)	vxge_mBIT(n)
+#define VXGE_HW_PCC_ERROR_REG_PCC_PCC_TXDO_DBE(n)	vxge_mBIT(n)
+#define VXGE_HW_PCC_ERROR_REG_PCC_PCC_FSM_ERR_ALARM(n)	vxge_mBIT(n)
+#define VXGE_HW_PCC_ERROR_REG_PCC_PCC_SERR(n)	vxge_mBIT(n)
+/*0x02730*/	u64	pcc_error_mask;
+/*0x02738*/	u64	pcc_error_alarm;
+/*0x02740*/	u64	lso_error_reg;
+#define VXGE_HW_LSO_ERROR_REG_PCC_LSO_ABORT(n)	vxge_mBIT(n)
+#define VXGE_HW_LSO_ERROR_REG_PCC_LSO_FSM_ERR_ALARM(n)	vxge_mBIT(n)
+/*0x02748*/	u64	lso_error_mask;
+/*0x02750*/	u64	lso_error_alarm;
+/*0x02758*/	u64	sm_error_reg;
+#define	VXGE_HW_SM_ERROR_REG_SM_FSM_ERR_ALARM	vxge_mBIT(15)
+/*0x02760*/	u64	sm_error_mask;
+/*0x02768*/	u64	sm_error_alarm;
+
+	u8	unused027a8[0x027a8-0x02770];
+
+/*0x027a8*/	u64	txd_ownership_ctrl;
+#define	VXGE_HW_TXD_OWNERSHIP_CTRL_KEEP_OWNERSHIP	vxge_mBIT(7)
+/*0x027b0*/	u64	pcc_cfg;
+#define VXGE_HW_PCC_CFG_PCC_ENABLE(n)	vxge_mBIT(n)
+#define VXGE_HW_PCC_CFG_PCC_ECC_ENABLE_N(n)	vxge_mBIT(n)
+/*0x027b8*/	u64	pcc_control;
+#define VXGE_HW_PCC_CONTROL_FE_ENABLE(val) vxge_vBIT(val, 6, 2)
+#define	VXGE_HW_PCC_CONTROL_EARLY_ASSIGN_EN	vxge_mBIT(15)
+#define	VXGE_HW_PCC_CONTROL_UNBLOCK_DB_ERR	vxge_mBIT(31)
+/*0x027c0*/	u64	pda_status1;
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_0_CTR(val) vxge_vBIT(val, 4, 4)
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_1_CTR(val) vxge_vBIT(val, 12, 4)
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_2_CTR(val) vxge_vBIT(val, 20, 4)
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_3_CTR(val) vxge_vBIT(val, 28, 4)
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_4_CTR(val) vxge_vBIT(val, 36, 4)
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_5_CTR(val) vxge_vBIT(val, 44, 4)
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_6_CTR(val) vxge_vBIT(val, 52, 4)
+#define VXGE_HW_PDA_STATUS1_PDA_WRAP_7_CTR(val) vxge_vBIT(val, 60, 4)
+/*0x027c8*/	u64	rtdma_bw_timer;
+#define VXGE_HW_RTDMA_BW_TIMER_TIMER_CTRL(val) vxge_vBIT(val, 12, 4)
+
+	u8	unused02900[0x02900-0x027d0];
+/*0x02900*/	u64	g3cmct_int_status;
+#define	VXGE_HW_G3CMCT_INT_STATUS_ERR_G3IF_INT	vxge_mBIT(0)
+/*0x02908*/	u64	g3cmct_int_mask;
+/*0x02910*/	u64	g3cmct_err_reg;
+#define	VXGE_HW_G3CMCT_ERR_REG_G3IF_SM_ERR	vxge_mBIT(4)
+#define	VXGE_HW_G3CMCT_ERR_REG_G3IF_GDDR3_DECC	vxge_mBIT(5)
+#define	VXGE_HW_G3CMCT_ERR_REG_G3IF_GDDR3_U_DECC	vxge_mBIT(6)
+#define	VXGE_HW_G3CMCT_ERR_REG_G3IF_CTRL_FIFO_DECC	vxge_mBIT(7)
+#define	VXGE_HW_G3CMCT_ERR_REG_G3IF_GDDR3_SECC	vxge_mBIT(29)
+#define	VXGE_HW_G3CMCT_ERR_REG_G3IF_GDDR3_U_SECC	vxge_mBIT(30)
+#define	VXGE_HW_G3CMCT_ERR_REG_G3IF_CTRL_FIFO_SECC	vxge_mBIT(31)
+/*0x02918*/	u64	g3cmct_err_mask;
+/*0x02920*/	u64	g3cmct_err_alarm;
+	u8	unused03000[0x03000-0x02928];
+
+/*0x03000*/	u64	mc_int_status;
+#define	VXGE_HW_MC_INT_STATUS_MC_ERR_MC_INT	vxge_mBIT(3)
+#define	VXGE_HW_MC_INT_STATUS_GROCRC_ALARM_ROCRC_INT	vxge_mBIT(7)
+#define	VXGE_HW_MC_INT_STATUS_FAU_GEN_ERR_FAU_GEN_INT	vxge_mBIT(11)
+#define	VXGE_HW_MC_INT_STATUS_FAU_ECC_ERR_FAU_ECC_INT	vxge_mBIT(15)
+/*0x03008*/	u64	mc_int_mask;
+/*0x03010*/	u64	mc_err_reg;
+#define	VXGE_HW_MC_ERR_REG_MC_XFMD_MEM_ECC_SG_ERR_A	vxge_mBIT(3)
+#define	VXGE_HW_MC_ERR_REG_MC_XFMD_MEM_ECC_SG_ERR_B	vxge_mBIT(4)
+#define	VXGE_HW_MC_ERR_REG_MC_G3IF_RD_FIFO_ECC_SG_ERR	vxge_mBIT(5)
+#define	VXGE_HW_MC_ERR_REG_MC_MIRI_ECC_SG_ERR_0	vxge_mBIT(6)
+#define	VXGE_HW_MC_ERR_REG_MC_MIRI_ECC_SG_ERR_1	vxge_mBIT(7)
+#define	VXGE_HW_MC_ERR_REG_MC_XFMD_MEM_ECC_DB_ERR_A	vxge_mBIT(10)
+#define	VXGE_HW_MC_ERR_REG_MC_XFMD_MEM_ECC_DB_ERR_B	vxge_mBIT(11)
+#define	VXGE_HW_MC_ERR_REG_MC_G3IF_RD_FIFO_ECC_DB_ERR	vxge_mBIT(12)
+#define	VXGE_HW_MC_ERR_REG_MC_MIRI_ECC_DB_ERR_0	vxge_mBIT(13)
+#define	VXGE_HW_MC_ERR_REG_MC_MIRI_ECC_DB_ERR_1	vxge_mBIT(14)
+#define	VXGE_HW_MC_ERR_REG_MC_SM_ERR	vxge_mBIT(15)
+/*0x03018*/	u64	mc_err_mask;
+/*0x03020*/	u64	mc_err_alarm;
+/*0x03028*/	u64	grocrc_alarm_reg;
+#define	VXGE_HW_GROCRC_ALARM_REG_XFMD_WR_FIFO_ERR	vxge_mBIT(3)
+#define	VXGE_HW_GROCRC_ALARM_REG_WDE2MSR_RD_FIFO_ERR	vxge_mBIT(7)
+/*0x03030*/	u64	grocrc_alarm_mask;
+/*0x03038*/	u64	grocrc_alarm_alarm;
+	u8	unused03100[0x03100-0x03040];
+
+/*0x03100*/	u64	rx_thresh_cfg_repl;
+#define VXGE_HW_RX_THRESH_CFG_REPL_PAUSE_LOW_THR(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_RX_THRESH_CFG_REPL_PAUSE_HIGH_THR(val) vxge_vBIT(val, 8, 8)
+#define VXGE_HW_RX_THRESH_CFG_REPL_RED_THR_0(val) vxge_vBIT(val, 16, 8)
+#define VXGE_HW_RX_THRESH_CFG_REPL_RED_THR_1(val) vxge_vBIT(val, 24, 8)
+#define VXGE_HW_RX_THRESH_CFG_REPL_RED_THR_2(val) vxge_vBIT(val, 32, 8)
+#define VXGE_HW_RX_THRESH_CFG_REPL_RED_THR_3(val) vxge_vBIT(val, 40, 8)
+#define	VXGE_HW_RX_THRESH_CFG_REPL_GLOBAL_WOL_EN	vxge_mBIT(62)
+#define	VXGE_HW_RX_THRESH_CFG_REPL_EXACT_VP_MATCH_REQ	vxge_mBIT(63)
+	u8	unused033b8[0x033b8-0x03108];
+
+/*0x033b8*/	u64	fbmc_ecc_cfg;
+#define VXGE_HW_FBMC_ECC_CFG_ENABLE(val) vxge_vBIT(val, 3, 5)
+	u8	unused03400[0x03400-0x033c0];
+
+/*0x03400*/	u64	pcipif_int_status;
+#define	VXGE_HW_PCIPIF_INT_STATUS_DBECC_ERR_DBECC_ERR_INT	vxge_mBIT(3)
+#define	VXGE_HW_PCIPIF_INT_STATUS_SBECC_ERR_SBECC_ERR_INT	vxge_mBIT(7)
+#define	VXGE_HW_PCIPIF_INT_STATUS_GENERAL_ERR_GENERAL_ERR_INT	vxge_mBIT(11)
+#define	VXGE_HW_PCIPIF_INT_STATUS_SRPCIM_MSG_SRPCIM_MSG_INT	vxge_mBIT(15)
+#define	VXGE_HW_PCIPIF_INT_STATUS_MRPCIM_SPARE_R1_MRPCIM_SPARE_R1_INT \
+								vxge_mBIT(19)
+/*0x03408*/	u64	pcipif_int_mask;
+/*0x03410*/	u64	dbecc_err_reg;
+#define	VXGE_HW_DBECC_ERR_REG_PCI_RETRY_BUF_DB_ERR	vxge_mBIT(3)
+#define	VXGE_HW_DBECC_ERR_REG_PCI_RETRY_SOT_DB_ERR	vxge_mBIT(7)
+#define	VXGE_HW_DBECC_ERR_REG_PCI_P_HDR_DB_ERR	vxge_mBIT(11)
+#define	VXGE_HW_DBECC_ERR_REG_PCI_P_DATA_DB_ERR	vxge_mBIT(15)
+#define	VXGE_HW_DBECC_ERR_REG_PCI_NP_HDR_DB_ERR	vxge_mBIT(19)
+#define	VXGE_HW_DBECC_ERR_REG_PCI_NP_DATA_DB_ERR	vxge_mBIT(23)
+/*0x03418*/	u64	dbecc_err_mask;
+/*0x03420*/	u64	dbecc_err_alarm;
+/*0x03428*/	u64	sbecc_err_reg;
+#define	VXGE_HW_SBECC_ERR_REG_PCI_RETRY_BUF_SG_ERR	vxge_mBIT(3)
+#define	VXGE_HW_SBECC_ERR_REG_PCI_RETRY_SOT_SG_ERR	vxge_mBIT(7)
+#define	VXGE_HW_SBECC_ERR_REG_PCI_P_HDR_SG_ERR	vxge_mBIT(11)
+#define	VXGE_HW_SBECC_ERR_REG_PCI_P_DATA_SG_ERR	vxge_mBIT(15)
+#define	VXGE_HW_SBECC_ERR_REG_PCI_NP_HDR_SG_ERR	vxge_mBIT(19)
+#define	VXGE_HW_SBECC_ERR_REG_PCI_NP_DATA_SG_ERR	vxge_mBIT(23)
+/*0x03430*/	u64	sbecc_err_mask;
+/*0x03438*/	u64	sbecc_err_alarm;
+/*0x03440*/	u64	general_err_reg;
+#define	VXGE_HW_GENERAL_ERR_REG_PCI_DROPPED_ILLEGAL_CFG	vxge_mBIT(3)
+#define	VXGE_HW_GENERAL_ERR_REG_PCI_ILLEGAL_MEM_MAP_PROG	vxge_mBIT(7)
+#define	VXGE_HW_GENERAL_ERR_REG_PCI_LINK_RST_FSM_ERR	vxge_mBIT(11)
+#define	VXGE_HW_GENERAL_ERR_REG_PCI_RX_ILLEGAL_TLP_VPLANE	vxge_mBIT(15)
+#define	VXGE_HW_GENERAL_ERR_REG_PCI_TRAINING_RESET_DET	vxge_mBIT(19)
+#define	VXGE_HW_GENERAL_ERR_REG_PCI_PCI_LINK_DOWN_DET	vxge_mBIT(23)
+#define	VXGE_HW_GENERAL_ERR_REG_PCI_RESET_ACK_DLLP	vxge_mBIT(27)
+/*0x03448*/	u64	general_err_mask;
+/*0x03450*/	u64	general_err_alarm;
+/*0x03458*/	u64	srpcim_msg_reg;
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE0_RMSG_INT \
+								vxge_mBIT(0)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE1_RMSG_INT \
+								vxge_mBIT(1)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE2_RMSG_INT \
+								vxge_mBIT(2)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE3_RMSG_INT \
+								vxge_mBIT(3)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE4_RMSG_INT \
+								vxge_mBIT(4)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE5_RMSG_INT \
+								vxge_mBIT(5)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE6_RMSG_INT \
+								vxge_mBIT(6)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE7_RMSG_INT \
+								vxge_mBIT(7)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE8_RMSG_INT \
+								vxge_mBIT(8)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE9_RMSG_INT \
+								vxge_mBIT(9)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE10_RMSG_INT \
+								vxge_mBIT(10)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE11_RMSG_INT \
+								vxge_mBIT(11)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE12_RMSG_INT \
+								vxge_mBIT(12)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE13_RMSG_INT \
+								vxge_mBIT(13)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE14_RMSG_INT \
+								vxge_mBIT(14)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE15_RMSG_INT \
+								vxge_mBIT(15)
+#define	VXGE_HW_SRPCIM_MSG_REG_SWIF_SRPCIM_TO_MRPCIM_VPLANE16_RMSG_INT \
+								vxge_mBIT(16)
+/*0x03460*/	u64	srpcim_msg_mask;
+/*0x03468*/	u64	srpcim_msg_alarm;
+	u8	unused03600[0x03600-0x03470];
+
+/*0x03600*/	u64	gcmg1_int_status;
+#define	VXGE_HW_GCMG1_INT_STATUS_GSSCC_ERR_GSSCC_INT	vxge_mBIT(0)
+#define	VXGE_HW_GCMG1_INT_STATUS_GSSC0_ERR0_GSSC0_0_INT	vxge_mBIT(1)
+#define	VXGE_HW_GCMG1_INT_STATUS_GSSC0_ERR1_GSSC0_1_INT	vxge_mBIT(2)
+#define	VXGE_HW_GCMG1_INT_STATUS_GSSC1_ERR0_GSSC1_0_INT	vxge_mBIT(3)
+#define	VXGE_HW_GCMG1_INT_STATUS_GSSC1_ERR1_GSSC1_1_INT	vxge_mBIT(4)
+#define	VXGE_HW_GCMG1_INT_STATUS_GSSC2_ERR0_GSSC2_0_INT	vxge_mBIT(5)
+#define	VXGE_HW_GCMG1_INT_STATUS_GSSC2_ERR1_GSSC2_1_INT	vxge_mBIT(6)
+#define	VXGE_HW_GCMG1_INT_STATUS_UQM_ERR_UQM_INT	vxge_mBIT(7)
+#define	VXGE_HW_GCMG1_INT_STATUS_GQCC_ERR_GQCC_INT	vxge_mBIT(8)
+/*0x03608*/	u64	gcmg1_int_mask;
+	u8	unused03a00[0x03a00-0x03610];
+
+/*0x03a00*/	u64	pcmg1_int_status;
+#define	VXGE_HW_PCMG1_INT_STATUS_PSSCC_ERR_PSSCC_INT	vxge_mBIT(0)
+#define	VXGE_HW_PCMG1_INT_STATUS_PQCC_ERR_PQCC_INT	vxge_mBIT(1)
+#define	VXGE_HW_PCMG1_INT_STATUS_PQCC_CQM_ERR_PQCC_CQM_INT	vxge_mBIT(2)
+#define	VXGE_HW_PCMG1_INT_STATUS_PQCC_SQM_ERR_PQCC_SQM_INT	vxge_mBIT(3)
+/*0x03a08*/	u64	pcmg1_int_mask;
+	u8	unused04000[0x04000-0x03a10];
+
+/*0x04000*/	u64	one_int_status;
+#define	VXGE_HW_ONE_INT_STATUS_RXPE_ERR_RXPE_INT	vxge_mBIT(7)
+#define	VXGE_HW_ONE_INT_STATUS_TXPE_BCC_MEM_SG_ECC_ERR_TXPE_BCC_MEM_SG_ECC_INT \
+							vxge_mBIT(13)
+#define	VXGE_HW_ONE_INT_STATUS_TXPE_BCC_MEM_DB_ECC_ERR_TXPE_BCC_MEM_DB_ECC_INT \
+							vxge_mBIT(14)
+#define	VXGE_HW_ONE_INT_STATUS_TXPE_ERR_TXPE_INT	vxge_mBIT(15)
+#define	VXGE_HW_ONE_INT_STATUS_DLM_ERR_DLM_INT	vxge_mBIT(23)
+#define	VXGE_HW_ONE_INT_STATUS_PE_ERR_PE_INT	vxge_mBIT(31)
+#define	VXGE_HW_ONE_INT_STATUS_RPE_ERR_RPE_INT	vxge_mBIT(39)
+#define	VXGE_HW_ONE_INT_STATUS_RPE_FSM_ERR_RPE_FSM_INT	vxge_mBIT(47)
+#define	VXGE_HW_ONE_INT_STATUS_OES_ERR_OES_INT	vxge_mBIT(55)
+/*0x04008*/	u64	one_int_mask;
+	u8	unused04818[0x04818-0x04010];
+
+/*0x04818*/	u64	noa_wct_ctrl;
+#define	VXGE_HW_NOA_WCT_CTRL_VP_INT_NUM	vxge_mBIT(0)
+/*0x04820*/	u64	rc_cfg2;
+#define VXGE_HW_RC_CFG2_BUFF1_SIZE(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_RC_CFG2_BUFF2_SIZE(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_RC_CFG2_BUFF3_SIZE(val) vxge_vBIT(val, 32, 16)
+#define VXGE_HW_RC_CFG2_BUFF4_SIZE(val) vxge_vBIT(val, 48, 16)
+/*0x04828*/	u64	rc_cfg3;
+#define VXGE_HW_RC_CFG3_BUFF5_SIZE(val) vxge_vBIT(val, 0, 16)
+/*0x04830*/	u64	rx_multi_cast_ctrl1;
+#define	VXGE_HW_RX_MULTI_CAST_CTRL1_ENABLE	vxge_mBIT(7)
+#define VXGE_HW_RX_MULTI_CAST_CTRL1_DELAY_COUNT(val) vxge_vBIT(val, 11, 5)
+/*0x04838*/	u64	rxdm_dbg_rd;
+#define VXGE_HW_RXDM_DBG_RD_ADDR(val) vxge_vBIT(val, 0, 12)
+#define	VXGE_HW_RXDM_DBG_RD_ENABLE	vxge_mBIT(31)
+/*0x04840*/	u64	rxdm_dbg_rd_data;
+#define VXGE_HW_RXDM_DBG_RD_DATA_RMC_RXDM_DBG_RD_DATA(val) vxge_vBIT(val, 0, 64)
+/*0x04848*/	u64	rqa_top_prty_for_vh[17];
+#define VXGE_HW_RQA_TOP_PRTY_FOR_VH_RQA_TOP_PRTY_FOR_VH(val) \
+							vxge_vBIT(val, 59, 5)
+	u8	unused04900[0x04900-0x048d0];
+
+/*0x04900*/	u64	tim_status;
+#define	VXGE_HW_TIM_STATUS_TIM_RESET_IN_PROGRESS	vxge_mBIT(0)
+/*0x04908*/	u64	tim_ecc_enable;
+#define	VXGE_HW_TIM_ECC_ENABLE_VBLS_N	vxge_mBIT(7)
+#define	VXGE_HW_TIM_ECC_ENABLE_BMAP_N	vxge_mBIT(15)
+#define	VXGE_HW_TIM_ECC_ENABLE_BMAP_MSG_N	vxge_mBIT(23)
+/*0x04910*/	u64	tim_bp_ctrl;
+#define	VXGE_HW_TIM_BP_CTRL_RD_XON	vxge_mBIT(7)
+#define	VXGE_HW_TIM_BP_CTRL_WR_XON	vxge_mBIT(15)
+#define	VXGE_HW_TIM_BP_CTRL_ROCRC_BYP	vxge_mBIT(23)
+/*0x04918*/	u64	tim_resource_assignment_vh[17];
+#define VXGE_HW_TIM_RESOURCE_ASSIGNMENT_VH_BMAP_ROOT(val) vxge_vBIT(val, 0, 32)
+/*0x049a0*/	u64	tim_bmap_mapping_vp_err[17];
+#define VXGE_HW_TIM_BMAP_MAPPING_VP_ERR_TIM_DEST_VPATH(val) vxge_vBIT(val, 3, 5)
+	u8	unused04b00[0x04b00-0x04a28];
+
+/*0x04b00*/	u64	gcmg2_int_status;
+#define	VXGE_HW_GCMG2_INT_STATUS_GXTMC_ERR_GXTMC_INT	vxge_mBIT(7)
+#define	VXGE_HW_GCMG2_INT_STATUS_GCP_ERR_GCP_INT	vxge_mBIT(15)
+#define	VXGE_HW_GCMG2_INT_STATUS_CMC_ERR_CMC_INT	vxge_mBIT(23)
+/*0x04b08*/	u64	gcmg2_int_mask;
+/*0x04b10*/	u64	gxtmc_err_reg;
+#define VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_MEM_DB_ERR(val) vxge_vBIT(val, 0, 4)
+#define VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_MEM_SG_ERR(val) vxge_vBIT(val, 4, 4)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMC_RD_DATA_DB_ERR	vxge_mBIT(8)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_REQ_FIFO_ERR	vxge_mBIT(9)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_REQ_DATA_FIFO_ERR	vxge_mBIT(10)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_WR_RSP_FIFO_ERR	vxge_mBIT(11)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_RD_RSP_FIFO_ERR	vxge_mBIT(12)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMI_WRP_FIFO_ERR	vxge_mBIT(13)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMI_WRP_ERR	vxge_mBIT(14)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMI_RRP_FIFO_ERR	vxge_mBIT(15)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMI_RRP_ERR	vxge_mBIT(16)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMI_DATA_SM_ERR	vxge_mBIT(17)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMI_CMC0_IF_ERR	vxge_mBIT(18)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_ARB_SM_ERR	vxge_mBIT(19)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_CFC_SM_ERR	vxge_mBIT(20)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_DFETCH_CREDIT_OVERFLOW \
+							vxge_mBIT(21)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_DFETCH_CREDIT_UNDERFLOW \
+							vxge_mBIT(22)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_DFETCH_SM_ERR	vxge_mBIT(23)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_RCTRL_CREDIT_OVERFLOW \
+							vxge_mBIT(24)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_RCTRL_CREDIT_UNDERFLOW \
+							vxge_mBIT(25)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_RCTRL_SM_ERR	vxge_mBIT(26)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_WCOMPL_SM_ERR	vxge_mBIT(27)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_WCOMPL_TAG_ERR	vxge_mBIT(28)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_WREQ_SM_ERR	vxge_mBIT(29)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_BDT_CMI_WREQ_FIFO_ERR	vxge_mBIT(30)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CP2BDT_RFIFO_POP_ERR	vxge_mBIT(31)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_XTMC_BDT_CMI_OP_ERR	vxge_mBIT(32)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_XTMC_BDT_DFETCH_OP_ERR	vxge_mBIT(33)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_XTMC_BDT_DFIFO_ERR	vxge_mBIT(34)
+#define	VXGE_HW_GXTMC_ERR_REG_XTMC_CMI_ARB_SM_ERR	vxge_mBIT(35)
+/*0x04b18*/	u64	gxtmc_err_mask;
+/*0x04b20*/	u64	gxtmc_err_alarm;
+/*0x04b28*/	u64	cmc_err_reg;
+#define	VXGE_HW_CMC_ERR_REG_CMC_CMC_SM_ERR	vxge_mBIT(0)
+/*0x04b30*/	u64	cmc_err_mask;
+/*0x04b38*/	u64	cmc_err_alarm;
+/*0x04b40*/	u64	gcp_err_reg;
+#define	VXGE_HW_GCP_ERR_REG_CP_H2L2CP_FIFO_ERR	vxge_mBIT(0)
+#define	VXGE_HW_GCP_ERR_REG_CP_STC2CP_FIFO_ERR	vxge_mBIT(1)
+#define	VXGE_HW_GCP_ERR_REG_CP_STE2CP_FIFO_ERR	vxge_mBIT(2)
+#define	VXGE_HW_GCP_ERR_REG_CP_TTE2CP_FIFO_ERR	vxge_mBIT(3)
+/*0x04b48*/	u64	gcp_err_mask;
+/*0x04b50*/	u64	gcp_err_alarm;
+	u8	unused04f00[0x04f00-0x04b58];
+
+/*0x04f00*/	u64	pcmg2_int_status;
+#define	VXGE_HW_PCMG2_INT_STATUS_PXTMC_ERR_PXTMC_INT	vxge_mBIT(7)
+#define	VXGE_HW_PCMG2_INT_STATUS_CP_EXC_CP_XT_EXC_INT	vxge_mBIT(15)
+#define	VXGE_HW_PCMG2_INT_STATUS_CP_ERR_CP_ERR_INT	vxge_mBIT(23)
+/*0x04f08*/	u64	pcmg2_int_mask;
+/*0x04f10*/	u64	pxtmc_err_reg;
+#define VXGE_HW_PXTMC_ERR_REG_XTMC_XT_PIF_SRAM_DB_ERR(val) vxge_vBIT(val, 0, 2)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MPT_REQ_FIFO_ERR	vxge_mBIT(2)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MPT_PRSP_FIFO_ERR	vxge_mBIT(3)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MPT_WRSP_FIFO_ERR	vxge_mBIT(4)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UPT_REQ_FIFO_ERR	vxge_mBIT(5)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UPT_PRSP_FIFO_ERR	vxge_mBIT(6)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UPT_WRSP_FIFO_ERR	vxge_mBIT(7)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CPT_REQ_FIFO_ERR	vxge_mBIT(8)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CPT_PRSP_FIFO_ERR	vxge_mBIT(9)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CPT_WRSP_FIFO_ERR	vxge_mBIT(10)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_REQ_FIFO_ERR	vxge_mBIT(11)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_REQ_DATA_FIFO_ERR	vxge_mBIT(12)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_WR_RSP_FIFO_ERR	vxge_mBIT(13)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_RD_RSP_FIFO_ERR	vxge_mBIT(14)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MPT_REQ_SHADOW_ERR	vxge_mBIT(15)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MPT_RSP_SHADOW_ERR	vxge_mBIT(16)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UPT_REQ_SHADOW_ERR	vxge_mBIT(17)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UPT_RSP_SHADOW_ERR	vxge_mBIT(18)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CPT_REQ_SHADOW_ERR	vxge_mBIT(19)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CPT_RSP_SHADOW_ERR	vxge_mBIT(20)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_XIL_SHADOW_ERR	vxge_mBIT(21)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_ARB_SHADOW_ERR	vxge_mBIT(22)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_RAM_SHADOW_ERR	vxge_mBIT(23)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CMW_SHADOW_ERR	vxge_mBIT(24)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CMR_SHADOW_ERR	vxge_mBIT(25)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MPT_REQ_FSM_ERR	vxge_mBIT(26)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MPT_RSP_FSM_ERR	vxge_mBIT(27)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UPT_REQ_FSM_ERR	vxge_mBIT(28)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UPT_RSP_FSM_ERR	vxge_mBIT(29)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CPT_REQ_FSM_ERR	vxge_mBIT(30)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CPT_RSP_FSM_ERR	vxge_mBIT(31)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_XIL_FSM_ERR	vxge_mBIT(32)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_ARB_FSM_ERR	vxge_mBIT(33)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CMW_FSM_ERR	vxge_mBIT(34)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CMR_FSM_ERR	vxge_mBIT(35)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MXP_RD_PROT_ERR	vxge_mBIT(36)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UXP_RD_PROT_ERR	vxge_mBIT(37)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CXP_RD_PROT_ERR	vxge_mBIT(38)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MXP_WR_PROT_ERR	vxge_mBIT(39)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UXP_WR_PROT_ERR	vxge_mBIT(40)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CXP_WR_PROT_ERR	vxge_mBIT(41)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MXP_INV_ADDR_ERR	vxge_mBIT(42)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UXP_INV_ADDR_ERR	vxge_mBIT(43)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CXP_INV_ADDR_ERR	vxge_mBIT(44)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MXP_RD_PROT_INFO_ERR	vxge_mBIT(45)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UXP_RD_PROT_INFO_ERR	vxge_mBIT(46)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CXP_RD_PROT_INFO_ERR	vxge_mBIT(47)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MXP_WR_PROT_INFO_ERR	vxge_mBIT(48)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UXP_WR_PROT_INFO_ERR	vxge_mBIT(49)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CXP_WR_PROT_INFO_ERR	vxge_mBIT(50)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_MXP_INV_ADDR_INFO_ERR	vxge_mBIT(51)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_UXP_INV_ADDR_INFO_ERR	vxge_mBIT(52)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CXP_INV_ADDR_INFO_ERR	vxge_mBIT(53)
+#define VXGE_HW_PXTMC_ERR_REG_XTMC_XT_PIF_SRAM_SG_ERR(val) vxge_vBIT(val, 54, 2)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CP2BDT_DFIFO_PUSH_ERR	vxge_mBIT(56)
+#define	VXGE_HW_PXTMC_ERR_REG_XTMC_CP2BDT_RFIFO_PUSH_ERR	vxge_mBIT(57)
+/*0x04f18*/	u64	pxtmc_err_mask;
+/*0x04f20*/	u64	pxtmc_err_alarm;
+/*0x04f28*/	u64	cp_err_reg;
+#define VXGE_HW_CP_ERR_REG_CP_CP_DCACHE_SG_ERR(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_CP_ERR_REG_CP_CP_ICACHE_SG_ERR(val) vxge_vBIT(val, 8, 2)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_DTAG_SG_ERR	vxge_mBIT(10)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_ITAG_SG_ERR	vxge_mBIT(11)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_TRACE_SG_ERR	vxge_mBIT(12)
+#define	VXGE_HW_CP_ERR_REG_CP_DMA2CP_SG_ERR	vxge_mBIT(13)
+#define	VXGE_HW_CP_ERR_REG_CP_MP2CP_SG_ERR	vxge_mBIT(14)
+#define	VXGE_HW_CP_ERR_REG_CP_QCC2CP_SG_ERR	vxge_mBIT(15)
+#define VXGE_HW_CP_ERR_REG_CP_STC2CP_SG_ERR(val) vxge_vBIT(val, 16, 2)
+#define VXGE_HW_CP_ERR_REG_CP_CP_DCACHE_DB_ERR(val) vxge_vBIT(val, 24, 8)
+#define VXGE_HW_CP_ERR_REG_CP_CP_ICACHE_DB_ERR(val) vxge_vBIT(val, 32, 2)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_DTAG_DB_ERR	vxge_mBIT(34)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_ITAG_DB_ERR	vxge_mBIT(35)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_TRACE_DB_ERR	vxge_mBIT(36)
+#define	VXGE_HW_CP_ERR_REG_CP_DMA2CP_DB_ERR	vxge_mBIT(37)
+#define	VXGE_HW_CP_ERR_REG_CP_MP2CP_DB_ERR	vxge_mBIT(38)
+#define	VXGE_HW_CP_ERR_REG_CP_QCC2CP_DB_ERR	vxge_mBIT(39)
+#define VXGE_HW_CP_ERR_REG_CP_STC2CP_DB_ERR(val) vxge_vBIT(val, 40, 2)
+#define	VXGE_HW_CP_ERR_REG_CP_H2L2CP_FIFO_ERR	vxge_mBIT(48)
+#define	VXGE_HW_CP_ERR_REG_CP_STC2CP_FIFO_ERR	vxge_mBIT(49)
+#define	VXGE_HW_CP_ERR_REG_CP_STE2CP_FIFO_ERR	vxge_mBIT(50)
+#define	VXGE_HW_CP_ERR_REG_CP_TTE2CP_FIFO_ERR	vxge_mBIT(51)
+#define	VXGE_HW_CP_ERR_REG_CP_SWIF2CP_FIFO_ERR	vxge_mBIT(52)
+#define	VXGE_HW_CP_ERR_REG_CP_CP2DMA_FIFO_ERR	vxge_mBIT(53)
+#define	VXGE_HW_CP_ERR_REG_CP_DAM2CP_FIFO_ERR	vxge_mBIT(54)
+#define	VXGE_HW_CP_ERR_REG_CP_MP2CP_FIFO_ERR	vxge_mBIT(55)
+#define	VXGE_HW_CP_ERR_REG_CP_QCC2CP_FIFO_ERR	vxge_mBIT(56)
+#define	VXGE_HW_CP_ERR_REG_CP_DMA2CP_FIFO_ERR	vxge_mBIT(57)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_WAKE_FSM_INTEGRITY_ERR	vxge_mBIT(60)
+#define	VXGE_HW_CP_ERR_REG_CP_CP_PMON_FSM_INTEGRITY_ERR	vxge_mBIT(61)
+#define	VXGE_HW_CP_ERR_REG_CP_DMA_RD_SHADOW_ERR	vxge_mBIT(62)
+#define	VXGE_HW_CP_ERR_REG_CP_PIFT_CREDIT_ERR	vxge_mBIT(63)
+/*0x04f30*/	u64	cp_err_mask;
+/*0x04f38*/	u64	cp_err_alarm;
+	u8	unused04fe8[0x04f50-0x04f40];
+
+/*0x04f50*/	u64	cp_exc_reg;
+#define	VXGE_HW_CP_EXC_REG_CP_CP_CAUSE_INFO_INT	vxge_mBIT(47)
+#define	VXGE_HW_CP_EXC_REG_CP_CP_CAUSE_CRIT_INT	vxge_mBIT(55)
+#define	VXGE_HW_CP_EXC_REG_CP_CP_SERR	vxge_mBIT(63)
+/*0x04f58*/	u64	cp_exc_mask;
+/*0x04f60*/	u64	cp_exc_alarm;
+/*0x04f68*/	u64	cp_exc_cause;
+#define VXGE_HW_CP_EXC_CAUSE_CP_CP_CAUSE(val) vxge_vBIT(val, 32, 32)
+	u8	unused05200[0x05200-0x04f70];
+
+/*0x05200*/	u64	msg_int_status;
+#define	VXGE_HW_MSG_INT_STATUS_TIM_ERR_TIM_INT	vxge_mBIT(7)
+#define	VXGE_HW_MSG_INT_STATUS_MSG_EXC_MSG_XT_EXC_INT	vxge_mBIT(60)
+#define	VXGE_HW_MSG_INT_STATUS_MSG_ERR3_MSG_ERR3_INT	vxge_mBIT(61)
+#define	VXGE_HW_MSG_INT_STATUS_MSG_ERR2_MSG_ERR2_INT	vxge_mBIT(62)
+#define	VXGE_HW_MSG_INT_STATUS_MSG_ERR_MSG_ERR_INT	vxge_mBIT(63)
+/*0x05208*/	u64	msg_int_mask;
+/*0x05210*/	u64	tim_err_reg;
+#define	VXGE_HW_TIM_ERR_REG_TIM_VBLS_SG_ERR	vxge_mBIT(4)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_PA_SG_ERR	vxge_mBIT(5)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_PB_SG_ERR	vxge_mBIT(6)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_MSG_SG_ERR	vxge_mBIT(7)
+#define	VXGE_HW_TIM_ERR_REG_TIM_VBLS_DB_ERR	vxge_mBIT(12)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_PA_DB_ERR	vxge_mBIT(13)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_PB_DB_ERR	vxge_mBIT(14)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_MSG_DB_ERR	vxge_mBIT(15)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_MEM_CNTRL_SM_ERR	vxge_mBIT(18)
+#define	VXGE_HW_TIM_ERR_REG_TIM_BMAP_MSG_MEM_CNTRL_SM_ERR	vxge_mBIT(19)
+#define	VXGE_HW_TIM_ERR_REG_TIM_MPIF_PCIWR_ERR	vxge_mBIT(20)
+#define	VXGE_HW_TIM_ERR_REG_TIM_ROCRC_BMAP_UPDT_FIFO_ERR	vxge_mBIT(22)
+#define	VXGE_HW_TIM_ERR_REG_TIM_CREATE_BMAPMSG_FIFO_ERR	vxge_mBIT(23)
+#define	VXGE_HW_TIM_ERR_REG_TIM_ROCRCIF_MISMATCH	vxge_mBIT(46)
+#define VXGE_HW_TIM_ERR_REG_TIM_BMAP_MAPPING_VP_ERR(n)	vxge_mBIT(n)
+/*0x05218*/	u64	tim_err_mask;
+/*0x05220*/	u64	tim_err_alarm;
+/*0x05228*/	u64	msg_err_reg;
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_WAKE_FSM_INTEGRITY_ERR	vxge_mBIT(0)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_WAKE_FSM_INTEGRITY_ERR	vxge_mBIT(1)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMQ_DMA_READ_CMD_FSM_INTEGRITY_ERR \
+								vxge_mBIT(2)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMQ_DMA_RESP_FSM_INTEGRITY_ERR \
+								vxge_mBIT(3)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMQ_OWN_FSM_INTEGRITY_ERR	vxge_mBIT(4)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_PDA_ACC_FSM_INTEGRITY_ERR	vxge_mBIT(5)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_PMON_FSM_INTEGRITY_ERR	vxge_mBIT(6)
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_PMON_FSM_INTEGRITY_ERR	vxge_mBIT(7)
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_DTAG_SG_ERR	vxge_mBIT(8)
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_ITAG_SG_ERR	vxge_mBIT(10)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_DTAG_SG_ERR	vxge_mBIT(12)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_ITAG_SG_ERR	vxge_mBIT(14)
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_TRACE_SG_ERR	vxge_mBIT(16)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_TRACE_SG_ERR	vxge_mBIT(17)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_CMG2MSG_SG_ERR	vxge_mBIT(18)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_TXPE2MSG_SG_ERR	vxge_mBIT(19)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_RXPE2MSG_SG_ERR	vxge_mBIT(20)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_RPE2MSG_SG_ERR	vxge_mBIT(21)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_UMQ_SG_ERR	vxge_mBIT(26)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_BWR_PF_SG_ERR	vxge_mBIT(27)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMQ_ECC_SG_ERR	vxge_mBIT(29)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMA_RESP_ECC_SG_ERR	vxge_mBIT(31)
+#define	VXGE_HW_MSG_ERR_REG_MSG_XFMDQRY_FSM_INTEGRITY_ERR	vxge_mBIT(33)
+#define	VXGE_HW_MSG_ERR_REG_MSG_FRMQRY_FSM_INTEGRITY_ERR	vxge_mBIT(34)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_UMQ_WRITE_FSM_INTEGRITY_ERR	vxge_mBIT(35)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_UMQ_BWR_PF_FSM_INTEGRITY_ERR \
+								vxge_mBIT(36)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_REG_RESP_FIFO_ERR	vxge_mBIT(38)
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_DTAG_DB_ERR	vxge_mBIT(39)
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_ITAG_DB_ERR	vxge_mBIT(41)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_DTAG_DB_ERR	vxge_mBIT(43)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_ITAG_DB_ERR	vxge_mBIT(45)
+#define	VXGE_HW_MSG_ERR_REG_UP_UXP_TRACE_DB_ERR	vxge_mBIT(47)
+#define	VXGE_HW_MSG_ERR_REG_MP_MXP_TRACE_DB_ERR	vxge_mBIT(48)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_CMG2MSG_DB_ERR	vxge_mBIT(49)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_TXPE2MSG_DB_ERR	vxge_mBIT(50)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_RXPE2MSG_DB_ERR	vxge_mBIT(51)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_RPE2MSG_DB_ERR	vxge_mBIT(52)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_REG_READ_FIFO_ERR	vxge_mBIT(53)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_MXP2UXP_FIFO_ERR	vxge_mBIT(54)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_KDFC_SIF_FIFO_ERR	vxge_mBIT(55)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_CXP2SWIF_FIFO_ERR	vxge_mBIT(56)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_UMQ_DB_ERR	vxge_mBIT(57)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_BWR_PF_DB_ERR	vxge_mBIT(58)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_BWR_SIF_FIFO_ERR	vxge_mBIT(59)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMQ_ECC_DB_ERR	vxge_mBIT(60)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMA_READ_FIFO_ERR	vxge_mBIT(61)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_DMA_RESP_ECC_DB_ERR	vxge_mBIT(62)
+#define	VXGE_HW_MSG_ERR_REG_MSG_QUE_UXP2MXP_FIFO_ERR	vxge_mBIT(63)
+/*0x05230*/	u64	msg_err_mask;
+/*0x05238*/	u64	msg_err_alarm;
+	u8	unused05340[0x05340-0x05240];
+
+/*0x05340*/	u64	msg_exc_reg;
+#define	VXGE_HW_MSG_EXC_REG_MP_MXP_CAUSE_INFO_INT	vxge_mBIT(50)
+#define	VXGE_HW_MSG_EXC_REG_MP_MXP_CAUSE_CRIT_INT	vxge_mBIT(51)
+#define	VXGE_HW_MSG_EXC_REG_UP_UXP_CAUSE_INFO_INT	vxge_mBIT(54)
+#define	VXGE_HW_MSG_EXC_REG_UP_UXP_CAUSE_CRIT_INT	vxge_mBIT(55)
+#define	VXGE_HW_MSG_EXC_REG_MP_MXP_SERR	vxge_mBIT(62)
+#define	VXGE_HW_MSG_EXC_REG_UP_UXP_SERR	vxge_mBIT(63)
+/*0x05348*/	u64	msg_exc_mask;
+/*0x05350*/	u64	msg_exc_alarm;
+/*0x05358*/	u64	msg_exc_cause;
+#define VXGE_HW_MSG_EXC_CAUSE_MP_MXP(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_MSG_EXC_CAUSE_UP_UXP(val) vxge_vBIT(val, 32, 32)
+	u8	unused05368[0x05380-0x05360];
+
+/*0x05380*/	u64	msg_err2_reg;
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_CMG2MSG_DISPATCH_FSM_INTEGRITY_ERR \
+							vxge_mBIT(0)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_DMQ_DISPATCH_FSM_INTEGRITY_ERR \
+								vxge_mBIT(1)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_SWIF_DISPATCH_FSM_INTEGRITY_ERR \
+								vxge_mBIT(2)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_PIC_WRITE_FSM_INTEGRITY_ERR \
+								vxge_mBIT(3)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_SWIFREG_FSM_INTEGRITY_ERR	vxge_mBIT(4)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_TIM_WRITE_FSM_INTEGRITY_ERR \
+								vxge_mBIT(5)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_UMQ_TA_FSM_INTEGRITY_ERR	vxge_mBIT(6)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_TXPE_TA_FSM_INTEGRITY_ERR	vxge_mBIT(7)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_RXPE_TA_FSM_INTEGRITY_ERR	vxge_mBIT(8)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_SWIF_TA_FSM_INTEGRITY_ERR	vxge_mBIT(9)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_DMA_TA_FSM_INTEGRITY_ERR	vxge_mBIT(10)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_CP_TA_FSM_INTEGRITY_ERR	vxge_mBIT(11)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA16_FSM_INTEGRITY_ERR \
+							vxge_mBIT(12)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA15_FSM_INTEGRITY_ERR \
+							vxge_mBIT(13)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA14_FSM_INTEGRITY_ERR \
+							vxge_mBIT(14)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA13_FSM_INTEGRITY_ERR \
+							vxge_mBIT(15)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA12_FSM_INTEGRITY_ERR \
+							vxge_mBIT(16)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA11_FSM_INTEGRITY_ERR \
+							vxge_mBIT(17)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA10_FSM_INTEGRITY_ERR \
+							vxge_mBIT(18)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA9_FSM_INTEGRITY_ERR \
+							vxge_mBIT(19)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA8_FSM_INTEGRITY_ERR \
+							vxge_mBIT(20)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA7_FSM_INTEGRITY_ERR \
+							vxge_mBIT(21)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA6_FSM_INTEGRITY_ERR \
+							vxge_mBIT(22)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA5_FSM_INTEGRITY_ERR \
+							vxge_mBIT(23)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA4_FSM_INTEGRITY_ERR \
+							vxge_mBIT(24)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA3_FSM_INTEGRITY_ERR \
+							vxge_mBIT(25)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA2_FSM_INTEGRITY_ERR \
+							vxge_mBIT(26)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA1_FSM_INTEGRITY_ERR \
+							vxge_mBIT(27)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_LONGTERMUMQ_TA0_FSM_INTEGRITY_ERR \
+							vxge_mBIT(28)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_FBMC_OWN_FSM_INTEGRITY_ERR	vxge_mBIT(29)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_TXPE2MSG_DISPATCH_FSM_INTEGRITY_ERR \
+							vxge_mBIT(30)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_RXPE2MSG_DISPATCH_FSM_INTEGRITY_ERR \
+							vxge_mBIT(31)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_RPE2MSG_DISPATCH_FSM_INTEGRITY_ERR \
+							vxge_mBIT(32)
+#define	VXGE_HW_MSG_ERR2_REG_MP_MP_PIFT_IF_CREDIT_CNT_ERR	vxge_mBIT(33)
+#define	VXGE_HW_MSG_ERR2_REG_UP_UP_PIFT_IF_CREDIT_CNT_ERR	vxge_mBIT(34)
+#define	VXGE_HW_MSG_ERR2_REG_MSG_QUE_UMQ2PIC_CMD_FIFO_ERR	vxge_mBIT(62)
+#define	VXGE_HW_MSG_ERR2_REG_TIM_TIM2MSG_CMD_FIFO_ERR	vxge_mBIT(63)
+/*0x05388*/	u64	msg_err2_mask;
+/*0x05390*/	u64	msg_err2_alarm;
+/*0x05398*/	u64	msg_err3_reg;
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR0	vxge_mBIT(0)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR1	vxge_mBIT(1)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR2	vxge_mBIT(2)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR3	vxge_mBIT(3)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR4	vxge_mBIT(4)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR5	vxge_mBIT(5)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR6	vxge_mBIT(6)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_SG_ERR7	vxge_mBIT(7)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_ICACHE_SG_ERR0	vxge_mBIT(8)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_ICACHE_SG_ERR1	vxge_mBIT(9)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR0	vxge_mBIT(16)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR1	vxge_mBIT(17)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR2	vxge_mBIT(18)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR3	vxge_mBIT(19)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR4	vxge_mBIT(20)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR5	vxge_mBIT(21)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR6	vxge_mBIT(22)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_SG_ERR7	vxge_mBIT(23)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_ICACHE_SG_ERR0	vxge_mBIT(24)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_ICACHE_SG_ERR1	vxge_mBIT(25)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR0	vxge_mBIT(32)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR1	vxge_mBIT(33)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR2	vxge_mBIT(34)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR3	vxge_mBIT(35)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR4	vxge_mBIT(36)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR5	vxge_mBIT(37)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR6	vxge_mBIT(38)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_DCACHE_DB_ERR7	vxge_mBIT(39)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_ICACHE_DB_ERR0	vxge_mBIT(40)
+#define	VXGE_HW_MSG_ERR3_REG_UP_UXP_ICACHE_DB_ERR1	vxge_mBIT(41)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR0	vxge_mBIT(48)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR1	vxge_mBIT(49)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR2	vxge_mBIT(50)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR3	vxge_mBIT(51)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR4	vxge_mBIT(52)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR5	vxge_mBIT(53)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR6	vxge_mBIT(54)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_DCACHE_DB_ERR7	vxge_mBIT(55)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_ICACHE_DB_ERR0	vxge_mBIT(56)
+#define	VXGE_HW_MSG_ERR3_REG_MP_MXP_ICACHE_DB_ERR1	vxge_mBIT(57)
+/*0x053a0*/	u64	msg_err3_mask;
+/*0x053a8*/	u64	msg_err3_alarm;
+	u8	unused05600[0x05600-0x053b0];
+
+/*0x05600*/	u64	fau_gen_err_reg;
+#define	VXGE_HW_FAU_GEN_ERR_REG_FMPF_PORT0_PERMANENT_STOP	vxge_mBIT(3)
+#define	VXGE_HW_FAU_GEN_ERR_REG_FMPF_PORT1_PERMANENT_STOP	vxge_mBIT(7)
+#define	VXGE_HW_FAU_GEN_ERR_REG_FMPF_PORT2_PERMANENT_STOP	vxge_mBIT(11)
+#define	VXGE_HW_FAU_GEN_ERR_REG_FALR_AUTO_LRO_NOTIFICATION	vxge_mBIT(15)
+/*0x05608*/	u64	fau_gen_err_mask;
+/*0x05610*/	u64	fau_gen_err_alarm;
+/*0x05618*/	u64	fau_ecc_err_reg;
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT0_FAU_MAC2F_N_SG_ERR	vxge_mBIT(0)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT0_FAU_MAC2F_N_DB_ERR	vxge_mBIT(1)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT0_FAU_MAC2F_W_SG_ERR(val) \
+							vxge_vBIT(val, 2, 2)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT0_FAU_MAC2F_W_DB_ERR(val) \
+							vxge_vBIT(val, 4, 2)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT1_FAU_MAC2F_N_SG_ERR	vxge_mBIT(6)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT1_FAU_MAC2F_N_DB_ERR	vxge_mBIT(7)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT1_FAU_MAC2F_W_SG_ERR(val) \
+							vxge_vBIT(val, 8, 2)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT1_FAU_MAC2F_W_DB_ERR(val) \
+							vxge_vBIT(val, 10, 2)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT2_FAU_MAC2F_N_SG_ERR	vxge_mBIT(12)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT2_FAU_MAC2F_N_DB_ERR	vxge_mBIT(13)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT2_FAU_MAC2F_W_SG_ERR(val) \
+							vxge_vBIT(val, 14, 2)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAU_PORT2_FAU_MAC2F_W_DB_ERR(val) \
+							vxge_vBIT(val, 16, 2)
+#define VXGE_HW_FAU_ECC_ERR_REG_FAU_FAU_XFMD_INS_SG_ERR(val) \
+							vxge_vBIT(val, 18, 2)
+#define VXGE_HW_FAU_ECC_ERR_REG_FAU_FAU_XFMD_INS_DB_ERR(val) \
+							vxge_vBIT(val, 20, 2)
+#define	VXGE_HW_FAU_ECC_ERR_REG_FAUJ_FAU_FSM_ERR	vxge_mBIT(31)
+/*0x05620*/	u64	fau_ecc_err_mask;
+/*0x05628*/	u64	fau_ecc_err_alarm;
+	u8	unused05658[0x05658-0x05630];
+/*0x05658*/	u64	fau_pa_cfg;
+#define	VXGE_HW_FAU_PA_CFG_REPL_L4_COMP_CSUM	vxge_mBIT(3)
+#define	VXGE_HW_FAU_PA_CFG_REPL_L3_INCL_CF	vxge_mBIT(7)
+#define	VXGE_HW_FAU_PA_CFG_REPL_L3_COMP_CSUM	vxge_mBIT(11)
+	u8	unused05668[0x05668-0x05660];
+
+/*0x05668*/	u64	dbg_stats_fau_rx_path;
+#define	VXGE_HW_DBG_STATS_FAU_RX_PATH_RX_PERMITTED_FRMS(val) \
+						vxge_vBIT(val, 32, 32)
+	u8	unused056c0[0x056c0-0x05670];
+
+/*0x056c0*/	u64	fau_lag_cfg;
+#define VXGE_HW_FAU_LAG_CFG_COLL_ALG(val) vxge_vBIT(val, 2, 2)
+#define	VXGE_HW_FAU_LAG_CFG_INCR_RX_AGGR_STATS	vxge_mBIT(7)
+	u8	unused05800[0x05800-0x056c8];
+
+/*0x05800*/	u64	tpa_int_status;
+#define	VXGE_HW_TPA_INT_STATUS_ORP_ERR_ORP_INT	vxge_mBIT(15)
+#define	VXGE_HW_TPA_INT_STATUS_PTM_ALARM_PTM_INT	vxge_mBIT(23)
+#define	VXGE_HW_TPA_INT_STATUS_TPA_ERROR_TPA_INT	vxge_mBIT(31)
+/*0x05808*/	u64	tpa_int_mask;
+/*0x05810*/	u64	orp_err_reg;
+#define	VXGE_HW_ORP_ERR_REG_ORP_FIFO_SG_ERR	vxge_mBIT(3)
+#define	VXGE_HW_ORP_ERR_REG_ORP_FIFO_DB_ERR	vxge_mBIT(7)
+#define	VXGE_HW_ORP_ERR_REG_ORP_XFMD_FIFO_UFLOW_ERR	vxge_mBIT(11)
+#define	VXGE_HW_ORP_ERR_REG_ORP_FRM_FIFO_UFLOW_ERR	vxge_mBIT(15)
+#define	VXGE_HW_ORP_ERR_REG_ORP_XFMD_RCV_FSM_ERR	vxge_mBIT(19)
+#define	VXGE_HW_ORP_ERR_REG_ORP_OUTREAD_FSM_ERR	vxge_mBIT(23)
+#define	VXGE_HW_ORP_ERR_REG_ORP_OUTQEM_FSM_ERR	vxge_mBIT(27)
+#define	VXGE_HW_ORP_ERR_REG_ORP_XFMD_RCV_SHADOW_ERR	vxge_mBIT(31)
+#define	VXGE_HW_ORP_ERR_REG_ORP_OUTREAD_SHADOW_ERR	vxge_mBIT(35)
+#define	VXGE_HW_ORP_ERR_REG_ORP_OUTQEM_SHADOW_ERR	vxge_mBIT(39)
+#define	VXGE_HW_ORP_ERR_REG_ORP_OUTFRM_SHADOW_ERR	vxge_mBIT(43)
+#define	VXGE_HW_ORP_ERR_REG_ORP_OPTPRS_SHADOW_ERR	vxge_mBIT(47)
+/*0x05818*/	u64	orp_err_mask;
+/*0x05820*/	u64	orp_err_alarm;
+/*0x05828*/	u64	ptm_alarm_reg;
+#define	VXGE_HW_PTM_ALARM_REG_PTM_RDCTRL_SYNC_ERR	vxge_mBIT(3)
+#define	VXGE_HW_PTM_ALARM_REG_PTM_RDCTRL_FIFO_ERR	vxge_mBIT(7)
+#define	VXGE_HW_PTM_ALARM_REG_XFMD_RD_FIFO_ERR	vxge_mBIT(11)
+#define	VXGE_HW_PTM_ALARM_REG_WDE2MSR_WR_FIFO_ERR	vxge_mBIT(15)
+#define VXGE_HW_PTM_ALARM_REG_PTM_FRMM_ECC_DB_ERR(val) vxge_vBIT(val, 18, 2)
+#define VXGE_HW_PTM_ALARM_REG_PTM_FRMM_ECC_SG_ERR(val) vxge_vBIT(val, 22, 2)
+/*0x05830*/	u64	ptm_alarm_mask;
+/*0x05838*/	u64	ptm_alarm_alarm;
+/*0x05840*/	u64	tpa_error_reg;
+#define	VXGE_HW_TPA_ERROR_REG_TPA_FSM_ERR_ALARM	vxge_mBIT(3)
+#define	VXGE_HW_TPA_ERROR_REG_TPA_TPA_DA_LKUP_PRT0_DB_ERR	vxge_mBIT(7)
+#define	VXGE_HW_TPA_ERROR_REG_TPA_TPA_DA_LKUP_PRT0_SG_ERR	vxge_mBIT(11)
+/*0x05848*/	u64	tpa_error_mask;
+/*0x05850*/	u64	tpa_error_alarm;
+/*0x05858*/	u64	tpa_global_cfg;
+#define	VXGE_HW_TPA_GLOBAL_CFG_SUPPORT_SNAP_AB_N	vxge_mBIT(7)
+#define	VXGE_HW_TPA_GLOBAL_CFG_ECC_ENABLE_N	vxge_mBIT(35)
+	u8	unused05868[0x05870-0x05860];
+
+/*0x05870*/	u64	ptm_ecc_cfg;
+#define	VXGE_HW_PTM_ECC_CFG_PTM_FRMM_ECC_EN_N	vxge_mBIT(3)
+/*0x05878*/	u64	ptm_phase_cfg;
+#define	VXGE_HW_PTM_PHASE_CFG_FRMM_WR_PHASE_EN	vxge_mBIT(3)
+#define	VXGE_HW_PTM_PHASE_CFG_FRMM_RD_PHASE_EN	vxge_mBIT(7)
+	u8	unused05898[0x05898-0x05880];
+
+/*0x05898*/	u64	dbg_stats_tpa_tx_path;
+#define	VXGE_HW_DBG_STATS_TPA_TX_PATH_TX_PERMITTED_FRMS(val) \
+							vxge_vBIT(val, 32, 32)
+	u8	unused05900[0x05900-0x058a0];
+
+/*0x05900*/	u64	tmac_int_status;
+#define	VXGE_HW_TMAC_INT_STATUS_TXMAC_GEN_ERR_TXMAC_GEN_INT	vxge_mBIT(3)
+#define	VXGE_HW_TMAC_INT_STATUS_TXMAC_ECC_ERR_TXMAC_ECC_INT	vxge_mBIT(7)
+/*0x05908*/	u64	tmac_int_mask;
+/*0x05910*/	u64	txmac_gen_err_reg;
+#define	VXGE_HW_TXMAC_GEN_ERR_REG_TMACJ_PERMANENT_STOP	vxge_mBIT(3)
+#define	VXGE_HW_TXMAC_GEN_ERR_REG_TMACJ_NO_VALID_VSPORT	vxge_mBIT(7)
+/*0x05918*/	u64	txmac_gen_err_mask;
+/*0x05920*/	u64	txmac_gen_err_alarm;
+/*0x05928*/	u64	txmac_ecc_err_reg;
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMACJ_TMAC_TPA2MAC_SG_ERR	vxge_mBIT(3)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMACJ_TMAC_TPA2MAC_DB_ERR	vxge_mBIT(7)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMACJ_TMAC_TPA2M_SB_SG_ERR	vxge_mBIT(11)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMACJ_TMAC_TPA2M_SB_DB_ERR	vxge_mBIT(15)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMACJ_TMAC_TPA2M_DA_SG_ERR	vxge_mBIT(19)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMACJ_TMAC_TPA2M_DA_DB_ERR	vxge_mBIT(23)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMAC_TMAC_PORT0_FSM_ERR	vxge_mBIT(27)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMAC_TMAC_PORT1_FSM_ERR	vxge_mBIT(31)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMAC_TMAC_PORT2_FSM_ERR	vxge_mBIT(35)
+#define	VXGE_HW_TXMAC_ECC_ERR_REG_TMACJ_TMACJ_FSM_ERR	vxge_mBIT(39)
+/*0x05930*/	u64	txmac_ecc_err_mask;
+/*0x05938*/	u64	txmac_ecc_err_alarm;
+	u8	unused05978[0x05978-0x05940];
+
+/*0x05978*/	u64	dbg_stat_tx_any_frms;
+#define VXGE_HW_DBG_STAT_TX_ANY_FRMS_PORT0_TX_ANY_FRMS(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_DBG_STAT_TX_ANY_FRMS_PORT1_TX_ANY_FRMS(val) vxge_vBIT(val, 8, 8)
+#define VXGE_HW_DBG_STAT_TX_ANY_FRMS_PORT2_TX_ANY_FRMS(val) \
+							vxge_vBIT(val, 16, 8)
+	u8	unused059a0[0x059a0-0x05980];
+
+/*0x059a0*/	u64	txmac_link_util_port[3];
+#define	VXGE_HW_TXMAC_LINK_UTIL_PORT_TMAC_TMAC_UTILIZATION(val) \
+							vxge_vBIT(val, 1, 7)
+#define VXGE_HW_TXMAC_LINK_UTIL_PORT_TMAC_UTIL_CFG(val) vxge_vBIT(val, 8, 4)
+#define VXGE_HW_TXMAC_LINK_UTIL_PORT_TMAC_TMAC_FRAC_UTIL(val) \
+							vxge_vBIT(val, 12, 4)
+#define VXGE_HW_TXMAC_LINK_UTIL_PORT_TMAC_PKT_WEIGHT(val) vxge_vBIT(val, 16, 4)
+#define	VXGE_HW_TXMAC_LINK_UTIL_PORT_TMAC_TMAC_SCALE_FACTOR	vxge_mBIT(23)
+/*0x059b8*/	u64	txmac_cfg0_port[3];
+#define	VXGE_HW_TXMAC_CFG0_PORT_TMAC_EN	vxge_mBIT(3)
+#define	VXGE_HW_TXMAC_CFG0_PORT_APPEND_PAD	vxge_mBIT(7)
+#define VXGE_HW_TXMAC_CFG0_PORT_PAD_BYTE(val) vxge_vBIT(val, 8, 8)
+/*0x059d0*/	u64	txmac_cfg1_port[3];
+#define VXGE_HW_TXMAC_CFG1_PORT_AVG_IPG(val) vxge_vBIT(val, 40, 8)
+/*0x059e8*/	u64	txmac_status_port[3];
+#define	VXGE_HW_TXMAC_STATUS_PORT_TMAC_TX_FRM_SENT	vxge_mBIT(3)
+	u8	unused05a20[0x05a20-0x05a00];
+
+/*0x05a20*/	u64	lag_distrib_dest;
+#define VXGE_HW_LAG_DISTRIB_DEST_MAP_VPATH(n)	vxge_mBIT(n)
+/*0x05a28*/	u64	lag_marker_cfg;
+#define	VXGE_HW_LAG_MARKER_CFG_GEN_RCVR_EN	vxge_mBIT(3)
+#define	VXGE_HW_LAG_MARKER_CFG_RESP_EN	vxge_mBIT(7)
+#define VXGE_HW_LAG_MARKER_CFG_RESP_TIMEOUT(val) vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_LAG_MARKER_CFG_SLOW_PROTO_MRKR_MIN_INTERVAL(val) \
+							vxge_vBIT(val, 32, 16)
+#define	VXGE_HW_LAG_MARKER_CFG_THROTTLE_MRKR_RESP	vxge_mBIT(51)
+/*0x05a30*/	u64	lag_tx_cfg;
+#define	VXGE_HW_LAG_TX_CFG_INCR_TX_AGGR_STATS	vxge_mBIT(3)
+#define VXGE_HW_LAG_TX_CFG_DISTRIB_ALG_SEL(val) vxge_vBIT(val, 6, 2)
+#define	VXGE_HW_LAG_TX_CFG_DISTRIB_REMAP_IF_FAIL	vxge_mBIT(11)
+#define VXGE_HW_LAG_TX_CFG_COLL_MAX_DELAY(val) vxge_vBIT(val, 16, 16)
+/*0x05a38*/	u64	lag_tx_status;
+#define VXGE_HW_LAG_TX_STATUS_TLAG_TIMER_VAL_EMPTIED_LINK(val) \
+							vxge_vBIT(val, 0, 8)
+#define	VXGE_HW_LAG_TX_STATUS_TLAG_TIMER_VAL_SLOW_PROTO_MRKR(val) \
+							vxge_vBIT(val, 8, 8)
+#define	VXGE_HW_LAG_TX_STATUS_TLAG_TIMER_VAL_SLOW_PROTO_MRKRRESP(val) \
+							vxge_vBIT(val, 16, 8)
+	u8	unused05d48[0x05d48-0x05a40];
+
+/*0x05d48*/	u64	srpcim_to_mrpcim_vplane_rmsg[17];
+#define	\
+VXGE_HAL_SRPCIM_TO_MRPCIM_VPLANE_RMSG_SWIF_SRPCIM_TO_MRPCIM_VPLANE_RMSG(val)\
+ vxge_vBIT(val, 0, 64)
+		u8	unused06420[0x06420-0x05dd0];
+
+/*0x06420*/	u64	mrpcim_to_srpcim_vplane_wmsg[17];
+#define	VXGE_HW_MRPCIM_TO_SRPCIM_VPLANE_WMSG_MRPCIM_TO_SRPCIM_VPLANE_WMSG(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x064a8*/	u64	mrpcim_to_srpcim_vplane_wmsg_trig[17];
+
+/*0x06530*/	u64	debug_stats0;
+#define VXGE_HW_DEBUG_STATS0_RSTDROP_MSG(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_DEBUG_STATS0_RSTDROP_CPL(val) vxge_vBIT(val, 32, 32)
+/*0x06538*/	u64	debug_stats1;
+#define VXGE_HW_DEBUG_STATS1_RSTDROP_CLIENT0(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_DEBUG_STATS1_RSTDROP_CLIENT1(val) vxge_vBIT(val, 32, 32)
+/*0x06540*/	u64	debug_stats2;
+#define VXGE_HW_DEBUG_STATS2_RSTDROP_CLIENT2(val) vxge_vBIT(val, 0, 32)
+/*0x06548*/	u64	debug_stats3_vplane[17];
+#define VXGE_HW_DEBUG_STATS3_VPLANE_DEPL_PH(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_DEBUG_STATS3_VPLANE_DEPL_NPH(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_DEBUG_STATS3_VPLANE_DEPL_CPLH(val) vxge_vBIT(val, 32, 16)
+/*0x065d0*/	u64	debug_stats4_vplane[17];
+#define VXGE_HW_DEBUG_STATS4_VPLANE_DEPL_PD(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_DEBUG_STATS4_VPLANE_DEPL_NPD(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_DEBUG_STATS4_VPLANE_DEPL_CPLD(val) vxge_vBIT(val, 32, 16)
+
+	u8	unused07000[0x07000-0x06658];
+
+/*0x07000*/	u64	mrpcim_general_int_status;
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_PIC_INT	vxge_mBIT(0)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_PCI_INT	vxge_mBIT(1)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_RTDMA_INT	vxge_mBIT(2)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_WRDMA_INT	vxge_mBIT(3)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_G3CMCT_INT	vxge_mBIT(4)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_GCMG1_INT	vxge_mBIT(5)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_GCMG2_INT	vxge_mBIT(6)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_GCMG3_INT	vxge_mBIT(7)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_G3CMIFL_INT	vxge_mBIT(8)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_G3CMIFU_INT	vxge_mBIT(9)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_PCMG1_INT	vxge_mBIT(10)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_PCMG2_INT	vxge_mBIT(11)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_PCMG3_INT	vxge_mBIT(12)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_XMAC_INT	vxge_mBIT(13)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_RXMAC_INT	vxge_mBIT(14)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_TMAC_INT	vxge_mBIT(15)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_G3FBIF_INT	vxge_mBIT(16)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_FBMC_INT	vxge_mBIT(17)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_G3FBCT_INT	vxge_mBIT(18)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_TPA_INT	vxge_mBIT(19)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_DRBELL_INT	vxge_mBIT(20)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_ONE_INT	vxge_mBIT(21)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_STATUS_MSG_INT	vxge_mBIT(22)
+/*0x07008*/	u64	mrpcim_general_int_mask;
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_PIC_INT	vxge_mBIT(0)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_PCI_INT	vxge_mBIT(1)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_RTDMA_INT	vxge_mBIT(2)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_WRDMA_INT	vxge_mBIT(3)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_G3CMCT_INT	vxge_mBIT(4)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_GCMG1_INT	vxge_mBIT(5)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_GCMG2_INT	vxge_mBIT(6)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_GCMG3_INT	vxge_mBIT(7)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_G3CMIFL_INT	vxge_mBIT(8)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_G3CMIFU_INT	vxge_mBIT(9)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_PCMG1_INT	vxge_mBIT(10)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_PCMG2_INT	vxge_mBIT(11)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_PCMG3_INT	vxge_mBIT(12)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_XMAC_INT	vxge_mBIT(13)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_RXMAC_INT	vxge_mBIT(14)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_TMAC_INT	vxge_mBIT(15)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_G3FBIF_INT	vxge_mBIT(16)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_FBMC_INT	vxge_mBIT(17)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_G3FBCT_INT	vxge_mBIT(18)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_TPA_INT	vxge_mBIT(19)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_DRBELL_INT	vxge_mBIT(20)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_ONE_INT	vxge_mBIT(21)
+#define	VXGE_HW_MRPCIM_GENERAL_INT_MASK_MSG_INT	vxge_mBIT(22)
+/*0x07010*/	u64	mrpcim_ppif_int_status;
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_INI_ERRORS_INI_INT	vxge_mBIT(3)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_DMA_ERRORS_DMA_INT	vxge_mBIT(7)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_TGT_ERRORS_TGT_INT	vxge_mBIT(11)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CONFIG_ERRORS_CONFIG_INT	vxge_mBIT(15)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_CRDT_INT	vxge_mBIT(19)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_PLL_ERRORS_PLL_INT	vxge_mBIT(27)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE0_CRD_INT_VPLANE0_INT\
+							vxge_mBIT(31)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE1_CRD_INT_VPLANE1_INT\
+							vxge_mBIT(32)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE2_CRD_INT_VPLANE2_INT\
+							vxge_mBIT(33)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE3_CRD_INT_VPLANE3_INT\
+							vxge_mBIT(34)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE4_CRD_INT_VPLANE4_INT\
+							vxge_mBIT(35)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE5_CRD_INT_VPLANE5_INT\
+							vxge_mBIT(36)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE6_CRD_INT_VPLANE6_INT\
+							vxge_mBIT(37)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE7_CRD_INT_VPLANE7_INT\
+							vxge_mBIT(38)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE8_CRD_INT_VPLANE8_INT\
+							vxge_mBIT(39)
+#define	VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE9_CRD_INT_VPLANE9_INT\
+							vxge_mBIT(40)
+#define \
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE10_CRD_INT_VPLANE10_INT \
+							vxge_mBIT(41)
+#define \
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE11_CRD_INT_VPLANE11_INT \
+							vxge_mBIT(42)
+#define	\
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE12_CRD_INT_VPLANE12_INT \
+							vxge_mBIT(43)
+#define	\
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE13_CRD_INT_VPLANE13_INT \
+							vxge_mBIT(44)
+#define	\
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE14_CRD_INT_VPLANE14_INT \
+							vxge_mBIT(45)
+#define	\
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE15_CRD_INT_VPLANE15_INT \
+							vxge_mBIT(46)
+#define	\
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_CRDT_ERRORS_VPLANE16_CRD_INT_VPLANE16_INT \
+							vxge_mBIT(47)
+#define	\
+VXGE_HW_MRPCIM_PPIF_INT_STATUS_VPATH_TO_MRPCIM_ALARM_VPATH_TO_MRPCIM_ALARM_INT \
+							vxge_mBIT(55)
+/*0x07018*/	u64	mrpcim_ppif_int_mask;
+	u8	unused07028[0x07028-0x07020];
+
+/*0x07028*/	u64	ini_errors_reg;
+#define	VXGE_HW_INI_ERRORS_REG_SCPL_CPL_TIMEOUT_UNUSED_TAG	vxge_mBIT(3)
+#define	VXGE_HW_INI_ERRORS_REG_SCPL_CPL_TIMEOUT	vxge_mBIT(7)
+#define	VXGE_HW_INI_ERRORS_REG_DCPL_FSM_ERR	vxge_mBIT(11)
+#define	VXGE_HW_INI_ERRORS_REG_DCPL_POISON	vxge_mBIT(12)
+#define	VXGE_HW_INI_ERRORS_REG_DCPL_UNSUPPORTED	vxge_mBIT(15)
+#define	VXGE_HW_INI_ERRORS_REG_DCPL_ABORT	vxge_mBIT(19)
+#define	VXGE_HW_INI_ERRORS_REG_INI_TLP_ABORT	vxge_mBIT(23)
+#define	VXGE_HW_INI_ERRORS_REG_INI_DLLP_ABORT	vxge_mBIT(27)
+#define	VXGE_HW_INI_ERRORS_REG_INI_ECRC_ERR	vxge_mBIT(31)
+#define	VXGE_HW_INI_ERRORS_REG_INI_BUF_DB_ERR	vxge_mBIT(35)
+#define	VXGE_HW_INI_ERRORS_REG_INI_BUF_SG_ERR	vxge_mBIT(39)
+#define	VXGE_HW_INI_ERRORS_REG_INI_DATA_OVERFLOW	vxge_mBIT(43)
+#define	VXGE_HW_INI_ERRORS_REG_INI_HDR_OVERFLOW	vxge_mBIT(47)
+#define	VXGE_HW_INI_ERRORS_REG_INI_MRD_SYS_DROP	vxge_mBIT(51)
+#define	VXGE_HW_INI_ERRORS_REG_INI_MWR_SYS_DROP	vxge_mBIT(55)
+#define	VXGE_HW_INI_ERRORS_REG_INI_MRD_CLIENT_DROP	vxge_mBIT(59)
+#define	VXGE_HW_INI_ERRORS_REG_INI_MWR_CLIENT_DROP	vxge_mBIT(63)
+/*0x07030*/	u64	ini_errors_mask;
+/*0x07038*/	u64	ini_errors_alarm;
+/*0x07040*/	u64	dma_errors_reg;
+#define	VXGE_HW_DMA_ERRORS_REG_RDARB_FSM_ERR	vxge_mBIT(3)
+#define	VXGE_HW_DMA_ERRORS_REG_WRARB_FSM_ERR	vxge_mBIT(7)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_WRDMA_WR_HDR_OVERFLOW	vxge_mBIT(8)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_WRDMA_WR_HDR_UNDERFLOW	vxge_mBIT(9)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_WRDMA_WR_DATA_OVERFLOW	vxge_mBIT(10)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_WRDMA_WR_DATA_UNDERFLOW	vxge_mBIT(11)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_MSG_WR_HDR_OVERFLOW	vxge_mBIT(12)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_MSG_WR_HDR_UNDERFLOW	vxge_mBIT(13)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_MSG_WR_DATA_OVERFLOW	vxge_mBIT(14)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_MSG_WR_DATA_UNDERFLOW	vxge_mBIT(15)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_STATS_WR_HDR_OVERFLOW	vxge_mBIT(16)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_STATS_WR_HDR_UNDERFLOW	vxge_mBIT(17)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_STATS_WR_DATA_OVERFLOW	vxge_mBIT(18)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_STATS_WR_DATA_UNDERFLOW	vxge_mBIT(19)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_RTDMA_WR_HDR_OVERFLOW	vxge_mBIT(20)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_RTDMA_WR_HDR_UNDERFLOW	vxge_mBIT(21)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_RTDMA_WR_DATA_OVERFLOW	vxge_mBIT(22)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_RTDMA_WR_DATA_UNDERFLOW	vxge_mBIT(23)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_WRDMA_RD_HDR_OVERFLOW	vxge_mBIT(24)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_WRDMA_RD_HDR_UNDERFLOW	vxge_mBIT(25)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_RTDMA_RD_HDR_OVERFLOW	vxge_mBIT(28)
+#define	VXGE_HW_DMA_ERRORS_REG_DMA_RTDMA_RD_HDR_UNDERFLOW	vxge_mBIT(29)
+#define	VXGE_HW_DMA_ERRORS_REG_DBLGEN_FSM_ERR	vxge_mBIT(32)
+#define	VXGE_HW_DMA_ERRORS_REG_DBLGEN_CREDIT_FSM_ERR	vxge_mBIT(33)
+#define	VXGE_HW_DMA_ERRORS_REG_DBLGEN_DMA_WRR_SM_ERR	vxge_mBIT(34)
+/*0x07048*/	u64	dma_errors_mask;
+/*0x07050*/	u64	dma_errors_alarm;
+/*0x07058*/	u64	tgt_errors_reg;
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_VENDOR_MSG	vxge_mBIT(0)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_MSG_UNLOCK	vxge_mBIT(1)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_ILLEGAL_TLP_BE	vxge_mBIT(2)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_BOOT_WRITE	vxge_mBIT(3)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_PIF_WR_CROSS_QWRANGE	vxge_mBIT(4)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_PIF_READ_CROSS_QWRANGE	vxge_mBIT(5)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_KDFC_READ	vxge_mBIT(6)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_USDC_READ	vxge_mBIT(7)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_USDC_WR_CROSS_QWRANGE	vxge_mBIT(8)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_MSIX_BEYOND_RANGE	vxge_mBIT(9)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_WR_TO_KDFC_POISON	vxge_mBIT(10)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_WR_TO_USDC_POISON	vxge_mBIT(11)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_WR_TO_PIF_POISON	vxge_mBIT(12)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_WR_TO_MSIX_POISON	vxge_mBIT(13)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_WR_TO_MRIOV_POISON	vxge_mBIT(14)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_NOT_MEM_TLP	vxge_mBIT(15)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_UNKNOWN_MEM_TLP	vxge_mBIT(16)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_REQ_FSM_ERR	vxge_mBIT(17)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_CPL_FSM_ERR	vxge_mBIT(18)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_KDFC_PROT_ERR	vxge_mBIT(19)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_SWIF_PROT_ERR	vxge_mBIT(20)
+#define	VXGE_HW_TGT_ERRORS_REG_TGT_MRIOV_MEM_MAP_CFG_ERR	vxge_mBIT(21)
+/*0x07060*/	u64	tgt_errors_mask;
+/*0x07068*/	u64	tgt_errors_alarm;
+/*0x07070*/	u64	config_errors_reg;
+#define	VXGE_HW_CONFIG_ERRORS_REG_I2C_ILLEGAL_STOP_COND	vxge_mBIT(3)
+#define	VXGE_HW_CONFIG_ERRORS_REG_I2C_ILLEGAL_START_COND	vxge_mBIT(7)
+#define	VXGE_HW_CONFIG_ERRORS_REG_I2C_EXP_RD_CNT	vxge_mBIT(11)
+#define	VXGE_HW_CONFIG_ERRORS_REG_I2C_EXTRA_CYCLE	vxge_mBIT(15)
+#define	VXGE_HW_CONFIG_ERRORS_REG_I2C_MAIN_FSM_ERR	vxge_mBIT(19)
+#define	VXGE_HW_CONFIG_ERRORS_REG_I2C_REQ_COLLISION	vxge_mBIT(23)
+#define	VXGE_HW_CONFIG_ERRORS_REG_I2C_REG_FSM_ERR	vxge_mBIT(27)
+#define	VXGE_HW_CONFIG_ERRORS_REG_CFGM_I2C_TIMEOUT	vxge_mBIT(31)
+#define	VXGE_HW_CONFIG_ERRORS_REG_RIC_I2C_TIMEOUT	vxge_mBIT(35)
+#define	VXGE_HW_CONFIG_ERRORS_REG_CFGM_FSM_ERR	vxge_mBIT(39)
+#define	VXGE_HW_CONFIG_ERRORS_REG_RIC_FSM_ERR	vxge_mBIT(43)
+#define	VXGE_HW_CONFIG_ERRORS_REG_PIFM_ILLEGAL_ACCESS	vxge_mBIT(47)
+#define	VXGE_HW_CONFIG_ERRORS_REG_PIFM_TIMEOUT	vxge_mBIT(51)
+#define	VXGE_HW_CONFIG_ERRORS_REG_PIFM_FSM_ERR	vxge_mBIT(55)
+#define	VXGE_HW_CONFIG_ERRORS_REG_PIFM_TO_FSM_ERR	vxge_mBIT(59)
+#define	VXGE_HW_CONFIG_ERRORS_REG_RIC_RIC_RD_TIMEOUT	vxge_mBIT(63)
+/*0x07078*/	u64	config_errors_mask;
+/*0x07080*/	u64	config_errors_alarm;
+	u8	unused07090[0x07090-0x07088];
+
+/*0x07090*/	u64	crdt_errors_reg;
+#define	VXGE_HW_CRDT_ERRORS_REG_WRCRDTARB_FSM_ERR	vxge_mBIT(11)
+#define	VXGE_HW_CRDT_ERRORS_REG_WRCRDTARB_INTCTL_ILLEGAL_CRD_DEAL \
+							vxge_mBIT(15)
+#define	VXGE_HW_CRDT_ERRORS_REG_WRCRDTARB_PDA_ILLEGAL_CRD_DEAL	vxge_mBIT(19)
+#define	VXGE_HW_CRDT_ERRORS_REG_WRCRDTARB_PCI_MSG_ILLEGAL_CRD_DEAL \
+							vxge_mBIT(23)
+#define	VXGE_HW_CRDT_ERRORS_REG_RDCRDTARB_FSM_ERR	vxge_mBIT(35)
+#define	VXGE_HW_CRDT_ERRORS_REG_RDCRDTARB_RDA_ILLEGAL_CRD_DEAL	vxge_mBIT(39)
+#define	VXGE_HW_CRDT_ERRORS_REG_RDCRDTARB_PDA_ILLEGAL_CRD_DEAL	vxge_mBIT(43)
+#define	VXGE_HW_CRDT_ERRORS_REG_RDCRDTARB_DBLGEN_ILLEGAL_CRD_DEAL \
+							vxge_mBIT(47)
+/*0x07098*/	u64	crdt_errors_mask;
+/*0x070a0*/	u64	crdt_errors_alarm;
+	u8	unused070b0[0x070b0-0x070a8];
+
+/*0x070b0*/	u64	mrpcim_general_errors_reg;
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_STATSB_FSM_ERR	vxge_mBIT(3)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_XGEN_FSM_ERR	vxge_mBIT(7)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_XMEM_FSM_ERR	vxge_mBIT(11)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_KDFCCTL_FSM_ERR	vxge_mBIT(15)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_MRIOVCTL_FSM_ERR	vxge_mBIT(19)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_SPI_FLSH_ERR	vxge_mBIT(23)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_SPI_IIC_ACK_ERR	vxge_mBIT(27)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_SPI_IIC_CHKSUM_ERR	vxge_mBIT(31)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_INI_SERR_DET	vxge_mBIT(35)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_INTCTL_MSIX_FSM_ERR	vxge_mBIT(39)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_INTCTL_MSI_OVERFLOW	vxge_mBIT(43)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_PPIF_PCI_NOT_FLUSH_DURING_SW_RESET \
+							vxge_mBIT(47)
+#define	VXGE_HW_MRPCIM_GENERAL_ERRORS_REG_PPIF_SW_RESET_FSM_ERR	vxge_mBIT(51)
+/*0x070b8*/	u64	mrpcim_general_errors_mask;
+/*0x070c0*/	u64	mrpcim_general_errors_alarm;
+	u8	unused070d0[0x070d0-0x070c8];
+
+/*0x070d0*/	u64	pll_errors_reg;
+#define	VXGE_HW_PLL_ERRORS_REG_CORE_CMG_PLL_OOL	vxge_mBIT(3)
+#define	VXGE_HW_PLL_ERRORS_REG_CORE_FB_PLL_OOL	vxge_mBIT(7)
+#define	VXGE_HW_PLL_ERRORS_REG_CORE_X_PLL_OOL	vxge_mBIT(11)
+/*0x070d8*/	u64	pll_errors_mask;
+/*0x070e0*/	u64	pll_errors_alarm;
+/*0x070e8*/	u64	srpcim_to_mrpcim_alarm_reg;
+#define	VXGE_HW_SRPCIM_TO_MRPCIM_ALARM_REG_PPIF_SRPCIM_TO_MRPCIM_ALARM(val) \
+							vxge_vBIT(val, 0, 17)
+/*0x070f0*/	u64	srpcim_to_mrpcim_alarm_mask;
+/*0x070f8*/	u64	srpcim_to_mrpcim_alarm_alarm;
+/*0x07100*/	u64	vpath_to_mrpcim_alarm_reg;
+#define	VXGE_HW_VPATH_TO_MRPCIM_ALARM_REG_PPIF_VPATH_TO_MRPCIM_ALARM(val) \
+							vxge_vBIT(val, 0, 17)
+/*0x07108*/	u64	vpath_to_mrpcim_alarm_mask;
+/*0x07110*/	u64	vpath_to_mrpcim_alarm_alarm;
+	u8	unused07128[0x07128-0x07118];
+
+/*0x07128*/	u64	crdt_errors_vplane_reg[17];
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_WRCRDTARB_P_H_CONSUME_CRDT_ERR \
+							vxge_mBIT(3)
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_WRCRDTARB_P_D_CONSUME_CRDT_ERR \
+							vxge_mBIT(7)
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_WRCRDTARB_P_H_RETURN_CRDT_ERR \
+							vxge_mBIT(11)
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_WRCRDTARB_P_D_RETURN_CRDT_ERR \
+							vxge_mBIT(15)
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_RDCRDTARB_NP_H_CONSUME_CRDT_ERR \
+							vxge_mBIT(19)
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_RDCRDTARB_NP_H_RETURN_CRDT_ERR \
+							vxge_mBIT(23)
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_RDCRDTARB_TAG_CONSUME_TAG_ERR \
+							vxge_mBIT(27)
+#define	VXGE_HW_CRDT_ERRORS_VPLANE_REG_RDCRDTARB_TAG_RETURN_TAG_ERR \
+							vxge_mBIT(31)
+/*0x07130*/	u64	crdt_errors_vplane_mask[17];
+/*0x07138*/	u64	crdt_errors_vplane_alarm[17];
+	u8	unused072f0[0x072f0-0x072c0];
+
+/*0x072f0*/	u64	mrpcim_rst_in_prog;
+#define	VXGE_HW_MRPCIM_RST_IN_PROG_MRPCIM_RST_IN_PROG	vxge_mBIT(7)
+/*0x072f8*/	u64	mrpcim_reg_modified;
+#define	VXGE_HW_MRPCIM_REG_MODIFIED_MRPCIM_REG_MODIFIED	vxge_mBIT(7)
+
+	u8	unused07378[0x07378-0x07300];
+
+/*0x07378*/	u64	write_arb_pending;
+#define	VXGE_HW_WRITE_ARB_PENDING_WRARB_WRDMA	vxge_mBIT(3)
+#define	VXGE_HW_WRITE_ARB_PENDING_WRARB_RTDMA	vxge_mBIT(7)
+#define	VXGE_HW_WRITE_ARB_PENDING_WRARB_MSG	vxge_mBIT(11)
+#define	VXGE_HW_WRITE_ARB_PENDING_WRARB_STATSB	vxge_mBIT(15)
+#define	VXGE_HW_WRITE_ARB_PENDING_WRARB_INTCTL	vxge_mBIT(19)
+/*0x07380*/	u64	read_arb_pending;
+#define	VXGE_HW_READ_ARB_PENDING_RDARB_WRDMA	vxge_mBIT(3)
+#define	VXGE_HW_READ_ARB_PENDING_RDARB_RTDMA	vxge_mBIT(7)
+#define	VXGE_HW_READ_ARB_PENDING_RDARB_DBLGEN	vxge_mBIT(11)
+/*0x07388*/	u64	dmaif_dmadbl_pending;
+#define	VXGE_HW_DMAIF_DMADBL_PENDING_DMAIF_WRDMA_WR	vxge_mBIT(0)
+#define	VXGE_HW_DMAIF_DMADBL_PENDING_DMAIF_WRDMA_RD	vxge_mBIT(1)
+#define	VXGE_HW_DMAIF_DMADBL_PENDING_DMAIF_RTDMA_WR	vxge_mBIT(2)
+#define	VXGE_HW_DMAIF_DMADBL_PENDING_DMAIF_RTDMA_RD	vxge_mBIT(3)
+#define	VXGE_HW_DMAIF_DMADBL_PENDING_DMAIF_MSG_WR	vxge_mBIT(4)
+#define	VXGE_HW_DMAIF_DMADBL_PENDING_DMAIF_STATS_WR	vxge_mBIT(5)
+#define	VXGE_HW_DMAIF_DMADBL_PENDING_DBLGEN_IN_PROG(val) \
+							vxge_vBIT(val, 13, 51)
+/*0x07390*/	u64	wrcrdtarb_status0_vplane[17];
+#define	VXGE_HW_WRCRDTARB_STATUS0_VPLANE_WRCRDTARB_ABS_AVAIL_P_H(val) \
+							vxge_vBIT(val, 0, 8)
+/*0x07418*/	u64	wrcrdtarb_status1_vplane[17];
+#define	VXGE_HW_WRCRDTARB_STATUS1_VPLANE_WRCRDTARB_ABS_AVAIL_P_D(val) \
+							vxge_vBIT(val, 4, 12)
+	u8	unused07500[0x07500-0x074a0];
+
+/*0x07500*/	u64	mrpcim_general_cfg1;
+#define	VXGE_HW_MRPCIM_GENERAL_CFG1_CLEAR_SERR	vxge_mBIT(7)
+/*0x07508*/	u64	mrpcim_general_cfg2;
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_INS_TX_WR_TD	vxge_mBIT(3)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_INS_TX_RD_TD	vxge_mBIT(7)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_INS_TX_CPL_TD	vxge_mBIT(11)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_INI_TIMEOUT_EN_MWR	vxge_mBIT(15)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_INI_TIMEOUT_EN_MRD	vxge_mBIT(19)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_IGNORE_VPATH_RST_FOR_MSIX	vxge_mBIT(23)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_FLASH_READ_MSB	vxge_mBIT(27)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_DIS_HOST_PIPELINE_WR	vxge_mBIT(31)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_MRPCIM_STATS_ENABLE	vxge_mBIT(43)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_MRPCIM_STATS_MAP_TO_VPATH(val) \
+							vxge_vBIT(val, 47, 5)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_EN_BLOCK_MSIX_DUE_TO_SERR	vxge_mBIT(55)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_FORCE_SENDING_INTA	vxge_mBIT(59)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG2_DIS_SWIF_PROT_ON_RDS	vxge_mBIT(63)
+/*0x07510*/	u64	mrpcim_general_cfg3;
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_PROTECTION_CA_OR_UNSUPN	vxge_mBIT(0)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_ILLEGAL_RD_CA_OR_UNSUPN	vxge_mBIT(3)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_RD_BYTE_SWAPEN	vxge_mBIT(7)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_RD_BIT_FLIPEN	vxge_mBIT(11)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_WR_BYTE_SWAPEN	vxge_mBIT(15)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_WR_BIT_FLIPEN	vxge_mBIT(19)
+#define VXGE_HW_MRPCIM_GENERAL_CFG3_MR_MAX_MVFS(val) vxge_vBIT(val, 20, 16)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_MR_MVF_TBL_SIZE(val) \
+							vxge_vBIT(val, 36, 16)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_PF0_SW_RESET_EN	vxge_mBIT(55)
+#define VXGE_HW_MRPCIM_GENERAL_CFG3_REG_MODIFIED_CFG(val) vxge_vBIT(val, 56, 2)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_CPL_ECC_ENABLE_N	vxge_mBIT(59)
+#define	VXGE_HW_MRPCIM_GENERAL_CFG3_BYPASS_DAISY_CHAIN	vxge_mBIT(63)
+/*0x07518*/	u64	mrpcim_stats_start_host_addr;
+#define	VXGE_HW_MRPCIM_STATS_START_HOST_ADDR_MRPCIM_STATS_START_HOST_ADDR(val)\
+							vxge_vBIT(val, 0, 57)
+
+	u8	unused07950[0x07950-0x07520];
+
+/*0x07950*/	u64	rdcrdtarb_cfg0;
+#define VXGE_HW_RDCRDTARB_CFG0_RDA_MAX_OUTSTANDING_RDS(val) \
+						vxge_vBIT(val, 18, 6)
+#define VXGE_HW_RDCRDTARB_CFG0_PDA_MAX_OUTSTANDING_RDS(val) \
+						vxge_vBIT(val, 26, 6)
+#define VXGE_HW_RDCRDTARB_CFG0_DBLGEN_MAX_OUTSTANDING_RDS(val) \
+						vxge_vBIT(val, 34, 6)
+#define VXGE_HW_RDCRDTARB_CFG0_WAIT_CNT(val) vxge_vBIT(val, 48, 4)
+#define VXGE_HW_RDCRDTARB_CFG0_MAX_OUTSTANDING_RDS(val) vxge_vBIT(val, 54, 6)
+#define	VXGE_HW_RDCRDTARB_CFG0_EN_XON	vxge_mBIT(63)
+	u8	unused07be8[0x07be8-0x07958];
+
+/*0x07be8*/	u64	bf_sw_reset;
+#define VXGE_HW_BF_SW_RESET_BF_SW_RESET(val) vxge_vBIT(val, 0, 8)
+/*0x07bf0*/	u64	sw_reset_status;
+#define	VXGE_HW_SW_RESET_STATUS_RESET_CMPLT	vxge_mBIT(7)
+#define	VXGE_HW_SW_RESET_STATUS_INIT_CMPLT	vxge_mBIT(15)
+	u8	unused07d30[0x07d30-0x07bf8];
+
+/*0x07d30*/	u64	mrpcim_debug_stats0;
+#define VXGE_HW_MRPCIM_DEBUG_STATS0_INI_WR_DROP(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_MRPCIM_DEBUG_STATS0_INI_RD_DROP(val) vxge_vBIT(val, 32, 32)
+/*0x07d38*/	u64	mrpcim_debug_stats1_vplane[17];
+#define	VXGE_HW_MRPCIM_DEBUG_STATS1_VPLANE_WRCRDTARB_PH_CRDT_DEPLETED(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x07dc0*/	u64	mrpcim_debug_stats2_vplane[17];
+#define	VXGE_HW_MRPCIM_DEBUG_STATS2_VPLANE_WRCRDTARB_PD_CRDT_DEPLETED(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x07e48*/	u64	mrpcim_debug_stats3_vplane[17];
+#define	VXGE_HW_MRPCIM_DEBUG_STATS3_VPLANE_RDCRDTARB_NPH_CRDT_DEPLETED(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x07ed0*/	u64	mrpcim_debug_stats4;
+#define VXGE_HW_MRPCIM_DEBUG_STATS4_INI_WR_VPIN_DROP(val) vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_MRPCIM_DEBUG_STATS4_INI_RD_VPIN_DROP(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x07ed8*/	u64	genstats_count01;
+#define VXGE_HW_GENSTATS_COUNT01_GENSTATS_COUNT1(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_GENSTATS_COUNT01_GENSTATS_COUNT0(val) vxge_vBIT(val, 32, 32)
+/*0x07ee0*/	u64	genstats_count23;
+#define VXGE_HW_GENSTATS_COUNT23_GENSTATS_COUNT3(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_GENSTATS_COUNT23_GENSTATS_COUNT2(val) vxge_vBIT(val, 32, 32)
+/*0x07ee8*/	u64	genstats_count4;
+#define VXGE_HW_GENSTATS_COUNT4_GENSTATS_COUNT4(val) vxge_vBIT(val, 32, 32)
+/*0x07ef0*/	u64	genstats_count5;
+#define VXGE_HW_GENSTATS_COUNT5_GENSTATS_COUNT5(val) vxge_vBIT(val, 32, 32)
+
+	u8	unused07f08[0x07f08-0x07ef8];
+
+/*0x07f08*/	u64	genstats_cfg[6];
+#define VXGE_HW_GENSTATS_CFG_DTYPE_SEL(val) vxge_vBIT(val, 3, 5)
+#define VXGE_HW_GENSTATS_CFG_CLIENT_NO_SEL(val) vxge_vBIT(val, 9, 3)
+#define VXGE_HW_GENSTATS_CFG_WR_RD_CPL_SEL(val) vxge_vBIT(val, 14, 2)
+#define VXGE_HW_GENSTATS_CFG_VPATH_SEL(val) vxge_vBIT(val, 31, 17)
+/*0x07f38*/	u64	genstat_64bit_cfg;
+#define	VXGE_HW_GENSTAT_64BIT_CFG_EN_FOR_GENSTATS0	vxge_mBIT(3)
+#define	VXGE_HW_GENSTAT_64BIT_CFG_EN_FOR_GENSTATS2	vxge_mBIT(7)
+	u8	unused08000[0x08000-0x07f40];
+/*0x08000*/	u64	gcmg3_int_status;
+#define	VXGE_HW_GCMG3_INT_STATUS_GSTC_ERR0_GSTC0_INT	vxge_mBIT(0)
+#define	VXGE_HW_GCMG3_INT_STATUS_GSTC_ERR1_GSTC1_INT	vxge_mBIT(1)
+#define	VXGE_HW_GCMG3_INT_STATUS_GH2L_ERR0_GH2L0_INT	vxge_mBIT(2)
+#define	VXGE_HW_GCMG3_INT_STATUS_GHSQ_ERR_GH2L1_INT	vxge_mBIT(3)
+#define	VXGE_HW_GCMG3_INT_STATUS_GHSQ_ERR2_GH2L2_INT	vxge_mBIT(4)
+#define	VXGE_HW_GCMG3_INT_STATUS_GH2L_SMERR0_GH2L3_INT	vxge_mBIT(5)
+#define	VXGE_HW_GCMG3_INT_STATUS_GHSQ_ERR3_GH2L4_INT	vxge_mBIT(6)
+/*0x08008*/	u64	gcmg3_int_mask;
+	u8	unused09000[0x09000-0x8010];
+
+/*0x09000*/	u64	g3ifcmd_fb_int_status;
+#define	VXGE_HW_G3IFCMD_FB_INT_STATUS_ERR_G3IF_INT	vxge_mBIT(0)
+/*0x09008*/	u64	g3ifcmd_fb_int_mask;
+/*0x09010*/	u64	g3ifcmd_fb_err_reg;
+#define	VXGE_HW_G3IFCMD_FB_ERR_REG_G3IF_CK_DLL_LOCK	vxge_mBIT(6)
+#define	VXGE_HW_G3IFCMD_FB_ERR_REG_G3IF_SM_ERR	vxge_mBIT(7)
+#define VXGE_HW_G3IFCMD_FB_ERR_REG_G3IF_RWDQS_DLL_LOCK(val) \
+						vxge_vBIT(val, 24, 8)
+#define	VXGE_HW_G3IFCMD_FB_ERR_REG_G3IF_IOCAL_FAULT	vxge_mBIT(55)
+/*0x09018*/	u64	g3ifcmd_fb_err_mask;
+/*0x09020*/	u64	g3ifcmd_fb_err_alarm;
+
+	u8	unused09400[0x09400-0x09028];
+
+/*0x09400*/	u64	g3ifcmd_cmu_int_status;
+#define	VXGE_HW_G3IFCMD_CMU_INT_STATUS_ERR_G3IF_INT	vxge_mBIT(0)
+/*0x09408*/	u64	g3ifcmd_cmu_int_mask;
+/*0x09410*/	u64	g3ifcmd_cmu_err_reg;
+#define	VXGE_HW_G3IFCMD_CMU_ERR_REG_G3IF_CK_DLL_LOCK	vxge_mBIT(6)
+#define	VXGE_HW_G3IFCMD_CMU_ERR_REG_G3IF_SM_ERR	vxge_mBIT(7)
+#define VXGE_HW_G3IFCMD_CMU_ERR_REG_G3IF_RWDQS_DLL_LOCK(val) \
+							vxge_vBIT(val, 24, 8)
+#define	VXGE_HW_G3IFCMD_CMU_ERR_REG_G3IF_IOCAL_FAULT	vxge_mBIT(55)
+/*0x09418*/	u64	g3ifcmd_cmu_err_mask;
+/*0x09420*/	u64	g3ifcmd_cmu_err_alarm;
+
+	u8	unused09800[0x09800-0x09428];
+
+/*0x09800*/	u64	g3ifcmd_cml_int_status;
+#define	VXGE_HW_G3IFCMD_CML_INT_STATUS_ERR_G3IF_INT	vxge_mBIT(0)
+/*0x09808*/	u64	g3ifcmd_cml_int_mask;
+/*0x09810*/	u64	g3ifcmd_cml_err_reg;
+#define	VXGE_HW_G3IFCMD_CML_ERR_REG_G3IF_CK_DLL_LOCK	vxge_mBIT(6)
+#define	VXGE_HW_G3IFCMD_CML_ERR_REG_G3IF_SM_ERR	vxge_mBIT(7)
+#define VXGE_HW_G3IFCMD_CML_ERR_REG_G3IF_RWDQS_DLL_LOCK(val) \
+						vxge_vBIT(val, 24, 8)
+#define	VXGE_HW_G3IFCMD_CML_ERR_REG_G3IF_IOCAL_FAULT	vxge_mBIT(55)
+/*0x09818*/	u64	g3ifcmd_cml_err_mask;
+/*0x09820*/	u64	g3ifcmd_cml_err_alarm;
+	u8	unused09b00[0x09b00-0x09828];
+
+/*0x09b00*/	u64	vpath_to_vplane_map[17];
+#define VXGE_HW_VPATH_TO_VPLANE_MAP_VPATH_TO_VPLANE_MAP(val) \
+							vxge_vBIT(val, 3, 5)
+	u8	unused09c30[0x09c30-0x09b88];
+
+/*0x09c30*/	u64	xgxs_cfg_port[2];
+#define VXGE_HW_XGXS_CFG_PORT_SIG_DETECT_FORCE_LOS(val) vxge_vBIT(val, 16, 4)
+#define VXGE_HW_XGXS_CFG_PORT_SIG_DETECT_FORCE_VALID(val) vxge_vBIT(val, 20, 4)
+#define	VXGE_HW_XGXS_CFG_PORT_SEL_INFO_0	vxge_mBIT(27)
+#define VXGE_HW_XGXS_CFG_PORT_SEL_INFO_1(val) vxge_vBIT(val, 29, 3)
+#define VXGE_HW_XGXS_CFG_PORT_TX_LANE0_SKEW(val) vxge_vBIT(val, 32, 4)
+#define VXGE_HW_XGXS_CFG_PORT_TX_LANE1_SKEW(val) vxge_vBIT(val, 36, 4)
+#define VXGE_HW_XGXS_CFG_PORT_TX_LANE2_SKEW(val) vxge_vBIT(val, 40, 4)
+#define VXGE_HW_XGXS_CFG_PORT_TX_LANE3_SKEW(val) vxge_vBIT(val, 44, 4)
+/*0x09c40*/	u64	xgxs_rxber_cfg_port[2];
+#define VXGE_HW_XGXS_RXBER_CFG_PORT_INTERVAL_DUR(val) vxge_vBIT(val, 0, 4)
+#define	VXGE_HW_XGXS_RXBER_CFG_PORT_RXGXS_INTERVAL_CNT(val) \
+							vxge_vBIT(val, 16, 48)
+/*0x09c50*/	u64	xgxs_rxber_status_port[2];
+#define	VXGE_HW_XGXS_RXBER_STATUS_PORT_RXGXS_RXGXS_LANE_A_ERR_CNT(val)	\
+							vxge_vBIT(val, 0, 16)
+#define	VXGE_HW_XGXS_RXBER_STATUS_PORT_RXGXS_RXGXS_LANE_B_ERR_CNT(val)	\
+							vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_XGXS_RXBER_STATUS_PORT_RXGXS_RXGXS_LANE_C_ERR_CNT(val)	\
+							vxge_vBIT(val, 32, 16)
+#define	VXGE_HW_XGXS_RXBER_STATUS_PORT_RXGXS_RXGXS_LANE_D_ERR_CNT(val)	\
+							vxge_vBIT(val, 48, 16)
+/*0x09c60*/	u64	xgxs_status_port[2];
+#define VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_TX_ACTIVITY(val) vxge_vBIT(val, 0, 4)
+#define VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_RX_ACTIVITY(val) vxge_vBIT(val, 4, 4)
+#define	VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_CTC_FIFO_ERR	BIT(11)
+#define VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_BYTE_SYNC_LOST(val) \
+							vxge_vBIT(val, 12, 4)
+#define VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_CTC_ERR(val) vxge_vBIT(val, 16, 4)
+#define	VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_ALIGNMENT_ERR	vxge_mBIT(23)
+#define VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_DEC_ERR(val) vxge_vBIT(val, 24, 8)
+#define VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_SKIP_INS_REQ(val) \
+							vxge_vBIT(val, 32, 4)
+#define VXGE_HW_XGXS_STATUS_PORT_XMACJ_PCS_SKIP_DEL_REQ(val) \
+							vxge_vBIT(val, 36, 4)
+/*0x09c70*/	u64	xgxs_pma_reset_port[2];
+#define VXGE_HW_XGXS_PMA_RESET_PORT_SERDES_RESET(val) vxge_vBIT(val, 0, 8)
+	u8	unused09c90[0x09c90-0x09c80];
+
+/*0x09c90*/	u64	xgxs_static_cfg_port[2];
+#define	VXGE_HW_XGXS_STATIC_CFG_PORT_FW_CTRL_SERDES	vxge_mBIT(3)
+	u8	unused09d40[0x09d40-0x09ca0];
+
+/*0x09d40*/	u64	xgxs_info_port[2];
+#define VXGE_HW_XGXS_INFO_PORT_XMACJ_INFO_0(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_XGXS_INFO_PORT_XMACJ_INFO_1(val) vxge_vBIT(val, 32, 32)
+/*0x09d50*/	u64	ratemgmt_cfg_port[2];
+#define VXGE_HW_RATEMGMT_CFG_PORT_MODE(val) vxge_vBIT(val, 2, 2)
+#define	VXGE_HW_RATEMGMT_CFG_PORT_RATE	vxge_mBIT(7)
+#define	VXGE_HW_RATEMGMT_CFG_PORT_FIXED_USE_FSM	vxge_mBIT(11)
+#define	VXGE_HW_RATEMGMT_CFG_PORT_ANTP_USE_FSM	vxge_mBIT(15)
+#define	VXGE_HW_RATEMGMT_CFG_PORT_ANBE_USE_FSM	vxge_mBIT(19)
+/*0x09d60*/	u64	ratemgmt_status_port[2];
+#define	VXGE_HW_RATEMGMT_STATUS_PORT_RATEMGMT_COMPLETE	vxge_mBIT(3)
+#define	VXGE_HW_RATEMGMT_STATUS_PORT_RATEMGMT_RATE	vxge_mBIT(7)
+#define	VXGE_HW_RATEMGMT_STATUS_PORT_RATEMGMT_MAC_MATCHES_PHY	vxge_mBIT(11)
+	u8	unused09d80[0x09d80-0x09d70];
+
+/*0x09d80*/	u64	ratemgmt_fixed_cfg_port[2];
+#define	VXGE_HW_RATEMGMT_FIXED_CFG_PORT_RESTART	vxge_mBIT(7)
+/*0x09d90*/	u64	ratemgmt_antp_cfg_port[2];
+#define	VXGE_HW_RATEMGMT_ANTP_CFG_PORT_RESTART	vxge_mBIT(7)
+#define	VXGE_HW_RATEMGMT_ANTP_CFG_PORT_USE_PREAMBLE_EXT_PHY	vxge_mBIT(11)
+#define	VXGE_HW_RATEMGMT_ANTP_CFG_PORT_USE_ACT_SEL	vxge_mBIT(15)
+#define VXGE_HW_RATEMGMT_ANTP_CFG_PORT_T_RETRY_PHY_QUERY(val) \
+							vxge_vBIT(val, 16, 4)
+#define	VXGE_HW_RATEMGMT_ANTP_CFG_PORT_T_WAIT_MDIO_RESPONSE(val) \
+							vxge_vBIT(val, 20, 4)
+#define	VXGE_HW_RATEMGMT_ANTP_CFG_PORT_T_LDOWN_REAUTO_RESPONSE(val) \
+							vxge_vBIT(val, 24, 4)
+#define	VXGE_HW_RATEMGMT_ANTP_CFG_PORT_ADVERTISE_10G	vxge_mBIT(31)
+#define	VXGE_HW_RATEMGMT_ANTP_CFG_PORT_ADVERTISE_1G	vxge_mBIT(35)
+/*0x09da0*/	u64	ratemgmt_anbe_cfg_port[2];
+#define	VXGE_HW_RATEMGMT_ANBE_CFG_PORT_RESTART	vxge_mBIT(7)
+#define	VXGE_HW_RATEMGMT_ANBE_CFG_PORT_PARALLEL_DETECT_10G_KX4_ENABLE \
+								vxge_mBIT(11)
+#define	VXGE_HW_RATEMGMT_ANBE_CFG_PORT_PARALLEL_DETECT_1G_KX_ENABLE \
+								vxge_mBIT(15)
+#define VXGE_HW_RATEMGMT_ANBE_CFG_PORT_T_SYNC_10G_KX4(val) vxge_vBIT(val, 16, 4)
+#define VXGE_HW_RATEMGMT_ANBE_CFG_PORT_T_SYNC_1G_KX(val) vxge_vBIT(val, 20, 4)
+#define VXGE_HW_RATEMGMT_ANBE_CFG_PORT_T_DME_EXCHANGE(val) vxge_vBIT(val, 24, 4)
+#define	VXGE_HW_RATEMGMT_ANBE_CFG_PORT_ADVERTISE_10G_KX4	vxge_mBIT(31)
+#define	VXGE_HW_RATEMGMT_ANBE_CFG_PORT_ADVERTISE_1G_KX	vxge_mBIT(35)
+/*0x09db0*/	u64	anbe_cfg_port[2];
+#define VXGE_HW_ANBE_CFG_PORT_RESET_CFG_REGS(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_ANBE_CFG_PORT_ALIGN_10G_KX4_OVERRIDE(val) vxge_vBIT(val, 10, 2)
+#define VXGE_HW_ANBE_CFG_PORT_SYNC_1G_KX_OVERRIDE(val) vxge_vBIT(val, 14, 2)
+/*0x09dc0*/	u64	anbe_mgr_ctrl_port[2];
+#define	VXGE_HW_ANBE_MGR_CTRL_PORT_WE	vxge_mBIT(3)
+#define	VXGE_HW_ANBE_MGR_CTRL_PORT_STROBE	vxge_mBIT(7)
+#define VXGE_HW_ANBE_MGR_CTRL_PORT_ADDR(val) vxge_vBIT(val, 15, 9)
+#define VXGE_HW_ANBE_MGR_CTRL_PORT_DATA(val) vxge_vBIT(val, 32, 32)
+	u8	unused09de0[0x09de0-0x09dd0];
+
+/*0x09de0*/	u64	anbe_fw_mstr_port[2];
+#define	VXGE_HW_ANBE_FW_MSTR_PORT_CONNECT_BEAN_TO_SERDES	vxge_mBIT(3)
+#define	VXGE_HW_ANBE_FW_MSTR_PORT_TX_ZEROES_TO_SERDES	vxge_mBIT(7)
+/*0x09df0*/	u64	anbe_hwfsm_gen_status_port[2];
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_CHOSE_10G_KX4_USING_PD \
+							vxge_mBIT(3)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_CHOSE_10G_KX4_USING_DME \
+							vxge_mBIT(7)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_CHOSE_1G_KX_USING_PD \
+							vxge_mBIT(11)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_CHOSE_1G_KX_USING_DME \
+							vxge_mBIT(15)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_ANBEFSM_STATE(val)	\
+							vxge_vBIT(val, 18, 6)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_BEAN_NEXT_PAGE_RECEIVED \
+							vxge_mBIT(27)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_BEAN_BASE_PAGE_RECEIVED \
+							vxge_mBIT(35)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_BEAN_AUTONEG_COMPLETE \
+							vxge_mBIT(39)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_NP_BEFORE_BP \
+							vxge_mBIT(43)
+#define	\
+VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_AN_COMPLETE_BEFORE_BP \
+							vxge_mBIT(47)
+#define	\
+VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_AN_COMPLETE_BEFORE_NP \
+vxge_mBIT(51)
+#define	\
+VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_MODE_WHEN_AN_COMPLETE \
+							vxge_mBIT(55)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_COUNT_BP(val) \
+							vxge_vBIT(val, 56, 4)
+#define	VXGE_HW_ANBE_HWFSM_GEN_STATUS_PORT_RATEMGMT_COUNT_NP(val) \
+							vxge_vBIT(val, 60, 4)
+/*0x09e00*/	u64	anbe_hwfsm_bp_status_port[2];
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_FEC_ENABLE \
+							vxge_mBIT(32)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_FEC_ABILITY \
+							vxge_mBIT(33)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_10G_KR_CAPABLE \
+							vxge_mBIT(40)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_10G_KX4_CAPABLE \
+							vxge_mBIT(41)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_1G_KX_CAPABLE \
+							vxge_mBIT(42)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_TX_NONCE(val)	\
+							vxge_vBIT(val, 43, 5)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_NP	vxge_mBIT(48)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_ACK	vxge_mBIT(49)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_REMOTE_FAULT \
+							vxge_mBIT(50)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_ASM_DIR	vxge_mBIT(51)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_PAUSE	vxge_mBIT(53)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_ECHOED_NONCE(val) \
+							vxge_vBIT(val, 54, 5)
+#define	VXGE_HW_ANBE_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_SELECTOR_FIELD(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x09e10*/	u64	anbe_hwfsm_np_status_port[2];
+#define	VXGE_HW_ANBE_HWFSM_NP_STATUS_PORT_RATEMGMT_NP_BITS_47_TO_32(val) \
+							vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_ANBE_HWFSM_NP_STATUS_PORT_RATEMGMT_NP_BITS_31_TO_0(val) \
+							vxge_vBIT(val, 32, 32)
+	u8	unused09e30[0x09e30-0x09e20];
+
+/*0x09e30*/	u64	antp_gen_cfg_port[2];
+/*0x09e40*/	u64	antp_hwfsm_gen_status_port[2];
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_CHOSE_10G	vxge_mBIT(3)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_CHOSE_1G	vxge_mBIT(7)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_ANTPFSM_STATE(val)	\
+							vxge_vBIT(val, 10, 6)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_AUTONEG_COMPLETE \
+								vxge_mBIT(23)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_NO_LP_XNP \
+							vxge_mBIT(27)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_GOT_LP_XNP	vxge_mBIT(31)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_MESSAGE_CODE \
+							vxge_mBIT(35)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_NO_HCD \
+							vxge_mBIT(43)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_FOUND_HCD	vxge_mBIT(47)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_UNEXPECTED_INVALID_RATE \
+							vxge_mBIT(51)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_VALID_RATE	vxge_mBIT(55)
+#define	VXGE_HW_ANTP_HWFSM_GEN_STATUS_PORT_RATEMGMT_PERSISTENT_LDOWN \
+							vxge_mBIT(59)
+/*0x09e50*/	u64	antp_hwfsm_bp_status_port[2];
+#define	VXGE_HW_ANTP_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_NP	vxge_mBIT(0)
+#define	VXGE_HW_ANTP_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_ACK	vxge_mBIT(1)
+#define	VXGE_HW_ANTP_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_RF	vxge_mBIT(2)
+#define	VXGE_HW_ANTP_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_XNP	vxge_mBIT(3)
+#define	VXGE_HW_ANTP_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_ABILITY_FIELD(val) \
+							vxge_vBIT(val, 4, 7)
+#define	VXGE_HW_ANTP_HWFSM_BP_STATUS_PORT_RATEMGMT_BP_SELECTOR_FIELD(val) \
+							vxge_vBIT(val, 11, 5)
+/*0x09e60*/	u64	antp_hwfsm_xnp_status_port[2];
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_NP	vxge_mBIT(0)
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_ACK	vxge_mBIT(1)
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_MP	vxge_mBIT(2)
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_ACK2	vxge_mBIT(3)
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_TOGGLE	vxge_mBIT(4)
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_MESSAGE_CODE(val) \
+							vxge_vBIT(val, 5, 11)
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_UNF_CODE_FIELD1(val) \
+							vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_ANTP_HWFSM_XNP_STATUS_PORT_RATEMGMT_XNP_UNF_CODE_FIELD2(val) \
+							vxge_vBIT(val, 32, 16)
+/*0x09e70*/	u64	mdio_mgr_access_port[2];
+#define	VXGE_HW_MDIO_MGR_ACCESS_PORT_STROBE_ONE	BIT(3)
+#define VXGE_HW_MDIO_MGR_ACCESS_PORT_OP_TYPE(val) vxge_vBIT(val, 5, 3)
+#define VXGE_HW_MDIO_MGR_ACCESS_PORT_DEVAD(val) vxge_vBIT(val, 11, 5)
+#define VXGE_HW_MDIO_MGR_ACCESS_PORT_ADDR(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_MDIO_MGR_ACCESS_PORT_DATA(val) vxge_vBIT(val, 32, 16)
+#define VXGE_HW_MDIO_MGR_ACCESS_PORT_ST_PATTERN(val) vxge_vBIT(val, 49, 2)
+#define	VXGE_HW_MDIO_MGR_ACCESS_PORT_PREAMBLE	vxge_mBIT(51)
+#define VXGE_HW_MDIO_MGR_ACCESS_PORT_PRTAD(val) vxge_vBIT(val, 55, 5)
+#define	VXGE_HW_MDIO_MGR_ACCESS_PORT_STROBE_TWO	vxge_mBIT(63)
+	u8	unused0a200[0x0a200-0x09e80];
+/*0x0a200*/	u64	xmac_vsport_choices_vh[17];
+#define VXGE_HW_XMAC_VSPORT_CHOICES_VH_VSPORT_VECTOR(val) vxge_vBIT(val, 0, 17)
+	u8	unused0a400[0x0a400-0x0a288];
+
+/*0x0a400*/	u64	rx_thresh_cfg_vp[17];
+#define VXGE_HW_RX_THRESH_CFG_VP_PAUSE_LOW_THR(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_RX_THRESH_CFG_VP_PAUSE_HIGH_THR(val) vxge_vBIT(val, 8, 8)
+#define VXGE_HW_RX_THRESH_CFG_VP_RED_THR_0(val) vxge_vBIT(val, 16, 8)
+#define VXGE_HW_RX_THRESH_CFG_VP_RED_THR_1(val) vxge_vBIT(val, 24, 8)
+#define VXGE_HW_RX_THRESH_CFG_VP_RED_THR_2(val) vxge_vBIT(val, 32, 8)
+#define VXGE_HW_RX_THRESH_CFG_VP_RED_THR_3(val) vxge_vBIT(val, 40, 8)
+	u8	unused0ac90[0x0ac90-0x0a488];
+} __packed;
+
+/*VXGE_HW_SRPCIM_REGS_H*/
+struct vxge_hw_srpcim_reg {
+
+/*0x00000*/	u64	tim_mr2sr_resource_assignment_vh;
+#define	VXGE_HW_TIM_MR2SR_RESOURCE_ASSIGNMENT_VH_BMAP_ROOT(val) \
+							vxge_vBIT(val, 0, 32)
+	u8	unused00100[0x00100-0x00008];
+
+/*0x00100*/	u64	srpcim_pcipif_int_status;
+#define	VXGE_HW_SRPCIM_PCIPIF_INT_STATUS_MRPCIM_MSG_MRPCIM_MSG_INT	BIT(3)
+#define	VXGE_HW_SRPCIM_PCIPIF_INT_STATUS_VPATH_MSG_VPATH_MSG_INT	BIT(7)
+#define	VXGE_HW_SRPCIM_PCIPIF_INT_STATUS_SRPCIM_SPARE_R1_SRPCIM_SPARE_R1_INT \
+									BIT(11)
+/*0x00108*/	u64	srpcim_pcipif_int_mask;
+/*0x00110*/	u64	mrpcim_msg_reg;
+#define	VXGE_HW_MRPCIM_MSG_REG_SWIF_MRPCIM_TO_SRPCIM_RMSG_INT	BIT(3)
+/*0x00118*/	u64	mrpcim_msg_mask;
+/*0x00120*/	u64	mrpcim_msg_alarm;
+/*0x00128*/	u64	vpath_msg_reg;
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH0_TO_SRPCIM_RMSG_INT	BIT(0)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH1_TO_SRPCIM_RMSG_INT	BIT(1)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH2_TO_SRPCIM_RMSG_INT	BIT(2)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH3_TO_SRPCIM_RMSG_INT	BIT(3)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH4_TO_SRPCIM_RMSG_INT	BIT(4)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH5_TO_SRPCIM_RMSG_INT	BIT(5)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH6_TO_SRPCIM_RMSG_INT	BIT(6)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH7_TO_SRPCIM_RMSG_INT	BIT(7)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH8_TO_SRPCIM_RMSG_INT	BIT(8)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH9_TO_SRPCIM_RMSG_INT	BIT(9)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH10_TO_SRPCIM_RMSG_INT	BIT(10)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH11_TO_SRPCIM_RMSG_INT	BIT(11)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH12_TO_SRPCIM_RMSG_INT	BIT(12)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH13_TO_SRPCIM_RMSG_INT	BIT(13)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH14_TO_SRPCIM_RMSG_INT	BIT(14)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH15_TO_SRPCIM_RMSG_INT	BIT(15)
+#define	VXGE_HW_VPATH_MSG_REG_SWIF_VPATH16_TO_SRPCIM_RMSG_INT	BIT(16)
+/*0x00130*/	u64	vpath_msg_mask;
+/*0x00138*/	u64	vpath_msg_alarm;
+	u8	unused00160[0x00160-0x00140];
+
+/*0x00160*/	u64	srpcim_to_mrpcim_wmsg;
+#define	VXGE_HW_SRPCIM_TO_MRPCIM_WMSG_SRPCIM_TO_MRPCIM_WMSG(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x00168*/	u64	srpcim_to_mrpcim_wmsg_trig;
+#define	VXGE_HW_SRPCIM_TO_MRPCIM_WMSG_TRIG_SRPCIM_TO_MRPCIM_WMSG_TRIG	BIT(0)
+/*0x00170*/	u64	mrpcim_to_srpcim_rmsg;
+#define	VXGE_HW_MRPCIM_TO_SRPCIM_RMSG_SWIF_MRPCIM_TO_SRPCIM_RMSG(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x00178*/	u64	vpath_to_srpcim_rmsg_sel;
+#define	VXGE_HW_VPATH_TO_SRPCIM_RMSG_SEL_VPATH_TO_SRPCIM_RMSG_SEL(val) \
+							vxge_vBIT(val, 0, 5)
+/*0x00180*/	u64	vpath_to_srpcim_rmsg;
+#define	VXGE_HW_VPATH_TO_SRPCIM_RMSG_SWIF_VPATH_TO_SRPCIM_RMSG(val) \
+							vxge_vBIT(val, 0, 64)
+	u8	unused00200[0x00200-0x00188];
+
+/*0x00200*/	u64	srpcim_general_int_status;
+#define	VXGE_HW_SRPCIM_GENERAL_INT_STATUS_PIC_INT	BIT(0)
+#define	VXGE_HW_SRPCIM_GENERAL_INT_STATUS_PCI_INT	BIT(3)
+#define	VXGE_HW_SRPCIM_GENERAL_INT_STATUS_XMAC_INT	BIT(7)
+	u8	unused00210[0x00210-0x00208];
+
+/*0x00210*/	u64	srpcim_general_int_mask;
+#define	VXGE_HW_SRPCIM_GENERAL_INT_MASK_PIC_INT	BIT(0)
+#define	VXGE_HW_SRPCIM_GENERAL_INT_MASK_PCI_INT	BIT(3)
+#define	VXGE_HW_SRPCIM_GENERAL_INT_MASK_XMAC_INT	BIT(7)
+	u8	unused00220[0x00220-0x00218];
+
+/*0x00220*/	u64	srpcim_ppif_int_status;
+
+/*0x00228*/	u64	srpcim_ppif_int_mask;
+/*0x00230*/	u64	srpcim_gen_errors_reg;
+#define	VXGE_HW_SRPCIM_GEN_ERRORS_REG_PCICONFIG_PF_STATUS_ERR	BIT(3)
+#define	VXGE_HW_SRPCIM_GEN_ERRORS_REG_PCICONFIG_PF_UNCOR_ERR	BIT(7)
+#define	VXGE_HW_SRPCIM_GEN_ERRORS_REG_PCICONFIG_PF_COR_ERR	BIT(11)
+#define	VXGE_HW_SRPCIM_GEN_ERRORS_REG_INTCTRL_SCHED_INT	BIT(15)
+#define	VXGE_HW_SRPCIM_GEN_ERRORS_REG_INI_SERR_DET	BIT(19)
+#define	VXGE_HW_SRPCIM_GEN_ERRORS_REG_TGT_PF_ILLEGAL_ACCESS	BIT(23)
+/*0x00238*/	u64	srpcim_gen_errors_mask;
+/*0x00240*/	u64	srpcim_gen_errors_alarm;
+/*0x00248*/	u64	mrpcim_to_srpcim_alarm_reg;
+#define	VXGE_HW_MRPCIM_TO_SRPCIM_ALARM_REG_PPIF_MRPCIM_TO_SRPCIM_ALARM	BIT(3)
+/*0x00250*/	u64	mrpcim_to_srpcim_alarm_mask;
+/*0x00258*/	u64	mrpcim_to_srpcim_alarm_alarm;
+/*0x00260*/	u64	vpath_to_srpcim_alarm_reg;
+
+/*0x00268*/	u64	vpath_to_srpcim_alarm_mask;
+/*0x00270*/	u64	vpath_to_srpcim_alarm_alarm;
+	u8	unused00280[0x00280-0x00278];
+
+/*0x00280*/	u64	pf_sw_reset;
+#define VXGE_HW_PF_SW_RESET_PF_SW_RESET(val) vxge_vBIT(val, 0, 8)
+/*0x00288*/	u64	srpcim_general_cfg1;
+#define	VXGE_HW_SRPCIM_GENERAL_CFG1_BOOT_BYTE_SWAPEN	BIT(19)
+#define	VXGE_HW_SRPCIM_GENERAL_CFG1_BOOT_BIT_FLIPEN	BIT(23)
+#define	VXGE_HW_SRPCIM_GENERAL_CFG1_MSIX_ADDR_SWAPEN	BIT(27)
+#define	VXGE_HW_SRPCIM_GENERAL_CFG1_MSIX_ADDR_FLIPEN	BIT(31)
+#define	VXGE_HW_SRPCIM_GENERAL_CFG1_MSIX_DATA_SWAPEN	BIT(35)
+#define	VXGE_HW_SRPCIM_GENERAL_CFG1_MSIX_DATA_FLIPEN	BIT(39)
+/*0x00290*/	u64	srpcim_interrupt_cfg1;
+#define VXGE_HW_SRPCIM_INTERRUPT_CFG1_ALARM_MAP_TO_MSG(val) vxge_vBIT(val, 1, 7)
+#define VXGE_HW_SRPCIM_INTERRUPT_CFG1_TRAFFIC_CLASS(val) vxge_vBIT(val, 9, 3)
+	u8	unused002a8[0x002a8-0x00298];
+
+/*0x002a8*/	u64	srpcim_clear_msix_mask;
+#define	VXGE_HW_SRPCIM_CLEAR_MSIX_MASK_SRPCIM_CLEAR_MSIX_MASK	BIT(0)
+/*0x002b0*/	u64	srpcim_set_msix_mask;
+#define	VXGE_HW_SRPCIM_SET_MSIX_MASK_SRPCIM_SET_MSIX_MASK	BIT(0)
+/*0x002b8*/	u64	srpcim_clr_msix_one_shot;
+#define	VXGE_HW_SRPCIM_CLR_MSIX_ONE_SHOT_SRPCIM_CLR_MSIX_ONE_SHOT	BIT(0)
+/*0x002c0*/	u64	srpcim_rst_in_prog;
+#define	VXGE_HW_SRPCIM_RST_IN_PROG_SRPCIM_RST_IN_PROG	BIT(7)
+/*0x002c8*/	u64	srpcim_reg_modified;
+#define	VXGE_HW_SRPCIM_REG_MODIFIED_SRPCIM_REG_MODIFIED	BIT(7)
+/*0x002d0*/	u64	tgt_pf_illegal_access;
+#define VXGE_HW_TGT_PF_ILLEGAL_ACCESS_SWIF_REGION(val) vxge_vBIT(val, 1, 7)
+/*0x002d8*/	u64	srpcim_msix_status;
+#define	VXGE_HW_SRPCIM_MSIX_STATUS_INTCTL_SRPCIM_MSIX_MASK	BIT(3)
+#define	VXGE_HW_SRPCIM_MSIX_STATUS_INTCTL_SRPCIM_MSIX_PENDING_VECTOR	BIT(7)
+	u8	unused00880[0x00880-0x002e0];
+
+/*0x00880*/	u64	xgmac_sr_int_status;
+#define	VXGE_HW_XGMAC_SR_INT_STATUS_ASIC_NTWK_SR_ERR_ASIC_NTWK_SR_INT	BIT(3)
+/*0x00888*/	u64	xgmac_sr_int_mask;
+/*0x00890*/	u64	asic_ntwk_sr_err_reg;
+#define	VXGE_HW_ASIC_NTWK_SR_ERR_REG_XMACJ_NTWK_SUSTAINED_FAULT	BIT(3)
+#define	VXGE_HW_ASIC_NTWK_SR_ERR_REG_XMACJ_NTWK_SUSTAINED_OK	BIT(7)
+#define	VXGE_HW_ASIC_NTWK_SR_ERR_REG_XMACJ_NTWK_SUSTAINED_FAULT_OCCURRED \
+									BIT(11)
+#define	VXGE_HW_ASIC_NTWK_SR_ERR_REG_XMACJ_NTWK_SUSTAINED_OK_OCCURRED	BIT(15)
+/*0x00898*/	u64	asic_ntwk_sr_err_mask;
+/*0x008a0*/	u64	asic_ntwk_sr_err_alarm;
+	u8	unused008c0[0x008c0-0x008a8];
+
+/*0x008c0*/	u64	xmac_vsport_choices_sr_clone;
+#define	VXGE_HW_XMAC_VSPORT_CHOICES_SR_CLONE_VSPORT_VECTOR(val) \
+							vxge_vBIT(val, 0, 17)
+	u8	unused00900[0x00900-0x008c8];
+
+/*0x00900*/	u64	mr_rqa_top_prty_for_vh;
+#define	VXGE_HW_MR_RQA_TOP_PRTY_FOR_VH_RQA_TOP_PRTY_FOR_VH(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00908*/	u64	umq_vh_data_list_empty;
+#define	VXGE_HW_UMQ_VH_DATA_LIST_EMPTY_ROCRC_UMQ_VH_DATA_LIST_EMPTY \
+							BIT(0)
+/*0x00910*/	u64	wde_cfg;
+#define	VXGE_HW_WDE_CFG_NS0_FORCE_MWB_START	BIT(0)
+#define	VXGE_HW_WDE_CFG_NS0_FORCE_MWB_END	BIT(1)
+#define	VXGE_HW_WDE_CFG_NS0_FORCE_QB_START	BIT(2)
+#define	VXGE_HW_WDE_CFG_NS0_FORCE_QB_END	BIT(3)
+#define	VXGE_HW_WDE_CFG_NS0_FORCE_MPSB_START	BIT(4)
+#define	VXGE_HW_WDE_CFG_NS0_FORCE_MPSB_END	BIT(5)
+#define	VXGE_HW_WDE_CFG_NS0_MWB_OPT_EN	BIT(6)
+#define	VXGE_HW_WDE_CFG_NS0_QB_OPT_EN	BIT(7)
+#define	VXGE_HW_WDE_CFG_NS0_MPSB_OPT_EN	BIT(8)
+#define	VXGE_HW_WDE_CFG_NS1_FORCE_MWB_START	BIT(9)
+#define	VXGE_HW_WDE_CFG_NS1_FORCE_MWB_END	BIT(10)
+#define	VXGE_HW_WDE_CFG_NS1_FORCE_QB_START	BIT(11)
+#define	VXGE_HW_WDE_CFG_NS1_FORCE_QB_END	BIT(12)
+#define	VXGE_HW_WDE_CFG_NS1_FORCE_MPSB_START	BIT(13)
+#define	VXGE_HW_WDE_CFG_NS1_FORCE_MPSB_END	BIT(14)
+#define	VXGE_HW_WDE_CFG_NS1_MWB_OPT_EN	BIT(15)
+#define	VXGE_HW_WDE_CFG_NS1_QB_OPT_EN	BIT(16)
+#define	VXGE_HW_WDE_CFG_NS1_MPSB_OPT_EN	BIT(17)
+#define	VXGE_HW_WDE_CFG_DISABLE_QPAD_FOR_UNALIGNED_ADDR	BIT(19)
+#define VXGE_HW_WDE_CFG_ALIGNMENT_PREFERENCE(val) vxge_vBIT(val, 30, 2)
+#define VXGE_HW_WDE_CFG_MEM_WORD_SIZE(val) vxge_vBIT(val, 46, 2)
+
+} __packed;
+
+/*VXGE_HW_VPMGMT_REGS_H*/
+struct vxge_hw_vpmgmt_reg {
+
+	u8	unused00040[0x00040-0x00000];
+
+/*0x00040*/	u64	vpath_to_func_map_cfg1;
+#define	VXGE_HW_VPATH_TO_FUNC_MAP_CFG1_VPATH_TO_FUNC_MAP_CFG1(val) \
+							vxge_vBIT(val, 3, 5)
+/*0x00048*/	u64	vpath_is_first;
+#define	VXGE_HW_VPATH_IS_FIRST_VPATH_IS_FIRST	vxge_mBIT(3)
+/*0x00050*/	u64	srpcim_to_vpath_wmsg;
+#define	VXGE_HW_SRPCIM_TO_VPATH_WMSG_SRPCIM_TO_VPATH_WMSG(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x00058*/	u64	srpcim_to_vpath_wmsg_trig;
+#define	VXGE_HW_SRPCIM_TO_VPATH_WMSG_TRIG_SRPCIM_TO_VPATH_WMSG_TRIG \
+								vxge_mBIT(0)
+	u8	unused00100[0x00100-0x00060];
+
+/*0x00100*/	u64	tim_vpath_assignment;
+#define VXGE_HW_TIM_VPATH_ASSIGNMENT_BMAP_ROOT(val) vxge_vBIT(val, 0, 32)
+	u8	unused00140[0x00140-0x00108];
+
+/*0x00140*/	u64	rqa_top_prty_for_vp;
+#define VXGE_HW_RQA_TOP_PRTY_FOR_VP_RQA_TOP_PRTY_FOR_VP(val) \
+							vxge_vBIT(val, 59, 5)
+	u8	unused001c0[0x001c0-0x00148];
+
+/*0x001c0*/	u64	rxmac_rx_pa_cfg0_vpmgmt_clone;
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_IGNORE_FRAME_ERR	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_SUPPORT_SNAP_AB_N	vxge_mBIT(7)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_SEARCH_FOR_HAO	vxge_mBIT(18)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_SUPPORT_MOBILE_IPV6_HDRS \
+								vxge_mBIT(19)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_IPV6_STOP_SEARCHING \
+								vxge_mBIT(23)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_NO_PS_IF_UNKNOWN	vxge_mBIT(27)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_SEARCH_FOR_ETYPE	vxge_mBIT(35)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_TOSS_ANY_FRM_IF_L3_CSUM_ERR \
+								vxge_mBIT(39)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_TOSS_OFFLD_FRM_IF_L3_CSUM_ERR \
+								vxge_mBIT(43)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_TOSS_ANY_FRM_IF_L4_CSUM_ERR \
+								vxge_mBIT(47)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_TOSS_OFFLD_FRM_IF_L4_CSUM_ERR \
+								vxge_mBIT(51)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_TOSS_ANY_FRM_IF_RPA_ERR \
+								vxge_mBIT(55)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_TOSS_OFFLD_FRM_IF_RPA_ERR \
+								vxge_mBIT(59)
+#define	VXGE_HW_RXMAC_RX_PA_CFG0_VPMGMT_CLONE_JUMBO_SNAP_EN	vxge_mBIT(63)
+/*0x001c8*/	u64	rts_mgr_cfg0_vpmgmt_clone;
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_RTS_DP_SP_PRIORITY	vxge_mBIT(3)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_FLEX_L4PRTCL_VALUE(val) \
+							vxge_vBIT(val, 24, 8)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_ICMP_TRASH	vxge_mBIT(35)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_TCPSYN_TRASH	vxge_mBIT(39)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_ZL4PYLD_TRASH	vxge_mBIT(43)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_L4PRTCL_TCP_TRASH	vxge_mBIT(47)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_L4PRTCL_UDP_TRASH	vxge_mBIT(51)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_L4PRTCL_FLEX_TRASH	vxge_mBIT(55)
+#define	VXGE_HW_RTS_MGR_CFG0_VPMGMT_CLONE_IPFRAG_TRASH	vxge_mBIT(59)
+/*0x001d0*/	u64	rts_mgr_criteria_priority_vpmgmt_clone;
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_ETYPE(val) \
+							vxge_vBIT(val, 5, 3)
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_ICMP_TCPSYN(val) \
+							vxge_vBIT(val, 9, 3)
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_L4PN(val) \
+							vxge_vBIT(val, 13, 3)
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_RANGE_L4PN(val) \
+							vxge_vBIT(val, 17, 3)
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_RTH_IT(val) \
+							vxge_vBIT(val, 21, 3)
+#define VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_DS(val) \
+							vxge_vBIT(val, 25, 3)
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_QOS(val) \
+							vxge_vBIT(val, 29, 3)
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_ZL4PYLD(val) \
+							vxge_vBIT(val, 33, 3)
+#define	VXGE_HW_RTS_MGR_CRITERIA_PRIORITY_VPMGMT_CLONE_L4PRTCL(val) \
+							vxge_vBIT(val, 37, 3)
+/*0x001d8*/	u64	rxmac_cfg0_port_vpmgmt_clone[3];
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_RMAC_EN	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_STRIP_FCS	vxge_mBIT(7)
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_DISCARD_PFRM	vxge_mBIT(11)
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_IGNORE_FCS_ERR	vxge_mBIT(15)
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_IGNORE_LONG_ERR	vxge_mBIT(19)
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_IGNORE_USIZED_ERR	vxge_mBIT(23)
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_IGNORE_LEN_MISMATCH \
+								vxge_mBIT(27)
+#define	VXGE_HW_RXMAC_CFG0_PORT_VPMGMT_CLONE_MAX_PYLD_LEN(val) \
+							vxge_vBIT(val, 50, 14)
+/*0x001f0*/	u64	rxmac_pause_cfg_port_vpmgmt_clone[3];
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_GEN_EN	vxge_mBIT(3)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_RCV_EN	vxge_mBIT(7)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_ACCEL_SEND(val) \
+							vxge_vBIT(val, 9, 3)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_DUAL_THR	vxge_mBIT(15)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_HIGH_PTIME(val) \
+							vxge_vBIT(val, 20, 16)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_IGNORE_PF_FCS_ERR \
+								vxge_mBIT(39)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_IGNORE_PF_LEN_ERR \
+								vxge_mBIT(43)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_LIMITER_EN	vxge_mBIT(47)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_MAX_LIMIT(val) \
+							vxge_vBIT(val, 48, 8)
+#define	VXGE_HW_RXMAC_PAUSE_CFG_PORT_VPMGMT_CLONE_PERMIT_RATEMGMT_CTRL \
+							vxge_mBIT(59)
+	u8	unused00240[0x00240-0x00208];
+
+/*0x00240*/	u64	xmac_vsport_choices_vp;
+#define VXGE_HW_XMAC_VSPORT_CHOICES_VP_VSPORT_VECTOR(val) vxge_vBIT(val, 0, 17)
+	u8	unused00260[0x00260-0x00248];
+
+/*0x00260*/	u64	xgmac_gen_status_vpmgmt_clone;
+#define	VXGE_HW_XGMAC_GEN_STATUS_VPMGMT_CLONE_XMACJ_NTWK_OK	vxge_mBIT(3)
+#define	VXGE_HW_XGMAC_GEN_STATUS_VPMGMT_CLONE_XMACJ_NTWK_DATA_RATE \
+								vxge_mBIT(11)
+/*0x00268*/	u64	xgmac_status_port_vpmgmt_clone[2];
+#define	VXGE_HW_XGMAC_STATUS_PORT_VPMGMT_CLONE_RMAC_REMOTE_FAULT \
+								vxge_mBIT(3)
+#define	VXGE_HW_XGMAC_STATUS_PORT_VPMGMT_CLONE_RMAC_LOCAL_FAULT	vxge_mBIT(7)
+#define	VXGE_HW_XGMAC_STATUS_PORT_VPMGMT_CLONE_XMACJ_MAC_PHY_LAYER_AVAIL \
+								vxge_mBIT(11)
+#define	VXGE_HW_XGMAC_STATUS_PORT_VPMGMT_CLONE_XMACJ_PORT_OK	vxge_mBIT(15)
+/*0x00278*/	u64	xmac_gen_cfg_vpmgmt_clone;
+#define	VXGE_HW_XMAC_GEN_CFG_VPMGMT_CLONE_RATEMGMT_MAC_RATE_SEL(val) \
+							vxge_vBIT(val, 2, 2)
+#define	VXGE_HW_XMAC_GEN_CFG_VPMGMT_CLONE_TX_HEAD_DROP_WHEN_FAULT \
+							vxge_mBIT(7)
+#define	VXGE_HW_XMAC_GEN_CFG_VPMGMT_CLONE_FAULT_BEHAVIOUR	vxge_mBIT(27)
+#define VXGE_HW_XMAC_GEN_CFG_VPMGMT_CLONE_PERIOD_NTWK_UP(val) \
+							vxge_vBIT(val, 28, 4)
+#define	VXGE_HW_XMAC_GEN_CFG_VPMGMT_CLONE_PERIOD_NTWK_DOWN(val) \
+							vxge_vBIT(val, 32, 4)
+/*0x00280*/	u64	xmac_timestamp_vpmgmt_clone;
+#define	VXGE_HW_XMAC_TIMESTAMP_VPMGMT_CLONE_EN	vxge_mBIT(3)
+#define VXGE_HW_XMAC_TIMESTAMP_VPMGMT_CLONE_USE_LINK_ID(val) \
+							vxge_vBIT(val, 6, 2)
+#define VXGE_HW_XMAC_TIMESTAMP_VPMGMT_CLONE_INTERVAL(val) vxge_vBIT(val, 12, 4)
+#define	VXGE_HW_XMAC_TIMESTAMP_VPMGMT_CLONE_TIMER_RESTART	vxge_mBIT(19)
+#define	VXGE_HW_XMAC_TIMESTAMP_VPMGMT_CLONE_XMACJ_ROLLOVER_CNT(val) \
+							vxge_vBIT(val, 32, 16)
+/*0x00288*/	u64	xmac_stats_gen_cfg_vpmgmt_clone;
+#define	VXGE_HW_XMAC_STATS_GEN_CFG_VPMGMT_CLONE_PRTAGGR_CUM_TIMER(val) \
+							vxge_vBIT(val, 4, 4)
+#define	VXGE_HW_XMAC_STATS_GEN_CFG_VPMGMT_CLONE_VPATH_CUM_TIMER(val) \
+							vxge_vBIT(val, 8, 4)
+#define	VXGE_HW_XMAC_STATS_GEN_CFG_VPMGMT_CLONE_VLAN_HANDLING	vxge_mBIT(15)
+/*0x00290*/	u64	xmac_cfg_port_vpmgmt_clone[3];
+#define	VXGE_HW_XMAC_CFG_PORT_VPMGMT_CLONE_XGMII_LOOPBACK	vxge_mBIT(3)
+#define	VXGE_HW_XMAC_CFG_PORT_VPMGMT_CLONE_XGMII_REVERSE_LOOPBACK \
+								vxge_mBIT(7)
+#define	VXGE_HW_XMAC_CFG_PORT_VPMGMT_CLONE_XGMII_TX_BEHAV	vxge_mBIT(11)
+#define	VXGE_HW_XMAC_CFG_PORT_VPMGMT_CLONE_XGMII_RX_BEHAV	vxge_mBIT(15)
+	u8	unused002c0[0x002c0-0x002a8];
+
+/*0x002c0*/	u64	txmac_gen_cfg0_vpmgmt_clone;
+#define	VXGE_HW_TXMAC_GEN_CFG0_VPMGMT_CLONE_CHOSEN_TX_PORT	vxge_mBIT(7)
+/*0x002c8*/	u64	txmac_cfg0_port_vpmgmt_clone[3];
+#define	VXGE_HW_TXMAC_CFG0_PORT_VPMGMT_CLONE_TMAC_EN	vxge_mBIT(3)
+#define	VXGE_HW_TXMAC_CFG0_PORT_VPMGMT_CLONE_APPEND_PAD	vxge_mBIT(7)
+#define VXGE_HW_TXMAC_CFG0_PORT_VPMGMT_CLONE_PAD_BYTE(val) vxge_vBIT(val, 8, 8)
+	u8	unused00300[0x00300-0x002e0];
+
+/*0x00300*/	u64	wol_mp_crc;
+#define VXGE_HW_WOL_MP_CRC_CRC(val) vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_WOL_MP_CRC_RC_EN	vxge_mBIT(63)
+/*0x00308*/	u64	wol_mp_mask_a;
+#define VXGE_HW_WOL_MP_MASK_A_MASK(val) vxge_vBIT(val, 0, 64)
+/*0x00310*/	u64	wol_mp_mask_b;
+#define VXGE_HW_WOL_MP_MASK_B_MASK(val) vxge_vBIT(val, 0, 64)
+	u8	unused00360[0x00360-0x00318];
+
+/*0x00360*/	u64	fau_pa_cfg_vpmgmt_clone;
+#define	VXGE_HW_FAU_PA_CFG_VPMGMT_CLONE_REPL_L4_COMP_CSUM	vxge_mBIT(3)
+#define	VXGE_HW_FAU_PA_CFG_VPMGMT_CLONE_REPL_L3_INCL_CF	vxge_mBIT(7)
+#define	VXGE_HW_FAU_PA_CFG_VPMGMT_CLONE_REPL_L3_COMP_CSUM	vxge_mBIT(11)
+/*0x00368*/	u64	rx_datapath_util_vp_clone;
+#define	VXGE_HW_RX_DATAPATH_UTIL_VP_CLONE_FAU_RX_UTILIZATION(val) \
+							vxge_vBIT(val, 7, 9)
+#define	VXGE_HW_RX_DATAPATH_UTIL_VP_CLONE_RX_UTIL_CFG(val) \
+							vxge_vBIT(val, 16, 4)
+#define	VXGE_HW_RX_DATAPATH_UTIL_VP_CLONE_FAU_RX_FRAC_UTIL(val) \
+							vxge_vBIT(val, 20, 4)
+#define	VXGE_HW_RX_DATAPATH_UTIL_VP_CLONE_RX_PKT_WEIGHT(val) \
+							vxge_vBIT(val, 24, 4)
+	u8	unused00380[0x00380-0x00370];
+
+/*0x00380*/	u64	tx_datapath_util_vp_clone;
+#define	VXGE_HW_TX_DATAPATH_UTIL_VP_CLONE_TPA_TX_UTILIZATION(val) \
+							vxge_vBIT(val, 7, 9)
+#define	VXGE_HW_TX_DATAPATH_UTIL_VP_CLONE_TX_UTIL_CFG(val) \
+							vxge_vBIT(val, 16, 4)
+#define	VXGE_HW_TX_DATAPATH_UTIL_VP_CLONE_TPA_TX_FRAC_UTIL(val) \
+							vxge_vBIT(val, 20, 4)
+#define	VXGE_HW_TX_DATAPATH_UTIL_VP_CLONE_TX_PKT_WEIGHT(val) \
+							vxge_vBIT(val, 24, 4)
+
+} __packed;
+
+struct vxge_hw_vpath_reg {
+
+	u8	unused00300[0x00300];
+
+/*0x00300*/	u64	usdc_vpath;
+#define VXGE_HW_USDC_VPATH_SGRP_ASSIGN(val) vxge_vBIT(val, 0, 32)
+	u8	unused00a00[0x00a00-0x00308];
+
+/*0x00a00*/	u64	wrdma_alarm_status;
+#define	VXGE_HW_WRDMA_ALARM_STATUS_PRC_ALARM_PRC_INT	vxge_mBIT(1)
+/*0x00a08*/	u64	wrdma_alarm_mask;
+	u8	unused00a30[0x00a30-0x00a10];
+
+/*0x00a30*/	u64	prc_alarm_reg;
+#define	VXGE_HW_PRC_ALARM_REG_PRC_RING_BUMP	vxge_mBIT(0)
+#define	VXGE_HW_PRC_ALARM_REG_PRC_RXDCM_SC_ERR	vxge_mBIT(1)
+#define	VXGE_HW_PRC_ALARM_REG_PRC_RXDCM_SC_ABORT	vxge_mBIT(2)
+#define	VXGE_HW_PRC_ALARM_REG_PRC_QUANTA_SIZE_ERR	vxge_mBIT(3)
+/*0x00a38*/	u64	prc_alarm_mask;
+/*0x00a40*/	u64	prc_alarm_alarm;
+/*0x00a48*/	u64	prc_cfg1;
+#define VXGE_HW_PRC_CFG1_RX_TIMER_VAL(val) vxge_vBIT(val, 3, 29)
+#define	VXGE_HW_PRC_CFG1_TIM_RING_BUMP_INT_ENABLE	vxge_mBIT(34)
+#define	VXGE_HW_PRC_CFG1_RTI_TINT_DISABLE	vxge_mBIT(35)
+#define	VXGE_HW_PRC_CFG1_GREEDY_RETURN	vxge_mBIT(36)
+#define	VXGE_HW_PRC_CFG1_QUICK_SHOT	vxge_mBIT(37)
+#define	VXGE_HW_PRC_CFG1_RX_TIMER_CI	vxge_mBIT(39)
+#define VXGE_HW_PRC_CFG1_RESET_TIMER_ON_RXD_RET(val) vxge_vBIT(val, 40, 2)
+	u8	unused00a60[0x00a60-0x00a50];
+
+/*0x00a60*/	u64	prc_cfg4;
+#define	VXGE_HW_PRC_CFG4_IN_SVC	vxge_mBIT(7)
+#define VXGE_HW_PRC_CFG4_RING_MODE(val) vxge_vBIT(val, 14, 2)
+#define	VXGE_HW_PRC_CFG4_RXD_NO_SNOOP	vxge_mBIT(22)
+#define	VXGE_HW_PRC_CFG4_FRM_NO_SNOOP	vxge_mBIT(23)
+#define	VXGE_HW_PRC_CFG4_RTH_DISABLE	vxge_mBIT(31)
+#define	VXGE_HW_PRC_CFG4_IGNORE_OWNERSHIP	vxge_mBIT(32)
+#define	VXGE_HW_PRC_CFG4_SIGNAL_BENIGN_OVFLW	vxge_mBIT(36)
+#define	VXGE_HW_PRC_CFG4_BIMODAL_INTERRUPT	vxge_mBIT(37)
+#define VXGE_HW_PRC_CFG4_BACKOFF_INTERVAL(val) vxge_vBIT(val, 40, 24)
+/*0x00a68*/	u64	prc_cfg5;
+#define VXGE_HW_PRC_CFG5_RXD0_ADD(val) vxge_vBIT(val, 0, 61)
+/*0x00a70*/	u64	prc_cfg6;
+#define	VXGE_HW_PRC_CFG6_FRM_PAD_EN	vxge_mBIT(0)
+#define	VXGE_HW_PRC_CFG6_QSIZE_ALIGNED_RXD	vxge_mBIT(2)
+#define	VXGE_HW_PRC_CFG6_DOORBELL_MODE_EN	vxge_mBIT(5)
+#define	VXGE_HW_PRC_CFG6_L3_CPC_TRSFR_CODE_EN	vxge_mBIT(8)
+#define	VXGE_HW_PRC_CFG6_L4_CPC_TRSFR_CODE_EN	vxge_mBIT(9)
+#define VXGE_HW_PRC_CFG6_RXD_CRXDT(val) vxge_vBIT(val, 23, 9)
+#define VXGE_HW_PRC_CFG6_RXD_SPAT(val) vxge_vBIT(val, 36, 9)
+/*0x00a78*/	u64	prc_cfg7;
+#define VXGE_HW_PRC_CFG7_SCATTER_MODE(val) vxge_vBIT(val, 6, 2)
+#define	VXGE_HW_PRC_CFG7_SMART_SCAT_EN	vxge_mBIT(11)
+#define	VXGE_HW_PRC_CFG7_RXD_NS_CHG_EN	vxge_mBIT(12)
+#define	VXGE_HW_PRC_CFG7_NO_HDR_SEPARATION	vxge_mBIT(14)
+#define VXGE_HW_PRC_CFG7_RXD_BUFF_SIZE_MASK(val) vxge_vBIT(val, 20, 4)
+#define VXGE_HW_PRC_CFG7_BUFF_SIZE0_MASK(val) vxge_vBIT(val, 27, 5)
+/*0x00a80*/	u64	tim_dest_addr;
+#define VXGE_HW_TIM_DEST_ADDR_TIM_DEST_ADDR(val) vxge_vBIT(val, 0, 64)
+/*0x00a88*/	u64	prc_rxd_doorbell;
+#define VXGE_HW_PRC_RXD_DOORBELL_NEW_QW_CNT(val) vxge_vBIT(val, 48, 16)
+/*0x00a90*/	u64	rqa_prty_for_vp;
+#define VXGE_HW_RQA_PRTY_FOR_VP_RQA_PRTY_FOR_VP(val) vxge_vBIT(val, 59, 5)
+/*0x00a98*/	u64	rxdmem_size;
+#define VXGE_HW_RXDMEM_SIZE_PRC_RXDMEM_SIZE(val) vxge_vBIT(val, 51, 13)
+/*0x00aa0*/	u64	frm_in_progress_cnt;
+#define	VXGE_HW_FRM_IN_PROGRESS_CNT_PRC_FRM_IN_PROGRESS_CNT(val) \
+							vxge_vBIT(val, 59, 5)
+/*0x00aa8*/	u64	rx_multi_cast_stats;
+#define VXGE_HW_RX_MULTI_CAST_STATS_FRAME_DISCARD(val) vxge_vBIT(val, 48, 16)
+/*0x00ab0*/	u64	rx_frm_transferred;
+#define	VXGE_HW_RX_FRM_TRANSFERRED_RX_FRM_TRANSFERRED(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x00ab8*/	u64	rxd_returned;
+#define VXGE_HW_RXD_RETURNED_RXD_RETURNED(val) vxge_vBIT(val, 48, 16)
+	u8	unused00c00[0x00c00-0x00ac0];
+
+/*0x00c00*/	u64	kdfc_fifo_trpl_partition;
+#define VXGE_HW_KDFC_FIFO_TRPL_PARTITION_LENGTH_0(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_FIFO_TRPL_PARTITION_LENGTH_1(val) vxge_vBIT(val, 33, 15)
+#define VXGE_HW_KDFC_FIFO_TRPL_PARTITION_LENGTH_2(val) vxge_vBIT(val, 49, 15)
+/*0x00c08*/	u64	kdfc_fifo_trpl_ctrl;
+#define	VXGE_HW_KDFC_FIFO_TRPL_CTRL_TRIPLET_ENABLE	vxge_mBIT(7)
+/*0x00c10*/	u64	kdfc_trpl_fifo_0_ctrl;
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_MODE(val) vxge_vBIT(val, 14, 2)
+#define	VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_FLIP_EN	vxge_mBIT(22)
+#define	VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_SWAP_EN	vxge_mBIT(23)
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_INT_CTRL(val) vxge_vBIT(val, 26, 2)
+#define	VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_CTRL_STRUC	vxge_mBIT(28)
+#define	VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_ADD_PAD	vxge_mBIT(29)
+#define	VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_NO_SNOOP	vxge_mBIT(30)
+#define	VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_RLX_ORD	vxge_mBIT(31)
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_SELECT(val) vxge_vBIT(val, 32, 8)
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_INT_NO(val) vxge_vBIT(val, 41, 7)
+#define VXGE_HW_KDFC_TRPL_FIFO_0_CTRL_BIT_MAP(val) vxge_vBIT(val, 48, 16)
+/*0x00c18*/	u64	kdfc_trpl_fifo_1_ctrl;
+#define VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_MODE(val) vxge_vBIT(val, 14, 2)
+#define	VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_FLIP_EN	vxge_mBIT(22)
+#define	VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_SWAP_EN	vxge_mBIT(23)
+#define VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_INT_CTRL(val) vxge_vBIT(val, 26, 2)
+#define	VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_CTRL_STRUC	vxge_mBIT(28)
+#define	VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_ADD_PAD	vxge_mBIT(29)
+#define	VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_NO_SNOOP	vxge_mBIT(30)
+#define	VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_RLX_ORD	vxge_mBIT(31)
+#define VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_SELECT(val) vxge_vBIT(val, 32, 8)
+#define VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_INT_NO(val) vxge_vBIT(val, 41, 7)
+#define VXGE_HW_KDFC_TRPL_FIFO_1_CTRL_BIT_MAP(val) vxge_vBIT(val, 48, 16)
+/*0x00c20*/	u64	kdfc_trpl_fifo_2_ctrl;
+#define	VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_FLIP_EN	vxge_mBIT(22)
+#define	VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_SWAP_EN	vxge_mBIT(23)
+#define VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_INT_CTRL(val) vxge_vBIT(val, 26, 2)
+#define	VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_CTRL_STRUC	vxge_mBIT(28)
+#define	VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_ADD_PAD	vxge_mBIT(29)
+#define	VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_NO_SNOOP	vxge_mBIT(30)
+#define	VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_RLX_ORD	vxge_mBIT(31)
+#define VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_SELECT(val) vxge_vBIT(val, 32, 8)
+#define VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_INT_NO(val) vxge_vBIT(val, 41, 7)
+#define VXGE_HW_KDFC_TRPL_FIFO_2_CTRL_BIT_MAP(val) vxge_vBIT(val, 48, 16)
+/*0x00c28*/	u64	kdfc_trpl_fifo_0_wb_address;
+#define VXGE_HW_KDFC_TRPL_FIFO_0_WB_ADDRESS_ADD(val) vxge_vBIT(val, 0, 64)
+/*0x00c30*/	u64	kdfc_trpl_fifo_1_wb_address;
+#define VXGE_HW_KDFC_TRPL_FIFO_1_WB_ADDRESS_ADD(val) vxge_vBIT(val, 0, 64)
+/*0x00c38*/	u64	kdfc_trpl_fifo_2_wb_address;
+#define VXGE_HW_KDFC_TRPL_FIFO_2_WB_ADDRESS_ADD(val) vxge_vBIT(val, 0, 64)
+/*0x00c40*/	u64	kdfc_trpl_fifo_offset;
+#define VXGE_HW_KDFC_TRPL_FIFO_OFFSET_KDFC_RCTR0(val) vxge_vBIT(val, 1, 15)
+#define VXGE_HW_KDFC_TRPL_FIFO_OFFSET_KDFC_RCTR1(val) vxge_vBIT(val, 17, 15)
+#define VXGE_HW_KDFC_TRPL_FIFO_OFFSET_KDFC_RCTR2(val) vxge_vBIT(val, 33, 15)
+/*0x00c48*/	u64	kdfc_drbl_triplet_total;
+#define	VXGE_HW_KDFC_DRBL_TRIPLET_TOTAL_KDFC_MAX_SIZE(val) \
+							vxge_vBIT(val, 17, 15)
+	u8	unused00c60[0x00c60-0x00c50];
+
+/*0x00c60*/	u64	usdc_drbl_ctrl;
+#define	VXGE_HW_USDC_DRBL_CTRL_FLIP_EN	vxge_mBIT(22)
+#define	VXGE_HW_USDC_DRBL_CTRL_SWAP_EN	vxge_mBIT(23)
+/*0x00c68*/	u64	usdc_vp_ready;
+#define	VXGE_HW_USDC_VP_READY_USDC_HTN_READY	vxge_mBIT(7)
+#define	VXGE_HW_USDC_VP_READY_USDC_SRQ_READY	vxge_mBIT(15)
+#define	VXGE_HW_USDC_VP_READY_USDC_CQRQ_READY	vxge_mBIT(23)
+/*0x00c70*/	u64	kdfc_status;
+#define	VXGE_HW_KDFC_STATUS_KDFC_WRR_0_READY	vxge_mBIT(0)
+#define	VXGE_HW_KDFC_STATUS_KDFC_WRR_1_READY	vxge_mBIT(1)
+#define	VXGE_HW_KDFC_STATUS_KDFC_WRR_2_READY	vxge_mBIT(2)
+	u8	unused00c80[0x00c80-0x00c78];
+
+/*0x00c80*/	u64	xmac_rpa_vcfg;
+#define	VXGE_HW_XMAC_RPA_VCFG_IPV4_TCP_INCL_PH	vxge_mBIT(3)
+#define	VXGE_HW_XMAC_RPA_VCFG_IPV6_TCP_INCL_PH	vxge_mBIT(7)
+#define	VXGE_HW_XMAC_RPA_VCFG_IPV4_UDP_INCL_PH	vxge_mBIT(11)
+#define	VXGE_HW_XMAC_RPA_VCFG_IPV6_UDP_INCL_PH	vxge_mBIT(15)
+#define	VXGE_HW_XMAC_RPA_VCFG_L4_INCL_CF	vxge_mBIT(19)
+#define	VXGE_HW_XMAC_RPA_VCFG_STRIP_VLAN_TAG	vxge_mBIT(23)
+/*0x00c88*/	u64	rxmac_vcfg0;
+#define VXGE_HW_RXMAC_VCFG0_RTS_MAX_FRM_LEN(val) vxge_vBIT(val, 2, 14)
+#define	VXGE_HW_RXMAC_VCFG0_RTS_USE_MIN_LEN	vxge_mBIT(19)
+#define VXGE_HW_RXMAC_VCFG0_RTS_MIN_FRM_LEN(val) vxge_vBIT(val, 26, 14)
+#define	VXGE_HW_RXMAC_VCFG0_UCAST_ALL_ADDR_EN	vxge_mBIT(43)
+#define	VXGE_HW_RXMAC_VCFG0_MCAST_ALL_ADDR_EN	vxge_mBIT(47)
+#define	VXGE_HW_RXMAC_VCFG0_BCAST_EN	vxge_mBIT(51)
+#define	VXGE_HW_RXMAC_VCFG0_ALL_VID_EN	vxge_mBIT(55)
+/*0x00c90*/	u64	rxmac_vcfg1;
+#define VXGE_HW_RXMAC_VCFG1_RTS_RTH_MULTI_IT_BD_MODE(val) vxge_vBIT(val, 42, 2)
+#define	VXGE_HW_RXMAC_VCFG1_RTS_RTH_MULTI_IT_EN_MODE	vxge_mBIT(47)
+#define	VXGE_HW_RXMAC_VCFG1_CONTRIB_L2_FLOW	vxge_mBIT(51)
+/*0x00c98*/	u64	rts_access_steer_ctrl;
+#define VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION(val) vxge_vBIT(val, 1, 7)
+#define VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL(val) vxge_vBIT(val, 8, 4)
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_STROBE	vxge_mBIT(15)
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_BEHAV_TBL_SEL	vxge_mBIT(23)
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_TABLE_SEL	vxge_mBIT(27)
+#define	VXGE_HW_RTS_ACCESS_STEER_CTRL_RMACJ_STATUS	vxge_mBIT(0)
+#define VXGE_HW_RTS_ACCESS_STEER_CTRL_OFFSET(val) vxge_vBIT(val, 40, 8)
+/*0x00ca0*/	u64	rts_access_steer_data0;
+#define VXGE_HW_RTS_ACCESS_STEER_DATA0_DATA(val) vxge_vBIT(val, 0, 64)
+/*0x00ca8*/	u64	rts_access_steer_data1;
+#define VXGE_HW_RTS_ACCESS_STEER_DATA1_DATA(val) vxge_vBIT(val, 0, 64)
+	u8	unused00d00[0x00d00-0x00cb0];
+
+/*0x00d00*/	u64	xmac_vsport_choice;
+#define VXGE_HW_XMAC_VSPORT_CHOICE_VSPORT_NUMBER(val) vxge_vBIT(val, 3, 5)
+/*0x00d08*/	u64	xmac_stats_cfg;
+/*0x00d10*/	u64	xmac_stats_access_cmd;
+#define VXGE_HW_XMAC_STATS_ACCESS_CMD_OP(val) vxge_vBIT(val, 6, 2)
+#define	VXGE_HW_XMAC_STATS_ACCESS_CMD_STROBE	vxge_mBIT(15)
+#define VXGE_HW_XMAC_STATS_ACCESS_CMD_OFFSET_SEL(val) vxge_vBIT(val, 32, 8)
+/*0x00d18*/	u64	xmac_stats_access_data;
+#define VXGE_HW_XMAC_STATS_ACCESS_DATA_XSMGR_DATA(val) vxge_vBIT(val, 0, 64)
+/*0x00d20*/	u64	asic_ntwk_vp_ctrl;
+#define	VXGE_HW_ASIC_NTWK_VP_CTRL_REQ_TEST_NTWK	vxge_mBIT(3)
+#define	VXGE_HW_ASIC_NTWK_VP_CTRL_XMACJ_SHOW_PORT_INFO	vxge_mBIT(55)
+#define	VXGE_HW_ASIC_NTWK_VP_CTRL_XMACJ_PORT_NUM	vxge_mBIT(63)
+	u8	unused00d30[0x00d30-0x00d28];
+
+/*0x00d30*/	u64	xgmac_vp_int_status;
+#define	VXGE_HW_XGMAC_VP_INT_STATUS_ASIC_NTWK_VP_ERR_ASIC_NTWK_VP_INT \
+								vxge_mBIT(3)
+/*0x00d38*/	u64	xgmac_vp_int_mask;
+/*0x00d40*/	u64	asic_ntwk_vp_err_reg;
+#define	VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT	vxge_mBIT(3)
+#define	VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK	vxge_mBIT(7)
+#define	VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT_OCCURR \
+								vxge_mBIT(11)
+#define	VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK_OCCURR \
+							vxge_mBIT(15)
+#define	VXGE_HW_ASIC_NTWK_VP_ERR_REG_XMACJ_NTWK_REAFFIRMED_FAULT \
+							vxge_mBIT(19)
+#define	VXGE_HW_ASIC_NTWK_VP_ERR_REG_XMACJ_NTWK_REAFFIRMED_OK	vxge_mBIT(23)
+/*0x00d48*/	u64	asic_ntwk_vp_err_mask;
+/*0x00d50*/	u64	asic_ntwk_vp_err_alarm;
+	u8	unused00d80[0x00d80-0x00d58];
+
+/*0x00d80*/	u64	rtdma_bw_ctrl;
+#define	VXGE_HW_RTDMA_BW_CTRL_BW_CTRL_EN	vxge_mBIT(39)
+#define VXGE_HW_RTDMA_BW_CTRL_DESIRED_BW(val) vxge_vBIT(val, 46, 18)
+/*0x00d88*/	u64	rtdma_rd_optimization_ctrl;
+#define	VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_GEN_INT_AFTER_ABORT	vxge_mBIT(3)
+#define VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_PAD_MODE(val) vxge_vBIT(val, 6, 2)
+#define VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_PAD_PATTERN(val) vxge_vBIT(val, 8, 8)
+#define	VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_WAIT_FOR_SPACE	vxge_mBIT(19)
+#define VXGE_HW_PCI_EXP_DEVCTL_READRQ   0x7000  /* Max_Read_Request_Size */
+#define VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_FILL_THRESH(val) \
+							vxge_vBIT(val, 21, 3)
+#define	VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_TXD_PYLD_WMARK_EN	vxge_mBIT(28)
+#define VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_TXD_PYLD_WMARK(val) \
+							vxge_vBIT(val, 29, 3)
+#define	VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_ADDR_BDRY_EN	vxge_mBIT(35)
+#define VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_FB_ADDR_BDRY(val) \
+							vxge_vBIT(val, 37, 3)
+#define	VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_TXD_WAIT_FOR_SPACE	vxge_mBIT(43)
+#define	VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_TXD_FILL_THRESH(val) \
+							vxge_vBIT(val, 51, 5)
+#define	VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_TXD_ADDR_BDRY_EN	vxge_mBIT(59)
+#define VXGE_HW_RTDMA_RD_OPTIMIZATION_CTRL_TXD_ADDR_BDRY(val) \
+							vxge_vBIT(val, 61, 3)
+/*0x00d90*/	u64	pda_pcc_job_monitor;
+#define	VXGE_HW_PDA_PCC_JOB_MONITOR_PDA_PCC_JOB_STATUS	vxge_mBIT(7)
+/*0x00d98*/	u64	tx_protocol_assist_cfg;
+#define	VXGE_HW_TX_PROTOCOL_ASSIST_CFG_LSOV2_EN	vxge_mBIT(6)
+#define	VXGE_HW_TX_PROTOCOL_ASSIST_CFG_IPV6_KEEP_SEARCHING	vxge_mBIT(7)
+	u8	unused01000[0x01000-0x00da0];
+
+/*0x01000*/	u64	tim_cfg1_int_num[4];
+#define VXGE_HW_TIM_CFG1_INT_NUM_BTIMER_VAL(val) vxge_vBIT(val, 6, 26)
+#define	VXGE_HW_TIM_CFG1_INT_NUM_BITMP_EN	vxge_mBIT(35)
+#define	VXGE_HW_TIM_CFG1_INT_NUM_TXFRM_CNT_EN	vxge_mBIT(36)
+#define	VXGE_HW_TIM_CFG1_INT_NUM_TXD_CNT_EN	vxge_mBIT(37)
+#define	VXGE_HW_TIM_CFG1_INT_NUM_TIMER_AC	vxge_mBIT(38)
+#define	VXGE_HW_TIM_CFG1_INT_NUM_TIMER_CI	vxge_mBIT(39)
+#define VXGE_HW_TIM_CFG1_INT_NUM_URNG_A(val) vxge_vBIT(val, 41, 7)
+#define VXGE_HW_TIM_CFG1_INT_NUM_URNG_B(val) vxge_vBIT(val, 49, 7)
+#define VXGE_HW_TIM_CFG1_INT_NUM_URNG_C(val) vxge_vBIT(val, 57, 7)
+/*0x01020*/	u64	tim_cfg2_int_num[4];
+#define VXGE_HW_TIM_CFG2_INT_NUM_UEC_A(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_TIM_CFG2_INT_NUM_UEC_B(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_TIM_CFG2_INT_NUM_UEC_C(val) vxge_vBIT(val, 32, 16)
+#define VXGE_HW_TIM_CFG2_INT_NUM_UEC_D(val) vxge_vBIT(val, 48, 16)
+/*0x01040*/	u64	tim_cfg3_int_num[4];
+#define	VXGE_HW_TIM_CFG3_INT_NUM_TIMER_RI	vxge_mBIT(0)
+#define VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_EVENT_SF(val) vxge_vBIT(val, 1, 4)
+#define VXGE_HW_TIM_CFG3_INT_NUM_RTIMER_VAL(val) vxge_vBIT(val, 6, 26)
+#define VXGE_HW_TIM_CFG3_INT_NUM_UTIL_SEL(val) vxge_vBIT(val, 32, 6)
+#define VXGE_HW_TIM_CFG3_INT_NUM_LTIMER_VAL(val) vxge_vBIT(val, 38, 26)
+/*0x01060*/	u64	tim_wrkld_clc;
+#define VXGE_HW_TIM_WRKLD_CLC_WRKLD_EVAL_PRD(val) vxge_vBIT(val, 0, 32)
+#define VXGE_HW_TIM_WRKLD_CLC_WRKLD_EVAL_DIV(val) vxge_vBIT(val, 35, 5)
+#define	VXGE_HW_TIM_WRKLD_CLC_CNT_FRM_BYTE	vxge_mBIT(40)
+#define VXGE_HW_TIM_WRKLD_CLC_CNT_RX_TX(val) vxge_vBIT(val, 41, 2)
+#define	VXGE_HW_TIM_WRKLD_CLC_CNT_LNK_EN	vxge_mBIT(43)
+#define VXGE_HW_TIM_WRKLD_CLC_HOST_UTIL(val) vxge_vBIT(val, 57, 7)
+/*0x01068*/	u64	tim_bitmap;
+#define VXGE_HW_TIM_BITMAP_MASK(val) vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_TIM_BITMAP_LLROOT_RXD_EN	vxge_mBIT(32)
+#define	VXGE_HW_TIM_BITMAP_LLROOT_TXD_EN	vxge_mBIT(33)
+/*0x01070*/	u64	tim_ring_assn;
+#define VXGE_HW_TIM_RING_ASSN_INT_NUM(val) vxge_vBIT(val, 6, 2)
+/*0x01078*/	u64	tim_remap;
+#define	VXGE_HW_TIM_REMAP_TX_EN	vxge_mBIT(5)
+#define	VXGE_HW_TIM_REMAP_RX_EN	vxge_mBIT(6)
+#define	VXGE_HW_TIM_REMAP_OFFLOAD_EN	vxge_mBIT(7)
+#define VXGE_HW_TIM_REMAP_TO_VPATH_NUM(val) vxge_vBIT(val, 11, 5)
+/*0x01080*/	u64	tim_vpath_map;
+#define VXGE_HW_TIM_VPATH_MAP_BMAP_ROOT(val) vxge_vBIT(val, 0, 32)
+/*0x01088*/	u64	tim_pci_cfg;
+#define	VXGE_HW_TIM_PCI_CFG_ADD_PAD	vxge_mBIT(7)
+#define	VXGE_HW_TIM_PCI_CFG_NO_SNOOP	vxge_mBIT(15)
+#define	VXGE_HW_TIM_PCI_CFG_RELAXED	vxge_mBIT(23)
+#define	VXGE_HW_TIM_PCI_CFG_CTL_STR	vxge_mBIT(31)
+	u8	unused01100[0x01100-0x01090];
+
+/*0x01100*/	u64	sgrp_assign;
+#define VXGE_HW_SGRP_ASSIGN_SGRP_ASSIGN(val) vxge_vBIT(val, 0, 64)
+/*0x01108*/	u64	sgrp_aoa_and_result;
+#define	VXGE_HW_SGRP_AOA_AND_RESULT_PET_SGRP_AOA_AND_RESULT(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x01110*/	u64	rpe_pci_cfg;
+#define	VXGE_HW_RPE_PCI_CFG_PAD_LRO_DATA_ENABLE	vxge_mBIT(7)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_LRO_HDR_ENABLE	vxge_mBIT(8)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_LRO_CQE_ENABLE	vxge_mBIT(9)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_NONLL_CQE_ENABLE	vxge_mBIT(10)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_BASE_LL_CQE_ENABLE	vxge_mBIT(11)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_LL_CQE_IDATA_ENABLE	vxge_mBIT(12)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_CQRQ_IR_ENABLE	vxge_mBIT(13)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_CQSQ_IR_ENABLE	vxge_mBIT(14)
+#define	VXGE_HW_RPE_PCI_CFG_PAD_CQRR_IR_ENABLE	vxge_mBIT(15)
+#define	VXGE_HW_RPE_PCI_CFG_NOSNOOP_DATA	vxge_mBIT(18)
+#define	VXGE_HW_RPE_PCI_CFG_NOSNOOP_NONLL_CQE	vxge_mBIT(19)
+#define	VXGE_HW_RPE_PCI_CFG_NOSNOOP_LL_CQE	vxge_mBIT(20)
+#define	VXGE_HW_RPE_PCI_CFG_NOSNOOP_CQRQ_IR	vxge_mBIT(21)
+#define	VXGE_HW_RPE_PCI_CFG_NOSNOOP_CQSQ_IR	vxge_mBIT(22)
+#define	VXGE_HW_RPE_PCI_CFG_NOSNOOP_CQRR_IR	vxge_mBIT(23)
+#define	VXGE_HW_RPE_PCI_CFG_RELAXED_DATA	vxge_mBIT(26)
+#define	VXGE_HW_RPE_PCI_CFG_RELAXED_NONLL_CQE	vxge_mBIT(27)
+#define	VXGE_HW_RPE_PCI_CFG_RELAXED_LL_CQE	vxge_mBIT(28)
+#define	VXGE_HW_RPE_PCI_CFG_RELAXED_CQRQ_IR	vxge_mBIT(29)
+#define	VXGE_HW_RPE_PCI_CFG_RELAXED_CQSQ_IR	vxge_mBIT(30)
+#define	VXGE_HW_RPE_PCI_CFG_RELAXED_CQRR_IR	vxge_mBIT(31)
+/*0x01118*/	u64	rpe_lro_cfg;
+#define	VXGE_HW_RPE_LRO_CFG_SUPPRESS_LRO_ETH_TRLR	vxge_mBIT(7)
+#define	VXGE_HW_RPE_LRO_CFG_ALLOW_LRO_SNAP_SNAPJUMBO_MRG	vxge_mBIT(11)
+#define	VXGE_HW_RPE_LRO_CFG_ALLOW_LRO_LLC_LLCJUMBO_MRG	vxge_mBIT(15)
+#define	VXGE_HW_RPE_LRO_CFG_INCL_ACK_CNT_IN_CQE	vxge_mBIT(23)
+/*0x01120*/	u64	pe_mr2vp_ack_blk_limit;
+#define VXGE_HW_PE_MR2VP_ACK_BLK_LIMIT_BLK_LIMIT(val) vxge_vBIT(val, 32, 32)
+/*0x01128*/	u64	pe_mr2vp_rirr_lirr_blk_limit;
+#define	VXGE_HW_PE_MR2VP_RIRR_LIRR_BLK_LIMIT_RIRR_BLK_LIMIT(val) \
+							vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_PE_MR2VP_RIRR_LIRR_BLK_LIMIT_LIRR_BLK_LIMIT(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x01130*/	u64	txpe_pci_nce_cfg;
+#define VXGE_HW_TXPE_PCI_NCE_CFG_NCE_THRESH(val) vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_TXPE_PCI_NCE_CFG_PAD_TOWI_ENABLE	vxge_mBIT(55)
+#define	VXGE_HW_TXPE_PCI_NCE_CFG_NOSNOOP_TOWI	vxge_mBIT(63)
+	u8	unused01180[0x01180-0x01138];
+
+/*0x01180*/	u64	msg_qpad_en_cfg;
+#define	VXGE_HW_MSG_QPAD_EN_CFG_UMQ_BWR_READ	vxge_mBIT(3)
+#define	VXGE_HW_MSG_QPAD_EN_CFG_DMQ_BWR_READ	vxge_mBIT(7)
+#define	VXGE_HW_MSG_QPAD_EN_CFG_MXP_GENDMA_READ	vxge_mBIT(11)
+#define	VXGE_HW_MSG_QPAD_EN_CFG_UXP_GENDMA_READ	vxge_mBIT(15)
+#define	VXGE_HW_MSG_QPAD_EN_CFG_UMQ_MSG_WRITE	vxge_mBIT(19)
+#define	VXGE_HW_MSG_QPAD_EN_CFG_UMQDMQ_IR_WRITE	vxge_mBIT(23)
+#define	VXGE_HW_MSG_QPAD_EN_CFG_MXP_GENDMA_WRITE	vxge_mBIT(27)
+#define	VXGE_HW_MSG_QPAD_EN_CFG_UXP_GENDMA_WRITE	vxge_mBIT(31)
+/*0x01188*/	u64	msg_pci_cfg;
+#define	VXGE_HW_MSG_PCI_CFG_GENDMA_NO_SNOOP	vxge_mBIT(3)
+#define	VXGE_HW_MSG_PCI_CFG_UMQDMQ_IR_NO_SNOOP	vxge_mBIT(7)
+#define	VXGE_HW_MSG_PCI_CFG_UMQ_NO_SNOOP	vxge_mBIT(11)
+#define	VXGE_HW_MSG_PCI_CFG_DMQ_NO_SNOOP	vxge_mBIT(15)
+/*0x01190*/	u64	umqdmq_ir_init;
+#define VXGE_HW_UMQDMQ_IR_INIT_HOST_WRITE_ADD(val) vxge_vBIT(val, 0, 64)
+/*0x01198*/	u64	dmq_ir_int;
+#define	VXGE_HW_DMQ_IR_INT_IMMED_ENABLE	vxge_mBIT(6)
+#define	VXGE_HW_DMQ_IR_INT_EVENT_ENABLE	vxge_mBIT(7)
+#define VXGE_HW_DMQ_IR_INT_NUMBER(val) vxge_vBIT(val, 9, 7)
+#define VXGE_HW_DMQ_IR_INT_BITMAP(val) vxge_vBIT(val, 16, 16)
+/*0x011a0*/	u64	dmq_bwr_init_add;
+#define VXGE_HW_DMQ_BWR_INIT_ADD_HOST(val) vxge_vBIT(val, 0, 64)
+/*0x011a8*/	u64	dmq_bwr_init_byte;
+#define VXGE_HW_DMQ_BWR_INIT_BYTE_COUNT(val) vxge_vBIT(val, 0, 32)
+/*0x011b0*/	u64	dmq_ir;
+#define VXGE_HW_DMQ_IR_POLICY(val) vxge_vBIT(val, 0, 8)
+/*0x011b8*/	u64	umq_int;
+#define	VXGE_HW_UMQ_INT_IMMED_ENABLE	vxge_mBIT(6)
+#define	VXGE_HW_UMQ_INT_EVENT_ENABLE	vxge_mBIT(7)
+#define VXGE_HW_UMQ_INT_NUMBER(val) vxge_vBIT(val, 9, 7)
+#define VXGE_HW_UMQ_INT_BITMAP(val) vxge_vBIT(val, 16, 16)
+/*0x011c0*/	u64	umq_mr2vp_bwr_pfch_init;
+#define VXGE_HW_UMQ_MR2VP_BWR_PFCH_INIT_NUMBER(val) vxge_vBIT(val, 0, 8)
+/*0x011c8*/	u64	umq_bwr_pfch_ctrl;
+#define	VXGE_HW_UMQ_BWR_PFCH_CTRL_POLL_EN	vxge_mBIT(3)
+/*0x011d0*/	u64	umq_mr2vp_bwr_eol;
+#define VXGE_HW_UMQ_MR2VP_BWR_EOL_POLL_LATENCY(val) vxge_vBIT(val, 32, 32)
+/*0x011d8*/	u64	umq_bwr_init_add;
+#define VXGE_HW_UMQ_BWR_INIT_ADD_HOST(val) vxge_vBIT(val, 0, 64)
+/*0x011e0*/	u64	umq_bwr_init_byte;
+#define VXGE_HW_UMQ_BWR_INIT_BYTE_COUNT(val) vxge_vBIT(val, 0, 32)
+/*0x011e8*/	u64	gendma_int;
+#define	VXGE_HW_GENDMA_INT_IMMED_ENABLE	vxge_mBIT(6)
+#define	VXGE_HW_GENDMA_INT_EVENT_ENABLE	vxge_mBIT(7)
+#define VXGE_HW_GENDMA_INT_NUMBER(val) vxge_vBIT(val, 9, 7)
+#define VXGE_HW_GENDMA_INT_BITMAP(val) vxge_vBIT(val, 16, 16)
+/*0x011f0*/	u64	umqdmq_ir_init_notify;
+#define	VXGE_HW_UMQDMQ_IR_INIT_NOTIFY_PULSE	vxge_mBIT(3)
+/*0x011f8*/	u64	dmq_init_notify;
+#define	VXGE_HW_DMQ_INIT_NOTIFY_PULSE	vxge_mBIT(3)
+/*0x01200*/	u64	umq_init_notify;
+#define	VXGE_HW_UMQ_INIT_NOTIFY_PULSE	vxge_mBIT(3)
+	u8	unused01380[0x01380-0x01208];
+
+/*0x01380*/	u64	tpa_cfg;
+#define	VXGE_HW_TPA_CFG_IGNORE_FRAME_ERR	vxge_mBIT(3)
+#define	VXGE_HW_TPA_CFG_IPV6_STOP_SEARCHING	vxge_mBIT(7)
+#define	VXGE_HW_TPA_CFG_L4_PSHDR_PRESENT	vxge_mBIT(11)
+#define	VXGE_HW_TPA_CFG_SUPPORT_MOBILE_IPV6_HDRS	vxge_mBIT(15)
+	u8	unused01400[0x01400-0x01388];
+
+/*0x01400*/	u64	tx_vp_reset_discarded_frms;
+#define	VXGE_HW_TX_VP_RESET_DISCARDED_FRMS_TX_VP_RESET_DISCARDED_FRMS(val) \
+							vxge_vBIT(val, 48, 16)
+	u8	unused01480[0x01480-0x01408];
+
+/*0x01480*/	u64	fau_rpa_vcfg;
+#define	VXGE_HW_FAU_RPA_VCFG_L4_COMP_CSUM	vxge_mBIT(7)
+#define	VXGE_HW_FAU_RPA_VCFG_L3_INCL_CF	vxge_mBIT(11)
+#define	VXGE_HW_FAU_RPA_VCFG_L3_COMP_CSUM	vxge_mBIT(15)
+	u8	unused014d0[0x014d0-0x01488];
+
+/*0x014d0*/	u64	dbg_stats_rx_mpa;
+#define VXGE_HW_DBG_STATS_RX_MPA_CRC_FAIL_FRMS(val) vxge_vBIT(val, 0, 16)
+#define VXGE_HW_DBG_STATS_RX_MPA_MRK_FAIL_FRMS(val) vxge_vBIT(val, 16, 16)
+#define VXGE_HW_DBG_STATS_RX_MPA_LEN_FAIL_FRMS(val) vxge_vBIT(val, 32, 16)
+/*0x014d8*/	u64	dbg_stats_rx_fau;
+#define VXGE_HW_DBG_STATS_RX_FAU_RX_WOL_FRMS(val) vxge_vBIT(val, 0, 16)
+#define	VXGE_HW_DBG_STATS_RX_FAU_RX_VP_RESET_DISCARDED_FRMS(val) \
+							vxge_vBIT(val, 16, 16)
+#define	VXGE_HW_DBG_STATS_RX_FAU_RX_PERMITTED_FRMS(val) \
+							vxge_vBIT(val, 32, 32)
+	u8	unused014f0[0x014f0-0x014e0];
+
+/*0x014f0*/	u64	fbmc_vp_rdy;
+#define	VXGE_HW_FBMC_VP_RDY_QUEUE_SPAV_FM	vxge_mBIT(0)
+	u8	unused01e00[0x01e00-0x014f8];
+
+/*0x01e00*/	u64	vpath_pcipif_int_status;
+#define \
+VXGE_HW_VPATH_PCIPIF_INT_STATUS_SRPCIM_MSG_TO_VPATH_SRPCIM_MSG_TO_VPATH_INT \
+								vxge_mBIT(3)
+#define	VXGE_HW_VPATH_PCIPIF_INT_STATUS_VPATH_SPARE_R1_VPATH_SPARE_R1_INT \
+								vxge_mBIT(7)
+/*0x01e08*/	u64	vpath_pcipif_int_mask;
+	u8	unused01e20[0x01e20-0x01e10];
+
+/*0x01e20*/	u64	srpcim_msg_to_vpath_reg;
+#define	VXGE_HW_SRPCIM_MSG_TO_VPATH_REG_SWIF_SRPCIM_TO_VPATH_RMSG_INT \
+								vxge_mBIT(3)
+/*0x01e28*/	u64	srpcim_msg_to_vpath_mask;
+/*0x01e30*/	u64	srpcim_msg_to_vpath_alarm;
+	u8	unused01ea0[0x01ea0-0x01e38];
+
+/*0x01ea0*/	u64	vpath_to_srpcim_wmsg;
+#define VXGE_HW_VPATH_TO_SRPCIM_WMSG_VPATH_TO_SRPCIM_WMSG(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x01ea8*/	u64	vpath_to_srpcim_wmsg_trig;
+#define	VXGE_HW_VPATH_TO_SRPCIM_WMSG_TRIG_VPATH_TO_SRPCIM_WMSG_TRIG \
+							vxge_mBIT(0)
+	u8	unused02000[0x02000-0x01eb0];
+
+/*0x02000*/	u64	vpath_general_int_status;
+#define	VXGE_HW_VPATH_GENERAL_INT_STATUS_PIC_INT	vxge_mBIT(3)
+#define	VXGE_HW_VPATH_GENERAL_INT_STATUS_PCI_INT	vxge_mBIT(7)
+#define	VXGE_HW_VPATH_GENERAL_INT_STATUS_WRDMA_INT	vxge_mBIT(15)
+#define	VXGE_HW_VPATH_GENERAL_INT_STATUS_XMAC_INT	vxge_mBIT(19)
+/*0x02008*/	u64	vpath_general_int_mask;
+#define	VXGE_HW_VPATH_GENERAL_INT_MASK_PIC_INT	vxge_mBIT(3)
+#define	VXGE_HW_VPATH_GENERAL_INT_MASK_PCI_INT	vxge_mBIT(7)
+#define	VXGE_HW_VPATH_GENERAL_INT_MASK_WRDMA_INT	vxge_mBIT(15)
+#define	VXGE_HW_VPATH_GENERAL_INT_MASK_XMAC_INT	vxge_mBIT(19)
+/*0x02010*/	u64	vpath_ppif_int_status;
+#define	VXGE_HW_VPATH_PPIF_INT_STATUS_KDFCCTL_ERRORS_KDFCCTL_INT \
+							vxge_mBIT(3)
+#define	VXGE_HW_VPATH_PPIF_INT_STATUS_GENERAL_ERRORS_GENERAL_INT \
+							vxge_mBIT(7)
+#define	VXGE_HW_VPATH_PPIF_INT_STATUS_PCI_CONFIG_ERRORS_PCI_CONFIG_INT \
+							vxge_mBIT(11)
+#define \
+VXGE_HW_VPATH_PPIF_INT_STATUS_MRPCIM_TO_VPATH_ALARM_MRPCIM_TO_VPATH_ALARM_INT \
+							vxge_mBIT(15)
+#define \
+VXGE_HW_VPATH_PPIF_INT_STATUS_SRPCIM_TO_VPATH_ALARM_SRPCIM_TO_VPATH_ALARM_INT \
+							vxge_mBIT(19)
+/*0x02018*/	u64	vpath_ppif_int_mask;
+/*0x02020*/	u64	kdfcctl_errors_reg;
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO0_OVRWR	vxge_mBIT(3)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO1_OVRWR	vxge_mBIT(7)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO2_OVRWR	vxge_mBIT(11)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO0_POISON	vxge_mBIT(15)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO1_POISON	vxge_mBIT(19)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO2_POISON	vxge_mBIT(23)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO0_DMA_ERR	vxge_mBIT(31)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO1_DMA_ERR	vxge_mBIT(35)
+#define	VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO2_DMA_ERR	vxge_mBIT(39)
+/*0x02028*/	u64	kdfcctl_errors_mask;
+/*0x02030*/	u64	kdfcctl_errors_alarm;
+	u8	unused02040[0x02040-0x02038];
+
+/*0x02040*/	u64	general_errors_reg;
+#define	VXGE_HW_GENERAL_ERRORS_REG_DBLGEN_FIFO0_OVRFLOW	vxge_mBIT(3)
+#define	VXGE_HW_GENERAL_ERRORS_REG_DBLGEN_FIFO1_OVRFLOW	vxge_mBIT(7)
+#define	VXGE_HW_GENERAL_ERRORS_REG_DBLGEN_FIFO2_OVRFLOW	vxge_mBIT(11)
+#define	VXGE_HW_GENERAL_ERRORS_REG_STATSB_PIF_CHAIN_ERR	vxge_mBIT(15)
+#define	VXGE_HW_GENERAL_ERRORS_REG_STATSB_DROP_TIMEOUT_REQ	vxge_mBIT(19)
+#define	VXGE_HW_GENERAL_ERRORS_REG_TGT_ILLEGAL_ACCESS	vxge_mBIT(27)
+#define	VXGE_HW_GENERAL_ERRORS_REG_INI_SERR_DET	vxge_mBIT(31)
+/*0x02048*/	u64	general_errors_mask;
+/*0x02050*/	u64	general_errors_alarm;
+/*0x02058*/	u64	pci_config_errors_reg;
+#define	VXGE_HW_PCI_CONFIG_ERRORS_REG_PCICONFIG_STATUS_ERR	vxge_mBIT(3)
+#define	VXGE_HW_PCI_CONFIG_ERRORS_REG_PCICONFIG_UNCOR_ERR	vxge_mBIT(7)
+#define	VXGE_HW_PCI_CONFIG_ERRORS_REG_PCICONFIG_COR_ERR	vxge_mBIT(11)
+/*0x02060*/	u64	pci_config_errors_mask;
+/*0x02068*/	u64	pci_config_errors_alarm;
+/*0x02070*/	u64	mrpcim_to_vpath_alarm_reg;
+#define	VXGE_HW_MRPCIM_TO_VPATH_ALARM_REG_PPIF_MRPCIM_TO_VPATH_ALARM \
+								vxge_mBIT(3)
+/*0x02078*/	u64	mrpcim_to_vpath_alarm_mask;
+/*0x02080*/	u64	mrpcim_to_vpath_alarm_alarm;
+/*0x02088*/	u64	srpcim_to_vpath_alarm_reg;
+#define	VXGE_HW_SRPCIM_TO_VPATH_ALARM_REG_PPIF_SRPCIM_TO_VPATH_ALARM(val) \
+							vxge_vBIT(val, 0, 17)
+/*0x02090*/	u64	srpcim_to_vpath_alarm_mask;
+/*0x02098*/	u64	srpcim_to_vpath_alarm_alarm;
+	u8	unused02108[0x02108-0x020a0];
+
+/*0x02108*/	u64	kdfcctl_status;
+#define VXGE_HW_KDFCCTL_STATUS_KDFCCTL_FIFO0_PRES(val) vxge_vBIT(val, 0, 8)
+#define VXGE_HW_KDFCCTL_STATUS_KDFCCTL_FIFO1_PRES(val) vxge_vBIT(val, 8, 8)
+#define VXGE_HW_KDFCCTL_STATUS_KDFCCTL_FIFO2_PRES(val) vxge_vBIT(val, 16, 8)
+#define VXGE_HW_KDFCCTL_STATUS_KDFCCTL_FIFO0_OVRWR(val) vxge_vBIT(val, 24, 8)
+#define VXGE_HW_KDFCCTL_STATUS_KDFCCTL_FIFO1_OVRWR(val) vxge_vBIT(val, 32, 8)
+#define VXGE_HW_KDFCCTL_STATUS_KDFCCTL_FIFO2_OVRWR(val) vxge_vBIT(val, 40, 8)
+/*0x02110*/	u64	rsthdlr_status;
+#define	VXGE_HW_RSTHDLR_STATUS_RSTHDLR_CURRENT_RESET	vxge_mBIT(3)
+#define VXGE_HW_RSTHDLR_STATUS_RSTHDLR_CURRENT_VPIN(val) vxge_vBIT(val, 6, 2)
+/*0x02118*/	u64	fifo0_status;
+#define VXGE_HW_FIFO0_STATUS_DBLGEN_FIFO0_RDIDX(val) vxge_vBIT(val, 0, 12)
+/*0x02120*/	u64	fifo1_status;
+#define VXGE_HW_FIFO1_STATUS_DBLGEN_FIFO1_RDIDX(val) vxge_vBIT(val, 0, 12)
+/*0x02128*/	u64	fifo2_status;
+#define VXGE_HW_FIFO2_STATUS_DBLGEN_FIFO2_RDIDX(val) vxge_vBIT(val, 0, 12)
+	u8	unused02158[0x02158-0x02130];
+
+/*0x02158*/	u64	tgt_illegal_access;
+#define VXGE_HW_TGT_ILLEGAL_ACCESS_SWIF_REGION(val) vxge_vBIT(val, 1, 7)
+	u8	unused02200[0x02200-0x02160];
+
+/*0x02200*/	u64	vpath_general_cfg1;
+#define VXGE_HW_VPATH_GENERAL_CFG1_TC_VALUE(val) vxge_vBIT(val, 1, 3)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_DATA_BYTE_SWAPEN	vxge_mBIT(7)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_DATA_FLIPEN	vxge_mBIT(11)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_CTL_BYTE_SWAPEN	vxge_mBIT(15)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_CTL_FLIPEN	vxge_mBIT(23)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_MSIX_ADDR_SWAPEN	vxge_mBIT(51)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_MSIX_ADDR_FLIPEN	vxge_mBIT(55)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_MSIX_DATA_SWAPEN	vxge_mBIT(59)
+#define	VXGE_HW_VPATH_GENERAL_CFG1_MSIX_DATA_FLIPEN	vxge_mBIT(63)
+/*0x02208*/	u64	vpath_general_cfg2;
+#define VXGE_HW_VPATH_GENERAL_CFG2_SIZE_QUANTUM(val) vxge_vBIT(val, 1, 3)
+/*0x02210*/	u64	vpath_general_cfg3;
+#define	VXGE_HW_VPATH_GENERAL_CFG3_IGNORE_VPATH_RST_FOR_INTA	vxge_mBIT(3)
+	u8	unused02220[0x02220-0x02218];
+
+/*0x02220*/	u64	kdfcctl_cfg0;
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_SWAPEN_FIFO0	vxge_mBIT(1)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_SWAPEN_FIFO1	vxge_mBIT(2)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_SWAPEN_FIFO2	vxge_mBIT(3)
+#define	VXGE_HW_KDFCCTL_CFG0_BIT_FLIPEN_FIFO0	vxge_mBIT(5)
+#define	VXGE_HW_KDFCCTL_CFG0_BIT_FLIPEN_FIFO1	vxge_mBIT(6)
+#define	VXGE_HW_KDFCCTL_CFG0_BIT_FLIPEN_FIFO2	vxge_mBIT(7)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE0_FIFO0	vxge_mBIT(9)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE0_FIFO1	vxge_mBIT(10)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE0_FIFO2	vxge_mBIT(11)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE1_FIFO0	vxge_mBIT(13)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE1_FIFO1	vxge_mBIT(14)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE1_FIFO2	vxge_mBIT(15)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE2_FIFO0	vxge_mBIT(17)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE2_FIFO1	vxge_mBIT(18)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE2_FIFO2	vxge_mBIT(19)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE3_FIFO0	vxge_mBIT(21)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE3_FIFO1	vxge_mBIT(22)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE3_FIFO2	vxge_mBIT(23)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE4_FIFO0	vxge_mBIT(25)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE4_FIFO1	vxge_mBIT(26)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE4_FIFO2	vxge_mBIT(27)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE5_FIFO0	vxge_mBIT(29)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE5_FIFO1	vxge_mBIT(30)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE5_FIFO2	vxge_mBIT(31)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE6_FIFO0	vxge_mBIT(33)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE6_FIFO1	vxge_mBIT(34)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE6_FIFO2	vxge_mBIT(35)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE7_FIFO0	vxge_mBIT(37)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE7_FIFO1	vxge_mBIT(38)
+#define	VXGE_HW_KDFCCTL_CFG0_BYTE_MASK_BYTE7_FIFO2	vxge_mBIT(39)
+
+	u8	unused02268[0x02268-0x02228];
+
+/*0x02268*/	u64	stats_cfg;
+#define VXGE_HW_STATS_CFG_START_HOST_ADDR(val) vxge_vBIT(val, 0, 57)
+/*0x02270*/	u64	interrupt_cfg0;
+#define VXGE_HW_INTERRUPT_CFG0_MSIX_FOR_RXTI(val) vxge_vBIT(val, 1, 7)
+#define VXGE_HW_INTERRUPT_CFG0_GROUP0_MSIX_FOR_TXTI(val) vxge_vBIT(val, 9, 7)
+#define VXGE_HW_INTERRUPT_CFG0_GROUP1_MSIX_FOR_TXTI(val) vxge_vBIT(val, 17, 7)
+#define VXGE_HW_INTERRUPT_CFG0_GROUP2_MSIX_FOR_TXTI(val) vxge_vBIT(val, 25, 7)
+#define VXGE_HW_INTERRUPT_CFG0_GROUP3_MSIX_FOR_TXTI(val) vxge_vBIT(val, 33, 7)
+	u8	unused02280[0x02280-0x02278];
+
+/*0x02280*/	u64	interrupt_cfg2;
+#define VXGE_HW_INTERRUPT_CFG2_ALARM_MAP_TO_MSG(val) vxge_vBIT(val, 1, 7)
+/*0x02288*/	u64	one_shot_vect0_en;
+#define	VXGE_HW_ONE_SHOT_VECT0_EN_ONE_SHOT_VECT0_EN	vxge_mBIT(3)
+/*0x02290*/	u64	one_shot_vect1_en;
+#define	VXGE_HW_ONE_SHOT_VECT1_EN_ONE_SHOT_VECT1_EN	vxge_mBIT(3)
+/*0x02298*/	u64	one_shot_vect2_en;
+#define	VXGE_HW_ONE_SHOT_VECT2_EN_ONE_SHOT_VECT2_EN	vxge_mBIT(3)
+/*0x022a0*/	u64	one_shot_vect3_en;
+#define	VXGE_HW_ONE_SHOT_VECT3_EN_ONE_SHOT_VECT3_EN	vxge_mBIT(3)
+	u8	unused022b0[0x022b0-0x022a8];
+
+/*0x022b0*/	u64	pci_config_access_cfg1;
+#define VXGE_HW_PCI_CONFIG_ACCESS_CFG1_ADDRESS(val) vxge_vBIT(val, 0, 12)
+#define	VXGE_HW_PCI_CONFIG_ACCESS_CFG1_SEL_FUNC0	vxge_mBIT(15)
+/*0x022b8*/	u64	pci_config_access_cfg2;
+#define	VXGE_HW_PCI_CONFIG_ACCESS_CFG2_REQ	vxge_mBIT(0)
+/*0x022c0*/	u64	pci_config_access_status;
+#define	VXGE_HW_PCI_CONFIG_ACCESS_STATUS_ACCESS_ERR	vxge_mBIT(0)
+#define VXGE_HW_PCI_CONFIG_ACCESS_STATUS_DATA(val) vxge_vBIT(val, 32, 32)
+	u8	unused02300[0x02300-0x022c8];
+
+/*0x02300*/	u64	vpath_debug_stats0;
+#define VXGE_HW_VPATH_DEBUG_STATS0_INI_NUM_MWR_SENT(val) vxge_vBIT(val, 0, 32)
+/*0x02308*/	u64	vpath_debug_stats1;
+#define VXGE_HW_VPATH_DEBUG_STATS1_INI_NUM_MRD_SENT(val) vxge_vBIT(val, 0, 32)
+/*0x02310*/	u64	vpath_debug_stats2;
+#define VXGE_HW_VPATH_DEBUG_STATS2_INI_NUM_CPL_RCVD(val) vxge_vBIT(val, 0, 32)
+/*0x02318*/	u64	vpath_debug_stats3;
+#define VXGE_HW_VPATH_DEBUG_STATS3_INI_NUM_MWR_BYTE_SENT(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x02320*/	u64	vpath_debug_stats4;
+#define VXGE_HW_VPATH_DEBUG_STATS4_INI_NUM_CPL_BYTE_RCVD(val) \
+							vxge_vBIT(val, 0, 64)
+/*0x02328*/	u64	vpath_debug_stats5;
+#define VXGE_HW_VPATH_DEBUG_STATS5_WRCRDTARB_XOFF(val) vxge_vBIT(val, 32, 32)
+/*0x02330*/	u64	vpath_debug_stats6;
+#define VXGE_HW_VPATH_DEBUG_STATS6_RDCRDTARB_XOFF(val) vxge_vBIT(val, 32, 32)
+/*0x02338*/	u64	vpath_genstats_count01;
+#define	VXGE_HW_VPATH_GENSTATS_COUNT01_PPIF_VPATH_GENSTATS_COUNT1(val) \
+							vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT01_PPIF_VPATH_GENSTATS_COUNT0(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x02340*/	u64	vpath_genstats_count23;
+#define	VXGE_HW_VPATH_GENSTATS_COUNT23_PPIF_VPATH_GENSTATS_COUNT3(val) \
+							vxge_vBIT(val, 0, 32)
+#define	VXGE_HW_VPATH_GENSTATS_COUNT23_PPIF_VPATH_GENSTATS_COUNT2(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x02348*/	u64	vpath_genstats_count4;
+#define	VXGE_HW_VPATH_GENSTATS_COUNT4_PPIF_VPATH_GENSTATS_COUNT4(val) \
+							vxge_vBIT(val, 32, 32)
+/*0x02350*/	u64	vpath_genstats_count5;
+#define	VXGE_HW_VPATH_GENSTATS_COUNT5_PPIF_VPATH_GENSTATS_COUNT5(val) \
+							vxge_vBIT(val, 32, 32)
+	u8	unused02648[0x02648-0x02358];
+} __packed;
+
+#define VXGE_HW_EEPROM_SIZE	(0x01 << 11)
+
+/* Capability lists */
+#define  VXGE_HW_PCI_EXP_LNKCAP_LNK_SPEED    0xf  /* Supported Link speeds */
+#define  VXGE_HW_PCI_EXP_LNKCAP_LNK_WIDTH    0x3f0 /* Supported Link speeds. */
+#define  VXGE_HW_PCI_EXP_LNKCAP_LW_RES       0x0  /* Reserved. */
+
+#endif
diff --git a/drivers/net/vxge/vxge-traffic.c b/drivers/net/vxge/vxge-traffic.c
new file mode 100644
index 000000000000..7be0ae10d69b
--- /dev/null
+++ b/drivers/net/vxge/vxge-traffic.c
@@ -0,0 +1,2528 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-traffic.c: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *                 Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#include <linux/etherdevice.h>
+
+#include "vxge-traffic.h"
+#include "vxge-config.h"
+#include "vxge-main.h"
+
+/*
+ * vxge_hw_vpath_intr_enable - Enable vpath interrupts.
+ * @vp: Virtual Path handle.
+ *
+ * Enable vpath interrupts. The function is to be executed the last in
+ * vpath initialization sequence.
+ *
+ * See also: vxge_hw_vpath_intr_disable()
+ */
+enum vxge_hw_status vxge_hw_vpath_intr_enable(struct __vxge_hw_vpath_handle *vp)
+{
+	u64 val64;
+
+	struct __vxge_hw_virtualpath *vpath;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+
+	vp_reg = vpath->vp_reg;
+
+	writeq(VXGE_HW_INTR_MASK_ALL, &vp_reg->kdfcctl_errors_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->general_errors_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->pci_config_errors_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->mrpcim_to_vpath_alarm_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->srpcim_to_vpath_alarm_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->vpath_ppif_int_status);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->srpcim_msg_to_vpath_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->vpath_pcipif_int_status);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->prc_alarm_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->wrdma_alarm_status);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->asic_ntwk_vp_err_reg);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->xgmac_vp_int_status);
+
+	val64 = readq(&vp_reg->vpath_general_int_status);
+
+	/* Mask unwanted interrupts */
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->vpath_pcipif_int_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->srpcim_msg_to_vpath_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->srpcim_to_vpath_alarm_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->mrpcim_to_vpath_alarm_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->pci_config_errors_mask);
+
+	/* Unmask the individual interrupts */
+
+	writeq((u32)vxge_bVALn((VXGE_HW_GENERAL_ERRORS_REG_DBLGEN_FIFO1_OVRFLOW|
+		VXGE_HW_GENERAL_ERRORS_REG_DBLGEN_FIFO2_OVRFLOW|
+		VXGE_HW_GENERAL_ERRORS_REG_STATSB_DROP_TIMEOUT_REQ|
+		VXGE_HW_GENERAL_ERRORS_REG_STATSB_PIF_CHAIN_ERR), 0, 32),
+		&vp_reg->general_errors_mask);
+
+	__vxge_hw_pio_mem_write32_upper(
+		(u32)vxge_bVALn((VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO1_OVRWR|
+		VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO2_OVRWR|
+		VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO1_POISON|
+		VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO2_POISON|
+		VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO1_DMA_ERR|
+		VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO1_DMA_ERR), 0, 32),
+		&vp_reg->kdfcctl_errors_mask);
+
+	__vxge_hw_pio_mem_write32_upper(0, &vp_reg->vpath_ppif_int_mask);
+
+	__vxge_hw_pio_mem_write32_upper(
+		(u32)vxge_bVALn(VXGE_HW_PRC_ALARM_REG_PRC_RING_BUMP, 0, 32),
+		&vp_reg->prc_alarm_mask);
+
+	__vxge_hw_pio_mem_write32_upper(0, &vp_reg->wrdma_alarm_mask);
+	__vxge_hw_pio_mem_write32_upper(0, &vp_reg->xgmac_vp_int_mask);
+
+	if (vpath->hldev->first_vp_id != vpath->vp_id)
+		__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->asic_ntwk_vp_err_mask);
+	else
+		__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn((
+		VXGE_HW_ASIC_NTWK_VP_ERR_REG_XMACJ_NTWK_REAFFIRMED_FAULT |
+		VXGE_HW_ASIC_NTWK_VP_ERR_REG_XMACJ_NTWK_REAFFIRMED_OK), 0, 32),
+		&vp_reg->asic_ntwk_vp_err_mask);
+
+	__vxge_hw_pio_mem_write32_upper(0,
+		&vp_reg->vpath_general_int_mask);
+exit:
+	return status;
+
+}
+
+/*
+ * vxge_hw_vpath_intr_disable - Disable vpath interrupts.
+ * @vp: Virtual Path handle.
+ *
+ * Disable vpath interrupts. The function is to be executed the last in
+ * vpath initialization sequence.
+ *
+ * See also: vxge_hw_vpath_intr_enable()
+ */
+enum vxge_hw_status vxge_hw_vpath_intr_disable(
+			struct __vxge_hw_vpath_handle *vp)
+{
+	u64 val64;
+
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+
+	if (vpath->vp_open == VXGE_HW_VP_NOT_OPEN) {
+		status = VXGE_HW_ERR_VPATH_NOT_OPEN;
+		goto exit;
+	}
+	vp_reg = vpath->vp_reg;
+
+	__vxge_hw_pio_mem_write32_upper(
+		(u32)VXGE_HW_INTR_MASK_ALL,
+		&vp_reg->vpath_general_int_mask);
+
+	val64 = VXGE_HW_TIM_CLR_INT_EN_VP(1 << (16 - vpath->vp_id));
+
+	writeq(VXGE_HW_INTR_MASK_ALL, &vp_reg->kdfcctl_errors_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->general_errors_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->pci_config_errors_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->mrpcim_to_vpath_alarm_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->srpcim_to_vpath_alarm_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->vpath_ppif_int_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->srpcim_msg_to_vpath_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->vpath_pcipif_int_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->wrdma_alarm_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->prc_alarm_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->xgmac_vp_int_mask);
+
+	__vxge_hw_pio_mem_write32_upper((u32)VXGE_HW_INTR_MASK_ALL,
+			&vp_reg->asic_ntwk_vp_err_mask);
+
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_channel_msix_mask - Mask MSIX Vector.
+ * @channeh: Channel for rx or tx handle
+ * @msix_id:  MSIX ID
+ *
+ * The function masks the msix interrupt for the given msix_id
+ *
+ * Returns: 0
+ */
+void vxge_hw_channel_msix_mask(struct __vxge_hw_channel *channel, int msix_id)
+{
+
+	__vxge_hw_pio_mem_write32_upper(
+		(u32)vxge_bVALn(vxge_mBIT(channel->first_vp_id+(msix_id/4)),
+			0, 32),
+		&channel->common_reg->set_msix_mask_vect[msix_id%4]);
+
+	return;
+}
+
+/**
+ * vxge_hw_channel_msix_unmask - Unmask the MSIX Vector.
+ * @channeh: Channel for rx or tx handle
+ * @msix_id:  MSI ID
+ *
+ * The function unmasks the msix interrupt for the given msix_id
+ *
+ * Returns: 0
+ */
+void
+vxge_hw_channel_msix_unmask(struct __vxge_hw_channel *channel, int msix_id)
+{
+
+	__vxge_hw_pio_mem_write32_upper(
+		(u32)vxge_bVALn(vxge_mBIT(channel->first_vp_id+(msix_id/4)),
+			0, 32),
+		&channel->common_reg->clear_msix_mask_vect[msix_id%4]);
+
+	return;
+}
+
+/**
+ * vxge_hw_device_set_intr_type - Updates the configuration
+ *		with new interrupt type.
+ * @hldev: HW device handle.
+ * @intr_mode: New interrupt type
+ */
+u32 vxge_hw_device_set_intr_type(struct __vxge_hw_device *hldev, u32 intr_mode)
+{
+
+	if ((intr_mode != VXGE_HW_INTR_MODE_IRQLINE) &&
+	   (intr_mode != VXGE_HW_INTR_MODE_MSIX) &&
+	   (intr_mode != VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) &&
+	   (intr_mode != VXGE_HW_INTR_MODE_DEF))
+		intr_mode = VXGE_HW_INTR_MODE_IRQLINE;
+
+	hldev->config.intr_mode = intr_mode;
+	return intr_mode;
+}
+
+/**
+ * vxge_hw_device_intr_enable - Enable interrupts.
+ * @hldev: HW device handle.
+ * @op: One of the enum vxge_hw_device_intr enumerated values specifying
+ *      the type(s) of interrupts to enable.
+ *
+ * Enable Titan interrupts. The function is to be executed the last in
+ * Titan initialization sequence.
+ *
+ * See also: vxge_hw_device_intr_disable()
+ */
+void vxge_hw_device_intr_enable(struct __vxge_hw_device *hldev)
+{
+	u32 i;
+	u64 val64;
+	u32 val32;
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!(hldev->vpaths_deployed & vxge_mBIT(i)))
+			continue;
+
+		vxge_hw_vpath_intr_enable(
+			VXGE_HW_VIRTUAL_PATH_HANDLE(&hldev->virtual_paths[i]));
+	}
+
+	if (hldev->config.intr_mode == VXGE_HW_INTR_MODE_IRQLINE) {
+		val64 = hldev->tim_int_mask0[VXGE_HW_VPATH_INTR_TX] |
+			hldev->tim_int_mask0[VXGE_HW_VPATH_INTR_RX];
+
+		if (val64 != 0) {
+			writeq(val64, &hldev->common_reg->tim_int_status0);
+
+			writeq(~val64, &hldev->common_reg->tim_int_mask0);
+		}
+
+		val32 = hldev->tim_int_mask1[VXGE_HW_VPATH_INTR_TX] |
+			hldev->tim_int_mask1[VXGE_HW_VPATH_INTR_RX];
+
+		if (val32 != 0) {
+			__vxge_hw_pio_mem_write32_upper(val32,
+					&hldev->common_reg->tim_int_status1);
+
+			__vxge_hw_pio_mem_write32_upper(~val32,
+					&hldev->common_reg->tim_int_mask1);
+		}
+	}
+
+	val64 = readq(&hldev->common_reg->titan_general_int_status);
+
+	vxge_hw_device_unmask_all(hldev);
+
+	return;
+}
+
+/**
+ * vxge_hw_device_intr_disable - Disable Titan interrupts.
+ * @hldev: HW device handle.
+ * @op: One of the enum vxge_hw_device_intr enumerated values specifying
+ *      the type(s) of interrupts to disable.
+ *
+ * Disable Titan interrupts.
+ *
+ * See also: vxge_hw_device_intr_enable()
+ */
+void vxge_hw_device_intr_disable(struct __vxge_hw_device *hldev)
+{
+	u32 i;
+
+	vxge_hw_device_mask_all(hldev);
+
+	/* mask all the tim interrupts */
+	writeq(VXGE_HW_INTR_MASK_ALL, &hldev->common_reg->tim_int_mask0);
+	__vxge_hw_pio_mem_write32_upper(VXGE_HW_DEFAULT_32,
+		&hldev->common_reg->tim_int_mask1);
+
+	for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+		if (!(hldev->vpaths_deployed & vxge_mBIT(i)))
+			continue;
+
+		vxge_hw_vpath_intr_disable(
+			VXGE_HW_VIRTUAL_PATH_HANDLE(&hldev->virtual_paths[i]));
+	}
+
+	return;
+}
+
+/**
+ * vxge_hw_device_mask_all - Mask all device interrupts.
+ * @hldev: HW device handle.
+ *
+ * Mask	all device interrupts.
+ *
+ * See also: vxge_hw_device_unmask_all()
+ */
+void vxge_hw_device_mask_all(struct __vxge_hw_device *hldev)
+{
+	u64 val64;
+
+	val64 = VXGE_HW_TITAN_MASK_ALL_INT_ALARM |
+		VXGE_HW_TITAN_MASK_ALL_INT_TRAFFIC;
+
+	__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(val64, 0, 32),
+				&hldev->common_reg->titan_mask_all_int);
+
+	return;
+}
+
+/**
+ * vxge_hw_device_unmask_all - Unmask all device interrupts.
+ * @hldev: HW device handle.
+ *
+ * Unmask all device interrupts.
+ *
+ * See also: vxge_hw_device_mask_all()
+ */
+void vxge_hw_device_unmask_all(struct __vxge_hw_device *hldev)
+{
+	u64 val64 = 0;
+
+	if (hldev->config.intr_mode == VXGE_HW_INTR_MODE_IRQLINE)
+		val64 =  VXGE_HW_TITAN_MASK_ALL_INT_TRAFFIC;
+
+	__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(val64, 0, 32),
+			&hldev->common_reg->titan_mask_all_int);
+
+	return;
+}
+
+/**
+ * vxge_hw_device_flush_io - Flush io writes.
+ * @hldev: HW device handle.
+ *
+ * The function	performs a read operation to flush io writes.
+ *
+ * Returns: void
+ */
+void vxge_hw_device_flush_io(struct __vxge_hw_device *hldev)
+{
+	u32 val32;
+
+	val32 = readl(&hldev->common_reg->titan_general_int_status);
+}
+
+/**
+ * vxge_hw_device_begin_irq - Begin IRQ processing.
+ * @hldev: HW device handle.
+ * @skip_alarms: Do not clear the alarms
+ * @reason: "Reason" for the interrupt, the value of Titan's
+ *	general_int_status register.
+ *
+ * The function	performs two actions, It first checks whether (shared IRQ) the
+ * interrupt was raised	by the device. Next, it	masks the device interrupts.
+ *
+ * Note:
+ * vxge_hw_device_begin_irq() does not flush MMIO writes through the
+ * bridge. Therefore, two back-to-back interrupts are potentially possible.
+ *
+ * Returns: 0, if the interrupt	is not "ours" (note that in this case the
+ * device remain enabled).
+ * Otherwise, vxge_hw_device_begin_irq() returns 64bit general adapter
+ * status.
+ */
+enum vxge_hw_status vxge_hw_device_begin_irq(struct __vxge_hw_device *hldev,
+					     u32 skip_alarms, u64 *reason)
+{
+	u32 i;
+	u64 val64;
+	u64 adapter_status;
+	u64 vpath_mask;
+	enum vxge_hw_status ret = VXGE_HW_OK;
+
+	val64 = readq(&hldev->common_reg->titan_general_int_status);
+
+	if (unlikely(!val64)) {
+		/* not Titan interrupt	*/
+		*reason	= 0;
+		ret = VXGE_HW_ERR_WRONG_IRQ;
+		goto exit;
+	}
+
+	if (unlikely(val64 == VXGE_HW_ALL_FOXES)) {
+
+		adapter_status = readq(&hldev->common_reg->adapter_status);
+
+		if (adapter_status == VXGE_HW_ALL_FOXES) {
+
+			__vxge_hw_device_handle_error(hldev,
+				NULL_VPID, VXGE_HW_EVENT_SLOT_FREEZE);
+			*reason	= 0;
+			ret = VXGE_HW_ERR_SLOT_FREEZE;
+			goto exit;
+		}
+	}
+
+	hldev->stats.sw_dev_info_stats.total_intr_cnt++;
+
+	*reason	= val64;
+
+	vpath_mask = hldev->vpaths_deployed >>
+				(64 - VXGE_HW_MAX_VIRTUAL_PATHS);
+
+	if (val64 &
+	    VXGE_HW_TITAN_GENERAL_INT_STATUS_VPATH_TRAFFIC_INT(vpath_mask)) {
+		hldev->stats.sw_dev_info_stats.traffic_intr_cnt++;
+
+		return VXGE_HW_OK;
+	}
+
+	hldev->stats.sw_dev_info_stats.not_traffic_intr_cnt++;
+
+	if (unlikely(val64 &
+			VXGE_HW_TITAN_GENERAL_INT_STATUS_VPATH_ALARM_INT)) {
+
+		enum vxge_hw_status error_level = VXGE_HW_OK;
+
+		hldev->stats.sw_dev_err_stats.vpath_alarms++;
+
+		for (i = 0; i < VXGE_HW_MAX_VIRTUAL_PATHS; i++) {
+
+			if (!(hldev->vpaths_deployed & vxge_mBIT(i)))
+				continue;
+
+			ret = __vxge_hw_vpath_alarm_process(
+				&hldev->virtual_paths[i], skip_alarms);
+
+			error_level = VXGE_HW_SET_LEVEL(ret, error_level);
+
+			if (unlikely((ret == VXGE_HW_ERR_CRITICAL) ||
+				(ret == VXGE_HW_ERR_SLOT_FREEZE)))
+				break;
+		}
+
+		ret = error_level;
+	}
+exit:
+	return ret;
+}
+
+/*
+ * __vxge_hw_device_handle_link_up_ind
+ * @hldev: HW device handle.
+ *
+ * Link up indication handler. The function is invoked by HW when
+ * Titan indicates that the link is up for programmable amount of time.
+ */
+enum vxge_hw_status
+__vxge_hw_device_handle_link_up_ind(struct __vxge_hw_device *hldev)
+{
+	/*
+	 * If the previous link state is not down, return.
+	 */
+	if (hldev->link_state == VXGE_HW_LINK_UP)
+		goto exit;
+
+	hldev->link_state = VXGE_HW_LINK_UP;
+
+	/* notify driver */
+	if (hldev->uld_callbacks.link_up)
+		hldev->uld_callbacks.link_up(hldev);
+exit:
+	return VXGE_HW_OK;
+}
+
+/*
+ * __vxge_hw_device_handle_link_down_ind
+ * @hldev: HW device handle.
+ *
+ * Link down indication handler. The function is invoked by HW when
+ * Titan indicates that the link is down.
+ */
+enum vxge_hw_status
+__vxge_hw_device_handle_link_down_ind(struct __vxge_hw_device *hldev)
+{
+	/*
+	 * If the previous link state is not down, return.
+	 */
+	if (hldev->link_state == VXGE_HW_LINK_DOWN)
+		goto exit;
+
+	hldev->link_state = VXGE_HW_LINK_DOWN;
+
+	/* notify driver */
+	if (hldev->uld_callbacks.link_down)
+		hldev->uld_callbacks.link_down(hldev);
+exit:
+	return VXGE_HW_OK;
+}
+
+/**
+ * __vxge_hw_device_handle_error - Handle error
+ * @hldev: HW device
+ * @vp_id: Vpath Id
+ * @type: Error type. Please see enum vxge_hw_event{}
+ *
+ * Handle error.
+ */
+enum vxge_hw_status
+__vxge_hw_device_handle_error(
+		struct __vxge_hw_device *hldev,
+		u32 vp_id,
+		enum vxge_hw_event type)
+{
+	switch (type) {
+	case VXGE_HW_EVENT_UNKNOWN:
+		break;
+	case VXGE_HW_EVENT_RESET_START:
+	case VXGE_HW_EVENT_RESET_COMPLETE:
+	case VXGE_HW_EVENT_LINK_DOWN:
+	case VXGE_HW_EVENT_LINK_UP:
+		goto out;
+	case VXGE_HW_EVENT_ALARM_CLEARED:
+		goto out;
+	case VXGE_HW_EVENT_ECCERR:
+	case VXGE_HW_EVENT_MRPCIM_ECCERR:
+		goto out;
+	case VXGE_HW_EVENT_FIFO_ERR:
+	case VXGE_HW_EVENT_VPATH_ERR:
+	case VXGE_HW_EVENT_CRITICAL_ERR:
+	case VXGE_HW_EVENT_SERR:
+		break;
+	case VXGE_HW_EVENT_SRPCIM_SERR:
+	case VXGE_HW_EVENT_MRPCIM_SERR:
+		goto out;
+	case VXGE_HW_EVENT_SLOT_FREEZE:
+		break;
+	default:
+		vxge_assert(0);
+		goto out;
+	}
+
+	/* notify driver */
+	if (hldev->uld_callbacks.crit_err)
+		hldev->uld_callbacks.crit_err(
+			(struct __vxge_hw_device *)hldev,
+			type, vp_id);
+out:
+
+	return VXGE_HW_OK;
+}
+
+/**
+ * vxge_hw_device_clear_tx_rx - Acknowledge (that is, clear) the
+ * condition that has caused the Tx and RX interrupt.
+ * @hldev: HW device.
+ *
+ * Acknowledge (that is, clear) the condition that has caused
+ * the Tx and Rx interrupt.
+ * See also: vxge_hw_device_begin_irq(),
+ * vxge_hw_device_mask_tx_rx(), vxge_hw_device_unmask_tx_rx().
+ */
+void vxge_hw_device_clear_tx_rx(struct __vxge_hw_device *hldev)
+{
+
+	if ((hldev->tim_int_mask0[VXGE_HW_VPATH_INTR_TX] != 0) ||
+	   (hldev->tim_int_mask0[VXGE_HW_VPATH_INTR_RX] != 0)) {
+		writeq((hldev->tim_int_mask0[VXGE_HW_VPATH_INTR_TX] |
+				 hldev->tim_int_mask0[VXGE_HW_VPATH_INTR_RX]),
+				&hldev->common_reg->tim_int_status0);
+	}
+
+	if ((hldev->tim_int_mask1[VXGE_HW_VPATH_INTR_TX] != 0) ||
+	   (hldev->tim_int_mask1[VXGE_HW_VPATH_INTR_RX] != 0)) {
+		__vxge_hw_pio_mem_write32_upper(
+				(hldev->tim_int_mask1[VXGE_HW_VPATH_INTR_TX] |
+				 hldev->tim_int_mask1[VXGE_HW_VPATH_INTR_RX]),
+				&hldev->common_reg->tim_int_status1);
+	}
+
+	return;
+}
+
+/*
+ * vxge_hw_channel_dtr_alloc - Allocate a dtr from the channel
+ * @channel: Channel
+ * @dtrh: Buffer to return the DTR pointer
+ *
+ * Allocates a dtr from the reserve array. If the reserve array is empty,
+ * it swaps the reserve and free arrays.
+ *
+ */
+enum vxge_hw_status
+vxge_hw_channel_dtr_alloc(struct __vxge_hw_channel *channel, void **dtrh)
+{
+	void **tmp_arr;
+
+	if (channel->reserve_ptr - channel->reserve_top > 0) {
+_alloc_after_swap:
+		*dtrh =	channel->reserve_arr[--channel->reserve_ptr];
+
+		return VXGE_HW_OK;
+	}
+
+	/* switch between empty	and full arrays	*/
+
+	/* the idea behind such	a design is that by having free	and reserved
+	 * arrays separated we basically separated irq and non-irq parts.
+	 * i.e.	no additional lock need	to be done when	we free	a resource */
+
+	if (channel->length - channel->free_ptr > 0) {
+
+		tmp_arr	= channel->reserve_arr;
+		channel->reserve_arr = channel->free_arr;
+		channel->free_arr = tmp_arr;
+		channel->reserve_ptr = channel->length;
+		channel->reserve_top = channel->free_ptr;
+		channel->free_ptr = channel->length;
+
+		channel->stats->reserve_free_swaps_cnt++;
+
+		goto _alloc_after_swap;
+	}
+
+	channel->stats->full_cnt++;
+
+	*dtrh =	NULL;
+	return VXGE_HW_INF_OUT_OF_DESCRIPTORS;
+}
+
+/*
+ * vxge_hw_channel_dtr_post - Post a dtr to the channel
+ * @channelh: Channel
+ * @dtrh: DTR pointer
+ *
+ * Posts a dtr to work array.
+ *
+ */
+void vxge_hw_channel_dtr_post(struct __vxge_hw_channel *channel, void *dtrh)
+{
+	vxge_assert(channel->work_arr[channel->post_index] == NULL);
+
+	channel->work_arr[channel->post_index++] = dtrh;
+
+	/* wrap-around */
+	if (channel->post_index	== channel->length)
+		channel->post_index = 0;
+}
+
+/*
+ * vxge_hw_channel_dtr_try_complete - Returns next completed dtr
+ * @channel: Channel
+ * @dtr: Buffer to return the next completed DTR pointer
+ *
+ * Returns the next completed dtr with out removing it from work array
+ *
+ */
+void
+vxge_hw_channel_dtr_try_complete(struct __vxge_hw_channel *channel, void **dtrh)
+{
+	vxge_assert(channel->compl_index < channel->length);
+
+	*dtrh =	channel->work_arr[channel->compl_index];
+}
+
+/*
+ * vxge_hw_channel_dtr_complete - Removes next completed dtr from the work array
+ * @channel: Channel handle
+ *
+ * Removes the next completed dtr from work array
+ *
+ */
+void vxge_hw_channel_dtr_complete(struct __vxge_hw_channel *channel)
+{
+	channel->work_arr[channel->compl_index]	= NULL;
+
+	/* wrap-around */
+	if (++channel->compl_index == channel->length)
+		channel->compl_index = 0;
+
+	channel->stats->total_compl_cnt++;
+}
+
+/*
+ * vxge_hw_channel_dtr_free - Frees a dtr
+ * @channel: Channel handle
+ * @dtr:  DTR pointer
+ *
+ * Returns the dtr to free array
+ *
+ */
+void vxge_hw_channel_dtr_free(struct __vxge_hw_channel *channel, void *dtrh)
+{
+	channel->free_arr[--channel->free_ptr] = dtrh;
+}
+
+/*
+ * vxge_hw_channel_dtr_count
+ * @channel: Channel handle. Obtained via vxge_hw_channel_open().
+ *
+ * Retreive number of DTRs available. This function can not be called
+ * from data path. ring_initial_replenishi() is the only user.
+ */
+int vxge_hw_channel_dtr_count(struct __vxge_hw_channel *channel)
+{
+	return (channel->reserve_ptr - channel->reserve_top) +
+		(channel->length - channel->free_ptr);
+}
+
+/**
+ * vxge_hw_ring_rxd_reserve	- Reserve ring descriptor.
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Reserved descriptor. On success HW fills this "out" parameter
+ * with a valid handle.
+ *
+ * Reserve Rx descriptor for the subsequent filling-in driver
+ * and posting on the corresponding channel (@channelh)
+ * via vxge_hw_ring_rxd_post().
+ *
+ * Returns: VXGE_HW_OK - success.
+ * VXGE_HW_INF_OUT_OF_DESCRIPTORS - Currently no descriptors available.
+ *
+ */
+enum vxge_hw_status vxge_hw_ring_rxd_reserve(struct __vxge_hw_ring *ring,
+	void **rxdh)
+{
+	enum vxge_hw_status status;
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	status = vxge_hw_channel_dtr_alloc(channel, rxdh);
+
+	if (status == VXGE_HW_OK) {
+		struct vxge_hw_ring_rxd_1 *rxdp =
+			(struct vxge_hw_ring_rxd_1 *)*rxdh;
+
+		rxdp->control_0	= rxdp->control_1 = 0;
+	}
+
+	return status;
+}
+
+/**
+ * vxge_hw_ring_rxd_free - Free descriptor.
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Descriptor handle.
+ *
+ * Free	the reserved descriptor. This operation is "symmetrical" to
+ * vxge_hw_ring_rxd_reserve. The "free-ing" completes the descriptor's
+ * lifecycle.
+ *
+ * After free-ing (see vxge_hw_ring_rxd_free()) the descriptor again can
+ * be:
+ *
+ * - reserved (vxge_hw_ring_rxd_reserve);
+ *
+ * - posted	(vxge_hw_ring_rxd_post);
+ *
+ * - completed (vxge_hw_ring_rxd_next_completed);
+ *
+ * - and recycled again	(vxge_hw_ring_rxd_free).
+ *
+ * For alternative state transitions and more details please refer to
+ * the design doc.
+ *
+ */
+void vxge_hw_ring_rxd_free(struct __vxge_hw_ring *ring, void *rxdh)
+{
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	vxge_hw_channel_dtr_free(channel, rxdh);
+
+}
+
+/**
+ * vxge_hw_ring_rxd_pre_post - Prepare rxd and post
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Descriptor handle.
+ *
+ * This routine prepares a rxd and posts
+ */
+void vxge_hw_ring_rxd_pre_post(struct __vxge_hw_ring *ring, void *rxdh)
+{
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	vxge_hw_channel_dtr_post(channel, rxdh);
+}
+
+/**
+ * vxge_hw_ring_rxd_post_post - Process rxd after post.
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Descriptor handle.
+ *
+ * Processes rxd after post
+ */
+void vxge_hw_ring_rxd_post_post(struct __vxge_hw_ring *ring, void *rxdh)
+{
+	struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh;
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	rxdp->control_0	|= VXGE_HW_RING_RXD_LIST_OWN_ADAPTER;
+
+	if (ring->stats->common_stats.usage_cnt > 0)
+		ring->stats->common_stats.usage_cnt--;
+}
+
+/**
+ * vxge_hw_ring_rxd_post - Post descriptor on the ring.
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Descriptor obtained via vxge_hw_ring_rxd_reserve().
+ *
+ * Post	descriptor on the ring.
+ * Prior to posting the	descriptor should be filled in accordance with
+ * Host/Titan interface specification for a given service (LL, etc.).
+ *
+ */
+void vxge_hw_ring_rxd_post(struct __vxge_hw_ring *ring, void *rxdh)
+{
+	struct vxge_hw_ring_rxd_1 *rxdp = (struct vxge_hw_ring_rxd_1 *)rxdh;
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	wmb();
+	rxdp->control_0	|= VXGE_HW_RING_RXD_LIST_OWN_ADAPTER;
+
+	vxge_hw_channel_dtr_post(channel, rxdh);
+
+	if (ring->stats->common_stats.usage_cnt > 0)
+		ring->stats->common_stats.usage_cnt--;
+}
+
+/**
+ * vxge_hw_ring_rxd_post_post_wmb - Process rxd after post with memory barrier.
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Descriptor handle.
+ *
+ * Processes rxd after post with memory barrier.
+ */
+void vxge_hw_ring_rxd_post_post_wmb(struct __vxge_hw_ring *ring, void *rxdh)
+{
+	struct __vxge_hw_channel *channel;
+
+	channel = &ring->channel;
+
+	wmb();
+	vxge_hw_ring_rxd_post_post(ring, rxdh);
+}
+
+/**
+ * vxge_hw_ring_rxd_next_completed - Get the _next_ completed descriptor.
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Descriptor handle. Returned by HW.
+ * @t_code:	Transfer code, as per Titan User Guide,
+ *	 Receive Descriptor Format. Returned by HW.
+ *
+ * Retrieve the	_next_ completed descriptor.
+ * HW uses ring callback (*vxge_hw_ring_callback_f) to notifiy
+ * driver of new completed descriptors. After that
+ * the driver can use vxge_hw_ring_rxd_next_completed to retrieve the rest
+ * completions (the very first completion is passed by HW via
+ * vxge_hw_ring_callback_f).
+ *
+ * Implementation-wise, the driver is free to call
+ * vxge_hw_ring_rxd_next_completed either immediately from inside the
+ * ring callback, or in a deferred fashion and separate (from HW)
+ * context.
+ *
+ * Non-zero @t_code means failure to fill-in receive buffer(s)
+ * of the descriptor.
+ * For instance, parity	error detected during the data transfer.
+ * In this case	Titan will complete the descriptor and indicate
+ * for the host	that the received data is not to be used.
+ * For details please refer to Titan User Guide.
+ *
+ * Returns: VXGE_HW_OK - success.
+ * VXGE_HW_INF_NO_MORE_COMPLETED_DESCRIPTORS - No completed descriptors
+ * are currently available for processing.
+ *
+ * See also: vxge_hw_ring_callback_f{},
+ * vxge_hw_fifo_rxd_next_completed(), enum vxge_hw_status{}.
+ */
+enum vxge_hw_status vxge_hw_ring_rxd_next_completed(
+	struct __vxge_hw_ring *ring, void **rxdh, u8 *t_code)
+{
+	struct __vxge_hw_channel *channel;
+	struct vxge_hw_ring_rxd_1 *rxdp;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	channel = &ring->channel;
+
+	vxge_hw_channel_dtr_try_complete(channel, rxdh);
+
+	rxdp = (struct vxge_hw_ring_rxd_1 *)*rxdh;
+	if (rxdp == NULL) {
+		status = VXGE_HW_INF_NO_MORE_COMPLETED_DESCRIPTORS;
+		goto exit;
+	}
+
+	/* check whether it is not the end */
+	if (!(rxdp->control_0 &	VXGE_HW_RING_RXD_LIST_OWN_ADAPTER)) {
+
+		vxge_assert(((struct vxge_hw_ring_rxd_1 *)rxdp)->host_control !=
+				0);
+
+		++ring->cmpl_cnt;
+		vxge_hw_channel_dtr_complete(channel);
+
+		*t_code	= (u8)VXGE_HW_RING_RXD_T_CODE_GET(rxdp->control_0);
+
+		vxge_assert(*t_code != VXGE_HW_RING_RXD_T_CODE_UNUSED);
+
+		ring->stats->common_stats.usage_cnt++;
+		if (ring->stats->common_stats.usage_max <
+				ring->stats->common_stats.usage_cnt)
+			ring->stats->common_stats.usage_max =
+				ring->stats->common_stats.usage_cnt;
+
+		status = VXGE_HW_OK;
+		goto exit;
+	}
+
+	/* reset it. since we don't want to return
+	 * garbage to the driver */
+	*rxdh =	NULL;
+	status = VXGE_HW_INF_NO_MORE_COMPLETED_DESCRIPTORS;
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_ring_handle_tcode - Handle transfer code.
+ * @ring: Handle to the ring object used for receive
+ * @rxdh: Descriptor handle.
+ * @t_code: One of the enumerated (and documented in the Titan user guide)
+ * "transfer codes".
+ *
+ * Handle descriptor's transfer code. The latter comes with each completed
+ * descriptor.
+ *
+ * Returns: one of the enum vxge_hw_status{} enumerated types.
+ * VXGE_HW_OK			- for success.
+ * VXGE_HW_ERR_CRITICAL         - when encounters critical error.
+ */
+enum vxge_hw_status vxge_hw_ring_handle_tcode(
+	struct __vxge_hw_ring *ring, void *rxdh, u8 t_code)
+{
+	struct __vxge_hw_channel *channel;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	channel = &ring->channel;
+
+	/* If the t_code is not supported and if the
+	 * t_code is other than 0x5 (unparseable packet
+	 * such as unknown UPV6 header), Drop it !!!
+	 */
+
+	if (t_code == 0 || t_code == 5) {
+		status = VXGE_HW_OK;
+		goto exit;
+	}
+
+	if (t_code > 0xF) {
+		status = VXGE_HW_ERR_INVALID_TCODE;
+		goto exit;
+	}
+
+	ring->stats->rxd_t_code_err_cnt[t_code]++;
+exit:
+	return status;
+}
+
+/**
+ * __vxge_hw_non_offload_db_post - Post non offload doorbell
+ *
+ * @fifo: fifohandle
+ * @txdl_ptr: The starting location of the TxDL in host memory
+ * @num_txds: The highest TxD in this TxDL (0 to 255 means 1 to 256)
+ * @no_snoop: No snoop flags
+ *
+ * This function posts a non-offload doorbell to doorbell FIFO
+ *
+ */
+static void __vxge_hw_non_offload_db_post(struct __vxge_hw_fifo *fifo,
+	u64 txdl_ptr, u32 num_txds, u32 no_snoop)
+{
+	struct __vxge_hw_channel *channel;
+
+	channel = &fifo->channel;
+
+	writeq(VXGE_HW_NODBW_TYPE(VXGE_HW_NODBW_TYPE_NODBW) |
+		VXGE_HW_NODBW_LAST_TXD_NUMBER(num_txds) |
+		VXGE_HW_NODBW_GET_NO_SNOOP(no_snoop),
+		&fifo->nofl_db->control_0);
+
+	wmb();
+
+	writeq(txdl_ptr, &fifo->nofl_db->txdl_ptr);
+	wmb();
+
+}
+
+/**
+ * vxge_hw_fifo_free_txdl_count_get - returns the number of txdls available in
+ * the fifo
+ * @fifoh: Handle to the fifo object used for non offload send
+ */
+u32 vxge_hw_fifo_free_txdl_count_get(struct __vxge_hw_fifo *fifoh)
+{
+	return vxge_hw_channel_dtr_count(&fifoh->channel);
+}
+
+/**
+ * vxge_hw_fifo_txdl_reserve - Reserve fifo descriptor.
+ * @fifoh: Handle to the fifo object used for non offload send
+ * @txdlh: Reserved descriptor. On success HW fills this "out" parameter
+ *        with a valid handle.
+ * @txdl_priv: Buffer to return the pointer to per txdl space
+ *
+ * Reserve a single TxDL (that is, fifo descriptor)
+ * for the subsequent filling-in by driver)
+ * and posting on the corresponding channel (@channelh)
+ * via vxge_hw_fifo_txdl_post().
+ *
+ * Note: it is the responsibility of driver to reserve multiple descriptors
+ * for lengthy (e.g., LSO) transmit operation. A single fifo descriptor
+ * carries up to configured number (fifo.max_frags) of contiguous buffers.
+ *
+ * Returns: VXGE_HW_OK - success;
+ * VXGE_HW_INF_OUT_OF_DESCRIPTORS - Currently no descriptors available
+ *
+ */
+enum vxge_hw_status vxge_hw_fifo_txdl_reserve(
+	struct __vxge_hw_fifo *fifo,
+	void **txdlh, void **txdl_priv)
+{
+	struct __vxge_hw_channel *channel;
+	enum vxge_hw_status status;
+	int i;
+
+	channel = &fifo->channel;
+
+	status = vxge_hw_channel_dtr_alloc(channel, txdlh);
+
+	if (status == VXGE_HW_OK) {
+		struct vxge_hw_fifo_txd *txdp =
+			(struct vxge_hw_fifo_txd *)*txdlh;
+		struct __vxge_hw_fifo_txdl_priv *priv;
+
+		priv = __vxge_hw_fifo_txdl_priv(fifo, txdp);
+
+		/* reset the TxDL's private */
+		priv->align_dma_offset = 0;
+		priv->align_vaddr_start = priv->align_vaddr;
+		priv->align_used_frags = 0;
+		priv->frags = 0;
+		priv->alloc_frags = fifo->config->max_frags;
+		priv->next_txdl_priv = NULL;
+
+		*txdl_priv = (void *)(size_t)txdp->host_control;
+
+		for (i = 0; i < fifo->config->max_frags; i++) {
+			txdp = ((struct vxge_hw_fifo_txd *)*txdlh) + i;
+			txdp->control_0 = txdp->control_1 = 0;
+		}
+	}
+
+	return status;
+}
+
+/**
+ * vxge_hw_fifo_txdl_buffer_set - Set transmit buffer pointer in the
+ * descriptor.
+ * @fifo: Handle to the fifo object used for non offload send
+ * @txdlh: Descriptor handle.
+ * @frag_idx: Index of the data buffer in the caller's scatter-gather list
+ *            (of buffers).
+ * @dma_pointer: DMA address of the data buffer referenced by @frag_idx.
+ * @size: Size of the data buffer (in bytes).
+ *
+ * This API is part of the preparation of the transmit descriptor for posting
+ * (via vxge_hw_fifo_txdl_post()). The related "preparation" APIs include
+ * vxge_hw_fifo_txdl_mss_set() and vxge_hw_fifo_txdl_cksum_set_bits().
+ * All three APIs fill in the fields of the fifo descriptor,
+ * in accordance with the Titan specification.
+ *
+ */
+void vxge_hw_fifo_txdl_buffer_set(struct __vxge_hw_fifo *fifo,
+				  void *txdlh, u32 frag_idx,
+				  dma_addr_t dma_pointer, u32 size)
+{
+	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
+	struct vxge_hw_fifo_txd *txdp, *txdp_last;
+	struct __vxge_hw_channel *channel;
+
+	channel = &fifo->channel;
+
+	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh);
+	txdp = (struct vxge_hw_fifo_txd *)txdlh  +  txdl_priv->frags;
+
+	if (frag_idx != 0)
+		txdp->control_0 = txdp->control_1 = 0;
+	else {
+		txdp->control_0 |= VXGE_HW_FIFO_TXD_GATHER_CODE(
+			VXGE_HW_FIFO_TXD_GATHER_CODE_FIRST);
+		txdp->control_1 |= fifo->interrupt_type;
+		txdp->control_1 |= VXGE_HW_FIFO_TXD_INT_NUMBER(
+			fifo->tx_intr_num);
+		if (txdl_priv->frags) {
+			txdp_last = (struct vxge_hw_fifo_txd *)txdlh  +
+			(txdl_priv->frags - 1);
+			txdp_last->control_0 |= VXGE_HW_FIFO_TXD_GATHER_CODE(
+				VXGE_HW_FIFO_TXD_GATHER_CODE_LAST);
+		}
+	}
+
+	vxge_assert(frag_idx < txdl_priv->alloc_frags);
+
+	txdp->buffer_pointer = (u64)dma_pointer;
+	txdp->control_0 |= VXGE_HW_FIFO_TXD_BUFFER_SIZE(size);
+	fifo->stats->total_buffers++;
+	txdl_priv->frags++;
+}
+
+/**
+ * vxge_hw_fifo_txdl_post - Post descriptor on the fifo channel.
+ * @fifo: Handle to the fifo object used for non offload send
+ * @txdlh: Descriptor obtained via vxge_hw_fifo_txdl_reserve()
+ * @frags: Number of contiguous buffers that are part of a single
+ *         transmit operation.
+ *
+ * Post descriptor on the 'fifo' type channel for transmission.
+ * Prior to posting the descriptor should be filled in accordance with
+ * Host/Titan interface specification for a given service (LL, etc.).
+ *
+ */
+void vxge_hw_fifo_txdl_post(struct __vxge_hw_fifo *fifo, void *txdlh)
+{
+	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
+	struct vxge_hw_fifo_txd *txdp_last;
+	struct vxge_hw_fifo_txd *txdp_first;
+	struct __vxge_hw_channel *channel;
+
+	channel = &fifo->channel;
+
+	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo, txdlh);
+	txdp_first = (struct vxge_hw_fifo_txd *)txdlh;
+
+	txdp_last = (struct vxge_hw_fifo_txd *)txdlh  +  (txdl_priv->frags - 1);
+	txdp_last->control_0 |=
+	      VXGE_HW_FIFO_TXD_GATHER_CODE(VXGE_HW_FIFO_TXD_GATHER_CODE_LAST);
+	txdp_first->control_0 |= VXGE_HW_FIFO_TXD_LIST_OWN_ADAPTER;
+
+	vxge_hw_channel_dtr_post(&fifo->channel, txdlh);
+
+	__vxge_hw_non_offload_db_post(fifo,
+		(u64)(size_t)txdl_priv->dma_addr,
+		txdl_priv->frags - 1,
+		fifo->no_snoop_bits);
+
+	fifo->stats->total_posts++;
+	fifo->stats->common_stats.usage_cnt++;
+	if (fifo->stats->common_stats.usage_max <
+		fifo->stats->common_stats.usage_cnt)
+		fifo->stats->common_stats.usage_max =
+			fifo->stats->common_stats.usage_cnt;
+}
+
+/**
+ * vxge_hw_fifo_txdl_next_completed - Retrieve next completed descriptor.
+ * @fifo: Handle to the fifo object used for non offload send
+ * @txdlh: Descriptor handle. Returned by HW.
+ * @t_code: Transfer code, as per Titan User Guide,
+ *          Transmit Descriptor Format.
+ *          Returned by HW.
+ *
+ * Retrieve the _next_ completed descriptor.
+ * HW uses channel callback (*vxge_hw_channel_callback_f) to notifiy
+ * driver of new completed descriptors. After that
+ * the driver can use vxge_hw_fifo_txdl_next_completed to retrieve the rest
+ * completions (the very first completion is passed by HW via
+ * vxge_hw_channel_callback_f).
+ *
+ * Implementation-wise, the driver is free to call
+ * vxge_hw_fifo_txdl_next_completed either immediately from inside the
+ * channel callback, or in a deferred fashion and separate (from HW)
+ * context.
+ *
+ * Non-zero @t_code means failure to process the descriptor.
+ * The failure could happen, for instance, when the link is
+ * down, in which case Titan completes the descriptor because it
+ * is not able to send the data out.
+ *
+ * For details please refer to Titan User Guide.
+ *
+ * Returns: VXGE_HW_OK - success.
+ * VXGE_HW_INF_NO_MORE_COMPLETED_DESCRIPTORS - No completed descriptors
+ * are currently available for processing.
+ *
+ */
+enum vxge_hw_status vxge_hw_fifo_txdl_next_completed(
+	struct __vxge_hw_fifo *fifo, void **txdlh,
+	enum vxge_hw_fifo_tcode *t_code)
+{
+	struct __vxge_hw_channel *channel;
+	struct vxge_hw_fifo_txd *txdp;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	channel = &fifo->channel;
+
+	vxge_hw_channel_dtr_try_complete(channel, txdlh);
+
+	txdp = (struct vxge_hw_fifo_txd *)*txdlh;
+	if (txdp == NULL) {
+		status = VXGE_HW_INF_NO_MORE_COMPLETED_DESCRIPTORS;
+		goto exit;
+	}
+
+	/* check whether host owns it */
+	if (!(txdp->control_0 & VXGE_HW_FIFO_TXD_LIST_OWN_ADAPTER)) {
+
+		vxge_assert(txdp->host_control != 0);
+
+		vxge_hw_channel_dtr_complete(channel);
+
+		*t_code = (u8)VXGE_HW_FIFO_TXD_T_CODE_GET(txdp->control_0);
+
+		if (fifo->stats->common_stats.usage_cnt > 0)
+			fifo->stats->common_stats.usage_cnt--;
+
+		status = VXGE_HW_OK;
+		goto exit;
+	}
+
+	/* no more completions */
+	*txdlh = NULL;
+	status = VXGE_HW_INF_NO_MORE_COMPLETED_DESCRIPTORS;
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_fifo_handle_tcode - Handle transfer code.
+ * @fifo: Handle to the fifo object used for non offload send
+ * @txdlh: Descriptor handle.
+ * @t_code: One of the enumerated (and documented in the Titan user guide)
+ *          "transfer codes".
+ *
+ * Handle descriptor's transfer code. The latter comes with each completed
+ * descriptor.
+ *
+ * Returns: one of the enum vxge_hw_status{} enumerated types.
+ * VXGE_HW_OK - for success.
+ * VXGE_HW_ERR_CRITICAL - when encounters critical error.
+ */
+enum vxge_hw_status vxge_hw_fifo_handle_tcode(struct __vxge_hw_fifo *fifo,
+					      void *txdlh,
+					      enum vxge_hw_fifo_tcode t_code)
+{
+	struct __vxge_hw_channel *channel;
+
+	enum vxge_hw_status status = VXGE_HW_OK;
+	channel = &fifo->channel;
+
+	if (((t_code & 0x7) < 0) || ((t_code & 0x7) > 0x4)) {
+		status = VXGE_HW_ERR_INVALID_TCODE;
+		goto exit;
+	}
+
+	fifo->stats->txd_t_code_err_cnt[t_code]++;
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_fifo_txdl_free - Free descriptor.
+ * @fifo: Handle to the fifo object used for non offload send
+ * @txdlh: Descriptor handle.
+ *
+ * Free the reserved descriptor. This operation is "symmetrical" to
+ * vxge_hw_fifo_txdl_reserve. The "free-ing" completes the descriptor's
+ * lifecycle.
+ *
+ * After free-ing (see vxge_hw_fifo_txdl_free()) the descriptor again can
+ * be:
+ *
+ * - reserved (vxge_hw_fifo_txdl_reserve);
+ *
+ * - posted (vxge_hw_fifo_txdl_post);
+ *
+ * - completed (vxge_hw_fifo_txdl_next_completed);
+ *
+ * - and recycled again (vxge_hw_fifo_txdl_free).
+ *
+ * For alternative state transitions and more details please refer to
+ * the design doc.
+ *
+ */
+void vxge_hw_fifo_txdl_free(struct __vxge_hw_fifo *fifo, void *txdlh)
+{
+	struct __vxge_hw_fifo_txdl_priv *txdl_priv;
+	u32 max_frags;
+	struct __vxge_hw_channel *channel;
+
+	channel = &fifo->channel;
+
+	txdl_priv = __vxge_hw_fifo_txdl_priv(fifo,
+			(struct vxge_hw_fifo_txd *)txdlh);
+
+	max_frags = fifo->config->max_frags;
+
+	vxge_hw_channel_dtr_free(channel, txdlh);
+}
+
+/**
+ * vxge_hw_vpath_mac_addr_add - Add the mac address entry for this vpath
+ *               to MAC address table.
+ * @vp: Vpath handle.
+ * @macaddr: MAC address to be added for this vpath into the list
+ * @macaddr_mask: MAC address mask for macaddr
+ * @duplicate_mode: Duplicate MAC address add mode. Please see
+ *             enum vxge_hw_vpath_mac_addr_add_mode{}
+ *
+ * Adds the given mac address and mac address mask into the list for this
+ * vpath.
+ * see also: vxge_hw_vpath_mac_addr_delete, vxge_hw_vpath_mac_addr_get and
+ * vxge_hw_vpath_mac_addr_get_next
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_add(
+	struct __vxge_hw_vpath_handle *vp,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN],
+	enum vxge_hw_vpath_mac_addr_add_mode duplicate_mode)
+{
+	u32 i;
+	u64 data1 = 0ULL;
+	u64 data2 = 0ULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		data1 <<= 8;
+		data1 |= (u8)macaddr[i];
+
+		data2 <<= 8;
+		data2 |= (u8)macaddr_mask[i];
+	}
+
+	switch (duplicate_mode) {
+	case VXGE_HW_VPATH_MAC_ADDR_ADD_DUPLICATE:
+		i = 0;
+		break;
+	case VXGE_HW_VPATH_MAC_ADDR_DISCARD_DUPLICATE:
+		i = 1;
+		break;
+	case VXGE_HW_VPATH_MAC_ADDR_REPLACE_DUPLICATE:
+		i = 2;
+		break;
+	default:
+		i = 0;
+		break;
+	}
+
+	status = __vxge_hw_vpath_rts_table_set(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_ADD_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA,
+			0,
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_DA_MAC_ADDR(data1),
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_DA_MAC_ADDR_MASK(data2)|
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_DA_MAC_ADDR_MODE(i));
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_mac_addr_get - Get the first mac address entry for this vpath
+ *               from MAC address table.
+ * @vp: Vpath handle.
+ * @macaddr: First MAC address entry for this vpath in the list
+ * @macaddr_mask: MAC address mask for macaddr
+ *
+ * Returns the first mac address and mac address mask in the list for this
+ * vpath.
+ * see also: vxge_hw_vpath_mac_addr_get_next
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_get(
+	struct __vxge_hw_vpath_handle *vp,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN])
+{
+	u32 i;
+	u64 data1 = 0ULL;
+	u64 data2 = 0ULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_rts_table_get(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA,
+			0, &data1, &data2);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	data1 = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(data1);
+
+	data2 = VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK(data2);
+
+	for (i = ETH_ALEN; i > 0; i--) {
+		macaddr[i-1] = (u8)(data1 & 0xFF);
+		data1 >>= 8;
+
+		macaddr_mask[i-1] = (u8)(data2 & 0xFF);
+		data2 >>= 8;
+	}
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_mac_addr_get_next - Get the next mac address entry for this
+ * vpath
+ *               from MAC address table.
+ * @vp: Vpath handle.
+ * @macaddr: Next MAC address entry for this vpath in the list
+ * @macaddr_mask: MAC address mask for macaddr
+ *
+ * Returns the next mac address and mac address mask in the list for this
+ * vpath.
+ * see also: vxge_hw_vpath_mac_addr_get
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_get_next(
+	struct __vxge_hw_vpath_handle *vp,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN])
+{
+	u32 i;
+	u64 data1 = 0ULL;
+	u64 data2 = 0ULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_rts_table_get(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_NEXT_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA,
+			0, &data1, &data2);
+
+	if (status != VXGE_HW_OK)
+		goto exit;
+
+	data1 = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_DA_MAC_ADDR(data1);
+
+	data2 = VXGE_HW_RTS_ACCESS_STEER_DATA1_GET_DA_MAC_ADDR_MASK(data2);
+
+	for (i = ETH_ALEN; i > 0; i--) {
+		macaddr[i-1] = (u8)(data1 & 0xFF);
+		data1 >>= 8;
+
+		macaddr_mask[i-1] = (u8)(data2 & 0xFF);
+		data2 >>= 8;
+	}
+
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_mac_addr_delete - Delete the mac address entry for this vpath
+ *               to MAC address table.
+ * @vp: Vpath handle.
+ * @macaddr: MAC address to be added for this vpath into the list
+ * @macaddr_mask: MAC address mask for macaddr
+ *
+ * Delete the given mac address and mac address mask into the list for this
+ * vpath.
+ * see also: vxge_hw_vpath_mac_addr_add, vxge_hw_vpath_mac_addr_get and
+ * vxge_hw_vpath_mac_addr_get_next
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_delete(
+	struct __vxge_hw_vpath_handle *vp,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN])
+{
+	u32 i;
+	u64 data1 = 0ULL;
+	u64 data2 = 0ULL;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	for (i = 0; i < ETH_ALEN; i++) {
+		data1 <<= 8;
+		data1 |= (u8)macaddr[i];
+
+		data2 <<= 8;
+		data2 |= (u8)macaddr_mask[i];
+	}
+
+	status = __vxge_hw_vpath_rts_table_set(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_DELETE_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_DA,
+			0,
+			VXGE_HW_RTS_ACCESS_STEER_DATA0_DA_MAC_ADDR(data1),
+			VXGE_HW_RTS_ACCESS_STEER_DATA1_DA_MAC_ADDR_MASK(data2));
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_vid_add - Add the vlan id entry for this vpath
+ *               to vlan id table.
+ * @vp: Vpath handle.
+ * @vid: vlan id to be added for this vpath into the list
+ *
+ * Adds the given vlan id into the list for this  vpath.
+ * see also: vxge_hw_vpath_vid_delete, vxge_hw_vpath_vid_get and
+ * vxge_hw_vpath_vid_get_next
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_vid_add(struct __vxge_hw_vpath_handle *vp, u64 vid)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_rts_table_set(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_ADD_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_VID,
+			0, VXGE_HW_RTS_ACCESS_STEER_DATA0_VLAN_ID(vid), 0);
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_vid_get - Get the first vid entry for this vpath
+ *               from vlan id table.
+ * @vp: Vpath handle.
+ * @vid: Buffer to return vlan id
+ *
+ * Returns the first vlan id in the list for this vpath.
+ * see also: vxge_hw_vpath_vid_get_next
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_vid_get(struct __vxge_hw_vpath_handle *vp, u64 *vid)
+{
+	u64 data;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_rts_table_get(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_FIRST_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_VID,
+			0, vid, &data);
+
+	*vid = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_VLAN_ID(*vid);
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_vid_get_next - Get the next vid entry for this vpath
+ *               from vlan id table.
+ * @vp: Vpath handle.
+ * @vid: Buffer to return vlan id
+ *
+ * Returns the next vlan id in the list for this vpath.
+ * see also: vxge_hw_vpath_vid_get
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_vid_get_next(struct __vxge_hw_vpath_handle *vp, u64 *vid)
+{
+	u64 data;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_rts_table_get(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_LIST_NEXT_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_VID,
+			0, vid, &data);
+
+	*vid = VXGE_HW_RTS_ACCESS_STEER_DATA0_GET_VLAN_ID(*vid);
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_vid_delete - Delete the vlan id entry for this vpath
+ *               to vlan id table.
+ * @vp: Vpath handle.
+ * @vid: vlan id to be added for this vpath into the list
+ *
+ * Adds the given vlan id into the list for this  vpath.
+ * see also: vxge_hw_vpath_vid_add, vxge_hw_vpath_vid_get and
+ * vxge_hw_vpath_vid_get_next
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_vid_delete(struct __vxge_hw_vpath_handle *vp, u64 vid)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_rts_table_set(vp,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_ACTION_DELETE_ENTRY,
+			VXGE_HW_RTS_ACCESS_STEER_CTRL_DATA_STRUCT_SEL_VID,
+			0, VXGE_HW_RTS_ACCESS_STEER_DATA0_VLAN_ID(vid), 0);
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_promisc_enable - Enable promiscuous mode.
+ * @vp: Vpath handle.
+ *
+ * Enable promiscuous mode of Titan-e operation.
+ *
+ * See also: vxge_hw_vpath_promisc_disable().
+ */
+enum vxge_hw_status vxge_hw_vpath_promisc_enable(
+			struct __vxge_hw_vpath_handle *vp)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((vp == NULL) || (vp->vpath->ringh == NULL)) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+
+	/* Enable promiscous mode for function 0 only */
+	if (!(vpath->hldev->access_rights &
+		VXGE_HW_DEVICE_ACCESS_RIGHT_MRPCIM))
+		return VXGE_HW_OK;
+
+	val64 = readq(&vpath->vp_reg->rxmac_vcfg0);
+
+	if (!(val64 & VXGE_HW_RXMAC_VCFG0_UCAST_ALL_ADDR_EN)) {
+
+		val64 |= VXGE_HW_RXMAC_VCFG0_UCAST_ALL_ADDR_EN |
+			 VXGE_HW_RXMAC_VCFG0_MCAST_ALL_ADDR_EN |
+			 VXGE_HW_RXMAC_VCFG0_BCAST_EN |
+			 VXGE_HW_RXMAC_VCFG0_ALL_VID_EN;
+
+		writeq(val64, &vpath->vp_reg->rxmac_vcfg0);
+	}
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_promisc_disable - Disable promiscuous mode.
+ * @vp: Vpath handle.
+ *
+ * Disable promiscuous mode of Titan-e operation.
+ *
+ * See also: vxge_hw_vpath_promisc_enable().
+ */
+enum vxge_hw_status vxge_hw_vpath_promisc_disable(
+			struct __vxge_hw_vpath_handle *vp)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((vp == NULL) || (vp->vpath->ringh == NULL)) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+
+	val64 = readq(&vpath->vp_reg->rxmac_vcfg0);
+
+	if (val64 & VXGE_HW_RXMAC_VCFG0_UCAST_ALL_ADDR_EN) {
+
+		val64 &= ~(VXGE_HW_RXMAC_VCFG0_UCAST_ALL_ADDR_EN |
+			   VXGE_HW_RXMAC_VCFG0_MCAST_ALL_ADDR_EN |
+			   VXGE_HW_RXMAC_VCFG0_ALL_VID_EN);
+
+		writeq(val64, &vpath->vp_reg->rxmac_vcfg0);
+	}
+exit:
+	return status;
+}
+
+/*
+ * vxge_hw_vpath_bcast_enable - Enable broadcast
+ * @vp: Vpath handle.
+ *
+ * Enable receiving broadcasts.
+ */
+enum vxge_hw_status vxge_hw_vpath_bcast_enable(
+			struct __vxge_hw_vpath_handle *vp)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((vp == NULL) || (vp->vpath->ringh == NULL)) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+
+	val64 = readq(&vpath->vp_reg->rxmac_vcfg0);
+
+	if (!(val64 & VXGE_HW_RXMAC_VCFG0_BCAST_EN)) {
+		val64 |= VXGE_HW_RXMAC_VCFG0_BCAST_EN;
+		writeq(val64, &vpath->vp_reg->rxmac_vcfg0);
+	}
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_mcast_enable - Enable multicast addresses.
+ * @vp: Vpath handle.
+ *
+ * Enable Titan-e multicast addresses.
+ * Returns: VXGE_HW_OK on success.
+ *
+ */
+enum vxge_hw_status vxge_hw_vpath_mcast_enable(
+			struct __vxge_hw_vpath_handle *vp)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((vp == NULL) || (vp->vpath->ringh == NULL)) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+
+	val64 = readq(&vpath->vp_reg->rxmac_vcfg0);
+
+	if (!(val64 & VXGE_HW_RXMAC_VCFG0_MCAST_ALL_ADDR_EN)) {
+		val64 |= VXGE_HW_RXMAC_VCFG0_MCAST_ALL_ADDR_EN;
+		writeq(val64, &vpath->vp_reg->rxmac_vcfg0);
+	}
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_mcast_disable - Disable  multicast addresses.
+ * @vp: Vpath handle.
+ *
+ * Disable Titan-e multicast addresses.
+ * Returns: VXGE_HW_OK - success.
+ * VXGE_HW_ERR_INVALID_HANDLE - Invalid handle
+ *
+ */
+enum vxge_hw_status
+vxge_hw_vpath_mcast_disable(struct __vxge_hw_vpath_handle *vp)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath;
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if ((vp == NULL) || (vp->vpath->ringh == NULL)) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	vpath = vp->vpath;
+
+	val64 = readq(&vpath->vp_reg->rxmac_vcfg0);
+
+	if (val64 & VXGE_HW_RXMAC_VCFG0_MCAST_ALL_ADDR_EN) {
+		val64 &= ~VXGE_HW_RXMAC_VCFG0_MCAST_ALL_ADDR_EN;
+		writeq(val64, &vpath->vp_reg->rxmac_vcfg0);
+	}
+exit:
+	return status;
+}
+
+/*
+ * __vxge_hw_vpath_alarm_process - Process Alarms.
+ * @vpath: Virtual Path.
+ * @skip_alarms: Do not clear the alarms
+ *
+ * Process vpath alarms.
+ *
+ */
+enum vxge_hw_status __vxge_hw_vpath_alarm_process(
+			struct __vxge_hw_virtualpath *vpath,
+			u32 skip_alarms)
+{
+	u64 val64;
+	u64 alarm_status;
+	u64 pic_status;
+	struct __vxge_hw_device *hldev = NULL;
+	enum vxge_hw_event alarm_event = VXGE_HW_EVENT_UNKNOWN;
+	u64 mask64;
+	struct vxge_hw_vpath_stats_sw_info *sw_stats;
+	struct vxge_hw_vpath_reg __iomem *vp_reg;
+
+	if (vpath == NULL) {
+		alarm_event = VXGE_HW_SET_LEVEL(VXGE_HW_EVENT_UNKNOWN,
+			alarm_event);
+		goto out;
+	}
+
+	hldev = vpath->hldev;
+	vp_reg = vpath->vp_reg;
+	alarm_status = readq(&vp_reg->vpath_general_int_status);
+
+	if (alarm_status == VXGE_HW_ALL_FOXES) {
+		alarm_event = VXGE_HW_SET_LEVEL(VXGE_HW_EVENT_SLOT_FREEZE,
+			alarm_event);
+		goto out;
+	}
+
+	sw_stats = vpath->sw_stats;
+
+	if (alarm_status & ~(
+		VXGE_HW_VPATH_GENERAL_INT_STATUS_PIC_INT |
+		VXGE_HW_VPATH_GENERAL_INT_STATUS_PCI_INT |
+		VXGE_HW_VPATH_GENERAL_INT_STATUS_WRDMA_INT |
+		VXGE_HW_VPATH_GENERAL_INT_STATUS_XMAC_INT)) {
+		sw_stats->error_stats.unknown_alarms++;
+
+		alarm_event = VXGE_HW_SET_LEVEL(VXGE_HW_EVENT_UNKNOWN,
+			alarm_event);
+		goto out;
+	}
+
+	if (alarm_status & VXGE_HW_VPATH_GENERAL_INT_STATUS_XMAC_INT) {
+
+		val64 = readq(&vp_reg->xgmac_vp_int_status);
+
+		if (val64 &
+		VXGE_HW_XGMAC_VP_INT_STATUS_ASIC_NTWK_VP_ERR_ASIC_NTWK_VP_INT) {
+
+			val64 = readq(&vp_reg->asic_ntwk_vp_err_reg);
+
+			if (((val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT) &&
+			    (!(val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK))) ||
+			    ((val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT_OCCURR)
+				&& (!(val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK_OCCURR)
+			))) {
+				sw_stats->error_stats.network_sustained_fault++;
+
+				writeq(
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT,
+					&vp_reg->asic_ntwk_vp_err_mask);
+
+				__vxge_hw_device_handle_link_down_ind(hldev);
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_LINK_DOWN, alarm_event);
+			}
+
+			if (((val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK) &&
+			    (!(val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT))) ||
+			    ((val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK_OCCURR)
+				&& (!(val64 &
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_FLT_OCCURR)
+			))) {
+
+				sw_stats->error_stats.network_sustained_ok++;
+
+				writeq(
+				VXGE_HW_ASIC_NW_VP_ERR_REG_XMACJ_STN_OK,
+					&vp_reg->asic_ntwk_vp_err_mask);
+
+				__vxge_hw_device_handle_link_up_ind(hldev);
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_LINK_UP, alarm_event);
+			}
+
+			writeq(VXGE_HW_INTR_MASK_ALL,
+				&vp_reg->asic_ntwk_vp_err_reg);
+
+			alarm_event = VXGE_HW_SET_LEVEL(
+				VXGE_HW_EVENT_ALARM_CLEARED, alarm_event);
+
+			if (skip_alarms)
+				return VXGE_HW_OK;
+		}
+	}
+
+	if (alarm_status & VXGE_HW_VPATH_GENERAL_INT_STATUS_PIC_INT) {
+
+		pic_status = readq(&vp_reg->vpath_ppif_int_status);
+
+		if (pic_status &
+		    VXGE_HW_VPATH_PPIF_INT_STATUS_GENERAL_ERRORS_GENERAL_INT) {
+
+			val64 = readq(&vp_reg->general_errors_reg);
+			mask64 = readq(&vp_reg->general_errors_mask);
+
+			if ((val64 &
+				VXGE_HW_GENERAL_ERRORS_REG_INI_SERR_DET) &
+				~mask64) {
+				sw_stats->error_stats.ini_serr_det++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_SERR, alarm_event);
+			}
+
+			if ((val64 &
+			    VXGE_HW_GENERAL_ERRORS_REG_DBLGEN_FIFO0_OVRFLOW) &
+				~mask64) {
+				sw_stats->error_stats.dblgen_fifo0_overflow++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_FIFO_ERR, alarm_event);
+			}
+
+			if ((val64 &
+			    VXGE_HW_GENERAL_ERRORS_REG_STATSB_PIF_CHAIN_ERR) &
+				~mask64)
+				sw_stats->error_stats.statsb_pif_chain_error++;
+
+			if ((val64 &
+			   VXGE_HW_GENERAL_ERRORS_REG_STATSB_DROP_TIMEOUT_REQ) &
+				~mask64)
+				sw_stats->error_stats.statsb_drop_timeout++;
+
+			if ((val64 &
+				VXGE_HW_GENERAL_ERRORS_REG_TGT_ILLEGAL_ACCESS) &
+				~mask64)
+				sw_stats->error_stats.target_illegal_access++;
+
+			if (!skip_alarms) {
+				writeq(VXGE_HW_INTR_MASK_ALL,
+					&vp_reg->general_errors_reg);
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_ALARM_CLEARED,
+					alarm_event);
+			}
+		}
+
+		if (pic_status &
+		    VXGE_HW_VPATH_PPIF_INT_STATUS_KDFCCTL_ERRORS_KDFCCTL_INT) {
+
+			val64 = readq(&vp_reg->kdfcctl_errors_reg);
+			mask64 = readq(&vp_reg->kdfcctl_errors_mask);
+
+			if ((val64 &
+			    VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO0_OVRWR) &
+				~mask64) {
+				sw_stats->error_stats.kdfcctl_fifo0_overwrite++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_FIFO_ERR,
+					alarm_event);
+			}
+
+			if ((val64 &
+			    VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO0_POISON) &
+				~mask64) {
+				sw_stats->error_stats.kdfcctl_fifo0_poison++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_FIFO_ERR,
+					alarm_event);
+			}
+
+			if ((val64 &
+			    VXGE_HW_KDFCCTL_ERRORS_REG_KDFCCTL_FIFO0_DMA_ERR) &
+				~mask64) {
+				sw_stats->error_stats.kdfcctl_fifo0_dma_error++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_FIFO_ERR,
+					alarm_event);
+			}
+
+			if (!skip_alarms) {
+				writeq(VXGE_HW_INTR_MASK_ALL,
+					&vp_reg->kdfcctl_errors_reg);
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_ALARM_CLEARED,
+					alarm_event);
+			}
+		}
+
+	}
+
+	if (alarm_status & VXGE_HW_VPATH_GENERAL_INT_STATUS_WRDMA_INT) {
+
+		val64 = readq(&vp_reg->wrdma_alarm_status);
+
+		if (val64 & VXGE_HW_WRDMA_ALARM_STATUS_PRC_ALARM_PRC_INT) {
+
+			val64 = readq(&vp_reg->prc_alarm_reg);
+			mask64 = readq(&vp_reg->prc_alarm_mask);
+
+			if ((val64 & VXGE_HW_PRC_ALARM_REG_PRC_RING_BUMP)&
+				~mask64)
+				sw_stats->error_stats.prc_ring_bumps++;
+
+			if ((val64 & VXGE_HW_PRC_ALARM_REG_PRC_RXDCM_SC_ERR) &
+				~mask64) {
+				sw_stats->error_stats.prc_rxdcm_sc_err++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_VPATH_ERR,
+					alarm_event);
+			}
+
+			if ((val64 & VXGE_HW_PRC_ALARM_REG_PRC_RXDCM_SC_ABORT)
+				& ~mask64) {
+				sw_stats->error_stats.prc_rxdcm_sc_abort++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+						VXGE_HW_EVENT_VPATH_ERR,
+						alarm_event);
+			}
+
+			if ((val64 & VXGE_HW_PRC_ALARM_REG_PRC_QUANTA_SIZE_ERR)
+				 & ~mask64) {
+				sw_stats->error_stats.prc_quanta_size_err++;
+
+				alarm_event = VXGE_HW_SET_LEVEL(
+					VXGE_HW_EVENT_VPATH_ERR,
+					alarm_event);
+			}
+
+			if (!skip_alarms) {
+				writeq(VXGE_HW_INTR_MASK_ALL,
+					&vp_reg->prc_alarm_reg);
+				alarm_event = VXGE_HW_SET_LEVEL(
+						VXGE_HW_EVENT_ALARM_CLEARED,
+						alarm_event);
+			}
+		}
+	}
+out:
+	hldev->stats.sw_dev_err_stats.vpath_alarms++;
+
+	if ((alarm_event == VXGE_HW_EVENT_ALARM_CLEARED) ||
+		(alarm_event == VXGE_HW_EVENT_UNKNOWN))
+		return VXGE_HW_OK;
+
+	__vxge_hw_device_handle_error(hldev, vpath->vp_id, alarm_event);
+
+	if (alarm_event == VXGE_HW_EVENT_SERR)
+		return VXGE_HW_ERR_CRITICAL;
+
+	return (alarm_event == VXGE_HW_EVENT_SLOT_FREEZE) ?
+		VXGE_HW_ERR_SLOT_FREEZE :
+		(alarm_event == VXGE_HW_EVENT_FIFO_ERR) ? VXGE_HW_ERR_FIFO :
+		VXGE_HW_ERR_VPATH;
+}
+
+/*
+ * vxge_hw_vpath_alarm_process - Process Alarms.
+ * @vpath: Virtual Path.
+ * @skip_alarms: Do not clear the alarms
+ *
+ * Process vpath alarms.
+ *
+ */
+enum vxge_hw_status vxge_hw_vpath_alarm_process(
+			struct __vxge_hw_vpath_handle *vp,
+			u32 skip_alarms)
+{
+	enum vxge_hw_status status = VXGE_HW_OK;
+
+	if (vp == NULL) {
+		status = VXGE_HW_ERR_INVALID_HANDLE;
+		goto exit;
+	}
+
+	status = __vxge_hw_vpath_alarm_process(vp->vpath, skip_alarms);
+exit:
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_msix_set - Associate MSIX vectors with TIM interrupts and
+ *                            alrms
+ * @vp: Virtual Path handle.
+ * @tim_msix_id: MSIX vectors associated with VXGE_HW_MAX_INTR_PER_VP number of
+ *             interrupts(Can be repeated). If fifo or ring are not enabled
+ *             the MSIX vector for that should be set to 0
+ * @alarm_msix_id: MSIX vector for alarm.
+ *
+ * This API will associate a given MSIX vector numbers with the four TIM
+ * interrupts and alarm interrupt.
+ */
+enum vxge_hw_status
+vxge_hw_vpath_msix_set(struct __vxge_hw_vpath_handle *vp, int *tim_msix_id,
+		       int alarm_msix_id)
+{
+	u64 val64;
+	struct __vxge_hw_virtualpath *vpath = vp->vpath;
+	struct vxge_hw_vpath_reg __iomem *vp_reg = vpath->vp_reg;
+	u32 first_vp_id = vpath->hldev->first_vp_id;
+
+	val64 =  VXGE_HW_INTERRUPT_CFG0_GROUP0_MSIX_FOR_TXTI(
+		  (first_vp_id * 4) + tim_msix_id[0]) |
+		 VXGE_HW_INTERRUPT_CFG0_GROUP1_MSIX_FOR_TXTI(
+		  (first_vp_id * 4) + tim_msix_id[1]) |
+		 VXGE_HW_INTERRUPT_CFG0_GROUP2_MSIX_FOR_TXTI(
+			(first_vp_id * 4) + tim_msix_id[2]);
+
+		val64 |= VXGE_HW_INTERRUPT_CFG0_GROUP3_MSIX_FOR_TXTI(
+			(first_vp_id * 4) + tim_msix_id[3]);
+
+	writeq(val64, &vp_reg->interrupt_cfg0);
+
+	writeq(VXGE_HW_INTERRUPT_CFG2_ALARM_MAP_TO_MSG(
+			(first_vp_id * 4) + alarm_msix_id),
+			&vp_reg->interrupt_cfg2);
+
+	if (vpath->hldev->config.intr_mode ==
+					VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) {
+		__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(
+				VXGE_HW_ONE_SHOT_VECT1_EN_ONE_SHOT_VECT1_EN,
+				0, 32), &vp_reg->one_shot_vect1_en);
+	}
+
+	if (vpath->hldev->config.intr_mode ==
+		VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) {
+		__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(
+				VXGE_HW_ONE_SHOT_VECT2_EN_ONE_SHOT_VECT2_EN,
+				0, 32), &vp_reg->one_shot_vect2_en);
+
+		__vxge_hw_pio_mem_write32_upper((u32)vxge_bVALn(
+				VXGE_HW_ONE_SHOT_VECT3_EN_ONE_SHOT_VECT3_EN,
+				0, 32), &vp_reg->one_shot_vect3_en);
+	}
+
+	return VXGE_HW_OK;
+}
+
+/**
+ * vxge_hw_vpath_msix_mask - Mask MSIX Vector.
+ * @vp: Virtual Path handle.
+ * @msix_id:  MSIX ID
+ *
+ * The function masks the msix interrupt for the given msix_id
+ *
+ * Returns: 0,
+ * Otherwise, VXGE_HW_ERR_WRONG_IRQ if the msix index is out of range
+ * status.
+ * See also:
+ */
+void
+vxge_hw_vpath_msix_mask(struct __vxge_hw_vpath_handle *vp, int msix_id)
+{
+	struct __vxge_hw_device *hldev = vp->vpath->hldev;
+	__vxge_hw_pio_mem_write32_upper(
+		(u32) vxge_bVALn(vxge_mBIT(hldev->first_vp_id +
+			(msix_id  / 4)), 0, 32),
+		&hldev->common_reg->set_msix_mask_vect[msix_id % 4]);
+
+	return;
+}
+
+/**
+ * vxge_hw_vpath_msix_clear - Clear MSIX Vector.
+ * @vp: Virtual Path handle.
+ * @msix_id:  MSI ID
+ *
+ * The function clears the msix interrupt for the given msix_id
+ *
+ * Returns: 0,
+ * Otherwise, VXGE_HW_ERR_WRONG_IRQ if the msix index is out of range
+ * status.
+ * See also:
+ */
+void
+vxge_hw_vpath_msix_clear(struct __vxge_hw_vpath_handle *vp, int msix_id)
+{
+	struct __vxge_hw_device *hldev = vp->vpath->hldev;
+	if (hldev->config.intr_mode ==
+			VXGE_HW_INTR_MODE_MSIX_ONE_SHOT) {
+		__vxge_hw_pio_mem_write32_upper(
+			(u32)vxge_bVALn(vxge_mBIT(hldev->first_vp_id +
+				(msix_id/4)), 0, 32),
+				&hldev->common_reg->
+					clr_msix_one_shot_vec[msix_id%4]);
+	} else {
+		__vxge_hw_pio_mem_write32_upper(
+			(u32)vxge_bVALn(vxge_mBIT(hldev->first_vp_id +
+				(msix_id/4)), 0, 32),
+				&hldev->common_reg->
+					clear_msix_mask_vect[msix_id%4]);
+	}
+
+	return;
+}
+
+/**
+ * vxge_hw_vpath_msix_unmask - Unmask the MSIX Vector.
+ * @vp: Virtual Path handle.
+ * @msix_id:  MSI ID
+ *
+ * The function unmasks the msix interrupt for the given msix_id
+ *
+ * Returns: 0,
+ * Otherwise, VXGE_HW_ERR_WRONG_IRQ if the msix index is out of range
+ * status.
+ * See also:
+ */
+void
+vxge_hw_vpath_msix_unmask(struct __vxge_hw_vpath_handle *vp, int msix_id)
+{
+	struct __vxge_hw_device *hldev = vp->vpath->hldev;
+	__vxge_hw_pio_mem_write32_upper(
+			(u32)vxge_bVALn(vxge_mBIT(hldev->first_vp_id +
+			(msix_id/4)), 0, 32),
+			&hldev->common_reg->clear_msix_mask_vect[msix_id%4]);
+
+	return;
+}
+
+/**
+ * vxge_hw_vpath_msix_mask_all - Mask all MSIX vectors for the vpath.
+ * @vp: Virtual Path handle.
+ *
+ * The function masks all msix interrupt for the given vpath
+ *
+ */
+void
+vxge_hw_vpath_msix_mask_all(struct __vxge_hw_vpath_handle *vp)
+{
+
+	__vxge_hw_pio_mem_write32_upper(
+		(u32)vxge_bVALn(vxge_mBIT(vp->vpath->vp_id), 0, 32),
+		&vp->vpath->hldev->common_reg->set_msix_mask_all_vect);
+
+	return;
+}
+
+/**
+ * vxge_hw_vpath_inta_mask_tx_rx - Mask Tx and Rx interrupts.
+ * @vp: Virtual Path handle.
+ *
+ * Mask Tx and Rx vpath interrupts.
+ *
+ * See also: vxge_hw_vpath_inta_mask_tx_rx()
+ */
+void vxge_hw_vpath_inta_mask_tx_rx(struct __vxge_hw_vpath_handle *vp)
+{
+	u64	tim_int_mask0[4] = {[0 ...3] = 0};
+	u32	tim_int_mask1[4] = {[0 ...3] = 0};
+	u64	val64;
+	struct __vxge_hw_device *hldev = vp->vpath->hldev;
+
+	VXGE_HW_DEVICE_TIM_INT_MASK_SET(tim_int_mask0,
+		tim_int_mask1, vp->vpath->vp_id);
+
+	val64 = readq(&hldev->common_reg->tim_int_mask0);
+
+	if ((tim_int_mask0[VXGE_HW_VPATH_INTR_TX] != 0) ||
+		(tim_int_mask0[VXGE_HW_VPATH_INTR_RX] != 0)) {
+		writeq((tim_int_mask0[VXGE_HW_VPATH_INTR_TX] |
+			tim_int_mask0[VXGE_HW_VPATH_INTR_RX] | val64),
+			&hldev->common_reg->tim_int_mask0);
+	}
+
+	val64 = readl(&hldev->common_reg->tim_int_mask1);
+
+	if ((tim_int_mask1[VXGE_HW_VPATH_INTR_TX] != 0) ||
+		(tim_int_mask1[VXGE_HW_VPATH_INTR_RX] != 0)) {
+		__vxge_hw_pio_mem_write32_upper(
+			(tim_int_mask1[VXGE_HW_VPATH_INTR_TX] |
+			tim_int_mask1[VXGE_HW_VPATH_INTR_RX] | val64),
+			&hldev->common_reg->tim_int_mask1);
+	}
+
+	return;
+}
+
+/**
+ * vxge_hw_vpath_inta_unmask_tx_rx - Unmask Tx and Rx interrupts.
+ * @vp: Virtual Path handle.
+ *
+ * Unmask Tx and Rx vpath interrupts.
+ *
+ * See also: vxge_hw_vpath_inta_mask_tx_rx()
+ */
+void vxge_hw_vpath_inta_unmask_tx_rx(struct __vxge_hw_vpath_handle *vp)
+{
+	u64	tim_int_mask0[4] = {[0 ...3] = 0};
+	u32	tim_int_mask1[4] = {[0 ...3] = 0};
+	u64	val64;
+	struct __vxge_hw_device *hldev = vp->vpath->hldev;
+
+	VXGE_HW_DEVICE_TIM_INT_MASK_SET(tim_int_mask0,
+		tim_int_mask1, vp->vpath->vp_id);
+
+	val64 = readq(&hldev->common_reg->tim_int_mask0);
+
+	if ((tim_int_mask0[VXGE_HW_VPATH_INTR_TX] != 0) ||
+	   (tim_int_mask0[VXGE_HW_VPATH_INTR_RX] != 0)) {
+		writeq((~(tim_int_mask0[VXGE_HW_VPATH_INTR_TX] |
+			tim_int_mask0[VXGE_HW_VPATH_INTR_RX])) & val64,
+			&hldev->common_reg->tim_int_mask0);
+	}
+
+	if ((tim_int_mask1[VXGE_HW_VPATH_INTR_TX] != 0) ||
+	   (tim_int_mask1[VXGE_HW_VPATH_INTR_RX] != 0)) {
+		__vxge_hw_pio_mem_write32_upper(
+			(~(tim_int_mask1[VXGE_HW_VPATH_INTR_TX] |
+			  tim_int_mask1[VXGE_HW_VPATH_INTR_RX])) & val64,
+			&hldev->common_reg->tim_int_mask1);
+	}
+
+	return;
+}
+
+/**
+ * vxge_hw_vpath_poll_rx - Poll Rx Virtual Path for completed
+ * descriptors and process the same.
+ * @ring: Handle to the ring object used for receive
+ *
+ * The function	polls the Rx for the completed	descriptors and	calls
+ * the driver via supplied completion	callback.
+ *
+ * Returns: VXGE_HW_OK, if the polling is completed successful.
+ * VXGE_HW_COMPLETIONS_REMAIN: There are still more completed
+ * descriptors available which are yet to be processed.
+ *
+ * See also: vxge_hw_vpath_poll_rx()
+ */
+enum vxge_hw_status vxge_hw_vpath_poll_rx(struct __vxge_hw_ring *ring)
+{
+	u8 t_code;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	void *first_rxdh;
+	u64 val64 = 0;
+	int new_count = 0;
+
+	ring->cmpl_cnt = 0;
+
+	status = vxge_hw_ring_rxd_next_completed(ring, &first_rxdh, &t_code);
+	if (status == VXGE_HW_OK)
+		ring->callback(ring, first_rxdh,
+			t_code, ring->channel.userdata);
+
+	if (ring->cmpl_cnt != 0) {
+		ring->doorbell_cnt += ring->cmpl_cnt;
+		if (ring->doorbell_cnt >= ring->rxds_limit) {
+			/*
+			 * Each RxD is of 4 qwords, update the number of
+			 * qwords replenished
+			 */
+			new_count = (ring->doorbell_cnt * 4);
+
+			/* For each block add 4 more qwords */
+			ring->total_db_cnt += ring->doorbell_cnt;
+			if (ring->total_db_cnt >= ring->rxds_per_block) {
+				new_count += 4;
+				/* Reset total count */
+				ring->total_db_cnt %= ring->rxds_per_block;
+			}
+			writeq(VXGE_HW_PRC_RXD_DOORBELL_NEW_QW_CNT(new_count),
+				&ring->vp_reg->prc_rxd_doorbell);
+			val64 =
+			  readl(&ring->common_reg->titan_general_int_status);
+			ring->doorbell_cnt = 0;
+		}
+	}
+
+	return status;
+}
+
+/**
+ * vxge_hw_vpath_poll_tx - Poll Tx for completed descriptors and process
+ * the same.
+ * @fifo: Handle to the fifo object used for non offload send
+ *
+ * The function	polls the Tx for the completed	descriptors and	calls
+ * the driver via supplied completion callback.
+ *
+ * Returns: VXGE_HW_OK, if the polling is completed successful.
+ * VXGE_HW_COMPLETIONS_REMAIN: There are still more completed
+ * descriptors available which are yet to be processed.
+ *
+ * See also: vxge_hw_vpath_poll_tx().
+ */
+enum vxge_hw_status vxge_hw_vpath_poll_tx(struct __vxge_hw_fifo *fifo,
+					void **skb_ptr)
+{
+	enum vxge_hw_fifo_tcode t_code;
+	void *first_txdlh;
+	enum vxge_hw_status status = VXGE_HW_OK;
+	struct __vxge_hw_channel *channel;
+
+	channel = &fifo->channel;
+
+	status = vxge_hw_fifo_txdl_next_completed(fifo,
+				&first_txdlh, &t_code);
+	if (status == VXGE_HW_OK)
+		if (fifo->callback(fifo, first_txdlh,
+			t_code, channel->userdata, skb_ptr) != VXGE_HW_OK)
+			status = VXGE_HW_COMPLETIONS_REMAIN;
+
+	return status;
+}
diff --git a/drivers/net/vxge/vxge-traffic.h b/drivers/net/vxge/vxge-traffic.h
new file mode 100644
index 000000000000..7567a1140d07
--- /dev/null
+++ b/drivers/net/vxge/vxge-traffic.h
@@ -0,0 +1,2409 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-traffic.h: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *                 Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#ifndef VXGE_TRAFFIC_H
+#define VXGE_TRAFFIC_H
+
+#include "vxge-reg.h"
+#include "vxge-version.h"
+
+#define VXGE_HW_DTR_MAX_T_CODE		16
+#define VXGE_HW_ALL_FOXES		0xFFFFFFFFFFFFFFFFULL
+#define VXGE_HW_INTR_MASK_ALL		0xFFFFFFFFFFFFFFFFULL
+#define	VXGE_HW_MAX_VIRTUAL_PATHS	17
+
+#define VXGE_HW_MAC_MAX_MAC_PORT_ID	2
+
+#define VXGE_HW_DEFAULT_32		0xffffffff
+/* frames sizes */
+#define VXGE_HW_HEADER_802_2_SIZE	3
+#define VXGE_HW_HEADER_SNAP_SIZE	5
+#define VXGE_HW_HEADER_VLAN_SIZE	4
+#define VXGE_HW_MAC_HEADER_MAX_SIZE \
+			(ETH_HLEN + \
+			VXGE_HW_HEADER_802_2_SIZE + \
+			VXGE_HW_HEADER_VLAN_SIZE + \
+			VXGE_HW_HEADER_SNAP_SIZE)
+
+#define VXGE_HW_TCPIP_HEADER_MAX_SIZE	(64 + 64)
+
+/* 32bit alignments */
+#define VXGE_HW_HEADER_ETHERNET_II_802_3_ALIGN		2
+#define VXGE_HW_HEADER_802_2_SNAP_ALIGN			2
+#define VXGE_HW_HEADER_802_2_ALIGN			3
+#define VXGE_HW_HEADER_SNAP_ALIGN			1
+
+#define VXGE_HW_L3_CKSUM_OK				0xFFFF
+#define VXGE_HW_L4_CKSUM_OK				0xFFFF
+
+/* Forward declarations */
+struct __vxge_hw_device;
+struct __vxge_hw_vpath_handle;
+struct vxge_hw_vp_config;
+struct __vxge_hw_virtualpath;
+struct __vxge_hw_channel;
+struct __vxge_hw_fifo;
+struct __vxge_hw_ring;
+struct vxge_hw_ring_attr;
+struct vxge_hw_mempool;
+
+#ifndef TRUE
+#define TRUE 1
+#endif
+
+#ifndef FALSE
+#define FALSE 0
+#endif
+
+/*VXGE_HW_STATUS_H*/
+
+#define VXGE_HW_EVENT_BASE			0
+#define VXGE_LL_EVENT_BASE			100
+
+/**
+ * enum vxge_hw_event- Enumerates slow-path HW events.
+ * @VXGE_HW_EVENT_UNKNOWN: Unknown (and invalid) event.
+ * @VXGE_HW_EVENT_SERR: Serious vpath hardware error event.
+ * @VXGE_HW_EVENT_ECCERR: vpath ECC error event.
+ * @VXGE_HW_EVENT_VPATH_ERR: Error local to the respective vpath
+ * @VXGE_HW_EVENT_FIFO_ERR: FIFO Doorbell fifo error.
+ * @VXGE_HW_EVENT_SRPCIM_SERR: srpcim hardware error event.
+ * @VXGE_HW_EVENT_MRPCIM_SERR: mrpcim hardware error event.
+ * @VXGE_HW_EVENT_MRPCIM_ECCERR: mrpcim ecc error event.
+ * @VXGE_HW_EVENT_RESET_START: Privileged entity is starting device reset
+ * @VXGE_HW_EVENT_RESET_COMPLETE: Device reset has been completed
+ * @VXGE_HW_EVENT_SLOT_FREEZE: Slot-freeze event. Driver tries to distinguish
+ * slot-freeze from the rest critical events (e.g. ECC) when it is
+ * impossible to PIO read "through" the bus, i.e. when getting all-foxes.
+ *
+ * enum vxge_hw_event enumerates slow-path HW eventis.
+ *
+ * See also: struct vxge_hw_uld_cbs{}, vxge_uld_link_up_f{},
+ * vxge_uld_link_down_f{}.
+ */
+enum vxge_hw_event {
+	VXGE_HW_EVENT_UNKNOWN		= 0,
+	/* HW events */
+	VXGE_HW_EVENT_RESET_START	= VXGE_HW_EVENT_BASE + 1,
+	VXGE_HW_EVENT_RESET_COMPLETE	= VXGE_HW_EVENT_BASE + 2,
+	VXGE_HW_EVENT_LINK_DOWN		= VXGE_HW_EVENT_BASE + 3,
+	VXGE_HW_EVENT_LINK_UP		= VXGE_HW_EVENT_BASE + 4,
+	VXGE_HW_EVENT_ALARM_CLEARED	= VXGE_HW_EVENT_BASE + 5,
+	VXGE_HW_EVENT_ECCERR		= VXGE_HW_EVENT_BASE + 6,
+	VXGE_HW_EVENT_MRPCIM_ECCERR	= VXGE_HW_EVENT_BASE + 7,
+	VXGE_HW_EVENT_FIFO_ERR		= VXGE_HW_EVENT_BASE + 8,
+	VXGE_HW_EVENT_VPATH_ERR		= VXGE_HW_EVENT_BASE + 9,
+	VXGE_HW_EVENT_CRITICAL_ERR	= VXGE_HW_EVENT_BASE + 10,
+	VXGE_HW_EVENT_SERR		= VXGE_HW_EVENT_BASE + 11,
+	VXGE_HW_EVENT_SRPCIM_SERR	= VXGE_HW_EVENT_BASE + 12,
+	VXGE_HW_EVENT_MRPCIM_SERR	= VXGE_HW_EVENT_BASE + 13,
+	VXGE_HW_EVENT_SLOT_FREEZE	= VXGE_HW_EVENT_BASE + 14,
+};
+
+#define VXGE_HW_SET_LEVEL(a, b) (((a) > (b)) ? (a) : (b))
+
+/*
+ * struct vxge_hw_mempool_dma - Represents DMA objects passed to the
+	caller.
+ */
+struct vxge_hw_mempool_dma {
+	dma_addr_t			addr;
+	struct pci_dev *handle;
+	struct pci_dev *acc_handle;
+};
+
+/*
+ * vxge_hw_mempool_item_f  - Mempool item alloc/free callback
+ * @mempoolh: Memory pool handle.
+ * @memblock: Address of memory block
+ * @memblock_index: Index of memory block
+ * @item: Item that gets allocated or freed.
+ * @index: Item's index in the memory pool.
+ * @is_last: True, if this item is the last one in the pool; false - otherwise.
+ * userdata: Per-pool user context.
+ *
+ * Memory pool allocation/deallocation callback.
+ */
+
+/*
+ * struct vxge_hw_mempool - Memory pool.
+ */
+struct vxge_hw_mempool {
+
+	void (*item_func_alloc)(
+	struct vxge_hw_mempool *mempoolh,
+	u32			memblock_index,
+	struct vxge_hw_mempool_dma	*dma_object,
+	u32			index,
+	u32			is_last);
+
+	void		*userdata;
+	void		**memblocks_arr;
+	void		**memblocks_priv_arr;
+	struct vxge_hw_mempool_dma	*memblocks_dma_arr;
+	struct __vxge_hw_device *devh;
+	u32			memblock_size;
+	u32			memblocks_max;
+	u32			memblocks_allocated;
+	u32			item_size;
+	u32			items_max;
+	u32			items_initial;
+	u32			items_current;
+	u32			items_per_memblock;
+	void		**items_arr;
+	u32			items_priv_size;
+};
+
+#define	VXGE_HW_MAX_INTR_PER_VP				4
+#define	VXGE_HW_VPATH_INTR_TX				0
+#define	VXGE_HW_VPATH_INTR_RX				1
+#define	VXGE_HW_VPATH_INTR_EINTA			2
+#define	VXGE_HW_VPATH_INTR_BMAP				3
+
+#define VXGE_HW_BLOCK_SIZE				4096
+
+/**
+ * struct vxge_hw_tim_intr_config - Titan Tim interrupt configuration.
+ * @intr_enable: Set to 1, if interrupt is enabled.
+ * @btimer_val: Boundary Timer Initialization value in units of 272 ns.
+ * @timer_ac_en: Timer Automatic Cancel. 1 : Automatic Canceling Enable: when
+ *             asserted, other interrupt-generating entities will cancel the
+ *             scheduled timer interrupt.
+ * @timer_ci_en: Timer Continuous Interrupt. 1 : Continuous Interrupting Enable:
+ *             When asserted, an interrupt will be generated every time the
+ *             boundary timer expires, even if no traffic has been transmitted
+ *             on this interrupt.
+ * @timer_ri_en: Timer Consecutive (Re-) Interrupt 1 : Consecutive
+ *             (Re-) Interrupt Enable: When asserted, an interrupt will be
+ *             generated the next time the timer expires, even if no traffic has
+ *             been transmitted on this interrupt. (This will only happen once
+ *             each time that this value is written to the TIM.) This bit is
+ *             cleared by H/W at the end of the current-timer-interval when
+ *             the interrupt is triggered.
+ * @rtimer_val: Restriction Timer Initialization value in units of 272 ns.
+ * @util_sel: Utilization Selector. Selects which of the workload approximations
+ *             to use (e.g. legacy Tx utilization, Tx/Rx utilization, host
+ *             specified utilization etc.), selects one of
+ *             the 17 host configured values.
+ *             0-Virtual Path 0
+ *             1-Virtual Path 1
+ *             ...
+ *             16-Virtual Path 17
+ *             17-Legacy Tx network utilization, provided by TPA
+ *             18-Legacy Rx network utilization, provided by FAU
+ *             19-Average of legacy Rx and Tx utilization calculated from link
+ *                utilization values.
+ *             20-31-Invalid configurations
+ *             32-Host utilization for Virtual Path 0
+ *             33-Host utilization for Virtual Path 1
+ *             ...
+ *             48-Host utilization for Virtual Path 17
+ *             49-Legacy Tx network utilization, provided by TPA
+ *             50-Legacy Rx network utilization, provided by FAU
+ *             51-Average of legacy Rx and Tx utilization calculated from
+ *                link utilization values.
+ *             52-63-Invalid configurations
+ * @ltimer_val: Latency Timer Initialization Value in units of 272 ns.
+ * @txd_cnt_en: TxD Return Event Count Enable. This configuration bit when set
+ *             to 1 enables counting of TxD0 returns (signalled by PCC's),
+ *             towards utilization event count values.
+ * @urange_a: Defines the upper limit (in percent) for this utilization range
+ *             to be active. This range is considered active
+ *             if 0 = UTIL = URNG_A
+ *             and the UEC_A field (below) is non-zero.
+ * @uec_a: Utilization Event Count A. If this range is active, the adapter will
+ *             wait until UEC_A events have occurred on the interrupt before
+ *             generating an interrupt.
+ * @urange_b: Link utilization range B.
+ * @uec_b: Utilization Event Count B.
+ * @urange_c: Link utilization range C.
+ * @uec_c: Utilization Event Count C.
+ * @urange_d: Link utilization range D.
+ * @uec_d: Utilization Event Count D.
+ * Traffic Interrupt Controller Module interrupt configuration.
+ */
+struct vxge_hw_tim_intr_config {
+
+	u32				intr_enable;
+#define VXGE_HW_TIM_INTR_ENABLE				1
+#define VXGE_HW_TIM_INTR_DISABLE				0
+#define VXGE_HW_TIM_INTR_DEFAULT				0
+
+	u32				btimer_val;
+#define VXGE_HW_MIN_TIM_BTIMER_VAL				0
+#define VXGE_HW_MAX_TIM_BTIMER_VAL				67108864
+#define VXGE_HW_USE_FLASH_DEFAULT				0xffffffff
+
+	u32				timer_ac_en;
+#define VXGE_HW_TIM_TIMER_AC_ENABLE				1
+#define VXGE_HW_TIM_TIMER_AC_DISABLE				0
+
+	u32				timer_ci_en;
+#define VXGE_HW_TIM_TIMER_CI_ENABLE				1
+#define VXGE_HW_TIM_TIMER_CI_DISABLE				0
+
+	u32				timer_ri_en;
+#define VXGE_HW_TIM_TIMER_RI_ENABLE				1
+#define VXGE_HW_TIM_TIMER_RI_DISABLE				0
+
+	u32				rtimer_val;
+#define VXGE_HW_MIN_TIM_RTIMER_VAL				0
+#define VXGE_HW_MAX_TIM_RTIMER_VAL				67108864
+
+	u32				util_sel;
+#define VXGE_HW_TIM_UTIL_SEL_LEGACY_TX_NET_UTIL		17
+#define VXGE_HW_TIM_UTIL_SEL_LEGACY_RX_NET_UTIL		18
+#define VXGE_HW_TIM_UTIL_SEL_LEGACY_TX_RX_AVE_NET_UTIL		19
+#define VXGE_HW_TIM_UTIL_SEL_PER_VPATH				63
+
+	u32				ltimer_val;
+#define VXGE_HW_MIN_TIM_LTIMER_VAL				0
+#define VXGE_HW_MAX_TIM_LTIMER_VAL				67108864
+
+	/* Line utilization interrupts */
+	u32				urange_a;
+#define VXGE_HW_MIN_TIM_URANGE_A				0
+#define VXGE_HW_MAX_TIM_URANGE_A				100
+
+	u32				uec_a;
+#define VXGE_HW_MIN_TIM_UEC_A					0
+#define VXGE_HW_MAX_TIM_UEC_A					65535
+
+	u32				urange_b;
+#define VXGE_HW_MIN_TIM_URANGE_B				0
+#define VXGE_HW_MAX_TIM_URANGE_B				100
+
+	u32				uec_b;
+#define VXGE_HW_MIN_TIM_UEC_B					0
+#define VXGE_HW_MAX_TIM_UEC_B					65535
+
+	u32				urange_c;
+#define VXGE_HW_MIN_TIM_URANGE_C				0
+#define VXGE_HW_MAX_TIM_URANGE_C				100
+
+	u32				uec_c;
+#define VXGE_HW_MIN_TIM_UEC_C					0
+#define VXGE_HW_MAX_TIM_UEC_C					65535
+
+	u32				uec_d;
+#define VXGE_HW_MIN_TIM_UEC_D					0
+#define VXGE_HW_MAX_TIM_UEC_D					65535
+};
+
+#define	VXGE_HW_STATS_OP_READ					0
+#define	VXGE_HW_STATS_OP_CLEAR_STAT				1
+#define	VXGE_HW_STATS_OP_CLEAR_ALL_VPATH_STATS			2
+#define	VXGE_HW_STATS_OP_CLEAR_ALL_STATS_OF_LOC			2
+#define	VXGE_HW_STATS_OP_CLEAR_ALL_STATS			3
+
+#define	VXGE_HW_STATS_LOC_AGGR					17
+#define VXGE_HW_STATS_AGGRn_OFFSET				0x00720
+
+#define VXGE_HW_STATS_VPATH_TX_OFFSET				0x0
+#define VXGE_HW_STATS_VPATH_RX_OFFSET				0x00090
+
+#define	VXGE_HW_STATS_VPATH_PROG_EVENT_VNUM0_OFFSET	   (0x001d0 >> 3)
+#define	VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM0(bits) \
+						vxge_bVALn(bits, 0, 32)
+
+#define	VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM1(bits) \
+						vxge_bVALn(bits, 32, 32)
+
+#define	VXGE_HW_STATS_VPATH_PROG_EVENT_VNUM2_OFFSET	   (0x001d8 >> 3)
+#define	VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM2(bits) \
+						vxge_bVALn(bits, 0, 32)
+
+#define	VXGE_HW_STATS_GET_VPATH_PROG_EVENT_VNUM3(bits) \
+						vxge_bVALn(bits, 32, 32)
+
+/**
+ * struct vxge_hw_xmac_aggr_stats - Per-Aggregator XMAC Statistics
+ *
+ * @tx_frms: Count of data frames transmitted on this Aggregator on all
+ *             its Aggregation ports. Does not include LACPDUs or Marker PDUs.
+ *             However, does include frames discarded by the Distribution
+ *             function.
+ * @tx_data_octets: Count of data and padding octets of frames transmitted
+ *             on this Aggregator on all its Aggregation ports. Does not include
+ *             octets of LACPDUs or Marker PDUs. However, does include octets of
+ *             frames discarded by the Distribution function.
+ * @tx_mcast_frms: Count of data frames transmitted (to a group destination
+ *             address other than the broadcast address) on this Aggregator on
+ *             all its Aggregation ports. Does not include LACPDUs or Marker
+ *             PDUs. However, does include frames discarded by the Distribution
+ *             function.
+ * @tx_bcast_frms: Count of broadcast data frames transmitted on this Aggregator
+ *             on all its Aggregation ports. Does not include LACPDUs or Marker
+ *             PDUs. However, does include frames discarded by the Distribution
+ *             function.
+ * @tx_discarded_frms: Count of data frames to be transmitted on this Aggregator
+ *             that are discarded by the Distribution function. This occurs when
+ *             conversation are allocated to different ports and have to be
+ *             flushed on old ports
+ * @tx_errored_frms: Count of data frames transmitted on this Aggregator that
+ *             experience transmission errors on its Aggregation ports.
+ * @rx_frms: Count of data frames received on this Aggregator on all its
+ *             Aggregation ports. Does not include LACPDUs or Marker PDUs.
+ *             Also, does not include frames discarded by the Collection
+ *             function.
+ * @rx_data_octets: Count of data and padding octets of frames received on this
+ *             Aggregator on all its Aggregation ports. Does not include octets
+ *             of LACPDUs or Marker PDUs. Also, does not include
+ *             octets of frames
+ *             discarded by the Collection function.
+ * @rx_mcast_frms: Count of data frames received (from a group destination
+ *             address other than the broadcast address) on this Aggregator on
+ *             all its Aggregation ports. Does not include LACPDUs or Marker
+ *             PDUs. Also, does not include frames discarded by the Collection
+ *             function.
+ * @rx_bcast_frms: Count of broadcast data frames received on this Aggregator on
+ *             all its Aggregation ports. Does not include LACPDUs or Marker
+ *             PDUs. Also, does not include frames discarded by the Collection
+ *             function.
+ * @rx_discarded_frms: Count of data frames received on this Aggregator that are
+ *             discarded by the Collection function because the Collection
+ *             function was disabled on the port which the frames are received.
+ * @rx_errored_frms: Count of data frames received on this Aggregator that are
+ *             discarded by its Aggregation ports, or are discarded by the
+ *             Collection function of the Aggregator, or that are discarded by
+ *             the Aggregator due to detection of an illegal Slow Protocols PDU.
+ * @rx_unknown_slow_proto_frms: Count of data frames received on this Aggregator
+ *             that are discarded by its Aggregation ports due to detection of
+ *             an unknown Slow Protocols PDU.
+ *
+ * Per aggregator XMAC RX statistics.
+ */
+struct vxge_hw_xmac_aggr_stats {
+/*0x000*/		u64	tx_frms;
+/*0x008*/		u64	tx_data_octets;
+/*0x010*/		u64	tx_mcast_frms;
+/*0x018*/		u64	tx_bcast_frms;
+/*0x020*/		u64	tx_discarded_frms;
+/*0x028*/		u64	tx_errored_frms;
+/*0x030*/		u64	rx_frms;
+/*0x038*/		u64	rx_data_octets;
+/*0x040*/		u64	rx_mcast_frms;
+/*0x048*/		u64	rx_bcast_frms;
+/*0x050*/		u64	rx_discarded_frms;
+/*0x058*/		u64	rx_errored_frms;
+/*0x060*/		u64	rx_unknown_slow_proto_frms;
+} __packed;
+
+/**
+ * struct vxge_hw_xmac_port_stats - XMAC Port Statistics
+ *
+ * @tx_ttl_frms: Count of successfully transmitted MAC frames
+ * @tx_ttl_octets: Count of total octets of transmitted frames, not including
+ *            framing characters (i.e. less framing bits). To determine the
+ *            total octets of transmitted frames, including framing characters,
+ *            multiply PORTn_TX_TTL_FRMS by 8 and add it to this stat (unless
+ *            otherwise configured, this stat only counts frames that have
+ *            8 bytes of preamble for each frame). This stat can be configured
+ *            (see XMAC_STATS_GLOBAL_CFG.TTL_FRMS_HANDLING) to count everything
+ *            including the preamble octets.
+ * @tx_data_octets: Count of data and padding octets of successfully transmitted
+ *            frames.
+ * @tx_mcast_frms: Count of successfully transmitted frames to a group address
+ *            other than the broadcast address.
+ * @tx_bcast_frms: Count of successfully transmitted frames to the broadcast
+ *            group address.
+ * @tx_ucast_frms: Count of transmitted frames containing a unicast address.
+ *            Includes discarded frames that are not sent to the network.
+ * @tx_tagged_frms: Count of transmitted frames containing a VLAN tag.
+ * @tx_vld_ip: Count of transmitted IP datagrams that are passed to the network.
+ * @tx_vld_ip_octets: Count of total octets of transmitted IP datagrams that
+ *            are passed to the network.
+ * @tx_icmp: Count of transmitted ICMP messages. Includes messages not sent
+ *            due to problems within ICMP.
+ * @tx_tcp: Count of transmitted TCP segments. Does not include segments
+ *            containing retransmitted octets.
+ * @tx_rst_tcp: Count of transmitted TCP segments containing the RST flag.
+ * @tx_udp: Count of transmitted UDP datagrams.
+ * @tx_parse_error: Increments when the TPA is unable to parse a packet. This
+ *            generally occurs when a packet is corrupt somehow, including
+ *            packets that have IP version mismatches, invalid Layer 2 control
+ *            fields, etc. L3/L4 checksums are not offloaded, but the packet
+ *            is still be transmitted.
+ * @tx_unknown_protocol: Increments when the TPA encounters an unknown
+ *            protocol, such as a new IPv6 extension header, or an unsupported
+ *            Routing Type. The packet still has a checksum calculated but it
+ *            may be incorrect.
+ * @tx_pause_ctrl_frms: Count of MAC PAUSE control frames that are transmitted.
+ *            Since, the only control frames supported by this device are
+ *            PAUSE frames, this register is a count of all transmitted MAC
+ *            control frames.
+ * @tx_marker_pdu_frms: Count of Marker PDUs transmitted
+ * on this Aggregation port.
+ * @tx_lacpdu_frms: Count of LACPDUs transmitted on this Aggregation port.
+ * @tx_drop_ip: Count of transmitted IP datagrams that could not be passed to
+ *            the network. Increments because of:
+ *            1) An internal processing error
+ *            (such as an uncorrectable ECC error). 2) A frame parsing error
+ *            during IP checksum calculation.
+ * @tx_marker_resp_pdu_frms: Count of Marker Response PDUs transmitted on this
+ *            Aggregation port.
+ * @tx_xgmii_char2_match: Maintains a count of the number of transmitted XGMII
+ *            characters that match a pattern that is programmable through
+ *            register XMAC_STATS_TX_XGMII_CHAR_PORTn. By default, the pattern
+ *            is set to /T/ (i.e. the terminate character), thus the statistic
+ *            tracks the number of transmitted Terminate characters.
+ * @tx_xgmii_char1_match: Maintains a count of the number of transmitted XGMII
+ *            characters that match a pattern that is programmable through
+ *            register XMAC_STATS_TX_XGMII_CHAR_PORTn. By default, the pattern
+ *            is set to /S/ (i.e. the start character),
+ *            thus the statistic tracks
+ *            the number of transmitted Start characters.
+ * @tx_xgmii_column2_match: Maintains a count of the number of transmitted XGMII
+ *            columns that match a pattern that is programmable through register
+ *            XMAC_STATS_TX_XGMII_COLUMN2_PORTn. By default, the pattern is set
+ *            to 4 x /E/ (i.e. a column containing all error characters), thus
+ *            the statistic tracks the number of Error columns transmitted at
+ *            any time. If XMAC_STATS_TX_XGMII_BEHAV_COLUMN2_PORTn.NEAR_COL1 is
+ *            set to 1, then this stat increments when COLUMN2 is found within
+ *            'n' clocks after COLUMN1. Here, 'n' is defined by
+ *            XMAC_STATS_TX_XGMII_BEHAV_COLUMN2_PORTn.NUM_COL (if 'n' is set
+ *            to 0, then it means to search anywhere for COLUMN2).
+ * @tx_xgmii_column1_match: Maintains a count of the number of transmitted XGMII
+ *            columns that match a pattern that is programmable through register
+ *            XMAC_STATS_TX_XGMII_COLUMN1_PORTn. By default, the pattern is set
+ *            to 4 x /I/ (i.e. a column containing all idle characters),
+ *            thus the statistic tracks the number of transmitted Idle columns.
+ * @tx_any_err_frms: Count of transmitted frames containing any error that
+ *            prevents them from being passed to the network. Increments if
+ *            there is an ECC while reading the frame out of the transmit
+ *            buffer. Also increments if the transmit protocol assist (TPA)
+ *            block determines that the frame should not be sent.
+ * @tx_drop_frms: Count of frames that could not be sent for no other reason
+ *            than internal MAC processing. Increments once whenever the
+ *            transmit buffer is flushed (due to an ECC error on a memory
+ *            descriptor).
+ * @rx_ttl_frms: Count of total received MAC frames, including frames received
+ *            with frame-too-long, FCS, or length errors. This stat can be
+ *            configured (see XMAC_STATS_GLOBAL_CFG.TTL_FRMS_HANDLING) to count
+ *            everything, even "frames" as small one byte of preamble.
+ * @rx_vld_frms: Count of successfully received MAC frames. Does not include
+ *            frames received with frame-too-long, FCS, or length errors.
+ * @rx_offload_frms: Count of offloaded received frames that are passed to
+ *            the host.
+ * @rx_ttl_octets: Count of total octets of received frames, not including
+ *            framing characters (i.e. less framing bits). To determine the
+ *            total octets of received frames, including framing characters,
+ *            multiply PORTn_RX_TTL_FRMS by 8 and add it to this stat (unless
+ *            otherwise configured, this stat only counts frames that have 8
+ *            bytes of preamble for each frame). This stat can be configured
+ *            (see XMAC_STATS_GLOBAL_CFG.TTL_FRMS_HANDLING) to count everything,
+ *            even the preamble octets of "frames" as small one byte of preamble
+ * @rx_data_octets: Count of data and padding octets of successfully received
+ *            frames. Does not include frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_offload_octets: Count of total octets, not including framing
+ *            characters, of offloaded received frames that are passed
+ *            to the host.
+ * @rx_vld_mcast_frms: Count of successfully received MAC frames containing a
+ *	      nonbroadcast group address. Does not include frames received
+ *            with frame-too-long, FCS, or length errors.
+ * @rx_vld_bcast_frms: Count of successfully received MAC frames containing
+ *            the broadcast group address. Does not include frames received
+ *            with frame-too-long, FCS, or length errors.
+ * @rx_accepted_ucast_frms: Count of successfully received frames containing
+ *            a unicast address. Only includes frames that are passed to
+ *            the system.
+ * @rx_accepted_nucast_frms: Count of successfully received frames containing
+ *            a non-unicast (broadcast or multicast) address. Only includes
+ *            frames that are passed to the system. Could include, for instance,
+ *            non-unicast frames that contain FCS errors if the MAC_ERROR_CFG
+ *            register is set to pass FCS-errored frames to the host.
+ * @rx_tagged_frms: Count of received frames containing a VLAN tag.
+ * @rx_long_frms: Count of received frames that are longer than RX_MAX_PYLD_LEN
+ *            + 18 bytes (+ 22 bytes if VLAN-tagged).
+ * @rx_usized_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) less than 64 octets, that are otherwise well-formed.
+ *            In other words, counts runts.
+ * @rx_osized_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) more than 1518 octets, that are otherwise
+ *            well-formed. Note: If register XMAC_STATS_GLOBAL_CFG.VLAN_HANDLING
+ *            is set to 1, then "more than 1518 octets" becomes "more than 1518
+ *            (1522 if VLAN-tagged) octets".
+ * @rx_frag_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) less than 64 octets that had bad FCS. In other
+ *            words, counts fragments.
+ * @rx_jabber_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) more than 1518 octets that had bad FCS. In other
+ *            words, counts jabbers. Note: If register
+ *            XMAC_STATS_GLOBAL_CFG.VLAN_HANDLING is set to 1, then "more than
+ *            1518 octets" becomes "more than 1518 (1522 if VLAN-tagged)
+ *            octets".
+ * @rx_ttl_64_frms: Count of total received MAC frames with length (including
+ *            FCS, but not framing bits) of exactly 64 octets. Includes frames
+ *            received with frame-too-long, FCS, or length errors.
+ * @rx_ttl_65_127_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 65 and 127
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_128_255_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 128 and 255
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_256_511_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 256 and 511
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_512_1023_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 512 and 1023
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_1024_1518_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 1024 and 1518
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_1519_4095_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 1519 and 4095
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_4096_8191_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 4096 and 8191
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_8192_max_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 8192 and
+ *            RX_MAX_PYLD_LEN+18 octets inclusive. Includes frames received
+ *            with frame-too-long, FCS, or length errors.
+ * @rx_ttl_gt_max_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) exceeding
+ *            RX_MAX_PYLD_LEN+18 (+22 bytes if VLAN-tagged) octets inclusive.
+ *            Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ip: Count of received IP datagrams. Includes errored IP datagrams.
+ * @rx_accepted_ip: Count of received IP datagrams that
+ * 		are passed to the system.
+ * @rx_ip_octets: Count of number of octets in received IP datagrams. Includes
+ *            errored IP datagrams.
+ * @rx_err_ip: 	Count of received IP datagrams containing errors. For example,
+ *            bad IP checksum.
+ * @rx_icmp: Count of received ICMP messages. Includes errored ICMP messages.
+ * @rx_tcp: Count of received TCP segments. Includes errored TCP segments.
+ *            Note: This stat contains a count of all received TCP segments,
+ *            regardless of whether or not they pertain to an established
+ *            connection.
+ * @rx_udp: Count of received UDP datagrams.
+ * @rx_err_tcp: Count of received TCP segments containing errors. For example,
+ *            bad TCP checksum.
+ * @rx_pause_count: Count of number of pause quanta that the MAC has been in
+ *            the paused state. Recall, one pause quantum equates to 512
+ *            bit times.
+ * @rx_pause_ctrl_frms: Count of received MAC PAUSE control frames.
+ * @rx_unsup_ctrl_frms: Count of received MAC control frames that do not
+ *            contain the PAUSE opcode. The sum of RX_PAUSE_CTRL_FRMS and
+ *            this register is a count of all received MAC control frames.
+ *            Note: This stat may be configured to count all layer 2 errors
+ *            (i.e. length errors and FCS errors).
+ * @rx_fcs_err_frms: Count of received MAC frames that do not pass FCS. Does
+ *            not include frames received with frame-too-long or
+ *            frame-too-short error.
+ * @rx_in_rng_len_err_frms: Count of received frames with a length/type field
+ *            value between 46 (42 for VLAN-tagged frames) and 1500 (also 1500
+ *            for VLAN-tagged frames), inclusive, that does not match the
+ *            number of data octets (including pad) received. Also contains
+ *            a count of received frames with a length/type field less than
+ *            46 (42 for VLAN-tagged frames) and the number of data octets
+ *            (including pad) received is greater than 46 (42 for VLAN-tagged
+ *            frames).
+ * @rx_out_rng_len_err_frms:  Count of received frames with length/type field
+ *            between 1501 and 1535 decimal, inclusive.
+ * @rx_drop_frms: Count of received frames that could not be passed to the host.
+ *            See PORTn_RX_L2_MGMT_DISCARD, PORTn_RX_RPA_DISCARD,
+ *            PORTn_RX_TRASH_DISCARD, PORTn_RX_RTS_DISCARD, PORTn_RX_RED_DISCARD
+ *            for a list of reasons. Because the RMAC drops one frame at a time,
+ *            this stat also indicates the number of drop events.
+ * @rx_discarded_frms: Count of received frames containing
+ * 		any error that prevents
+ *            them from being passed to the system. See PORTn_RX_FCS_DISCARD,
+ *            PORTn_RX_LEN_DISCARD, and PORTn_RX_SWITCH_DISCARD for a list of
+ *            reasons.
+ * @rx_drop_ip: Count of received IP datagrams that could not be passed to the
+ *            host. See PORTn_RX_DROP_FRMS for a list of reasons.
+ * @rx_drop_udp: Count of received UDP datagrams that are not delivered to the
+ *            host. See PORTn_RX_DROP_FRMS for a list of reasons.
+ * @rx_marker_pdu_frms: Count of valid Marker PDUs received on this Aggregation
+ *            port.
+ * @rx_lacpdu_frms: Count of valid LACPDUs received on this Aggregation port.
+ * @rx_unknown_pdu_frms: Count of received frames (on this Aggregation port)
+ *            that carry the Slow Protocols EtherType, but contain an unknown
+ *            PDU. Or frames that contain the Slow Protocols group MAC address,
+ *            but do not carry the Slow Protocols EtherType.
+ * @rx_marker_resp_pdu_frms: Count of valid Marker Response PDUs received on
+ *            this Aggregation port.
+ * @rx_fcs_discard: Count of received frames that are discarded because the
+ *            FCS check failed.
+ * @rx_illegal_pdu_frms: Count of received frames (on this Aggregation port)
+ *            that carry the Slow Protocols EtherType, but contain a badly
+ *            formed PDU. Or frames that carry the Slow Protocols EtherType,
+ *            but contain an illegal value of Protocol Subtype.
+ * @rx_switch_discard: Count of received frames that are discarded by the
+ *            internal switch because they did not have an entry in the
+ *            Filtering Database. This includes frames that had an invalid
+ *            destination MAC address or VLAN ID. It also includes frames are
+ *            discarded because they did not satisfy the length requirements
+ *            of the target VPATH.
+ * @rx_len_discard: Count of received frames that are discarded because of an
+ *            invalid frame length (includes fragments, oversized frames and
+ *            mismatch between frame length and length/type field). This stat
+ *            can be configured
+ *            (see XMAC_STATS_GLOBAL_CFG.LEN_DISCARD_HANDLING).
+ * @rx_rpa_discard: Count of received frames that were discarded because the
+ *            receive protocol assist (RPA) discovered and error in the frame
+ *            or was unable to parse the frame.
+ * @rx_l2_mgmt_discard: Count of Layer 2 management frames (eg. pause frames,
+ *            Link Aggregation Control Protocol (LACP) frames, etc.) that are
+ *            discarded.
+ * @rx_rts_discard: Count of received frames that are discarded by the receive
+ *            traffic steering (RTS) logic. Includes those frame discarded
+ *            because the SSC response contradicted the switch table, because
+ *            the SSC timed out, or because the target queue could not fit the
+ *            frame.
+ * @rx_trash_discard: Count of received frames that are discarded because
+ *            receive traffic steering (RTS) steered the frame to the trash
+ *            queue.
+ * @rx_buff_full_discard: Count of received frames that are discarded because
+ *            internal buffers are full. Includes frames discarded because the
+ *            RTS logic is waiting for an SSC lookup that has no timeout bound.
+ *            Also, includes frames that are dropped because the MAC2FAU buffer
+ *            is nearly full -- this can happen if the external receive buffer
+ *            is full and the receive path is backing up.
+ * @rx_red_discard: Count of received frames that are discarded because of RED
+ *            (Random Early Discard).
+ * @rx_xgmii_ctrl_err_cnt: Maintains a count of unexpected or misplaced control
+ *            characters occuring between times of normal data transmission
+ *            (i.e. not included in RX_XGMII_DATA_ERR_CNT). This counter is
+ *            incremented when either -
+ *            1) The Reconciliation Sublayer (RS) is expecting one control
+ *               character and gets another (i.e. is expecting a Start
+ *               character, but gets another control character).
+ *            2) Start control character is not in lane 0
+ *            Only increments the count by one for each XGMII column.
+ * @rx_xgmii_data_err_cnt: Maintains a count of unexpected control characters
+ *            during normal data transmission. If the Reconciliation Sublayer
+ *            (RS) receives a control character, other than a terminate control
+ *            character, during receipt of data octets then this register is
+ *            incremented. Also increments if the start frame delimiter is not
+ *            found in the correct location. Only increments the count by one
+ *            for each XGMII column.
+ * @rx_xgmii_char1_match: Maintains a count of the number of XGMII characters
+ *            that match a pattern that is programmable through register
+ *            XMAC_STATS_RX_XGMII_CHAR_PORTn. By default, the pattern is set
+ *            to /E/ (i.e. the error character), thus the statistic tracks the
+ *            number of Error characters received at any time.
+ * @rx_xgmii_err_sym: Count of the number of symbol errors in the received
+ *            XGMII data (i.e. PHY indicates "Receive Error" on the XGMII).
+ *            Only includes symbol errors that are observed between the XGMII
+ *            Start Frame Delimiter and End Frame Delimiter, inclusive. And
+ *            only increments the count by one for each frame.
+ * @rx_xgmii_column1_match: Maintains a count of the number of XGMII columns
+ *            that match a pattern that is programmable through register
+ *            XMAC_STATS_RX_XGMII_COLUMN1_PORTn. By default, the pattern is set
+ *            to 4 x /E/ (i.e. a column containing all error characters), thus
+ *            the statistic tracks the number of Error columns received at any
+ *            time.
+ * @rx_xgmii_char2_match: Maintains a count of the number of XGMII characters
+ *            that match a pattern that is programmable through register
+ *            XMAC_STATS_RX_XGMII_CHAR_PORTn. By default, the pattern is set
+ *            to /E/ (i.e. the error character), thus the statistic tracks the
+ *            number of Error characters received at any time.
+ * @rx_local_fault: Maintains a count of the number of times that link
+ *            transitioned from "up" to "down" due to a local fault.
+ * @rx_xgmii_column2_match: Maintains a count of the number of XGMII columns
+ *            that match a pattern that is programmable through register
+ *            XMAC_STATS_RX_XGMII_COLUMN2_PORTn. By default, the pattern is set
+ *            to 4 x /E/ (i.e. a column containing all error characters), thus
+ *            the statistic tracks the number of Error columns received at any
+ *            time. If XMAC_STATS_RX_XGMII_BEHAV_COLUMN2_PORTn.NEAR_COL1 is set
+ *            to 1, then this stat increments when COLUMN2 is found within 'n'
+ *            clocks after COLUMN1. Here, 'n' is defined by
+ *            XMAC_STATS_RX_XGMII_BEHAV_COLUMN2_PORTn.NUM_COL (if 'n' is set to
+ *            0, then it means to search anywhere for COLUMN2).
+ * @rx_jettison: Count of received frames that are jettisoned because internal
+ *            buffers are full.
+ * @rx_remote_fault: Maintains a count of the number of times that link
+ *            transitioned from "up" to "down" due to a remote fault.
+ *
+ * XMAC Port Statistics.
+ */
+struct vxge_hw_xmac_port_stats {
+/*0x000*/		u64	tx_ttl_frms;
+/*0x008*/		u64	tx_ttl_octets;
+/*0x010*/		u64	tx_data_octets;
+/*0x018*/		u64	tx_mcast_frms;
+/*0x020*/		u64	tx_bcast_frms;
+/*0x028*/		u64	tx_ucast_frms;
+/*0x030*/		u64	tx_tagged_frms;
+/*0x038*/		u64	tx_vld_ip;
+/*0x040*/		u64	tx_vld_ip_octets;
+/*0x048*/		u64	tx_icmp;
+/*0x050*/		u64	tx_tcp;
+/*0x058*/		u64	tx_rst_tcp;
+/*0x060*/		u64	tx_udp;
+/*0x068*/		u32	tx_parse_error;
+/*0x06c*/		u32	tx_unknown_protocol;
+/*0x070*/		u64	tx_pause_ctrl_frms;
+/*0x078*/		u32	tx_marker_pdu_frms;
+/*0x07c*/		u32	tx_lacpdu_frms;
+/*0x080*/		u32	tx_drop_ip;
+/*0x084*/		u32	tx_marker_resp_pdu_frms;
+/*0x088*/		u32	tx_xgmii_char2_match;
+/*0x08c*/		u32	tx_xgmii_char1_match;
+/*0x090*/		u32	tx_xgmii_column2_match;
+/*0x094*/		u32	tx_xgmii_column1_match;
+/*0x098*/		u32	unused1;
+/*0x09c*/		u16	tx_any_err_frms;
+/*0x09e*/		u16	tx_drop_frms;
+/*0x0a0*/		u64	rx_ttl_frms;
+/*0x0a8*/		u64	rx_vld_frms;
+/*0x0b0*/		u64	rx_offload_frms;
+/*0x0b8*/		u64	rx_ttl_octets;
+/*0x0c0*/		u64	rx_data_octets;
+/*0x0c8*/		u64	rx_offload_octets;
+/*0x0d0*/		u64	rx_vld_mcast_frms;
+/*0x0d8*/		u64	rx_vld_bcast_frms;
+/*0x0e0*/		u64	rx_accepted_ucast_frms;
+/*0x0e8*/		u64	rx_accepted_nucast_frms;
+/*0x0f0*/		u64	rx_tagged_frms;
+/*0x0f8*/		u64	rx_long_frms;
+/*0x100*/		u64	rx_usized_frms;
+/*0x108*/		u64	rx_osized_frms;
+/*0x110*/		u64	rx_frag_frms;
+/*0x118*/		u64	rx_jabber_frms;
+/*0x120*/		u64	rx_ttl_64_frms;
+/*0x128*/		u64	rx_ttl_65_127_frms;
+/*0x130*/		u64	rx_ttl_128_255_frms;
+/*0x138*/		u64	rx_ttl_256_511_frms;
+/*0x140*/		u64	rx_ttl_512_1023_frms;
+/*0x148*/		u64	rx_ttl_1024_1518_frms;
+/*0x150*/		u64	rx_ttl_1519_4095_frms;
+/*0x158*/		u64	rx_ttl_4096_8191_frms;
+/*0x160*/		u64	rx_ttl_8192_max_frms;
+/*0x168*/		u64	rx_ttl_gt_max_frms;
+/*0x170*/		u64	rx_ip;
+/*0x178*/		u64	rx_accepted_ip;
+/*0x180*/		u64	rx_ip_octets;
+/*0x188*/		u64	rx_err_ip;
+/*0x190*/		u64	rx_icmp;
+/*0x198*/		u64	rx_tcp;
+/*0x1a0*/		u64	rx_udp;
+/*0x1a8*/		u64	rx_err_tcp;
+/*0x1b0*/		u64	rx_pause_count;
+/*0x1b8*/		u64	rx_pause_ctrl_frms;
+/*0x1c0*/		u64	rx_unsup_ctrl_frms;
+/*0x1c8*/		u64	rx_fcs_err_frms;
+/*0x1d0*/		u64	rx_in_rng_len_err_frms;
+/*0x1d8*/		u64	rx_out_rng_len_err_frms;
+/*0x1e0*/		u64	rx_drop_frms;
+/*0x1e8*/		u64	rx_discarded_frms;
+/*0x1f0*/		u64	rx_drop_ip;
+/*0x1f8*/		u64	rx_drop_udp;
+/*0x200*/		u32	rx_marker_pdu_frms;
+/*0x204*/		u32	rx_lacpdu_frms;
+/*0x208*/		u32	rx_unknown_pdu_frms;
+/*0x20c*/		u32	rx_marker_resp_pdu_frms;
+/*0x210*/		u32	rx_fcs_discard;
+/*0x214*/		u32	rx_illegal_pdu_frms;
+/*0x218*/		u32	rx_switch_discard;
+/*0x21c*/		u32	rx_len_discard;
+/*0x220*/		u32	rx_rpa_discard;
+/*0x224*/		u32	rx_l2_mgmt_discard;
+/*0x228*/		u32	rx_rts_discard;
+/*0x22c*/		u32	rx_trash_discard;
+/*0x230*/		u32	rx_buff_full_discard;
+/*0x234*/		u32	rx_red_discard;
+/*0x238*/		u32	rx_xgmii_ctrl_err_cnt;
+/*0x23c*/		u32	rx_xgmii_data_err_cnt;
+/*0x240*/		u32	rx_xgmii_char1_match;
+/*0x244*/		u32	rx_xgmii_err_sym;
+/*0x248*/		u32	rx_xgmii_column1_match;
+/*0x24c*/		u32	rx_xgmii_char2_match;
+/*0x250*/		u32	rx_local_fault;
+/*0x254*/		u32	rx_xgmii_column2_match;
+/*0x258*/		u32	rx_jettison;
+/*0x25c*/		u32	rx_remote_fault;
+} __packed;
+
+/**
+ * struct vxge_hw_xmac_vpath_tx_stats - XMAC Vpath Tx Statistics
+ *
+ * @tx_ttl_eth_frms: Count of successfully transmitted MAC frames.
+ * @tx_ttl_eth_octets: Count of total octets of transmitted frames,
+ *             not including framing characters (i.e. less framing bits).
+ *             To determine the total octets of transmitted frames, including
+ *             framing characters, multiply TX_TTL_ETH_FRMS by 8 and add it to
+ *             this stat (the device always prepends 8 bytes of preamble for
+ *             each frame)
+ * @tx_data_octets: Count of data and padding octets of successfully transmitted
+ *             frames.
+ * @tx_mcast_frms: Count of successfully transmitted frames to a group address
+ *             other than the broadcast address.
+ * @tx_bcast_frms: Count of successfully transmitted frames to the broadcast
+ *             group address.
+ * @tx_ucast_frms: Count of transmitted frames containing a unicast address.
+ *             Includes discarded frames that are not sent to the network.
+ * @tx_tagged_frms: Count of transmitted frames containing a VLAN tag.
+ * @tx_vld_ip: Count of transmitted IP datagrams that are passed to the network.
+ * @tx_vld_ip_octets: Count of total octets of transmitted IP datagrams that
+ *            are passed to the network.
+ * @tx_icmp: Count of transmitted ICMP messages. Includes messages not sent due
+ *            to problems within ICMP.
+ * @tx_tcp: Count of transmitted TCP segments. Does not include segments
+ *            containing retransmitted octets.
+ * @tx_rst_tcp: Count of transmitted TCP segments containing the RST flag.
+ * @tx_udp: Count of transmitted UDP datagrams.
+ * @tx_unknown_protocol: Increments when the TPA encounters an unknown protocol,
+ *            such as a new IPv6 extension header, or an unsupported Routing
+ *            Type. The packet still has a checksum calculated but it may be
+ *            incorrect.
+ * @tx_lost_ip: Count of transmitted IP datagrams that could not be passed
+ *            to the network. Increments because of: 1) An internal processing
+ *            error (such as an uncorrectable ECC error). 2) A frame parsing
+ *            error during IP checksum calculation.
+ * @tx_parse_error: Increments when the TPA is unable to parse a packet. This
+ *            generally occurs when a packet is corrupt somehow, including
+ *            packets that have IP version mismatches, invalid Layer 2 control
+ *            fields, etc. L3/L4 checksums are not offloaded, but the packet
+ *            is still be transmitted.
+ * @tx_tcp_offload: For frames belonging to offloaded sessions only, a count
+ *            of transmitted TCP segments. Does not include segments containing
+ *            retransmitted octets.
+ * @tx_retx_tcp_offload: For frames belonging to offloaded sessions only, the
+ *            total number of segments retransmitted. Retransmitted segments
+ *            that are sourced by the host are counted by the host.
+ * @tx_lost_ip_offload: For frames belonging to offloaded sessions only, a count
+ *            of transmitted IP datagrams that could not be passed to the
+ *            network.
+ *
+ * XMAC Vpath TX Statistics.
+ */
+struct vxge_hw_xmac_vpath_tx_stats {
+	u64	tx_ttl_eth_frms;
+	u64	tx_ttl_eth_octets;
+	u64	tx_data_octets;
+	u64	tx_mcast_frms;
+	u64	tx_bcast_frms;
+	u64	tx_ucast_frms;
+	u64	tx_tagged_frms;
+	u64	tx_vld_ip;
+	u64	tx_vld_ip_octets;
+	u64	tx_icmp;
+	u64	tx_tcp;
+	u64	tx_rst_tcp;
+	u64	tx_udp;
+	u32	tx_unknown_protocol;
+	u32	tx_lost_ip;
+	u32	unused1;
+	u32	tx_parse_error;
+	u64	tx_tcp_offload;
+	u64	tx_retx_tcp_offload;
+	u64	tx_lost_ip_offload;
+} __packed;
+
+/**
+ * struct vxge_hw_xmac_vpath_rx_stats - XMAC Vpath RX Statistics
+ *
+ * @rx_ttl_eth_frms: Count of successfully received MAC frames.
+ * @rx_vld_frms: Count of successfully received MAC frames. Does not include
+ *            frames received with frame-too-long, FCS, or length errors.
+ * @rx_offload_frms: Count of offloaded received frames that are passed to
+ *            the host.
+ * @rx_ttl_eth_octets: Count of total octets of received frames, not including
+ *            framing characters (i.e. less framing bits). Only counts octets
+ *            of frames that are at least 14 bytes (18 bytes for VLAN-tagged)
+ *            before FCS. To determine the total octets of received frames,
+ *            including framing characters, multiply RX_TTL_ETH_FRMS by 8 and
+ *            add it to this stat (the stat RX_TTL_ETH_FRMS only counts frames
+ *            that have the required 8 bytes of preamble).
+ * @rx_data_octets: Count of data and padding octets of successfully received
+ *            frames. Does not include frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_offload_octets: Count of total octets, not including framing characters,
+ *            of offloaded received frames that are passed to the host.
+ * @rx_vld_mcast_frms: Count of successfully received MAC frames containing a
+ *            nonbroadcast group address. Does not include frames received with
+ *            frame-too-long, FCS, or length errors.
+ * @rx_vld_bcast_frms: Count of successfully received MAC frames containing the
+ *            broadcast group address. Does not include frames received with
+ *            frame-too-long, FCS, or length errors.
+ * @rx_accepted_ucast_frms: Count of successfully received frames containing
+ *            a unicast address. Only includes frames that are passed to the
+ *            system.
+ * @rx_accepted_nucast_frms: Count of successfully received frames containing
+ *            a non-unicast (broadcast or multicast) address. Only includes
+ *            frames that are passed to the system. Could include, for instance,
+ *            non-unicast frames that contain FCS errors if the MAC_ERROR_CFG
+ *            register is set to pass FCS-errored frames to the host.
+ * @rx_tagged_frms: Count of received frames containing a VLAN tag.
+ * @rx_long_frms: Count of received frames that are longer than RX_MAX_PYLD_LEN
+ *            + 18 bytes (+ 22 bytes if VLAN-tagged).
+ * @rx_usized_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) less than 64 octets, that are otherwise well-formed.
+ *            In other words, counts runts.
+ * @rx_osized_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) more than 1518 octets, that are otherwise
+ *            well-formed.
+ * @rx_frag_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) less than 64 octets that had bad FCS.
+ *            In other words, counts fragments.
+ * @rx_jabber_frms: Count of received frames of length (including FCS, but not
+ *            framing bits) more than 1518 octets that had bad FCS. In other
+ *            words, counts jabbers.
+ * @rx_ttl_64_frms: Count of total received MAC frames with length (including
+ *            FCS, but not framing bits) of exactly 64 octets. Includes frames
+ *            received with frame-too-long, FCS, or length errors.
+ * @rx_ttl_65_127_frms: Count of total received MAC frames
+ * 		with length (including
+ *            FCS, but not framing bits) of between 65 and 127 octets inclusive.
+ *            Includes frames received with frame-too-long, FCS,
+ *            or length errors.
+ * @rx_ttl_128_255_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits)
+ *            of between 128 and 255 octets
+ *            inclusive. Includes frames received with frame-too-long, FCS,
+ *            or length errors.
+ * @rx_ttl_256_511_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits)
+ *            of between 256 and 511 octets
+ *            inclusive. Includes frames received with frame-too-long, FCS, or
+ *            length errors.
+ * @rx_ttl_512_1023_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 512 and 1023
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_1024_1518_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 1024 and 1518
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_1519_4095_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 1519 and 4095
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_4096_8191_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 4096 and 8191
+ *            octets inclusive. Includes frames received with frame-too-long,
+ *            FCS, or length errors.
+ * @rx_ttl_8192_max_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) of between 8192 and
+ *            RX_MAX_PYLD_LEN+18 octets inclusive. Includes frames received
+ *            with frame-too-long, FCS, or length errors.
+ * @rx_ttl_gt_max_frms: Count of total received MAC frames with length
+ *            (including FCS, but not framing bits) exceeding RX_MAX_PYLD_LEN+18
+ *            (+22 bytes if VLAN-tagged) octets inclusive. Includes frames
+ *            received with frame-too-long, FCS, or length errors.
+ * @rx_ip: Count of received IP datagrams. Includes errored IP datagrams.
+ * @rx_accepted_ip: Count of received IP datagrams that
+ * 		are passed to the system.
+ * @rx_ip_octets: Count of number of octets in received IP datagrams.
+ *            Includes errored IP datagrams.
+ * @rx_err_ip: Count of received IP datagrams containing errors. For example,
+ *            bad IP checksum.
+ * @rx_icmp: Count of received ICMP messages. Includes errored ICMP messages.
+ * @rx_tcp: Count of received TCP segments. Includes errored TCP segments.
+ *             Note: This stat contains a count of all received TCP segments,
+ *             regardless of whether or not they pertain to an established
+ *             connection.
+ * @rx_udp: Count of received UDP datagrams.
+ * @rx_err_tcp: Count of received TCP segments containing errors. For example,
+ *             bad TCP checksum.
+ * @rx_lost_frms: Count of received frames that could not be passed to the host.
+ *             See RX_QUEUE_FULL_DISCARD and RX_RED_DISCARD
+ *             for a list of reasons.
+ * @rx_lost_ip: Count of received IP datagrams that could not be passed to
+ *             the host. See RX_LOST_FRMS for a list of reasons.
+ * @rx_lost_ip_offload: For frames belonging to offloaded sessions only, a count
+ *             of received IP datagrams that could not be passed to the host.
+ *             See RX_LOST_FRMS for a list of reasons.
+ * @rx_various_discard: Count of received frames that are discarded because
+ *             the target receive queue is full.
+ * @rx_sleep_discard: Count of received frames that are discarded because the
+ *            target VPATH is asleep (a Wake-on-LAN magic packet can be used
+ *            to awaken the VPATH).
+ * @rx_red_discard: Count of received frames that are discarded because of RED
+ *            (Random Early Discard).
+ * @rx_queue_full_discard: Count of received frames that are discarded because
+ *             the target receive queue is full.
+ * @rx_mpa_ok_frms: Count of received frames that pass the MPA checks.
+ *
+ * XMAC Vpath RX Statistics.
+ */
+struct vxge_hw_xmac_vpath_rx_stats {
+	u64	rx_ttl_eth_frms;
+	u64	rx_vld_frms;
+	u64	rx_offload_frms;
+	u64	rx_ttl_eth_octets;
+	u64	rx_data_octets;
+	u64	rx_offload_octets;
+	u64	rx_vld_mcast_frms;
+	u64	rx_vld_bcast_frms;
+	u64	rx_accepted_ucast_frms;
+	u64	rx_accepted_nucast_frms;
+	u64	rx_tagged_frms;
+	u64	rx_long_frms;
+	u64	rx_usized_frms;
+	u64	rx_osized_frms;
+	u64	rx_frag_frms;
+	u64	rx_jabber_frms;
+	u64	rx_ttl_64_frms;
+	u64	rx_ttl_65_127_frms;
+	u64	rx_ttl_128_255_frms;
+	u64	rx_ttl_256_511_frms;
+	u64	rx_ttl_512_1023_frms;
+	u64	rx_ttl_1024_1518_frms;
+	u64	rx_ttl_1519_4095_frms;
+	u64	rx_ttl_4096_8191_frms;
+	u64	rx_ttl_8192_max_frms;
+	u64	rx_ttl_gt_max_frms;
+	u64	rx_ip;
+	u64	rx_accepted_ip;
+	u64	rx_ip_octets;
+	u64	rx_err_ip;
+	u64	rx_icmp;
+	u64	rx_tcp;
+	u64	rx_udp;
+	u64	rx_err_tcp;
+	u64	rx_lost_frms;
+	u64	rx_lost_ip;
+	u64	rx_lost_ip_offload;
+	u16	rx_various_discard;
+	u16	rx_sleep_discard;
+	u16	rx_red_discard;
+	u16	rx_queue_full_discard;
+	u64	rx_mpa_ok_frms;
+} __packed;
+
+/**
+ * struct vxge_hw_xmac_stats - XMAC Statistics
+ *
+ * @aggr_stats: Statistics on aggregate port(port 0, port 1)
+ * @port_stats: Staticstics on ports(wire 0, wire 1, lag)
+ * @vpath_tx_stats: Per vpath XMAC TX stats
+ * @vpath_rx_stats: Per vpath XMAC RX stats
+ *
+ * XMAC Statistics.
+ */
+struct vxge_hw_xmac_stats {
+	struct vxge_hw_xmac_aggr_stats
+				aggr_stats[VXGE_HW_MAC_MAX_MAC_PORT_ID];
+	struct vxge_hw_xmac_port_stats
+				port_stats[VXGE_HW_MAC_MAX_MAC_PORT_ID+1];
+	struct vxge_hw_xmac_vpath_tx_stats
+				vpath_tx_stats[VXGE_HW_MAX_VIRTUAL_PATHS];
+	struct vxge_hw_xmac_vpath_rx_stats
+				vpath_rx_stats[VXGE_HW_MAX_VIRTUAL_PATHS];
+};
+
+/**
+ * struct vxge_hw_vpath_stats_hw_info - Titan vpath hardware statistics.
+ * @ini_num_mwr_sent: The number of PCI memory writes initiated by the PIC block
+ *             for the given VPATH
+ * @ini_num_mrd_sent: The number of PCI memory reads initiated by the PIC block
+ * @ini_num_cpl_rcvd: The number of PCI read completions received by the
+ *             PIC block
+ * @ini_num_mwr_byte_sent: The number of PCI memory write bytes sent by the PIC
+ *             block to the host
+ * @ini_num_cpl_byte_rcvd: The number of PCI read completion bytes received by
+ *             the PIC block
+ * @wrcrdtarb_xoff: TBD
+ * @rdcrdtarb_xoff: TBD
+ * @vpath_genstats_count0: TBD
+ * @vpath_genstats_count1: TBD
+ * @vpath_genstats_count2: TBD
+ * @vpath_genstats_count3: TBD
+ * @vpath_genstats_count4: TBD
+ * @vpath_gennstats_count5: TBD
+ * @tx_stats: Transmit stats
+ * @rx_stats: Receive stats
+ * @prog_event_vnum1: Programmable statistic. Increments when internal logic
+ *             detects a certain event. See register
+ *             XMAC_STATS_CFG.EVENT_VNUM1_CFG for more information.
+ * @prog_event_vnum0: Programmable statistic. Increments when internal logic
+ *             detects a certain event. See register
+ *             XMAC_STATS_CFG.EVENT_VNUM0_CFG for more information.
+ * @prog_event_vnum3: Programmable statistic. Increments when internal logic
+ *             detects a certain event. See register
+ *             XMAC_STATS_CFG.EVENT_VNUM3_CFG for more information.
+ * @prog_event_vnum2: Programmable statistic. Increments when internal logic
+ *             detects a certain event. See register
+ *             XMAC_STATS_CFG.EVENT_VNUM2_CFG for more information.
+ * @rx_multi_cast_frame_discard: TBD
+ * @rx_frm_transferred: TBD
+ * @rxd_returned: TBD
+ * @rx_mpa_len_fail_frms: Count of received frames
+ * 		that fail the MPA length check
+ * @rx_mpa_mrk_fail_frms: Count of received frames
+ * 		that fail the MPA marker check
+ * @rx_mpa_crc_fail_frms: Count of received frames that fail the MPA CRC check
+ * @rx_permitted_frms: Count of frames that pass through the FAU and on to the
+ *             frame buffer (and subsequently to the host).
+ * @rx_vp_reset_discarded_frms: Count of receive frames that are discarded
+ *             because the VPATH is in reset
+ * @rx_wol_frms: Count of received "magic packet" frames. Stat increments
+ *             whenever the received frame matches the VPATH's Wake-on-LAN
+ *             signature(s) CRC.
+ * @tx_vp_reset_discarded_frms: Count of transmit frames that are discarded
+ *             because the VPATH is in reset. Includes frames that are discarded
+ *             because the current VPIN does not match that VPIN of the frame
+ *
+ * Titan vpath hardware statistics.
+ */
+struct vxge_hw_vpath_stats_hw_info {
+/*0x000*/	u32 ini_num_mwr_sent;
+/*0x004*/	u32 unused1;
+/*0x008*/	u32 ini_num_mrd_sent;
+/*0x00c*/	u32 unused2;
+/*0x010*/	u32 ini_num_cpl_rcvd;
+/*0x014*/	u32 unused3;
+/*0x018*/	u64 ini_num_mwr_byte_sent;
+/*0x020*/	u64 ini_num_cpl_byte_rcvd;
+/*0x028*/	u32 wrcrdtarb_xoff;
+/*0x02c*/	u32 unused4;
+/*0x030*/	u32 rdcrdtarb_xoff;
+/*0x034*/	u32 unused5;
+/*0x038*/	u32 vpath_genstats_count0;
+/*0x03c*/	u32 vpath_genstats_count1;
+/*0x040*/	u32 vpath_genstats_count2;
+/*0x044*/	u32 vpath_genstats_count3;
+/*0x048*/	u32 vpath_genstats_count4;
+/*0x04c*/	u32 unused6;
+/*0x050*/	u32 vpath_genstats_count5;
+/*0x054*/	u32 unused7;
+/*0x058*/	struct vxge_hw_xmac_vpath_tx_stats tx_stats;
+/*0x0e8*/	struct vxge_hw_xmac_vpath_rx_stats rx_stats;
+/*0x220*/	u64 unused9;
+/*0x228*/	u32 prog_event_vnum1;
+/*0x22c*/	u32 prog_event_vnum0;
+/*0x230*/	u32 prog_event_vnum3;
+/*0x234*/	u32 prog_event_vnum2;
+/*0x238*/	u16 rx_multi_cast_frame_discard;
+/*0x23a*/	u8 unused10[6];
+/*0x240*/	u32 rx_frm_transferred;
+/*0x244*/	u32 unused11;
+/*0x248*/	u16 rxd_returned;
+/*0x24a*/	u8 unused12[6];
+/*0x252*/	u16 rx_mpa_len_fail_frms;
+/*0x254*/	u16 rx_mpa_mrk_fail_frms;
+/*0x256*/	u16 rx_mpa_crc_fail_frms;
+/*0x258*/	u16 rx_permitted_frms;
+/*0x25c*/	u64 rx_vp_reset_discarded_frms;
+/*0x25e*/	u64 rx_wol_frms;
+/*0x260*/	u64 tx_vp_reset_discarded_frms;
+} __packed;
+
+
+/**
+ * struct vxge_hw_device_stats_mrpcim_info - Titan mrpcim hardware statistics.
+ * @pic.ini_rd_drop  	 0x0000  	 4  	 Number of DMA reads initiated
+ *  by the adapter that were discarded because the VPATH is out of service
+ * @pic.ini_wr_drop 	0x0004 	4 	Number of DMA writes initiated by the
+ *  adapter that were discared because the VPATH is out of service
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane0] 	0x0008 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane1] 	0x0010 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane2] 	0x0018 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane3] 	0x0020 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane4] 	0x0028 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane5] 	0x0030 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane6] 	0x0038 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane7] 	0x0040 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane8] 	0x0048 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane9] 	0x0050 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane10] 	0x0058 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane11] 	0x0060 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane12] 	0x0068 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane13] 	0x0070 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane14] 	0x0078 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane15] 	0x0080 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_ph_crdt_depleted[vplane16] 	0x0088 	4 	Number of times
+ *  the posted header credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane0] 	0x0090 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane1] 	0x0098 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane2] 	0x00a0 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane3] 	0x00a8 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane4] 	0x00b0 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane5] 	0x00b8 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane6] 	0x00c0 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane7] 	0x00c8 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane8] 	0x00d0 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane9] 	0x00d8 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane10] 	0x00e0 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane11] 	0x00e8 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane12] 	0x00f0 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane13] 	0x00f8 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane14] 	0x0100 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane15] 	0x0108 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.wrcrdtarb_pd_crdt_depleted[vplane16] 	0x0110 	4 	Number of times
+ *  the posted data credits for upstream PCI writes were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane0] 	0x0118 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane1] 	0x0120 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane2] 	0x0128 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane3] 	0x0130 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane4] 	0x0138 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane5] 	0x0140 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane6] 	0x0148 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane7] 	0x0150 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane8] 	0x0158 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane9] 	0x0160 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane10] 	0x0168 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane11] 	0x0170 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane12] 	0x0178 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane13] 	0x0180 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane14] 	0x0188 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane15] 	0x0190 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.rdcrdtarb_nph_crdt_depleted[vplane16] 	0x0198 	4 	Number of times
+ *  the non-posted header credits for upstream PCI reads were depleted
+ * @pic.ini_rd_vpin_drop 	0x01a0 	4 	Number of DMA reads initiated by
+ *  the adapter that were discarded because the VPATH instance number does
+ *  not match
+ * @pic.ini_wr_vpin_drop 	0x01a4 	4 	Number of DMA writes initiated
+ *  by the adapter that were discarded because the VPATH instance number
+ *  does not match
+ * @pic.genstats_count0 	0x01a8 	4 	Configurable statistic #1. Refer
+ *  to the GENSTATS0_CFG for information on configuring this statistic
+ * @pic.genstats_count1 	0x01ac 	4 	Configurable statistic #2. Refer
+ *  to the GENSTATS1_CFG for information on configuring this statistic
+ * @pic.genstats_count2 	0x01b0 	4 	Configurable statistic #3. Refer
+ *  to the GENSTATS2_CFG for information on configuring this statistic
+ * @pic.genstats_count3 	0x01b4 	4 	Configurable statistic #4. Refer
+ *  to the GENSTATS3_CFG for information on configuring this statistic
+ * @pic.genstats_count4 	0x01b8 	4 	Configurable statistic #5. Refer
+ *  to the GENSTATS4_CFG for information on configuring this statistic
+ * @pic.genstats_count5 	0x01c0 	4 	Configurable statistic #6. Refer
+ *  to the GENSTATS5_CFG for information on configuring this statistic
+ * @pci.rstdrop_cpl 	0x01c8 	4
+ * @pci.rstdrop_msg 	0x01cc 	4
+ * @pci.rstdrop_client1 	0x01d0 	4
+ * @pci.rstdrop_client0 	0x01d4 	4
+ * @pci.rstdrop_client2 	0x01d8 	4
+ * @pci.depl_cplh[vplane0] 	0x01e2 	2 	Number of times completion
+ *  header credits were depleted
+ * @pci.depl_nph[vplane0] 	0x01e4 	2 	Number of times non posted
+ *  header credits were depleted
+ * @pci.depl_ph[vplane0] 	0x01e6 	2 	Number of times the posted
+ *  header credits were depleted
+ * @pci.depl_cplh[vplane1] 	0x01ea 	2
+ * @pci.depl_nph[vplane1] 	0x01ec 	2
+ * @pci.depl_ph[vplane1] 	0x01ee 	2
+ * @pci.depl_cplh[vplane2] 	0x01f2 	2
+ * @pci.depl_nph[vplane2] 	0x01f4 	2
+ * @pci.depl_ph[vplane2] 	0x01f6 	2
+ * @pci.depl_cplh[vplane3] 	0x01fa 	2
+ * @pci.depl_nph[vplane3] 	0x01fc 	2
+ * @pci.depl_ph[vplane3] 	0x01fe 	2
+ * @pci.depl_cplh[vplane4] 	0x0202 	2
+ * @pci.depl_nph[vplane4] 	0x0204 	2
+ * @pci.depl_ph[vplane4] 	0x0206 	2
+ * @pci.depl_cplh[vplane5] 	0x020a 	2
+ * @pci.depl_nph[vplane5] 	0x020c 	2
+ * @pci.depl_ph[vplane5] 	0x020e 	2
+ * @pci.depl_cplh[vplane6] 	0x0212 	2
+ * @pci.depl_nph[vplane6] 	0x0214 	2
+ * @pci.depl_ph[vplane6] 	0x0216 	2
+ * @pci.depl_cplh[vplane7] 	0x021a 	2
+ * @pci.depl_nph[vplane7] 	0x021c 	2
+ * @pci.depl_ph[vplane7] 	0x021e 	2
+ * @pci.depl_cplh[vplane8] 	0x0222 	2
+ * @pci.depl_nph[vplane8] 	0x0224 	2
+ * @pci.depl_ph[vplane8] 	0x0226 	2
+ * @pci.depl_cplh[vplane9] 	0x022a 	2
+ * @pci.depl_nph[vplane9] 	0x022c 	2
+ * @pci.depl_ph[vplane9] 	0x022e 	2
+ * @pci.depl_cplh[vplane10] 	0x0232 	2
+ * @pci.depl_nph[vplane10] 	0x0234 	2
+ * @pci.depl_ph[vplane10] 	0x0236 	2
+ * @pci.depl_cplh[vplane11] 	0x023a 	2
+ * @pci.depl_nph[vplane11] 	0x023c 	2
+ * @pci.depl_ph[vplane11] 	0x023e 	2
+ * @pci.depl_cplh[vplane12] 	0x0242 	2
+ * @pci.depl_nph[vplane12] 	0x0244 	2
+ * @pci.depl_ph[vplane12] 	0x0246 	2
+ * @pci.depl_cplh[vplane13] 	0x024a 	2
+ * @pci.depl_nph[vplane13] 	0x024c 	2
+ * @pci.depl_ph[vplane13] 	0x024e 	2
+ * @pci.depl_cplh[vplane14] 	0x0252 	2
+ * @pci.depl_nph[vplane14] 	0x0254 	2
+ * @pci.depl_ph[vplane14] 	0x0256 	2
+ * @pci.depl_cplh[vplane15] 	0x025a 	2
+ * @pci.depl_nph[vplane15] 	0x025c 	2
+ * @pci.depl_ph[vplane15] 	0x025e 	2
+ * @pci.depl_cplh[vplane16] 	0x0262 	2
+ * @pci.depl_nph[vplane16] 	0x0264 	2
+ * @pci.depl_ph[vplane16] 	0x0266 	2
+ * @pci.depl_cpld[vplane0] 	0x026a 	2 	Number of times completion data
+ *  credits were depleted
+ * @pci.depl_npd[vplane0] 	0x026c 	2 	Number of times non posted data
+ *  credits were depleted
+ * @pci.depl_pd[vplane0] 	0x026e 	2 	Number of times the posted data
+ *  credits were depleted
+ * @pci.depl_cpld[vplane1] 	0x0272 	2
+ * @pci.depl_npd[vplane1] 	0x0274 	2
+ * @pci.depl_pd[vplane1] 	0x0276 	2
+ * @pci.depl_cpld[vplane2] 	0x027a 	2
+ * @pci.depl_npd[vplane2] 	0x027c 	2
+ * @pci.depl_pd[vplane2] 	0x027e 	2
+ * @pci.depl_cpld[vplane3] 	0x0282 	2
+ * @pci.depl_npd[vplane3] 	0x0284 	2
+ * @pci.depl_pd[vplane3] 	0x0286 	2
+ * @pci.depl_cpld[vplane4] 	0x028a 	2
+ * @pci.depl_npd[vplane4] 	0x028c 	2
+ * @pci.depl_pd[vplane4] 	0x028e 	2
+ * @pci.depl_cpld[vplane5] 	0x0292 	2
+ * @pci.depl_npd[vplane5] 	0x0294 	2
+ * @pci.depl_pd[vplane5] 	0x0296 	2
+ * @pci.depl_cpld[vplane6] 	0x029a 	2
+ * @pci.depl_npd[vplane6] 	0x029c 	2
+ * @pci.depl_pd[vplane6] 	0x029e 	2
+ * @pci.depl_cpld[vplane7] 	0x02a2 	2
+ * @pci.depl_npd[vplane7] 	0x02a4 	2
+ * @pci.depl_pd[vplane7] 	0x02a6 	2
+ * @pci.depl_cpld[vplane8] 	0x02aa 	2
+ * @pci.depl_npd[vplane8] 	0x02ac 	2
+ * @pci.depl_pd[vplane8] 	0x02ae 	2
+ * @pci.depl_cpld[vplane9] 	0x02b2 	2
+ * @pci.depl_npd[vplane9] 	0x02b4 	2
+ * @pci.depl_pd[vplane9] 	0x02b6 	2
+ * @pci.depl_cpld[vplane10] 	0x02ba 	2
+ * @pci.depl_npd[vplane10] 	0x02bc 	2
+ * @pci.depl_pd[vplane10] 	0x02be 	2
+ * @pci.depl_cpld[vplane11] 	0x02c2 	2
+ * @pci.depl_npd[vplane11] 	0x02c4 	2
+ * @pci.depl_pd[vplane11] 	0x02c6 	2
+ * @pci.depl_cpld[vplane12] 	0x02ca 	2
+ * @pci.depl_npd[vplane12] 	0x02cc 	2
+ * @pci.depl_pd[vplane12] 	0x02ce 	2
+ * @pci.depl_cpld[vplane13] 	0x02d2 	2
+ * @pci.depl_npd[vplane13] 	0x02d4 	2
+ * @pci.depl_pd[vplane13] 	0x02d6 	2
+ * @pci.depl_cpld[vplane14] 	0x02da 	2
+ * @pci.depl_npd[vplane14] 	0x02dc 	2
+ * @pci.depl_pd[vplane14] 	0x02de 	2
+ * @pci.depl_cpld[vplane15] 	0x02e2 	2
+ * @pci.depl_npd[vplane15] 	0x02e4 	2
+ * @pci.depl_pd[vplane15] 	0x02e6 	2
+ * @pci.depl_cpld[vplane16] 	0x02ea 	2
+ * @pci.depl_npd[vplane16] 	0x02ec 	2
+ * @pci.depl_pd[vplane16] 	0x02ee 	2
+ * @xgmac_port[3];
+ * @xgmac_aggr[2];
+ * @xgmac.global_prog_event_gnum0 	0x0ae0 	8 	Programmable statistic.
+ *  Increments when internal logic detects a certain event. See register
+ *  XMAC_STATS_GLOBAL_CFG.EVENT_GNUM0_CFG for more information.
+ * @xgmac.global_prog_event_gnum1 	0x0ae8 	8 	Programmable statistic.
+ *  Increments when internal logic detects a certain event. See register
+ *  XMAC_STATS_GLOBAL_CFG.EVENT_GNUM1_CFG for more information.
+ * @xgmac.orp_lro_events 	0x0af8 	8
+ * @xgmac.orp_bs_events 	0x0b00 	8
+ * @xgmac.orp_iwarp_events 	0x0b08 	8
+ * @xgmac.tx_permitted_frms 	0x0b14 	4
+ * @xgmac.port2_tx_any_frms 	0x0b1d 	1
+ * @xgmac.port1_tx_any_frms 	0x0b1e 	1
+ * @xgmac.port0_tx_any_frms 	0x0b1f 	1
+ * @xgmac.port2_rx_any_frms 	0x0b25 	1
+ * @xgmac.port1_rx_any_frms 	0x0b26 	1
+ * @xgmac.port0_rx_any_frms 	0x0b27 	1
+ *
+ * Titan mrpcim hardware statistics.
+ */
+struct vxge_hw_device_stats_mrpcim_info {
+/*0x0000*/	u32	pic_ini_rd_drop;
+/*0x0004*/	u32	pic_ini_wr_drop;
+/*0x0008*/	struct {
+	/*0x0000*/	u32	pic_wrcrdtarb_ph_crdt_depleted;
+	/*0x0004*/	u32	unused1;
+		} pic_wrcrdtarb_ph_crdt_depleted_vplane[17];
+/*0x0090*/	struct {
+	/*0x0000*/	u32	pic_wrcrdtarb_pd_crdt_depleted;
+	/*0x0004*/	u32	unused2;
+		} pic_wrcrdtarb_pd_crdt_depleted_vplane[17];
+/*0x0118*/	struct {
+	/*0x0000*/	u32	pic_rdcrdtarb_nph_crdt_depleted;
+	/*0x0004*/	u32	unused3;
+		} pic_rdcrdtarb_nph_crdt_depleted_vplane[17];
+/*0x01a0*/	u32	pic_ini_rd_vpin_drop;
+/*0x01a4*/	u32	pic_ini_wr_vpin_drop;
+/*0x01a8*/	u32	pic_genstats_count0;
+/*0x01ac*/	u32	pic_genstats_count1;
+/*0x01b0*/	u32	pic_genstats_count2;
+/*0x01b4*/	u32	pic_genstats_count3;
+/*0x01b8*/	u32	pic_genstats_count4;
+/*0x01bc*/	u32	unused4;
+/*0x01c0*/	u32	pic_genstats_count5;
+/*0x01c4*/	u32	unused5;
+/*0x01c8*/	u32	pci_rstdrop_cpl;
+/*0x01cc*/	u32	pci_rstdrop_msg;
+/*0x01d0*/	u32	pci_rstdrop_client1;
+/*0x01d4*/	u32	pci_rstdrop_client0;
+/*0x01d8*/	u32	pci_rstdrop_client2;
+/*0x01dc*/	u32	unused6;
+/*0x01e0*/	struct {
+	/*0x0000*/	u16	unused7;
+	/*0x0002*/	u16	pci_depl_cplh;
+	/*0x0004*/	u16	pci_depl_nph;
+	/*0x0006*/	u16	pci_depl_ph;
+		} pci_depl_h_vplane[17];
+/*0x0268*/	struct {
+	/*0x0000*/	u16	unused8;
+	/*0x0002*/	u16	pci_depl_cpld;
+	/*0x0004*/	u16	pci_depl_npd;
+	/*0x0006*/	u16	pci_depl_pd;
+		} pci_depl_d_vplane[17];
+/*0x02f0*/	struct vxge_hw_xmac_port_stats xgmac_port[3];
+/*0x0a10*/	struct vxge_hw_xmac_aggr_stats xgmac_aggr[2];
+/*0x0ae0*/	u64	xgmac_global_prog_event_gnum0;
+/*0x0ae8*/	u64	xgmac_global_prog_event_gnum1;
+/*0x0af0*/	u64	unused7;
+/*0x0af8*/	u64	unused8;
+/*0x0b00*/	u64	unused9;
+/*0x0b08*/	u64	unused10;
+/*0x0b10*/	u32	unused11;
+/*0x0b14*/	u32	xgmac_tx_permitted_frms;
+/*0x0b18*/	u32	unused12;
+/*0x0b1c*/	u8	unused13;
+/*0x0b1d*/	u8	xgmac_port2_tx_any_frms;
+/*0x0b1e*/	u8	xgmac_port1_tx_any_frms;
+/*0x0b1f*/	u8	xgmac_port0_tx_any_frms;
+/*0x0b20*/	u32	unused14;
+/*0x0b24*/	u8	unused15;
+/*0x0b25*/	u8	xgmac_port2_rx_any_frms;
+/*0x0b26*/	u8	xgmac_port1_rx_any_frms;
+/*0x0b27*/	u8	xgmac_port0_rx_any_frms;
+} __packed;
+
+/**
+ * struct vxge_hw_device_stats_hw_info - Titan hardware statistics.
+ * @vpath_info: VPath statistics
+ * @vpath_info_sav: Vpath statistics saved
+ *
+ * Titan hardware statistics.
+ */
+struct vxge_hw_device_stats_hw_info {
+	struct vxge_hw_vpath_stats_hw_info
+		*vpath_info[VXGE_HW_MAX_VIRTUAL_PATHS];
+	struct vxge_hw_vpath_stats_hw_info
+		vpath_info_sav[VXGE_HW_MAX_VIRTUAL_PATHS];
+};
+
+/**
+ * struct vxge_hw_vpath_stats_sw_common_info - HW common
+ * statistics for queues.
+ * @full_cnt: Number of times the queue was full
+ * @usage_cnt: usage count.
+ * @usage_max: Maximum usage
+ * @reserve_free_swaps_cnt: Reserve/free swap counter. Internal usage.
+ * @total_compl_cnt: Total descriptor completion count.
+ *
+ * Hw queue counters
+ * See also: struct vxge_hw_vpath_stats_sw_fifo_info{},
+ * struct vxge_hw_vpath_stats_sw_ring_info{},
+ */
+struct vxge_hw_vpath_stats_sw_common_info {
+	u32	full_cnt;
+	u32	usage_cnt;
+	u32	usage_max;
+	u32	reserve_free_swaps_cnt;
+	u32 total_compl_cnt;
+};
+
+/**
+ * struct vxge_hw_vpath_stats_sw_fifo_info - HW fifo statistics
+ * @common_stats: Common counters for all queues
+ * @total_posts: Total number of postings on the queue.
+ * @total_buffers: Total number of buffers posted.
+ * @txd_t_code_err_cnt: Array of transmit transfer codes. The position
+ * (index) in this array reflects the transfer code type, for instance
+ * 0xA - "loss of link".
+ * Value txd_t_code_err_cnt[i] reflects the
+ * number of times the corresponding transfer code was encountered.
+ *
+ * HW fifo counters
+ * See also: struct vxge_hw_vpath_stats_sw_common_info{},
+ * struct vxge_hw_vpath_stats_sw_ring_info{},
+ */
+struct vxge_hw_vpath_stats_sw_fifo_info {
+	struct vxge_hw_vpath_stats_sw_common_info common_stats;
+	u32 total_posts;
+	u32 total_buffers;
+	u32 txd_t_code_err_cnt[VXGE_HW_DTR_MAX_T_CODE];
+};
+
+/**
+ * struct vxge_hw_vpath_stats_sw_ring_info - HW ring statistics
+ * @common_stats: Common counters for all queues
+ * @rxd_t_code_err_cnt: Array of receive transfer codes. The position
+ *             (index) in this array reflects the transfer code type,
+ *             for instance
+ *             0x7 - for "invalid receive buffer size", or 0x8 - for ECC.
+ *             Value rxd_t_code_err_cnt[i] reflects the
+ *             number of times the corresponding transfer code was encountered.
+ *
+ * HW ring counters
+ * See also: struct vxge_hw_vpath_stats_sw_common_info{},
+ * struct vxge_hw_vpath_stats_sw_fifo_info{},
+ */
+struct vxge_hw_vpath_stats_sw_ring_info {
+	struct vxge_hw_vpath_stats_sw_common_info common_stats;
+	u32 rxd_t_code_err_cnt[VXGE_HW_DTR_MAX_T_CODE];
+
+};
+
+/**
+ * struct vxge_hw_vpath_stats_sw_err - HW vpath error statistics
+ * @unknown_alarms:
+ * @network_sustained_fault:
+ * @network_sustained_ok:
+ * @kdfcctl_fifo0_overwrite:
+ * @kdfcctl_fifo0_poison:
+ * @kdfcctl_fifo0_dma_error:
+ * @dblgen_fifo0_overflow:
+ * @statsb_pif_chain_error:
+ * @statsb_drop_timeout:
+ * @target_illegal_access:
+ * @ini_serr_det:
+ * @prc_ring_bumps:
+ * @prc_rxdcm_sc_err:
+ * @prc_rxdcm_sc_abort:
+ * @prc_quanta_size_err:
+ *
+ * HW vpath error statistics
+ */
+struct vxge_hw_vpath_stats_sw_err {
+	u32	unknown_alarms;
+	u32	network_sustained_fault;
+	u32	network_sustained_ok;
+	u32	kdfcctl_fifo0_overwrite;
+	u32	kdfcctl_fifo0_poison;
+	u32	kdfcctl_fifo0_dma_error;
+	u32	dblgen_fifo0_overflow;
+	u32	statsb_pif_chain_error;
+	u32	statsb_drop_timeout;
+	u32	target_illegal_access;
+	u32	ini_serr_det;
+	u32	prc_ring_bumps;
+	u32	prc_rxdcm_sc_err;
+	u32	prc_rxdcm_sc_abort;
+	u32	prc_quanta_size_err;
+};
+
+/**
+ * struct vxge_hw_vpath_stats_sw_info - HW vpath sw statistics
+ * @soft_reset_cnt: Number of times soft reset is done on this vpath.
+ * @error_stats: error counters for the vpath
+ * @ring_stats: counters for ring belonging to the vpath
+ * @fifo_stats: counters for fifo belonging to the vpath
+ *
+ * HW vpath sw statistics
+ * See also: struct vxge_hw_device_info{} }.
+ */
+struct vxge_hw_vpath_stats_sw_info {
+	u32    soft_reset_cnt;
+	struct vxge_hw_vpath_stats_sw_err	error_stats;
+	struct vxge_hw_vpath_stats_sw_ring_info	ring_stats;
+	struct vxge_hw_vpath_stats_sw_fifo_info	fifo_stats;
+};
+
+/**
+ * struct vxge_hw_device_stats_sw_info - HW own per-device statistics.
+ *
+ * @not_traffic_intr_cnt: Number of times the host was interrupted
+ *                        without new completions.
+ *                        "Non-traffic interrupt counter".
+ * @traffic_intr_cnt: Number of traffic interrupts for the device.
+ * @total_intr_cnt: Total number of traffic interrupts for the device.
+ *                  @total_intr_cnt == @traffic_intr_cnt +
+ *                              @not_traffic_intr_cnt
+ * @soft_reset_cnt: Number of times soft reset is done on this device.
+ * @vpath_info: please see struct vxge_hw_vpath_stats_sw_info{}
+ * HW per-device statistics.
+ */
+struct vxge_hw_device_stats_sw_info {
+	u32	not_traffic_intr_cnt;
+	u32	traffic_intr_cnt;
+	u32	total_intr_cnt;
+	u32	soft_reset_cnt;
+	struct vxge_hw_vpath_stats_sw_info
+		vpath_info[VXGE_HW_MAX_VIRTUAL_PATHS];
+};
+
+/**
+ * struct vxge_hw_device_stats_sw_err - HW device error statistics.
+ * @vpath_alarms: Number of vpath alarms
+ *
+ * HW Device error stats
+ */
+struct vxge_hw_device_stats_sw_err {
+	u32     vpath_alarms;
+};
+
+/**
+ * struct vxge_hw_device_stats - Contains HW per-device statistics,
+ * including hw.
+ * @devh: HW device handle.
+ * @dma_addr: DMA addres of the %hw_info. Given to device to fill-in the stats.
+ * @hw_info_dmah: DMA handle used to map hw statistics onto the device memory
+ *                space.
+ * @hw_info_dma_acch: One more DMA handle used subsequently to free the
+ *                    DMA object. Note that this and the previous handle have
+ *                    physical meaning for Solaris; on Windows and Linux the
+ *                    corresponding value will be simply pointer to PCI device.
+ *
+ * @hw_dev_info_stats: Titan statistics maintained by the hardware.
+ * @sw_dev_info_stats: HW's "soft" device informational statistics, e.g. number
+ *                     of completions per interrupt.
+ * @sw_dev_err_stats: HW's "soft" device error statistics.
+ *
+ * Structure-container of HW per-device statistics. Note that per-channel
+ * statistics are kept in separate structures under HW's fifo and ring
+ * channels.
+ */
+struct vxge_hw_device_stats {
+	/* handles */
+	struct __vxge_hw_device *devh;
+
+	/* HW device hardware statistics */
+	struct vxge_hw_device_stats_hw_info	hw_dev_info_stats;
+
+	/* HW device "soft" stats */
+	struct vxge_hw_device_stats_sw_err   sw_dev_err_stats;
+	struct vxge_hw_device_stats_sw_info  sw_dev_info_stats;
+
+};
+
+enum vxge_hw_status vxge_hw_device_hw_stats_enable(
+			struct __vxge_hw_device *devh);
+
+enum vxge_hw_status vxge_hw_device_stats_get(
+			struct __vxge_hw_device *devh,
+			struct vxge_hw_device_stats_hw_info *hw_stats);
+
+enum vxge_hw_status vxge_hw_driver_stats_get(
+			struct __vxge_hw_device *devh,
+			struct vxge_hw_device_stats_sw_info *sw_stats);
+
+enum vxge_hw_status vxge_hw_mrpcim_stats_enable(struct __vxge_hw_device *devh);
+
+enum vxge_hw_status vxge_hw_mrpcim_stats_disable(struct __vxge_hw_device *devh);
+
+enum vxge_hw_status
+vxge_hw_mrpcim_stats_access(
+	struct __vxge_hw_device *devh,
+	u32 operation,
+	u32 location,
+	u32 offset,
+	u64 *stat);
+
+enum vxge_hw_status
+vxge_hw_device_xmac_aggr_stats_get(struct __vxge_hw_device *devh, u32 port,
+				   struct vxge_hw_xmac_aggr_stats *aggr_stats);
+
+enum vxge_hw_status
+vxge_hw_device_xmac_port_stats_get(struct __vxge_hw_device *devh, u32 port,
+				   struct vxge_hw_xmac_port_stats *port_stats);
+
+enum vxge_hw_status
+vxge_hw_device_xmac_stats_get(struct __vxge_hw_device *devh,
+			      struct vxge_hw_xmac_stats *xmac_stats);
+
+/**
+ * enum enum vxge_hw_mgmt_reg_type - Register types.
+ *
+ * @vxge_hw_mgmt_reg_type_legacy: Legacy registers
+ * @vxge_hw_mgmt_reg_type_toc: TOC Registers
+ * @vxge_hw_mgmt_reg_type_common: Common Registers
+ * @vxge_hw_mgmt_reg_type_mrpcim: mrpcim registers
+ * @vxge_hw_mgmt_reg_type_srpcim: srpcim registers
+ * @vxge_hw_mgmt_reg_type_vpmgmt: vpath management registers
+ * @vxge_hw_mgmt_reg_type_vpath: vpath registers
+ *
+ * Register type enumaration
+ */
+enum vxge_hw_mgmt_reg_type {
+	vxge_hw_mgmt_reg_type_legacy = 0,
+	vxge_hw_mgmt_reg_type_toc = 1,
+	vxge_hw_mgmt_reg_type_common = 2,
+	vxge_hw_mgmt_reg_type_mrpcim = 3,
+	vxge_hw_mgmt_reg_type_srpcim = 4,
+	vxge_hw_mgmt_reg_type_vpmgmt = 5,
+	vxge_hw_mgmt_reg_type_vpath = 6
+};
+
+enum vxge_hw_status
+vxge_hw_mgmt_reg_read(struct __vxge_hw_device *devh,
+		      enum vxge_hw_mgmt_reg_type type,
+		      u32 index,
+		      u32 offset,
+		      u64 *value);
+
+enum vxge_hw_status
+vxge_hw_mgmt_reg_write(struct __vxge_hw_device *devh,
+		      enum vxge_hw_mgmt_reg_type type,
+		      u32 index,
+		      u32 offset,
+		      u64 value);
+
+/**
+ * enum enum vxge_hw_rxd_state - Descriptor (RXD) state.
+ * @VXGE_HW_RXD_STATE_NONE: Invalid state.
+ * @VXGE_HW_RXD_STATE_AVAIL: Descriptor is available for reservation.
+ * @VXGE_HW_RXD_STATE_POSTED: Descriptor is posted for processing by the
+ * device.
+ * @VXGE_HW_RXD_STATE_FREED: Descriptor is free and can be reused for
+ * filling-in and posting later.
+ *
+ * Titan/HW descriptor states.
+ *
+ */
+enum vxge_hw_rxd_state {
+	VXGE_HW_RXD_STATE_NONE		= 0,
+	VXGE_HW_RXD_STATE_AVAIL		= 1,
+	VXGE_HW_RXD_STATE_POSTED	= 2,
+	VXGE_HW_RXD_STATE_FREED		= 3
+};
+
+/**
+ * struct vxge_hw_ring_rxd_info - Extended information associated with a
+ * completed ring descriptor.
+ * @syn_flag: SYN flag
+ * @is_icmp: Is ICMP
+ * @fast_path_eligible: Fast Path Eligible flag
+ * @l3_cksum: in L3 checksum is valid
+ * @l3_cksum: Result of IP checksum check (by Titan hardware).
+ *            This field containing VXGE_HW_L3_CKSUM_OK would mean that
+ *            the checksum is correct, otherwise - the datagram is
+ *            corrupted.
+ * @l4_cksum: in L4 checksum is valid
+ * @l4_cksum: Result of TCP/UDP checksum check (by Titan hardware).
+ *            This field containing VXGE_HW_L4_CKSUM_OK would mean that
+ *            the checksum is correct. Otherwise - the packet is
+ *            corrupted.
+ * @frame: Zero or more of enum vxge_hw_frame_type flags.
+ * 		See enum vxge_hw_frame_type{}.
+ * @proto: zero or more of enum vxge_hw_frame_proto flags.  Reporting bits for
+ *            various higher-layer protocols, including (but note restricted to)
+ *            TCP and UDP. See enum vxge_hw_frame_proto{}.
+ * @is_vlan: If vlan tag is valid
+ * @vlan: VLAN tag extracted from the received frame.
+ * @rth_bucket: RTH bucket
+ * @rth_it_hit: Set, If RTH hash value calculated by the Titan hardware
+ *             has a matching entry in the Indirection table.
+ * @rth_spdm_hit: Set, If RTH hash value calculated by the Titan hardware
+ *             has a matching entry in the Socket Pair Direct Match table.
+ * @rth_hash_type: RTH hash code of the function used to calculate the hash.
+ * @rth_value: Receive Traffic Hashing(RTH) hash value. Produced by Titan
+ *             hardware if RTH is enabled.
+ */
+struct vxge_hw_ring_rxd_info {
+	u32	syn_flag;
+	u32	is_icmp;
+	u32	fast_path_eligible;
+	u32	l3_cksum_valid;
+	u32	l3_cksum;
+	u32	l4_cksum_valid;
+	u32	l4_cksum;
+	u32	frame;
+	u32	proto;
+	u32	is_vlan;
+	u32	vlan;
+	u32	rth_bucket;
+	u32	rth_it_hit;
+	u32	rth_spdm_hit;
+	u32	rth_hash_type;
+	u32	rth_value;
+};
+
+/**
+ * enum enum vxge_hw_ring_hash_type - RTH hash types
+ * @VXGE_HW_RING_HASH_TYPE_NONE: No Hash
+ * @VXGE_HW_RING_HASH_TYPE_TCP_IPV4: TCP IPv4
+ * @VXGE_HW_RING_HASH_TYPE_UDP_IPV4: UDP IPv4
+ * @VXGE_HW_RING_HASH_TYPE_IPV4: IPv4
+ * @VXGE_HW_RING_HASH_TYPE_TCP_IPV6: TCP IPv6
+ * @VXGE_HW_RING_HASH_TYPE_UDP_IPV6: UDP IPv6
+ * @VXGE_HW_RING_HASH_TYPE_IPV6: IPv6
+ * @VXGE_HW_RING_HASH_TYPE_TCP_IPV6_EX: TCP IPv6 extension
+ * @VXGE_HW_RING_HASH_TYPE_UDP_IPV6_EX: UDP IPv6 extension
+ * @VXGE_HW_RING_HASH_TYPE_IPV6_EX: IPv6 extension
+ *
+ * RTH hash types
+ */
+enum vxge_hw_ring_hash_type {
+	VXGE_HW_RING_HASH_TYPE_NONE			= 0x0,
+	VXGE_HW_RING_HASH_TYPE_TCP_IPV4		= 0x1,
+	VXGE_HW_RING_HASH_TYPE_UDP_IPV4		= 0x2,
+	VXGE_HW_RING_HASH_TYPE_IPV4			= 0x3,
+	VXGE_HW_RING_HASH_TYPE_TCP_IPV6		= 0x4,
+	VXGE_HW_RING_HASH_TYPE_UDP_IPV6		= 0x5,
+	VXGE_HW_RING_HASH_TYPE_IPV6			= 0x6,
+	VXGE_HW_RING_HASH_TYPE_TCP_IPV6_EX	= 0x7,
+	VXGE_HW_RING_HASH_TYPE_UDP_IPV6_EX	= 0x8,
+	VXGE_HW_RING_HASH_TYPE_IPV6_EX		= 0x9
+};
+
+enum vxge_hw_status vxge_hw_ring_rxd_reserve(
+	struct __vxge_hw_ring *ring_handle,
+	void **rxdh);
+
+void
+vxge_hw_ring_rxd_pre_post(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh);
+
+void
+vxge_hw_ring_rxd_post_post(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh);
+
+enum vxge_hw_status
+vxge_hw_ring_replenish(struct __vxge_hw_ring *ring_handle, u16 min_flag);
+
+void
+vxge_hw_ring_rxd_post_post_wmb(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh);
+
+void vxge_hw_ring_rxd_post(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh);
+
+enum vxge_hw_status vxge_hw_ring_rxd_next_completed(
+	struct __vxge_hw_ring *ring_handle,
+	void **rxdh,
+	u8 *t_code);
+
+enum vxge_hw_status vxge_hw_ring_handle_tcode(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh,
+	u8 t_code);
+
+void vxge_hw_ring_rxd_free(
+	struct __vxge_hw_ring *ring_handle,
+	void *rxdh);
+
+/**
+ * enum enum vxge_hw_frame_proto - Higher-layer ethernet protocols.
+ * @VXGE_HW_FRAME_PROTO_VLAN_TAGGED: VLAN.
+ * @VXGE_HW_FRAME_PROTO_IPV4: IPv4.
+ * @VXGE_HW_FRAME_PROTO_IPV6: IPv6.
+ * @VXGE_HW_FRAME_PROTO_IP_FRAG: IP fragmented.
+ * @VXGE_HW_FRAME_PROTO_TCP: TCP.
+ * @VXGE_HW_FRAME_PROTO_UDP: UDP.
+ * @VXGE_HW_FRAME_PROTO_TCP_OR_UDP: TCP or UDP.
+ *
+ * Higher layer ethernet protocols and options.
+ */
+enum vxge_hw_frame_proto {
+	VXGE_HW_FRAME_PROTO_VLAN_TAGGED = 0x80,
+	VXGE_HW_FRAME_PROTO_IPV4		= 0x10,
+	VXGE_HW_FRAME_PROTO_IPV6		= 0x08,
+	VXGE_HW_FRAME_PROTO_IP_FRAG		= 0x04,
+	VXGE_HW_FRAME_PROTO_TCP			= 0x02,
+	VXGE_HW_FRAME_PROTO_UDP			= 0x01,
+	VXGE_HW_FRAME_PROTO_TCP_OR_UDP	= (VXGE_HW_FRAME_PROTO_TCP | \
+						   VXGE_HW_FRAME_PROTO_UDP)
+};
+
+/**
+ * enum enum vxge_hw_fifo_gather_code - Gather codes used in fifo TxD
+ * @VXGE_HW_FIFO_GATHER_CODE_FIRST: First TxDL
+ * @VXGE_HW_FIFO_GATHER_CODE_MIDDLE: Middle TxDL
+ * @VXGE_HW_FIFO_GATHER_CODE_LAST: Last TxDL
+ * @VXGE_HW_FIFO_GATHER_CODE_FIRST_LAST: First and Last TxDL.
+ *
+ * These gather codes are used to indicate the position of a TxD in a TxD list
+ */
+enum vxge_hw_fifo_gather_code {
+	VXGE_HW_FIFO_GATHER_CODE_FIRST		= 0x2,
+	VXGE_HW_FIFO_GATHER_CODE_MIDDLE		= 0x0,
+	VXGE_HW_FIFO_GATHER_CODE_LAST		= 0x1,
+	VXGE_HW_FIFO_GATHER_CODE_FIRST_LAST	= 0x3
+};
+
+/**
+ * enum enum vxge_hw_fifo_tcode - tcodes used in fifo
+ * @VXGE_HW_FIFO_T_CODE_OK: Transfer OK
+ * @VXGE_HW_FIFO_T_CODE_PCI_READ_CORRUPT: PCI read transaction (either TxD or
+ *             frame data) returned with corrupt data.
+ * @VXGE_HW_FIFO_T_CODE_PCI_READ_FAIL:PCI read transaction was returned
+ *             with no data.
+ * @VXGE_HW_FIFO_T_CODE_INVALID_MSS: The host attempted to send either a
+ *             frame or LSO MSS that was too long (>9800B).
+ * @VXGE_HW_FIFO_T_CODE_LSO_ERROR: Error detected during TCP/UDP Large Send
+	*	       Offload operation, due to improper header template,
+	*	       unsupported protocol, etc.
+ * @VXGE_HW_FIFO_T_CODE_UNUSED: Unused
+ * @VXGE_HW_FIFO_T_CODE_MULTI_ERROR: Set to 1 by the adapter if multiple
+ *             data buffer transfer errors are encountered (see below).
+ *             Otherwise it is set to 0.
+ *
+ * These tcodes are returned in various API for TxD status
+ */
+enum vxge_hw_fifo_tcode {
+	VXGE_HW_FIFO_T_CODE_OK			= 0x0,
+	VXGE_HW_FIFO_T_CODE_PCI_READ_CORRUPT	= 0x1,
+	VXGE_HW_FIFO_T_CODE_PCI_READ_FAIL	= 0x2,
+	VXGE_HW_FIFO_T_CODE_INVALID_MSS		= 0x3,
+	VXGE_HW_FIFO_T_CODE_LSO_ERROR		= 0x4,
+	VXGE_HW_FIFO_T_CODE_UNUSED		= 0x7,
+	VXGE_HW_FIFO_T_CODE_MULTI_ERROR		= 0x8
+};
+
+enum vxge_hw_status vxge_hw_fifo_txdl_reserve(
+	struct __vxge_hw_fifo *fifoh,
+	void **txdlh,
+	void **txdl_priv);
+
+void vxge_hw_fifo_txdl_buffer_set(
+			struct __vxge_hw_fifo *fifo_handle,
+			void *txdlh,
+			u32 frag_idx,
+			dma_addr_t dma_pointer,
+			u32 size);
+
+void vxge_hw_fifo_txdl_post(
+			struct __vxge_hw_fifo *fifo_handle,
+			void *txdlh);
+
+u32 vxge_hw_fifo_free_txdl_count_get(
+			struct __vxge_hw_fifo *fifo_handle);
+
+enum vxge_hw_status vxge_hw_fifo_txdl_next_completed(
+	struct __vxge_hw_fifo *fifoh,
+	void **txdlh,
+	enum vxge_hw_fifo_tcode *t_code);
+
+enum vxge_hw_status vxge_hw_fifo_handle_tcode(
+	struct __vxge_hw_fifo *fifoh,
+	void *txdlh,
+	enum vxge_hw_fifo_tcode t_code);
+
+void vxge_hw_fifo_txdl_free(
+	struct __vxge_hw_fifo *fifoh,
+	void *txdlh);
+
+/*
+ * Device
+ */
+
+#define VXGE_HW_RING_NEXT_BLOCK_POINTER_OFFSET	(VXGE_HW_BLOCK_SIZE-8)
+#define VXGE_HW_RING_MEMBLOCK_IDX_OFFSET		(VXGE_HW_BLOCK_SIZE-16)
+#define VXGE_HW_RING_MIN_BUFF_ALLOCATION		64
+
+/*
+ * struct __vxge_hw_ring_rxd_priv - Receive descriptor HW-private data.
+ * @dma_addr: DMA (mapped) address of _this_ descriptor.
+ * @dma_handle: DMA handle used to map the descriptor onto device.
+ * @dma_offset: Descriptor's offset in the memory block. HW allocates
+ *              descriptors in memory blocks of %VXGE_HW_BLOCK_SIZE
+ *              bytes. Each memblock is contiguous DMA-able memory. Each
+ *              memblock contains 1 or more 4KB RxD blocks visible to the
+ *              Titan hardware.
+ * @dma_object: DMA address and handle of the memory block that contains
+ *              the descriptor. This member is used only in the "checked"
+ *              version of the HW (to enforce certain assertions);
+ *              otherwise it gets compiled out.
+ * @allocated: True if the descriptor is reserved, 0 otherwise. Internal usage.
+ *
+ * Per-receive decsriptor HW-private data. HW uses the space to keep DMA
+ * information associated with the descriptor. Note that driver can ask HW
+ * to allocate additional per-descriptor space for its own (driver-specific)
+ * purposes.
+ */
+struct __vxge_hw_ring_rxd_priv {
+	dma_addr_t	dma_addr;
+	struct pci_dev *dma_handle;
+	ptrdiff_t	dma_offset;
+#ifdef VXGE_DEBUG_ASSERT
+	struct vxge_hw_mempool_dma	*dma_object;
+#endif
+};
+
+/* ========================= RING PRIVATE API ============================= */
+u64
+__vxge_hw_ring_first_block_address_get(
+	struct __vxge_hw_ring *ringh);
+
+enum vxge_hw_status
+__vxge_hw_ring_create(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	struct vxge_hw_ring_attr *attr);
+
+enum vxge_hw_status
+__vxge_hw_ring_abort(
+	struct __vxge_hw_ring *ringh);
+
+enum vxge_hw_status
+__vxge_hw_ring_reset(
+	struct __vxge_hw_ring *ringh);
+
+enum vxge_hw_status
+__vxge_hw_ring_delete(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+/* ========================= FIFO PRIVATE API ============================= */
+
+struct vxge_hw_fifo_attr;
+
+enum vxge_hw_status
+__vxge_hw_fifo_create(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	struct vxge_hw_fifo_attr *attr);
+
+enum vxge_hw_status
+__vxge_hw_fifo_abort(
+	struct __vxge_hw_fifo *fifoh);
+
+enum vxge_hw_status
+__vxge_hw_fifo_reset(
+	struct __vxge_hw_fifo *ringh);
+
+enum vxge_hw_status
+__vxge_hw_fifo_delete(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+struct vxge_hw_mempool_cbs {
+	void (*item_func_alloc)(
+			struct vxge_hw_mempool *mempoolh,
+			u32			memblock_index,
+			struct vxge_hw_mempool_dma	*dma_object,
+			u32			index,
+			u32			is_last);
+};
+
+void
+__vxge_hw_mempool_destroy(
+	struct vxge_hw_mempool *mempool);
+
+#define VXGE_HW_VIRTUAL_PATH_HANDLE(vpath)				\
+		((struct __vxge_hw_vpath_handle *)(vpath)->vpath_handles.next)
+
+enum vxge_hw_status
+__vxge_hw_vpath_rts_table_get(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u32			action,
+	u32			rts_table,
+	u32			offset,
+	u64			*data1,
+	u64			*data2);
+
+enum vxge_hw_status
+__vxge_hw_vpath_rts_table_set(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u32			action,
+	u32			rts_table,
+	u32			offset,
+	u64			data1,
+	u64			data2);
+
+enum vxge_hw_status
+__vxge_hw_vpath_reset(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vpath_sw_reset(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vpath_enable(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+void
+__vxge_hw_vpath_prc_configure(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vpath_kdfc_configure(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vpath_mac_configure(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vpath_tim_configure(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vpath_initialize(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vp_initialize(
+	struct __vxge_hw_device *devh,
+	u32			vp_id,
+	struct vxge_hw_vp_config	*config);
+
+void
+__vxge_hw_vp_terminate(
+	struct __vxge_hw_device *devh,
+	u32			vp_id);
+
+enum vxge_hw_status
+__vxge_hw_vpath_alarm_process(
+	struct __vxge_hw_virtualpath	*vpath,
+	u32			skip_alarms);
+
+void vxge_hw_device_intr_enable(
+	struct __vxge_hw_device *devh);
+
+u32 vxge_hw_device_set_intr_type(struct __vxge_hw_device *devh, u32 intr_mode);
+
+void vxge_hw_device_intr_disable(
+	struct __vxge_hw_device *devh);
+
+void vxge_hw_device_mask_all(
+	struct __vxge_hw_device *devh);
+
+void vxge_hw_device_unmask_all(
+	struct __vxge_hw_device *devh);
+
+enum vxge_hw_status vxge_hw_device_begin_irq(
+	struct __vxge_hw_device *devh,
+	u32 skip_alarms,
+	u64 *reason);
+
+void vxge_hw_device_clear_tx_rx(
+	struct __vxge_hw_device *devh);
+
+/*
+ *  Virtual Paths
+ */
+
+u32 vxge_hw_vpath_id(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_vpath_mac_addr_add_mode {
+	VXGE_HW_VPATH_MAC_ADDR_ADD_DUPLICATE = 0,
+	VXGE_HW_VPATH_MAC_ADDR_DISCARD_DUPLICATE = 1,
+	VXGE_HW_VPATH_MAC_ADDR_REPLACE_DUPLICATE = 2
+};
+
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_add(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN],
+	enum vxge_hw_vpath_mac_addr_add_mode duplicate_mode);
+
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_get(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN]);
+
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_get_next(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN]);
+
+enum vxge_hw_status
+vxge_hw_vpath_mac_addr_delete(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u8 (macaddr)[ETH_ALEN],
+	u8 (macaddr_mask)[ETH_ALEN]);
+
+enum vxge_hw_status
+vxge_hw_vpath_vid_add(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			vid);
+
+enum vxge_hw_status
+vxge_hw_vpath_vid_get(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			*vid);
+
+enum vxge_hw_status
+vxge_hw_vpath_vid_get_next(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			*vid);
+
+enum vxge_hw_status
+vxge_hw_vpath_vid_delete(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			vid);
+
+enum vxge_hw_status
+vxge_hw_vpath_etype_add(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			etype);
+
+enum vxge_hw_status
+vxge_hw_vpath_etype_get(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			*etype);
+
+enum vxge_hw_status
+vxge_hw_vpath_etype_get_next(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			*etype);
+
+enum vxge_hw_status
+vxge_hw_vpath_etype_delete(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u64			etype);
+
+enum vxge_hw_status vxge_hw_vpath_promisc_enable(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status vxge_hw_vpath_promisc_disable(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status vxge_hw_vpath_bcast_enable(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status vxge_hw_vpath_mcast_enable(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status vxge_hw_vpath_mcast_disable(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status vxge_hw_vpath_poll_rx(
+	struct __vxge_hw_ring *ringh);
+
+enum vxge_hw_status vxge_hw_vpath_poll_tx(
+	struct __vxge_hw_fifo *fifoh,
+	void **skb_ptr);
+
+enum vxge_hw_status vxge_hw_vpath_alarm_process(
+	struct __vxge_hw_vpath_handle *vpath_handle,
+	u32 skip_alarms);
+
+enum vxge_hw_status
+vxge_hw_vpath_msix_set(struct __vxge_hw_vpath_handle *vpath_handle,
+		       int *tim_msix_id, int alarm_msix_id);
+
+void
+vxge_hw_vpath_msix_mask(struct __vxge_hw_vpath_handle *vpath_handle,
+			int msix_id);
+
+void vxge_hw_device_flush_io(struct __vxge_hw_device *devh);
+
+void
+vxge_hw_vpath_msix_clear(struct __vxge_hw_vpath_handle *vpath_handle,
+			 int msix_id);
+
+void
+vxge_hw_vpath_msix_unmask(struct __vxge_hw_vpath_handle *vpath_handle,
+			  int msix_id);
+
+void
+vxge_hw_vpath_msix_mask_all(struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status vxge_hw_vpath_intr_enable(
+				struct __vxge_hw_vpath_handle *vpath_handle);
+
+enum vxge_hw_status vxge_hw_vpath_intr_disable(
+				struct __vxge_hw_vpath_handle *vpath_handle);
+
+void vxge_hw_vpath_inta_mask_tx_rx(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+void vxge_hw_vpath_inta_unmask_tx_rx(
+	struct __vxge_hw_vpath_handle *vpath_handle);
+
+void
+vxge_hw_channel_msix_mask(struct __vxge_hw_channel *channelh, int msix_id);
+
+void
+vxge_hw_channel_msix_unmask(struct __vxge_hw_channel *channelh, int msix_id);
+
+enum vxge_hw_status
+vxge_hw_channel_dtr_alloc(struct __vxge_hw_channel *channel, void **dtrh);
+
+void
+vxge_hw_channel_dtr_post(struct __vxge_hw_channel *channel, void *dtrh);
+
+void
+vxge_hw_channel_dtr_try_complete(struct __vxge_hw_channel *channel,
+				 void **dtrh);
+
+void
+vxge_hw_channel_dtr_complete(struct __vxge_hw_channel *channel);
+
+void
+vxge_hw_channel_dtr_free(struct __vxge_hw_channel *channel, void *dtrh);
+
+int
+vxge_hw_channel_dtr_count(struct __vxge_hw_channel *channel);
+
+/* ========================== PRIVATE API ================================= */
+
+enum vxge_hw_status
+__vxge_hw_device_handle_link_up_ind(struct __vxge_hw_device *hldev);
+
+enum vxge_hw_status
+__vxge_hw_device_handle_link_down_ind(struct __vxge_hw_device *hldev);
+
+enum vxge_hw_status
+__vxge_hw_device_handle_error(
+		struct __vxge_hw_device *hldev,
+		u32 vp_id,
+		enum vxge_hw_event type);
+
+#endif
diff --git a/drivers/net/vxge/vxge-version.h b/drivers/net/vxge/vxge-version.h
new file mode 100644
index 000000000000..7da02c545ed5
--- /dev/null
+++ b/drivers/net/vxge/vxge-version.h
@@ -0,0 +1,23 @@
+/******************************************************************************
+ * This software may be used and distributed according to the terms of
+ * the GNU General Public License (GPL), incorporated herein by reference.
+ * Drivers based on or derived from this code fall under the GPL and must
+ * retain the authorship, copyright and license notice.  This file is not
+ * a complete program and may only be used when the entire operating
+ * system is licensed under the GPL.
+ * See the file COPYING in this distribution for more information.
+ *
+ * vxge-version.h: Driver for Neterion Inc's X3100 Series 10GbE PCIe I/O
+ *                 Virtualized Server Adapter.
+ * Copyright(c) 2002-2009 Neterion Inc.
+ ******************************************************************************/
+#ifndef VXGE_VERSION_H
+
+#define VXGE_VERSION_H
+
+#define VXGE_VERSION_MAJOR	"2"
+#define VXGE_VERSION_MINOR	"0"
+#define VXGE_VERSION_FIX	"1"
+#define VXGE_VERSION_BUILD	"17129"
+#define VXGE_VERSION_FOR	"k"
+#endif
diff --git a/drivers/net/wan/farsync.c b/drivers/net/wan/farsync.c
index 00945f7c1e9b..25c9ef6a1815 100644
--- a/drivers/net/wan/farsync.c
+++ b/drivers/net/wan/farsync.c
@@ -69,7 +69,7 @@ MODULE_LICENSE("GPL");
 #endif
 
 /*
- * Modules parameters and associated varaibles
+ * Modules parameters and associated variables
  */
 static int fst_txq_low = FST_LOW_WATER_MARK;
 static int fst_txq_high = FST_HIGH_WATER_MARK;
diff --git a/drivers/net/wireless/ipw2x00/ipw2100.c b/drivers/net/wireless/ipw2x00/ipw2100.c
index 115b70487502..f4e963ba768b 100644
--- a/drivers/net/wireless/ipw2x00/ipw2100.c
+++ b/drivers/net/wireless/ipw2x00/ipw2100.c
@@ -2362,7 +2362,7 @@ static void ipw2100_corruption_detected(struct ipw2100_priv *priv, int i)
 		       i * sizeof(struct ipw2100_status));
 
 #ifdef IPW2100_DEBUG_C3
-	/* Halt the fimrware so we can get a good image */
+	/* Halt the firmware so we can get a good image */
 	write_register(priv->net_dev, IPW_REG_RESET_REG,
 		       IPW_AUX_HOST_RESET_REG_STOP_MASTER);
 	j = 5;
diff --git a/drivers/net/wireless/ipw2x00/ipw2200.c b/drivers/net/wireless/ipw2x00/ipw2200.c
index 4a92af1d7877..e17a4593e1f5 100644
--- a/drivers/net/wireless/ipw2x00/ipw2200.c
+++ b/drivers/net/wireless/ipw2x00/ipw2200.c
@@ -8844,7 +8844,7 @@ static int ipw_wx_set_mode(struct net_device *dev,
 #endif				/* CONFIG_IPW2200_MONITOR */
 
 	/* Free the existing firmware and reset the fw_loaded
-	 * flag so ipw_load() will bring in the new firmawre */
+	 * flag so ipw_load() will bring in the new firmware */
 	free_firmware();
 
 	priv->ieee->iw_mode = wrqu->mode;
diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index 663dc83be501..3889158b359c 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -1337,7 +1337,7 @@ static int iwl_read_ucode(struct iwl_priv *priv)
 
 	/* api_ver should match the api version forming part of the
 	 * firmware filename ... but we don't check for that and only rely
-	 * on the API version read from firware header from here on forward */
+	 * on the API version read from firmware header from here on forward */
 
 	if (api_ver < api_min || api_ver > api_max) {
 		IWL_ERR(priv, "Driver unable to support your firmware API. "
diff --git a/drivers/net/wireless/iwlwifi/iwl3945-base.c b/drivers/net/wireless/iwlwifi/iwl3945-base.c
index a71b08ca7c71..9d5f97dd7c73 100644
--- a/drivers/net/wireless/iwlwifi/iwl3945-base.c
+++ b/drivers/net/wireless/iwlwifi/iwl3945-base.c
@@ -2562,7 +2562,7 @@ static int iwl3945_read_ucode(struct iwl_priv *priv)
 
 	/* api_ver should match the api version forming part of the
 	 * firmware filename ... but we don't check for that and only rely
-	 * on the API version read from firware header from here on forward */
+	 * on the API version read from firmware header from here on forward */
 
 	if (api_ver < api_min || api_ver > api_max) {
 		IWL_ERR(priv, "Driver unable to support your firmware API. "
diff --git a/drivers/net/wireless/libertas/cmd.c b/drivers/net/wireless/libertas/cmd.c
index 639dd02d3d31..8c3605cdc64c 100644
--- a/drivers/net/wireless/libertas/cmd.c
+++ b/drivers/net/wireless/libertas/cmd.c
@@ -1649,7 +1649,7 @@ static struct cmd_ctrl_node *lbs_get_cmd_ctrl_node(struct lbs_private *priv)
 
 /**
  *  @brief This function executes next command in command
- *  pending queue. It will put fimware back to PS mode
+ *  pending queue. It will put firmware back to PS mode
  *  if applicable.
  *
  *  @param priv     A pointer to struct lbs_private structure
diff --git a/drivers/oprofile/buffer_sync.c b/drivers/oprofile/buffer_sync.c
index 2c9aa49e43cd..8574622e36a5 100644
--- a/drivers/oprofile/buffer_sync.c
+++ b/drivers/oprofile/buffer_sync.c
@@ -154,6 +154,10 @@ int sync_start(void)
 {
 	int err;
 
+	if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL))
+		return -ENOMEM;
+	cpumask_clear(marked_cpus);
+
 	start_cpu_work();
 
 	err = task_handoff_register(&task_free_nb);
@@ -179,6 +183,7 @@ out2:
 	task_handoff_unregister(&task_free_nb);
 out1:
 	end_sync();
+	free_cpumask_var(marked_cpus);
 	goto out;
 }
 
@@ -190,6 +195,7 @@ void sync_stop(void)
 	profile_event_unregister(PROFILE_TASK_EXIT, &task_exit_nb);
 	task_handoff_unregister(&task_free_nb);
 	end_sync();
+	free_cpumask_var(marked_cpus);
 }
 
 
@@ -565,20 +571,6 @@ void sync_buffer(int cpu)
 	mutex_unlock(&buffer_mutex);
 }
 
-int __init buffer_sync_init(void)
-{
-	if (!alloc_cpumask_var(&marked_cpus, GFP_KERNEL))
-		return -ENOMEM;
-
-	cpumask_clear(marked_cpus);
-		return 0;
-}
-
-void buffer_sync_cleanup(void)
-{
-	free_cpumask_var(marked_cpus);
-}
-
 /* The function can be used to add a buffer worth of data directly to
  * the kernel buffer. The buffer is assumed to be a circular buffer.
  * Take the entries from index start and end at index end, wrapping
diff --git a/drivers/oprofile/buffer_sync.h b/drivers/oprofile/buffer_sync.h
index 0ebf5db62679..3110732c1835 100644
--- a/drivers/oprofile/buffer_sync.h
+++ b/drivers/oprofile/buffer_sync.h
@@ -19,8 +19,4 @@ void sync_stop(void);
 /* sync the given CPU's buffer */
 void sync_buffer(int cpu);
 
-/* initialize/destroy the buffer system. */
-int buffer_sync_init(void);
-void buffer_sync_cleanup(void);
-
 #endif /* OPROFILE_BUFFER_SYNC_H */
diff --git a/drivers/oprofile/oprof.c b/drivers/oprofile/oprof.c
index ced39f602292..3cffce90f82a 100644
--- a/drivers/oprofile/oprof.c
+++ b/drivers/oprofile/oprof.c
@@ -183,10 +183,6 @@ static int __init oprofile_init(void)
 {
 	int err;
 
-	err = buffer_sync_init();
-	if (err)
-		return err;
-
 	err = oprofile_arch_init(&oprofile_ops);
 
 	if (err < 0 || timer) {
@@ -195,10 +191,8 @@ static int __init oprofile_init(void)
 	}
 
 	err = oprofilefs_register();
-	if (err) {
+	if (err)
 		oprofile_arch_exit();
-		buffer_sync_cleanup();
-	}
 
 	return err;
 }
@@ -208,7 +202,6 @@ static void __exit oprofile_exit(void)
 {
 	oprofilefs_unregister();
 	oprofile_arch_exit();
-	buffer_sync_cleanup();
 }
 
 
diff --git a/drivers/parisc/asp.c b/drivers/parisc/asp.c
index 7931133526c4..9ca21098b146 100644
--- a/drivers/parisc/asp.c
+++ b/drivers/parisc/asp.c
@@ -81,7 +81,7 @@ static int __init asp_init_chip(struct parisc_device *dev)
 	asp.hpa = ASP_INTERRUPT_ADDR;
 
 	printk(KERN_INFO "%s version %d at 0x%lx found.\n", 
-		asp.name, asp.version, dev->hpa.start);
+		asp.name, asp.version, (unsigned long)dev->hpa.start);
 
 	/* the IRQ ASP should use */
 	ret = -EBUSY;
diff --git a/drivers/parisc/ccio-dma.c b/drivers/parisc/ccio-dma.c
index cd4dd7ed2c06..5d610cbcfe80 100644
--- a/drivers/parisc/ccio-dma.c
+++ b/drivers/parisc/ccio-dma.c
@@ -406,8 +406,6 @@ resource_found:
 	}
 	ioc->avg_search[ioc->avg_idx++] = cr_start;
 	ioc->avg_idx &= CCIO_SEARCH_SAMPLE - 1;
-#endif
-#ifdef CCIO_COLLECT_STATS
 	ioc->used_pages += pages_needed;
 #endif
 	/* 
@@ -453,10 +451,10 @@ ccio_free_range(struct ioc *ioc, dma_addr_t iova, unsigned long pages_mapped)
 		unsigned long mask = ~(~0UL >> pages_mapped);
 		CCIO_FREE_MAPPINGS(ioc, res_idx, mask, 8);
 #else
-		CCIO_FREE_MAPPINGS(ioc, res_idx, 0xff, 8);
+		CCIO_FREE_MAPPINGS(ioc, res_idx, 0xffUL, 8);
 #endif
 	} else if(pages_mapped <= 16) {
-		CCIO_FREE_MAPPINGS(ioc, res_idx, 0xffff, 16);
+		CCIO_FREE_MAPPINGS(ioc, res_idx, 0xffffUL, 16);
 	} else if(pages_mapped <= 32) {
 		CCIO_FREE_MAPPINGS(ioc, res_idx, ~(unsigned int)0, 32);
 #ifdef __LP64__
@@ -1028,8 +1026,10 @@ static int ccio_proc_info(struct seq_file *m, void *p)
 
 	while (ioc != NULL) {
 		unsigned int total_pages = ioc->res_size << 3;
+#ifdef CCIO_COLLECT_STATS
 		unsigned long avg = 0, min, max;
 		int j;
+#endif
 
 		len += seq_printf(m, "%s\n", ioc->name);
 		
@@ -1060,8 +1060,7 @@ static int ccio_proc_info(struct seq_file *m, void *p)
 		avg /= CCIO_SEARCH_SAMPLE;
 		len += seq_printf(m, "  Bitmap search : %ld/%ld/%ld (min/avg/max CPU Cycles)\n",
 				  min, avg, max);
-#endif
-#ifdef CCIO_COLLECT_STATS
+
 		len += seq_printf(m, "pci_map_single(): %8ld calls  %8ld pages (avg %d/1000)\n",
 				  ioc->msingle_calls, ioc->msingle_pages,
 				  (int)((ioc->msingle_pages * 1000)/ioc->msingle_calls));
@@ -1400,7 +1399,7 @@ ccio_init_resource(struct resource *res, char *name, void __iomem *ioaddr)
 	result = insert_resource(&iomem_resource, res);
 	if (result < 0) {
 		printk(KERN_ERR "%s() failed to claim CCIO bus address space (%08lx,%08lx)\n", 
-			__func__, res->start, res->end);
+			__func__, (unsigned long)res->start, (unsigned long)res->end);
 	}
 }
 
@@ -1551,7 +1550,8 @@ static int __init ccio_probe(struct parisc_device *dev)
 
 	ioc->name = dev->id.hversion == U2_IOA_RUNWAY ? "U2" : "UTurn";
 
-	printk(KERN_INFO "Found %s at 0x%lx\n", ioc->name, dev->hpa.start);
+	printk(KERN_INFO "Found %s at 0x%lx\n", ioc->name,
+		(unsigned long)dev->hpa.start);
 
 	for (i = 0; i < ioc_count; i++) {
 		ioc_p = &(*ioc_p)->next;
diff --git a/drivers/parisc/dino.c b/drivers/parisc/dino.c
index bb5a1c9597cb..52ae0b1d470c 100644
--- a/drivers/parisc/dino.c
+++ b/drivers/parisc/dino.c
@@ -819,7 +819,9 @@ dino_bridge_init(struct dino_device *dino_dev, const char *name)
 
 		result = ccio_request_resource(dino_dev->hba.dev, &res[i]);
 		if (result < 0) {
-			printk(KERN_ERR "%s: failed to claim PCI Bus address space %d (0x%lx-0x%lx)!\n", name, i, res[i].start, res[i].end);
+			printk(KERN_ERR "%s: failed to claim PCI Bus address "
+			       "space %d (0x%lx-0x%lx)!\n", name, i,
+			       (unsigned long)res[i].start, (unsigned long)res[i].end);
 			return result;
 		}
 	}
@@ -899,7 +901,8 @@ static int __init dino_common_init(struct parisc_device *dev,
 	if (request_resource(&ioport_resource, res) < 0) {
 		printk(KERN_ERR "%s: request I/O Port region failed "
 		       "0x%lx/%lx (hpa 0x%p)\n",
-		       name, res->start, res->end, dino_dev->hba.base_addr);
+		       name, (unsigned long)res->start, (unsigned long)res->end,
+		       dino_dev->hba.base_addr);
 		return 1;
 	}
 
diff --git a/drivers/parisc/eisa.c b/drivers/parisc/eisa.c
index 7891db50c483..f415fdd9a885 100644
--- a/drivers/parisc/eisa.c
+++ b/drivers/parisc/eisa.c
@@ -314,7 +314,7 @@ static int __init eisa_probe(struct parisc_device *dev)
 	char *name = is_mongoose(dev) ? "Mongoose" : "Wax";
 
 	printk(KERN_INFO "%s EISA Adapter found at 0x%08lx\n", 
-		name, dev->hpa.start);
+		name, (unsigned long)dev->hpa.start);
 
 	eisa_dev.hba.dev = dev;
 	eisa_dev.hba.iommu = ccio_get_iommu(dev);
diff --git a/drivers/parisc/eisa_enumerator.c b/drivers/parisc/eisa_enumerator.c
index 6d8aae003f6c..c709ecc2b7f7 100644
--- a/drivers/parisc/eisa_enumerator.c
+++ b/drivers/parisc/eisa_enumerator.c
@@ -98,7 +98,7 @@ static int configure_memory(const unsigned char *buf,
 			res->start = mem_parent->start + get_24(buf+len+2);
 			res->end = res->start + get_16(buf+len+5)*1024;
 			res->flags = IORESOURCE_MEM;
-			printk("memory %lx-%lx ", res->start, res->end);
+			printk("memory %lx-%lx ", (unsigned long)res->start, (unsigned long)res->end);
 			result = request_resource(mem_parent, res);
 			if (result < 0) {
 				printk("\n" KERN_ERR "EISA Enumerator: failed to claim EISA Bus address space!\n");
@@ -188,7 +188,7 @@ static int configure_port(const unsigned char *buf, struct resource *io_parent,
 			res->start = get_16(buf+len+1);
 			res->end = get_16(buf+len+1)+(c&HPEE_PORT_SIZE_MASK)+1;
 			res->flags = IORESOURCE_IO;
-			printk("ioports %lx-%lx ", res->start, res->end);
+			printk("ioports %lx-%lx ", (unsigned long)res->start, (unsigned long)res->end);
 			result = request_resource(io_parent, res);
 			if (result < 0) {
 				printk("\n" KERN_ERR "EISA Enumerator: failed to claim EISA Bus address space!\n");
diff --git a/drivers/parisc/iosapic.c b/drivers/parisc/iosapic.c
index 501aaf1f253f..73348c4047e9 100644
--- a/drivers/parisc/iosapic.c
+++ b/drivers/parisc/iosapic.c
@@ -714,7 +714,7 @@ static void iosapic_set_affinity_irq(unsigned int irq,
 	if (dest_cpu < 0)
 		return;
 
-	irq_desc[irq].affinity = cpumask_of_cpu(dest_cpu);
+	cpumask_copy(irq_desc[irq].affinity, cpumask_of(dest_cpu));
 	vi->txn_addr = txn_affinity_addr(irq, dest_cpu);
 
 	spin_lock_irqsave(&iosapic_lock, flags);
diff --git a/drivers/parisc/led.c b/drivers/parisc/led.c
index 454b6532e409..9581d3619450 100644
--- a/drivers/parisc/led.c
+++ b/drivers/parisc/led.c
@@ -3,7 +3,7 @@
  *
  *      (c) Copyright 2000 Red Hat Software
  *      (c) Copyright 2000 Helge Deller <hdeller@redhat.com>
- *      (c) Copyright 2001-2005 Helge Deller <deller@gmx.de>
+ *      (c) Copyright 2001-2009 Helge Deller <deller@gmx.de>
  *      (c) Copyright 2001 Randolph Chung <tausq@debian.org>
  *
  *      This program is free software; you can redistribute it and/or modify
@@ -243,13 +243,11 @@ static int __init led_create_procfs(void)
 
 	proc_pdc_root = proc_mkdir("pdc", 0);
 	if (!proc_pdc_root) return -1;
-	proc_pdc_root->owner = THIS_MODULE;
 	ent = create_proc_entry("led", S_IFREG|S_IRUGO|S_IWUSR, proc_pdc_root);
 	if (!ent) return -1;
 	ent->data = (void *)LED_NOLCD; /* LED */
 	ent->read_proc = led_proc_read;
 	ent->write_proc = led_proc_write;
-	ent->owner = THIS_MODULE;
 
 	if (led_type == LED_HASLCD)
 	{
@@ -258,7 +256,6 @@ static int __init led_create_procfs(void)
 		ent->data = (void *)LED_HASLCD; /* LCD */
 		ent->read_proc = led_proc_read;
 		ent->write_proc = led_proc_write;
-		ent->owner = THIS_MODULE;
 	}
 
 	return 0;
@@ -463,9 +460,20 @@ static void led_work_func (struct work_struct *unused)
 	if (likely(led_lanrxtx))  currentleds |= led_get_net_activity();
 	if (likely(led_diskio))   currentleds |= led_get_diskio_activity();
 
-	/* blink all LEDs twice a second if we got an Oops (HPMC) */
-	if (unlikely(oops_in_progress)) 
-		currentleds = (count_HZ<=(HZ/2)) ? 0 : 0xff;
+	/* blink LEDs if we got an Oops (HPMC) */
+	if (unlikely(oops_in_progress)) {
+		if (boot_cpu_data.cpu_type >= pcxl2) {
+			/* newer machines don't have loadavg. LEDs, so we
+			 * let all LEDs blink twice per second instead */
+			currentleds = (count_HZ <= (HZ/2)) ? 0 : 0xff;
+		} else {
+			/* old machines: blink loadavg. LEDs twice per second */
+			if (count_HZ <= (HZ/2))
+				currentleds &= ~(LED4|LED5|LED6|LED7);
+			else
+				currentleds |= (LED4|LED5|LED6|LED7);
+		}
+	}
 
 	if (currentleds != lastleds)
 	{
@@ -511,7 +519,7 @@ static int led_halt(struct notifier_block *nb, unsigned long event, void *buf)
 	
 	/* Cancel the work item and delete the queue */
 	if (led_wq) {
-		cancel_rearming_delayed_workqueue(led_wq, &led_task);
+		cancel_delayed_work_sync(&led_task);
 		destroy_workqueue(led_wq);
 		led_wq = NULL;
 	}
@@ -630,7 +638,7 @@ int lcd_print( const char *str )
 	
 	/* temporarily disable the led work task */
 	if (led_wq)
-		cancel_rearming_delayed_workqueue(led_wq, &led_task);
+		cancel_delayed_work_sync(&led_task);
 
 	/* copy display string to buffer for procfs */
 	strlcpy(lcd_text, str, sizeof(lcd_text));
diff --git a/drivers/parport/parport_serial.c b/drivers/parport/parport_serial.c
index 032db815b0f9..f3492110b1ad 100644
--- a/drivers/parport/parport_serial.c
+++ b/drivers/parport/parport_serial.c
@@ -30,6 +30,7 @@ enum parport_pc_pci_cards {
 	titan_210l,
 	netmos_9xx5_combo,
 	netmos_9855,
+	netmos_9855_2p,
 	avlab_1s1p,
 	avlab_1s2p,
 	avlab_2s1p,
@@ -62,7 +63,7 @@ struct parport_pc_pci {
 				struct parport_pc_pci *card, int failed);
 };
 
-static int __devinit netmos_parallel_init(struct pci_dev *dev, struct parport_pc_pci *card, int autoirq, int autodma)
+static int __devinit netmos_parallel_init(struct pci_dev *dev, struct parport_pc_pci *par, int autoirq, int autodma)
 {
 	/* the rule described below doesn't hold for this device */
 	if (dev->device == PCI_DEVICE_ID_NETMOS_9835 &&
@@ -74,9 +75,17 @@ static int __devinit netmos_parallel_init(struct pci_dev *dev, struct parport_pc
 	 * and serial ports.  The form is 0x00PS, where <P> is the number of
 	 * parallel ports and <S> is the number of serial ports.
 	 */
-	card->numports = (dev->subsystem_device & 0xf0) >> 4;
-	if (card->numports > ARRAY_SIZE(card->addr))
-		card->numports = ARRAY_SIZE(card->addr);
+	par->numports = (dev->subsystem_device & 0xf0) >> 4;
+	if (par->numports > ARRAY_SIZE(par->addr))
+		par->numports = ARRAY_SIZE(par->addr);
+	/*
+	 * This function is currently only called for cards with up to
+	 * one parallel port.
+	 * Parallel port BAR is either before or after serial ports BARS;
+	 * hence, lo should be either 0 or equal to the number of serial ports.
+	 */
+	if (par->addr[0].lo != 0)
+		par->addr[0].lo = dev->subsystem_device & 0xf;
 	return 0;
 }
 
@@ -84,7 +93,8 @@ static struct parport_pc_pci cards[] __devinitdata = {
 	/* titan_110l */		{ 1, { { 3, -1 }, } },
 	/* titan_210l */		{ 1, { { 3, -1 }, } },
 	/* netmos_9xx5_combo */		{ 1, { { 2, -1 }, }, netmos_parallel_init },
-	/* netmos_9855 */		{ 1, { { 2, -1 }, }, netmos_parallel_init },
+	/* netmos_9855 */		{ 1, { { 0, -1 }, }, netmos_parallel_init },
+	/* netmos_9855_2p */		{ 2, { { 0, -1 }, { 2, -1 }, } },
 	/* avlab_1s1p     */		{ 1, { { 1, 2}, } },
 	/* avlab_1s2p     */		{ 2, { { 1, 2}, { 3, 4 },} },
 	/* avlab_2s1p     */		{ 1, { { 2, 3}, } },
@@ -110,6 +120,10 @@ static struct pci_device_id parport_serial_pci_tbl[] = {
 	{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9845,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9xx5_combo },
 	{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855,
+	  0x1000, 0x0020, 0, 0, netmos_9855_2p },
+	{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855,
+	  0x1000, 0x0022, 0, 0, netmos_9855_2p },
+	{ PCI_VENDOR_ID_NETMOS, PCI_DEVICE_ID_NETMOS_9855,
 	  PCI_ANY_ID, PCI_ANY_ID, 0, 0, netmos_9855 },
 	/* PCI_VENDOR_ID_AVLAB/Intek21 has another bunch of cards ...*/
 	{ PCI_VENDOR_ID_AFAVLAB, 0x2110,
@@ -192,6 +206,12 @@ static struct pciserial_board pci_parport_serial_boards[] __devinitdata = {
 		.uart_offset	= 8,
 	},
 	[netmos_9855] = {
+		.flags		= FL_BASE2 | FL_BASE_BARS,
+		.num_ports	= 1,
+		.base_baud	= 115200,
+		.uart_offset	= 8,
+	},
+	[netmos_9855_2p] = {
 		.flags		= FL_BASE4 | FL_BASE_BARS,
 		.num_ports	= 1,
 		.base_baud	= 115200,
diff --git a/drivers/pci/intel-iommu.c b/drivers/pci/intel-iommu.c
index 9dbd5066acaf..23e56a564e05 100644
--- a/drivers/pci/intel-iommu.c
+++ b/drivers/pci/intel-iommu.c
@@ -164,7 +164,8 @@ static inline void context_clear_entry(struct context_entry *context)
  * 1: writable
  * 2-6: reserved
  * 7: super page
- * 8-11: available
+ * 8-10: available
+ * 11: snoop behavior
  * 12-63: Host physcial address
  */
 struct dma_pte {
@@ -186,6 +187,11 @@ static inline void dma_set_pte_writable(struct dma_pte *pte)
 	pte->val |= DMA_PTE_WRITE;
 }
 
+static inline void dma_set_pte_snp(struct dma_pte *pte)
+{
+	pte->val |= DMA_PTE_SNP;
+}
+
 static inline void dma_set_pte_prot(struct dma_pte *pte, unsigned long prot)
 {
 	pte->val = (pte->val & ~3) | (prot & 3);
@@ -231,6 +237,7 @@ struct dmar_domain {
 	int		flags;		/* flags to find out type of domain */
 
 	int		iommu_coherency;/* indicate coherency of iommu access */
+	int		iommu_snooping; /* indicate snooping control feature*/
 	int		iommu_count;	/* reference count of iommu */
 	spinlock_t	iommu_lock;	/* protect iommu set in domain */
 	u64		max_addr;	/* maximum mapped address */
@@ -421,7 +428,6 @@ static struct intel_iommu *domain_get_iommu(struct dmar_domain *domain)
 	return g_iommus[iommu_id];
 }
 
-/* "Coherency" capability may be different across iommus */
 static void domain_update_iommu_coherency(struct dmar_domain *domain)
 {
 	int i;
@@ -438,6 +444,29 @@ static void domain_update_iommu_coherency(struct dmar_domain *domain)
 	}
 }
 
+static void domain_update_iommu_snooping(struct dmar_domain *domain)
+{
+	int i;
+
+	domain->iommu_snooping = 1;
+
+	i = find_first_bit(&domain->iommu_bmp, g_num_of_iommus);
+	for (; i < g_num_of_iommus; ) {
+		if (!ecap_sc_support(g_iommus[i]->ecap)) {
+			domain->iommu_snooping = 0;
+			break;
+		}
+		i = find_next_bit(&domain->iommu_bmp, g_num_of_iommus, i+1);
+	}
+}
+
+/* Some capabilities may be different across iommus */
+static void domain_update_iommu_cap(struct dmar_domain *domain)
+{
+	domain_update_iommu_coherency(domain);
+	domain_update_iommu_snooping(domain);
+}
+
 static struct intel_iommu *device_to_iommu(u8 bus, u8 devfn)
 {
 	struct dmar_drhd_unit *drhd = NULL;
@@ -689,15 +718,17 @@ static void dma_pte_clear_one(struct dmar_domain *domain, u64 addr)
 static void dma_pte_clear_range(struct dmar_domain *domain, u64 start, u64 end)
 {
 	int addr_width = agaw_to_width(domain->agaw);
+	int npages;
 
 	start &= (((u64)1) << addr_width) - 1;
 	end &= (((u64)1) << addr_width) - 1;
 	/* in case it's partial page */
 	start = PAGE_ALIGN(start);
 	end &= PAGE_MASK;
+	npages = (end - start) / VTD_PAGE_SIZE;
 
 	/* we don't need lock here, nobody else touches the iova range */
-	while (start < end) {
+	while (npages--) {
 		dma_pte_clear_one(domain, start);
 		start += VTD_PAGE_SIZE;
 	}
@@ -1241,6 +1272,11 @@ static int domain_init(struct dmar_domain *domain, int guest_width)
 	else
 		domain->iommu_coherency = 0;
 
+	if (ecap_sc_support(iommu->ecap))
+		domain->iommu_snooping = 1;
+	else
+		domain->iommu_snooping = 0;
+
 	domain->iommu_count = 1;
 
 	/* always allocate the top pgd */
@@ -1369,7 +1405,7 @@ static int domain_context_mapping_one(struct dmar_domain *domain,
 	spin_lock_irqsave(&domain->iommu_lock, flags);
 	if (!test_and_set_bit(iommu->seq_id, &domain->iommu_bmp)) {
 		domain->iommu_count++;
-		domain_update_iommu_coherency(domain);
+		domain_update_iommu_cap(domain);
 	}
 	spin_unlock_irqrestore(&domain->iommu_lock, flags);
 	return 0;
@@ -1469,6 +1505,8 @@ domain_page_mapping(struct dmar_domain *domain, dma_addr_t iova,
 		BUG_ON(dma_pte_addr(pte));
 		dma_set_pte_addr(pte, start_pfn << VTD_PAGE_SHIFT);
 		dma_set_pte_prot(pte, prot);
+		if (prot & DMA_PTE_SNP)
+			dma_set_pte_snp(pte);
 		domain_flush_cache(domain, pte, sizeof(*pte));
 		start_pfn++;
 		index++;
@@ -2119,7 +2157,7 @@ static dma_addr_t __intel_map_single(struct device *hwdev, phys_addr_t paddr,
 error:
 	if (iova)
 		__free_iova(&domain->iovad, iova);
-	printk(KERN_ERR"Device %s request: %lx@%llx dir %d --- failed\n",
+	printk(KERN_ERR"Device %s request: %zx@%llx dir %d --- failed\n",
 		pci_name(pdev), size, (unsigned long long)paddr, dir);
 	return 0;
 }
@@ -2218,7 +2256,7 @@ static void intel_unmap_page(struct device *dev, dma_addr_t dev_addr,
 	start_addr = iova->pfn_lo << PAGE_SHIFT;
 	size = aligned_size((u64)dev_addr, size);
 
-	pr_debug("Device %s unmapping: %lx@%llx\n",
+	pr_debug("Device %s unmapping: %zx@%llx\n",
 		pci_name(pdev), size, (unsigned long long)start_addr);
 
 	/*  clear the whole page */
@@ -2282,8 +2320,6 @@ static void intel_free_coherent(struct device *hwdev, size_t size, void *vaddr,
 	free_pages((unsigned long)vaddr, order);
 }
 
-#define SG_ENT_VIRT_ADDRESS(sg)	(sg_virt((sg)))
-
 static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 			   int nelems, enum dma_data_direction dir,
 			   struct dma_attrs *attrs)
@@ -2294,7 +2330,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 	unsigned long start_addr;
 	struct iova *iova;
 	size_t size = 0;
-	void *addr;
+	phys_addr_t addr;
 	struct scatterlist *sg;
 	struct intel_iommu *iommu;
 
@@ -2310,7 +2346,7 @@ static void intel_unmap_sg(struct device *hwdev, struct scatterlist *sglist,
 	if (!iova)
 		return;
 	for_each_sg(sglist, sg, nelems, i) {
-		addr = SG_ENT_VIRT_ADDRESS(sg);
+		addr = page_to_phys(sg_page(sg)) + sg->offset;
 		size += aligned_size((u64)addr, sg->length);
 	}
 
@@ -2337,7 +2373,7 @@ static int intel_nontranslate_map_sg(struct device *hddev,
 
 	for_each_sg(sglist, sg, nelems, i) {
 		BUG_ON(!sg_page(sg));
-		sg->dma_address = virt_to_bus(SG_ENT_VIRT_ADDRESS(sg));
+		sg->dma_address = page_to_phys(sg_page(sg)) + sg->offset;
 		sg->dma_length = sg->length;
 	}
 	return nelems;
@@ -2346,7 +2382,7 @@ static int intel_nontranslate_map_sg(struct device *hddev,
 static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int nelems,
 			enum dma_data_direction dir, struct dma_attrs *attrs)
 {
-	void *addr;
+	phys_addr_t addr;
 	int i;
 	struct pci_dev *pdev = to_pci_dev(hwdev);
 	struct dmar_domain *domain;
@@ -2370,8 +2406,7 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
 	iommu = domain_get_iommu(domain);
 
 	for_each_sg(sglist, sg, nelems, i) {
-		addr = SG_ENT_VIRT_ADDRESS(sg);
-		addr = (void *)virt_to_phys(addr);
+		addr = page_to_phys(sg_page(sg)) + sg->offset;
 		size += aligned_size((u64)addr, sg->length);
 	}
 
@@ -2394,8 +2429,7 @@ static int intel_map_sg(struct device *hwdev, struct scatterlist *sglist, int ne
 	start_addr = iova->pfn_lo << PAGE_SHIFT;
 	offset = 0;
 	for_each_sg(sglist, sg, nelems, i) {
-		addr = SG_ENT_VIRT_ADDRESS(sg);
-		addr = (void *)virt_to_phys(addr);
+		addr = page_to_phys(sg_page(sg)) + sg->offset;
 		size = aligned_size((u64)addr, sg->length);
 		ret = domain_page_mapping(domain, start_addr + offset,
 			((u64)addr) & PAGE_MASK,
@@ -2628,6 +2662,33 @@ static int vm_domain_add_dev_info(struct dmar_domain *domain,
 	return 0;
 }
 
+static void iommu_detach_dependent_devices(struct intel_iommu *iommu,
+					   struct pci_dev *pdev)
+{
+	struct pci_dev *tmp, *parent;
+
+	if (!iommu || !pdev)
+		return;
+
+	/* dependent device detach */
+	tmp = pci_find_upstream_pcie_bridge(pdev);
+	/* Secondary interface's bus number and devfn 0 */
+	if (tmp) {
+		parent = pdev->bus->self;
+		while (parent != tmp) {
+			iommu_detach_dev(iommu, parent->bus->number,
+				parent->devfn);
+			parent = parent->bus->self;
+		}
+		if (tmp->is_pcie) /* this is a PCIE-to-PCI bridge */
+			iommu_detach_dev(iommu,
+				tmp->subordinate->number, 0);
+		else /* this is a legacy PCI bridge */
+			iommu_detach_dev(iommu,
+				tmp->bus->number, tmp->devfn);
+	}
+}
+
 static void vm_domain_remove_one_dev_info(struct dmar_domain *domain,
 					  struct pci_dev *pdev)
 {
@@ -2653,6 +2714,7 @@ static void vm_domain_remove_one_dev_info(struct dmar_domain *domain,
 			spin_unlock_irqrestore(&device_domain_lock, flags);
 
 			iommu_detach_dev(iommu, info->bus, info->devfn);
+			iommu_detach_dependent_devices(iommu, pdev);
 			free_devinfo_mem(info);
 
 			spin_lock_irqsave(&device_domain_lock, flags);
@@ -2676,7 +2738,7 @@ static void vm_domain_remove_one_dev_info(struct dmar_domain *domain,
 		spin_lock_irqsave(&domain->iommu_lock, tmp_flags);
 		clear_bit(iommu->seq_id, &domain->iommu_bmp);
 		domain->iommu_count--;
-		domain_update_iommu_coherency(domain);
+		domain_update_iommu_cap(domain);
 		spin_unlock_irqrestore(&domain->iommu_lock, tmp_flags);
 	}
 
@@ -2702,15 +2764,16 @@ static void vm_domain_remove_all_dev_info(struct dmar_domain *domain)
 
 		iommu = device_to_iommu(info->bus, info->devfn);
 		iommu_detach_dev(iommu, info->bus, info->devfn);
+		iommu_detach_dependent_devices(iommu, info->dev);
 
 		/* clear this iommu in iommu_bmp, update iommu count
-		 * and coherency
+		 * and capabilities
 		 */
 		spin_lock_irqsave(&domain->iommu_lock, flags2);
 		if (test_and_clear_bit(iommu->seq_id,
 				       &domain->iommu_bmp)) {
 			domain->iommu_count--;
-			domain_update_iommu_coherency(domain);
+			domain_update_iommu_cap(domain);
 		}
 		spin_unlock_irqrestore(&domain->iommu_lock, flags2);
 
@@ -2933,6 +2996,8 @@ static int intel_iommu_map_range(struct iommu_domain *domain,
 		prot |= DMA_PTE_READ;
 	if (iommu_prot & IOMMU_WRITE)
 		prot |= DMA_PTE_WRITE;
+	if ((iommu_prot & IOMMU_CACHE) && dmar_domain->iommu_snooping)
+		prot |= DMA_PTE_SNP;
 
 	max_addr = (iova & VTD_PAGE_MASK) + VTD_PAGE_ALIGN(size);
 	if (dmar_domain->max_addr < max_addr) {
@@ -2986,6 +3051,17 @@ static phys_addr_t intel_iommu_iova_to_phys(struct iommu_domain *domain,
 	return phys;
 }
 
+static int intel_iommu_domain_has_cap(struct iommu_domain *domain,
+				      unsigned long cap)
+{
+	struct dmar_domain *dmar_domain = domain->priv;
+
+	if (cap == IOMMU_CAP_CACHE_COHERENCY)
+		return dmar_domain->iommu_snooping;
+
+	return 0;
+}
+
 static struct iommu_ops intel_iommu_ops = {
 	.domain_init	= intel_iommu_domain_init,
 	.domain_destroy = intel_iommu_domain_destroy,
@@ -2994,6 +3070,7 @@ static struct iommu_ops intel_iommu_ops = {
 	.map		= intel_iommu_map_range,
 	.unmap		= intel_iommu_unmap_range,
 	.iova_to_phys	= intel_iommu_iova_to_phys,
+	.domain_has_cap = intel_iommu_domain_has_cap,
 };
 
 static void __devinit quirk_iommu_rwbf(struct pci_dev *dev)
diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c
index c0cbbb5a245e..d76c4c85367e 100644
--- a/drivers/pci/pci-driver.c
+++ b/drivers/pci/pci-driver.c
@@ -277,10 +277,9 @@ static int pci_call_probe(struct pci_driver *drv, struct pci_dev *dev,
 	node = dev_to_node(&dev->dev);
 	if (node >= 0) {
 		int cpu;
-		node_to_cpumask_ptr(nodecpumask, node);
 
 		get_online_cpus();
-		cpu = cpumask_any_and(nodecpumask, cpu_online_mask);
+		cpu = cpumask_any_and(cpumask_of_node(node), cpu_online_mask);
 		if (cpu < nr_cpu_ids)
 			error = work_on_cpu(cpu, local_pci_probe, &ddi);
 		else
diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c
index fe7ac2cea7c9..445fb6f7ea3f 100644
--- a/drivers/pci/pci.c
+++ b/drivers/pci/pci.c
@@ -593,7 +593,7 @@ EXPORT_SYMBOL_GPL(__pci_complete_power_transition);
  * @dev: PCI device to handle.
  * @state: PCI power state (D0, D1, D2, D3hot) to put the device into.
  *
- * Transition a device to a new power state, using the platform formware and/or
+ * Transition a device to a new power state, using the platform firmware and/or
  * the device's PCI PM registers.
  *
  * RETURN VALUE:
diff --git a/drivers/pcmcia/pxa2xx_cm_x255.c b/drivers/pcmcia/pxa2xx_cm_x255.c
index 4ed64d8e95e7..5143a760153b 100644
--- a/drivers/pcmcia/pxa2xx_cm_x255.c
+++ b/drivers/pcmcia/pxa2xx_cm_x255.c
@@ -63,7 +63,7 @@ static void cmx255_pcmcia_socket_state(struct soc_pcmcia_socket *skt,
 				       struct pcmcia_state *state)
 {
 	int cd = skt->nr ? GPIO_PCMCIA_S1_CD_VALID : GPIO_PCMCIA_S0_CD_VALID;
-	int rdy = skt->nr ? GPIO_PCMCIA_S0_RDYINT : GPIO_PCMCIA_S1_RDYINT;
+	int rdy = skt->nr ? GPIO_PCMCIA_S1_RDYINT : GPIO_PCMCIA_S0_RDYINT;
 
 	state->detect = !gpio_get_value(cd);
 	state->ready  = !!gpio_get_value(rdy);
diff --git a/drivers/platform/x86/thinkpad_acpi.c b/drivers/platform/x86/thinkpad_acpi.c
index 3dad27a385d3..d99f1cd435a2 100644
--- a/drivers/platform/x86/thinkpad_acpi.c
+++ b/drivers/platform/x86/thinkpad_acpi.c
@@ -5811,7 +5811,7 @@ static struct ibm_struct volume_driver_data = {
  *	ThinkPads from this same time period (and earlier) probably lack the
  *	tachometer as well.
  *
- *	Unfortunately a lot of ThinkPads with new-style ECs but whose firwmare
+ *	Unfortunately a lot of ThinkPads with new-style ECs but whose firmware
  *	was never fixed by IBM to report the EC firmware version string
  *	probably support the tachometer (like the early X models), so
  *	detecting it is quite hard.  We need more data to know for sure.
diff --git a/drivers/pnp/pnpbios/core.c b/drivers/pnp/pnpbios/core.c
index 996f64838079..cfe86853feb2 100644
--- a/drivers/pnp/pnpbios/core.c
+++ b/drivers/pnp/pnpbios/core.c
@@ -94,7 +94,6 @@ struct pnp_dev_node_info node_info;
 
 #ifdef CONFIG_HOTPLUG
 
-static int unloading = 0;
 static struct completion unload_sem;
 
 /*
@@ -158,7 +157,7 @@ static int pnp_dock_thread(void *unused)
 	int docked = -1, d = 0;
 
 	set_freezable();
-	while (!unloading) {
+	while (1) {
 		int status;
 
 		/*
@@ -575,8 +574,6 @@ fs_initcall(pnpbios_init);
 
 static int __init pnpbios_thread_init(void)
 {
-	struct task_struct *task;
-
 #if defined(CONFIG_PPC)
 	if (check_legacy_ioport(PNPBIOS_BASE))
 		return 0;
@@ -584,10 +581,13 @@ static int __init pnpbios_thread_init(void)
 	if (pnpbios_disabled)
 		return 0;
 #ifdef CONFIG_HOTPLUG
-	init_completion(&unload_sem);
-	task = kthread_run(pnp_dock_thread, NULL, "kpnpbiosd");
-	if (!IS_ERR(task))
-		unloading = 0;
+	{
+		struct task_struct *task;
+		init_completion(&unload_sem);
+		task = kthread_run(pnp_dock_thread, NULL, "kpnpbiosd");
+		if (IS_ERR(task))
+			return PTR_ERR(task);
+	}
 #endif
 	return 0;
 }
diff --git a/drivers/power/bq27x00_battery.c b/drivers/power/bq27x00_battery.c
index 0c056fcc01ce..62bb98124e26 100644
--- a/drivers/power/bq27x00_battery.c
+++ b/drivers/power/bq27x00_battery.c
@@ -83,7 +83,7 @@ static int bq27x00_read(u8 reg, int *rt_value, int b_single,
 }
 
 /*
- * Return the battery temperature in Celcius degrees
+ * Return the battery temperature in Celsius degrees
  * Or < 0 if something fails.
  */
 static int bq27x00_battery_temperature(struct bq27x00_device_info *di)
diff --git a/drivers/regulator/Kconfig b/drivers/regulator/Kconfig
index e7e0cf102d6d..e58c0ce65aa6 100644
--- a/drivers/regulator/Kconfig
+++ b/drivers/regulator/Kconfig
@@ -29,8 +29,12 @@ config REGULATOR_DEBUG
 	  Say yes here to enable debugging support.
 
 config REGULATOR_FIXED_VOLTAGE
-	tristate
+	tristate "Fixed voltage regulator support"
 	default n
+	help
+	  This driver provides support for fixed voltage regulators,
+	  useful for systems which use a combination of software
+	  managed regulators and simple non-configurable regulators.
 
 config REGULATOR_VIRTUAL_CONSUMER
 	tristate "Virtual regulator consumer support"
@@ -52,6 +56,13 @@ config REGULATOR_BQ24022
 	  charging select between 100 mA and 500 mA charging current
 	  limit.
 
+config REGULATOR_TWL4030
+	bool "TI TWL4030/TWL5030/TPS695x0 PMIC"
+	depends on TWL4030_CORE
+	help
+	  This driver supports the voltage regulators provided by
+	  this family of companion chips.
+
 config REGULATOR_WM8350
 	tristate "Wolfson Microelectroncis WM8350 AudioPlus PMIC"
 	depends on MFD_WM8350
diff --git a/drivers/regulator/Makefile b/drivers/regulator/Makefile
index 61b30c6ddecc..bac133afc061 100644
--- a/drivers/regulator/Makefile
+++ b/drivers/regulator/Makefile
@@ -8,6 +8,7 @@ obj-$(CONFIG_REGULATOR_FIXED_VOLTAGE) += fixed.o
 obj-$(CONFIG_REGULATOR_VIRTUAL_CONSUMER) += virtual.o
 
 obj-$(CONFIG_REGULATOR_BQ24022) += bq24022.o
+obj-$(CONFIG_REGULATOR_TWL4030) += twl4030-regulator.o
 obj-$(CONFIG_REGULATOR_WM8350) += wm8350-regulator.o
 obj-$(CONFIG_REGULATOR_WM8400) += wm8400-regulator.o
 obj-$(CONFIG_REGULATOR_DA903X)	+= da903x.o
diff --git a/drivers/regulator/bq24022.c b/drivers/regulator/bq24022.c
index c175e38a4cd5..7ecb820ceebc 100644
--- a/drivers/regulator/bq24022.c
+++ b/drivers/regulator/bq24022.c
@@ -105,7 +105,8 @@ static int __init bq24022_probe(struct platform_device *pdev)
 	ret = gpio_direction_output(pdata->gpio_iset2, 0);
 	ret = gpio_direction_output(pdata->gpio_nce, 1);
 
-	bq24022 = regulator_register(&bq24022_desc, &pdev->dev, pdata);
+	bq24022 = regulator_register(&bq24022_desc, &pdev->dev,
+				     pdata->init_data, pdata);
 	if (IS_ERR(bq24022)) {
 		dev_dbg(&pdev->dev, "couldn't register regulator\n");
 		ret = PTR_ERR(bq24022);
diff --git a/drivers/regulator/core.c b/drivers/regulator/core.c
index f511a406fcaa..01f7702a805d 100644
--- a/drivers/regulator/core.c
+++ b/drivers/regulator/core.c
@@ -28,33 +28,7 @@
 static DEFINE_MUTEX(regulator_list_mutex);
 static LIST_HEAD(regulator_list);
 static LIST_HEAD(regulator_map_list);
-
-/*
- * struct regulator_dev
- *
- * Voltage / Current regulator class device. One for each regulator.
- */
-struct regulator_dev {
-	struct regulator_desc *desc;
-	int use_count;
-
-	/* lists we belong to */
-	struct list_head list; /* list of all regulators */
-	struct list_head slist; /* list of supplied regulators */
-
-	/* lists we own */
-	struct list_head consumer_list; /* consumers we supply */
-	struct list_head supply_list; /* regulators we supply */
-
-	struct blocking_notifier_head notifier;
-	struct mutex mutex; /* consumer lock */
-	struct module *owner;
-	struct device dev;
-	struct regulation_constraints *constraints;
-	struct regulator_dev *supply;	/* for tree */
-
-	void *reg_data;		/* regulator_dev data */
-};
+static int has_full_constraints;
 
 /*
  * struct regulator_map
@@ -79,7 +53,6 @@ struct regulator {
 	int uA_load;
 	int min_uV;
 	int max_uV;
-	int enabled; /* count of client enables */
 	char *supply_name;
 	struct device_attribute dev_attr;
 	struct regulator_dev *rdev;
@@ -312,6 +285,47 @@ static ssize_t regulator_state_show(struct device *dev,
 }
 static DEVICE_ATTR(state, 0444, regulator_state_show, NULL);
 
+static ssize_t regulator_status_show(struct device *dev,
+				   struct device_attribute *attr, char *buf)
+{
+	struct regulator_dev *rdev = dev_get_drvdata(dev);
+	int status;
+	char *label;
+
+	status = rdev->desc->ops->get_status(rdev);
+	if (status < 0)
+		return status;
+
+	switch (status) {
+	case REGULATOR_STATUS_OFF:
+		label = "off";
+		break;
+	case REGULATOR_STATUS_ON:
+		label = "on";
+		break;
+	case REGULATOR_STATUS_ERROR:
+		label = "error";
+		break;
+	case REGULATOR_STATUS_FAST:
+		label = "fast";
+		break;
+	case REGULATOR_STATUS_NORMAL:
+		label = "normal";
+		break;
+	case REGULATOR_STATUS_IDLE:
+		label = "idle";
+		break;
+	case REGULATOR_STATUS_STANDBY:
+		label = "standby";
+		break;
+	default:
+		return -ERANGE;
+	}
+
+	return sprintf(buf, "%s\n", label);
+}
+static DEVICE_ATTR(status, 0444, regulator_status_show, NULL);
+
 static ssize_t regulator_min_uA_show(struct device *dev,
 				    struct device_attribute *attr, char *buf)
 {
@@ -678,6 +692,73 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 	else
 		name = "regulator";
 
+	/* constrain machine-level voltage specs to fit
+	 * the actual range supported by this regulator.
+	 */
+	if (ops->list_voltage && rdev->desc->n_voltages) {
+		int	count = rdev->desc->n_voltages;
+		int	i;
+		int	min_uV = INT_MAX;
+		int	max_uV = INT_MIN;
+		int	cmin = constraints->min_uV;
+		int	cmax = constraints->max_uV;
+
+		/* it's safe to autoconfigure fixed-voltage supplies */
+		if (count == 1 && !cmin) {
+			cmin = INT_MIN;
+			cmax = INT_MAX;
+		}
+
+		/* voltage constraints are optional */
+		if ((cmin == 0) && (cmax == 0))
+			goto out;
+
+		/* else require explicit machine-level constraints */
+		if (cmin <= 0 || cmax <= 0 || cmax < cmin) {
+			pr_err("%s: %s '%s' voltage constraints\n",
+				       __func__, "invalid", name);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		/* initial: [cmin..cmax] valid, [min_uV..max_uV] not */
+		for (i = 0; i < count; i++) {
+			int	value;
+
+			value = ops->list_voltage(rdev, i);
+			if (value <= 0)
+				continue;
+
+			/* maybe adjust [min_uV..max_uV] */
+			if (value >= cmin && value < min_uV)
+				min_uV = value;
+			if (value <= cmax && value > max_uV)
+				max_uV = value;
+		}
+
+		/* final: [min_uV..max_uV] valid iff constraints valid */
+		if (max_uV < min_uV) {
+			pr_err("%s: %s '%s' voltage constraints\n",
+				       __func__, "unsupportable", name);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		/* use regulator's subset of machine constraints */
+		if (constraints->min_uV < min_uV) {
+			pr_debug("%s: override '%s' %s, %d -> %d\n",
+				       __func__, name, "min_uV",
+					constraints->min_uV, min_uV);
+			constraints->min_uV = min_uV;
+		}
+		if (constraints->max_uV > max_uV) {
+			pr_debug("%s: override '%s' %s, %d -> %d\n",
+				       __func__, name, "max_uV",
+					constraints->max_uV, max_uV);
+			constraints->max_uV = max_uV;
+		}
+	}
+
 	rdev->constraints = constraints;
 
 	/* do we need to apply the constraint voltage */
@@ -695,10 +776,6 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 			}
 	}
 
-	/* are we enabled at boot time by firmware / bootloader */
-	if (rdev->constraints->boot_on)
-		rdev->use_count = 1;
-
 	/* do we need to setup our suspend state */
 	if (constraints->initial_state) {
 		ret = suspend_prepare(rdev, constraints->initial_state);
@@ -710,11 +787,27 @@ static int set_machine_constraints(struct regulator_dev *rdev,
 		}
 	}
 
-	/* if always_on is set then turn the regulator on if it's not
-	 * already on. */
-	if (constraints->always_on && ops->enable &&
-	    ((ops->is_enabled && !ops->is_enabled(rdev)) ||
-	     (!ops->is_enabled && !constraints->boot_on))) {
+	if (constraints->initial_mode) {
+		if (!ops->set_mode) {
+			printk(KERN_ERR "%s: no set_mode operation for %s\n",
+			       __func__, name);
+			ret = -EINVAL;
+			goto out;
+		}
+
+		ret = ops->set_mode(rdev, constraints->initial_mode);
+		if (ret < 0) {
+			printk(KERN_ERR
+			       "%s: failed to set initial mode for %s: %d\n",
+			       __func__, name, ret);
+			goto out;
+		}
+	}
+
+	/* If the constraints say the regulator should be on at this point
+	 * and we have control then make sure it is enabled.
+	 */
+	if ((constraints->always_on || constraints->boot_on) && ops->enable) {
 		ret = ops->enable(rdev);
 		if (ret < 0) {
 			printk(KERN_ERR "%s: failed to enable %s\n",
@@ -817,6 +910,19 @@ static void unset_consumer_device_supply(struct regulator_dev *rdev,
 	}
 }
 
+static void unset_regulator_supplies(struct regulator_dev *rdev)
+{
+	struct regulator_map *node, *n;
+
+	list_for_each_entry_safe(node, n, &regulator_map_list, list) {
+		if (rdev == node->regulator) {
+			list_del(&node->list);
+			kfree(node);
+			return;
+		}
+	}
+}
+
 #define REG_STR_SIZE	32
 
 static struct regulator *create_regulator(struct regulator_dev *rdev,
@@ -898,9 +1004,12 @@ overflow_err:
  * @id: Supply name or regulator ID.
  *
  * Returns a struct regulator corresponding to the regulator producer,
- * or IS_ERR() condition containing errno.  Use of supply names
- * configured via regulator_set_device_supply() is strongly
- * encouraged.
+ * or IS_ERR() condition containing errno.
+ *
+ * Use of supply names configured via regulator_set_device_supply() is
+ * strongly encouraged.  It is recommended that the supply name used
+ * should match the name used for the supply and/or the relevant
+ * device pins in the datasheet.
  */
 struct regulator *regulator_get(struct device *dev, const char *id)
 {
@@ -922,8 +1031,6 @@ struct regulator *regulator_get(struct device *dev, const char *id)
 			goto found;
 		}
 	}
-	printk(KERN_ERR "regulator: Unable to get requested regulator: %s\n",
-	       id);
 	mutex_unlock(&regulator_list_mutex);
 	return regulator;
 
@@ -961,10 +1068,6 @@ void regulator_put(struct regulator *regulator)
 	mutex_lock(&regulator_list_mutex);
 	rdev = regulator->rdev;
 
-	if (WARN(regulator->enabled, "Releasing supply %s while enabled\n",
-			       regulator->supply_name))
-		_regulator_disable(rdev);
-
 	/* remove any sysfs entries */
 	if (regulator->dev) {
 		sysfs_remove_link(&rdev->dev.kobj, regulator->supply_name);
@@ -1039,12 +1142,7 @@ int regulator_enable(struct regulator *regulator)
 	int ret = 0;
 
 	mutex_lock(&rdev->mutex);
-	if (regulator->enabled == 0)
-		ret = _regulator_enable(rdev);
-	else if (regulator->enabled < 0)
-		ret = -EIO;
-	if (ret == 0)
-		regulator->enabled++;
+	ret = _regulator_enable(rdev);
 	mutex_unlock(&rdev->mutex);
 	return ret;
 }
@@ -1055,6 +1153,11 @@ static int _regulator_disable(struct regulator_dev *rdev)
 {
 	int ret = 0;
 
+	if (WARN(rdev->use_count <= 0,
+			"unbalanced disables for %s\n",
+			rdev->desc->name))
+		return -EIO;
+
 	/* are we the last user and permitted to disable ? */
 	if (rdev->use_count == 1 && !rdev->constraints->always_on) {
 
@@ -1103,16 +1206,7 @@ int regulator_disable(struct regulator *regulator)
 	int ret = 0;
 
 	mutex_lock(&rdev->mutex);
-	if (regulator->enabled == 1) {
-		ret = _regulator_disable(rdev);
-		if (ret == 0)
-			regulator->uA_load = 0;
-	} else if (WARN(regulator->enabled <= 0,
-			"unbalanced disables for supply %s\n",
-			regulator->supply_name))
-		ret = -EIO;
-	if (ret == 0)
-		regulator->enabled--;
+	ret = _regulator_disable(rdev);
 	mutex_unlock(&rdev->mutex);
 	return ret;
 }
@@ -1159,7 +1253,6 @@ int regulator_force_disable(struct regulator *regulator)
 	int ret;
 
 	mutex_lock(&regulator->rdev->mutex);
-	regulator->enabled = 0;
 	regulator->uA_load = 0;
 	ret = _regulator_force_disable(regulator->rdev);
 	mutex_unlock(&regulator->rdev->mutex);
@@ -1204,6 +1297,56 @@ int regulator_is_enabled(struct regulator *regulator)
 EXPORT_SYMBOL_GPL(regulator_is_enabled);
 
 /**
+ * regulator_count_voltages - count regulator_list_voltage() selectors
+ * @regulator: regulator source
+ *
+ * Returns number of selectors, or negative errno.  Selectors are
+ * numbered starting at zero, and typically correspond to bitfields
+ * in hardware registers.
+ */
+int regulator_count_voltages(struct regulator *regulator)
+{
+	struct regulator_dev	*rdev = regulator->rdev;
+
+	return rdev->desc->n_voltages ? : -EINVAL;
+}
+EXPORT_SYMBOL_GPL(regulator_count_voltages);
+
+/**
+ * regulator_list_voltage - enumerate supported voltages
+ * @regulator: regulator source
+ * @selector: identify voltage to list
+ * Context: can sleep
+ *
+ * Returns a voltage that can be passed to @regulator_set_voltage(),
+ * zero if this selector code can't be used on this sytem, or a
+ * negative errno.
+ */
+int regulator_list_voltage(struct regulator *regulator, unsigned selector)
+{
+	struct regulator_dev	*rdev = regulator->rdev;
+	struct regulator_ops	*ops = rdev->desc->ops;
+	int			ret;
+
+	if (!ops->list_voltage || selector >= rdev->desc->n_voltages)
+		return -EINVAL;
+
+	mutex_lock(&rdev->mutex);
+	ret = ops->list_voltage(rdev, selector);
+	mutex_unlock(&rdev->mutex);
+
+	if (ret > 0) {
+		if (ret < rdev->constraints->min_uV)
+			ret = 0;
+		else if (ret > rdev->constraints->max_uV)
+			ret = 0;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(regulator_list_voltage);
+
+/**
  * regulator_set_voltage - set regulator output voltage
  * @regulator: regulator source
  * @min_uV: Minimum required voltage in uV
@@ -1243,6 +1386,7 @@ int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV)
 	ret = rdev->desc->ops->set_voltage(rdev, min_uV, max_uV);
 
 out:
+	_notifier_call_chain(rdev, REGULATOR_EVENT_VOLTAGE_CHANGE, NULL);
 	mutex_unlock(&rdev->mutex);
 	return ret;
 }
@@ -1543,20 +1687,23 @@ int regulator_unregister_notifier(struct regulator *regulator,
 }
 EXPORT_SYMBOL_GPL(regulator_unregister_notifier);
 
-/* notify regulator consumers and downstream regulator consumers */
+/* notify regulator consumers and downstream regulator consumers.
+ * Note mutex must be held by caller.
+ */
 static void _notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data)
 {
 	struct regulator_dev *_rdev;
 
 	/* call rdev chain first */
-	mutex_lock(&rdev->mutex);
 	blocking_notifier_call_chain(&rdev->notifier, event, NULL);
-	mutex_unlock(&rdev->mutex);
 
 	/* now notify regulator we supply */
-	list_for_each_entry(_rdev, &rdev->supply_list, slist)
-		_notifier_call_chain(_rdev, event, data);
+	list_for_each_entry(_rdev, &rdev->supply_list, slist) {
+	  mutex_lock(&_rdev->mutex);
+	  _notifier_call_chain(_rdev, event, data);
+	  mutex_unlock(&_rdev->mutex);
+	}
 }
 
 /**
@@ -1703,6 +1850,7 @@ EXPORT_SYMBOL_GPL(regulator_bulk_free);
  *
  * Called by regulator drivers to notify clients a regulator event has
  * occurred. We also notify regulator clients downstream.
+ * Note lock must be held by caller.
  */
 int regulator_notifier_call_chain(struct regulator_dev *rdev,
 				  unsigned long event, void *data)
@@ -1744,6 +1892,11 @@ static int add_regulator_attributes(struct regulator_dev *rdev)
 		if (status < 0)
 			return status;
 	}
+	if (ops->get_status) {
+		status = device_create_file(dev, &dev_attr_status);
+		if (status < 0)
+			return status;
+	}
 
 	/* some attributes are type-specific */
 	if (rdev->desc->type == REGULATOR_CURRENT) {
@@ -1828,17 +1981,18 @@ static int add_regulator_attributes(struct regulator_dev *rdev)
  * regulator_register - register regulator
  * @regulator_desc: regulator to register
  * @dev: struct device for the regulator
+ * @init_data: platform provided init data, passed through by driver
  * @driver_data: private regulator data
  *
  * Called by regulator drivers to register a regulator.
  * Returns 0 on success.
  */
 struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
-	struct device *dev, void *driver_data)
+	struct device *dev, struct regulator_init_data *init_data,
+	void *driver_data)
 {
 	static atomic_t regulator_no = ATOMIC_INIT(0);
 	struct regulator_dev *rdev;
-	struct regulator_init_data *init_data = dev->platform_data;
 	int ret, i;
 
 	if (regulator_desc == NULL)
@@ -1945,6 +2099,7 @@ void regulator_unregister(struct regulator_dev *rdev)
 		return;
 
 	mutex_lock(&regulator_list_mutex);
+	unset_regulator_supplies(rdev);
 	list_del(&rdev->list);
 	if (rdev->supply)
 		sysfs_remove_link(&rdev->dev.kobj, "supply");
@@ -1989,6 +2144,23 @@ out:
 EXPORT_SYMBOL_GPL(regulator_suspend_prepare);
 
 /**
+ * regulator_has_full_constraints - the system has fully specified constraints
+ *
+ * Calling this function will cause the regulator API to disable all
+ * regulators which have a zero use count and don't have an always_on
+ * constraint in a late_initcall.
+ *
+ * The intention is that this will become the default behaviour in a
+ * future kernel release so users are encouraged to use this facility
+ * now.
+ */
+void regulator_has_full_constraints(void)
+{
+	has_full_constraints = 1;
+}
+EXPORT_SYMBOL_GPL(regulator_has_full_constraints);
+
+/**
  * rdev_get_drvdata - get rdev regulator driver data
  * @rdev: regulator
  *
@@ -2055,3 +2227,77 @@ static int __init regulator_init(void)
 
 /* init early to allow our consumers to complete system booting */
 core_initcall(regulator_init);
+
+static int __init regulator_init_complete(void)
+{
+	struct regulator_dev *rdev;
+	struct regulator_ops *ops;
+	struct regulation_constraints *c;
+	int enabled, ret;
+	const char *name;
+
+	mutex_lock(&regulator_list_mutex);
+
+	/* If we have a full configuration then disable any regulators
+	 * which are not in use or always_on.  This will become the
+	 * default behaviour in the future.
+	 */
+	list_for_each_entry(rdev, &regulator_list, list) {
+		ops = rdev->desc->ops;
+		c = rdev->constraints;
+
+		if (c->name)
+			name = c->name;
+		else if (rdev->desc->name)
+			name = rdev->desc->name;
+		else
+			name = "regulator";
+
+		if (!ops->disable || c->always_on)
+			continue;
+
+		mutex_lock(&rdev->mutex);
+
+		if (rdev->use_count)
+			goto unlock;
+
+		/* If we can't read the status assume it's on. */
+		if (ops->is_enabled)
+			enabled = ops->is_enabled(rdev);
+		else
+			enabled = 1;
+
+		if (!enabled)
+			goto unlock;
+
+		if (has_full_constraints) {
+			/* We log since this may kill the system if it
+			 * goes wrong. */
+			printk(KERN_INFO "%s: disabling %s\n",
+			       __func__, name);
+			ret = ops->disable(rdev);
+			if (ret != 0) {
+				printk(KERN_ERR
+				       "%s: couldn't disable %s: %d\n",
+				       __func__, name, ret);
+			}
+		} else {
+			/* The intention is that in future we will
+			 * assume that full constraints are provided
+			 * so warn even if we aren't going to do
+			 * anything here.
+			 */
+			printk(KERN_WARNING
+			       "%s: incomplete constraints, leaving %s on\n",
+			       __func__, name);
+		}
+
+unlock:
+		mutex_unlock(&rdev->mutex);
+	}
+
+	mutex_unlock(&regulator_list_mutex);
+
+	return 0;
+}
+late_initcall(regulator_init_complete);
diff --git a/drivers/regulator/da903x.c b/drivers/regulator/da903x.c
index fe77730a7edb..72b15495183c 100644
--- a/drivers/regulator/da903x.c
+++ b/drivers/regulator/da903x.c
@@ -471,7 +471,8 @@ static int __devinit da903x_regulator_probe(struct platform_device *pdev)
 	if (ri->desc.id == DA9030_ID_LDO1 || ri->desc.id == DA9030_ID_LDO15)
 		ri->desc.ops = &da9030_regulator_ldo1_15_ops;
 
-	rdev = regulator_register(&ri->desc, &pdev->dev, ri);
+	rdev = regulator_register(&ri->desc, &pdev->dev,
+				  pdev->dev.platform_data, ri);
 	if (IS_ERR(rdev)) {
 		dev_err(&pdev->dev, "failed to register regulator %s\n",
 				ri->desc.name);
diff --git a/drivers/regulator/fixed.c b/drivers/regulator/fixed.c
index d31db3e14913..23d554628a76 100644
--- a/drivers/regulator/fixed.c
+++ b/drivers/regulator/fixed.c
@@ -73,7 +73,8 @@ static int regulator_fixed_voltage_probe(struct platform_device *pdev)
 
 	drvdata->microvolts = config->microvolts;
 
-	drvdata->dev = regulator_register(&drvdata->desc, drvdata);
+	drvdata->dev = regulator_register(&drvdata->desc, &pdev->dev,
+					  config->init_data, drvdata);
 	if (IS_ERR(drvdata->dev)) {
 		ret = PTR_ERR(drvdata->dev);
 		goto err_name;
diff --git a/drivers/regulator/pcf50633-regulator.c b/drivers/regulator/pcf50633-regulator.c
index 4cc85ec6e120..cd761d85c8fd 100644
--- a/drivers/regulator/pcf50633-regulator.c
+++ b/drivers/regulator/pcf50633-regulator.c
@@ -284,7 +284,8 @@ static int __devinit pcf50633_regulator_probe(struct platform_device *pdev)
 	/* Already set by core driver */
 	pcf = platform_get_drvdata(pdev);
 
-	rdev = regulator_register(&regulators[pdev->id], &pdev->dev, pcf);
+	rdev = regulator_register(&regulators[pdev->id], &pdev->dev,
+				  pdev->dev.platform_data, pcf);
 	if (IS_ERR(rdev))
 		return PTR_ERR(rdev);
 
diff --git a/drivers/regulator/twl4030-regulator.c b/drivers/regulator/twl4030-regulator.c
new file mode 100644
index 000000000000..e2032fb60b55
--- /dev/null
+++ b/drivers/regulator/twl4030-regulator.c
@@ -0,0 +1,500 @@
+/*
+ * twl4030-regulator.c -- support regulators in twl4030 family chips
+ *
+ * Copyright (C) 2008 David Brownell
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/err.h>
+#include <linux/platform_device.h>
+#include <linux/regulator/driver.h>
+#include <linux/regulator/machine.h>
+#include <linux/i2c/twl4030.h>
+
+
+/*
+ * The TWL4030/TW5030/TPS659x0 family chips include power management, a
+ * USB OTG transceiver, an RTC, ADC, PWM, and lots more.  Some versions
+ * include an audio codec, battery charger, and more voltage regulators.
+ * These chips are often used in OMAP-based systems.
+ *
+ * This driver implements software-based resource control for various
+ * voltage regulators.  This is usually augmented with state machine
+ * based control.
+ */
+
+struct twlreg_info {
+	/* start of regulator's PM_RECEIVER control register bank */
+	u8			base;
+
+	/* twl4030 resource ID, for resource control state machine */
+	u8			id;
+
+	/* voltage in mV = table[VSEL]; table_len must be a power-of-two */
+	u8			table_len;
+	const u16		*table;
+
+	/* chip constraints on regulator behavior */
+	u16			min_mV;
+
+	/* used by regulator core */
+	struct regulator_desc	desc;
+};
+
+
+/* LDO control registers ... offset is from the base of its register bank.
+ * The first three registers of all power resource banks help hardware to
+ * manage the various resource groups.
+ */
+#define VREG_GRP		0
+#define VREG_TYPE		1
+#define VREG_REMAP		2
+#define VREG_DEDICATED		3	/* LDO control */
+
+
+static inline int
+twl4030reg_read(struct twlreg_info *info, unsigned offset)
+{
+	u8 value;
+	int status;
+
+	status = twl4030_i2c_read_u8(TWL4030_MODULE_PM_RECEIVER,
+			&value, info->base + offset);
+	return (status < 0) ? status : value;
+}
+
+static inline int
+twl4030reg_write(struct twlreg_info *info, unsigned offset, u8 value)
+{
+	return twl4030_i2c_write_u8(TWL4030_MODULE_PM_RECEIVER,
+			value, info->base + offset);
+}
+
+/*----------------------------------------------------------------------*/
+
+/* generic power resource operations, which work on all regulators */
+
+static int twl4030reg_grp(struct regulator_dev *rdev)
+{
+	return twl4030reg_read(rdev_get_drvdata(rdev), VREG_GRP);
+}
+
+/*
+ * Enable/disable regulators by joining/leaving the P1 (processor) group.
+ * We assume nobody else is updating the DEV_GRP registers.
+ */
+
+#define P3_GRP		BIT(7)		/* "peripherals" */
+#define P2_GRP		BIT(6)		/* secondary processor, modem, etc */
+#define P1_GRP		BIT(5)		/* CPU/Linux */
+
+static int twl4030reg_is_enabled(struct regulator_dev *rdev)
+{
+	int	state = twl4030reg_grp(rdev);
+
+	if (state < 0)
+		return state;
+
+	return (state & P1_GRP) != 0;
+}
+
+static int twl4030reg_enable(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			grp;
+
+	grp = twl4030reg_read(info, VREG_GRP);
+	if (grp < 0)
+		return grp;
+
+	grp |= P1_GRP;
+	return twl4030reg_write(info, VREG_GRP, grp);
+}
+
+static int twl4030reg_disable(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			grp;
+
+	grp = twl4030reg_read(info, VREG_GRP);
+	if (grp < 0)
+		return grp;
+
+	grp &= ~P1_GRP;
+	return twl4030reg_write(info, VREG_GRP, grp);
+}
+
+static int twl4030reg_get_status(struct regulator_dev *rdev)
+{
+	int	state = twl4030reg_grp(rdev);
+
+	if (state < 0)
+		return state;
+	state &= 0x0f;
+
+	/* assume state != WARM_RESET; we'd not be running...  */
+	if (!state)
+		return REGULATOR_STATUS_OFF;
+	return (state & BIT(3))
+		? REGULATOR_STATUS_NORMAL
+		: REGULATOR_STATUS_STANDBY;
+}
+
+static int twl4030reg_set_mode(struct regulator_dev *rdev, unsigned mode)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	unsigned		message;
+	int			status;
+
+	/* We can only set the mode through state machine commands... */
+	switch (mode) {
+	case REGULATOR_MODE_NORMAL:
+		message = MSG_SINGULAR(DEV_GRP_P1, info->id, RES_STATE_ACTIVE);
+		break;
+	case REGULATOR_MODE_STANDBY:
+		message = MSG_SINGULAR(DEV_GRP_P1, info->id, RES_STATE_SLEEP);
+		break;
+	default:
+		return -EINVAL;
+	}
+
+	/* Ensure the resource is associated with some group */
+	status = twl4030reg_grp(rdev);
+	if (status < 0)
+		return status;
+	if (!(status & (P3_GRP | P2_GRP | P1_GRP)))
+		return -EACCES;
+
+	status = twl4030_i2c_write_u8(TWL4030_MODULE_PM_MASTER,
+			message >> 8, 0x15 /* PB_WORD_MSB */ );
+	if (status >= 0)
+		return status;
+
+	return twl4030_i2c_write_u8(TWL4030_MODULE_PM_MASTER,
+			message, 0x16 /* PB_WORD_LSB */ );
+}
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Support for adjustable-voltage LDOs uses a four bit (or less) voltage
+ * select field in its control register.   We use tables indexed by VSEL
+ * to record voltages in milliVolts.  (Accuracy is about three percent.)
+ *
+ * Note that VSEL values for VAUX2 changed in twl5030 and newer silicon;
+ * currently handled by listing two slightly different VAUX2 regulators,
+ * only one of which will be configured.
+ *
+ * VSEL values documented as "TI cannot support these values" are flagged
+ * in these tables as UNSUP() values; we normally won't assign them.
+ *
+ * VAUX3 at 3V is incorrectly listed in some TI manuals as unsupported.
+ * TI are revising the twl5030/tps659x0 specs to support that 3.0V setting.
+ */
+#ifdef CONFIG_TWL4030_ALLOW_UNSUPPORTED
+#define UNSUP_MASK	0x0000
+#else
+#define UNSUP_MASK	0x8000
+#endif
+
+#define UNSUP(x)	(UNSUP_MASK | (x))
+#define IS_UNSUP(x)	(UNSUP_MASK & (x))
+#define LDO_MV(x)	(~UNSUP_MASK & (x))
+
+
+static const u16 VAUX1_VSEL_table[] = {
+	UNSUP(1500), UNSUP(1800), 2500, 2800,
+	3000, 3000, 3000, 3000,
+};
+static const u16 VAUX2_4030_VSEL_table[] = {
+	UNSUP(1000), UNSUP(1000), UNSUP(1200), 1300,
+	1500, 1800, UNSUP(1850), 2500,
+	UNSUP(2600), 2800, UNSUP(2850), UNSUP(3000),
+	UNSUP(3150), UNSUP(3150), UNSUP(3150), UNSUP(3150),
+};
+static const u16 VAUX2_VSEL_table[] = {
+	1700, 1700, 1900, 1300,
+	1500, 1800, 2000, 2500,
+	2100, 2800, 2200, 2300,
+	2400, 2400, 2400, 2400,
+};
+static const u16 VAUX3_VSEL_table[] = {
+	1500, 1800, 2500, 2800,
+	3000, 3000, 3000, 3000,
+};
+static const u16 VAUX4_VSEL_table[] = {
+	700, 1000, 1200, UNSUP(1300),
+	1500, 1800, UNSUP(1850), 2500,
+	UNSUP(2600), 2800, UNSUP(2850), UNSUP(3000),
+	UNSUP(3150), UNSUP(3150), UNSUP(3150), UNSUP(3150),
+};
+static const u16 VMMC1_VSEL_table[] = {
+	1850, 2850, 3000, 3150,
+};
+static const u16 VMMC2_VSEL_table[] = {
+	UNSUP(1000), UNSUP(1000), UNSUP(1200), UNSUP(1300),
+	UNSUP(1500), UNSUP(1800), 1850, UNSUP(2500),
+	2600, 2800, 2850, 3000,
+	3150, 3150, 3150, 3150,
+};
+static const u16 VPLL1_VSEL_table[] = {
+	1000, 1200, 1300, 1800,
+	UNSUP(2800), UNSUP(3000), UNSUP(3000), UNSUP(3000),
+};
+static const u16 VPLL2_VSEL_table[] = {
+	700, 1000, 1200, 1300,
+	UNSUP(1500), 1800, UNSUP(1850), UNSUP(2500),
+	UNSUP(2600), UNSUP(2800), UNSUP(2850), UNSUP(3000),
+	UNSUP(3150), UNSUP(3150), UNSUP(3150), UNSUP(3150),
+};
+static const u16 VSIM_VSEL_table[] = {
+	UNSUP(1000), UNSUP(1200), UNSUP(1300), 1800,
+	2800, 3000, 3000, 3000,
+};
+static const u16 VDAC_VSEL_table[] = {
+	1200, 1300, 1800, 1800,
+};
+
+
+static int twl4030ldo_list_voltage(struct regulator_dev *rdev, unsigned index)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			mV = info->table[index];
+
+	return IS_UNSUP(mV) ? 0 : (LDO_MV(mV) * 1000);
+}
+
+static int
+twl4030ldo_set_voltage(struct regulator_dev *rdev, int min_uV, int max_uV)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			vsel;
+
+	for (vsel = 0; vsel < info->table_len; vsel++) {
+		int mV = info->table[vsel];
+		int uV;
+
+		if (IS_UNSUP(mV))
+			continue;
+		uV = LDO_MV(mV) * 1000;
+
+		/* REVISIT for VAUX2, first match may not be best/lowest */
+
+		/* use the first in-range value */
+		if (min_uV <= uV && uV <= max_uV)
+			return twl4030reg_write(info, VREG_DEDICATED, vsel);
+	}
+
+	return -EDOM;
+}
+
+static int twl4030ldo_get_voltage(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+	int			vsel = twl4030reg_read(info, VREG_DEDICATED);
+
+	if (vsel < 0)
+		return vsel;
+
+	vsel &= info->table_len - 1;
+	return LDO_MV(info->table[vsel]) * 1000;
+}
+
+static struct regulator_ops twl4030ldo_ops = {
+	.list_voltage	= twl4030ldo_list_voltage,
+
+	.set_voltage	= twl4030ldo_set_voltage,
+	.get_voltage	= twl4030ldo_get_voltage,
+
+	.enable		= twl4030reg_enable,
+	.disable	= twl4030reg_disable,
+	.is_enabled	= twl4030reg_is_enabled,
+
+	.set_mode	= twl4030reg_set_mode,
+
+	.get_status	= twl4030reg_get_status,
+};
+
+/*----------------------------------------------------------------------*/
+
+/*
+ * Fixed voltage LDOs don't have a VSEL field to update.
+ */
+static int twl4030fixed_list_voltage(struct regulator_dev *rdev, unsigned index)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+
+	return info->min_mV * 1000;
+}
+
+static int twl4030fixed_get_voltage(struct regulator_dev *rdev)
+{
+	struct twlreg_info	*info = rdev_get_drvdata(rdev);
+
+	return info->min_mV * 1000;
+}
+
+static struct regulator_ops twl4030fixed_ops = {
+	.list_voltage	= twl4030fixed_list_voltage,
+
+	.get_voltage	= twl4030fixed_get_voltage,
+
+	.enable		= twl4030reg_enable,
+	.disable	= twl4030reg_disable,
+	.is_enabled	= twl4030reg_is_enabled,
+
+	.set_mode	= twl4030reg_set_mode,
+
+	.get_status	= twl4030reg_get_status,
+};
+
+/*----------------------------------------------------------------------*/
+
+#define TWL_ADJUSTABLE_LDO(label, offset, num) { \
+	.base = offset, \
+	.id = num, \
+	.table_len = ARRAY_SIZE(label##_VSEL_table), \
+	.table = label##_VSEL_table, \
+	.desc = { \
+		.name = #label, \
+		.id = TWL4030_REG_##label, \
+		.n_voltages = ARRAY_SIZE(label##_VSEL_table), \
+		.ops = &twl4030ldo_ops, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
+#define TWL_FIXED_LDO(label, offset, mVolts, num) { \
+	.base = offset, \
+	.id = num, \
+	.min_mV = mVolts, \
+	.desc = { \
+		.name = #label, \
+		.id = TWL4030_REG_##label, \
+		.n_voltages = 1, \
+		.ops = &twl4030fixed_ops, \
+		.type = REGULATOR_VOLTAGE, \
+		.owner = THIS_MODULE, \
+		}, \
+	}
+
+/*
+ * We list regulators here if systems need some level of
+ * software control over them after boot.
+ */
+static struct twlreg_info twl4030_regs[] = {
+	TWL_ADJUSTABLE_LDO(VAUX1, 0x17, 1),
+	TWL_ADJUSTABLE_LDO(VAUX2_4030, 0x1b, 2),
+	TWL_ADJUSTABLE_LDO(VAUX2, 0x1b, 2),
+	TWL_ADJUSTABLE_LDO(VAUX3, 0x1f, 3),
+	TWL_ADJUSTABLE_LDO(VAUX4, 0x23, 4),
+	TWL_ADJUSTABLE_LDO(VMMC1, 0x27, 5),
+	TWL_ADJUSTABLE_LDO(VMMC2, 0x2b, 6),
+	/*
+	TWL_ADJUSTABLE_LDO(VPLL1, 0x2f, 7),
+	*/
+	TWL_ADJUSTABLE_LDO(VPLL2, 0x33, 8),
+	TWL_ADJUSTABLE_LDO(VSIM, 0x37, 9),
+	TWL_ADJUSTABLE_LDO(VDAC, 0x3b, 10),
+	/*
+	TWL_ADJUSTABLE_LDO(VINTANA1, 0x3f, 11),
+	TWL_ADJUSTABLE_LDO(VINTANA2, 0x43, 12),
+	TWL_ADJUSTABLE_LDO(VINTDIG, 0x47, 13),
+	TWL_SMPS(VIO, 0x4b, 14),
+	TWL_SMPS(VDD1, 0x55, 15),
+	TWL_SMPS(VDD2, 0x63, 16),
+	 */
+	TWL_FIXED_LDO(VUSB1V5, 0x71, 1500, 17),
+	TWL_FIXED_LDO(VUSB1V8, 0x74, 1800, 18),
+	TWL_FIXED_LDO(VUSB3V1, 0x77, 3100, 19),
+	/* VUSBCP is managed *only* by the USB subchip */
+};
+
+static int twl4030reg_probe(struct platform_device *pdev)
+{
+	int				i;
+	struct twlreg_info		*info;
+	struct regulator_init_data	*initdata;
+	struct regulation_constraints	*c;
+	struct regulator_dev		*rdev;
+
+	for (i = 0, info = NULL; i < ARRAY_SIZE(twl4030_regs); i++) {
+		if (twl4030_regs[i].desc.id != pdev->id)
+			continue;
+		info = twl4030_regs + i;
+		break;
+	}
+	if (!info)
+		return -ENODEV;
+
+	initdata = pdev->dev.platform_data;
+	if (!initdata)
+		return -EINVAL;
+
+	/* Constrain board-specific capabilities according to what
+	 * this driver and the chip itself can actually do.
+	 */
+	c = &initdata->constraints;
+	c->valid_modes_mask &= REGULATOR_MODE_NORMAL | REGULATOR_MODE_STANDBY;
+	c->valid_ops_mask &= REGULATOR_CHANGE_VOLTAGE
+				| REGULATOR_CHANGE_MODE
+				| REGULATOR_CHANGE_STATUS;
+
+	rdev = regulator_register(&info->desc, &pdev->dev, initdata, info);
+	if (IS_ERR(rdev)) {
+		dev_err(&pdev->dev, "can't register %s, %ld\n",
+				info->desc.name, PTR_ERR(rdev));
+		return PTR_ERR(rdev);
+	}
+	platform_set_drvdata(pdev, rdev);
+
+	/* NOTE:  many regulators support short-circuit IRQs (presentable
+	 * as REGULATOR_OVER_CURRENT notifications?) configured via:
+	 *  - SC_CONFIG
+	 *  - SC_DETECT1 (vintana2, vmmc1/2, vaux1/2/3/4)
+	 *  - SC_DETECT2 (vusb, vdac, vio, vdd1/2, vpll2)
+	 *  - IT_CONFIG
+	 */
+
+	return 0;
+}
+
+static int __devexit twl4030reg_remove(struct platform_device *pdev)
+{
+	regulator_unregister(platform_get_drvdata(pdev));
+	return 0;
+}
+
+MODULE_ALIAS("platform:twl4030_reg");
+
+static struct platform_driver twl4030reg_driver = {
+	.probe		= twl4030reg_probe,
+	.remove		= __devexit_p(twl4030reg_remove),
+	/* NOTE: short name, to work around driver model truncation of
+	 * "twl4030_regulator.12" (and friends) to "twl4030_regulator.1".
+	 */
+	.driver.name	= "twl4030_reg",
+	.driver.owner	= THIS_MODULE,
+};
+
+static int __init twl4030reg_init(void)
+{
+	return platform_driver_register(&twl4030reg_driver);
+}
+subsys_initcall(twl4030reg_init);
+
+static void __exit twl4030reg_exit(void)
+{
+	platform_driver_unregister(&twl4030reg_driver);
+}
+module_exit(twl4030reg_exit)
+
+MODULE_DESCRIPTION("TWL4030 regulator driver");
+MODULE_LICENSE("GPL");
diff --git a/drivers/regulator/virtual.c b/drivers/regulator/virtual.c
index 5ddb464b1c3f..3d08348584e1 100644
--- a/drivers/regulator/virtual.c
+++ b/drivers/regulator/virtual.c
@@ -226,13 +226,17 @@ static ssize_t set_mode(struct device *dev, struct device_attribute *attr,
 	unsigned int mode;
 	int ret;
 
-	if (strncmp(buf, "fast", strlen("fast")) == 0)
+	/*
+	 * sysfs_streq() doesn't need the \n's, but we add them so the strings
+	 * will be shared with show_mode(), above.
+	 */
+	if (sysfs_streq(buf, "fast\n") == 0)
 		mode = REGULATOR_MODE_FAST;
-	else if (strncmp(buf, "normal", strlen("normal")) == 0)
+	else if (sysfs_streq(buf, "normal\n") == 0)
 		mode = REGULATOR_MODE_NORMAL;
-	else if (strncmp(buf, "idle", strlen("idle")) == 0)
+	else if (sysfs_streq(buf, "idle\n") == 0)
 		mode = REGULATOR_MODE_IDLE;
-	else if (strncmp(buf, "standby", strlen("standby")) == 0)
+	else if (sysfs_streq(buf, "standby\n") == 0)
 		mode = REGULATOR_MODE_STANDBY;
 	else {
 		dev_err(dev, "Configuring invalid mode\n");
@@ -256,7 +260,7 @@ static DEVICE_ATTR(min_microamps, 0666, show_min_uA, set_min_uA);
 static DEVICE_ATTR(max_microamps, 0666, show_max_uA, set_max_uA);
 static DEVICE_ATTR(mode, 0666, show_mode, set_mode);
 
-struct device_attribute *attributes[] = {
+static struct device_attribute *attributes[] = {
 	&dev_attr_min_microvolts,
 	&dev_attr_max_microvolts,
 	&dev_attr_min_microamps,
diff --git a/drivers/regulator/wm8350-regulator.c b/drivers/regulator/wm8350-regulator.c
index 5056e23e4414..771eca1066b5 100644
--- a/drivers/regulator/wm8350-regulator.c
+++ b/drivers/regulator/wm8350-regulator.c
@@ -24,6 +24,9 @@
 #include <linux/regulator/driver.h>
 #include <linux/regulator/machine.h>
 
+/* Maximum value possible for VSEL */
+#define WM8350_DCDC_MAX_VSEL 0x66
+
 /* Microamps */
 static const int isink_cur[] = {
 	4,
@@ -385,6 +388,14 @@ static int wm8350_dcdc_get_voltage(struct regulator_dev *rdev)
 	return wm8350_dcdc_val_to_mvolts(val) * 1000;
 }
 
+static int wm8350_dcdc_list_voltage(struct regulator_dev *rdev,
+				    unsigned selector)
+{
+	if (selector > WM8350_DCDC_MAX_VSEL)
+		return -EINVAL;
+	return wm8350_dcdc_val_to_mvolts(selector) * 1000;
+}
+
 static int wm8350_dcdc_set_suspend_voltage(struct regulator_dev *rdev, int uV)
 {
 	struct wm8350 *wm8350 = rdev_get_drvdata(rdev);
@@ -775,6 +786,14 @@ static int wm8350_ldo_get_voltage(struct regulator_dev *rdev)
 	return wm8350_ldo_val_to_mvolts(val) * 1000;
 }
 
+static int wm8350_ldo_list_voltage(struct regulator_dev *rdev,
+				    unsigned selector)
+{
+	if (selector > WM8350_LDO1_VSEL_MASK)
+		return -EINVAL;
+	return wm8350_ldo_val_to_mvolts(selector) * 1000;
+}
+
 int wm8350_dcdc_set_slot(struct wm8350 *wm8350, int dcdc, u16 start,
 			 u16 stop, u16 fault)
 {
@@ -1031,18 +1050,30 @@ static unsigned int wm8350_dcdc_get_mode(struct regulator_dev *rdev)
 	int dcdc = rdev_get_id(rdev);
 	u16 mask, sleep, active, force;
 	int mode = REGULATOR_MODE_NORMAL;
+	int reg;
 
-	if (dcdc < WM8350_DCDC_1 || dcdc > WM8350_DCDC_6)
-		return -EINVAL;
-
-	if (dcdc == WM8350_DCDC_2 || dcdc == WM8350_DCDC_5)
+	switch (dcdc) {
+	case WM8350_DCDC_1:
+		reg = WM8350_DCDC1_FORCE_PWM;
+		break;
+	case WM8350_DCDC_3:
+		reg = WM8350_DCDC3_FORCE_PWM;
+		break;
+	case WM8350_DCDC_4:
+		reg = WM8350_DCDC4_FORCE_PWM;
+		break;
+	case WM8350_DCDC_6:
+		reg = WM8350_DCDC6_FORCE_PWM;
+		break;
+	default:
 		return -EINVAL;
+	}
 
 	mask = 1 << (dcdc - WM8350_DCDC_1);
 	active = wm8350_reg_read(wm8350, WM8350_DCDC_ACTIVE_OPTIONS) & mask;
+	force = wm8350_reg_read(wm8350, reg) & WM8350_DCDC1_FORCE_PWM_ENA;
 	sleep = wm8350_reg_read(wm8350, WM8350_DCDC_SLEEP_OPTIONS) & mask;
-	force = wm8350_reg_read(wm8350, WM8350_DCDC1_FORCE_PWM)
-	    & WM8350_DCDC1_FORCE_PWM_ENA;
+
 	dev_dbg(wm8350->dev, "mask %x active %x sleep %x force %x",
 		mask, active, sleep, force);
 
@@ -1150,6 +1181,7 @@ static int wm8350_ldo_is_enabled(struct regulator_dev *rdev)
 static struct regulator_ops wm8350_dcdc_ops = {
 	.set_voltage = wm8350_dcdc_set_voltage,
 	.get_voltage = wm8350_dcdc_get_voltage,
+	.list_voltage = wm8350_dcdc_list_voltage,
 	.enable = wm8350_dcdc_enable,
 	.disable = wm8350_dcdc_disable,
 	.get_mode = wm8350_dcdc_get_mode,
@@ -1173,6 +1205,7 @@ static struct regulator_ops wm8350_dcdc2_5_ops = {
 static struct regulator_ops wm8350_ldo_ops = {
 	.set_voltage = wm8350_ldo_set_voltage,
 	.get_voltage = wm8350_ldo_get_voltage,
+	.list_voltage = wm8350_ldo_list_voltage,
 	.enable = wm8350_ldo_enable,
 	.disable = wm8350_ldo_disable,
 	.is_enabled = wm8350_ldo_is_enabled,
@@ -1197,6 +1230,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_dcdc_ops,
 		.irq = WM8350_IRQ_UV_DC1,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_DCDC_MAX_VSEL + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1213,6 +1247,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_dcdc_ops,
 		.irq = WM8350_IRQ_UV_DC3,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_DCDC_MAX_VSEL + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1221,6 +1256,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_dcdc_ops,
 		.irq = WM8350_IRQ_UV_DC4,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_DCDC_MAX_VSEL + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1237,6 +1273,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_dcdc_ops,
 		.irq = WM8350_IRQ_UV_DC6,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_DCDC_MAX_VSEL + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1245,6 +1282,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_ldo_ops,
 		.irq = WM8350_IRQ_UV_LDO1,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_LDO1_VSEL_MASK + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1253,6 +1291,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_ldo_ops,
 		.irq = WM8350_IRQ_UV_LDO2,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_LDO2_VSEL_MASK + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1261,6 +1300,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_ldo_ops,
 		.irq = WM8350_IRQ_UV_LDO3,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_LDO3_VSEL_MASK + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1269,6 +1309,7 @@ static struct regulator_desc wm8350_reg[NUM_WM8350_REGULATORS] = {
 		.ops = &wm8350_ldo_ops,
 		.irq = WM8350_IRQ_UV_LDO4,
 		.type = REGULATOR_VOLTAGE,
+		.n_voltages = WM8350_LDO4_VSEL_MASK + 1,
 		.owner = THIS_MODULE,
 	},
 	{
@@ -1293,6 +1334,7 @@ static void pmic_uv_handler(struct wm8350 *wm8350, int irq, void *data)
 {
 	struct regulator_dev *rdev = (struct regulator_dev *)data;
 
+	mutex_lock(&rdev->mutex);
 	if (irq == WM8350_IRQ_CS1 || irq == WM8350_IRQ_CS2)
 		regulator_notifier_call_chain(rdev,
 					      REGULATOR_EVENT_REGULATION_OUT,
@@ -1301,6 +1343,7 @@ static void pmic_uv_handler(struct wm8350 *wm8350, int irq, void *data)
 		regulator_notifier_call_chain(rdev,
 					      REGULATOR_EVENT_UNDER_VOLTAGE,
 					      wm8350);
+	mutex_unlock(&rdev->mutex);
 }
 
 static int wm8350_regulator_probe(struct platform_device *pdev)
@@ -1333,9 +1376,9 @@ static int wm8350_regulator_probe(struct platform_device *pdev)
 		break;
 	}
 
-
 	/* register regulator */
 	rdev = regulator_register(&wm8350_reg[pdev->id], &pdev->dev,
+				  pdev->dev.platform_data,
 				  dev_get_drvdata(&pdev->dev));
 	if (IS_ERR(rdev)) {
 		dev_err(&pdev->dev, "failed to register %s\n",
diff --git a/drivers/regulator/wm8400-regulator.c b/drivers/regulator/wm8400-regulator.c
index 56e23d44ba59..157426029071 100644
--- a/drivers/regulator/wm8400-regulator.c
+++ b/drivers/regulator/wm8400-regulator.c
@@ -43,6 +43,18 @@ static int wm8400_ldo_disable(struct regulator_dev *dev)
 			       WM8400_LDO1_ENA, 0);
 }
 
+static int wm8400_ldo_list_voltage(struct regulator_dev *dev,
+				   unsigned selector)
+{
+	if (selector > WM8400_LDO1_VSEL_MASK)
+		return -EINVAL;
+
+	if (selector < 15)
+		return 900000 + (selector * 50000);
+	else
+		return 1600000 + ((selector - 14) * 100000);
+}
+
 static int wm8400_ldo_get_voltage(struct regulator_dev *dev)
 {
 	struct wm8400 *wm8400 = rdev_get_drvdata(dev);
@@ -51,10 +63,7 @@ static int wm8400_ldo_get_voltage(struct regulator_dev *dev)
 	val = wm8400_reg_read(wm8400, WM8400_LDO1_CONTROL + rdev_get_id(dev));
 	val &= WM8400_LDO1_VSEL_MASK;
 
-	if (val < 15)
-		return 900000 + (val * 50000);
-	else
-		return 1600000 + ((val - 14) * 100000);
+	return wm8400_ldo_list_voltage(dev, val);
 }
 
 static int wm8400_ldo_set_voltage(struct regulator_dev *dev,
@@ -92,6 +101,7 @@ static struct regulator_ops wm8400_ldo_ops = {
 	.is_enabled = wm8400_ldo_is_enabled,
 	.enable = wm8400_ldo_enable,
 	.disable = wm8400_ldo_disable,
+	.list_voltage = wm8400_ldo_list_voltage,
 	.get_voltage = wm8400_ldo_get_voltage,
 	.set_voltage = wm8400_ldo_set_voltage,
 };
@@ -124,6 +134,15 @@ static int wm8400_dcdc_disable(struct regulator_dev *dev)
 			       WM8400_DC1_ENA, 0);
 }
 
+static int wm8400_dcdc_list_voltage(struct regulator_dev *dev,
+				    unsigned selector)
+{
+	if (selector > WM8400_DC1_VSEL_MASK)
+		return -EINVAL;
+
+	return 850000 + (selector * 25000);
+}
+
 static int wm8400_dcdc_get_voltage(struct regulator_dev *dev)
 {
 	struct wm8400 *wm8400 = rdev_get_drvdata(dev);
@@ -237,6 +256,7 @@ static struct regulator_ops wm8400_dcdc_ops = {
 	.is_enabled = wm8400_dcdc_is_enabled,
 	.enable = wm8400_dcdc_enable,
 	.disable = wm8400_dcdc_disable,
+	.list_voltage = wm8400_dcdc_list_voltage,
 	.get_voltage = wm8400_dcdc_get_voltage,
 	.set_voltage = wm8400_dcdc_set_voltage,
 	.get_mode = wm8400_dcdc_get_mode,
@@ -249,6 +269,7 @@ static struct regulator_desc regulators[] = {
 		.name = "LDO1",
 		.id = WM8400_LDO1,
 		.ops = &wm8400_ldo_ops,
+		.n_voltages = WM8400_LDO1_VSEL_MASK + 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
 	},
@@ -256,6 +277,7 @@ static struct regulator_desc regulators[] = {
 		.name = "LDO2",
 		.id = WM8400_LDO2,
 		.ops = &wm8400_ldo_ops,
+		.n_voltages = WM8400_LDO2_VSEL_MASK + 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
 	},
@@ -263,6 +285,7 @@ static struct regulator_desc regulators[] = {
 		.name = "LDO3",
 		.id = WM8400_LDO3,
 		.ops = &wm8400_ldo_ops,
+		.n_voltages = WM8400_LDO3_VSEL_MASK + 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
 	},
@@ -270,6 +293,7 @@ static struct regulator_desc regulators[] = {
 		.name = "LDO4",
 		.id = WM8400_LDO4,
 		.ops = &wm8400_ldo_ops,
+		.n_voltages = WM8400_LDO4_VSEL_MASK + 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
 	},
@@ -277,6 +301,7 @@ static struct regulator_desc regulators[] = {
 		.name = "DCDC1",
 		.id = WM8400_DCDC1,
 		.ops = &wm8400_dcdc_ops,
+		.n_voltages = WM8400_DC1_VSEL_MASK + 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
 	},
@@ -284,6 +309,7 @@ static struct regulator_desc regulators[] = {
 		.name = "DCDC2",
 		.id = WM8400_DCDC2,
 		.ops = &wm8400_dcdc_ops,
+		.n_voltages = WM8400_DC2_VSEL_MASK + 1,
 		.type = REGULATOR_VOLTAGE,
 		.owner = THIS_MODULE,
 	},
@@ -294,7 +320,7 @@ static int __devinit wm8400_regulator_probe(struct platform_device *pdev)
 	struct regulator_dev *rdev;
 
 	rdev = regulator_register(&regulators[pdev->id], &pdev->dev,
-		pdev->dev.driver_data);
+		pdev->dev.platform_data, pdev->dev.driver_data);
 
 	if (IS_ERR(rdev))
 		return PTR_ERR(rdev);
diff --git a/drivers/rtc/Kconfig b/drivers/rtc/Kconfig
index 09d5cd33a3f6..ffe34a12f446 100644
--- a/drivers/rtc/Kconfig
+++ b/drivers/rtc/Kconfig
@@ -225,11 +225,11 @@ config RTC_DRV_PCF8583
 	  will be called rtc-pcf8583.
 
 config RTC_DRV_M41T80
-	tristate "ST M41T65/M41T80/81/82/83/84/85/87"
+	tristate "ST M41T62/65/M41T80/81/82/83/84/85/87"
 	help
 	  If you say Y here you will get support for the ST M41T60
 	  and M41T80 RTC chips series. Currently, the following chips are
-	  supported: M41T65, M41T80, M41T81, M41T82, M41T83, M41ST84,
+	  supported: M41T62, M41T65, M41T80, M41T81, M41T82, M41T83, M41ST84,
 	  M41ST85, and M41ST87.
 
 	  This driver can also be built as a module. If so, the module
@@ -688,22 +688,16 @@ config RTC_DRV_RS5C313
 	help
 	  If you say yes here you get support for the Ricoh RS5C313 RTC chips.
 
-config RTC_DRV_PARISC
-	tristate "PA-RISC firmware RTC support"
-	depends on PARISC
+config RTC_DRV_GENERIC
+	tristate "Generic RTC support"
+	# Please consider writing a new RTC driver instead of using the generic
+	# RTC abstraction
+	depends on PARISC || M68K || PPC
 	help
-	  Say Y or M here to enable RTC support on PA-RISC systems using
-	  firmware calls. If you do not know what you are doing, you should
+	  Say Y or M here to enable RTC support on systems using the generic
+	  RTC abstraction. If you do not know what you are doing, you should
 	  just say Y.
 
-config RTC_DRV_PPC
-       tristate "PowerPC machine dependent RTC support"
-       depends on PPC
-       help
-	 The PowerPC kernel has machine-specific functions for accessing
-	 the RTC. This exposes that functionality through the generic RTC
-	 class.
-
 config RTC_DRV_PXA
        tristate "PXA27x/PXA3xx"
        depends on ARCH_PXA
@@ -747,4 +741,13 @@ config RTC_DRV_MV
 	  This driver can also be built as a module. If so, the module
 	  will be called rtc-mv.
 
+config RTC_DRV_PS3
+	tristate "PS3 RTC"
+	depends on PPC_PS3
+	help
+	  If you say yes here you will get support for the RTC on PS3.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called rtc-ps3.
+
 endif # RTC_CLASS
diff --git a/drivers/rtc/Makefile b/drivers/rtc/Makefile
index e7b09986d26e..6c0639a14f09 100644
--- a/drivers/rtc/Makefile
+++ b/drivers/rtc/Makefile
@@ -56,8 +56,7 @@ obj-$(CONFIG_RTC_DRV_PCF8563)	+= rtc-pcf8563.o
 obj-$(CONFIG_RTC_DRV_PCF8583)	+= rtc-pcf8583.o
 obj-$(CONFIG_RTC_DRV_PL030)	+= rtc-pl030.o
 obj-$(CONFIG_RTC_DRV_PL031)	+= rtc-pl031.o
-obj-$(CONFIG_RTC_DRV_PARISC)	+= rtc-parisc.o
-obj-$(CONFIG_RTC_DRV_PPC)	+= rtc-ppc.o
+obj-$(CONFIG_RTC_DRV_GENERIC)	+= rtc-generic.o
 obj-$(CONFIG_RTC_DRV_PXA)	+= rtc-pxa.o
 obj-$(CONFIG_RTC_DRV_R9701)	+= rtc-r9701.o
 obj-$(CONFIG_RTC_DRV_RS5C313)	+= rtc-rs5c313.o
@@ -77,3 +76,4 @@ obj-$(CONFIG_RTC_DRV_VR41XX)	+= rtc-vr41xx.o
 obj-$(CONFIG_RTC_DRV_WM8350)	+= rtc-wm8350.o
 obj-$(CONFIG_RTC_DRV_X1205)	+= rtc-x1205.o
 obj-$(CONFIG_RTC_DRV_PCF50633)	+= rtc-pcf50633.o
+obj-$(CONFIG_RTC_DRV_PS3)	+= rtc-ps3.o
diff --git a/drivers/rtc/rtc-generic.c b/drivers/rtc/rtc-generic.c
new file mode 100644
index 000000000000..98322004ad2e
--- /dev/null
+++ b/drivers/rtc/rtc-generic.c
@@ -0,0 +1,84 @@
+/* rtc-generic: RTC driver using the generic RTC abstraction
+ *
+ * Copyright (C) 2008 Kyle McMartin <kyle@mcmartin.ca>
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/time.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+
+#include <asm/rtc.h>
+
+static int generic_get_time(struct device *dev, struct rtc_time *tm)
+{
+	unsigned int ret = get_rtc_time(tm);
+
+	if (ret & RTC_BATT_BAD)
+		return -EOPNOTSUPP;
+
+	return rtc_valid_tm(tm);
+}
+
+static int generic_set_time(struct device *dev, struct rtc_time *tm)
+{
+	if (set_rtc_time(tm) < 0)
+		return -EOPNOTSUPP;
+
+	return 0;
+}
+
+static const struct rtc_class_ops generic_rtc_ops = {
+	.read_time = generic_get_time,
+	.set_time = generic_set_time,
+};
+
+static int __init generic_rtc_probe(struct platform_device *dev)
+{
+	struct rtc_device *rtc;
+
+	rtc = rtc_device_register("rtc-generic", &dev->dev, &generic_rtc_ops,
+				  THIS_MODULE);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	platform_set_drvdata(dev, rtc);
+
+	return 0;
+}
+
+static int __exit generic_rtc_remove(struct platform_device *dev)
+{
+	struct rtc_device *rtc = platform_get_drvdata(dev);
+
+	rtc_device_unregister(rtc);
+
+	return 0;
+}
+
+static struct platform_driver generic_rtc_driver = {
+	.driver = {
+		.name = "rtc-generic",
+		.owner = THIS_MODULE,
+	},
+	.remove = __exit_p(generic_rtc_remove),
+};
+
+static int __init generic_rtc_init(void)
+{
+	return platform_driver_probe(&generic_rtc_driver, generic_rtc_probe);
+}
+
+static void __exit generic_rtc_fini(void)
+{
+	platform_driver_unregister(&generic_rtc_driver);
+}
+
+module_init(generic_rtc_init);
+module_exit(generic_rtc_fini);
+
+MODULE_AUTHOR("Kyle McMartin <kyle@mcmartin.ca>");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("Generic RTC driver");
+MODULE_ALIAS("platform:rtc-generic");
diff --git a/drivers/rtc/rtc-m41t80.c b/drivers/rtc/rtc-m41t80.c
index 893f7dece239..60fe266f0f49 100644
--- a/drivers/rtc/rtc-m41t80.c
+++ b/drivers/rtc/rtc-m41t80.c
@@ -64,10 +64,12 @@
 #define M41T80_FEATURE_BL	(1 << 1)	/* Battery low indicator */
 #define M41T80_FEATURE_SQ	(1 << 2)	/* Squarewave feature */
 #define M41T80_FEATURE_WD	(1 << 3)	/* Extra watchdog resolution */
+#define M41T80_FEATURE_SQ_ALT	(1 << 4)	/* RSx bits are in reg 4 */
 
 #define DRV_VERSION "0.05"
 
 static const struct i2c_device_id m41t80_id[] = {
+	{ "m41t62", M41T80_FEATURE_SQ | M41T80_FEATURE_SQ_ALT },
 	{ "m41t65", M41T80_FEATURE_HT | M41T80_FEATURE_WD },
 	{ "m41t80", M41T80_FEATURE_SQ },
 	{ "m41t81", M41T80_FEATURE_HT | M41T80_FEATURE_SQ},
@@ -393,12 +395,15 @@ static ssize_t m41t80_sysfs_show_sqwfreq(struct device *dev,
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct m41t80_data *clientdata = i2c_get_clientdata(client);
-	int val;
+	int val, reg_sqw;
 
 	if (!(clientdata->features & M41T80_FEATURE_SQ))
 		return -EINVAL;
 
-	val = i2c_smbus_read_byte_data(client, M41T80_REG_SQW);
+	reg_sqw = M41T80_REG_SQW;
+	if (clientdata->features & M41T80_FEATURE_SQ_ALT)
+		reg_sqw = M41T80_REG_WDAY;
+	val = i2c_smbus_read_byte_data(client, reg_sqw);
 	if (val < 0)
 		return -EIO;
 	val = (val >> 4) & 0xf;
@@ -419,7 +424,7 @@ static ssize_t m41t80_sysfs_set_sqwfreq(struct device *dev,
 {
 	struct i2c_client *client = to_i2c_client(dev);
 	struct m41t80_data *clientdata = i2c_get_clientdata(client);
-	int almon, sqw;
+	int almon, sqw, reg_sqw;
 	int val = simple_strtoul(buf, NULL, 0);
 
 	if (!(clientdata->features & M41T80_FEATURE_SQ))
@@ -440,13 +445,16 @@ static ssize_t m41t80_sysfs_set_sqwfreq(struct device *dev,
 	almon = i2c_smbus_read_byte_data(client, M41T80_REG_ALARM_MON);
 	if (almon < 0)
 		return -EIO;
-	sqw = i2c_smbus_read_byte_data(client, M41T80_REG_SQW);
+	reg_sqw = M41T80_REG_SQW;
+	if (clientdata->features & M41T80_FEATURE_SQ_ALT)
+		reg_sqw = M41T80_REG_WDAY;
+	sqw = i2c_smbus_read_byte_data(client, reg_sqw);
 	if (sqw < 0)
 		return -EIO;
 	sqw = (sqw & 0x0f) | (val << 4);
 	if (i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON,
 				      almon & ~M41T80_ALMON_SQWE) < 0 ||
-	    i2c_smbus_write_byte_data(client, M41T80_REG_SQW, sqw) < 0)
+	    i2c_smbus_write_byte_data(client, reg_sqw, sqw) < 0)
 		return -EIO;
 	if (val && i2c_smbus_write_byte_data(client, M41T80_REG_ALARM_MON,
 					     almon | M41T80_ALMON_SQWE) < 0)
diff --git a/drivers/rtc/rtc-parisc.c b/drivers/rtc/rtc-parisc.c
deleted file mode 100644
index b966f56da976..000000000000
--- a/drivers/rtc/rtc-parisc.c
+++ /dev/null
@@ -1,86 +0,0 @@
-/* rtc-parisc: RTC for HP PA-RISC firmware
- *
- * Copyright (C) 2008 Kyle McMartin <kyle@mcmartin.ca>
- */
-
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/time.h>
-#include <linux/platform_device.h>
-#include <linux/rtc.h>
-
-#include <asm/rtc.h>
-
-static int parisc_get_time(struct device *dev, struct rtc_time *tm)
-{
-	unsigned long ret;
-
-	ret = get_rtc_time(tm);
-
-	if (ret & RTC_BATT_BAD)
-		return -EOPNOTSUPP;
-
-	return rtc_valid_tm(tm);
-}
-
-static int parisc_set_time(struct device *dev, struct rtc_time *tm)
-{
-	if (set_rtc_time(tm) < 0)
-		return -EOPNOTSUPP;
-
-	return 0;
-}
-
-static const struct rtc_class_ops parisc_rtc_ops = {
-	.read_time = parisc_get_time,
-	.set_time = parisc_set_time,
-};
-
-static int __init parisc_rtc_probe(struct platform_device *dev)
-{
-	struct rtc_device *rtc;
-
-	rtc = rtc_device_register("rtc-parisc", &dev->dev, &parisc_rtc_ops,
-				  THIS_MODULE);
-	if (IS_ERR(rtc))
-		return PTR_ERR(rtc);
-
-	platform_set_drvdata(dev, rtc);
-
-	return 0;
-}
-
-static int __exit parisc_rtc_remove(struct platform_device *dev)
-{
-	struct rtc_device *rtc = platform_get_drvdata(dev);
-
-	rtc_device_unregister(rtc);
-
-	return 0;
-}
-
-static struct platform_driver parisc_rtc_driver = {
-	.driver = {
-		.name = "rtc-parisc",
-		.owner = THIS_MODULE,
-	},
-	.probe = parisc_rtc_probe,
-	.remove = __devexit_p(parisc_rtc_remove),
-};
-
-static int __init parisc_rtc_init(void)
-{
-	return platform_driver_probe(&parisc_rtc_driver, parisc_rtc_probe);
-}
-
-static void __exit parisc_rtc_fini(void)
-{
-	platform_driver_unregister(&parisc_rtc_driver);
-}
-
-module_init(parisc_rtc_init);
-module_exit(parisc_rtc_fini);
-
-MODULE_AUTHOR("Kyle McMartin <kyle@mcmartin.ca>");
-MODULE_LICENSE("GPL");
-MODULE_DESCRIPTION("HP PA-RISC RTC driver");
diff --git a/drivers/rtc/rtc-ppc.c b/drivers/rtc/rtc-ppc.c
deleted file mode 100644
index c8e97e25ef7e..000000000000
--- a/drivers/rtc/rtc-ppc.c
+++ /dev/null
@@ -1,69 +0,0 @@
-/*
- * RTC driver for ppc_md RTC functions
- *
- * © 2007 Red Hat, Inc.
- *
- * Author: David Woodhouse <dwmw2@infradead.org>
- *
- * This program is free software; you can redistribute it and/or modify
- * it under the terms of the GNU General Public License version 2 as
- * published by the Free Software Foundation.
- */
-
-
-#include <linux/module.h>
-#include <linux/err.h>
-#include <linux/rtc.h>
-#include <linux/platform_device.h>
-#include <asm/machdep.h>
-
-static int ppc_rtc_read_time(struct device *dev, struct rtc_time *tm)
-{
-	ppc_md.get_rtc_time(tm);
-	return 0;
-}
-
-static int ppc_rtc_set_time(struct device *dev, struct rtc_time *tm)
-{
-	return ppc_md.set_rtc_time(tm);
-}
-
-static const struct rtc_class_ops ppc_rtc_ops = {
-	.set_time = ppc_rtc_set_time,
-	.read_time = ppc_rtc_read_time,
-};
-
-static struct rtc_device *rtc;
-static struct platform_device *ppc_rtc_pdev;
-
-static int __init ppc_rtc_init(void)
-{
-	if (!ppc_md.get_rtc_time || !ppc_md.set_rtc_time)
-		return -ENODEV;
-
-	ppc_rtc_pdev = platform_device_register_simple("ppc-rtc", 0, NULL, 0);
-	if (IS_ERR(ppc_rtc_pdev))
-		return PTR_ERR(ppc_rtc_pdev);
-
-	rtc = rtc_device_register("ppc_md", &ppc_rtc_pdev->dev,
-				  &ppc_rtc_ops, THIS_MODULE);
-	if (IS_ERR(rtc)) {
-		platform_device_unregister(ppc_rtc_pdev);
-		return PTR_ERR(rtc);
-	}
-
-	return 0;
-}
-
-static void __exit ppc_rtc_exit(void)
-{
-	rtc_device_unregister(rtc);
-	platform_device_unregister(ppc_rtc_pdev);
-}
-
-module_init(ppc_rtc_init);
-module_exit(ppc_rtc_exit);
-
-MODULE_LICENSE("GPL");
-MODULE_AUTHOR("David Woodhouse <dwmw2@infradead.org>");
-MODULE_DESCRIPTION("Generic RTC class driver for PowerPC");
diff --git a/drivers/rtc/rtc-ps3.c b/drivers/rtc/rtc-ps3.c
new file mode 100644
index 000000000000..968133ce1ee8
--- /dev/null
+++ b/drivers/rtc/rtc-ps3.c
@@ -0,0 +1,104 @@
+/*
+ * PS3 RTC Driver
+ *
+ * Copyright 2009 Sony Corporation
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; version 2 of the License.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program.
+ * If not, see <http://www.gnu.org/licenses/>.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/rtc.h>
+
+#include <asm/lv1call.h>
+#include <asm/ps3.h>
+
+
+static u64 read_rtc(void)
+{
+	int result;
+	u64 rtc_val;
+	u64 tb_val;
+
+	result = lv1_get_rtc(&rtc_val, &tb_val);
+	BUG_ON(result);
+
+	return rtc_val;
+}
+
+static int ps3_get_time(struct device *dev, struct rtc_time *tm)
+{
+	rtc_time_to_tm(read_rtc() + ps3_os_area_get_rtc_diff(), tm);
+	return rtc_valid_tm(tm);
+}
+
+static int ps3_set_time(struct device *dev, struct rtc_time *tm)
+{
+	unsigned long now;
+
+	rtc_tm_to_time(tm, &now);
+	ps3_os_area_set_rtc_diff(now - read_rtc());
+	return 0;
+}
+
+static const struct rtc_class_ops ps3_rtc_ops = {
+	.read_time = ps3_get_time,
+	.set_time = ps3_set_time,
+};
+
+static int __init ps3_rtc_probe(struct platform_device *dev)
+{
+	struct rtc_device *rtc;
+
+	rtc = rtc_device_register("rtc-ps3", &dev->dev, &ps3_rtc_ops,
+				  THIS_MODULE);
+	if (IS_ERR(rtc))
+		return PTR_ERR(rtc);
+
+	platform_set_drvdata(dev, rtc);
+	return 0;
+}
+
+static int __exit ps3_rtc_remove(struct platform_device *dev)
+{
+	rtc_device_unregister(platform_get_drvdata(dev));
+	return 0;
+}
+
+static struct platform_driver ps3_rtc_driver = {
+	.driver = {
+		.name = "rtc-ps3",
+		.owner = THIS_MODULE,
+	},
+	.remove = __exit_p(ps3_rtc_remove),
+};
+
+static int __init ps3_rtc_init(void)
+{
+	return platform_driver_probe(&ps3_rtc_driver, ps3_rtc_probe);
+}
+
+static void __exit ps3_rtc_fini(void)
+{
+	platform_driver_unregister(&ps3_rtc_driver);
+}
+
+module_init(ps3_rtc_init);
+module_exit(ps3_rtc_fini);
+
+MODULE_AUTHOR("Sony Corporation");
+MODULE_LICENSE("GPL");
+MODULE_DESCRIPTION("ps3 RTC driver");
+MODULE_ALIAS("platform:rtc-ps3");
diff --git a/drivers/rtc/rtc-v3020.c b/drivers/rtc/rtc-v3020.c
index 66955cc9c746..ad164056feb6 100644
--- a/drivers/rtc/rtc-v3020.c
+++ b/drivers/rtc/rtc-v3020.c
@@ -27,17 +27,162 @@
 #include <linux/bcd.h>
 #include <linux/rtc-v3020.h>
 #include <linux/delay.h>
+#include <linux/gpio.h>
 
 #include <linux/io.h>
 
 #undef DEBUG
 
+struct v3020;
+
+struct v3020_chip_ops {
+	int (*map_io)(struct v3020 *chip, struct platform_device *pdev,
+		      struct v3020_platform_data *pdata);
+	void (*unmap_io)(struct v3020 *chip);
+	unsigned char (*read_bit)(struct v3020 *chip);
+	void (*write_bit)(struct v3020 *chip, unsigned char bit);
+};
+
+#define V3020_CS	0
+#define V3020_WR	1
+#define V3020_RD	2
+#define V3020_IO	3
+
+struct v3020_gpio {
+	const char *name;
+	unsigned int gpio;
+};
+
 struct v3020 {
+	/* MMIO access */
 	void __iomem *ioaddress;
 	int leftshift;
+
+	/* GPIO access */
+	struct v3020_gpio *gpio;
+
+	struct v3020_chip_ops *ops;
+
 	struct rtc_device *rtc;
 };
 
+
+static int v3020_mmio_map(struct v3020 *chip, struct platform_device *pdev,
+			  struct v3020_platform_data *pdata)
+{
+	if (pdev->num_resources != 1)
+		return -EBUSY;
+
+	if (pdev->resource[0].flags != IORESOURCE_MEM)
+		return -EBUSY;
+
+	chip->leftshift = pdata->leftshift;
+	chip->ioaddress = ioremap(pdev->resource[0].start, 1);
+	if (chip->ioaddress == NULL)
+		return -EBUSY;
+
+	return 0;
+}
+
+static void v3020_mmio_unmap(struct v3020 *chip)
+{
+	iounmap(chip->ioaddress);
+}
+
+static void v3020_mmio_write_bit(struct v3020 *chip, unsigned char bit)
+{
+	writel(bit << chip->leftshift, chip->ioaddress);
+}
+
+static unsigned char v3020_mmio_read_bit(struct v3020 *chip)
+{
+	return readl(chip->ioaddress) & (1 << chip->leftshift);
+}
+
+static struct v3020_chip_ops v3020_mmio_ops = {
+	.map_io		= v3020_mmio_map,
+	.unmap_io	= v3020_mmio_unmap,
+	.read_bit	= v3020_mmio_read_bit,
+	.write_bit	= v3020_mmio_write_bit,
+};
+
+static struct v3020_gpio v3020_gpio[] = {
+	{ "RTC CS", 0 },
+	{ "RTC WR", 0 },
+	{ "RTC RD", 0 },
+	{ "RTC IO", 0 },
+};
+
+static int v3020_gpio_map(struct v3020 *chip, struct platform_device *pdev,
+			  struct v3020_platform_data *pdata)
+{
+	int i, err;
+
+	v3020_gpio[V3020_CS].gpio = pdata->gpio_cs;
+	v3020_gpio[V3020_WR].gpio = pdata->gpio_wr;
+	v3020_gpio[V3020_RD].gpio = pdata->gpio_rd;
+	v3020_gpio[V3020_IO].gpio = pdata->gpio_io;
+
+	for (i = 0; i < ARRAY_SIZE(v3020_gpio); i++) {
+		err = gpio_request(v3020_gpio[i].gpio, v3020_gpio[i].name);
+		if (err)
+			goto err_request;
+
+		gpio_direction_output(v3020_gpio[i].gpio, 1);
+	}
+
+	chip->gpio = v3020_gpio;
+
+	return 0;
+
+err_request:
+	while (--i >= 0)
+		gpio_free(v3020_gpio[i].gpio);
+
+	return err;
+}
+
+static void v3020_gpio_unmap(struct v3020 *chip)
+{
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(v3020_gpio); i++)
+		gpio_free(v3020_gpio[i].gpio);
+}
+
+static void v3020_gpio_write_bit(struct v3020 *chip, unsigned char bit)
+{
+	gpio_direction_output(chip->gpio[V3020_IO].gpio, bit);
+	gpio_set_value(chip->gpio[V3020_CS].gpio, 0);
+	gpio_set_value(chip->gpio[V3020_WR].gpio, 0);
+	udelay(1);
+	gpio_set_value(chip->gpio[V3020_WR].gpio, 1);
+	gpio_set_value(chip->gpio[V3020_CS].gpio, 1);
+}
+
+static unsigned char v3020_gpio_read_bit(struct v3020 *chip)
+{
+	int bit;
+
+	gpio_direction_input(chip->gpio[V3020_IO].gpio);
+	gpio_set_value(chip->gpio[V3020_CS].gpio, 0);
+	gpio_set_value(chip->gpio[V3020_RD].gpio, 0);
+	udelay(1);
+	bit = !!gpio_get_value(chip->gpio[V3020_IO].gpio);
+	udelay(1);
+	gpio_set_value(chip->gpio[V3020_RD].gpio, 1);
+	gpio_set_value(chip->gpio[V3020_CS].gpio, 1);
+
+	return bit;
+}
+
+static struct v3020_chip_ops v3020_gpio_ops = {
+	.map_io		= v3020_gpio_map,
+	.unmap_io	= v3020_gpio_unmap,
+	.read_bit	= v3020_gpio_read_bit,
+	.write_bit	= v3020_gpio_write_bit,
+};
+
 static void v3020_set_reg(struct v3020 *chip, unsigned char address,
 			unsigned char data)
 {
@@ -46,7 +191,7 @@ static void v3020_set_reg(struct v3020 *chip, unsigned char address,
 
 	tmp = address;
 	for (i = 0; i < 4; i++) {
-		writel((tmp & 1) << chip->leftshift, chip->ioaddress);
+		chip->ops->write_bit(chip, (tmp & 1));
 		tmp >>= 1;
 		udelay(1);
 	}
@@ -54,7 +199,7 @@ static void v3020_set_reg(struct v3020 *chip, unsigned char address,
 	/* Commands dont have data */
 	if (!V3020_IS_COMMAND(address)) {
 		for (i = 0; i < 8; i++) {
-			writel((data & 1) << chip->leftshift, chip->ioaddress);
+			chip->ops->write_bit(chip, (data & 1));
 			data >>= 1;
 			udelay(1);
 		}
@@ -67,14 +212,14 @@ static unsigned char v3020_get_reg(struct v3020 *chip, unsigned char address)
 	int i;
 
 	for (i = 0; i < 4; i++) {
-		writel((address & 1) << chip->leftshift, chip->ioaddress);
+		chip->ops->write_bit(chip, (address & 1));
 		address >>= 1;
 		udelay(1);
 	}
 
 	for (i = 0; i < 8; i++) {
 		data >>= 1;
-		if (readl(chip->ioaddress) & (1 << chip->leftshift))
+		if (chip->ops->read_bit(chip))
 			data |= 0x80;
 		udelay(1);
 	}
@@ -164,25 +309,23 @@ static int rtc_probe(struct platform_device *pdev)
 	int i;
 	int temp;
 
-	if (pdev->num_resources != 1)
-		return -EBUSY;
-
-	if (pdev->resource[0].flags != IORESOURCE_MEM)
-		return -EBUSY;
-
 	chip = kzalloc(sizeof *chip, GFP_KERNEL);
 	if (!chip)
 		return -ENOMEM;
 
-	chip->leftshift = pdata->leftshift;
-	chip->ioaddress = ioremap(pdev->resource[0].start, 1);
-	if (chip->ioaddress == NULL)
+	if (pdata->use_gpio)
+		chip->ops = &v3020_gpio_ops;
+	else
+		chip->ops = &v3020_mmio_ops;
+
+	retval = chip->ops->map_io(chip, pdev, pdata);
+	if (retval)
 		goto err_chip;
 
 	/* Make sure the v3020 expects a communication cycle
 	 * by reading 8 times */
 	for (i = 0; i < 8; i++)
-		temp = readl(chip->ioaddress);
+		temp = chip->ops->read_bit(chip);
 
 	/* Test chip by doing a write/read sequence
 	 * to the chip ram */
@@ -196,10 +339,17 @@ static int rtc_probe(struct platform_device *pdev)
 	 * are all disabled */
 	v3020_set_reg(chip, V3020_STATUS_0, 0x0);
 
-	dev_info(&pdev->dev, "Chip available at physical address 0x%llx,"
-		"data connected to D%d\n",
-		(unsigned long long)pdev->resource[0].start,
-		chip->leftshift);
+	if (pdata->use_gpio)
+		dev_info(&pdev->dev, "Chip available at GPIOs "
+			 "%d, %d, %d, %d\n",
+			 chip->gpio[V3020_CS].gpio, chip->gpio[V3020_WR].gpio,
+			 chip->gpio[V3020_RD].gpio, chip->gpio[V3020_IO].gpio);
+	else
+		dev_info(&pdev->dev, "Chip available at "
+			 "physical address 0x%llx,"
+			 "data connected to D%d\n",
+			 (unsigned long long)pdev->resource[0].start,
+			 chip->leftshift);
 
 	platform_set_drvdata(pdev, chip);
 
@@ -214,7 +364,7 @@ static int rtc_probe(struct platform_device *pdev)
 	return 0;
 
 err_io:
-	iounmap(chip->ioaddress);
+	chip->ops->unmap_io(chip);
 err_chip:
 	kfree(chip);
 
@@ -229,7 +379,7 @@ static int rtc_remove(struct platform_device *dev)
 	if (rtc)
 		rtc_device_unregister(rtc);
 
-	iounmap(chip->ioaddress);
+	chip->ops->unmap_io(chip);
 	kfree(chip);
 
 	return 0;
diff --git a/drivers/s390/net/qeth_core_offl.c b/drivers/s390/net/qeth_core_offl.c
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/drivers/s390/net/qeth_core_offl.c
+++ /dev/null
diff --git a/drivers/s390/net/qeth_core_offl.h b/drivers/s390/net/qeth_core_offl.h
deleted file mode 100644
index e69de29bb2d1..000000000000
--- a/drivers/s390/net/qeth_core_offl.h
+++ /dev/null
diff --git a/drivers/s390/scsi/zfcp_fc.c b/drivers/s390/scsi/zfcp_fc.c
index aab8123c5966..e8d032b9dfbd 100644
--- a/drivers/s390/scsi/zfcp_fc.c
+++ b/drivers/s390/scsi/zfcp_fc.c
@@ -94,7 +94,7 @@ static int zfcp_wka_port_get(struct zfcp_wka_port *wka_port)
 
 static void zfcp_wka_port_offline(struct work_struct *work)
 {
-	struct delayed_work *dw = container_of(work, struct delayed_work, work);
+	struct delayed_work *dw = to_delayed_work(work);
 	struct zfcp_wka_port *wka_port =
 			container_of(dw, struct zfcp_wka_port, work);
 
diff --git a/drivers/scsi/Kconfig b/drivers/scsi/Kconfig
index e2f44e6c0bcb..20297c521e50 100644
--- a/drivers/scsi/Kconfig
+++ b/drivers/scsi/Kconfig
@@ -1380,7 +1380,7 @@ config SCSI_LPFC_DEBUG_FS
 	bool "Emulex LightPulse Fibre Channel debugfs Support"
 	depends on SCSI_LPFC && DEBUG_FS
 	help
-	  This makes debugging infomation from the lpfc driver
+	  This makes debugging information from the lpfc driver
 	  available via the debugfs filesystem.
 
 config SCSI_SIM710
@@ -1388,7 +1388,7 @@ config SCSI_SIM710
 	depends on (EISA || MCA) && SCSI
 	select SCSI_SPI_ATTRS
 	---help---
-	  This driver for NCR53c710 based SCSI host adapters.
+	  This driver is for NCR53c710 based SCSI host adapters.
 
 	  It currently supports Compaq EISA cards and NCR MCA cards
 
diff --git a/drivers/serial/Kconfig b/drivers/serial/Kconfig
index 9be11b0963f2..aa9d3a4c2d50 100644
--- a/drivers/serial/Kconfig
+++ b/drivers/serial/Kconfig
@@ -1374,7 +1374,7 @@ config SERIAL_BFIN_SPORT
 	depends on BLACKFIN && EXPERIMENTAL
 	select SERIAL_CORE
 	help
-	  Enble support SPORT emulate UART on Blackfin series.
+	  Enable SPORT emulate UART on Blackfin series.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called bfin_sport_uart.
diff --git a/drivers/serial/mcf.c b/drivers/serial/mcf.c
index 56841fe5f483..0eefb07bebaf 100644
--- a/drivers/serial/mcf.c
+++ b/drivers/serial/mcf.c
@@ -513,7 +513,7 @@ static int __init mcf_console_setup(struct console *co, char *options)
 	int parity = 'n';
 	int flow = 'n';
 
-	if ((co->index >= 0) && (co->index <= MCF_MAXPORTS))
+	if ((co->index < 0) || (co->index >= MCF_MAXPORTS))
 		co->index = 0;
 	port = &mcf_ports[co->index].port;
 	if (port->membase == 0)
diff --git a/drivers/serial/serial_core.c b/drivers/serial/serial_core.c
index bf3c0e32a334..b0bb29d804ae 100644
--- a/drivers/serial/serial_core.c
+++ b/drivers/serial/serial_core.c
@@ -1765,7 +1765,7 @@ static void uart_line_info(struct seq_file *m, struct uart_driver *drv, int i)
 
 static int uart_proc_show(struct seq_file *m, void *v)
 {
-	struct tty_driver *ttydrv = v;
+	struct tty_driver *ttydrv = m->private;
 	struct uart_driver *drv = ttydrv->driver_state;
 	int i;
 
diff --git a/drivers/spi/spi_gpio.c b/drivers/spi/spi_gpio.c
index d2866c293dee..26bd03e61855 100644
--- a/drivers/spi/spi_gpio.c
+++ b/drivers/spi/spi_gpio.c
@@ -178,8 +178,10 @@ static void spi_gpio_chipselect(struct spi_device *spi, int is_active)
 	if (is_active)
 		setsck(spi, spi->mode & SPI_CPOL);
 
-	/* SPI is normally active-low */
-	gpio_set_value(cs, (spi->mode & SPI_CS_HIGH) ? is_active : !is_active);
+	if (cs != SPI_GPIO_NO_CHIPSELECT) {
+		/* SPI is normally active-low */
+		gpio_set_value(cs, (spi->mode & SPI_CS_HIGH) ? is_active : !is_active);
+	}
 }
 
 static int spi_gpio_setup(struct spi_device *spi)
@@ -191,15 +193,17 @@ static int spi_gpio_setup(struct spi_device *spi)
 		return -EINVAL;
 
 	if (!spi->controller_state) {
-		status = gpio_request(cs, dev_name(&spi->dev));
-		if (status)
-			return status;
-		status = gpio_direction_output(cs, spi->mode & SPI_CS_HIGH);
+		if (cs != SPI_GPIO_NO_CHIPSELECT) {
+			status = gpio_request(cs, dev_name(&spi->dev));
+			if (status)
+				return status;
+			status = gpio_direction_output(cs, spi->mode & SPI_CS_HIGH);
+		}
 	}
 	if (!status)
 		status = spi_bitbang_setup(spi);
 	if (status) {
-		if (!spi->controller_state)
+		if (!spi->controller_state && cs != SPI_GPIO_NO_CHIPSELECT)
 			gpio_free(cs);
 	}
 	return status;
@@ -209,7 +213,8 @@ static void spi_gpio_cleanup(struct spi_device *spi)
 {
 	unsigned long	cs = (unsigned long) spi->controller_data;
 
-	gpio_free(cs);
+	if (cs != SPI_GPIO_NO_CHIPSELECT)
+		gpio_free(cs);
 	spi_bitbang_cleanup(spi);
 }
 
diff --git a/drivers/staging/Kconfig b/drivers/staging/Kconfig
index 211af86a6c55..92981c2383ee 100644
--- a/drivers/staging/Kconfig
+++ b/drivers/staging/Kconfig
@@ -4,7 +4,7 @@ menuconfig STAGING
 	---help---
 	  This option allows you to select a number of drivers that are
 	  not of the "normal" Linux kernel quality level.  These drivers
-	  are placed here in order to get a wider audience for use of
+	  are placed here in order to get a wider audience to make use of
 	  them.  Please note that these drivers are under heavy
 	  development, may or may not work, and may contain userspace
 	  interfaces that most likely will be changed in the near
@@ -12,7 +12,7 @@ menuconfig STAGING
 
 	  Using any of these drivers will taint your kernel which might
 	  affect support options from both the community, and various
-	  commercial support orginizations.
+	  commercial support organizations.
 
 	  If you wish to work on these drivers, to help improve them, or
 	  to report problems you have with them, please see the
diff --git a/drivers/staging/comedi/Kconfig b/drivers/staging/comedi/Kconfig
index b47ca1e7e383..83a93a5c6392 100644
--- a/drivers/staging/comedi/Kconfig
+++ b/drivers/staging/comedi/Kconfig
@@ -1,9 +1,9 @@
 config COMEDI
-	tristate "Data Acquision support (comedi)"
+	tristate "Data acquisition support (comedi)"
 	default N
 	depends on m
 	---help---
-	  Enable support a wide range of data acquision devices
+	  Enable support a wide range of data acquisition devices
 	  for Linux.
 
 config COMEDI_RT
diff --git a/drivers/staging/go7007/Kconfig b/drivers/staging/go7007/Kconfig
index f2cf7f66ae05..ca6ade6c4b47 100644
--- a/drivers/staging/go7007/Kconfig
+++ b/drivers/staging/go7007/Kconfig
@@ -10,7 +10,7 @@ config VIDEO_GO7007
 	select CRC32
 	default N
 	---help---
-	  This is a video4linux driver for some wierd device...
+	  This is a video4linux driver for some weird device...
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called go7007
@@ -20,7 +20,7 @@ config VIDEO_GO7007_USB
 	depends on VIDEO_GO7007 && USB
 	default N
 	---help---
-	  This is a video4linux driver for some wierd device...
+	  This is a video4linux driver for some weird device...
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called go7007-usb
diff --git a/drivers/staging/otus/hal/hpmain.c b/drivers/staging/otus/hal/hpmain.c
index 2e65c466aae8..dab278326931 100644
--- a/drivers/staging/otus/hal/hpmain.c
+++ b/drivers/staging/otus/hal/hpmain.c
@@ -152,7 +152,7 @@ u16_t zfHpInit(zdev_t* dev, u32_t frequency)
     else
     {
     #ifndef ZM_OTUS_LINUX_PHASE_2
-        /* donwload the normal frimware */
+        /* download the normal firmware */
         if ((ret = zfFirmwareDownload(dev, (u32_t*)zcFwImage,
                 (u32_t)zcFwImageSize, ZM_FIRMWARE_WLAN_ADDR)) != ZM_SUCCESS)
         {
diff --git a/drivers/staging/panel/Kconfig b/drivers/staging/panel/Kconfig
index c4b30f2a549b..3abe7c9d558d 100644
--- a/drivers/staging/panel/Kconfig
+++ b/drivers/staging/panel/Kconfig
@@ -110,7 +110,7 @@ config PANEL_LCD_BWIDTH
 	---help---
 	  Most LCDs use a standard controller which supports hardware lines of 40
 	  characters, although sometimes only 16, 20 or 24 of them are really wired
-	  to the terminal. This results in some non-visible but adressable characters,
+	  to the terminal. This results in some non-visible but addressable characters,
 	  and is the case for most parallel LCDs. Other LCDs, and some serial ones,
 	  however, use the same line width internally as what is visible. The KS0074
 	  for example, uses 16 characters per line for 16 visible characters per line.
diff --git a/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c b/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c
index e5752f615e09..80f9cc7137c2 100644
--- a/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c
+++ b/drivers/staging/rtl8187se/ieee80211/ieee80211_softmac.c
@@ -719,7 +719,7 @@ void ieee80211_softmac_scan(struct ieee80211_device *ieee)
 #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20))
 void ieee80211_softmac_scan_wq(struct work_struct *work)
 {
-	struct delayed_work *dwork = container_of(work, struct delayed_work, work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct ieee80211_device *ieee = container_of(dwork, struct ieee80211_device, softmac_scan_wq);
 #else
 void ieee80211_softmac_scan_wq(struct ieee80211_device *ieee)
@@ -777,7 +777,7 @@ out:
 #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20))
 void ieee80211_softmac_scan_wq(struct work_struct *work)
 {
-        struct delayed_work *dwork = container_of(work, struct delayed_work, work);
+	struct delayed_work *dwork = to_delayed_work(work);
         struct ieee80211_device *ieee = container_of(work, struct ieee80211_device, softmac_scan_wq);
 #else
 void ieee80211_softmac_scan_wq(struct ieee80211_device *ieee)
@@ -2980,7 +2980,7 @@ void ieee80211_start_monitor_mode(struct ieee80211_device *ieee)
 #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20))
 void ieee80211_start_ibss_wq(struct work_struct *work)
 {
-	struct delayed_work *dwork = container_of(work, struct delayed_work, work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct ieee80211_device *ieee = container_of(dwork, struct ieee80211_device, start_ibss_wq);
 #else
 void ieee80211_start_ibss_wq(struct ieee80211_device *ieee)
@@ -3162,7 +3162,7 @@ void ieee80211_disassociate(struct ieee80211_device *ieee)
 #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20))
 void ieee80211_associate_retry_wq(struct work_struct *work)
 {
-	struct delayed_work *dwork = container_of(work, struct delayed_work, work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct ieee80211_device *ieee = container_of(dwork, struct ieee80211_device, associate_retry_wq);
 #else
 void ieee80211_associate_retry_wq(struct ieee80211_device *ieee)
diff --git a/drivers/staging/rtl8187se/r8180_core.c b/drivers/staging/rtl8187se/r8180_core.c
index 66de5cc8ddf1..ff1f23f99f27 100644
--- a/drivers/staging/rtl8187se/r8180_core.c
+++ b/drivers/staging/rtl8187se/r8180_core.c
@@ -5438,7 +5438,7 @@ void rtl8180_hw_wakeup_wq (struct work_struct *work)
 //	struct r8180_priv *priv = container_of(work, struct r8180_priv, watch_dog_wq);
 //	struct ieee80211_device * ieee = (struct ieee80211_device*)
 //	                                       container_of(work, struct ieee80211_device, watch_dog_wq);
-	struct delayed_work *dwork = container_of(work,struct delayed_work,work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct ieee80211_device *ieee = container_of(dwork,struct ieee80211_device,hw_wakeup_wq);
 	struct net_device *dev = ieee->dev;
 #else
@@ -5459,7 +5459,7 @@ void rtl8180_hw_sleep_wq (struct work_struct *work)
 //      struct r8180_priv *priv = container_of(work, struct r8180_priv, watch_dog_wq);
 //      struct ieee80211_device * ieee = (struct ieee80211_device*)
 //                                             container_of(work, struct ieee80211_device, watch_dog_wq);
-        struct delayed_work *dwork = container_of(work,struct delayed_work,work);
+	struct delayed_work *dwork = to_delayed_work(work);
         struct ieee80211_device *ieee = container_of(dwork,struct ieee80211_device,hw_sleep_wq);
         struct net_device *dev = ieee->dev;
 #else
@@ -6407,7 +6407,7 @@ priv->txnpring)/8);
 void rtl8180_tx_irq_wq(struct work_struct *work)
 {
 	//struct r8180_priv *priv = container_of(work, struct r8180_priv, reset_wq);
-        struct delayed_work *dwork = container_of(work,struct delayed_work,work);
+	struct delayed_work *dwork = to_delayed_work(work);
 	struct ieee80211_device * ieee = (struct ieee80211_device*)
 	                                       container_of(dwork, struct ieee80211_device, watch_dog_wq);
 	struct net_device *dev = ieee->dev;
@@ -6691,7 +6691,7 @@ lizhaoming--------------------------- RF power on/power off -----------------
 #if (LINUX_VERSION_CODE >= KERNEL_VERSION(2,6,20))
 void GPIOChangeRFWorkItemCallBack(struct work_struct *work)
 {
-	//struct delayed_work *dwork = container_of(work, struct delayed_work, work);
+	//struct delayed_work *dwork = to_delayed_work(work);
 	struct ieee80211_device *ieee = container_of(work, struct ieee80211_device, GPIOChangeRFWorkItem.work);
 	struct net_device *dev = ieee->dev;
 	struct r8180_priv *priv = ieee80211_priv(dev);
diff --git a/drivers/usb/atm/ueagle-atm.c b/drivers/usb/atm/ueagle-atm.c
index b6483dd98acc..9cf9ff69e3e3 100644
--- a/drivers/usb/atm/ueagle-atm.c
+++ b/drivers/usb/atm/ueagle-atm.c
@@ -626,7 +626,7 @@ static void uea_upload_pre_firmware(const struct firmware *fw_entry, void *conte
 		goto err_fw_corrupted;
 
 	/*
-	 * Start to upload formware : send reset
+	 * Start to upload firmware : send reset
 	 */
 	value = 1;
 	ret = uea_send_modem_cmd(usb, F8051_USBCS, sizeof(value), &value);
diff --git a/drivers/usb/gadget/Kconfig b/drivers/usb/gadget/Kconfig
index 770b3eaa9184..080bb1e4b847 100644
--- a/drivers/usb/gadget/Kconfig
+++ b/drivers/usb/gadget/Kconfig
@@ -392,7 +392,7 @@ config USB_GADGET_FSL_QE
 	   controllers having QE or CPM2, given minor tweaks.
 
 	   Set CONFIG_USB_GADGET to "m" to build this driver as a
-	   dynmically linked module called "fsl_qe_udc".
+	   dynamically linked module called "fsl_qe_udc".
 
 config USB_FSL_QE
 	tristate
diff --git a/drivers/usb/serial/ChangeLog.history b/drivers/usb/serial/ChangeLog.history
index c1b279939bbf..f13fd488ebec 100644
--- a/drivers/usb/serial/ChangeLog.history
+++ b/drivers/usb/serial/ChangeLog.history
@@ -715,7 +715,7 @@ io_edgeport.c Change Log comments:
 
  0.2 (01/30/2000) greg kroah-hartman
 	Milestone 1 release.
-	Device is found by USB subsystem, enumerated, fimware is downloaded
+	Device is found by USB subsystem, enumerated, firmware is downloaded
 	and the descriptors are printed to the debug log, config is set, and
 	green light starts to blink. Open port works, and data can be sent
 	and received at the default settings of the UART. Loopback connector
diff --git a/drivers/usb/serial/Kconfig b/drivers/usb/serial/Kconfig
index a65f9196b0a0..c480ea4c19f2 100644
--- a/drivers/usb/serial/Kconfig
+++ b/drivers/usb/serial/Kconfig
@@ -518,8 +518,8 @@ config USB_SERIAL_SIERRAWIRELESS
 	help
 	  Say M here if you want to use Sierra Wireless devices.
 
-	  Many deviecs have a feature known as TRU-Install, for those devices
-	  to work properly the USB Storage Sierra feature must be enabled.
+	  Many devices have a feature known as TRU-Install. For those devices
+	  to work properly, the USB Storage Sierra feature must be enabled.
 
 	  To compile this driver as a module, choose M here: the
 	  module will be called sierra.
diff --git a/drivers/usb/storage/isd200.c b/drivers/usb/storage/isd200.c
index 882c57b399f7..fdba2f69d4c9 100644
--- a/drivers/usb/storage/isd200.c
+++ b/drivers/usb/storage/isd200.c
@@ -46,6 +46,7 @@
 #include <linux/errno.h>
 #include <linux/module.h>
 #include <linux/slab.h>
+#include <linux/ata.h>
 #include <linux/hdreg.h>
 #include <linux/scatterlist.h>
 
@@ -328,7 +329,7 @@ struct isd200_config {
 
 struct isd200_info {
 	struct inquiry_data InquiryData;
-	struct hd_driveid *id;
+	u16 *id;
 	struct isd200_config ConfigData;
 	unsigned char *RegsBuf;
 	unsigned char ATARegs[8];
@@ -419,19 +420,19 @@ static void isd200_build_sense(struct us_data *us, struct scsi_cmnd *srb)
 		buf->Flags = UNIT_ATTENTION;
 		buf->AdditionalSenseCode = 0;
 		buf->AdditionalSenseCodeQualifier = 0;
-	} else if(error & MCR_ERR) {
+	} else if (error & ATA_MCR) {
 		buf->ErrorCode = 0x70 | SENSE_ERRCODE_VALID;
 		buf->AdditionalSenseLength = 0xb;
 		buf->Flags =  UNIT_ATTENTION;
 		buf->AdditionalSenseCode = 0;
 		buf->AdditionalSenseCodeQualifier = 0;
-	} else if(error & TRK0_ERR) {
+	} else if (error & ATA_TRK0NF) {
 		buf->ErrorCode = 0x70 | SENSE_ERRCODE_VALID;
 		buf->AdditionalSenseLength = 0xb;
 		buf->Flags =  NOT_READY;
 		buf->AdditionalSenseCode = 0;
 		buf->AdditionalSenseCodeQualifier = 0;
-	} else if(error & ECC_ERR) {
+	} else if (error & ATA_UNC) {
 		buf->ErrorCode = 0x70 | SENSE_ERRCODE_VALID;
 		buf->AdditionalSenseLength = 0xb;
 		buf->Flags =  DATA_PROTECT;
@@ -547,16 +548,16 @@ static int isd200_action( struct us_data *us, int action,
 		ata.generic.ActionSelect = ACTION_SELECT_1|ACTION_SELECT_5;
 		ata.generic.RegisterSelect = REG_DEVICE_HEAD | REG_COMMAND;
 		ata.write.DeviceHeadByte = info->DeviceHead;
-		ata.write.CommandByte = WIN_SRST;
+		ata.write.CommandByte = ATA_CMD_DEV_RESET;
 		isd200_set_srb(info, DMA_NONE, NULL, 0);
 		break;
 
 	case ACTION_IDENTIFY:
 		US_DEBUGP("   isd200_action(IDENTIFY)\n");
 		ata.generic.RegisterSelect = REG_COMMAND;
-		ata.write.CommandByte = WIN_IDENTIFY;
+		ata.write.CommandByte = ATA_CMD_ID_ATA;
 		isd200_set_srb(info, DMA_FROM_DEVICE, info->id,
-		                                sizeof(struct hd_driveid));
+				ATA_ID_WORDS * 2);
 		break;
 
 	default:
@@ -944,22 +945,22 @@ static int isd200_try_enum(struct us_data *us, unsigned char master_slave,
 			break;
 
 		if (!detect) {
-			if (regs[ATA_REG_STATUS_OFFSET] & BUSY_STAT) {
+			if (regs[ATA_REG_STATUS_OFFSET] & ATA_BUSY) {
 				US_DEBUGP("   %s status is still BSY, try again...\n",mstr);
 			} else {
 				US_DEBUGP("   %s status !BSY, continue with next operation\n",mstr);
 				break;
 			}
 		}
-		/* check for BUSY_STAT and */
-		/* WRERR_STAT (workaround ATA Zip drive) and */ 
-		/* ERR_STAT (workaround for Archos CD-ROM) */
+		/* check for ATA_BUSY and */
+		/* ATA_DF (workaround ATA Zip drive) and */
+		/* ATA_ERR (workaround for Archos CD-ROM) */
 		else if (regs[ATA_REG_STATUS_OFFSET] &
-			 (BUSY_STAT | WRERR_STAT | ERR_STAT )) {
+			 (ATA_BUSY | ATA_DF | ATA_ERR)) {
 			US_DEBUGP("   Status indicates it is not ready, try again...\n");
 		}
 		/* check for DRDY, ATA devices set DRDY after SRST */
-		else if (regs[ATA_REG_STATUS_OFFSET] & READY_STAT) {
+		else if (regs[ATA_REG_STATUS_OFFSET] & ATA_DRDY) {
 			US_DEBUGP("   Identified ATA device\n");
 			info->DeviceFlags |= DF_ATA_DEVICE;
 			info->DeviceHead = master_slave;
@@ -1053,103 +1054,50 @@ static int isd200_manual_enum(struct us_data *us)
 	return(retStatus);
 }
 
-static void isd200_fix_driveid (struct hd_driveid *id)
+static void isd200_fix_driveid(u16 *id)
 {
 #ifndef __LITTLE_ENDIAN
 # ifdef __BIG_ENDIAN
 	int i;
-	u16 *stringcast;
-
-	id->config         = __le16_to_cpu(id->config);
-	id->cyls           = __le16_to_cpu(id->cyls);
-	id->reserved2      = __le16_to_cpu(id->reserved2);
-	id->heads          = __le16_to_cpu(id->heads);
-	id->track_bytes    = __le16_to_cpu(id->track_bytes);
-	id->sector_bytes   = __le16_to_cpu(id->sector_bytes);
-	id->sectors        = __le16_to_cpu(id->sectors);
-	id->vendor0        = __le16_to_cpu(id->vendor0);
-	id->vendor1        = __le16_to_cpu(id->vendor1);
-	id->vendor2        = __le16_to_cpu(id->vendor2);
-	stringcast = (u16 *)&id->serial_no[0];
-	for (i = 0; i < (20/2); i++)
-		stringcast[i] = __le16_to_cpu(stringcast[i]);
-	id->buf_type       = __le16_to_cpu(id->buf_type);
-	id->buf_size       = __le16_to_cpu(id->buf_size);
-	id->ecc_bytes      = __le16_to_cpu(id->ecc_bytes);
-	stringcast = (u16 *)&id->fw_rev[0];
-	for (i = 0; i < (8/2); i++)
-		stringcast[i] = __le16_to_cpu(stringcast[i]);
-	stringcast = (u16 *)&id->model[0];
-	for (i = 0; i < (40/2); i++)
-		stringcast[i] = __le16_to_cpu(stringcast[i]);
-	id->dword_io       = __le16_to_cpu(id->dword_io);
-	id->reserved50     = __le16_to_cpu(id->reserved50);
-	id->field_valid    = __le16_to_cpu(id->field_valid);
-	id->cur_cyls       = __le16_to_cpu(id->cur_cyls);
-	id->cur_heads      = __le16_to_cpu(id->cur_heads);
-	id->cur_sectors    = __le16_to_cpu(id->cur_sectors);
-	id->cur_capacity0  = __le16_to_cpu(id->cur_capacity0);
-	id->cur_capacity1  = __le16_to_cpu(id->cur_capacity1);
-	id->lba_capacity   = __le32_to_cpu(id->lba_capacity);
-	id->dma_1word      = __le16_to_cpu(id->dma_1word);
-	id->dma_mword      = __le16_to_cpu(id->dma_mword);
-	id->eide_pio_modes = __le16_to_cpu(id->eide_pio_modes);
-	id->eide_dma_min   = __le16_to_cpu(id->eide_dma_min);
-	id->eide_dma_time  = __le16_to_cpu(id->eide_dma_time);
-	id->eide_pio       = __le16_to_cpu(id->eide_pio);
-	id->eide_pio_iordy = __le16_to_cpu(id->eide_pio_iordy);
-	for (i = 0; i < 2; ++i)
-		id->words69_70[i] = __le16_to_cpu(id->words69_70[i]);
-	for (i = 0; i < 4; ++i)
-		id->words71_74[i] = __le16_to_cpu(id->words71_74[i]);
-	id->queue_depth    = __le16_to_cpu(id->queue_depth);
-	for (i = 0; i < 4; ++i)
-		id->words76_79[i] = __le16_to_cpu(id->words76_79[i]);
-	id->major_rev_num  = __le16_to_cpu(id->major_rev_num);
-	id->minor_rev_num  = __le16_to_cpu(id->minor_rev_num);
-	id->command_set_1  = __le16_to_cpu(id->command_set_1);
-	id->command_set_2  = __le16_to_cpu(id->command_set_2);
-	id->cfsse          = __le16_to_cpu(id->cfsse);
-	id->cfs_enable_1   = __le16_to_cpu(id->cfs_enable_1);
-	id->cfs_enable_2   = __le16_to_cpu(id->cfs_enable_2);
-	id->csf_default    = __le16_to_cpu(id->csf_default);
-	id->dma_ultra      = __le16_to_cpu(id->dma_ultra);
-	id->trseuc         = __le16_to_cpu(id->trseuc);
-	id->trsEuc         = __le16_to_cpu(id->trsEuc);
-	id->CurAPMvalues   = __le16_to_cpu(id->CurAPMvalues);
-	id->mprc           = __le16_to_cpu(id->mprc);
-	id->hw_config      = __le16_to_cpu(id->hw_config);
-	id->acoustic       = __le16_to_cpu(id->acoustic);
-	id->msrqs          = __le16_to_cpu(id->msrqs);
-	id->sxfert         = __le16_to_cpu(id->sxfert);
-	id->sal            = __le16_to_cpu(id->sal);
-	id->spg            = __le32_to_cpu(id->spg);
-	id->lba_capacity_2 = __le64_to_cpu(id->lba_capacity_2);
-	for (i = 0; i < 22; i++)
-		id->words104_125[i]   = __le16_to_cpu(id->words104_125[i]);
-	id->last_lun       = __le16_to_cpu(id->last_lun);
-	id->word127        = __le16_to_cpu(id->word127);
-	id->dlf            = __le16_to_cpu(id->dlf);
-	id->csfo           = __le16_to_cpu(id->csfo);
-	for (i = 0; i < 26; i++)
-		id->words130_155[i] = __le16_to_cpu(id->words130_155[i]);
-	id->word156        = __le16_to_cpu(id->word156);
-	for (i = 0; i < 3; i++)
-		id->words157_159[i] = __le16_to_cpu(id->words157_159[i]);
-	id->cfa_power      = __le16_to_cpu(id->cfa_power);
-	for (i = 0; i < 14; i++)
-		id->words161_175[i] = __le16_to_cpu(id->words161_175[i]);
-	for (i = 0; i < 31; i++)
-		id->words176_205[i] = __le16_to_cpu(id->words176_205[i]);
-	for (i = 0; i < 48; i++)
-		id->words206_254[i] = __le16_to_cpu(id->words206_254[i]);
-	id->integrity_word  = __le16_to_cpu(id->integrity_word);
+
+	for (i = 0; i < ATA_ID_WORDS; i++)
+		id[i] = __le16_to_cpu(id[i]);
 # else
 #  error "Please fix <asm/byteorder.h>"
 # endif
 #endif
 }
 
+static void isd200_dump_driveid(u16 *id)
+{
+	US_DEBUGP("   Identify Data Structure:\n");
+	US_DEBUGP("      config = 0x%x\n",	  id[ATA_ID_CONFIG]);
+	US_DEBUGP("      cyls = 0x%x\n",	  id[ATA_ID_CYLS]);
+	US_DEBUGP("      heads = 0x%x\n",	  id[ATA_ID_HEADS]);
+	US_DEBUGP("      track_bytes = 0x%x\n",	  id[4]);
+	US_DEBUGP("      sector_bytes = 0x%x\n",  id[5]);
+	US_DEBUGP("      sectors = 0x%x\n",	  id[ATA_ID_SECTORS]);
+	US_DEBUGP("      serial_no[0] = 0x%x\n",  *(char *)&id[ATA_ID_SERNO]);
+	US_DEBUGP("      buf_type = 0x%x\n",	  id[20]);
+	US_DEBUGP("      buf_size = 0x%x\n",	  id[ATA_ID_BUF_SIZE]);
+	US_DEBUGP("      ecc_bytes = 0x%x\n",	  id[22]);
+	US_DEBUGP("      fw_rev[0] = 0x%x\n",	  *(char *)&id[ATA_ID_FW_REV]);
+	US_DEBUGP("      model[0] = 0x%x\n",	  *(char *)&id[ATA_ID_PROD]);
+	US_DEBUGP("      max_multsect = 0x%x\n",  id[ATA_ID_MAX_MULTSECT] & 0xff);
+	US_DEBUGP("      dword_io = 0x%x\n",	  id[ATA_ID_DWORD_IO]);
+	US_DEBUGP("      capability = 0x%x\n",	  id[ATA_ID_CAPABILITY] >> 8);
+	US_DEBUGP("      tPIO = 0x%x\n",	  id[ATA_ID_OLD_PIO_MODES] >> 8);
+	US_DEBUGP("      tDMA = 0x%x\n",	  id[ATA_ID_OLD_DMA_MODES] >> 8);
+	US_DEBUGP("      field_valid = 0x%x\n",	  id[ATA_ID_FIELD_VALID]);
+	US_DEBUGP("      cur_cyls = 0x%x\n",	  id[ATA_ID_CUR_CYLS]);
+	US_DEBUGP("      cur_heads = 0x%x\n",	  id[ATA_ID_CUR_HEADS]);
+	US_DEBUGP("      cur_sectors = 0x%x\n",	  id[ATA_ID_CUR_SECTORS]);
+	US_DEBUGP("      cur_capacity = 0x%x\n",  ata_id_u32(id, 57));
+	US_DEBUGP("      multsect = 0x%x\n",	  id[ATA_ID_MULTSECT] & 0xff);
+	US_DEBUGP("      lba_capacity = 0x%x\n",  ata_id_u32(id, ATA_ID_LBA_CAPACITY));
+	US_DEBUGP("      command_set_1 = 0x%x\n", id[ATA_ID_COMMAND_SET_1]);
+	US_DEBUGP("      command_set_2 = 0x%x\n", id[ATA_ID_COMMAND_SET_2]);
+}
 
 /**************************************************************************
  * isd200_get_inquiry_data
@@ -1163,7 +1111,7 @@ static int isd200_get_inquiry_data( struct us_data *us )
 {
 	struct isd200_info *info = (struct isd200_info *)us->extra;
 	int retStatus = ISD200_GOOD;
-	struct hd_driveid *id = info->id;
+	u16 *id = info->id;
 
 	US_DEBUGP("Entering isd200_get_inquiry_data\n");
 
@@ -1180,8 +1128,7 @@ static int isd200_get_inquiry_data( struct us_data *us )
 			/* this must be an ATA device */
 			/* perform an ATA Command Identify */
 			transferStatus = isd200_action( us, ACTION_IDENTIFY,
-							id, 
-							sizeof(struct hd_driveid) );
+							id, ATA_ID_WORDS * 2);
 			if (transferStatus != ISD200_TRANSPORT_GOOD) {
 				/* Error issuing ATA Command Identify */
 				US_DEBUGP("   Error issuing ATA Command Identify\n");
@@ -1191,35 +1138,9 @@ static int isd200_get_inquiry_data( struct us_data *us )
 				int i;
 				__be16 *src;
 				__u16 *dest;
-				isd200_fix_driveid(id);
 
-				US_DEBUGP("   Identify Data Structure:\n");
-				US_DEBUGP("      config = 0x%x\n", id->config);
-				US_DEBUGP("      cyls = 0x%x\n", id->cyls);
-				US_DEBUGP("      heads = 0x%x\n", id->heads);
-				US_DEBUGP("      track_bytes = 0x%x\n", id->track_bytes);
-				US_DEBUGP("      sector_bytes = 0x%x\n", id->sector_bytes);
-				US_DEBUGP("      sectors = 0x%x\n", id->sectors);
-				US_DEBUGP("      serial_no[0] = 0x%x\n", id->serial_no[0]);
-				US_DEBUGP("      buf_type = 0x%x\n", id->buf_type);
-				US_DEBUGP("      buf_size = 0x%x\n", id->buf_size);
-				US_DEBUGP("      ecc_bytes = 0x%x\n", id->ecc_bytes);
-				US_DEBUGP("      fw_rev[0] = 0x%x\n", id->fw_rev[0]);
-				US_DEBUGP("      model[0] = 0x%x\n", id->model[0]);
-				US_DEBUGP("      max_multsect = 0x%x\n", id->max_multsect);
-				US_DEBUGP("      dword_io = 0x%x\n", id->dword_io);
-				US_DEBUGP("      capability = 0x%x\n", id->capability);
-				US_DEBUGP("      tPIO = 0x%x\n", id->tPIO);
-				US_DEBUGP("      tDMA = 0x%x\n", id->tDMA);
-				US_DEBUGP("      field_valid = 0x%x\n", id->field_valid);
-				US_DEBUGP("      cur_cyls = 0x%x\n", id->cur_cyls);
-				US_DEBUGP("      cur_heads = 0x%x\n", id->cur_heads);
-				US_DEBUGP("      cur_sectors = 0x%x\n", id->cur_sectors);
-				US_DEBUGP("      cur_capacity = 0x%x\n", (id->cur_capacity1 << 16) + id->cur_capacity0 );
-				US_DEBUGP("      multsect = 0x%x\n", id->multsect);
-				US_DEBUGP("      lba_capacity = 0x%x\n", id->lba_capacity);
-				US_DEBUGP("      command_set_1 = 0x%x\n", id->command_set_1);
-				US_DEBUGP("      command_set_2 = 0x%x\n", id->command_set_2);
+				isd200_fix_driveid(id);
+				isd200_dump_driveid(id);
 
 				memset(&info->InquiryData, 0, sizeof(info->InquiryData));
 
@@ -1229,30 +1150,30 @@ static int isd200_get_inquiry_data( struct us_data *us )
 				/* The length must be at least 36 (5 + 31) */
 				info->InquiryData.AdditionalLength = 0x1F;
 
-				if (id->command_set_1 & COMMANDSET_MEDIA_STATUS) {
+				if (id[ATA_ID_COMMAND_SET_1] & COMMANDSET_MEDIA_STATUS) {
 					/* set the removable bit */
 					info->InquiryData.DeviceTypeModifier = DEVICE_REMOVABLE;
 					info->DeviceFlags |= DF_REMOVABLE_MEDIA;
 				}
 
 				/* Fill in vendor identification fields */
-				src = (__be16*)id->model;
+				src = (__be16 *)&id[ATA_ID_PROD];
 				dest = (__u16*)info->InquiryData.VendorId;
 				for (i=0;i<4;i++)
 					dest[i] = be16_to_cpu(src[i]);
 
-				src = (__be16*)(id->model+8);
+				src = (__be16 *)&id[ATA_ID_PROD + 8/2];
 				dest = (__u16*)info->InquiryData.ProductId;
 				for (i=0;i<8;i++)
 					dest[i] = be16_to_cpu(src[i]);
 
-				src = (__be16*)id->fw_rev;
+				src = (__be16 *)&id[ATA_ID_FW_REV];
 				dest = (__u16*)info->InquiryData.ProductRevisionLevel;
 				for (i=0;i<2;i++)
 					dest[i] = be16_to_cpu(src[i]);
 
 				/* determine if it supports Media Status Notification */
-				if (id->command_set_2 & COMMANDSET_MEDIA_STATUS) {
+				if (id[ATA_ID_COMMAND_SET_2] & COMMANDSET_MEDIA_STATUS) {
 					US_DEBUGP("   Device supports Media Status Notification\n");
 
 					/* Indicate that it is enabled, even though it is not
@@ -1301,7 +1222,7 @@ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us,
 			      union ata_cdb * ataCdb)
 {
 	struct isd200_info *info = (struct isd200_info *)us->extra;
-	struct hd_driveid *id = info->id;
+	u16 *id = info->id;
 	int sendToTransport = 1;
 	unsigned char sectnum, head;
 	unsigned short cylinder;
@@ -1369,13 +1290,12 @@ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us,
 
 		US_DEBUGP("   ATA OUT - SCSIOP_READ_CAPACITY\n");
 
-		if (id->capability & CAPABILITY_LBA ) {
-			capacity = id->lba_capacity - 1;
-		} else {
-			capacity = (id->heads *
-				    id->cyls *
-				    id->sectors) - 1;
-		}
+		if (ata_id_has_lba(id))
+			capacity = ata_id_u32(id, ATA_ID_LBA_CAPACITY) - 1;
+		else
+			capacity = (id[ATA_ID_HEADS] * id[ATA_ID_CYLS] *
+				    id[ATA_ID_SECTORS]) - 1;
+
 		readCapacityData.LogicalBlockAddress = cpu_to_be32(capacity);
 		readCapacityData.BytesPerBlock = cpu_to_be32(0x200);
 
@@ -1392,16 +1312,16 @@ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us,
 		lba = be32_to_cpu(*(__be32 *)&srb->cmnd[2]);
 		blockCount = (unsigned long)srb->cmnd[7]<<8 | (unsigned long)srb->cmnd[8];
 
-		if (id->capability & CAPABILITY_LBA) {
+		if (ata_id_has_lba(id)) {
 			sectnum = (unsigned char)(lba);
 			cylinder = (unsigned short)(lba>>8);
 			head = ATA_ADDRESS_DEVHEAD_LBA_MODE | (unsigned char)(lba>>24 & 0x0F);
 		} else {
-			sectnum = (unsigned char)((lba % id->sectors) + 1);
-			cylinder = (unsigned short)(lba / (id->sectors *
-							   id->heads));
-			head = (unsigned char)((lba / id->sectors) %
-					       id->heads);
+			sectnum = (u8)((lba % id[ATA_ID_SECTORS]) + 1);
+			cylinder = (u16)(lba / (id[ATA_ID_SECTORS] *
+					id[ATA_ID_HEADS]));
+			head = (u8)((lba / id[ATA_ID_SECTORS]) %
+					id[ATA_ID_HEADS]);
 		}
 		ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand;
 		ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand;
@@ -1415,7 +1335,7 @@ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us,
 		ataCdb->write.CylinderHighByte = (unsigned char)(cylinder>>8);
 		ataCdb->write.CylinderLowByte = (unsigned char)cylinder;
 		ataCdb->write.DeviceHeadByte = (head | ATA_ADDRESS_DEVHEAD_STD);
-		ataCdb->write.CommandByte = WIN_READ;
+		ataCdb->write.CommandByte = ATA_CMD_PIO_READ;
 		break;
 
 	case WRITE_10:
@@ -1424,14 +1344,16 @@ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us,
 		lba = be32_to_cpu(*(__be32 *)&srb->cmnd[2]);
 		blockCount = (unsigned long)srb->cmnd[7]<<8 | (unsigned long)srb->cmnd[8];
 
-		if (id->capability & CAPABILITY_LBA) {
+		if (ata_id_has_lba(id)) {
 			sectnum = (unsigned char)(lba);
 			cylinder = (unsigned short)(lba>>8);
 			head = ATA_ADDRESS_DEVHEAD_LBA_MODE | (unsigned char)(lba>>24 & 0x0F);
 		} else {
-			sectnum = (unsigned char)((lba % id->sectors) + 1);
-			cylinder = (unsigned short)(lba / (id->sectors * id->heads));
-			head = (unsigned char)((lba / id->sectors) % id->heads);
+			sectnum = (u8)((lba % id[ATA_ID_SECTORS]) + 1);
+			cylinder = (u16)(lba / (id[ATA_ID_SECTORS] *
+					id[ATA_ID_HEADS]));
+			head = (u8)((lba / id[ATA_ID_SECTORS]) %
+					id[ATA_ID_HEADS]);
 		}
 		ataCdb->generic.SignatureByte0 = info->ConfigData.ATAMajorCommand;
 		ataCdb->generic.SignatureByte1 = info->ConfigData.ATAMinorCommand;
@@ -1445,7 +1367,7 @@ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us,
 		ataCdb->write.CylinderHighByte = (unsigned char)(cylinder>>8);
 		ataCdb->write.CylinderLowByte = (unsigned char)cylinder;
 		ataCdb->write.DeviceHeadByte = (head | ATA_ADDRESS_DEVHEAD_STD);
-		ataCdb->write.CommandByte = WIN_WRITE;
+		ataCdb->write.CommandByte = ATA_CMD_PIO_WRITE;
 		break;
 
 	case ALLOW_MEDIUM_REMOVAL:
@@ -1459,7 +1381,7 @@ static int isd200_scsi_to_ata(struct scsi_cmnd *srb, struct us_data *us,
 			ataCdb->generic.TransferBlockSize = 1;
 			ataCdb->generic.RegisterSelect = REG_COMMAND;
 			ataCdb->write.CommandByte = (srb->cmnd[4] & 0x1) ?
-				WIN_DOORLOCK : WIN_DOORUNLOCK;
+				ATA_CMD_MEDIA_LOCK : ATA_CMD_MEDIA_UNLOCK;
 			isd200_srb_set_bufflen(srb, 0);
 		} else {
 			US_DEBUGP("   Not removeable media, just report okay\n");
@@ -1539,8 +1461,7 @@ static int isd200_init_info(struct us_data *us)
 	if (!info)
 		retStatus = ISD200_ERROR;
 	else {
-		info->id = (struct hd_driveid *)
-				kzalloc(sizeof(struct hd_driveid), GFP_KERNEL);
+		info->id = kzalloc(ATA_ID_WORDS * 2, GFP_KERNEL);
 		info->RegsBuf = (unsigned char *)
 				kmalloc(sizeof(info->ATARegs), GFP_KERNEL);
 		info->srb.sense_buffer =
diff --git a/drivers/usb/wusbcore/devconnect.c b/drivers/usb/wusbcore/devconnect.c
index f0aac0cf315a..386eaa22d215 100644
--- a/drivers/usb/wusbcore/devconnect.c
+++ b/drivers/usb/wusbcore/devconnect.c
@@ -471,7 +471,7 @@ static void __wusbhc_keep_alive(struct wusbhc *wusbhc)
  */
 static void wusbhc_keep_alive_run(struct work_struct *ws)
 {
-	struct delayed_work *dw = container_of(ws, struct delayed_work, work);
+	struct delayed_work *dw = to_delayed_work(ws);
 	struct wusbhc *wusbhc =	container_of(dw, struct wusbhc, keep_alive_timer);
 
 	mutex_lock(&wusbhc->mutex);
diff --git a/drivers/usb/wusbcore/security.c b/drivers/usb/wusbcore/security.c
index 8118db7f1d8d..b2f149fedcc5 100644
--- a/drivers/usb/wusbcore/security.c
+++ b/drivers/usb/wusbcore/security.c
@@ -562,7 +562,7 @@ void wusbhc_gtk_rekey(struct wusbhc *wusbhc)
 		struct wusb_dev *wusb_dev;
 
 		wusb_dev = wusbhc->port[p].wusb_dev;
-		if (!wusb_dev || !wusb_dev->usb_dev | !wusb_dev->usb_dev->authenticated)
+		if (!wusb_dev || !wusb_dev->usb_dev || !wusb_dev->usb_dev->authenticated)
 			continue;
 
 		usb_fill_control_urb(wusb_dev->set_gtk_urb, wusb_dev->usb_dev,
diff --git a/drivers/uwb/Kconfig b/drivers/uwb/Kconfig
index ca783127af36..bac8e7a6f17b 100644
--- a/drivers/uwb/Kconfig
+++ b/drivers/uwb/Kconfig
@@ -48,10 +48,10 @@ config UWB_WHCI
         help
           This driver enables the radio controller for WHCI cards.
 
-          WHCI is an specification developed by Intel
+          WHCI is a specification developed by Intel
           (http://www.intel.com/technology/comms/wusb/whci.htm) much
           in the spirit of USB's EHCI, but for UWB and Wireless USB
-          radio/host controllers connected via memmory mapping (eg:
+          radio/host controllers connected via memory mapping (eg:
           PCI). Most of these cards come also with a Wireless USB host
           controller.
 
diff --git a/drivers/video/nvidia/nv_setup.c b/drivers/video/nvidia/nv_setup.c
index d9627b57eb4d..135ae18bfce8 100644
--- a/drivers/video/nvidia/nv_setup.c
+++ b/drivers/video/nvidia/nv_setup.c
@@ -362,6 +362,7 @@ int NVCommonSetup(struct fb_info *info)
 	case 0x0186:
 	case 0x0187:
 	case 0x018D:
+	case 0x01D7:
 	case 0x0228:
 	case 0x0286:
 	case 0x028C:
diff --git a/drivers/w1/w1_io.c b/drivers/w1/w1_io.c
index 442bd8bbd4a5..3ebe9726a9e5 100644
--- a/drivers/w1/w1_io.c
+++ b/drivers/w1/w1_io.c
@@ -69,7 +69,7 @@ static u8 w1_touch_bit(struct w1_master *dev, int bit)
 		return w1_read_bit(dev);
 	else {
 		w1_write_bit(dev, 0);
-		return(0);
+		return 0;
 	}
 }
 
@@ -184,17 +184,17 @@ static u8 w1_read_bit(struct w1_master *dev)
  */
 u8 w1_triplet(struct w1_master *dev, int bdir)
 {
-	if ( dev->bus_master->triplet )
-		return(dev->bus_master->triplet(dev->bus_master->data, bdir));
+	if (dev->bus_master->triplet)
+		return dev->bus_master->triplet(dev->bus_master->data, bdir);
 	else {
 		u8 id_bit   = w1_touch_bit(dev, 1);
 		u8 comp_bit = w1_touch_bit(dev, 1);
 		u8 retval;
 
-		if ( id_bit && comp_bit )
-			return(0x03);  /* error */
+		if (id_bit && comp_bit)
+			return 0x03;  /* error */
 
-		if ( !id_bit && !comp_bit ) {
+		if (!id_bit && !comp_bit) {
 			/* Both bits are valid, take the direction given */
 			retval = bdir ? 0x04 : 0;
 		} else {
@@ -203,11 +203,11 @@ u8 w1_triplet(struct w1_master *dev, int bdir)
 			retval = id_bit ? 0x05 : 0x02;
 		}
 
-		if ( dev->bus_master->touch_bit )
+		if (dev->bus_master->touch_bit)
 			w1_touch_bit(dev, bdir);
 		else
 			w1_write_bit(dev, bdir);
-		return(retval);
+		return retval;
 	}
 }
 
diff --git a/drivers/xen/Kconfig b/drivers/xen/Kconfig
index 526187c8a12d..8ac9cddac575 100644
--- a/drivers/xen/Kconfig
+++ b/drivers/xen/Kconfig
@@ -37,7 +37,7 @@ config XEN_COMPAT_XENFS
          The old xenstore userspace tools expect to find "xenbus"
          under /proc/xen, but "xenbus" is now found at the root of the
          xenfs filesystem.  Selecting this causes the kernel to create
-         the compatibilty mount point /proc/xen if it is running on
+         the compatibility mount point /proc/xen if it is running on
          a xen platform.
          If in doubt, say yes.
 
diff --git a/drivers/xen/cpu_hotplug.c b/drivers/xen/cpu_hotplug.c
index 974f56d1ebe1..5f54c01c1568 100644
--- a/drivers/xen/cpu_hotplug.c
+++ b/drivers/xen/cpu_hotplug.c
@@ -10,7 +10,7 @@ static void enable_hotplug_cpu(int cpu)
 	if (!cpu_present(cpu))
 		arch_register_cpu(cpu);
 
-	cpu_set(cpu, cpu_present_map);
+	set_cpu_present(cpu, true);
 }
 
 static void disable_hotplug_cpu(int cpu)
@@ -18,7 +18,7 @@ static void disable_hotplug_cpu(int cpu)
 	if (cpu_present(cpu))
 		arch_unregister_cpu(cpu);
 
-	cpu_clear(cpu, cpu_present_map);
+	set_cpu_present(cpu, false);
 }
 
 static void vcpu_hotplug(unsigned int cpu)
diff --git a/firmware/3com/3C359.bin.ihex b/firmware/3com/3C359.bin.ihex
new file mode 100644
index 000000000000..781bac3b2a02
--- /dev/null
+++ b/firmware/3com/3C359.bin.ihex
@@ -0,0 +1,1573 @@
+:10000000FE3A0000000000000000000000000000B8
+:1000100000000000000000000000000000000000E0
+:1000200000000000000000000000000000000000D0
+:1000300000000000000000000000000000000000C0
+:1000400000000000000030332F30322F39392031CA
+:10005000373A3133000000000000000000000000CB
+:1000600030313233343536373839414243444546EE
+:10007000000007FF0200FE9F0600007C48000070A1
+:100080008200FFFF8600FFFF8800FFFF9A00FFFF4E
+:10009000FFFF1100C000FFFFFFFF11223344556630
+:1000A00033434F4D20424142451140C000FFFFFF06
+:1000B000FF1122334455665374617274206F6620B9
+:1000C0004C4C43206672616D652E2020546F746124
+:1000D0006C20646174612073697A6520697320788B
+:1000E000787820202042414245E8D201833EF7340F
+:1000F000007521E84100833EF734007517E882005F
+:10010000833EF73400750DE8BF00833EF734007579
+:1001100003E84102C31EB800F08ED833F6B9008060
+:1001200033DBAD03D8E2FB1FB8000083FB00740390
+:10013000B82200A3F734C3FABA5600B0FFEE33C0BA
+:100140008EC033F6B9FF7F833EFF340074088D3EC6
+:100150003061D1EF2BCF268B1C26C704FFFF2683EF
+:100160003CFF751726C704000026833C00750C264B
+:10017000891C4646E2E0B80000EB03B82400A3F770
+:1001800034C3FAB4D79E733A753879367B349FB14D
+:1001900005D2EC732DB040D0E071277925D0E07303
+:1001A000217B1F32C0751B32E49E721674147812C4
+:1001B0007A109FD2EC720BD0E470077505B800007E
+:1001C000EB03B82600A3F734C3FABA5A0033C0EFE2
+:1001D000EFEFEFB000E656B000E654BA5200B801B7
+:1001E00001EFE8CA003C01757FE88300BA5200B80D
+:1001F0000202EFE8B9003C02756EE87A00BA5200DC
+:10020000B80404EFE8A8003C04755DE87100BA5238
+:1002100000B80808EFE897003C08754CE86800BA99
+:100220005200B81010EFE886003C10753BE85F0004
+:10023000BA5200B82020EFE875003C20752AE85635
+:1002400000BA5200B84040EFE864003C407519E83D
+:100250004D00BA5200B88080EFE853003C8075082A
+:10026000E84400B80000EB03B82800A3F734C3BA91
+:100270005A00B80080EFC3BA5A00B80180EFC3BA81
+:100280005A00B80280EFC3BA5A00B80380EFC3BA6D
+:100290005A00B80480EFC3BA5A00B80580EFC3BA59
+:1002A0005A00B80680EFC3BA5A00B80780EFC3B946
+:1002B000FFFFE458E4543C0075034975F7C3FA3274
+:1002C000C0E656E4563C007403E98200B0FFE656EF
+:1002D000E4563CFF7578BA5200B8FFFFEFED3CFFE3
+:1002E000756CB800FFEFED3C007563B0FFE654E4B9
+:1002F000543CFF755932C0E654E4543C00754FB08D
+:100300000FE650E450240F3C0F7543B000E650E474
+:1003100050240F3C0075378CC88EC0BE7000268BF1
+:1003200014268B5C02B80000EFED23C33D0000757E
+:100330001DB8FFFF23C3EF8BC8ED23C33BC1750E70
+:1003400083C60426833CFF75D5B80000EB03B82AAA
+:1003500000A3F734C3FA33C0BF0020B91700F3ABD2
+:10036000BF0030B91700F3ABBF0022B94000F3ABB8
+:10037000BF0032B94000F3ABFC1E8CC88ED833C02E
+:100380008EC0BE9200BF0020B91700F3A4BEA90022
+:10039000BF0022B94000F3A41FC706FB346400BAB3
+:1003A0000800B80F00EFE88201E89B01720DC70654
+:1003B000F7342C00C706F9340400C3BA0A0033C06E
+:1003C000EFE89801E8B501B81700BA9C00EFB80053
+:1003D00010BA9A00EFB81700A90100740140BA8C56
+:1003E00000EFB80018BA8600EFB80C00BA8200EF30
+:1003F000BA0200ED25F9FF0D0200EFBA060033C086
+:10040000EFBA0400B86000EFBA0000B81800EFBA05
+:100410008000B9FFFFEDA901007504E2F8EB3EBAD8
+:100420000A00EDA900407435A90020743033C0EFF4
+:1004300051B9C800E2FE591E061F268B0E023083FA
+:10044000F91775184949BE0220BF0630F3A61F23CD
+:10045000C9750AFF0EFB347412E94DFF1FB82C005A
+:10046000BB0000A3F734891EF934C3C706FB34640C
+:1004700000E8D300720DC706F7342C00C706F93424
+:100480000400C3E8D600E8F300B80300BA8200EF26
+:10049000B84080BA9800EFB80011BA9600EFB840A3
+:1004A00000A90100740140BA9200EFB80019BA8E99
+:1004B00000EFBA0200ED25F9FF0D0600EFBA0600C5
+:1004C00033C0EFBA0000B81800EFBA8000B9FFFFE0
+:1004D000EDA920007504E2F8EB43BA0A00EDA9008B
+:1004E00040743AA90020743533C0EF51B9C800E216
+:1004F000FE591E061F268B0E023283F940751D49D8
+:1005000049BE0222BF0632F3A61F23C9750FFF0E94
+:10051000FB347403E95AFFB80000EB0B1FB82C0042
+:10052000BB0200891EF934A3F734C3BA0200B80035
+:100530009CEFBA0000B80084EF33C0EFBA0A00EFB6
+:10054000BA0E0033C0EFC3BA0A00B9FFFFED2500B1
+:10055000603D00607404E2F5F8C3F9C3B000E656EC
+:10056000B800FFBA5200EFB9FFFFBA5800ED25EF0F
+:10057000007408BA5A0033C0EFE2EFC3BA8000ED4E
+:10058000BA8400EFBA8000EDC30000000000000054
+:10059000C606EC341533C08ED88EC01E8CC8BE4043
+:1005A00054BF60FE8ED8B91000F3A41FC706803672
+:1005B0001035C7068C3630358D063835A33035A357
+:1005C0003235053301A33435C70636355001C70629
+:1005D000843680FEC7068836C0FEC606C2FEFFC649
+:1005E00006933680C606923600C60680FE80C70691
+:1005F00082FE5450C70684FE2B4DE5CEA90200753D
+:1006000008C60681FE23E90500C60681FE22A1F781
+:1006100034A386FEB8483486E0A388FE8D064E34A7
+:1006200086E0A38AFEB8583486E0A38CFEB89C34DA
+:1006300086E0A38EFE8D06200386E0A390FE33C0E5
+:10064000BA7200EF33C0BA7400EFBA7600EFB88028
+:10065000FE86E0BA7200EFE8BF07BA0C01B840406E
+:10066000EFEDBA6A00B80300C1E0080D0300EFB96E
+:100670000A00E89400BA6A00B80300C1E008EFA1DC
+:100680003234A3A233C706A63304008D06A033C1BB
+:10069000E804CD39C7069036FFFFE9E300630D6635
+:1006A0000D660D8A0DE60E75122E0F030F500F60AA
+:1006B0000D600D600DED0FE912600D600D600D60B5
+:1006C0000D600D2210600D600D600D600DFE10605C
+:1006D0000D600D600D600D600D600DAF0F321037B5
+:1006E0000D600D600D600D600D600D600D600D60A2
+:1006F0000D600D600D600D600D600D600D600D6092
+:100700000D640E000F9509600A49BBFFFFBA6A002D
+:10071000EDA900207438803E80FE127531E84A0051
+:10072000A13234A3A233C706A63304008D06A0333A
+:10073000C1E804CD39E82200C706F3344600C706F5
+:10074000F534FFFFC7069036FFFF58E932004B83B0
+:10075000FB0075B983F90075B0C352BA6A00B803DB
+:1007600000C1E0080D0300EF5AC352BA6A00B80393
+:1007700000C1E008EF5AC3000000000000000000C4
+:10078000688007A19036CD358B3624022EFFA43524
+:100790000AFA8A2694368826E834C606943600FB80
+:1007A00022E47501C3F6C420747DF6C40874058084
+:1007B0000E9236048026E834D7C41E8436268B3742
+:1007C00081E6FF0083FE207605B001E9280053068C
+:1007D000D1E62EFF949D06075B268847023CFF74F6
+:1007E000073CFE7511E93B00F6069236087534F6B3
+:1007F00006923604742D80269236F3803E9536009C
+:10080000752126803F057513C60695360026807F24
+:1008100006007407268B4704A29536BA0C01B8402F
+:1008200040EFED8A26E834F6C4107503E95B00F664
+:10083000C4047405800E9236018026E834EBC43E71
+:100840008836268B3583E67F83FE12720826C645DE
+:100850000201E9240083C620D1E62EFF949D06C440
+:100860003E8836268845023CFF750EF60692360114
+:100870007414F606923602750D80269236FCBA0C78
+:1008800001B82020EFED8A26E834F6C408742280EF
+:1008900026E834F7800E923604F606923608741174
+:1008A00080269236F3BA0C01B84040EFED8A26E874
+:1008B00034F6C40474228026E834FB800E9236019C
+:1008C000F606923602751180269236FEBA0C01B8F1
+:1008D0002020EFED8A26E834F6C40174678026E80C
+:1008E00034FE803EE8FF007439803EE8FF04743235
+:1008F000803EE8FF017521E580A90007740ABA9ED1
+:1009000000B80002EFE9EFFFC606E8FF03BA0C01EA
+:10091000B80808EFEDE92800803EE8FF037406E917
+:100920001E00E90000BA1001B80202EFEDE5000D6B
+:100930001800E700E5820D0200E782C606E8FF0422
+:100940008A26E834F6C402740D8026E834FD802639
+:100950009236BFE84F0BFAA0E83408069436C60674
+:10096000E83400FBC3E8E70FC41E84362EFF1601EF
+:100970000726884702E97EFEE82D10C41E84362E25
+:10098000FF16030726884702E96BFE8E0626022E15
+:10099000FF160707C3C3833EF53400740FFF0EF341
+:1009A000347509E8C4FDC706F5340000F606933631
+:1009B000207430A1C2343B06E934A3E934742480A6
+:1009C0003E953600751DF706E63420007412A92006
+:1009D00000740D8326C234DF8326E934DFE9030087
+:1009E000E8DD09BA0601ED8BD081E200C0C1EA0E54
+:1009F00003167434C1E002110672347304FF0674E6
+:100A000034BA0201ED8BD081E200C0C1EA0E0316B8
+:100A10007034C1E00211066E347304FF067034C7EF
+:100A200006A6330400C706AA3300008D06A033C112
+:100A3000E804CD39C39509950965097809950995A3
+:100A4000099107950996098B0995099509950995C5
+:100A500009950995098BC08BC08BC08BC08BC0904A
+:100A6000F6069336207503E9CC008CC0408EC02674
+:100A70008B0E060086E926890E06008CC2C1E204B0
+:100A8000BE0E0026A10400D0E024C08AE0C0EC0421
+:100A90000AC426A2050026A10800A900C07403E923
+:100AA0009E0026F6061000807503E90A0026A016AF
+:100AB00000241F32E403F0803EEC3406725C803E7A
+:100AC00095360075668BFA33DB8EC326891D268822
+:100AD0005D045150C41E8C36B90F0033C0E82109A3
+:100AE00058590BDB7434FE0EE63A26C6078126C63B
+:100AF00047010026C64702FF26C747040000268993
+:100B00004F0A86F2268957062689770826C647099E
+:100B10000026C6470C02E88C09C3FF06EC338CC0E4
+:100B2000488EC0FAE89710FBE9EBFF8CC0488EC0F6
+:100B3000FAE88A10FBC38CC08EC0FAE88010FBC3B1
+:100B4000803E9536007503E9C200BF080026F60610
+:100B5000100080750503FEE90C0026A01600241F76
+:100B600032E403F003FEA095363C007503E99C00D7
+:100B70003C01740B3C0274143C03741DE98D00C6E7
+:100B800006963601E83C017227E98000C6069636D3
+:100B900002E88300721AE97300C606963601E8225D
+:100BA00001720DC606963602E86C007203E95C001D
+:100BB000530650C41E8C36B90B0033C0E8420858A7
+:100BC00026C6078226C64702FF8D06E0FE86C4269B
+:100BD000894706A0963626884708E8C808075B8339
+:100BE00026AD36FEA1AD36E704BA1001B88080EF1D
+:100BF000EDBA1001B80202EFED52BAE000B84110B0
+:100C0000EF5AB89C03CD39C6069536008CC0488E85
+:100C1000C0FAE8A90FFBC31E061F0633C08EC08BA7
+:100C2000F08D3E20F351B10A26837D0C01752A57C1
+:100C300026837D0E007406E82F00E90300E86607AE
+:100C40005F731633C08ED8268B4D128D75208D3E66
+:100C5000E0FEF3A459071FF9C3FEC9740781C7203A
+:100C600001E9C4FF59071FF8C35150535652573377
+:100C7000DB268A5D0E268B4D128D7D205A87D72666
+:100C80008A451487D74232FF80FF087508FECB22C1
+:100C9000DB75EA33DB23DB7406FEC7D0C8730C5068
+:100CA000268A053804587403E90A0049464723C9CF
+:100CB000740AE9D3FF5A5E5B5859F8C35A5E5B5811
+:100CC00059F9C31E061F0633C08EC086CD2BCE8BAE
+:100CD000F78BC133C9803CFF741680F90673093263
+:100CE000C94648742EE9EDFF3D6000730CE923000E
+:100CF000FEC14648741DE9DCFFB810008D3E183473
+:100D000032EDB106F3A67403E908004823C0740766
+:100D1000E9E9FF071FF8C38D36183433C08ED88D2C
+:100D20003EE0FEB81000B9060056F3A45E483D0050
+:100D30000075F3071FF9C3FF06E433C606EB340062
+:100D4000268B450686E0C1E80448068EC0FE06E60E
+:100D50003AFAE8690EFB07B0FFC30000000000008C
+:100D6000B001C3B000C3F6069336207503B004C3C8
+:100D70008B0E973681E18030268B4704257FCF0B81
+:100D8000C1A39736A3E634B000C3F60693362074A9
+:100D900003B003C3268B4708A39736A3E634268AFD
+:100DA0004720A2FD343C017506C706A13600002687
+:100DB0008A4721A2FE34268B470AA31834A358344D
+:100DC000268B470CA31A34A35A34268B470EA31C38
+:100DD00034A35C34C6062A34C0268B4714257FFF13
+:100DE00009062C34268B471625FFFE25FFFC090635
+:100DF0002E34C6060034C0268B4710A30234268B3F
+:100E00004712A304340653E8840A5B073D000075CB
+:100E100007800E923608B0FEC3B90001A1AC33338F
+:100E2000D2F7F9A3AE33914933D2F7E905003BA3DA
+:100E30004634BF003B893E4434BA6800B8E0E0EF76
+:100E4000A1AE33E762A1AE33BA0801EFA14434E7A3
+:100E500064A14434BA0A01EFB800012D04000D006A
+:100E600010E792C33D0000740A26894707E8833AD9
+:100E7000B007C3A1AE332689472BA1443426894746
+:100E80002DA146342689472F800E933620A188361F
+:100E900086E026894708A1843686E02689470AA18C
+:100EA000803686E02689470CB860FE86E0268947B2
+:100EB0000EA0A136268847108B36883626C64402F7
+:100EC000FFE59EA90008740CBA8400ED0D0800EF40
+:100ED000BA8E00EFE50225F9FFE702BA1001B80269
+:100EE00002EFEDB000C3F6069336207503B001C3E0
+:100EF000802693369FE88D0A800E923608B0FEC396
+:100F0000B000C3F6069336207503B004C3C6062AA4
+:100F100034C0268B4706257FFFA32C34268B470839
+:100F200025FFFE25FFFCA32E34CD52B000C3F606EC
+:100F30009336207503B004C3C6060034C0268B4721
+:100F400006A30234268B4708A30434CD52B000C355
+:100F5000F6069336207503B004C3578D7F0651B94A
+:100F6000070033C0F3AB598D7F06A17A34030639ED
+:100F700037268805A1953726884502A180340306C7
+:100F8000763426884507A1C63426884509A1D8337A
+:100F90002688450A33C0A37A34A33937A39537A3EB
+:100FA0008034A37634A3C634A3D8335FB000C3F62D
+:100FB000069336207503B004C3268B4F0483F906CD
+:100FC000741283F904740D83F900740883F90274B0
+:100FD00003B001C3890EE83A8326AB36F9090EAB9C
+:100FE00036E50225F9FF0BC1E702B000C3F6069310
+:100FF00036207503B004C3268B4F0480F9FF7408B4
+:1010000080F9007410B001C3830EAD3602A1AD3675
+:10101000E704E90A008326AD36FDA1AD36E704B04A
+:1010200000C3F6069336207503B004C3E8D504B0B8
+:1010300000C3F6069336807503B001C326837F068E
+:10104000057503E99D00268B5704268B47082681EA
+:101050007F0600807508ED2689470AE99D002683F2
+:101060007F06017504EFE9920026817F06018075F5
+:1010700009EFED2689470AE9810026837F0602757C
+:101080000726214704E9730026817F060280750C3C
+:1010900026214704ED2689470AE95F0026837F065B
+:1010A00003750726094704E9510026817F0603805E
+:1010B000750C26094704ED2689470AE93D00268379
+:1010C0007F0604750726314704E92F0026817F0635
+:1010D0000480750C26314704ED2689470AE91B0078
+:1010E000B001C3FA53268B4F080BC9740C8D1EE058
+:1010F000FEE852FF83C308E2F85BFBB000C3F606CC
+:10110000933680750AF6069336207503B001C38DB9
+:101110003EE0FEE500268905E50226894502A1ADEF
+:101120003626894504E50626894506E508268945CB
+:1011300008E50A2689450AE50E2689450CE5482674
+:1011400089450EE54A26894510E54C26894512A1B8
+:10115000B73626894514E55026894516E552268975
+:101160004518E5542689451AE5562689451CE55853
+:101170002689451EE56226894520E56426894522A3
+:10118000E56626894524E56826894526E56A268997
+:101190004528E56C2689452AE5702689452CE572A7
+:1011A0002689452EE57426894530E576268945321F
+:1011B000E57C26894534E57E26894536E580268905
+:1011C0004538E5822689453AE5862689453CE58805
+:1011D0002689453EE59A26894540E59E2689454271
+:1011E000E5CC26894544E5CE26894546E5D02689C5
+:1011F0004548E5D22689454ABA0001ED1106663414
+:101200007304FF0668342689454CBA0201EDC1E03B
+:101210000211066E347304FF0670342689454EBAF7
+:101220000401ED11066A347304FF066C3426894507
+:1012300050BA0601EDC1E002110672347304FF06D4
+:10124000743426894552BA0801ED26894554BA0AF4
+:1012500001ED26894556BA0C01ED26894558BA0E8E
+:1012600001ED01067A342689455EBA1001ED268922
+:10127000455CB000C3F6069336807407F6069336D5
+:10128000207503B001C326807F06007530803E952F
+:1012900036007452C6069536008326AD36FEA1ADE3
+:1012A00036E704BA1001B88080EFEDBA1001B80239
+:1012B00002EFEDBAE000B80010EFB000C3268B4794
+:1012C000043D000074203D0300771BBA1001B802F2
+:1012D00000EFBAE000B80110EF830EAD3601A1AD0A
+:1012E00036E704B000C3B006C3F606933680750334
+:1012F000B001C326837F0401740A26837F0402742D
+:1013000019B006C326837F060C77F626837F0A6012
+:1013100077EFE81000720BB046C3E84E007203B0DE
+:1013200046C3B000C351B10A8B3E20F326837D0C27
+:10133000027503E90E00FEC9740781C72001E9EBBD
+:10134000FF59F8C3578D7D0E8D7706B91200F3A4AF
+:101350008D7D208D36E0FE268B4D12F3A4FF060115
+:10136000355F26C7450C010059F9C351B10A8D3EBE
+:1013700020F38D36E0FE26837D0C01751B57E82592
+:10138000005F731433C0B92001F3AA26C7450C02CD
+:1013900000FF0E013559F9C3FEC9740781C720014A
+:1013A000E9D3FF59F8C351268B4D128D7D20F3A64A
+:1013B000740359F8C359F9C300000000000000008D
+:1013C000803EEC34067233FF06F03350C41E8C3678
+:1013D000B90F0033C0E82900588126C234DF7F816D
+:1013E00026E934DF7F0BDB741126C6078426C64747
+:1013F00002FF26894706E8AC00C3FF06EA33E9F599
+:10140000FF57268B3F03F9263B7F027416263B7F4E
+:10141000047C2A3D000075138D7F0803F9263B7F6D
+:10142000027C14FF06DE3333DB5FC3268B7F02268C
+:10143000893F03F9E9060026893F26290F26C705BB
+:10144000FFFF26873F26890D8D5D02508BFB83E9C8
+:101450000233C0F3AA58FE0EEC345FC38B7C023B10
+:101460003C742F833DFF750B8D7C08897C02833D86
+:10147000FF741E8A45023C81750C803EEB3400747B
+:101480000533C0E90B008B0D014C028D750283E919
+:1014900002C3803EEC3406720533C0E9F3FFFF0659
+:1014A000EE33E9BEFFF6069236407401C35756513B
+:1014B000528B368C36E8A4FF7503E91A00E91C004C
+:1014C000FE06EC34C43E8036F3A4800E923640BA59
+:1014D0000C01B88080EFED5A595E5FC3FF06E03320
+:1014E000803C81750CFF06E233C606EB3401E9CF80
+:1014F000FF803C847507FF06E633E9C3FFFF06E87B
+:1015000033E9BCFF8D3EE0FEA17234C706723400A1
+:10151000008905A17434C70674340000894502BAF5
+:101520000401ED894504C745060000A16E34C706D5
+:101530006E340000894508A17034C706703400007D
+:1015400089450ABA0001ED89450CC7450E000032F5
+:10155000E4BA0E01EC894510A17E34C7067E340042
+:1015600000894512A18C34C7068C340000894514CB
+:10157000A18A34C7068A340000894516A17C34C785
+:10158000067C340000894518A18834C706883400D9
+:101590000089451AA1CA33C706CA33000089451C11
+:1015A000A17834C7067834000089451EA1C634C727
+:1015B00006C6340000894520C3000000000000007A
+:1015C000FA33C08ED88EC0B8A001C1E8048ED08D89
+:1015D000268000E80001E810EB8B1EF7348B16F92B
+:1015E000348B36FF3433C0B9EFFF8D3E14002BCF60
+:1015F0002BCED1E9F3AB891EF7348916F93483FE7B
+:1016000000740CB9EFFFBF80FE2BCFD1E9F3ABB96B
+:10161000FFFF81E9003B83FE007403E91B00511EBC
+:10162000B800E08ED833F68D3E00D8B9000CF3A593
+:101630001F59BEFFFF81EE00D82BCE81E100FF894C
+:101640000EAC338D062002C1E804A332348ED036AE
+:10165000C7061E00801836C7062200FF7F36C70661
+:101660000A00FFFF36C7061C0080008D06A002C1DD
+:10167000E804A330348ED036C7061E00502836C783
+:10168000060A00FFFF36C7061C008000B8A001C193
+:10169000E804A33434A3F2338ED08D268000B80042
+:1016A00090E7028D3E70018BC7C1E804B903008941
+:1016B000450E894502C705FFFF83C710050100E2FB
+:1016C000EEE85B01E5CEA3B536E82100E84501A1CF
+:1016D00032348CCBCD370E58A900F0740733F6891D
+:1016E00036FF34C38D3630618936FF34C333C08B47
+:1016F000D08BF2B968002E80BCAC17807501EF83E7
+:10170000C20246E2F1B80200E750B95A0033FFC7FF
+:101710000565188C4D0283C704E2F433C08EC08C7B
+:10172000C88ED88D3E80008D369C17B90800E837EA
+:10173000008D3620218D3EC000B90D00E829008DB6
+:101740003E4001B90A00E81F00E84B0E33C08ED8B6
+:10175000C7064E376F17E748E74CB8409CE74AE5A5
+:101760004890B80070E748C3A583C702E2FAC3E512
+:101770004CC35051565752061E33C08ED8E558D12F
+:10178000E073118BF0D1E633C08ED88BB480008328
+:10179000C60BFFE61F075A5F5E5958CF581CE41C62
+:1017A0006C1C8E1AC01F401A441C6518808080FF74
+:1017B00080030280FFFFFFFFFFFFFFFFFFFFFFFF30
+:1017C000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF29
+:1017D0008003034380800280420302FF0301030170
+:1017E00001030203FFFFFFFFFFFFFFFF02030103EF
+:1017F00003FF0101FF01FF0101030303FFFFFFFFDF
+:10180000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFE8
+:10181000FFFFFF02B80F00E784B80FF8E782C3B9F3
+:101820000800890EE63A8D0620038BD0C1E804A398
+:1018300090018BC28BD8C1E8048EC005610026A33D
+:101840000000A1303426A3020083C314D1EB268903
+:101850001E080081C21006E2D926C7060000FFFF5D
+:101860008C069201C35051565752061E33C08ED873
+:10187000E75AFF06BE33BAD200EDCF0000000000E9
+:101880008CCBA13034CD37E906EDB83200C3E88CFB
+:1018900001FE06E234E8210175F0E8530E810EAF37
+:1018A0003600C0C706AD366000F706E63480007526
+:1018B0001AF706E63400087409C706AB360B00E9D0
+:1018C0000F00C706AB360300E90600C706AB3611AA
+:1018D0009CC706A9361800F706E6348000750DF798
+:1018E00006B53602007405830EA93620A1A936E795
+:1018F00000A1AB36E702F706E6348000742EE8F26A
+:101900002F33C00D4100E756A1B1360D0010E70896
+:10191000A1B336E70AA1AF36E706B84000E74E3379
+:10192000C0E70EC70626020000E92300C7064E37AF
+:101930003F208E06303426F7060A00008074072602
+:10194000810E08000080C606E03401B80000C3FE26
+:1019500006E134C606E03400A126020BC07401C3C0
+:10196000E80400B80000C3A1A936E7008B1EAB361F
+:1019700083E306E50225F9FF0BC30D1000E702A182
+:10198000AD36E704C3B80A00E784FE06E534C606B0
+:10199000E334018E06303426F7060A00004074074F
+:1019A00026810E08000040C3C7064E376F17FE069B
+:1019B000E434C606E33400C3C3F606183480750D5C
+:1019C000A118340B061A340B061C347501C3A12E62
+:1019D0003425FFFE8B16E73681E200010BC2A32EF1
+:1019E000348D161000BF0000B908008B850034EF5D
+:1019F00083C2108B850234EF83C2108B850434EFD1
+:101A000083C2E283C7064975E2B800008EC0BE00FB
+:101A100034BFB936B91800F3A5B80000C333C08E7F
+:101A2000C08D3EB033B90800F3AB8D3E3E34B903F0
+:101A300000F3ABC300000000000000000000000045
+:101A40005051565752061E33C08ED8E75AFF06BA79
+:101A500033E5560D2000E756BA7A00ED0826943695
+:101A600033C0B10832ED068EC08D3EE0FFF3AA8E82
+:101A700006323426810E0800000207E55625DFFFF6
+:101A8000E756E9F8FC00BD1B101BD91AF31A505198
+:101A9000565752061E33C08ED8E75AFF06B6335348
+:101AA0000651E580A3B4338BD88BC8251000A3ED75
+:101AB000340BC07414FF068034803EFE340074037F
+:101AC000E90600B88000E89D0483E303D1E32EFF1C
+:101AD00097861A59075BE9A4FCBA20008E063C34AD
+:101AE000833E3C34007503E9F000C7063C34000037
+:101AF000E92A00BA10008E063A34833E3A34007563
+:101B000003E9D5FFC7063A340000E81000E9C9FF31
+:101B1000BA10008E063A34C7063A34000026A114E3
+:101B20000026A30C0026A1160026A30E0026C6063A
+:101B30000A0000C1EA0223D1741CBA200026C7069D
+:101B40000E00EA05260B160C002689160C00FF066F
+:101B50008634FF06DC3326A10C00A9003774162654
+:101B6000C6060A0002A900307404FF067A34FF0694
+:101B7000DA33E94900C0EC0783168A340024073CB5
+:101B8000077504FF068C34FF067E34A130348CC305
+:101B90008EC08EDB26830E0800408CD82687061662
+:101BA0000026833E1400FF740A8EC0268C1E00009F
+:101BB000E90500268C1E140033C08ED8C3C38CC028
+:101BC000870692013DFFFF740D8ED88C060000330E
+:101BD000C08ED8E904008C069001E80100C306839A
+:101BE0003E9001FF7429833E3A34007511BA860095
+:101BF000E81E008C063A34833E9001FF7411833E48
+:101C00003C3400750ABA8800E806008C063C3407AC
+:101C1000C3A190018EC026A10800EF26A1000026D6
+:101C2000C7060000FFFFA390013DFFFF7503A392CD
+:101C300001833EED3400740BB81000E784C706ED55
+:101C4000340000C35051565752061E33C08ED8E799
+:101C50005AFF06BC33E925FB5051565752061E3336
+:101C6000C08ED8E75AFF06B033E911FB50515657E2
+:101C700052061E33C08ED8E75AFF06B43306FF065D
+:101C80007634803EFE3400740407E9F0FAB8800030
+:101C9000E8D30207E9E6FA000000000000000000B7
+:101CA000C61D081D911E5D1E731E891E911EA81D56
+:101CB000911E911EAF1EAF1E151D151D911E991F61
+:101CC000000000000000000000040000000200000E
+:101CD00000010010000100400000000000010000B1
+:101CE00007E999FA5051565752061E33C08ED8E76D
+:101CF0005AFF06B2330668F61CE506A3B2338BF032
+:101D000083E61E2EFFA4A01CE50CA980007406E843
+:101D1000A401E506C353E50C8BD8A9010074148314
+:101D20003EE03A00740D8E063834E8BF06C706E080
+:101D30003A0000E5000D1800E700E5020D1100E78C
+:101D4000028BC35BA901007401C38BD0B80008E704
+:101D5000848BC28E06383426A30C008BD0C1E003DE
+:101D60008316883400FF067C3426833E06000A75FD
+:101D7000218BC22540183D4000740C3D00107512A7
+:101D800026FE0E0A00740BF706EF3420007503E9F7
+:101D90005A068CC0268E06020026830E08002026D6
+:101DA000A3120026A31000C3FF06C433E50CA9014B
+:101DB000007501C3A9F0077401C3FF06D433E50021
+:101DC0000D1800E700C3FF06CA33803EA036087531
+:101DD000148E06303426F7060A00000874072681A0
+:101DE0000E08000008E58225FDFFE782E50C50E5BE
+:101DF00080250007A3E43AE58C250080A3E23A5849
+:101E0000A902007525833EE23A00751E833EE43A3E
+:101E1000007517E5080D000425FF04E708E86A01CE
+:101E2000E5820D0200E782E92100E81A06803EE81B
+:101E3000FF00740A803EE8FF047403E90D00C60643
+:101E4000E8FF01BA0C01B80808EFED803E9F3606A6
+:101E50007505830E993640B80001E90901FF06CCEB
+:101E6000338126AF36FFF7A1AF36E706FF06C6344B
+:101E7000E91E00FF06CE33FF0695378126AF36FFF9
+:101E8000EFA1AF36E706E90800FF06D033FF067A78
+:101E900034FF06D233D1E68E0630342E8B84C01C3C
+:101EA00026090608002E8B84C21C09066637C3E586
+:101EB0000CA98000745650E8F00058A9000175077D
+:101EC000FF06C633E90800FF067834FF06C833E58D
+:101ED0008225FDFFE782E86E05BA1001ED803EE83D
+:101EE000FF00740A803EE8FF047403E91D00C60683
+:101EF000E8FF01BA0C01B80808EFEDE90D00C606CD
+:101F0000E8FF03BA0C01B80808EFEDC3A90100749B
+:101F10001CE82C00833EE03A00740F068E0638342D
+:101F2000E8C904C706E03A000007E95D008BD08EDF
+:101F300006383426A30C00E8060068691DE94A004B
+:101F4000A90004740AB80004FF06D833E91700A9F1
+:101F50000001740AFF063937B80001E90800A9102A
+:101F600000B81000741D090666378CC08E06303428
+:101F700026F7060A000001740726810E08000001FA
+:101F80008EC0C3FF06C233E9F8FFE5000D1800E775
+:101F900000E5020D1100E702C358E943FDE5080D15
+:101FA000000425FF04E708E9E0FFE50EA900087535
+:101FB00001C3E9F5FF000000000000000000000080
+:101FC0005051565752061E33C08ED8E75AFF06B8F6
+:101FD00033E548065357FF164E375F5B833E80015B
+:101FE000FF74588E06800126FF0E0800754D26A14D
+:101FF0000000A3800126C7060000FFFF8CC0268ECC
+:1020000006020026810E080080008BD02687061A63
+:102010000026833E1800FF740A8EC0268916000031
+:10202000E905002689161800833E8001FF740C8E96
+:1020300006800126833E08000074B307E93EF7E5F9
+:102040004C90E502A90020740D25FFDF0D0100E78B
+:10205000020D0020E702E50A8BD8A3F43325C3570D
+:102060000D0010E70AF7069B3600807437F7C300AF
+:10207000807406F7C30008745D8126C2347FFFC7F1
+:102080000635370500B88003CD3981269B36FF7FA2
+:10209000C7060F370400F7069B3640007506C706D3
+:1020A0000F370300F7069B360020742AF7C3000899
+:1020B0007424803E9D36067C1DFF069434830E6694
+:1020C00037208E06303426F7060A000001740726F2
+:1020D000810E08000001F7C30020753BF7069A3710
+:1020E0008000740BFF06893733C0E70EE90400FF58
+:1020F000063B37F7069B360020741C80269E36FF71
+:1021000075158E06303426F7060A00000874072677
+:10211000810E08000008C3C300000000000000009A
+:1021200002230223022302230323DD220223FD21B3
+:102130000223A424F32402238D227A23022397244A
+:102140001B247524022302238E25FB8E067E01FBB1
+:1021500026833E0000FF74F2268E060000FA268BCE
+:102160001E080026231E0A0074E58CC08ED0268B24
+:102170002602008C16F23322FF756A26A11C008A03
+:10218000E38ADC22D8750DD0E824F80AC075F2B0D5
+:1021900080E9EDFFD0E824F80AC07502B08032E48F
+:1021A00026A31C00F7C3080075472E8A9FC5252E5D
+:1021B0008BBFC52680C310268E1D268C1E06008B65
+:1021C000160000C7060000FFFF26891583FAFF7579
+:1021D0000A2E8B97CD26262116080033C08ED826CE
+:1021E000891E0400C38ADFB7002E8A9FC525E9E057
+:1021F000FF2683260800F783C310E9DEFF60061E72
+:102200006887256A001F8E06F2338B0E3434390E30
+:10221000F233740E26810E0A00000226810E080099
+:1022200000022689260200A3F2338ED08D2680007C
+:10223000368926020036891E200036C706080000AF
+:1022400000B90400BE00002E8BBCC52636C705FFB2
+:10225000FF36C74502FFFF83C602E2EB8E067E0112
+:10226000368B0E22008CC026833E0000FF268E0691
+:1022700000007407263B0E22007DEA368C06000023
+:102280008EC0268C160000FB36FF2E1E00061E6830
+:102290008B256A001F2609360800F7C600FF740167
+:1022A000C356522E8BB4C52581E6FF002E8BB4C5D4
+:1022B000268CC28EC026C7060000FFFF8EC2268372
+:1022C0003CFF740F8BD0268754028EC226A30000D9
+:1022D000E90700268944022689045A5EC3061E685F
+:1022E0008B256A001F8E06F23326A30A0026892654
+:1022F0000200A134348ED08D2680008C16F233E992
+:102300004DFECF501E525333C08ED826833E04005C
+:10231000FF26C706040000007403E91A00833EE6A6
+:102320003A027613FF06D6338CC08E063234BE4096
+:1023300000683A23E95EFFE884F85B5A1F58CFE84B
+:10234000E10026C606180010268A1E2900881E1BDA
+:102350003726C7060C00FF7F26A10E00E79C26A1AA
+:102360000800E79AE50080FB0874090D18ACE70047
+:10237000071F58CF0D1800E9F4FF501E0633C08E1A
+:10238000D8833EA1360075B7268B3606002EFF9403
+:10239000DC23071F58CFE88A00E5000D1800E7008E
+:1023A000E84900C353F706EF342000752DE58C256E
+:1023B00000708BD8E58C2500703BC374058BD8E981
+:1023C000F2FF3D00307510E50225EFFFE702C7067A
+:1023D000E03AFFFFE90300E812005BC3A323962362
+:1023E000A423A4239623A4239623962326A029007E
+:1023F000A21B3726C7060C00FF7F26A10E00E79C14
+:1024000026A10800E79AE50025FF53268B36060033
+:1024100083E60E2E0B84AD25E700C3061E688B25D0
+:102420006A001F830EEF3420830E9B3608E50025DB
+:10243000EFFF0D0800E700E500A910007501C3E5F6
+:1024400000A9100075F9C350535156061E33C08EB3
+:10245000D8B80500E784E5080D000425FF04E70867
+:10246000E5000D1800E700E5020D1100E7021F0767
+:102470005E595B58C3501E33C08ED8C706EF340078
+:102480000083269B36F7E5000D1800E700E5020DF6
+:102490001100E7021F58CF60061E6887256A001FDB
+:1024A000E816F5C3061E688B256A001F8EC02683BA
+:1024B0003E0A00007403E8430026C7060A00FFFF37
+:1024C000268B1606008E1E8E018CD88BCA833E008A
+:1024D00000FF8E1E0000740A2B16080073EB290EF5
+:1024E000080026890E0800268C1E00008ED88C0657
+:1024F0000000C360061E6887256A001F8EC08BC857
+:102500008E1E8E0126C7060A0000008CD8833E006E
+:1025100000FF74253B0E00008E1E000075ED8ED866
+:1025200026A10000A300003DFFFF74568ED826A10F
+:10253000080001060800E94900268E1E0200BE18A8
+:1025400000833CFF743C390C74198E1CBE00008360
+:102550003E0000FF742C390E000074078E1E000030
+:10256000E9ECFF26A10000890433C98ED93DFFFFA5
+:10257000751083FE18750B268E1E0200812608003A
+:102580007FFF33C08ED8C31F0761CF1F07CF600600
+:102590001E6887256A001FE506251E003D1E007582
+:1025A000F6B90800E558E75A23C0E0F8C300000078
+:1025B000000000000000AC000000A8008C02040035
+:1025C0000008102000FF0E0C0C0A0A0A0A0808086E
+:1025D0000808080808060606060606060606060691
+:1025E00006060606060404040404040404040404A1
+:1025F000040404040404040404040404040404049B
+:1026000004040404040202020202020202020202A0
+:10261000020202020202020202020202020202029A
+:10262000020202020202020202020202020202028A
+:10263000020202020202020202020202020202027A
+:102640000202020202000000000000000000000080
+:10265000000000000000000000000000000000007A
+:10266000000000000000000000000000000000006A
+:10267000000000000000000000000000000000005A
+:10268000000000000000000000000000000000004A
+:10269000000000000000000000000000000000003A
+:1026A000000000000000000000000000000000002A
+:1026B000000000000000000000000000000000001A
+:1026C00000000000001800140010000C00FF7FFF45
+:1026D000BFFFDFFFEFFFF7FFFBFFFDFFFE7FFFBF49
+:1026E000FFDFFFEFFFF7FFFBFFFDFFFEFF00000036
+:1026F000803EE234017603E9A500B80000E74EB958
+:102700002800E2FEC606453702BF3F282E8B45084B
+:10271000E74EB92800E2FE2E8B1DC706B3364011E6
+:10272000C706B1362700C70646370200C706483736
+:102730006400F706B5360200751C2E0B5D0281267B
+:10274000B336FFFEC706B1369C00C7064637080001
+:10275000C70648379001891EB736891EFE33BE2052
+:10276000008BC3E74EB92800E2FE2E8B4504E74EEE
+:10277000B92800E2FEE54E8BCB2E2345062E234DD5
+:10278000063AC174364E75D9803E453700740BC683
+:1027900006453700BF2F28E972FFC606453701F707
+:1027A00006B53602007414E5CE25FDFFE7CEE843FA
+:1027B00000E5CE0D0200E7CEE83900803EE23401AC
+:1027C0007601C3B8EA05E78CFAE812F4FB8D06D06F
+:1027D000398BD8C1E804A338348EC0A1303426A385
+:1027E000020026C7060000FFFF83C318D1EB26892D
+:1027F0001E0800C3E5020D0040E702E5000D0400DD
+:10280000E700B80000E70AE50AA900807514E508AA
+:102810000D0010E708E50A0D0008B90500E70AE217
+:10282000FCC3E5080D0010B90500E708E2FCC3048D
+:102830000C2000010C7EFF000C0200100040000C78
+:10284000C6010000C0F7FF00C002001000400000F9
+:1028500033C08ED88D3E72498D36B037B914008B97
+:102860001E3034895C022E8B45028944062E8B056E
+:1028700089440483C70483C610E2E8C6069E360E68
+:10288000E8FD26688328A1AA02CD35833EA1360043
+:102890007403E93B2733FF8E06A6028B36A4022E73
+:1028A000FFA42E30830E993604C70637370100C6C1
+:1028B00006CA3401E97D19803EA0360874E68026F8
+:1028C0009E36FF751AF7069B3600207412F7069B9A
+:1028D000360300750A830E663710C606A03608E96F
+:1028E000FB01803E9E360275CEC606A03606E9EC98
+:1028F00001C3E9E80126C7060A00000026FF2604F6
+:1029000000A1D1362639061A007522A1D336263900
+:10291000061C007518A1D5362639061E00750E2630
+:10292000F7060C0040007405830E663740810EAF39
+:10293000360010A1AF36E706803E9D36027506CD03
+:1029400034E9A21AC3F7069B361000755426F60622
+:102950000A00FF754C26A0190024C03C4075118068
+:102960003E953600743B26C7060400FFFFE93100A0
+:10297000E8F104F7069B360300742F8BD8B87D036B
+:10298000CD3A8BC3C606A03606F7069B3602007505
+:1029900005C606A03604810E9B36800083269B3632
+:1029A000FCE92301E8871DE933015026A10C00252D
+:1029B00007003D07007503E984003D05007503E944
+:1029C0007C00833EE83A047475833EE83A02746EF4
+:1029D000F706E63418807503E96A00F706E6340066
+:1029E00080743526803E290002752D5156578D364C
+:1029F0003E348D3E2000B90600F3A65F5E59744553
+:102A000026A12000A33E3426A12200A3403426A103
+:102A10002400A34234E92600F706E6340800740BCC
+:102A200026803E1900007403E91300F706E634100F
+:102A300000741226A02800C0E80422C0740726C72C
+:102A4000060400FFFF5823C07403E957FF81269B4B
+:102A500036FFFE83FE067F2426A120003B06D136EA
+:102A6000751A26A122003B06D336751026A1240034
+:102A70003B06D5367506810E9B36000126A1200047
+:102A8000257FFFA3B83426A12200A3BA3426A124AF
+:102A900000A3BC348BC686C4A3C034D1E680FC0935
+:102AA0007403E8AA1C8BC62EFFA4304926A10C0093
+:102AB0003DFF7F740F26FF2604008E063834E8366B
+:102AC00006CD50C3E91600CD34E91100CD34893666
+:102AD0003D37A19D36A33F37C606A0360CE88E00D1
+:102AE000A19F3622E47532F7064C370100752AF6AD
+:102AF000069D3680740788269E36E931003A069D89
+:102B000036A39D3674288BF02EFFA40D2B4429EE9E
+:102B1000421944CD442F455A453A269E367501C385
+:102B200032C086C48BF0A29E362EFFA420498B2E85
+:102B3000993623ED7501C3BF0100BE000085FD7508
+:102B40001A46D1E7E9F6FF2A0029002800270025C8
+:102B50000005000700260006002000F7D7213E9957
+:102B600036D1E62E8BB4472BE94FFFE956FF80267E
+:102B70009E36FF7517F7064C370100750FF6069D58
+:102B800036807408F7066637FFFF7507C706663795
+:102B90000000C3F70641370100750BB87F03CD393C
+:102BA000C7064137010033F6B80040850666377422
+:102BB0002180BC5437FF7404FE84543780BC9634A3
+:102BC000FF7404FE84963431066637833E66370010
+:102BD000740546D1E873D4C3A1F433A90088740BFB
+:102BE000A9001075098B1E4337FFE3E9D700C7061C
+:102BF00035370500C70643371E2CF706F4330008A7
+:102C00007406C7064337102CB88003CD39E9CDFED2
+:102C1000A9000874D9FF0E353775EDE96600A900E3
+:102C20000875CBFF0E353775DF810EC234C000F654
+:102C3000069D36807448810E9B360080F7069B36D1
+:102C40000100741EB87D03CD3A810E9B368000834F
+:102C5000269B36FEC7060F370200C606A03604E9DB
+:102C60007BFE803EA036047507833E0F3701750555
+:102C7000C606A03606C7060F370200E95FFEBE0291
+:102C800000E94AFE80269E36FF753AF6069D36809C
+:102C9000742DF7069B360020752BC606A03606FF5E
+:102CA000069434830E6637208E06303426F7060AE3
+:102CB000000001740726810E08000001E90600BE2D
+:102CC0000400E909FE810EAF360008A1AF36E70621
+:102CD000E50AA90080740E8126AF36FFF7A1AF3652
+:102CE000E706E909FFE9F5FDC70641370000830E55
+:102CF000993602E9E7FD80269E36FF751DF7069B93
+:102D00003600407505830E993608830E993620816A
+:102D1000269B36FFBFB88503CD39E9C0FD803E9EB6
+:102D200036067407803E9E360A7534F6069D368058
+:102D30007506BE0700E996FDC606A03604833E0F61
+:102D40003702741BC7060F370400803E9E36067597
+:102D50000EF7069B3640007506C7060F370300E9DD
+:102D60007BFD803E9D36047512810EC2340040FF0B
+:102D7000069234C606A03606E962FDBE0500E94D9E
+:102D8000FDF6069D36807519830EC23404BE06001A
+:102D9000E93BFD80269E36FF75C5FF063137E90009
+:102DA000008326C234BFC606A03606E92FFDE50A19
+:102DB0005025C3BFE70A5880269E36FF750DA9002F
+:102DC000407508C606A03606E912FDB88303CD3962
+:102DD000C3B87C03CD39F706F43300107509C70674
+:102DE00033370200E9F6FCFF0E33377403E9EDFCDC
+:102DF000FF068E34E8F719830EC23408BE0300E9DB
+:102E0000CCFC0000000000000000000400040405E9
+:102E1000040404000300030300000000000000009D
+:102E20000004000808050808080003000303000068
+:102E3000020404040400000800000A1400001A0040
+:102E40001C001E2000000441060B08C2FFE704031B
+:102E500006040405040604870403060404854EA240
+:102E600004CF04CDC706A2370000C706A63700006E
+:102E700026A12000257FFFA3F53626A12200A3F777
+:102E80003626A12400A3F936E83B198BF0268B0ED9
+:102E90000E002BC883E90EB8018083F9047C51260B
+:102EA0008A542888161C3740268B6C2686CD3BCD4D
+:102EB00086CD890EA43775384032FF268A5C29807A
+:102EC000FB15772580FB0A742080FB01741BB80476
+:102ED000802E3A97022E74072E3A97182E751133CA
+:102EE000C080FB09754F8BF3C326C7060400FFFFA4
+:102EF0005052A1A43786C4263B0626007C32268188
+:102F00003E260000047E298D742A268B1422D2745A
+:102F10001F80E6BF80FE097517C706A23701008033
+:102F2000FA04750C268B4402A3033786C4A3D0345D
+:102F30005A58E9B1FFBD72372E8A872E2E22C074EF
+:102F40001605442E8BF82E8B053E89460083C5025C
+:102F500083C70222E47DEF8D742A83E9047503E9B7
+:102F6000A100268B1422D27503E97C00C706A63780
+:102F70000100BF72378B0583C70280E6BF80E43F44
+:102F800080FE09752280FA04755EC706A23701002B
+:102F9000268B4402A3033786C4A3D03486C4C70655
+:102FA000A6370000E947003BFD7E15268B04A840AC
+:102FB0007406B80780E938FF32C0268B04E92E007A
+:102FC0003AF475B1C745FE000080FE22750D3AD077
+:102FD0007716C706A6370000E913003AD07509C76F
+:102FE00006A6370000E90600B80580E902FF32F6C0
+:102FF00003F22BCAB8058023C97603E964FF740382
+:10300000E9EDFE33C0BF72378B1547473BFD7F1B91
+:10301000F6C6807416F706A63701007406B8088055
+:10302000E9C3FEF6C64074E0B80780E9B8FE7D4209
+:10303000A34544294429B728E228EE2BF228F52895
+:103040000129AC2A4429442944294429442900005F
+:10305000733600000336C535833545350735D23420
+:1030600045340000000000000000000000000000E7
+:103070000000A6380000E03800000000000000005A
+:103080000000000000000000000000000000000040
+:10309000F2330000A6336033FD32BC3277323C326B
+:1030A000FB316A310A31E0E0101010E0E0E0E000AE
+:1030B0000000000000000000000000000000000010
+:1030C000000000000000E000E0E0E0E0E0E0E0E020
+:1030D000E033FF26F6061A0080741B2680261A00AD
+:1030E0007F268B3E260083E71F740B26800E200070
+:1030F0008026013E0E00C3602E8B84A63026A318C6
+:1031000000D1E62EFF94503061C326C7060400C4E8
+:103110002A26C7060E00160026C706060006002649
+:10312000C606190000E8BF05E8980526C706260070
+:10313000000826C60628004026C60629002ABF2AFF
+:103140000026C6050426C645012AA1933733DBA90C
+:1031500040007502B301A900107402B788A90008E5
+:10316000740380CF4426895D02C3830EC2342026B7
+:10317000C70604006B2B26C7060E00300026C706C4
+:1031800006000A0026C7060A00040026C606190023
+:1031900000E86905E82C0526C7062600002226C699
+:1031A0000628006026C606290029BF2A0026C60573
+:1031B0000826C645012D8D7D02BE5437B90300F3A4
+:1031C000A526C6050826C645012E8D7D02BE5A37A6
+:1031D000B90300F3A5E8D405E86405B90600BE54B8
+:1031E000378D2E2C00268B4600290483C60283C50A
+:1031F0000283F90475024545E2EBC326C7060400C5
+:10320000C42A26C7060E00240026C70606000600AC
+:1032100026C606190000E8E404E8A70426C7062627
+:1032200000001626C60628006026C606290028BF0C
+:103230002A00E85B06E87405E80405C326C706040F
+:1032400000C42A26C7060E001A0026C70606000676
+:103250000026C606190000E8A304E8660426C7068F
+:103260002600000C26C60628006026C60629002770
+:10327000BF2A00E82105C326C7060400C42A26C7C2
+:10328000060E00200026C70606000A0026C7060A0A
+:1032900000040026C606190000E84B04E8240426B2
+:1032A000C7062600001226C60628004026C60629A4
+:1032B0000026BF2A00E8F404E88404C326C70604F5
+:1032C00000C42A26C7060E00340026C706060006DC
+:1032D0000026C606190000E80D04E8E60326C70626
+:1032E0002600002626C60628004026C606290025F8
+:1032F000BF2A00E8B604E84604E8FA04C326C70675
+:103300000400C42A26C7060E003800A1A237500BBD
+:10331000C0750726C7060E00340026C7060600063D
+:103320000026C606190000E89903E8A4FD26C74553
+:1033300026002A580BC0750626C745260026A11C64
+:1033400037C1E0042688452826C645292483C72A94
+:10335000E82904E8A004E82205E8F803E80904C322
+:1033600026C7060400C42A26C7060E00320026C758
+:10337000060600060026C606190000E84503E850C8
+:10338000FD26C745260024A11C37C1E00426884538
+:103390002826C645292383C72AE8E003E86C04E809
+:1033A0008A04E89C04C326C7060400C42A26C7066C
+:1033B0000E00340026C7060600060026C6061900C1
+:1033C00000E8FF02E80AFD26C745260026A11C37B3
+:1033D000C1E0042688452826C645292283C72AE855
+:1033E0009A03E8C703E85703E8F803E87804E88A93
+:1033F00004C326C7060400744526C7060E003E0017
+:1034000026C7060600060026C7060A00040026C6D0
+:1034100006190000E8FC02E8A902833E8D37037517
+:10342000019026C7062600003026C6062800502632
+:10343000C606290020BF2A00E8D003E80103E8B54A
+:1034400003E89F03C326C70604006143B9F0008365
+:10345000E90226890E0E0026C7060600020026C6CF
+:103460000619000026C7061A00000026C7061C0021
+:10347000000026C7061E000000E8470283E90E860A
+:10348000CD26890E260086CD26C60628000026C633
+:1034900006290008BF2A0083E90426890D26C645AF
+:1034A00001268D7D0283E902BB0100B830304B75E7
+:1034B00017BB0A008AC4268805B03180C40180FC8D
+:1034C0003A750AB461E90500268805040147497583
+:1034D000DDC326C7060400044526C7060E001200F9
+:1034E00026C7060600060026C606190001E8E50103
+:1034F000E8D00126C7062600000426C606280000DC
+:1035000026C606290007C326C7060400C42A26C704
+:10351000060E00200026C7060600060026C606196D
+:103520000006E80402E89B0126C7062600001226D2
+:10353000C60628000026C606290006BF2A00E86B3A
+:1035400002E8FB01C326C7060400C42A26C7060EEC
+:1035500000200026C7060600060026C6061900053C
+:10356000E8C601E85D0126C7062600001226C60649
+:1035700028000026C606290005BF2A00E82D02E81B
+:10358000BD01C3FF06823426C70604003D4126C79D
+:10359000060E00200026C70606000E0026C60619E5
+:1035A0000004E88401E81B0126C706260000122655
+:1035B000C60628000026C606290004BF2A00E8EB3C
+:1035C00001E87B01C326C7060400674226C7060E32
+:1035D00000200026C7060600080026C606190003BC
+:1035E000E84601E8DD0026C7062600001226C606CA
+:1035F00028000026C606290003BF2A00E8AD01E81E
+:103600003D01C3FF06843426C7060400674226C76F
+:10361000060E00240026C7060600080026C6061966
+:103620000002E80401E89B0026C7062600001626D3
+:10363000C60628000026C606290002BF2A0026C6A4
+:10364000050426C6450101A10F3786E0F6066F374F
+:1036500001750F3906CC3474098BD8B88903CD397C
+:103660008BC3A3CC34268945028D7D04E83D01E857
+:10367000CD00C326C7060400C42A26C7060E001CB8
+:1036800000A1A237500BC0750726C7060E00180010
+:1036900026C7060600060026C606190000E8230015
+:1036A000E82EFA26C74526000E580BC0750626C719
+:1036B0004526000A26C645290083C72AE8BD00E83A
+:1036C000FF00C3565751B90300BED136BF2000F3E7
+:1036D000A5595F5EC3565751B90300BED136BF1A14
+:1036E00000F3A5595F5EC326C7061A00C00026C7AF
+:1036F000061C00000026C7061E000010C326C706D1
+:103700001A00C00026C7061C00000026C7061E00BF
+:103710000008C326C7061A00C00026C7061C000002
+:103720000026C7061E000002C326C7061A00C000F6
+:1037300026C7061C00FFFF26C7061E00FFFFC32684
+:10374000C6050826C64501028D7D02BE0537B903B0
+:1037500000F3A5C326C6050426C6450106A10D37FC
+:10376000268945028D7D04C326C6050426C645016B
+:1037700007A10B372689450283C704C3A1A2370BD3
+:10378000C0741326C6050426C6450109A1033726C1
+:1037900089450283C704C326C6050826C64501021B
+:1037A0008D7D02BE0537B90300F3A5C326C6050605
+:1037B00026C645010B8D7D02BEEF36B90200F3A58A
+:1037C000C326C6050626C6450120A16837268945B9
+:1037D00002A16A3726886505C1E00426884504836E
+:1037E000C706C326C6050426C645012126C74502CD
+:1037F000000083C704C326C6051426C64501228DD2
+:103800007D02BE1F37B90900F3A5C326C6050C26E5
+:10381000C64501238D7D021E0E1F8D364054B9030F
+:1038200000F3A533C0B90200F3AB1FC326C60508D9
+:1038300026C64501288D7D02BED136B90300F3A509
+:10384000C326C6050826C6450129A1C23486E0263E
+:10385000894502A19B362689450426884506268887
+:1038600045078D7D08C326C6050626C645012B8D56
+:103870007D02BEBB36B90200F3A5C326C6050626E7
+:10388000C645012C8D7D02BEE536B90200F3A5C305
+:1038900026C6050426C6450130A1373786E02689AD
+:1038A00045028D7D04C326C7060E001E0026C706EE
+:1038B0000600020026C606190000E86CFEE803FEBA
+:1038C00026C7062600001026C60628003026C60693
+:1038D000290011BF2A00E83500E84500E85500C37B
+:1038E00026C7060E00120026C7060600020026C6DE
+:1038F00006190000E832FEE8C9FD26C706260000CA
+:103900000426C60628003026C606290013C326C68C
+:10391000050426C645010C26C74502000183C704DD
+:10392000C326C6050426C645010E26C74502000269
+:1039300083C704C326C6050426C645012126C745FC
+:1039400002000083C704C300000000000000000064
+:10395000B339C939833AB339B339B3391C3A1C3A4C
+:10396000A3B634A1E936A31137A3D234A1EB36A311
+:103970001337A3D434A1ED36A31537A3D634A10150
+:1039800037A3CE34A1F736A31737A3DC34A1F93619
+:10399000A31937A3DE34F7069B360200750C33C03B
+:1039A000A09E368BF02EFFA45039E90F01BE070010
+:1039B000E919F1F6069D368074F3C606A03602C6F4
+:1039C000066E3708C606703702B88803CD39F6068A
+:1039D0006F3701754AA1D1363A06E93675413A2664
+:1039E000EA36753BA1D3363A06EB3675323A26EC09
+:1039F00036752CA1D5363A06ED3675233A26EE36C5
+:103A0000751DC606703702FE0E6E37750FB8880337
+:103A1000CD3A830E9B3612C606A0360CE9A8F0A15B
+:103A20000537263B0620007540A10737263B0622B6
+:103A3000007536A10937263B062400752CA09E365A
+:103A40003C02750826F6061800087547C6066E374C
+:103A500008FE0E7037751CC606703702E5020D01B0
+:103A60000425EFFFE702E95EF0C606703702C606DE
+:103A70006E3708E50225FFFB0D010025EFFFE70289
+:103A8000E944F0F7069B360001742526F606180077
+:103A90000875ED81269B367FFFB88903CD3AB8843F
+:103AA00003CD3AC606A036068326C234AFE917F026
+:103AB000A101373A260F377FC7E9F7FE83269B36E9
+:103AC000ECE82A0D810E9B368000BBFF7FCD53C6EC
+:103AD00006A03602E9F0EF830E9B3611C606A0362B
+:103AE0000CE9F9EF443B2C3BC72A6B3B443BC72A0C
+:103AF000C72AC72AA3B634810EC2340020F7064174
+:103B0000370100741B8CC3C70641370000B87F0320
+:103B1000CD3A33C08EC0BF5437B90600F3AB8EC365
+:103B200033C0A09E368BF02EFFA4E43AF7069B36F6
+:103B3000000175218326C234BFA1A936E700A19BED
+:103B400036E90900A19B3681269B36FFDFA90020BC
+:103B50007506E96E00E96FEF830E993604C70637E4
+:103B6000370100C606CA3401E95800830E9B36406F
+:103B7000E85800A105373B06E9367537A107373B02
+:103B800006EB36752EA109373B06ED367525FE0E80
+:103B90007137751CB88703CD3A830E993610A15042
+:103BA00037C7065037000009069936C606A0360802
+:103BB000E914EF830E993604C70637370300C606AB
+:103BC000CA3403C606A0360AE9FCEEA1D136263B6C
+:103BD0000620007515A1D336263B0622007512A1DA
+:103BE000D536263B062400750FC38D362000E90B21
+:103BF000008D362200E904008D36240083C402F7CC
+:103C000006E63401007415263A047708720E263A47
+:103C100064017208C606A03606E9ABEEE87C0A8CA1
+:103C2000C03DFFFF741B26C60618001026C70604F9
+:103C300000493C26C70606000C00CD50B94E00E2F4
+:103C4000FEC606A0360AE994EEE97BEE8F3C063DFF
+:103C5000063D063DD23CEA3C063D063DA3B6348116
+:103C600026C234AFDFC7064C370000B88A03CD3A0E
+:103C7000803E9D3604750C803E9E36067405C60651
+:103C80009F360633C0A09E368BF02EFFA44C3CF727
+:103C9000069B360020750E81269B36FFBFB88B032E
+:103CA000CD3AE95400F7069B3600017403E917EE9C
+:103CB000C70637370200C606CA3402830E99360497
+:103CC000830E503704F6069D3680752AE81F0BE9EF
+:103CD0002700F7069B36000175D3C7063737020069
+:103CE000C606CA3402830E993604C606A03600F60C
+:103CF000069D36807403E8DE0A81269B367CFFBB76
+:103D0000FFFFCD53CD54E9BEEDA3B634E8AD01B805
+:103D10008603CD39C7064C3700008126C234AFDF99
+:103D2000F6069D36807434F7069B3600207456F7ED
+:103D3000069B3600017427E83501721CBE004085E1
+:103D400036C23475080936C234FF069234E88B0156
+:103D50007306810E99368000E96CEDE9B500C7065F
+:103D600037370200C606CA3402830E993604830E22
+:103D7000503704803E9E36087403E85A0AE8EF0084
+:103D800072D6E9C8FF803E9E360A7512C606A03676
+:103D900000F7069B3608007402CD54E8390A8126E4
+:103DA0009B36FFBFE8C80072AFB88B03CD39E99CE2
+:103DB000FFF6069E36FF7558A3B634E8FE0081264E
+:103DC000C234FFBFF6069D36807448F7069B360066
+:103DD000207422F7069B3600407508E89100723087
+:103DE000E9220026A10C00A960007524810E663727
+:103DF0000008E9D2ECC7064C370000E871007210E9
+:103E0000B88B03CD39E8D3007306810E9936800054
+:103E1000E9B4EC803E9D3604750C803E9E360674F7
+:103E200046C6069F3606F7069B360001740C803E98
+:103E30009D36087505C6069F360AE8320072D1E83D
+:103E40009900803E9D36087513810E99368000F7E3
+:103E5000069B3600207508B88B03CD39E968ECC69F
+:103E6000069F360AE960ECB88603CD3AE958EC269D
+:103E7000A10C00A9600074088126C234FFBFF9C3F9
+:103E8000F7069B3600407413810E66370008E84A37
+:103E9000007306810E99368000F9C3810E9B3600AF
+:103EA0004080266F37FE81269B367FFFC606A036F0
+:103EB00000F8C3810E99360001E921EC26A120000B
+:103EC000A3FB36A3AA3426A12200A3FD36A3AC345B
+:103ED00026A12400A3FF36A3AE34C3A10537263B99
+:103EE0000620007519A10737263B062200750FA191
+:103EF0000937263B0624007505E80200F8C3511E69
+:103F0000068BC78D362000BF0537B903001E061F7C
+:103F100007F3A58BF88D362000BFA034B90300F35A
+:103F2000A5071F598BF8A10737A3A634A10937A30A
+:103F3000A834F9C3C606B63401E98BEBE887088BD1
+:103F4000F00512002629060E00268B442A263A0682
+:103F50000E00755B26832E0E000280FC277550260E
+:103F60008B442CA9FFFF75478BFE33C026F6453CDA
+:103F7000807406268A453A241F03F826807D450969
+:103F8000752D8CC28E0638348EDA8B0E0E00268983
+:103F90000E0E008D742CBF1800F3A433C08ED826EB
+:103FA000C7060400B53F26C70606000600CD50B878
+:103FB0000680E9EFE926A10C00A39337830E99361A
+:103FC00001E900EB26803E1C00FF752F26803E1E77
+:103FD00000FF752726F7060C004000751BA1D1369F
+:103FE00026A31A00A1D33626A31C00A1D53626A3EA
+:103FF0001E00B80A80E83607E9E2EAFF069034BE00
+:104000000A00C606B63401F6069D36807505830E95
+:10401000C23401E9B6EA803E9D360A750F26A10C2E
+:10402000002507003D04007503E87900A1F33686FA
+:10403000E0E71EA3E33681260B37000381260D3708
+:104040007B7F830E0D3748E81E0026A10C00250754
+:10405000003D0400740926F7060C0020007506B820
+:104060000100E93FE9E95FEAC70641370000B87F90
+:1040700003CD3AA11D37A3C43486E0687F031FA394
+:10408000060033C08ED8A10B37A3B234A10D37A3DD
+:10409000B434A1F336A3C834A1EF36A39C34A1F104
+:1040A00036A39E34C3800E9D3680BE0000E8B40760
+:1040B000B87B03CD3AB87C03CD39C706333702004D
+:1040C000A1E536E72EA1E736E73EB88203CD3AF701
+:1040D000069B3600207503E8FD06A1D336A3EF3614
+:1040E000A39C34A1D536A3F136A39E34C3F6069D16
+:1040F00036807431BE2200E91700F6069D368074C2
+:1041000024BE2300E90A00F6069D36807417BE24FB
+:104110000056E8A8058CC03DFFFF5E7405E8D7EFA8
+:10412000CD50E91FE8E99FE9000000000000000011
+:10413000B88403CD3AB88A03CD39E9F700803EA0B0
+:104140003608752EA9D007752CA1B1360D0004E7ED
+:1041500008E50025FF73E700B88A03CD3AE8C306F7
+:1041600033C0E70EE50A25C317E70ACD54C606A0FB
+:104170003600E968E9BE0400E93FE983269B36BFC3
+:10418000C606713703B88603CD3AB88803CD3AB86E
+:104190008303CD3AB88703CD39810EC2340020E9BC
+:1041A0009200E84906B88703CD39BBFF7FCD53B8ED
+:1041B0008403CD3AB88803CD3AB88B03CD3AB8839F
+:1041C00003CD3AB88603CD3AB88503CD3AC3E500AE
+:1041D00025FF53E700830EC234408326C234EFE844
+:1041E0000C06BBFF7FCD53B88A03CD3AB88503CD0B
+:1041F0003AB88603CD3AB88303CD3AB88703CD3AAF
+:10420000B88B03CD3AB88403CD3AB88903CD3AC30D
+:10421000830EC23450E81804E8D305F6066F370160
+:104220007512B88903CD39833E0F37007506C7066E
+:104230000F370400A19D3680FC087405B88403CDB7
+:1042400039E5020D010825EFFFE702A19D3686E062
+:1042500032E48BF0D1EE33C00D20000906AD36A15B
+:10426000AD36E704E953E8E95AE833C0A01B37D17B
+:10427000E03A06A0367503E9BAFFE960E8C70641EF
+:10428000370000E8C1E1E86A0633C00D4100E75697
+:10429000A1B1360D0010E708E50225F9FF0D030076
+:1042A000E702A1B336E70AA1AF36E706A1AD36E7CC
+:1042B00004E87C03E89F03C7061D3700C8C7060B48
+:1042C000370003C7060D377B7F33C0A39936A39B06
+:1042D00036A39D36A39F36A34C37A3F336A3EF3600
+:1042E000A3F136E882FDC6069F3602E9EFE7E50254
+:1042F0000D018825EFFF0D00400D0004E702E8F2F4
+:1043000005E50A0D4000E70A33C0A38137A38537CE
+:10431000A38337A38737A38937E5000D0084E7001F
+:10432000B88C03CD39B88000CD35C706AA02FFFF8F
+:10433000E50025FF7BE700810E9A378000B87E03F9
+:10434000CD3933C0E70EBE08008E063834E8A7ED3D
+:104350008326EF34DFFF068137CD50830EEF342004
+:10436000C3F7069A378000743DA9D0077410A900DE
+:1043700004741233C0E70EFF068737E9D2FFFF0649
+:104380008537E9CBFFFF068337E9C4FF83269A37D9
+:104390007FA18937030687373D05007F01C3BBFF37
+:1043A0007FCD53E90000E50225FFFB25EFFF0D015E
+:1043B00000E702A183373B0646377F2AA185373BBA
+:1043C0000648377C21A18937030687373D05007FE2
+:1043D00015C6069F3604E50225FFF70D010025EFFF
+:1043E000FFE702E9F7E6BE0100F7069B360300741B
+:1043F0000A83269B36FC830EC23404E9D0E6B87BE0
+:1044000003CD39E5020D016025EFFFE702C706F194
+:10441000342003B88E03CD39C38126C2347FFF8098
+:104420000E6F3701F7069B36030074D2B87B03CDBD
+:104430003AB87D03CD3983269B36EF33C0B08AA2CC
+:104440009F36A29D36C7064C370100C7060F3704BA
+:1044500000F7069B3640007506C7060F370300B805
+:104460008D03CD39E800D5E5020D014025EFFF8B26
+:10447000D8B87C03CD39C706333702008BC30D0093
+:104480002025F9FF0B06E83AE702C3FF0EF1347569
+:1044900001C3E54EA901007512E500A900047505E8
+:1044A0000D0004E700B88E03CD39C3E500A9000470
+:1044B00074F325FFFBE700E9EBFFC606A036048393
+:1044C000269B36FC810E9B368000E910E6B88E03F1
+:1044D000CD3ACD54810EAF360018A1AF36E706B8FD
+:1044E0007B03CD39A1D336A38F37A1D536A391371E
+:1044F000C7068B370200C7068D370200830E993638
+:1045000040E9D9E5803E9F36067515A9D00775ECC0
+:10451000250018750EFF0E8B3775E1C6069F36080D
+:10452000E9BAE5FF0E8D3775D3BE0800E99FE5B8FF
+:104530007B03CD39F7069B3600207408C6069F36EC
+:104540000AE90D00F7069B360040740BB88B03CDCB
+:1045500039810E99368000E983E5B87B03CD39C7F0
+:10456000068B370400C7068D370400810E9936008C
+:1045700002E969E5F6069D3680751BA9D00775EB43
+:10458000A90018750CFF0E8D3775E0E817FBE94C94
+:10459000E5B88203CD39C3FF0E8B3775CEBE090057
+:1045A000E92BE5C7063D370000C7069B360000E84B
+:1045B0003C028126AF36FFE7A1AF36E70681269B96
+:1045C00036FF7FE5020D010025EFFF25FFDFE70243
+:1045D000BBFF7FCD5333C0A39D36A39F36E8500069
+:1045E000E87300B88103CD39C3F7069B3603007426
+:1045F0000DC6069F3602C606A03600E9DFE4830E2C
+:104600009B3610C70699360000E8E702E5560D0212
+:1046100000E756C706A80200008B363D37E8440283
+:10462000C606A0360EE9B5E4000000000000000058
+:1046300006B88A03CD3AB88503CD3AB88603CD3A99
+:10464000B88303CD3AB88703CD3AB88B03CD3AB8D7
+:104650008803CD3A07C306B88803CD3AB87B03CDAB
+:104660003AB88203CD3AB87F03CD3AB87C03CD3A4D
+:10467000B87E03CD3AB88003CD3AB88103CD3AB8BD
+:104680008403CD3AB88903CD3AB87D03CD3AB88DCD
+:1046900003CD3AC7064137000007C3068E063834FB
+:1046A0001F8B0E0E0026890E0E00BE1800BF1800CC
+:1046B000F3A4061E07CD340733C08ED8C326F606F2
+:1046C000200080744433C026A02600241F8BF026CF
+:1046D0008B5C28891E6A37068E0638341FC0E304B7
+:1046E00026885C288BC6B90600BE2000BF1A00F3DE
+:1046F000A48BC883C706F3A426812626001F802624
+:10470000813626000080E9A9FF268B1E2800891E1D
+:104710006A37068E0638341FC0E30426881E280038
+:10472000B90600BE2000BF1A00F3A4E984FF86C4C6
+:10473000A36837E887FFF7066A370F007410803EDA
+:104740009E36007509BE0000E8ACE9CD50C3C350E9
+:10475000560633C026F606200080740626A02600E2
+:10476000241F8BF0268B5C2686FB83EB04744F831F
+:10477000C62A8CC08ED8B9070033C08EC0BF72372E
+:10478000F3AB33C98A0C80F9007503E930003BD9DB
+:104790007303E929002BD98A4401253F0074193D90
+:1047A0000B007D14D1E08BF82E8BBD5C498D74021B
+:1047B00083E902F3A4E9020003F123DB75C433C0EB
+:1047C0008ED8075E58C333C026F6062000807406D4
+:1047D00026A02600241FC3E50A25C3BFE70AB88622
+:1047E00003CD39B88303CD3981269B367CDFB8856C
+:1047F00003CD3AE50225FFF30D010025EFFFE702A7
+:10480000E50025FF53E700A1E73625FFFEA3E736C5
+:10481000E73E83269936CF810EAF360010A1AF3622
+:10482000E706C3E5020D010C25EFFFE702A1E7361D
+:104830000D0001E73EA3E736810E9B360020830E74
+:1048400099362081269B367CBF810EAF360010A1A1
+:10485000AF36E706B88603CD39B88503CD39B883BE
+:1048600003CD3AC30BF67549068E063234803EE01E
+:104870003401751B26893606008E06323426F7066B
+:104880000A000020740726810E0800002007C3805C
+:104890003EE33401751926893606008E0632342629
+:1048A000F7060A000010740726810E0800001007A2
+:1048B000C3E9B4FF50515733C0B906008EC0BFD111
+:1048C00036F3AE5F740C26F6060000C07504F85986
+:1048D00058C3F9E9F9FF8B050B45020B4504C35298
+:1048E00050E506251E003D1E0075F6B80180E75A0A
+:1048F000585AC3E8E9FF50E50225FF7F0D01002566
+:10490000EFFFE7020D0080E702A1AD36E704A1AF9B
+:1049100036E70658C3000000000000000000000059
+:104920002E2BCE4110427B413041A241AF4544295C
+:10493000C72AC72A6039F43A5C3C093DB13D343F8F
+:10494000C72A3C3FC72AC43F16401640ED40FA40F4
+:104950000741C72AC72AC72AC72AD65200000137EB
+:10496000E936F336EF361D370D370B379C370337F3
+:10497000FB36622D4006D12DF401BA4440068C432B
+:104980006400E82CC800D82B0500E9455000974585
+:10499000FA00AE2D04016A420200F62CBC02932DEF
+:1049A000DC051D2D6400A12D1400D73A0807812DC8
+:1049B0006400B33E020030436400C52CF4018B4414
+:1049C00002000000000000000000000000000000E5
+:1049D000803EFD3402740CE82005C706A1360000B5
+:1049E000E99AF8FF06C033E810058B363D37E873C7
+:1049F000FEC3CD34E9E805C706A3360000C706416B
+:104A0000370000E8EDFE33C00D4100E756A1B13696
+:104A10000D0010E708A1B336E70AA1AF36E706A1FB
+:104A2000AD36E704E82B09C7061D3700C8C7060BDB
+:104A3000370003C7060D377B7F33C0A39B36A39D8A
+:104A400036C7064C370100C6069E36FFC706053737
+:104A50000000C70607370000C70609370000A3F3A8
+:104A600036A3EF36A3F136E8FEF5E50225F9FF0D92
+:104A700003000D008825EFFF0D00400D0004E70244
+:104A8000B88F03CD39B88000CD35C706AA02FFFF25
+:104A9000A1A936A3A7360D00A40D0008E700A3A91D
+:104AA00036C706A3360100C706A5360C00833EA50F
+:104AB00036007509C7063D370500E913FFFF0EA54F
+:104AC00036BE1100E82205B89003CD39C3833EA35A
+:104AD000360174D9C3B89003CD3A26A02B00268B9B
+:104AE0001E2C00CD34833EA336017403E9F0043C50
+:104AF0000F751E81FB0002751826A12000A3053743
+:104B000026A12200A3073726A12400A30937E9091B
+:104B100000C7063D370100E9B6FEC706A33602000E
+:104B2000C6069E36FFE8CBFDE81CD933C0A3853707
+:104B3000A38337A38737A38937B89103CD39B880CA
+:104B400000CD35C706AA02FFFFE50025FF53E700A9
+:104B5000810E9A378000B89203CD3933C0E70EBE7C
+:104B600008008E063834E88EE526C70604007D4B23
+:104B70008326EF34DFCD50830EEF3420C3F7069A3F
+:104B80003780007432A9D007740CA90004740E3366
+:104B9000C0E70EE9DAFFFF068537E9D3FFFF06839A
+:104BA00037E9CCFFC7063D370100E936FE83269A78
+:104BB000377FBBFF7FCD53E5000D00ACE700E5027A
+:104BC00025FFFB25EFFF25FFF70D0100E702A1837D
+:104BD000373B0646377FCDA185373B0648377CC437
+:104BE000C706A3360300BE1300E8FD03B89303CD48
+:104BF00039B89403CD39B89603CD39B89503CD397A
+:104C0000BE0600E8E303E9D603833EA3360374013E
+:104C1000C3BE1300E8D203B89403CD39C3B89403DC
+:104C2000CD3A26A02B00268B1E2C00CD34833EA32C
+:104C300036037403E9A8033C0D753E83FB00753908
+:104C4000E5020D0020E702B89303CD3AC706A3366C
+:104C50000400BE0000E80CFCC6069D3680C6069E19
+:104C60003600C70633370200B89A03CD39E8FC0096
+:104C7000C7064C370000E96603C7063D370800E960
+:104C800061FD833EA336037509C7063D370500E97C
+:104C900051FDE94A03833EA336047412833EA336D2
+:104CA00005740BCD34C7063D370700E935FDC7064F
+:104CB000A3360600C6069E36FFB89A03CD3AB899C9
+:104CC00003CD3AB89603CD3AB89703CD39B89803D7
+:104CD000CD39B89B03CD39E918FDCD34833EA336D9
+:104CE000047718833EA336037508F7069B36000148
+:104CF0007509C7063D370100E9E8FCE9E102CD345A
+:104D0000833EA336027709C7063D370100E9D3FC8D
+:104D1000833EA336047705B89603CD39E9C00283F4
+:104D20003EA33603751026A10C00250700503D0454
+:104D3000007503E83600A1F33686E0E71EA3E336EC
+:104D400081260B37000381260D377B7F830E0D37BD
+:104D500048E814F3583D0400740926F7060C0020B7
+:104D6000007506B80100E97A02E986FCA1E536E79C
+:104D70002EA1E736E73EA1D336A39C34A1D536A3B6
+:104D80009E34C326803E1C00FF752F26803E1E00E9
+:104D9000FF752726F7060C004000751BA1D13626AB
+:104DA000A31A00A1D33626A31C00A1D53626A31E24
+:104DB00000B80A80E92C02E938FCFF069034BE0AEC
+:104DC00000C606B63401F6069D36807505830EC210
+:104DD0003401CD34E90CFC833EA336037509C706C4
+:104DE0003D370500E9FCFBE5020D03000D00880DD1
+:104DF00000400D0004E702C706A3360500C6069E64
+:104E000036FFBE0200E8E101B88903CD3AB89A0343
+:104E1000CD3AB89903CD39B89703CD39B89803CDB9
+:104E200039E9BB01833EA33603740A833EA33604EB
+:104E30007403E9AA01BE0600E8AE01B89503CD39B6
+:104E4000E99C01833EA336057403E99201BE02008A
+:104E5000E89601B89903CD39E98401C7060F3705F3
+:104E600000E97B01E50225FFDFE702C706A336075D
+:104E700000C7060F370500E96501E8D504C6069DA1
+:104E80003600C7069B360000C7060F370500C70669
+:104E9000A8020000C7064C370100E50225F9FF0D06
+:104EA00003000D008825EFFF0D00400D0004E70210
+:104EB000E967FCB89A03CD39F706F4330010750999
+:104EC000C70633370200E91601FF0E33377403E9D2
+:104ED0000D01FF068E34830EC23408C7063D37032A
+:104EE00000E9FFFAC35250BAE000B80010EF585A78
+:104EF000C3C7063D370000E9E9FAFAE85404B88070
+:104F0000038EC026C7060400D82BB87F038EC026A8
+:104F1000C7060400E82C33C08EC0A1A736A3A9366B
+:104F2000A1A936E700A1AB36E702C70605370000A6
+:104F3000C70607370000C70609370000C6069D36BA
+:104F400000C6069E36FFC7069B360000C706A3367E
+:104F50000000C7060F370000C706A8020000C706FA
+:104F60004C3701008126AF36FFE7A1AF36E706BB1D
+:104F7000FF7FCD53E87CF9E5560D0200E756FBC3F1
+:104F80008D3EC0538D36F038B90E008B1E303489FB
+:104F90005C022E8B45028944062E8B0589440483CE
+:104FA000C70483C610E2E8B880038EC026C7060493
+:104FB00000E251B87F038EC026C7060400B2523308
+:104FC000C08EC0C706A1360100C7060F370500C353
+:104FD00033FF8E06A6028B36A4022EFFA4A053E850
+:104FE0008CDBC3E848F7E9F6FF8E063834E807E1C2
+:104FF00026C7060400DF4FCD50C326C7060A0000AF
+:105000000026FF260400CD34E9D4FFA1D13626398D
+:10501000061A007522A1D3362639061C007518A180
+:10502000D5362639061E00750E26F7060C00400000
+:105030007405830E663740810EAF360010A1AF367F
+:10504000E706833EA336027505CD34E956FB833E61
+:10505000A3360074B1833EA3360577AA26F6060A66
+:1050600000FF75A2E8FDDD50F6069336207503E9D2
+:105070008C0026A10C002507003D07007503E9768A
+:10508000003D05007503E96E00F706E634188075EB
+:1050900003E96A00F706E6340080743526803E296D
+:1050A0000002752D5156578D363E348D3E2000B985
+:1050B0000600F3A65F5E59754526A12000A33E3485
+:1050C00026A12200A3403426A12400A34234E926CD
+:1050D00000F706E6340800740B26803E19000074C1
+:1050E00003E91300F706E6341000741226A0280026
+:1050F000C0E80422C0740726C7060400FFFF582337
+:10510000C07403E9DDFE81269B36FFFE26A1200048
+:105110003B06D136751A26A122003B06D336751000
+:1051200026A124003B06D5367506810E9B3600016C
+:1051300026A12000257FFFA3B83426A12200A3BA10
+:105140003426A12400A3BC348BC686C4A3C034D1AA
+:10515000E680FC097403E8F6F5A105370B0607376E
+:105160000B060937743E26A120003B06053775174C
+:1051700026A122003B060737750D26A124003B0619
+:1051800009377503E91D0026A02800240F3C03748D
+:105190001B3C00750F833EA336047410F7069B3644
+:1051A000000174082EFF94F853E933FECD34C7068E
+:1051B0003D370100E92CF8833EA336057410833E89
+:1051C000A336017E0983EE162EFF942454C3CD34FA
+:1051D000C326A10C003DFF7F740526FF260400E9CD
+:1051E000FDFDA1F433A90088740BA9001075098B8B
+:1051F0001E4337FFE3E99700C70635370500C706AA
+:1052000043372852F706F43300087406C7064337BD
+:105210001A52B88003CD39E9C5FDA9000874D9FF39
+:105220000E353775EDE93000A9000875CBFF0E3556
+:105230003775DF810EC234C000F6069D3680740FCC
+:10524000810E9B360080C7060F370200E990FDC72C
+:10525000063D370200E98BF780269E36FF7530F653
+:10526000069D36807420FF069434830E6637208EA8
+:1052700006303426F7060A000001740726810E085E
+:10528000000001E90900C7063D370400E954F78131
+:105290000EAF360008A1AF36E706E50AA900807414
+:1052A0000E8126AF36FFF7A1AF36E706E949FFE9E1
+:1052B0002DFDC70641370000BE2900E82BFDE91E81
+:1052C000FDCD34833EA336047709C7063D37010080
+:1052D000E910F7E909FDCD34C3C7069B360000E8A5
+:1052E0000CF58126AF36FFE7A1AF36E70681269B96
+:1052F00036FF7FE5020D010025EFFF25FFDFE70206
+:10530000BBFF7FCD5333C0A39D36A39F36E820F368
+:10531000E843F3830E9B3610C70699360000E8D2A7
+:10532000F5E5560D0200E756C706A8020000BE00CC
+:1053300000E830F5C606A0360EB89C03CD39B8801B
+:1053400000CD35C706AA02FFFFC706A1360100E956
+:10535000A5F606B88F03CD3AB89003CD3AB89103BD
+:10536000CD3AB89203CD3AB89303CD3AB89403CD71
+:105370003AB89503CD3AB89603CD3AB89703CD3AEB
+:10538000B89803CD3AB89903CD3AB89A03CD3AB854
+:105390009B03CD3AB87F03CD3AB88003CD3A07C31B
+:1053A000F749F14EDF4FDF4FDF4FDF4FF851DF4F4F
+:1053B000FA4F0B50D151DF4FDF4FDF4FDF4FDF4F41
+:1053C000E44E0600CD4A0400E44E1900AD4BFA004D
+:1053D000824C0807094C1400244E6400D74DF40198
+:1053E000644EBC027A4EE803434E0200B34EF40111
+:1053F0005B4EF401E54E140006500650954CC15228
+:10540000C152FE4CDA4C0650065006500650B751B9
+:10541000B751B751B751B751B7510650D54A065099
+:105420001D4C0650834D1F4D1F4DED40FA40074166
+:1054300037372E3737202079792F79792F797920CE
+:1054400030312E3930202030322F31372F3939206A
+:10545000000000000000000000000000000000004C
+:10546000000000000000000000000000000000003C
+:10547000000000000000000000000000000000002C
+:10548000000000000000000000000000000000001C
+:10549000000000000000000000000000000000000C
+:1054A00000000000000000000000000000000000FC
+:1054B00000000000000000000000000000000000EC
+:1054C00000000000000000000000000000000000DC
+:1054D00000000000000000000000000000000000CC
+:1054E00000000000000000000000000000000000BC
+:1054F00000000000000000000000000000000000AC
+:10550000000000000000000000000000000000009B
+:10551000000000000000000000000000000000008B
+:10552000000000000000000000000000000000007B
+:10553000000000000000000000000000000000006B
+:10554000000000000000000000000000000000005B
+:10555000000000000000000000000000000000004B
+:10556000000000000000000000000000000000003B
+:10557000000000000000000000000000000000002B
+:10558000000000000000000000000000000000001B
+:10559000000000000000000000000000000000000B
+:1055A00000000000000000000000000000000000FB
+:1055B00000000000000000000000000000000000EB
+:1055C00000000000000000000000000000000000DB
+:1055D00000000000000000000000000000000000CB
+:1055E00000000000000000000000000000000000BB
+:1055F00000000000000000000000000000000000AB
+:10560000000000000000000000000000000000009A
+:10561000000000000000000000000000000000008A
+:10562000000000000000000000000000000000007A
+:10563000000000000000000000000000000000006A
+:10564000000000000000000000000000000000005A
+:10565000000000000000000000000000000000004A
+:10566000000000000000000000000000000000003A
+:10567000000000000000000000000000000000002A
+:10568000000000000000000000000000000000001A
+:10569000000000000000000000000000000000000A
+:1056A00000000000000000000000000000000000FA
+:1056B00000000000000000000000000000000000EA
+:1056C00000000000000000000000000000000000DA
+:1056D00000000000000000000000000000000000CA
+:1056E00000000000000000000000000000000000BA
+:1056F00000000000000000000000000000000000AA
+:105700000000000000000000000000000000000099
+:105710000000000000000000000000000000000089
+:105720000000000000000000000000000000000079
+:105730000000000000000000000000000000000069
+:105740000000000000000000000000000000000059
+:105750000000000000000000000000000000000049
+:105760000000000000000000000000000000000039
+:105770000000000000000000000000000000000029
+:105780000000000000000000000000000000000019
+:105790000000000000000000000000000000000009
+:1057A00000000000000000000000000000000000F9
+:1057B00000000000000000000000000000000000E9
+:1057C00000000000000000000000000000000000D9
+:1057D00000000000000000000000000000000000C9
+:1057E00000000000000000000000000000000000B9
+:1057F00000000000000000000000000000000000A9
+:105800000000000000000000000000000000000098
+:105810000000000000000000000000000000000088
+:105820000000000000000000000000000000000078
+:105830000000000000000000000000000000000068
+:105840000000000000000000000000000000000058
+:105850000000000000000000000000000000000048
+:105860000000000000000000000000000000000038
+:105870000000000000000000000000000000000028
+:105880000000000000000000000000000000000018
+:105890000000000000000000000000000000000008
+:1058A00000000000000000000000000000000000F8
+:1058B00000000000000000000000000000000000E8
+:1058C00000000000000000000000000000000000D8
+:1058D00000000000000000000000000000000000C8
+:1058E00000000000000000000000000000000000B8
+:1058F00000000000000000000000000000000000A8
+:105900000000000000000000000000000000000097
+:105910000000000000000000000000000000000087
+:105920000000000000000000000000000000000077
+:105930000000000000000000000000000000000067
+:105940000000000000000000000000000000000057
+:105950000000000000000000000000000000000047
+:105960000000000000000000000000000000000037
+:105970000000000000000000000000000000000027
+:105980000000000000000000000000000000000017
+:105990000000000000000000000000000000000007
+:1059A00000000000000000000000000000000000F7
+:1059B00000000000000000000000000000000000E7
+:1059C00000000000000000000000000000000000D7
+:1059D00000000000000000000000000000000000C7
+:1059E00000000000000000000000000000000000B7
+:1059F00000000000000000000000000000000000A7
+:105A00000000000000000000000000000000000096
+:105A10000000000000000000000000000000000086
+:105A20000000000000000000000000000000000076
+:105A30000000000000000000000000000000000066
+:105A40000000000000000000000000000000000056
+:105A50000000000000000000000000000000000046
+:105A60000000000000000000000000000000000036
+:105A70000000000000000000000000000000000026
+:105A80000000000000000000000000000000000016
+:105A90000000000000000000000000000000000006
+:105AA00000000000000000000000000000000000F6
+:105AB00000000000000000000000000000000000E6
+:105AC00000000000000000000000000000000000D6
+:105AD00000000000000000000000000000000000C6
+:105AE00000000000000000000000000000000000B6
+:105AF00000000000000000000000000000000000A6
+:105B00000000000000000000000000000000000095
+:105B10000000000000000000000000000000000085
+:105B20000000000000000000000000000000000075
+:105B30000000000000000000000000000000000065
+:105B40000000000000000000000000000000000055
+:105B50000000000000000000000000000000000045
+:105B60000000000000000000000000000000000035
+:105B70000000000000000000000000000000000025
+:105B80000000000000000000000000000000000015
+:105B90000000000000000000000000000000000005
+:105BA00000000000000000000000000000000000F5
+:105BB00000000000000000000000000000000000E5
+:105BC00000000000000000000000000000000000D5
+:105BD00000000000000000000000000000000000C5
+:105BE00000000000000000000000000000000000B5
+:105BF00000000000000000000000000000000000A5
+:105C00000000000000000000000000000000000094
+:105C10000000000000000000000000000000000084
+:105C20000000000000000000000000000000000074
+:105C30000000000000000000000000000000000064
+:105C40000000000000000000000000000000000054
+:105C50000000000000000000000000000000000044
+:105C60000000000000000000000000000000000034
+:105C70000000000000000000000000000000000024
+:105C80000000000000000000000000000000000014
+:105C90000000000000000000000000000000000004
+:105CA00000000000000000000000000000000000F4
+:105CB00000000000000000000000000000000000E4
+:105CC00000000000000000000000000000000000D4
+:105CD00000000000000000000000000000000000C4
+:105CE00000000000000000000000000000000000B4
+:105CF00000000000000000000000000000000000A4
+:105D00000000000000000000000000000000000093
+:105D10000000000000000000000000000000000083
+:105D20000000000000000000000000000000000073
+:105D30000000000000000000000000000000000063
+:105D40000000000000000000000000000000000053
+:105D50000000000000000000000000000000000043
+:105D60000000000000000000000000000000000033
+:105D70000000000000000000000000000000000023
+:105D80000000000000000000000000000000000013
+:105D90000000000000000000000000000000000003
+:105DA00000000000000000000000000000000000F3
+:105DB00000000000000000000000000000000000E3
+:105DC00000000000000000000000000000000000D3
+:105DD00000000000000000000000000000000000C3
+:105DE00000000000000000000000000000000000B3
+:105DF00000000000000000000000000000000000A3
+:105E00000000000000000000000000000000000092
+:105E10000000000000000000000000000000000082
+:105E20000000000000000000000000000000000072
+:105E30000000000000000000000000000000000062
+:105E40000000000000000000000000000000000052
+:105E50000000000000000000000000000000000042
+:105E60000000000000000000000000000000000032
+:105E70000000000000000000000000000000000022
+:105E80000000000000000000000000000000000012
+:105E90000000000000000000000000000000000002
+:105EA00000000000000000000000000000000000F2
+:105EB00000000000000000000000000000000000E2
+:105EC00000000000000000000000000000000000D2
+:105ED00000000000000000000000000000000000C2
+:105EE00000000000000000000000000000000000B2
+:105EF00000000000000000000000000000000000A2
+:105F00000000000000000000000000000000000091
+:105F10000000000000000000000000000000000081
+:105F20000000000000000000000000000000000071
+:105F30000000000000000000000000000000000061
+:105F40000000000000000000000000000000000051
+:105F50000000000000000000000000000000000041
+:105F60000000000000000000000000000000000031
+:105F70000000000000000000000000000000000021
+:105F80000000000000000000000000000000000011
+:105F90000000000000000000000000000000000001
+:105FA00000000000000000000000000000000000F1
+:105FB00000000000000000000000000000000000E1
+:105FC00000000000000000000000000000000000D1
+:105FD00000000000000000000000000000000000C1
+:105FE00000000000000000000000000000000000B1
+:105FF00000000000000000000000000000000000A1
+:106000000000000000000000000000000000000090
+:106010000000000000000000000000000000000080
+:106020000000000000000000000000000000000070
+:106030000000000000000000000000000000000060
+:106040000000000000000000000000000000000050
+:106050000000000000000000000000000000000040
+:106060000000000000000000000000000000000030
+:106070000000000000000000000000000000000020
+:106080000000000000000000000000000000000010
+:106090000000000000000000000000000000000000
+:1060A00000000000000000000000000000000000F0
+:1060B00000000000000000000000000000000000E0
+:1060C00000000000000000000000000000000000D0
+:1060D00000000000000000000000000000000000C0
+:1060E00000000000000000000000000000000000B0
+:1060F00000000000000000000000000000000000A0
+:10610000000000000000000000000000000000008F
+:10611000000000000000000000000000000000007F
+:1061200090EAC01500000000000000000000130607
+:00000001FF
+/*
+ * The firmware this driver downloads into the tokenring card is a
+ * separate program and is not GPL'd source code, even though the Linux
+ * side driver and the routine that loads this data into the card are.
+ *
+ * This firmware is licensed to you strictly for use in conjunction
+ * with the use of 3Com 3C359 TokenRing adapters. There is no
+ * waranty expressed or implied about its fitness for any purpose.
+ */
+
+/* 3c359_microcode.mac: 3Com 3C359 Tokenring microcode.
+ *
+ * Notes:
+ *  - Loaded from xl_init upon adapter initialization.
+ *
+ * Available from 3Com as part of their standard 3C359 driver.
+ */
diff --git a/firmware/Makefile b/firmware/Makefile
index c6af61b4e51e..baf5ae45642d 100644
--- a/firmware/Makefile
+++ b/firmware/Makefile
@@ -26,6 +26,7 @@ fw-shipped- += acenic/tg1.bin
 else
 acenic-objs := acenic/tg1.bin acenic/tg2.bin
 endif
+fw-shipped-$(CONFIG_3C359) += 3com/3C359.bin
 fw-shipped-$(CONFIG_ACENIC) += $(acenic-objs)
 fw-shipped-$(CONFIG_ADAPTEC_STARFIRE) += adaptec/starfire_rx.bin \
 					 adaptec/starfire_tx.bin
@@ -39,6 +40,7 @@ fw-shipped-$(CONFIG_CHELSIO_T3) += cxgb3/t3b_psram-1.1.0.bin \
 fw-shipped-$(CONFIG_DVB_TTUSB_BUDGET) += ttusb-budget/dspbootcode.bin
 fw-shipped-$(CONFIG_E100) += e100/d101m_ucode.bin e100/d101s_ucode.bin \
 			     e100/d102e_ucode.bin
+fw-shipped-$(CONFIG_PCMCIA_SMC91C92) += ositech/Xilinx7OD.bin
 fw-shipped-$(CONFIG_SMCTR) += tr_smctr.bin
 fw-shipped-$(CONFIG_SND_KORG1212) += korg/k1212.dsp
 fw-shipped-$(CONFIG_SND_MAESTRO3) += ess/maestro3_assp_kernel.fw \
@@ -91,6 +93,7 @@ fw-shipped-$(CONFIG_USB_SERIAL_KEYSPAN_PDA) += keyspan_pda/keyspan_pda.fw
 fw-shipped-$(CONFIG_USB_SERIAL_XIRCOM) += keyspan_pda/xircom_pgs.fw
 fw-shipped-$(CONFIG_USB_VICAM) += vicam/firmware.fw
 fw-shipped-$(CONFIG_VIDEO_CPIA2) += cpia2/stv0672_vp4.bin
+fw-shipped-$(CONFIG_YAM) += yam/1200.bin yam/9600.bin
 
 fw-shipped-all := $(fw-shipped-y) $(fw-shipped-m) $(fw-shipped-)
 
diff --git a/firmware/WHENCE b/firmware/WHENCE
index 00b6e3c0905d..3814d7d42665 100644
--- a/firmware/WHENCE
+++ b/firmware/WHENCE
@@ -493,3 +493,53 @@ Licence:
 Found in hex form in kernel source.
 
 --------------------------------------------------------------------------
+
+Driver: YAM - YAM driver for AX.25
+
+File: yam/1200.bin
+File: yam/9600.bin
+
+Licence:
+ * (C) F6FBB 1998
+
+Found in hex form in kernel source.
+
+--------------------------------------------------------------------------
+
+Driver: 3C359 - 3Com 3C359 Token Link Velocity XL adapter
+
+File: 3com/3C359.bin
+
+Licence:
+/*
+ * The firmware this driver downloads into the tokenring card is a
+ * separate program and is not GPL'd source code, even though the Linux
+ * side driver and the routine that loads this data into the card are.
+ *
+ * This firmware is licensed to you strictly for use in conjunction
+ * with the use of 3Com 3C359 TokenRing adapters. There is no
+ * waranty expressed or implied about its fitness for any purpose.
+ */
+/* 3c359_microcode.mac: 3Com 3C359 Tokenring microcode.
+ *
+ * Notes:
+ *  - Loaded from xl_init upon adapter initialization.
+ *
+ * Available from 3Com as part of their standard 3C359 driver.
+ */
+
+Found in hex form in kernel source.
+
+--------------------------------------------------------------------------
+
+Driver: PCMCIA_SMC91C92 - SMC 91Cxx PCMCIA
+
+File: ositech/Xilinx7OD.bin
+
+Licence: Allegedly GPL, but no source visible. Marked:
+    This file contains the firmware of Seven of Diamonds from OSITECH.
+    (Special thanks to Kevin MacPherson of OSITECH)
+
+Found in hex form in kernel source.
+
+--------------------------------------------------------------------------
diff --git a/firmware/ositech/Xilinx7OD.bin.ihex b/firmware/ositech/Xilinx7OD.bin.ihex
new file mode 100644
index 000000000000..03e80857a549
--- /dev/null
+++ b/firmware/ositech/Xilinx7OD.bin.ihex
@@ -0,0 +1,177 @@
+:10000000FF04A036F3ECFFFFFFDFFBFFF3FFFFFF72
+:10001000EF3FFFF7FFFFFFFFEF7FFEFFCEFEFEFE8D
+:10002000FEDEBDDDFDFFFDCFF7BF7FFF7F3FFEBFE3
+:10003000FFFFFFBCFFFFBDB57F7FBFBF7FFFEFFFAF
+:10004000FFFFFBFFF7F7FFFFFFFFFEDEFEFEFADE1E
+:10005000BDFDEDFDFDCFEFEFEFEFC7DFDFDFDFDF52
+:10006000FF7EFEFD7D6DEEFE7CFBF4FBCFDBDFFF54
+:10007000FFBB7FFF7FFFF7FF9EBF3BBFBF7F7F7F41
+:100080007E6FDFEFF5F6FDF6F5EDEBFFEFEFEF7EC0
+:100090007F7F6F7FFFFEFEFEFEFEEFBFFFFFFFFFD5
+:1000A000FFFFFFFFFFFFBC1F1FEEFFBCB7FFDFFF1F
+:1000B000DFEF3BE3D3FFFBFFFFDFFFFFFFBABF2D07
+:1000C000DBBDFDDBDFFAFBFFEFFBDBF3FFDFFD7FDB
+:1000D000EFFBFFFFBEBF27BAFEFBDFFFF6FFFFEF20
+:1000E000FBDBF3D99A3FFFAFBFFFFFBE3F37BD96A3
+:1000F000FFFFFFFFFFFFAEFBF3F3EBFFFFFFFFFF91
+:10010000FFF7FABCAEFEBEFEBB7FFDFF7FEFF7FB45
+:10011000BBD7F77FFFF7FFFFF7BCEDFDBD9D7D7BF4
+:10012000FB7B7BFBAFFFFEFDFDFEFEFFFFFFFFF74E
+:10013000AAB9BF8FBFDFFF7FFFFF7FCFFBEBCBEB0A
+:10014000EEFFFFD7FFFFFF3E333F1C7CFCFFFFFFAE
+:10015000FFFFCFD3F3E3F3FBFFFFFFFFFFEBFE3522
+:100160003F3DFDFDFFFFFFBFFFEF6FE3E3E3EFFF69
+:10017000FFDFFFFFF7FE3E5EFEFFFFFFFFFDFFFF1D
+:10018000AFCFF2CBCF8EFFFFFFFFFFFDFC3E1F9EE8
+:10019000ADFDFFFFBFFFFFEFFFB3F7E7F7FAFFFF8C
+:1001A000FFFFFFEEEBABAF9FE37FFFDEFF7FEEFFD6
+:1001B000FFFB3AFAFFF277FFFFF7FEFFFEBDAEDE70
+:1001C0007D7DFDFFBFEEFFFDFFDBFBFFF7EFFBFFDC
+:1001D000FFFEFF2DAFB9FD79FBFAFFBFEFFFFF91E7
+:1001E000FAFBDFF7F7FFFFFFFCCF37BFBFFF7F7FD3
+:1001F000FFFFFFAFFFFFF3FBFBFFF5EFFFFFF7FA9A
+:10020000FFFFEEFAFEFB55DDFF7FAFFEFFFBFBF5C8
+:10021000FFF7EFFFFFFFBEBDBDBDBD7D7B7B7B7BE1
+:10022000FBAEFFFDFEFFFFFFFFFFFFFFF7DAB76149
+:10023000FFB959F373F3DF7F6FDFEFF7EBEBD7FF16
+:10024000D7FFFFF7FE7FFB3E3873F67FFCFFFFCF43
+:10025000FFB7FBB3B367FFE7FDFFEFF67FB7BCF572
+:100260007BF6F7F5FFFFEFFFF7FFF7CEE7FF9FFF06
+:10027000FFF5FE7DFF5FFFFFFFFFFFFFFFEFFFF6D4
+:10028000CBDBEEFEFFDFFFFFFFFE7FBE1E3EFEFF6D
+:100290007DFEFFFFEFBFE7FFE3E3FFDFE7FFFFFFC9
+:1002A000B8EFB72FEEFFDFFFBFFF7FEFEBBFA3D3AA
+:1002B000FF7FFFFFFFFFF7BEFD3FCFFDFBFFFFFF0F
+:1002C000FFFFAFFBBFBBBFDBFDFBFFFFFFFF3EFE42
+:1002D0003FBABAFEFFFFFFEFFFEFC37FB29BFFFF06
+:1002E000FFFFFEFFFF3CFF3F3CFFFEFFFFFFFFFF66
+:1002F000AFF3FEF3E3EBFFFFFFFBFFF79AFEAF9ECA
+:10030000BEFEFFDFFFFF7BEFF7BFFBFBFBFFFF7FC7
+:10031000FFFFFFBCBDFDBDDD7D7B7B7B7BFBAEFFBF
+:10032000FFFFFEFEFFFDFFFFFFF79AFF9FFFAFEF0E
+:10033000FFFFFFFF7FCFF3FFEBFFEBFFFFBFFFFFF1
+:10034000EFFEFF37FCBFFFFFFFFFFFFFCFEFFDF327
+:10035000FFEEFEFFFFFFFFFF6EFD2FFDFFFDFFFF26
+:10036000FFFFFFEFCFFFF3BF69FFFFFFFFFFFFFEC0
+:10037000FB9FFFBFFDFFFFFFFFFFEF87FEDAEFCF21
+:10038000FFFFFFFFFFFFFEEFBFEFEFFDFFFFFFFFF0
+:10039000FFEFFDFF7BFFEBFEFFFFFFFFEBF8FFEF43
+:1003A000AFFFFFBDFFFFFF7FEE7FEFFFBBFFBFFB98
+:1003B000FFFFFFF7F6FBBDFDDDF5FFFFFFFFFFAF22
+:1003C000FF5FF5DFFF7FFFFFFFFFFFF6F3FFDEFEBE
+:1003D000EFFDFFFFFFFFEFFFDEDF5FDFFDFFFFFF52
+:1003E000FFFFFEFFFFFEFEFFFDFFFFFFFFAFFFFF72
+:1003F000EFEDFFDFFFFFFBFFFFDABDBEAEFE7FFDCF
+:10040000DFFFFF7FEFFFFBFBFB7FF7FFFFFFFFF748
+:10041000BCFDBDBDBDFD7B7B7B7BFBAEFFFFFDFF60
+:10042000FFFFFDFFFFFFFFFA9FBFBFCF7FFFFFFF73
+:10043000FFFFAFFFEBEBEBFFD7FEFFFFBFE7FEBF1A
+:100440007FFCFFFFEDFFFFFFFF4FFFFBFBFFFFDD2B
+:10045000FFFFFFFFFFFEBDDF9DFDDFB9FFFFFFFFD9
+:10046000EFFFFBEFEBFFDEFFFFFFFFFFF69FFFFC61
+:10047000FEFBFDFFFFFFFFEFDFFACDCFBF9FFFFFCA
+:10048000FFFFF7FEBFFFDFEF5FFFFFFFFF7F6FFFA5
+:10049000BBFDFFFFFFFFFFFFFFFF7EFF5FFFBFBF53
+:1004A000F9FFFFFF7F6E7BFFEFFDEBDFFFFFFFFF3D
+:1004B000F7B63EFCFDBF7EFBFFFFFFF7EFF7F3F75C
+:1004C000FFFBFFFFFFFFFFFF6E3579FFBFFCFFFF64
+:1004D000FFFFFFEFFB53DFFFEBBFFFFFFFFFFFBCA3
+:1004E000FFFFFFBFFFFDFFFFFFFFAFF5FFF7FFFBC4
+:1004F000FFFFFFFFFFFFBAAAEEFE3F7DFDFFFFFFFC
+:100500007FAF77FBFBFFFBF7FFFFFFFFF7BEBDBD34
+:10051000BDBDFD7B7B7B7BFBAEFFEFFFFFFFFFFCE9
+:10052000FFFFFFFF9AD9B8FFFF79FFFFFFFFFFCF63
+:10053000FBFFEBFFEBD7FFFFFFFFE7DEF8FBFE3F24
+:10054000FBFDFFFFFFFFCFADBFFAFF73DFFFFFFF34
+:10055000FFFF3AF5B7FC3FF9FDFFFFFF7FEFF3FF29
+:10056000BFFEF39FFEFFFFFFF73EFFFFFFBFFFFF52
+:10057000FFFFFFFFAFD3FEDBFFDBDFFFFFFFFFFF70
+:100580003EFFBFFF7FFFFDFFFFFFFF8FF3FFEDFF8C
+:10059000F7FBFFFFFFFFEFF63CFEFFFFFFFFFFFF54
+:1005A000FF9FEFEFD1FFFFFFFFFFFFFFFFFF7EBFCA
+:1005B000FDFFFFFFFFFFFFFFBBEFDFF1FFFFFFFFCF
+:1005C000FFFFFFFFFFEE3EFEFFFFFFFFFFFFFFBF4E
+:1005D000EFFDC3FFFFFFFFFFFFFFBFFFFC3EFEFF7E
+:1005E000FFFFFFFFFFFFFF2EEFF3FFFFFFFFFFFF08
+:1005F000FFFFF7BABEFEFFFFFFFFFFFFFF7FAFFB6E
+:10060000FBFDFFFFFFFEFFFFFFF2D6EDBDBDBD7D91
+:100610007B7B7B7BFBAFDFFFFFFFFFFFFFFFFFFF6E
+:10062000FF92BFFFFFFFFFFFFFFFFF7FAFEBEBFF7F
+:10063000FFFFFFFFFFFFFFE7FE2EFEFFFFFFFFFFB5
+:10064000FFFFFF4FEFF3FFFFFFFFFFFFFFFFFFFE87
+:100650003CFEFFFFFFFFFFFFFFFFEFCEC3FDFFFFED
+:10066000FFFFFFFFFFFFFE5DFFFFFFFFFFFFFFFF3D
+:10067000FFEFCFEBFFFFFFFFFFFFFFFFF7EE3EFFB8
+:10068000FFFFFFFFFFFFFF7FEFDFE2FFFFFFFBFF4B
+:10069000FFFFFFFFF6BEFCFFFFFFFFFFFFFF7FEE48
+:1006A0005FE6FFFFFFFFFFFFFFFFFF3E7DFFFFFF56
+:1006B000FFFFFFFFFFFFEFF3FBFFFFFFFFFFFFFF6A
+:1006C000BFF736BEFEFFFFFFFFFFFFFFFFEFD3F6D2
+:1006D000FEFFFFFFFFFFFFFFFFFC7FEEFFFFFFFFBF
+:1006E000FFFFFFFFAFEFEBFFFFFFFFFFFFFFFFFF8E
+:1006F000BABEFEFFFFFFFFFFFFFFFFEEFBFAFFFFAB
+:10070000FFFFFFFFFFFFF7D6FDBDBDBD7D7B7B7B00
+:100710007BFBAEFF7EFFFFFFFFFFFFFFFFF7BABFD0
+:10072000FFFFFFFFFFFFFFFF7FEFEB6BFFFFFFFF11
+:10073000FFFFFFFFF7FEBEFEFFFFFFFFFFFFFFFF14
+:100740004FEFF7FFFFFFFFFFFFFFFFEF3E6EFCFFE6
+:10075000FFFFFFFFFFFFFFEFC3C9FFFFFFFFFFFF2B
+:10076000FFFFFF3EBFFFFFFFFFFFFFFFFFFFEFFBAE
+:10077000D5FFFFFFFFFFFFFFFFFFFEFEFEFFFFFFB6
+:10078000FFFFFFFFFF6FEFFBFFFFFFFBFFFFFFFF21
+:10079000FFF6DFFFFFFFFFFFFFFF7FFEEFFFFFFF23
+:1007A000FFFFFFFFFFFFE7FFFEFFF7FFFFFFFFFF7A
+:1007B000FF7FFAEFBFFFFFFFFFFFFFFFFFE7FFFE37
+:1007C000FFFFFFFFFFFFFFFF7FFEEFBFFFFFFFFF0A
+:1007D000FFFFFFFFA7FFFCF7FFFFFFFFFFFFFF7F0C
+:1007E000FEAEFFFFFDFFFFFFFFFFFFE7F7FAFFFD94
+:1007F000FFFFFFFFFFFFFF7FAFFFFFFFFFFFFFFFD9
+:10080000FFFFFFF7BEBDBDBDBD7D7B7B7B7BFBAF2F
+:100810007FFFFFFFFFFFFFFFFFFFFFCAFFFFFFFF9D
+:10082000FFFFFFFFFF7F6FFFFFFFFFFFFFFFFFFFE8
+:10083000FFE7FEFFFFFFFFFFFFFFFFFFFFCFFEFF12
+:10084000FFFFFFFFFFFFFFFFFFFEDFFFFFFFFFFFD9
+:10085000FFFFFFFFEFFFFEFFFFFFFFFFFFFFFFFFB9
+:10086000FEFFFFFFFFFFFFFFFFFFFFEFFFFFFFFFA9
+:10087000FFFFFFFFFFFFF7FEFFFFFFFFFFFFFFFF91
+:10088000FFFFEFFFFEFFFFFFFBFFFFFFFFE7F2FCB5
+:10089000EFFFFFFFFFFFFFFF7FAEEFFFFFFFFFFF59
+:1008A000FFFFFFFFF77EFDFFFFFFFFFFFFFFFFFFE3
+:1008B000EFFFFEFFFFFFBFFFFFFFBFFFFEFEFFFFDB
+:1008C000FFFFFFFFFFFFDFEFDDFEFFFFFFFFFFFF8B
+:1008D000FFFFFFFEFEFFFFFFFFFFFFFFFFFFAFEF8A
+:1008E000FFFFFFFFFFFFFFFFFFFFBAFEFFFFFFFF5E
+:1008F000FFFFFFFFFFEFFAFEFFFFFFFFFFFFFFFF1E
+:10090000F69CBDBDBDBD7D7B7B7B7BFBAEFFFFFF52
+:10091000FFFFFFFFFFFFFFF77AFFFFFFFFDFFFFF94
+:10092000FFFF6FEFF7FFFFFFDFFFFFFFFFFFF7FEA8
+:10093000FEFFFFFFDFFFFFFFFFFFCFEBFFFFFFFF2C
+:10094000FFFFFFFFFFEF9EFCFFFFFFFFFFFFFFFF2B
+:10095000FFEFEFFFFFFFFFFFFFFFFFFFFFFEFFFFC8
+:10096000FFFFFFFFFFFFFF7FEFCBFFFFFFFFFFFD5D
+:10097000FFFFFFFFBEFDFFFFFFFFFFFFFFFFFFEFDA
+:10098000EFFFFFFFDFFFFFFFFFFFFFF8FFFFFFFFAE
+:10099000BFFFFFFFFFFFEFFFFFFFFFFFFFFFFFFFB7
+:1009A000FFFFFEFFFFFFFFFFFFFFFFFFFBAF7FFF2C
+:1009B000FFFFDFFFFFFFFFFFFFFEEFFFFFFFFFFF78
+:1009C000FFFFFFFFEFFFFFFFFFFFFFFFFFFFBFFF87
+:1009D000FEFFFFFFFFFFFFFFFFFFFFAEFFFFFFFF79
+:1009E000FFFFFFFFFFFFF7FAFFFFFFFFFFFFFFFF24
+:1009F000FF7FEFFFFFFFFFFFFFFFFFFFFFF7BCBD24
+:100A0000BDBDBD7D7B7B7B7BFBAFFFFFFFFFFFFFA2
+:100A1000FFFFFFFFF7FAFFFFFFFFFFFFFFFFFF7F73
+:100A2000AF7FFFFFFFFFFFFFFFFFFFEFFEFFFFFFB7
+:100A3000FFFFFFFFFFFFFFCFFFFFFFFFFFFFFFFFF6
+:100A4000FFFFFFFEFFFFFFFFFFFFFBFFFFFFEFFFCB
+:100A5000FFFFFFFFFFFFFFFFFFFFFEFFFFFFFFFFA7
+:100A6000FFFFFFFFFFEFFFFFFFFFFFFFBFFFFFFFE6
+:100A7000FFFCFFFFFFFFFFFFFFFFFFFFEFFFFFFF99
+:100A8000FFFFFBFFFFFFFFEFFEFF9F9F9F3F3F3FEB
+:100A90003F3FFFEFDFDFDFDFCFB7BFBFBFBFFFBC31
+:100AA000B99DBDBD7D7B7B7B7BFBEFD7F5F3F1D1A2
+:100AB00065E3E3E3A3FFFE7FFEDEDEFFBDBDBDBD5C
+:100AC000DFEFFBF7F3F3F3E7E7E7E7E7FBFEFFFF13
+:0A0AD000FFFFFFFFFFFFFFFFFFFF26
+:00000001FF
+This file contains the firmware of Seven of Diamonds from OSITECH.
+(Special thanks to Kevin MacPherson of OSITECH)
diff --git a/firmware/yam/1200.bin.ihex b/firmware/yam/1200.bin.ihex
new file mode 100644
index 000000000000..9d34e5680e38
--- /dev/null
+++ b/firmware/yam/1200.bin.ihex
@@ -0,0 +1,342 @@
+:10000000FFF200A5ADFFFE9FFFEFF3CBFFDBFCF29D
+:10001000FFF6FF3CBFFDBFDF6E3F6FF17DB4FDBF5C
+:10002000DF6F3F6FF70BFFDBFDF2FFF6FFFFFFFF18
+:10003000F0CFFFFFFFFEFFFFDFFFFFFFEFFFFFFF40
+:10004000FDFFFFFFFEFFFFFFFFFFF1FFFFFFFFBF11
+:10005000FFFFF7FFFFFBFFFFFFFCFFFEFFFFFFF0CF
+:100060005FFFFFFFFEFFFFFFFFFFFFFFFFFFFFFF41
+:10007000FFFFFFFFFFF7FFFFFFF1FFFFFE7FBFFF67
+:10008000FFFFFFFFFFFFFFFFF7FFFBFFFFFFF09FFB
+:10009000FFFFFFFEFFFDFFFFFFFFDFFFFFFFF7FF9B
+:1000A000FFFFFBFFFBFFFFFFF0FFFFFFFFFFFFFF77
+:1000B000F7FFFFFBFFFFFFFEFFFFFFEFFFF05FFF1C
+:1000C000FFFFFEFFFFEFFFFFFBFFFFFFFFFFFFFF55
+:1000D000FFBFFFFFDFF7FFF1FFFFFFFFFFFFFFFFA6
+:1000E000FFFFFFFFFFFBFEFFFFFFFFFFF0FFFFFF34
+:1000F000FFFEFFFFFFFFFFFFFFFFFFFFFFFFFFEB25
+:10010000FFFFFFFDFFBFF1FFFFFFFFDFFFFFFFFB73
+:10011000FFFFFFFFFFFFFFFFFFFFFFF06FFFFFFF8E
+:10012000FEFFFFFFFFFFFFFFFFFFDFFFFFFFFFFF00
+:10013000FFFFF7FFFFF1FFFFF7BFE7FFFFFFFFFB49
+:10014000FFFFFFFFFFFF77FFFFFFF0FFFFFFFFFE57
+:10015000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFAF
+:10016000FFFFFFFFF1FFFFFFFFFFFFFFFFFFFFFFAD
+:10017000FFFFFFFFFFFFFFFFFFF01FFFFFFFFEDBA3
+:10018000FFFFF5A5FD4B6EEF3332DDD34AD692FE6D
+:10019000B33FBDF1FADBFEF7F696BDBDFFBDFFED47
+:1001A0007F6B7FFBDFFEFBFE90CFFFFFFFFEBEEF0E
+:1001B000FFFFDB5FF6FFF68FFDA5DDFFFFFFFF6FA3
+:1001C0007FDBF1FCBFFF6FFFEFFC5B5DDADFF4FF6D
+:1001D000F2FFFDBFFFFFFFD01FFFFFFFFEFFFFFF8E
+:1001E000FFFBEFB7FC33FFFBFF046AF33C36FFF085
+:1001F0000FF10FFFFFFFF315720FF16FFFFE943F3A
+:10020000FFFFFF7BFFFFF0FFFFFFFFFEFFFFFFF0A1
+:10021000F7EFB7FC33FFFFFF046AF33C36FFF00F44
+:10022000F10FFFFFFFF315738FF26FFFFE943FFF97
+:10023000FFFF7D9FFFF00FFFFFFFFEFFFFFFFF9E11
+:10024000FFFCEFD3FBFF7FF55FFE59FFFFFFFCF1E3
+:10025000FE7FFFFFFA17FFE7EFEFFFFF3FF1FFFF22
+:10026000FFFFFFFFF0FFFFFFFFFEF5FFBFFFFCEA10
+:10027000FFF0FFFFBFF93FB1EFFFD7FFFBFFF0FF3C
+:10028000FFF3FFDFFF7BFFFDFFF6FFBFFFFFBFFFB9
+:10029000FFFFDAF0FFFFFFFFFEF2C00100000202E5
+:1002A0000202004040401000000020000001000059
+:1002B000000000001900040400000000000000100D
+:1002C000003CF0AFFFFFFFFEFDBFFFFFFBFFFDFFA8
+:1002D000FF7FFFFFBFFFEFFFFFFDFFFFF1FFDFFF2E
+:1002E000FFFFFFFFFFBFFEFFFFFEFFFFFFFFFFDF80
+:1002F000DBF06FFFFFFFFEF0BFDFFF7FFFFFFFFFC1
+:10030000DFDFFFEFFF9EEFFFFF7FFFF1EFFFFFFF5C
+:10031000F7FABFFFFFFE47EFFFBDF6FFFFDFF5F087
+:10032000F0EFFFFFFFFEF8300000000400010208BC
+:1003300016000000800001020080010C0200000194
+:100340000000200000060020001000140004C1F08E
+:100350002FFFFFFFFEFFFFFFFFFFFFFFFBFFFF7F02
+:10036000ECFFFFFAFFBFFF6FFFE1FFFFFFFFBDFEE6
+:1003700046FFEF7FCDDFFFFFFDFFBDFF7F7FF04F2B
+:10038000FFFFFFFEFFFFFFFFFFFFFFFFFFFFFFFF7E
+:10039000FFFFFFFFFFFFFFFFF1FFFFFFFFFFFFFF7B
+:1003A000FFFFFFFFFFFFFFFFFFFFFFFFFFF00FFF5C
+:1003B000FFFFFEFFFFFFFDA4BCCD6D6B6F5BDC3369
+:1003C0005AF6F7F6B33FBDC1FA5AF6F6B6F7FFBDD7
+:1003D000BB3CCECF34EF33BBCCFFFFFFF04FFFFF72
+:1003E000FFFEBFFFFFFFDBFFF6D6FFFDFDBFFFAD4A
+:1003F000BFF97F6FFCDBF1FDBFFF6FFFFFDADBFCB6
+:10040000DBFF768FF6FFCDABFEFBFFD0FFFFFFFFDC
+:10041000FEFF9FFFF420AF6D0BC17BFFFFFFCBFF03
+:100420003FF0EF7F0FF1C33CFFFFFFFFFFFFF80B33
+:100430001D6A64056B9901FFFDEFF02FFFFFFFFEC2
+:10044000FFFFFFF4002FCC0BC37FFFFFFF0ADFBFCE
+:10045000FD7FFFFFF1C3BFFFFFFFFFFFFFF04A0E6D
+:10046000966402979910FFFFFFF0DFFFFFFFFEFF8A
+:10047000FFFFFE84F9D527F17FFFF8EBDFF3CF3FD5
+:100480001FFFF711FFCFFFFE67FFFFFFFFC4FFFF56
+:10049000B3A1FFF9E0FFFFFFF0EFFFFFFFFEF5FF65
+:1004A000FFFB7FE0FFC7FE7F3FFFFD778D7F0FFFE4
+:1004B000C3FFF1BF8FCFFFFFDD7BFFF6FAF7FF40F1
+:1004C0009FF97FD8FFFFFAF01FFFFFFFFEF1C0008A
+:1004D00000030000000000000000400010000010B9
+:1004E00000010010202000001000040105000000A1
+:1004F00000404000003CF01FFFFFFFFEFDBFFFFF7C
+:10050000FFFFFE7F7FFFEFFFFFDFFFFFDFFFEFF764
+:10051000F1FFFFFFFFDFFFFFF7FFFFFFFCFDFF7FA6
+:100520007EFFFFFFDBF06FFFFFFFFEF0BBFFFFFF73
+:10053000FFFFFEEBFD6FFFF7FEF57FFFFF7FBFB113
+:10054000FFFF9FBFFBFFFEFFFEFFF7EBDFBF5FDD9F
+:10055000FFDBFDD0F06FFFFFFFFEF8302000420010
+:100560000000301804080921828002000800010000
+:1005700000000C2010001100448400202084800022
+:100580000000C1F0DFFFFFFFFEFFF7FFFBDDF9FF1B
+:10059000DAFFDCDDFCFBFFBFFB3ED796FE61F7FF19
+:1005A0007FFF3FFDFFDFCFF7DFF7BFFDFFFEEFEF80
+:1005B000FEFFF07FFFFFFFFEFFFFFFFFFFFFFFFFDC
+:1005C000FFFFFFFFFFFFFFFFFFFFFFFFF1FFFFFF49
+:1005D000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF2B
+:1005E000FFF02FFFFFFFFEFFFFFFF3BDFD4B74CFBA
+:1005F000735BCB3BDFFEF7FED375ACA1FBDFFEF7F1
+:100600007696B524BDA5AD492F692B525BBDFFFF82
+:10061000F0CFFFFFFFFEBFFFFFFFDBFFF6FEFFCCCB
+:10062000A7FBADFF7F6FFF6D7FDBF1FDBFFF6FFFAE
+:100630006FFFDBFFDBFFF697F6FFB5B5FFFFFFD0DF
+:10064000EFFFFFFFFEFFFFFFFDA5BC43FC7C03E7C0
+:10065000FFFF20FFFFFFCCFD7DF1FFFFFFFFD5591E
+:10066000BA56666AAD9AA99A97A5AABBFFFFF00F82
+:10067000FFFFFFFEFEFBFFFDF7FD43FFFD6BE7FF06
+:10068000FFDFFFFFFFFFFF3FF1FFFFFFFFD559B582
+:10069000A6666AAD9AA9996B5AAAFFFFB7F03FFF09
+:1006A000FFFFFEFFFFFFFE9CF7FDD241FFFFF27F41
+:1006B0008FFFFF3DF3FF17F1FFFFFFFFFF7FDFFC21
+:1006C0008F38FFEF23FFFBF7C8FFFFFFF09FFFFF0F
+:1006D000FFFEF57FFFFDFFE4FFEBFFCFBFFAFFABAF
+:1006E000EFFFFBFFF3FD61FFFFFFFFFAFFFBFD0DD7
+:1006F000FFFEFF437FFEBFD0FDFFFAF03FFFFFFF8D
+:10070000FEF3C0000000020002010060C0400000D3
+:100710000000340400010000000000000008880010
+:100720000003000040004000003CF03FFFFFFFFEE0
+:10073000FD3FFFFFFFFFFFFF7F7FBFFFFFFFFFFFCB
+:10074000FFFFFFF7F1FFFFFFFFFFF7FFFFFFFDFFD9
+:10075000FFFFFFFEFE5FFFFFCBF0DFFFFFFFFEF0BE
+:10076000FFFFFDFFEFE3DEEED9C593FFFFFEFEFFC7
+:10077000FBEEFEF1FFFFFFFFFFFDFFBFF7FFFF7F77
+:10078000AFBDDFDFFBF3F3F0F0AFFFFFFFFEF834A8
+:10079000000661001801A0051700200528200000B0
+:1007A0000500410000400009000120868208400346
+:1007B000803070081402C1F0CFFFFFFFFEFFFFFF83
+:1007C000FFFFBDEFFBFFFFFB9C7FEFDFFFBFEBDE1B
+:1007D000FFC17FFFFB7FFFFFFF5FFFFFFFDFBFEF7B
+:1007E0003FF78FEF7FFFF07FFFFFFFFEFFFFFFFF71
+:1007F000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF09
+:10080000F1FFFFFFFFFFFFFFFFFFFFFFFFFFFFFF06
+:10081000FFFFFFFFFFF03FFFFFFFFEFFFFFFFFBDFA
+:10082000DFEF7D6D2B5A5DD2DFF692B6B2B3ACA18D
+:10083000FBDFFEF1EEF5F6BC6BBD7DAF1AEF5F6B33
+:10084000C6FFFFFFF05FFFFFFFFEBFFFFFFFDBFF05
+:10085000F6FFF6B7FDADFDBFF36FFF6FFFDBD1FD18
+:10086000BFFF6FF56BBC5B3CDAEF16AF16FFCDAB8D
+:10087000FF6FFFD0FFFFFFFFFEFFFFFFFCBFFFFF8B
+:10088000FF6C0310C1F3FFF33AF3CAFFAFF1FFFFB0
+:10089000FFFFD996A665A6666A9569696A5A5AFFE6
+:1008A000FF5FF01FFFFFFFFEFFFFFFFFBFFFFFFF28
+:1008B000EA0F50C3F37FFFF3F3C3FFAFF1FFFFFF76
+:1008C000FFD996A665A6666A9569696A5A5AFFFFB6
+:1008D000FFF03FFFFFFFFEFFFFFFFFD7FFFF5FC1FE
+:1008E0003FF75EF5CE9E5F3F17FFF3E1FFFFFFFF8F
+:1008F000D8FFFAFE67FFFEBF5AFFFFAFF5FFFFFF0D
+:10090000F02FFFFFFFFEF5FFFFFDFFF7FFFD4E3D60
+:100910003FE70BBF8FF9FFEBE3FFE1FFFFFCFFC7F2
+:100920009FFF3E39E5FFCF9BF9FFFFC5FFFFFAF0C0
+:100930005FFFFFFFFEF3C00000000000000040006A
+:100940000000006000000000000100000020002006
+:10095000000110080000000000000000003CF04F03
+:10096000FFFFFFFEFDBFFFFFFFFFFFFFFEFFFFBF1B
+:100970003FFFFFBFFFFFFFFBF1FFFFFFFFF7FFF7A9
+:10098000FFEDFFFBFEFF7FFF7FDFFFFFDDF03FFF9F
+:10099000FFFFFEF0FFFFF3FFF7FFFE5FFFF7FFFF34
+:1009A000DFFFFFFFF7FE7BF1FFFDFDFFDFDFFF7DD8
+:1009B00073F9FFC37EFEFFEFD7FFCFD0F06FFFFFCD
+:1009C000FFFEF83000004004000141200004000256
+:1009D000D50900028002010000000A04000700019E
+:1009E000500180026140410C1408C1F09FFFFFFFDD
+:1009F000FEFFFFFFFEFFFFFFFEDFCB5FFEEFFFFE10
+:100A0000FF3FFF7FFDC1FFFF7FFFDFFDFCFDF7EE36
+:100A1000FFFF4EFFDFCFDBEBFFFFF01FFFFFFFFE0F
+:100A2000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFD6
+:100A3000FFFFFFFFF1FFFFFFFFFFFFFFFFFFFFFFD4
+:100A4000FFFFFFFFFFFFFFFFFFF02FFFFFFFFE7F16
+:100A5000FFFFFFFDFFFFFFFFFFFFFFFFDFFFFFFFC8
+:100A6000F7FBFFF1FFFFFFFFFFFFFFFFFFFFFFFFB0
+:100A7000FFFF7FFFFFFF7FFFF01FFFFFFFFEDDFF98
+:100A8000FFFFA5FF6F6BE96FDACAFBDDEEF7F6B289
+:100A9000B3A4A15B5BF6D7F4F77BBDBDADCFEF7F11
+:100AA0006B7F3BDFDBFFFF30CFFFFFFFFEBFFFFFB2
+:100AB000FFFFFFF6FE96FFFDB5FDBFAD7FFF6FFFA9
+:100AC000DED1ADADE9FFF1ECEFDE3FCBFFF6FF325B
+:100AD000FFC5BDFFFFFFD0BFFFFFFFFEFEFBFFF422
+:100AE00028BFFFFDFBD3FFFF42FFFFFFEAB3FCC3BC
+:100AF000C1FF33FFC0156B70FFF0F24FFFFC3E9754
+:100B00003CFFFFFDEFF0BFFFFFFFFEFFFFFFFE78A2
+:100B1000BFFFFDF3EF55FF7EFFFFFFEAB3FCC3C14C
+:100B2000FF33FFC0156FFF0FF0F00FFFFC3D6BC3ED
+:100B3000FFFFFEF7F0CFFFFFFFFEFFFFFFFFFCFF11
+:100B4000FF23F87FFF4EFFFFFFFBF917FFF6F1FFD2
+:100B5000CFEFFFFF13DFE62FC7FFFFE7C1FDFFFE6B
+:100B6000FFFFFFF04FFFFFFFFEF5FFFFFFFEAEFFB1
+:100B7000FF7F3B3FFC7FFCEFFFFCE27BFFF1FDEDE5
+:100B8000EFFFFF3573FFFFFEFAFFFFFFFEBFFFFF22
+:100B9000FFFAF08FFFFFFFFEF1C000000000000031
+:100BA000000000800000400000000C0401404000F4
+:100BB00000302804000800000001000100000000CF
+:100BC00038F00FFFFFFFFEFDBFFFFFFFFFFBFF7FC2
+:100BD000FFFF9FFFFFFFFFFFFFFFFFF1FFDFDFFFD3
+:100BE000FFFFFFEDFFFDFFFFFFFFFFBFBFFFFFC3E5
+:100BF000F03FFFFFFFFEF0BFFDFFBFFFFFFDFFFF68
+:100C0000FFFFFFFD7BFF7FFFBDFFF1EFFFFFFDDF7C
+:100C1000FDFBFFFFBFBEFFCD7FFCF7F76FBFD8F036
+:100C2000EFFFFFFFFEF830000000040000A000000E
+:100C3000C0000020340000000C810020A42000101F
+:100C400008044808004093001000381820C1F03F05
+:100C5000FFFFFFFEFFFBFFFFB9DFFEB3FFFFE7FD76
+:100C6000FFFF3BFF7FFFBFFFC1FFFCFFFF3F77FEA2
+:100C7000FECFFFBFFDBFFFFEEDF2FDF7FFF02FFF40
+:100C8000FFFFFEFFFFFFFFFFFFFFFFFFFFFFFFFF75
+:100C9000FFFFFFFFFFFFFFF1FFFFFFFFFFFFFFFF72
+:100CA000FFFFFFFFFFFFFFFFFFFFFFFFF0BFFFFFA3
+:100CB000FFFEFFFFFFF3ADCFEF70C9733BDF5B4A71
+:100CC000F6B7FED7F5BCC133CAD6B76EF7FBBDC5C4
+:100CD00024CF6F2F4D2BBA5AFFFFFFF0AFFFFFFF5E
+:100CE000FEBFFFFFFFFFF6F6D7FFFFADBDFFFFFF23
+:100CF000EFF77FFC5BB1FDBD756FEF6AFD5BFBDB62
+:100D00003ABF8E9FFFBFFDFF6FFFD06FFFFFFFFE5B
+:100D1000FFBBFFF03FFFFFFDFB7FDEFFFF5AD6BFAB
+:100D2000D82ABFBFF1E5FFCCC0A970FFF33C3CFD62
+:100D300057FD980300C3FFFFFFF0AFFFFFFFFEFF6B
+:100D4000FFFFFF3DBFFFFDFBFFDBFFFF0FFC3FD8B9
+:100D50002ABFBFF1EFFFCCC096BEFFF33FFFFD57A8
+:100D6000FD990FFFC3FFFFFFF04FFFFFFFFEFFFFE7
+:100D7000FFF1E7FFFFF38E7BFFA8FFDF7F8E787325
+:100D8000FFF15162FFFC4BFFF3FF7ECFF9FFFDFF48
+:100D9000FF7FFFE0FFFFFFF04FFFFFFFFEF5FFFFCC
+:100DA000FBFDAEFFFCFE6F3FF8FD77AFFE37FE7B2D
+:100DB000FFB18CFFEFFDF8E7BFFFF1FE3EF7FE95B8
+:100DC0003EBFFFFFFFFAF0BFFFFFFFFEF1C00000D4
+:100DD0000104000000008002000010001000100854
+:100DE0004180100000081084000C040261000081A2
+:100DF000000000003DF07FFFFFFFFEFDBFFFFFFF93
+:100E0000FFFF7FFFFEFDBFFFFFFFFFFFFFFFFFF1C3
+:100E10007FBFF77FEFFFEFFFF7FDFFFFFD7FFFBE17
+:100E2000DFFFFFD9F0BFFFFFFFFEF0BBFF7FFBFF3F
+:100E3000FBFFBFFFF37FFBFDEB7FDFFAFFDEF0ED93
+:100E4000FFB1F7F91FB55BFE7EF7BEFD7F5FB5F71B
+:100E5000FFFFD0F04FFFFFFFFEF830010007420117
+:100E6000006A185080000002400101200101241492
+:100E700021100208070800401080580084801810D4
+:100E800040C1F0BFFFFFFFFEFFFFFFF7FFDBB7F33F
+:100E9000DF7CF874FFFF6F7D3F7EEC7FC1F5FFCFF5
+:100EA0006F9FF9DFBEE5E7FFD7F3DDFBFFFCFFBF78
+:100EB000FFF0FFFFFFFFFEFFFFFFFFFFFFFFFFFF52
+:100EC000FFFFFFFFFFFFFFFFFFFFFFF1FFFFFFFF40
+:100ED000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF22
+:100EE000F02FFFFFFFFED7FFFFFFB4CFEF776F7349
+:100EF0003A4A3ACBD4F72ED6BDBDA13BDFD6F7EEAA
+:100F0000D335BDFBBDCEEB2B4D2FBBDAFFFFFEB0C3
+:100F10005FFFFFFFFEBFFFFFFFDF5F36AF3FEDB7B5
+:100F2000F5FDF32BEF77FFFBDAB1BDA377697F4FB8
+:100F3000FFDBFA5BFFF2FEFF96FFFFFEDFFFD0AFA5
+:100F4000FFFFFFFEFFFFFFFD8FFD406F9E835A0FE7
+:100F5000FAC3FFFFFCE97FF301D000FEBFCD3FF0F5
+:100F6000EFFCC50C3FFD680BFFFFFFFEDFF0FFFF4E
+:100F7000FFFFFEFFBBFFFD85FFD46F9FC35A0FFF2E
+:100F8000FFFFFFFCE97FF301F0FBC2BFFC0037EF7E
+:100F9000FCCDBC3FFF0CBFFFFFFFFFFFF05FFFFF7B
+:100FA000FFFEFFFFFFFFD9F7D1B77E7FF1E4FDFF22
+:100FB000FBFBFF5FFF7FB1BC0F67EBB83FFFE2FFBA
+:100FC000E9FFFDE3FF3F9FC2FFFFFFF09FFFFFFF31
+:100FD000FEF57FFFF03FBCFFD5F5CE3FFEFFFE6D77
+:100FE000FFF1BF7BFFF1FDFF4FFF87FFAEFFB1F8C1
+:100FF000FEFFFF7801B9FFFFFFFAF02FFFFFFFFEB2
+:10100000F3C00000000402130200804000901000B2
+:1010100010000200012080121000400800040000AF
+:1010200002000140008000003CF0EFFFFFFFFEFDEA
+:101030001FFFFFFF7FFFFFFFFF7FFF7FF7DFF7FF50
+:10104000F7FBEBD1FFFFFFFFEFF7FFFFFBFFFEFF1B
+:10105000FF7EFFFBFFFFFFDBF0FFFFFFFFFEF0FF68
+:10106000FFB7EBF7DFFFFEF56BE7EDF73EECFF5464
+:10107000EF6FF1F5AF6FF6FDFFDD7BFFEFBF7FFF99
+:10108000FFF7FFF35FF7D0F0CFFFFFFFFEF8300070
+:1010900080400400812C0424000201C802000224C4
+:1010A0000001B442DC4402159002034839100224C6
+:1010B000A0BA000040C1F0BFFFFFFFFEFFFFFFFF2F
+:1010C000FEFCF7F0EEB65DFDF5FFDBF77F7FBEFFC0
+:1010D000C1FEBFFAFA5FFFADFFEFFF7FDF7FFEBF0C
+:1010E000B794BFFFFFF09FFFFFFFFEFFFFFFFFFF73
+:1010F000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF10E
+:10110000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFEF
+:10111000FFFFFFFFF08FFFFFFFFED7FFFFFBB5FFD5
+:10112000EF7CEB2B525B3BDAD4F33696B5BDF1FB8B
+:10113000DAEEF6FED335BDDFADCFEF7ECD6BBBDF94
+:10114000FFFFFDB0EFFFFFFFFEBFFFFFFFD35FF626
+:10115000FFF6FFFDADFDFF7FEFFF6F7FDBF1A5A386
+:101160007F6F6B4FFFDBFBCBFFF6FFF4D7FDBFFEBE
+:10117000DFFFD0CFFFFFFFFEFFFFFFF7DFFFFFFF27
+:101180003F7FFCE5FF20FEFFFFDF7FFFF17FFFFEDB
+:10119000FFF07C3D4FF3C33FFFFF6FC3FF0FFFFF27
+:1011A000AFF02FFFFFFFFEFFFFFBB7E00FFFFF2BAE
+:1011B000FF7DBFFFDFFFFFF89F7FFFF155FFFFFFC0
+:1011C000FD7C3CFFF3C33FFFFFEFC3FFDFFFFFFFEB
+:1011D000F09FFFFFFFFEFFFFFFFFEFFFFF9FBF7FBF
+:1011E000F919478EE79F3F17FFFC81C17EF3D9F9BC
+:1011F00073DFF47FFAFFFFFFFB7F77C7FFFFFFF08E
+:101200002FFFFFFFFEF5F7FFFBFFF73FFCBF3E3F61
+:10121000ECFF81AFFE4FF3BBFFF07EFF6FFF87FF58
+:10122000BBFFD5FCFF7FFC6FFFEFE7FFFFFAF03F4E
+:10123000FFFFFFFEF3C00000000000000000008080
+:101240000030106020000800012080001000040021
+:101250000000000000020080400008203CF06FFF0A
+:10126000FFFFFEF5BFFFFFFEFFFFFFFF7FFE3FFF1B
+:10127000FFFFFFFFEFFFFFF1DFDFFFFFFF7FDFFF7C
+:10128000FDBDFFFFFFFBDFFFFFFFFF5BF0FFFFFF89
+:10129000FFFEF0BFBFBFFFF7FBFFFEEEFAFFFFFF51
+:1012A0003D3BFFFFFEFBF1FFBF7BFFFFEFFFBFFFFB
+:1012B000FFFFFFFFFEFFF7EFFFFBD0F0DFFFFFFFB9
+:1012C000FEF83000000000000B10050100080002CD
+:1012D000010100001001C8080000000042020000E7
+:1012E000008002000040248000C1F03FFFFFFFFEAD
+:1012F000FFFFFFFFF7FDF7FAEFEEF9FDFFF7FEBF87
+:101300001FFD9EFDD1EFFFF77F9FFFEFFFF6FFFE72
+:10131000FE7BFFBDFF7EFFFFFFF03FFFFFFFFEFFF5
+:10132000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFCD
+:10133000FFFFFFF1FFFFFFFFFFFFFFFFFFFFFFFFCB
+:10134000FFFFFFFFFFFFFFFFF0AFFFFFFFFEFFFF0D
+:10135000FFF7FFFFFFFF7FFFFFFFDFFDFFFFDFFF67
+:10136000FF5FF1BFFFFFFFFFFFFFFFFFFFFFFFFF7B
+:10137000FFFFFFFFFFFFFFF0DFFFFFFFFEFFEFFFBD
+:10138000F7FFFFFFFFFFFFFFFF3FFBFFFFEFFBFD4F
+:10139000FFF1FFFFFBFFFFFFFFFFFFFFFFFFFFFF6F
+:1013A000FFFFFFFFFFFFF02FFFFFFFFEF7FFFFFF35
+:1013B000FFFFFFFFFDFFFFFFFFFFFF7FFFFFE7FFD7
+:1013C000F1FFFFFFFFFFFFFFFFFFFFFFFFFFFFFF3B
+:1013D000FFFFFFFFFFF0FFFFFFFFFEFFFFFFFFFF2D
+:1013E000FFFFFFFFFFFFFFFFFFFFCFFFFBFFFBF153
+:1013F000FFFFFBFFFFFFFFFFFFFFFFFFFFFFFFFF01
+:10140000FFFFFFFFF02FFFFFFFFEFFFFFFFFFFFFCC
+:10141000FFFFFFFFFFFFFFFF7BFFFFFF7FFFF1FFEE
+:10142000FFFFDFFFFFFFFFFFFFFFFFFFFFFFFFFFEC
+:10143000FFFFFFF07FFFFFFFFEFFFFFFEFFFFFFF5C
+:10144000FFFFFFFFFFFFFFDF57FFFEBFFBF1FFFFC7
+:10145000FDF7FFFFFFFFFFFFFFFFFFFFFFFFFFFFA6
+:10146000D7FFF07FFFFFFFFEFFFFFFF7DBFFDBFD96
+:10147000F6FFF6FF3CBCBCBFDF6FEF2FF13CBFBCFB
+:10148000BFDF6FFF6FF7DBFFDBFDF6FFF6FFFFFF50
+:1014900001E2EFFFFFFFFEFFFFFFFFFFFFFFFFFF88
+:1014A000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF4C
+:0614B000FFFFFFFFFFFF3C
+:00000001FF
+/*
+ *
+ * File yam1k2b5.mcs converted to h format by mcs2h
+ *
+ * (C) F6FBB 1998
+ *
+ * Tue Aug 25 20:24:08 1998
+ *
+ */
diff --git a/firmware/yam/9600.bin.ihex b/firmware/yam/9600.bin.ihex
new file mode 100644
index 000000000000..817a34be22cc
--- /dev/null
+++ b/firmware/yam/9600.bin.ihex
@@ -0,0 +1,342 @@
+:10000000FFF200A5ADFFFE9FFFEFFBCBFFDBFEF293
+:10001000FFF6FF9CBFFDBFEF2E3F6FF1FDB4FDBFAC
+:10002000FF6FFF6FFF0BFFDBFFF2FFF6FFFFFFFF2E
+:10003000F06FFFFFFFFEFFFDDFFFFFFFF7FFFFFF9A
+:10004000FBFFFFF7FFFFFFFEFF7FF1FFFEFFBFBFDC
+:10005000FFFFFFFFFFF7FFFFFFFEFFFEFFFFFFF0C9
+:10006000EFFFFFFFFEFFFFFFFFFFFFBFFFFFFFF7F9
+:10007000FFFFF7EFFFFFFFFFFFF1FFFFFF7EFFFF37
+:10008000FFFFFFFFDFFFFFFFFFFFFDFFFFFFF0DFD1
+:10009000FFFFFFFEFFFFDFFFFFFFFFFFFFFFFFFF91
+:1000A000FFFFEFFFF3FBFEFFF1FFFDFFFFFFFFFF91
+:1000B000FFFFFFFFFFFFFFFEFFFFFFDFFFF07FFF00
+:1000C000FFFFFEFFFFEFFFFFFFFFFFFFFFFFFFFF51
+:1000D000FFFFDFFFFFFFF7F1FFFFFFDFFFFFFFFF86
+:1000E000FFFFFFFFFFFFFFFEFFFFFFFFF00FFFFF20
+:1000F000FFFEFFFFFFFFFFFFFFFFFFFFFFFF7FFF91
+:10010000FFFFFFFFFFFFF1FFFFFFFFFFFFFFFFF517
+:10011000FFFFFFFFFFFFFFFFFFFFFFF02FFFFFFFCE
+:10012000FEFFFFFFFFFFFFFBFFFFFFEFFF7FFFEF84
+:10013000FFEFFF7FEFF1FFEFFF7FFFFFFFFFFFFF0D
+:10014000FFFFFFFFFFFEFFFFFFFFF09FFFFFFFFE30
+:10015000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFAF
+:10016000FFFFFFFFF1FFFFFFFFFFFFFFFFFFFFFFAD
+:10017000FFFFFFFFFFFFFFFFFFF0BFFFFFFFFEFFDF
+:10018000FFFFFFBDFFEF7FEF7FFBDFD35AFED7D628
+:10019000F77FBDF1BB5DD6F7FE96FFBDAFADBFEFFC
+:1001A0007F6B7FFBD6FEF7FF10EFFFFFFFFEBEEF7A
+:1001B000FFFFDBFFF6FFF6FFFDBFFDBFFF7FFF7F09
+:1001C000DFDBF1FD35FF6FFF6FFFDBFFCBFFF6FFDE
+:1001D000F2FDFDBFFFFFFFD0EFFFFFFFFEFFFFFFC0
+:1001E000FFFFFFFFFFFFFFFFFFFF55FFCCC03FFFFB
+:1001F000FFF124F0FFFFCFEF3FFFF0FFFFFFFC3FD9
+:10020000FFFFFFFFFFFFF0CFFFFFFFFEFFFFFFFF3E
+:10021000FFFFFFFFFFFFFFFFFF55FFCCC03FFFFFCA
+:10022000F100F0FFFFCFDFFFFFF0FFFFFFFC3FFF1C
+:10023000FFFF7DFFFFF0FFFFFFFFFEFFFFFFFFFF60
+:10024000FFFFFFFFFFFFFFFFDFFE7FDFFFFFFFF18D
+:10025000FFCFFFF3FF97FFFF8FE7FFFFFC71FFFF6B
+:10026000FFFFFFFFF0EFFFFFFFFEF5FFBFFFFFFF08
+:10027000FFFFFFFFFFFFE3F7EFFFFFFC7BFFF13F17
+:10028000FFEFFFCFE3E3FFFFFFFF3FFFFFFFBFFFF6
+:10029000BFFFDAF07FFFFFFFFEF2C00000000000AA
+:1002A000000000000000000000000000000100004D
+:1002B000000000000000000100000200000000003B
+:1002C000013CF0AFFFFFFFFEFDBFFFFFFFFFFFFFA1
+:1002D000FFFFFFFFFFDBFFFFFFFFFFFFF1FF9FFFC0
+:1002E000FFFFF7FFEFFFFFFFFFFFFFFFFFFFFFFF36
+:1002F000DBF07FFFFFFFFEF0BBDFFFFFFFFFFFFF35
+:10030000FFFFFFFFFFFFFFEFFBDFBFF1FEFDF7FF8A
+:10031000FFFFFFFFFEFFFFFFFFFFFFFFFF77FDF285
+:10032000F01FFFFFFFFEF838000000000000000390
+:100330000000000200900000000C010000042400F6
+:100340004001000000400000000002000001C0F079
+:100350004FFFFFFFFEFFFFFFFFFFFFFFFFFFFFFF5E
+:10036000FFFFBFFFFF6FFFDFFFD1FFFEFFFFFFFFBC
+:10037000FFFFDFFFFBFFFBEFFFFFEEFFFF7FF0DF85
+:10038000FFFFFFFEFFFFFFFFFFFFFFFFFFFFFFFF7E
+:10039000FFFFFFFFFFFFFFFFF1FFFFFFFFFFFFFF7B
+:1003A000FFFFFFFFFFFFFFFFFFFFFFFFFFF08FFFDC
+:1003B000FFFFFEFFFFFFF5ADFF692AED6BFBDF3AA4
+:1003C000DCF496EEB33D35C1BBDDFEF6FED6B5AD31
+:1003D000BFA5AD492F4F2BDA5FFFFFFFF02FFFFFC7
+:1003E000FFFEBFFFFFFB5BF7F6FFF6FFFDBFFDA5BE
+:1003F000F36FF36EFA7BD1FDB5776FE96FFFDBFB2F
+:10040000DBDFF6FFF6FFFD3FFEF7FFD04FFFFFFFFC
+:10041000FEFF9FFFFF0FFFC03F9C03FFFF8BA5FE6A
+:10042000803EC2BFACB124FFFFFFFFFFFF0FFFA361
+:10043000FFFD6BFFFFF0A5FFFFFFF0AFFFFFFFFE2B
+:10044000FFFFFFFF0FFFC03FD46BFFFFDBFFFE8608
+:10045000BFC2BF30A124FFFFFFFFCCFF0FFFA3FFF0
+:10046000056BFFFFF0A5FFFFFFF07FFFFFFFFEFF23
+:10047000FFFFFBC7FFC4FFFF7FFFECFE7FDFD8B9A4
+:1004800047FC36C1DFFFFFF9FFF3FFF7FFFCFFFD7D
+:100490003FFFFFFF3FFFFFFFF07FFFFFFFFEF5FF86
+:1004A000FFFFFFFEFFFF7EBD3FFF2BFE2FF5A3FCEE
+:1004B0005BFE619F7FEFFFFFA7FBFFFFFAFEFF33AD
+:1004C000F1FFBFFFFFFFFAF07FFFFFFFFEF1C0006B
+:1004D0000000000000000000000000400030240484
+:1004E000000100804000080000000201010002003D
+:1004F00000000000013DF02FFFFFFFFEFDBDFFFDEE
+:10050000FFFFFFFFFFFBFFFF7FF6EFBFF7FF73EB80
+:10051000F1FFFFFFDFFFFFFFFFFFF9FFFDFEFFFF22
+:10052000FFFFFFFFD9F0DFFFFFFFFEF0BF7FFFFF00
+:10053000FF7FFFFFDEFFFFEFDDDE77F2FBEDE7F190
+:1005400073FDFDDFFF7DBEDFFFFBFFEFFFEFFFFF72
+:10055000FFFFFFD0F0BFFFFFFFFEF83020020022B8
+:1005600040C0000000080002410212002187810003
+:100570000080040B2801B000820040000000000051
+:100580000000C1F0DFFFFFFFFEFFFFFFFFFFFDFFE9
+:10059000F7FFFE7FED79FFDEEB7F74F7F7E1F9FF00
+:1005A000F65F7FFFFFFFD7DBEFFFBBFFFFFFCCFF57
+:1005B000FFFFF0CFFFFFFFFEFFFFFFFFFFFFFFFF8B
+:1005C000FFFFFFFFFFFFFFFFFFFFFFFFF1FFFFFF49
+:1005D000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF2B
+:1005E000FFF00FFFFFFFFEFFFFFFFD3DCD497F6FD7
+:1005F0002BBA5CD2DAF6F33EF7FFBDF1FADFFEF775
+:10060000CCF6BBA5B3ADBF6F7D6F6BDBDFBDFFFE6F
+:10061000B05FFFFFFFFEBFFFFFFBDB57F6FE9FD57E
+:10062000B7FFAFE53FFFFF6FFFDBF1FDBFFF6F6976
+:100630006CDFDADFCBFFF6FF76FDFDBFFFFFFFD0FB
+:100640003FFFFFFFFEFFFFFFFFFDBD0803894F5A7D
+:100650000FF0FFF8BFFFFFFFFFF15AFFFFFFFFF3AF
+:10066000FAA0F0F2BFFFFFFFFFFFFFFFFFFFF0FF69
+:10067000FFFFFFFEFFFFFFFFFCFD006BFFFF5A0FB8
+:10068000F0FFFFFFFFFFFFFFF15AFFFFFFFFB3F592
+:1006900050F0F0FFFFFFD7FFFFFFFFFFFFF07FFFEE
+:1006A000FFFFFEFFFFFFFDBCFFE4E771FFF9C4F4AD
+:1006B0007F7FCFFFFFFFFFF1FFFFFFFBF773BF144B
+:1006C000FFE6FFFFE17DFFFFE7FFFFFFF03FFFFFDA
+:1006D000FFFEF5FFFFFED2FAFFC4F45CBFFAFFFF96
+:1006E000EC7EBFFFFFFFF1FFFFEFFFFF6BDBFFDFE4
+:1006F000F9FBBFFFF1FFBFFFFFFFFBF0BFFFFFFFF5
+:10070000FEF3C00002000000008200000000800034
+:10071000000000400001000000010820000000006F
+:100720000100010000800200013CF05FFFFFFFFEBE
+:10073000FDBFFFFFFFDFFFFFFFFF7FFFDFFFEFFFDB
+:10074000FFFFFFFFF1FFFFFFFFFFF7FFFBFFFDFFD5
+:10075000FFFFFFFFFFFDFFFFC3F0AFFFFFFFFEF056
+:10076000FFDFFFFFF723FFFFFDFFEFFFFE7F7DF7BA
+:10077000FEFF7F71FFFB7FFFFFFF6EFDF7FDFFBFF9
+:10078000FFBFF9FDFFDFEFF0F0AFFFFFFFFEF83036
+:10079000400100830000000C060804262600000625
+:1007A0000300010000000004007008800020012008
+:1007B000000200300000C1F05FFFFFFFFEFFFFFFFF
+:1007C000FFFF7B3FF7FFD7FEFEFBFE3BFEBDFF2F8B
+:1007D000FF71FFFB7FE7FFF9EFFFD7FAFFB7BBFE23
+:1007E000FFFF74FFF7FFF0CFFFFFFFFEFFFFFFFFEC
+:1007F000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF09
+:10080000F1FFFFFFFFFFFFFFFFFFFFFFFFFFFFFF06
+:10081000FFFFFFFFFFF08FFFFFFFFEFFFFFFFFB5B2
+:10082000BD6F7CEB7FFBDBD34BEED6F6B7FDACA107
+:10083000FBDFFEF7F496BDB4C5A5AF6F694F7FBA75
+:10084000DBFFFFFFF03FFFFFFFFEBFFFFFFFDBFF10
+:10085000F6FFF6FFBDBFA5BFFF7D7FEFFFFBF1FDFC
+:10086000BFFF6FFF6B7ADBFFDBDFF6FEB6FDFDBF80
+:10087000FEF7FFD0EFFFFFFFFEFFFFFFFFF42FFFAC
+:10088000FC436BFFFFFF0DFFFC333FF05FF1FFFF09
+:10089000FFFFF9DEF04CFE77AFFFFFEFFFF0FFDB6D
+:1008A000FF5FF0EFFFFFFFFEFFFEF7FFF02FFFFD02
+:1008B000437FFFFFF10FFFFC333FFFAFF1FFFFFF6F
+:1008C000FFF6D7FFBCFDBDFFFFFFFFFFF0FFFFFFFF
+:1008D000FFF0EFFFFFFFFEFFFFFFFFFCFFFFFBF15D
+:1008E000BFFFF9FDCFF270FF1F9FF3F1FFFFFFFF86
+:1008F000FCF7FF139FFCFFFF84F7FFFF47FFFFFF9D
+:10090000F0BFFFFFFFFEF5FFFFFFF1FCFFFEFE79EA
+:100910003FFF1D46CFFFCFFC7BFFF1FFFFFFFFED49
+:10092000F3ABFFCBFFF8FFFCF5FFBFFFFFFFFAF0D3
+:100930008FFFFFFFFEF3C200000000000000010077
+:10094000000020002000000408010000000000203A
+:100950000C0000040100010000800000013CF07F59
+:10096000FFFFFFFEFDBFFFFFFDFEFFFFFFFFFEFFDE
+:10097000DFFFFFF7FFFFFFEFF1FFFFFFFFFFFFEBE1
+:10098000FFDFFFFFFBF77FFFFEFFFFBFDBF0FFFF97
+:10099000FFFFFEF0FFFFFFFFFFDFFFFFFF7FF7FF1F
+:1009A000BFBFCFFFFFFF3EF17FFFFFEFFFFFFFFE67
+:1009B000FFFDFFBFBDFEFFFBF7DFFBD0F09FFFFF9A
+:1009C000FFFEF8302000400180C030000020001001
+:1009D00050882000001301000000000000100000FB
+:1009E00000000180080000A00010C1F0EFFFFFFF31
+:1009F000FEFDEF7FFFFFBFFFF7FFEFFBFD77EFBFD0
+:100A0000F77FFFFFBFD17FFFFFF7FFFFFFFFAFFFC4
+:100A1000DFF7FBFFFDFFFCFFFDFFF0FFFFFFFFFE29
+:100A2000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFD6
+:100A3000FFFFFFFFF1FFFFFFFFFFFFFFFFFFFFFFD4
+:100A4000FFFFFFFFFFFFFFFFFFF05FFFFFFFFEFF66
+:100A5000FFFFFFFFFFFFFFFFFFFFFFFFDFFFFFFFC6
+:100A6000FFFFFFF1FFFFFFFFFFFFFFFFFFFFFFFFA4
+:100A7000FFFFFFFFFFFFFFFFE03FFFFFFFFEDDFF88
+:100A8000FFFFA5FD6F7D6D7F52DF5A4BEEB6EEF294
+:100A9000BBACA15B4DD6F7FEB2BD35B5B5DD6F7F02
+:100AA000E95F52DFBDFFFFF0DFFFFFFFFEBFFFFF8B
+:100AB000FFDBFEF6FFF6FFFDBFFDB5BFF97F6FFF61
+:100AC000DBF1FDBFFF6FFF697FDBFFD3FFF6FEF2B7
+:100AD000FFADBFFFFFFFD0DFFFFFFFFEFFFFFFF512
+:100AE000300FFFFFFD6BCAFFF00FD6BFCF3FFFFFF8
+:100AF000F1FFFFFFCAFEBFFFF005AF0FFFFCF0CF15
+:100B0000F0FFFFFFFFF0EFFFFFFFFEFFFFFFF530FD
+:100B10000FFFFFFC3FCAFF0F0FD6BFFFFFF55FF1CE
+:100B2000FF8BFFC3FFFFFFFFFFFF0FFFFCF0CFF0C6
+:100B3000FFFFFFFFF03FFFFFFFFEFFFFFFFFCFFFC5
+:100B4000FFBF9F3FFEFCFF4FFFFFFFFFFFF7F1FFDF
+:100B5000DFFE7E3F9FF4FC7FFCFFFF3FFF3FFE3F39
+:100B6000FFFFFFF04FFFFFFFFEF5FFFFFBFFFEFF64
+:100B7000FFFFFFBFFBFFF8EDFF8FFFBBFFB1F3EF00
+:100B80008FF7FFFFDBFFFFFFEFBFFD79BFBFFFFF69
+:100B9000FFFBF0DFFFFFFFFEF3C0000000040000DA
+:100BA000000000000000008000040808010100901F
+:100BB000000000040008000000000800040000011C
+:100BC0003CF0DFFFFFFFFEFDBFFFFFFFFFFFFFFF6A
+:100BD000FFFFFFFF9FFFAFDFFFFFFFF1FFFFFFFF03
+:100BE000BFEFFFFFFFEDFFFFFFEFFFBFFFFFFFC303
+:100BF000F03FFFFFFFFEF0FFFDFFFFFFFBFFBBFF2E
+:100C0000FFFF7FF6FF7FFBFDEDFFF1FFFE7FFFFFA4
+:100C1000FF5FFFF7FF7EFFFDFFEFFFFFFFEFF0F04D
+:100C20008FFFFFFFFEF83080000400004002000349
+:100C300000050420000001D0008100200404000011
+:100C4000810408801000C0000000200008C1F06F7F
+:100C5000FFFFFFFEFFFF7FFFFFFFFFF3FDFFEDFC48
+:100C6000FFFF9FFBFDFFFFFFF1FFFF7FFB3EFF9FAD
+:100C7000FFFFFFFFFDF9FFFFFFFDFFFFFFF06FFF2D
+:100C8000FFFFFEFFFFFFFFFFFFFFFFFFFFFFFFFF75
+:100C9000FFFFFFFFFFFFFFF1FFFFFFFFFFFFFFFF72
+:100CA000FFFFFFFFFFFFFFFFFFFFFFFFF0CFFFFF93
+:100CB000FFFEFFFFFFFDBDFFEF7CEB7FFBDBFADC00
+:100CC000EEF7F6D7F52DA1BBDDEEF754F7FB2CB50B
+:100CD000B4BD6B6FEF6FBBDFFFFFFFF01FFFFFFFC8
+:100CE000FEBFFFFFFFFBFFF6FFF6FFFDBFFFBFEFFD
+:100CF0006FFF6FFADBF1C5BDF56FFF6FCADBFFDB7E
+:100D0000FBF697F6FFFDBFFEF7FFD09FFFFFFFFE4C
+:100D1000FFFFFFFFFFFFFFFF8B7FFFFFE763FFFF8B
+:100D2000FFFC77DFF1DBFFD6A83FFFFF082FF0FFC6
+:100D3000C3FFEBFFFFFFFFFF5FF0EFFFFFFFFEFFD3
+:100D4000FFFFFFFFFFFFFF8BFFFFFFFFFFFFFFFF27
+:100D5000FCFFCFF1DBFFD6A83FFFFF082FF0FFC35A
+:100D6000FFEBFFFFFFFFFFFFF05FFFFFFFFEFFFF57
+:100D7000FFFFFFFFFFFFF5BFFFCAFF9FFFFAB9E7C5
+:100D80009FF381FFFFFC73D7FFFF77FFFDFFFCFFA1
+:100D9000FFFFFFCFFFFFFFF01FFFFFFFFEF5FFFF8D
+:100DA000FFF7DEFFFE7EFFBFFFBFF1B3FFFFE3FBF8
+:100DB000FFE11F7FFFF878FFFB1EFFF7FEE7FFFF55
+:100DC000FFBFFFFFFFFAF04FFFFFFFFEF3C0000081
+:100DD00000000000000000000000500000000400BF
+:100DE00001804040200000080000000003000000D7
+:100DF000800000013CF0AFFFFFFFFEFDBFFFFBFFE7
+:100E0000FFFFFFFFFFFEFFFFFFFFFFFFFFEFF7F119
+:100E1000FDFFFFFFDFFFEFFFFFFFFFFFFFFF7FFF94
+:100E2000FFFFFFDBF08FFFFFFFFEF0FFDFFFFF7F25
+:100E3000FFFFFFBED7FFEDBD7EBFFEF67FBF71FF98
+:100E4000FFDAFFF9FFBF7FFEFF6F7FFFFFFFFFFFAE
+:100E50007FFFD0F0CFFFFFFFFEF830420000000020
+:100E600080C100009000C400001220432281840051
+:100E700000140001000880000200020004020000CB
+:100E800010C1F01FFFFFFFFEFFFFFDFFFFDDFEFFB4
+:100E9000B676E5BCF9F7AF5FBFFCDFCFF1FFEF79C6
+:100EA000FFBDFFEFFFFFF76F5FFFFFFDEFEFBFFF3E
+:100EB000FFF09FFFFFFFFEFFFFFFFFFFFFFFFFFFB2
+:100EC000FFFFFFFFFFFFFFFFFFFFFFF1FFFFFFFF40
+:100ED000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF22
+:100EE000F0FFFFFFFFFEDBFFFFFD2DFF692AEF771D
+:100EF000BBDD5ADFF6F6D6F77DBDD1B24AD6B2BE1B
+:100F000097F5BDB3ADFFEF7F696BFBDFFFFFFFF030
+:100F10002FFFFFFFFEBFFFFFFFDBFFF6FE9FD4BFEB
+:100F2000EDAFFF6B6FF7FFDDDB31FDBFFF6F7FFFC5
+:100F3000FFDBFFCBDFF6FFF6FFFDBFFEF7FFD08F35
+:100F4000FFFFFFFEFFFFFFFD1FFF462F9FFFFFFF7D
+:100F5000A5FFFFFFDFB7FFFFF1FFFFFFF7E96ABF64
+:100F6000FFFFFDFFFFFD5557FFFFFFFFAFF04FFFF6
+:100F7000FFFFFEFEDFFFFD1FFF462F9FFFFFFFA5C8
+:100F8000FFFFFFC037FFFFF1998EDC7FE96ABFFFEB
+:100F9000F00FFFFFFD5557FFFFFFFFFFF00FFFFFB3
+:100FA000FFFEFFFFFFFF07FFC0BEFFFFCFEF9FFF6A
+:100FB000FFFBFFE7FFFFA1E3CE3C583FF3FFFDEF50
+:100FC000F9FFFFF7F17FFFCBFFFFFFF02FFFFFFFE0
+:100FD000FEF57FFFF0FFFEFFC475E7B9FFFFFFEFEF
+:100FE000FFC7373BFFF0139E0FF4FFFEFBFFFFF937
+:100FF000FCFFFFFFFFBFFFFFFFFAF0EFFFFFFFFE69
+:10100000F3C0010000020002220000C040004000C6
+:101010000408040A0101102020000004080804004C
+:1010200000000000010000013CF0CFFFFFFFFEFDCB
+:101030003FFFFFFFFFFFFF7FFF7FFF7FFFCF9DFF92
+:10104000FFF7FDF1FFFFFFEEBFFFFFFFFFFEFFFF1A
+:10105000FFFFFFFFFFFFFFDBF06FFFFFFFFEF0FF73
+:10106000FFFFF7F7FFFFFEBFF7FFFF5BFFBFF7FFD5
+:10107000FD7F71FDFFEDF7FEEFFFFF7FFFFFFFFF3D
+:10108000FFFFEFFF7FFFD0F0FFFFFFFFFEF8301103
+:10109000004860408260246000CC008004010000B1
+:1010A00014010C0400300000000808000100C20018
+:1010B0000002008000C1F05FFFFFFFFEFFFFFFFFA7
+:1010C000F77BFFF3EBBFFFF7FFFFFFE75D3FFFF6A7
+:1010D000D1FDFFEBF73DFFFFFF5FFF7F7FF3FFFFDA
+:1010E000EFFDBFFFFFF05FFFFFFFFEFFFFFFFFFF12
+:1010F000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF10E
+:10110000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFEF
+:10111000FFFFFFFFF0DFFFFFFFFEFFFFFFF5B5DF83
+:101120006F7D697FFBDF525FF6F7FEF6F3BDB1DA44
+:10113000CDFEF6EED2BDA5AFBDFF6F7CEB2BFADA8C
+:10114000FFFEDFF04FFFFFFFFEBFFFFFFFDBFFF6FD
+:10115000FFF6FFBDBFCDBFEB6FF76FDFDB51FDBD0E
+:10116000FF6FFF6FFB5BFFDBFFF6FEF6FDFDBFFED3
+:10117000F7FFD0FFFFFFFFFEFFFFFFFA50FFFFFF6B
+:10118000F06FFFFFF096FFFFC62BFFFFF1FCFFFFA4
+:10119000F7DBC3FF00FFFFFFFFFFC14FC3FFFFFFF0
+:1011A000AFF09FFFFFFFFEFFFFFFF5A0FFFFFFF087
+:1011B0006FFFFFF096FFFFC62BFFFFF15AFFFFFF07
+:1011C000F3C3FF00FFFFFFFFFFC14FC3FFFFFFFFA0
+:1011D000F0CFFFFFFFFEFFFFFFFFFCFFFF9FF07F51
+:1011E000FFF9FC4FF3FF27EBFFFC81FC7FFE7BFF49
+:1011F000F7FF127FFFFFFFFF18FFFFFFFFFFFFF06A
+:101200007FFFFFFFFEF5FFFFFFDFFEFFFC7E7FBFDE
+:10121000FFFFAFEFFFDFDFFBFFF1C3FE6FF1CF3F5B
+:10122000FBFFFFCFFEFFFFFE7FBFFFFFBFFAF0DF38
+:10123000FFFFFFFEF3C000000100000000010000FE
+:10124000200001001000000001000200000000006A
+:101250000000000200008000028000023CF02FFF2E
+:10126000FFFFFEFDBFFFFBFDFFFFFFFFFFFFFFFFD7
+:10127000FFFFFFFFFFFFF5F1FF7FFFFFFFFFEFFF26
+:10128000FFFFFFFFFEFFFFFFFFFFFFDBF02FFFFF72
+:10129000FFFEF0FFFFFFFBFFBFFFFFFFFFF7BFFBFE
+:1012A000FFFFFFDFF7FFF1F7BFFBFFFFFF7FDEFF71
+:1012B000FFFFFFFFFFEDF7FFFF7FD0F03FFFFFFFD6
+:1012C000FEF830000000004000000000E000008058
+:1012D0002001019200010100E01C6020300808009C
+:1012E000000000000000008000C1F06FFFFFFFFE63
+:1012F000FFFFFFFFFFDBFEFFFFDFFFFC7FFBBFFF0A
+:10130000FFFFFFFFF1F6FFF77E3FFF7FFFFFFFF7D5
+:10131000FFFFFFEDFFDFFFB7FFF03FFFFFFFFEFF27
+:10132000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFCD
+:10133000FFFFFFF1FFFFFFFFFFFFFFFFFFFFFFFFCB
+:10134000FFFFFFFFFFFFFFFFF0FFFFFFFFFEFFFFBD
+:10135000FFFFFFFFDFFFFFFFDFFFFFFFFFBFFFDF3D
+:1013600057EFF1FDFE7FFFFFFFFFFFFFFFDFFBFFFA
+:10137000FFFFFFFFFFFFFFF07FFFFFFFFEFFFFFF0D
+:10138000FFFFFF7FFFFFFFFFFFFFFFFFFBFFDFFF11
+:10139000FFF1FDFF7FBFFFFFFFFFFFFFFFFFFFFF2D
+:1013A000FFFEFFFFFFFFF09FFFFFFFFEF7FDFFFFC8
+:1013B000FFFFFFFFFFFFFFFFFFFFBFFFFFFFFFFF7D
+:1013C000F1FFFFFFFFFFFFFFFFFFFFFFFFFFFFFF3B
+:1013D000FFFFFFFFFFF06FFFFFFFFEFFFFFFFFFFBD
+:1013E000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF11B
+:1013F000FFFFFDFFFFFFFFFFFFFFFFFFFFFFFFFFFF
+:10140000FFFFFFFFF0CFFFFFFFFEFFFFFFFFFFFF2C
+:10141000FFFBFFFFFFFEFFFFFB6FFFFEBFFFF1FFC4
+:10142000F7FFFF7FFFFFFFFFFFFFFFFFFFFFFFFD56
+:10143000FFFFFFF0EFFFFFFFFEFFFFFFFFFFFFFFDC
+:10144000FBFFFFFFFEFFFFFF57FFFDBFFFF1FFEFB9
+:10145000FEFFBFFFFFFFFFFFFFFFFFFFFFFFFEFFDE
+:10146000DEFFF0CFFFFFFFFEFFFFFFF7DBFFDBFD3F
+:10147000F6FFF6FF3CBCBCBFDF6FE72FF13CBFFDC2
+:10148000BFDF6FFF6FF7DBFFDBFDF6FFF6FFFFFF50
+:101490000201DFFFFFFFFEFFFFFFFFFFFFFFFFFF78
+:1014A000FFFFFFFFFFFFFFFFFFFFFFFFFFFFFFFF4C
+:0614B000FFFFFFFFFFFF3C
+:00000001FF
+/*
+ *
+ * File yam111.mcs converted to h format by mcs2h
+ *
+ * (C) F6FBB 1998
+ *
+ * Tue Aug 25 20:23:03 1998
+ *
+ */
diff --git a/fs/Kconfig b/fs/Kconfig
index cef8b18ceaa3..86b203fc3c56 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -66,6 +66,13 @@ config GENERIC_ACL
 	bool
 	select FS_POSIX_ACL
 
+menu "Caches"
+
+source "fs/fscache/Kconfig"
+source "fs/cachefiles/Kconfig"
+
+endmenu
+
 if BLOCK
 menu "CD-ROM/DVD Filesystems"
 
@@ -169,6 +176,8 @@ source "fs/romfs/Kconfig"
 source "fs/sysv/Kconfig"
 source "fs/ufs/Kconfig"
 
+source "fs/exofs/Kconfig"
+
 endif # MISC_FILESYSTEMS
 
 menuconfig NETWORK_FILESYSTEMS
diff --git a/fs/Makefile b/fs/Makefile
index 6e82a307bcd4..70b2aed87133 100644
--- a/fs/Makefile
+++ b/fs/Makefile
@@ -11,7 +11,7 @@ obj-y :=	open.o read_write.o file_table.o super.o \
 		attr.o bad_inode.o file.o filesystems.o namespace.o \
 		seq_file.o xattr.o libfs.o fs-writeback.o \
 		pnode.o drop_caches.o splice.o sync.o utimes.o \
-		stack.o
+		stack.o fs_struct.o
 
 ifeq ($(CONFIG_BLOCK),y)
 obj-y +=	buffer.o bio.o block_dev.o direct-io.o mpage.o ioprio.o
@@ -63,6 +63,7 @@ obj-$(CONFIG_PROFILING)		+= dcookies.o
 obj-$(CONFIG_DLM)		+= dlm/
  
 # Do not add any filesystems before this line
+obj-$(CONFIG_FSCACHE)		+= fscache/
 obj-$(CONFIG_REISERFS_FS)	+= reiserfs/
 obj-$(CONFIG_EXT3_FS)		+= ext3/ # Before ext2 so root fs can be ext3
 obj-$(CONFIG_EXT2_FS)		+= ext2/
@@ -116,7 +117,9 @@ obj-$(CONFIG_AFS_FS)		+= afs/
 obj-$(CONFIG_BEFS_FS)		+= befs/
 obj-$(CONFIG_HOSTFS)		+= hostfs/
 obj-$(CONFIG_HPPFS)		+= hppfs/
+obj-$(CONFIG_CACHEFILES)	+= cachefiles/
 obj-$(CONFIG_DEBUG_FS)		+= debugfs/
 obj-$(CONFIG_OCFS2_FS)		+= ocfs2/
 obj-$(CONFIG_BTRFS_FS)		+= btrfs/
 obj-$(CONFIG_GFS2_FS)           += gfs2/
+obj-$(CONFIG_EXOFS_FS)          += exofs/
diff --git a/fs/adfs/super.c b/fs/adfs/super.c
index 7f83a46f2b7e..dd9becca4241 100644
--- a/fs/adfs/super.c
+++ b/fs/adfs/super.c
@@ -219,16 +219,20 @@ static int adfs_remount(struct super_block *sb, int *flags, char *data)
 
 static int adfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct adfs_sb_info *asb = ADFS_SB(dentry->d_sb);
+	struct super_block *sb = dentry->d_sb;
+	struct adfs_sb_info *sbi = ADFS_SB(sb);
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type    = ADFS_SUPER_MAGIC;
-	buf->f_namelen = asb->s_namelen;
-	buf->f_bsize   = dentry->d_sb->s_blocksize;
-	buf->f_blocks  = asb->s_size;
-	buf->f_files   = asb->s_ids_per_zone * asb->s_map_size;
+	buf->f_namelen = sbi->s_namelen;
+	buf->f_bsize   = sb->s_blocksize;
+	buf->f_blocks  = sbi->s_size;
+	buf->f_files   = sbi->s_ids_per_zone * sbi->s_map_size;
 	buf->f_bavail  =
-	buf->f_bfree   = adfs_map_free(dentry->d_sb);
+	buf->f_bfree   = adfs_map_free(sb);
 	buf->f_ffree   = (long)(buf->f_bfree * buf->f_files) / (long)buf->f_blocks;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 
 	return 0;
 }
diff --git a/fs/affs/super.c b/fs/affs/super.c
index a19d64b582aa..5ce695e707fe 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -533,6 +533,7 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
 	int		 free;
+	u64		 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	pr_debug("AFFS: statfs() partsize=%d, reserved=%d\n",AFFS_SB(sb)->s_partition_size,
 	     AFFS_SB(sb)->s_reserved);
@@ -543,6 +544,9 @@ affs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks  = AFFS_SB(sb)->s_partition_size - AFFS_SB(sb)->s_reserved;
 	buf->f_bfree   = free;
 	buf->f_bavail  = free;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
+	buf->f_namelen = 30;
 	return 0;
 }
 
diff --git a/fs/afs/Kconfig b/fs/afs/Kconfig
index e7b522fe15e1..5c4e61d3c772 100644
--- a/fs/afs/Kconfig
+++ b/fs/afs/Kconfig
@@ -19,3 +19,11 @@ config AFS_DEBUG
 	  See <file:Documentation/filesystems/afs.txt> for more information.
 
 	  If unsure, say N.
+
+config AFS_FSCACHE
+	bool "Provide AFS client caching support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on AFS_FS=m && FSCACHE || AFS_FS=y && FSCACHE=y
+	help
+	  Say Y here if you want AFS data to be cached locally on disk through
+	  the generic filesystem cache manager
diff --git a/fs/afs/Makefile b/fs/afs/Makefile
index a66671082cfb..4f64b95d57bd 100644
--- a/fs/afs/Makefile
+++ b/fs/afs/Makefile
@@ -2,7 +2,10 @@
 # Makefile for Red Hat Linux AFS client.
 #
 
+afs-cache-$(CONFIG_AFS_FSCACHE) := cache.o
+
 kafs-objs := \
+	$(afs-cache-y) \
 	callback.o \
 	cell.o \
 	cmservice.o \
diff --git a/fs/afs/cache.c b/fs/afs/cache.c
index de0d7de69edc..e2b1d3f16519 100644
--- a/fs/afs/cache.c
+++ b/fs/afs/cache.c
@@ -1,6 +1,6 @@
 /* AFS caching stuff
  *
- * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -9,248 +9,395 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_cell_cache_match(void *target,
-						const void *entry);
-static void afs_cell_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_cache_cell_index_def = {
-	.name			= "cell_ix",
-	.data_size		= sizeof(struct afs_cache_cell),
-	.keys[0]		= { CACHEFS_INDEX_KEYS_ASCIIZ, 64 },
-	.match			= afs_cell_cache_match,
-	.update			= afs_cell_cache_update,
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include "internal.h"
+
+static uint16_t afs_cell_cache_get_key(const void *cookie_netfs_data,
+				       void *buffer, uint16_t buflen);
+static uint16_t afs_cell_cache_get_aux(const void *cookie_netfs_data,
+				       void *buffer, uint16_t buflen);
+static enum fscache_checkaux afs_cell_cache_check_aux(void *cookie_netfs_data,
+						      const void *buffer,
+						      uint16_t buflen);
+
+static uint16_t afs_vlocation_cache_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t buflen);
+static uint16_t afs_vlocation_cache_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t buflen);
+static enum fscache_checkaux afs_vlocation_cache_check_aux(
+	void *cookie_netfs_data, const void *buffer, uint16_t buflen);
+
+static uint16_t afs_volume_cache_get_key(const void *cookie_netfs_data,
+					 void *buffer, uint16_t buflen);
+
+static uint16_t afs_vnode_cache_get_key(const void *cookie_netfs_data,
+					void *buffer, uint16_t buflen);
+static void afs_vnode_cache_get_attr(const void *cookie_netfs_data,
+				     uint64_t *size);
+static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data,
+					void *buffer, uint16_t buflen);
+static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
+						       const void *buffer,
+						       uint16_t buflen);
+static void afs_vnode_cache_now_uncached(void *cookie_netfs_data);
+
+struct fscache_netfs afs_cache_netfs = {
+	.name			= "afs",
+	.version		= 0,
+};
+
+struct fscache_cookie_def afs_cell_cache_index_def = {
+	.name		= "AFS.cell",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= afs_cell_cache_get_key,
+	.get_aux	= afs_cell_cache_get_aux,
+	.check_aux	= afs_cell_cache_check_aux,
+};
+
+struct fscache_cookie_def afs_vlocation_cache_index_def = {
+	.name			= "AFS.vldb",
+	.type			= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key		= afs_vlocation_cache_get_key,
+	.get_aux		= afs_vlocation_cache_get_aux,
+	.check_aux		= afs_vlocation_cache_check_aux,
+};
+
+struct fscache_cookie_def afs_volume_cache_index_def = {
+	.name		= "AFS.volume",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= afs_volume_cache_get_key,
+};
+
+struct fscache_cookie_def afs_vnode_cache_index_def = {
+	.name			= "AFS.vnode",
+	.type			= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key		= afs_vnode_cache_get_key,
+	.get_attr		= afs_vnode_cache_get_attr,
+	.get_aux		= afs_vnode_cache_get_aux,
+	.check_aux		= afs_vnode_cache_check_aux,
+	.now_uncached		= afs_vnode_cache_now_uncached,
 };
-#endif
 
 /*
- * match a cell record obtained from the cache
+ * set the key for the index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_cell_cache_match(void *target,
-						const void *entry)
+static uint16_t afs_cell_cache_get_key(const void *cookie_netfs_data,
+				       void *buffer, uint16_t bufmax)
 {
-	const struct afs_cache_cell *ccell = entry;
-	struct afs_cell *cell = target;
+	const struct afs_cell *cell = cookie_netfs_data;
+	uint16_t klen;
 
-	_enter("{%s},{%s}", ccell->name, cell->name);
+	_enter("%p,%p,%u", cell, buffer, bufmax);
 
-	if (strncmp(ccell->name, cell->name, sizeof(ccell->name)) == 0) {
-		_leave(" = SUCCESS");
-		return CACHEFS_MATCH_SUCCESS;
-	}
+	klen = strlen(cell->name);
+	if (klen > bufmax)
+		return 0;
 
-	_leave(" = FAILED");
-	return CACHEFS_MATCH_FAILED;
+	memcpy(buffer, cell->name, klen);
+	return klen;
 }
-#endif
 
 /*
- * update a cell record in the cache
+ * provide new auxilliary cache data
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_cell_cache_update(void *source, void *entry)
+static uint16_t afs_cell_cache_get_aux(const void *cookie_netfs_data,
+				       void *buffer, uint16_t bufmax)
 {
-	struct afs_cache_cell *ccell = entry;
-	struct afs_cell *cell = source;
+	const struct afs_cell *cell = cookie_netfs_data;
+	uint16_t dlen;
 
-	_enter("%p,%p", source, entry);
+	_enter("%p,%p,%u", cell, buffer, bufmax);
 
-	strncpy(ccell->name, cell->name, sizeof(ccell->name));
+	dlen = cell->vl_naddrs * sizeof(cell->vl_addrs[0]);
+	dlen = min(dlen, bufmax);
+	dlen &= ~(sizeof(cell->vl_addrs[0]) - 1);
 
-	memcpy(ccell->vl_servers,
-	       cell->vl_addrs,
-	       min(sizeof(ccell->vl_servers), sizeof(cell->vl_addrs)));
+	memcpy(buffer, cell->vl_addrs, dlen);
+	return dlen;
+}
 
+/*
+ * check that the auxilliary data indicates that the entry is still valid
+ */
+static enum fscache_checkaux afs_cell_cache_check_aux(void *cookie_netfs_data,
+						      const void *buffer,
+						      uint16_t buflen)
+{
+	_leave(" = OKAY");
+	return FSCACHE_CHECKAUX_OKAY;
 }
-#endif
-
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vlocation_cache_match(void *target,
-						     const void *entry);
-static void afs_vlocation_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_vlocation_cache_index_def = {
-	.name		= "vldb",
-	.data_size	= sizeof(struct afs_cache_vlocation),
-	.keys[0]	= { CACHEFS_INDEX_KEYS_ASCIIZ, 64 },
-	.match		= afs_vlocation_cache_match,
-	.update		= afs_vlocation_cache_update,
-};
-#endif
 
+/*****************************************************************************/
 /*
- * match a VLDB record stored in the cache
- * - may also load target from entry
+ * set the key for the index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vlocation_cache_match(void *target,
-						     const void *entry)
+static uint16_t afs_vlocation_cache_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
 {
-	const struct afs_cache_vlocation *vldb = entry;
-	struct afs_vlocation *vlocation = target;
+	const struct afs_vlocation *vlocation = cookie_netfs_data;
+	uint16_t klen;
+
+	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, bufmax);
+
+	klen = strnlen(vlocation->vldb.name, sizeof(vlocation->vldb.name));
+	if (klen > bufmax)
+		return 0;
 
-	_enter("{%s},{%s}", vlocation->vldb.name, vldb->name);
+	memcpy(buffer, vlocation->vldb.name, klen);
 
-	if (strncmp(vlocation->vldb.name, vldb->name, sizeof(vldb->name)) == 0
-	    ) {
-		if (!vlocation->valid ||
-		    vlocation->vldb.rtime == vldb->rtime
+	_leave(" = %u", klen);
+	return klen;
+}
+
+/*
+ * provide new auxilliary cache data
+ */
+static uint16_t afs_vlocation_cache_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct afs_vlocation *vlocation = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, bufmax);
+
+	dlen = sizeof(struct afs_cache_vlocation);
+	dlen -= offsetof(struct afs_cache_vlocation, nservers);
+	if (dlen > bufmax)
+		return 0;
+
+	memcpy(buffer, (uint8_t *)&vlocation->vldb.nservers, dlen);
+
+	_leave(" = %u", dlen);
+	return dlen;
+}
+
+/*
+ * check that the auxilliary data indicates that the entry is still valid
+ */
+static
+enum fscache_checkaux afs_vlocation_cache_check_aux(void *cookie_netfs_data,
+						    const void *buffer,
+						    uint16_t buflen)
+{
+	const struct afs_cache_vlocation *cvldb;
+	struct afs_vlocation *vlocation = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%s},%p,%u", vlocation->vldb.name, buffer, buflen);
+
+	/* check the size of the data is what we're expecting */
+	dlen = sizeof(struct afs_cache_vlocation);
+	dlen -= offsetof(struct afs_cache_vlocation, nservers);
+	if (dlen != buflen)
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	cvldb = container_of(buffer, struct afs_cache_vlocation, nservers);
+
+	/* if what's on disk is more valid than what's in memory, then use the
+	 * VL record from the cache */
+	if (!vlocation->valid || vlocation->vldb.rtime == cvldb->rtime) {
+		memcpy((uint8_t *)&vlocation->vldb.nservers, buffer, dlen);
+		vlocation->valid = 1;
+		_leave(" = SUCCESS [c->m]");
+		return FSCACHE_CHECKAUX_OKAY;
+	}
+
+	/* need to update the cache if the cached info differs */
+	if (memcmp(&vlocation->vldb, buffer, dlen) != 0) {
+		/* delete if the volume IDs for this name differ */
+		if (memcmp(&vlocation->vldb.vid, &cvldb->vid,
+			   sizeof(cvldb->vid)) != 0
 		    ) {
-			vlocation->vldb = *vldb;
-			vlocation->valid = 1;
-			_leave(" = SUCCESS [c->m]");
-			return CACHEFS_MATCH_SUCCESS;
-		} else if (memcmp(&vlocation->vldb, vldb, sizeof(*vldb)) != 0) {
-			/* delete if VIDs for this name differ */
-			if (memcmp(&vlocation->vldb.vid,
-				   &vldb->vid,
-				   sizeof(vldb->vid)) != 0) {
-				_leave(" = DELETE");
-				return CACHEFS_MATCH_SUCCESS_DELETE;
-			}
-
-			_leave(" = UPDATE");
-			return CACHEFS_MATCH_SUCCESS_UPDATE;
-		} else {
-			_leave(" = SUCCESS");
-			return CACHEFS_MATCH_SUCCESS;
+			_leave(" = OBSOLETE");
+			return FSCACHE_CHECKAUX_OBSOLETE;
 		}
+
+		_leave(" = UPDATE");
+		return FSCACHE_CHECKAUX_NEEDS_UPDATE;
 	}
 
-	_leave(" = FAILED");
-	return CACHEFS_MATCH_FAILED;
+	_leave(" = OKAY");
+	return FSCACHE_CHECKAUX_OKAY;
 }
-#endif
 
+/*****************************************************************************/
 /*
- * update a VLDB record stored in the cache
+ * set the key for the volume index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_vlocation_cache_update(void *source, void *entry)
+static uint16_t afs_volume_cache_get_key(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
 {
-	struct afs_cache_vlocation *vldb = entry;
-	struct afs_vlocation *vlocation = source;
+	const struct afs_volume *volume = cookie_netfs_data;
+	uint16_t klen;
+
+	_enter("{%u},%p,%u", volume->type, buffer, bufmax);
+
+	klen = sizeof(volume->type);
+	if (klen > bufmax)
+		return 0;
 
-	_enter("");
+	memcpy(buffer, &volume->type, sizeof(volume->type));
+
+	_leave(" = %u", klen);
+	return klen;
 
-	*vldb = vlocation->vldb;
 }
-#endif
-
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_volume_cache_match(void *target,
-						  const void *entry);
-static void afs_volume_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_volume_cache_index_def = {
-	.name		= "volume",
-	.data_size	= sizeof(struct afs_cache_vhash),
-	.keys[0]	= { CACHEFS_INDEX_KEYS_BIN, 1 },
-	.keys[1]	= { CACHEFS_INDEX_KEYS_BIN, 1 },
-	.match		= afs_volume_cache_match,
-	.update		= afs_volume_cache_update,
-};
-#endif
 
+/*****************************************************************************/
 /*
- * match a volume hash record stored in the cache
+ * set the key for the index entry
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_volume_cache_match(void *target,
-						  const void *entry)
+static uint16_t afs_vnode_cache_get_key(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
 {
-	const struct afs_cache_vhash *vhash = entry;
-	struct afs_volume *volume = target;
+	const struct afs_vnode *vnode = cookie_netfs_data;
+	uint16_t klen;
 
-	_enter("{%u},{%u}", volume->type, vhash->vtype);
+	_enter("{%x,%x,%llx},%p,%u",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
+	       buffer, bufmax);
 
-	if (volume->type == vhash->vtype) {
-		_leave(" = SUCCESS");
-		return CACHEFS_MATCH_SUCCESS;
-	}
+	klen = sizeof(vnode->fid.vnode);
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, &vnode->fid.vnode, sizeof(vnode->fid.vnode));
 
-	_leave(" = FAILED");
-	return CACHEFS_MATCH_FAILED;
+	_leave(" = %u", klen);
+	return klen;
 }
-#endif
 
 /*
- * update a volume hash record stored in the cache
+ * provide updated file attributes
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_volume_cache_update(void *source, void *entry)
+static void afs_vnode_cache_get_attr(const void *cookie_netfs_data,
+				     uint64_t *size)
 {
-	struct afs_cache_vhash *vhash = entry;
-	struct afs_volume *volume = source;
+	const struct afs_vnode *vnode = cookie_netfs_data;
 
-	_enter("");
+	_enter("{%x,%x,%llx},",
+	       vnode->fid.vnode, vnode->fid.unique,
+	       vnode->status.data_version);
 
-	vhash->vtype = volume->type;
+	*size = vnode->status.size;
 }
-#endif
-
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vnode_cache_match(void *target,
-						 const void *entry);
-static void afs_vnode_cache_update(void *source, void *entry);
-
-struct cachefs_index_def afs_vnode_cache_index_def = {
-	.name		= "vnode",
-	.data_size	= sizeof(struct afs_cache_vnode),
-	.keys[0]	= { CACHEFS_INDEX_KEYS_BIN, 4 },
-	.match		= afs_vnode_cache_match,
-	.update		= afs_vnode_cache_update,
-};
-#endif
 
 /*
- * match a vnode record stored in the cache
+ * provide new auxilliary cache data
+ */
+static uint16_t afs_vnode_cache_get_aux(const void *cookie_netfs_data,
+					void *buffer, uint16_t bufmax)
+{
+	const struct afs_vnode *vnode = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%x,%x,%Lx},%p,%u",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
+	       buffer, bufmax);
+
+	dlen = sizeof(vnode->fid.unique) + sizeof(vnode->status.data_version);
+	if (dlen > bufmax)
+		return 0;
+
+	memcpy(buffer, &vnode->fid.unique, sizeof(vnode->fid.unique));
+	buffer += sizeof(vnode->fid.unique);
+	memcpy(buffer, &vnode->status.data_version,
+	       sizeof(vnode->status.data_version));
+
+	_leave(" = %u", dlen);
+	return dlen;
+}
+
+/*
+ * check that the auxilliary data indicates that the entry is still valid
  */
-#ifdef AFS_CACHING_SUPPORT
-static cachefs_match_val_t afs_vnode_cache_match(void *target,
-						 const void *entry)
+static enum fscache_checkaux afs_vnode_cache_check_aux(void *cookie_netfs_data,
+						       const void *buffer,
+						       uint16_t buflen)
 {
-	const struct afs_cache_vnode *cvnode = entry;
-	struct afs_vnode *vnode = target;
-
-	_enter("{%x,%x,%Lx},{%x,%x,%Lx}",
-	       vnode->fid.vnode,
-	       vnode->fid.unique,
-	       vnode->status.version,
-	       cvnode->vnode_id,
-	       cvnode->vnode_unique,
-	       cvnode->data_version);
-
-	if (vnode->fid.vnode != cvnode->vnode_id) {
-		_leave(" = FAILED");
-		return CACHEFS_MATCH_FAILED;
+	struct afs_vnode *vnode = cookie_netfs_data;
+	uint16_t dlen;
+
+	_enter("{%x,%x,%llx},%p,%u",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version,
+	       buffer, buflen);
+
+	/* check the size of the data is what we're expecting */
+	dlen = sizeof(vnode->fid.unique) + sizeof(vnode->status.data_version);
+	if (dlen != buflen) {
+		_leave(" = OBSOLETE [len %hx != %hx]", dlen, buflen);
+		return FSCACHE_CHECKAUX_OBSOLETE;
 	}
 
-	if (vnode->fid.unique != cvnode->vnode_unique ||
-	    vnode->status.version != cvnode->data_version) {
-		_leave(" = DELETE");
-		return CACHEFS_MATCH_SUCCESS_DELETE;
+	if (memcmp(buffer,
+		   &vnode->fid.unique,
+		   sizeof(vnode->fid.unique)
+		   ) != 0) {
+		unsigned unique;
+
+		memcpy(&unique, buffer, sizeof(unique));
+
+		_leave(" = OBSOLETE [uniq %x != %x]",
+		       unique, vnode->fid.unique);
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	if (memcmp(buffer + sizeof(vnode->fid.unique),
+		   &vnode->status.data_version,
+		   sizeof(vnode->status.data_version)
+		   ) != 0) {
+		afs_dataversion_t version;
+
+		memcpy(&version, buffer + sizeof(vnode->fid.unique),
+		       sizeof(version));
+
+		_leave(" = OBSOLETE [vers %llx != %llx]",
+		       version, vnode->status.data_version);
+		return FSCACHE_CHECKAUX_OBSOLETE;
 	}
 
 	_leave(" = SUCCESS");
-	return CACHEFS_MATCH_SUCCESS;
+	return FSCACHE_CHECKAUX_OKAY;
 }
-#endif
 
 /*
- * update a vnode record stored in the cache
+ * indication the cookie is no longer uncached
+ * - this function is called when the backing store currently caching a cookie
+ *   is removed
+ * - the netfs should use this to clean up any markers indicating cached pages
+ * - this is mandatory for any object that may have data
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_vnode_cache_update(void *source, void *entry)
+static void afs_vnode_cache_now_uncached(void *cookie_netfs_data)
 {
-	struct afs_cache_vnode *cvnode = entry;
-	struct afs_vnode *vnode = source;
+	struct afs_vnode *vnode = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	_enter("{%x,%x,%Lx}",
+	       vnode->fid.vnode, vnode->fid.unique, vnode->status.data_version);
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	for (;;) {
+		/* grab a bunch of pages to clean */
+		nr_pages = pagevec_lookup(&pvec, vnode->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
 
-	_enter("");
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
 
-	cvnode->vnode_id	= vnode->fid.vnode;
-	cvnode->vnode_unique	= vnode->fid.unique;
-	cvnode->data_version	= vnode->status.version;
+	_leave("");
 }
-#endif
diff --git a/fs/afs/cache.h b/fs/afs/cache.h
index 36a3642cf90e..5c4f6b499e90 100644
--- a/fs/afs/cache.h
+++ b/fs/afs/cache.h
@@ -1,6 +1,6 @@
 /* AFS local cache management interface
  *
- * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -9,15 +9,4 @@
  * 2 of the License, or (at your option) any later version.
  */
 
-#ifndef AFS_CACHE_H
-#define AFS_CACHE_H
-
-#undef AFS_CACHING_SUPPORT
-
-#include <linux/mm.h>
-#ifdef AFS_CACHING_SUPPORT
-#include <linux/cachefs.h>
-#endif
-#include "types.h"
-
-#endif /* AFS_CACHE_H */
+#include <linux/fscache.h>
diff --git a/fs/afs/cell.c b/fs/afs/cell.c
index 5e1df14e16b1..e19c13f059ed 100644
--- a/fs/afs/cell.c
+++ b/fs/afs/cell.c
@@ -147,12 +147,11 @@ struct afs_cell *afs_cell_create(const char *name, char *vllist)
 	if (ret < 0)
 		goto error;
 
-#ifdef AFS_CACHING_SUPPORT
-	/* put it up for caching */
-	cachefs_acquire_cookie(afs_cache_netfs.primary_index,
-			       &afs_vlocation_cache_index_def,
-			       cell,
-			       &cell->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	/* put it up for caching (this never returns an error) */
+	cell->cache = fscache_acquire_cookie(afs_cache_netfs.primary_index,
+					     &afs_cell_cache_index_def,
+					     cell);
 #endif
 
 	/* add to the cell lists */
@@ -362,10 +361,9 @@ static void afs_cell_destroy(struct afs_cell *cell)
 	list_del_init(&cell->proc_link);
 	up_write(&afs_proc_cells_sem);
 
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(cell->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(cell->cache, 0);
 #endif
-
 	key_put(cell->anonymous_key);
 	kfree(cell);
 
diff --git a/fs/afs/file.c b/fs/afs/file.c
index a3901769a96c..7a1d942ef68d 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -23,6 +23,9 @@ static void afs_invalidatepage(struct page *page, unsigned long offset);
 static int afs_releasepage(struct page *page, gfp_t gfp_flags);
 static int afs_launder_page(struct page *page);
 
+static int afs_readpages(struct file *filp, struct address_space *mapping,
+			 struct list_head *pages, unsigned nr_pages);
+
 const struct file_operations afs_file_operations = {
 	.open		= afs_open,
 	.release	= afs_release,
@@ -46,6 +49,7 @@ const struct inode_operations afs_file_inode_operations = {
 
 const struct address_space_operations afs_fs_aops = {
 	.readpage	= afs_readpage,
+	.readpages	= afs_readpages,
 	.set_page_dirty	= afs_set_page_dirty,
 	.launder_page	= afs_launder_page,
 	.releasepage	= afs_releasepage,
@@ -101,37 +105,18 @@ int afs_release(struct inode *inode, struct file *file)
 /*
  * deal with notification that a page was read from the cache
  */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_readpage_read_complete(void *cookie_data,
-				       struct page *page,
-				       void *data,
-				       int error)
+static void afs_file_readpage_read_complete(struct page *page,
+					    void *data,
+					    int error)
 {
-	_enter("%p,%p,%p,%d", cookie_data, page, data, error);
+	_enter("%p,%p,%d", page, data, error);
 
-	if (error)
-		SetPageError(page);
-	else
+	/* if the read completes with an error, we just unlock the page and let
+	 * the VM reissue the readpage */
+	if (!error)
 		SetPageUptodate(page);
 	unlock_page(page);
-
 }
-#endif
-
-/*
- * deal with notification that a page was written to the cache
- */
-#ifdef AFS_CACHING_SUPPORT
-static void afs_readpage_write_complete(void *cookie_data,
-					struct page *page,
-					void *data,
-					int error)
-{
-	_enter("%p,%p,%p,%d", cookie_data, page, data, error);
-
-	unlock_page(page);
-}
-#endif
 
 /*
  * AFS read page from file, directory or symlink
@@ -161,9 +146,9 @@ static int afs_readpage(struct file *file, struct page *page)
 	if (test_bit(AFS_VNODE_DELETED, &vnode->flags))
 		goto error;
 
-#ifdef AFS_CACHING_SUPPORT
 	/* is it cached? */
-	ret = cachefs_read_or_alloc_page(vnode->cache,
+#ifdef CONFIG_AFS_FSCACHE
+	ret = fscache_read_or_alloc_page(vnode->cache,
 					 page,
 					 afs_file_readpage_read_complete,
 					 NULL,
@@ -171,20 +156,21 @@ static int afs_readpage(struct file *file, struct page *page)
 #else
 	ret = -ENOBUFS;
 #endif
-
 	switch (ret) {
-		/* read BIO submitted and wb-journal entry found */
-	case 1:
-		BUG(); // TODO - handle wb-journal match
-
 		/* read BIO submitted (page in cache) */
 	case 0:
 		break;
 
-		/* no page available in cache */
-	case -ENOBUFS:
+		/* page not yet cached */
 	case -ENODATA:
+		_debug("cache said ENODATA");
+		goto go_on;
+
+		/* page will not be cached */
+	case -ENOBUFS:
+		_debug("cache said ENOBUFS");
 	default:
+	go_on:
 		offset = page->index << PAGE_CACHE_SHIFT;
 		len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
 
@@ -198,27 +184,25 @@ static int afs_readpage(struct file *file, struct page *page)
 				set_bit(AFS_VNODE_DELETED, &vnode->flags);
 				ret = -ESTALE;
 			}
-#ifdef AFS_CACHING_SUPPORT
-			cachefs_uncache_page(vnode->cache, page);
+
+#ifdef CONFIG_AFS_FSCACHE
+			fscache_uncache_page(vnode->cache, page);
 #endif
+			BUG_ON(PageFsCache(page));
 			goto error;
 		}
 
 		SetPageUptodate(page);
 
-#ifdef AFS_CACHING_SUPPORT
-		if (cachefs_write_page(vnode->cache,
-				       page,
-				       afs_file_readpage_write_complete,
-				       NULL,
-				       GFP_KERNEL) != 0
-		    ) {
-			cachefs_uncache_page(vnode->cache, page);
-			unlock_page(page);
+		/* send the page to the cache */
+#ifdef CONFIG_AFS_FSCACHE
+		if (PageFsCache(page) &&
+		    fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
+			fscache_uncache_page(vnode->cache, page);
+			BUG_ON(PageFsCache(page));
 		}
-#else
-		unlock_page(page);
 #endif
+		unlock_page(page);
 	}
 
 	_leave(" = 0");
@@ -232,34 +216,59 @@ error:
 }
 
 /*
- * invalidate part or all of a page
+ * read a set of pages
  */
-static void afs_invalidatepage(struct page *page, unsigned long offset)
+static int afs_readpages(struct file *file, struct address_space *mapping,
+			 struct list_head *pages, unsigned nr_pages)
 {
-	int ret = 1;
+	struct afs_vnode *vnode;
+	int ret = 0;
 
-	_enter("{%lu},%lu", page->index, offset);
+	_enter(",{%lu},,%d", mapping->host->i_ino, nr_pages);
 
-	BUG_ON(!PageLocked(page));
+	vnode = AFS_FS_I(mapping->host);
+	if (vnode->flags & AFS_VNODE_DELETED) {
+		_leave(" = -ESTALE");
+		return -ESTALE;
+	}
 
-	if (PagePrivate(page)) {
-		/* We release buffers only if the entire page is being
-		 * invalidated.
-		 * The get_block cached value has been unconditionally
-		 * invalidated, so real IO is not possible anymore.
-		 */
-		if (offset == 0) {
-			BUG_ON(!PageLocked(page));
-
-			ret = 0;
-			if (!PageWriteback(page))
-				ret = page->mapping->a_ops->releasepage(page,
-									0);
-			/* possibly should BUG_ON(!ret); - neilb */
-		}
+	/* attempt to read as many of the pages as possible */
+#ifdef CONFIG_AFS_FSCACHE
+	ret = fscache_read_or_alloc_pages(vnode->cache,
+					  mapping,
+					  pages,
+					  &nr_pages,
+					  afs_file_readpage_read_complete,
+					  NULL,
+					  mapping_gfp_mask(mapping));
+#else
+	ret = -ENOBUFS;
+#endif
+
+	switch (ret) {
+		/* all pages are being read from the cache */
+	case 0:
+		BUG_ON(!list_empty(pages));
+		BUG_ON(nr_pages != 0);
+		_leave(" = 0 [reading all]");
+		return 0;
+
+		/* there were pages that couldn't be read from the cache */
+	case -ENODATA:
+	case -ENOBUFS:
+		break;
+
+		/* other error */
+	default:
+		_leave(" = %d", ret);
+		return ret;
 	}
 
-	_leave(" = %d", ret);
+	/* load the missing pages from the network */
+	ret = read_cache_pages(mapping, pages, (void *) afs_readpage, file);
+
+	_leave(" = %d [netting]", ret);
+	return ret;
 }
 
 /*
@@ -273,25 +282,82 @@ static int afs_launder_page(struct page *page)
 }
 
 /*
- * release a page and cleanup its private data
+ * invalidate part or all of a page
+ * - release a page and clean up its private data if offset is 0 (indicating
+ *   the entire page)
+ */
+static void afs_invalidatepage(struct page *page, unsigned long offset)
+{
+	struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
+
+	_enter("{%lu},%lu", page->index, offset);
+
+	BUG_ON(!PageLocked(page));
+
+	/* we clean up only if the entire page is being invalidated */
+	if (offset == 0) {
+#ifdef CONFIG_AFS_FSCACHE
+		if (PageFsCache(page)) {
+			struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
+			fscache_wait_on_page_write(vnode->cache, page);
+			fscache_uncache_page(vnode->cache, page);
+			ClearPageFsCache(page);
+		}
+#endif
+
+		if (PagePrivate(page)) {
+			if (wb && !PageWriteback(page)) {
+				set_page_private(page, 0);
+				afs_put_writeback(wb);
+			}
+
+			if (!page_private(page))
+				ClearPagePrivate(page);
+		}
+	}
+
+	_leave("");
+}
+
+/*
+ * release a page and clean up its private state if it's not busy
+ * - return true if the page can now be released, false if not
  */
 static int afs_releasepage(struct page *page, gfp_t gfp_flags)
 {
+	struct afs_writeback *wb = (struct afs_writeback *) page_private(page);
 	struct afs_vnode *vnode = AFS_FS_I(page->mapping->host);
-	struct afs_writeback *wb;
 
 	_enter("{{%x:%u}[%lu],%lx},%x",
 	       vnode->fid.vid, vnode->fid.vnode, page->index, page->flags,
 	       gfp_flags);
 
+	/* deny if page is being written to the cache and the caller hasn't
+	 * elected to wait */
+#ifdef CONFIG_AFS_FSCACHE
+	if (PageFsCache(page)) {
+		if (fscache_check_page_write(vnode->cache, page)) {
+			if (!(gfp_flags & __GFP_WAIT)) {
+				_leave(" = F [cache busy]");
+				return 0;
+			}
+			fscache_wait_on_page_write(vnode->cache, page);
+		}
+
+		fscache_uncache_page(vnode->cache, page);
+		ClearPageFsCache(page);
+	}
+#endif
+
 	if (PagePrivate(page)) {
-		wb = (struct afs_writeback *) page_private(page);
-		ASSERT(wb != NULL);
-		set_page_private(page, 0);
+		if (wb) {
+			set_page_private(page, 0);
+			afs_put_writeback(wb);
+		}
 		ClearPagePrivate(page);
-		afs_put_writeback(wb);
 	}
 
-	_leave(" = 0");
-	return 0;
+	/* indicate that the page can be released */
+	_leave(" = T");
+	return 1;
 }
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index bb47217f6a18..c048f0658751 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -61,6 +61,11 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 		return -EBADMSG;
 	}
 
+#ifdef CONFIG_AFS_FSCACHE
+	if (vnode->status.size != inode->i_size)
+		fscache_attr_changed(vnode->cache);
+#endif
+
 	inode->i_nlink		= vnode->status.nlink;
 	inode->i_uid		= vnode->status.owner;
 	inode->i_gid		= 0;
@@ -149,15 +154,6 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 		return inode;
 	}
 
-#ifdef AFS_CACHING_SUPPORT
-	/* set up caching before reading the status, as fetch-status reads the
-	 * first page of symlinks to see if they're really mntpts */
-	cachefs_acquire_cookie(vnode->volume->cache,
-			       NULL,
-			       vnode,
-			       &vnode->cache);
-#endif
-
 	if (!status) {
 		/* it's a remotely extant inode */
 		set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags);
@@ -183,6 +179,15 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 		}
 	}
 
+	/* set up caching before mapping the status, as map-status reads the
+	 * first page of symlinks to see if they're really mountpoints */
+	inode->i_size = vnode->status.size;
+#ifdef CONFIG_AFS_FSCACHE
+	vnode->cache = fscache_acquire_cookie(vnode->volume->cache,
+					      &afs_vnode_cache_index_def,
+					      vnode);
+#endif
+
 	ret = afs_inode_map_status(vnode, key);
 	if (ret < 0)
 		goto bad_inode;
@@ -196,6 +201,10 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 
 	/* failure */
 bad_inode:
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(vnode->cache, 0);
+	vnode->cache = NULL;
+#endif
 	iget_failed(inode);
 	_leave(" = %d [bad]", ret);
 	return ERR_PTR(ret);
@@ -340,8 +349,8 @@ void afs_clear_inode(struct inode *inode)
 	ASSERT(list_empty(&vnode->writebacks));
 	ASSERT(!vnode->cb_promised);
 
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(vnode->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(vnode->cache, 0);
 	vnode->cache = NULL;
 #endif
 
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 67f259d99cd6..106be66dafd2 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -21,6 +21,7 @@
 
 #include "afs.h"
 #include "afs_vl.h"
+#include "cache.h"
 
 #define AFS_CELL_MAX_ADDRS 15
 
@@ -193,8 +194,8 @@ struct afs_cell {
 	struct key		*anonymous_key;	/* anonymous user key for this cell */
 	struct list_head	proc_link;	/* /proc cell list link */
 	struct proc_dir_entry	*proc_dir;	/* /proc dir for this cell */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 
 	/* server record management */
@@ -249,8 +250,8 @@ struct afs_vlocation {
 	struct list_head	grave;		/* link in master graveyard list */
 	struct list_head	update;		/* link in master update list */
 	struct afs_cell		*cell;		/* cell to which volume belongs */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 	struct afs_cache_vlocation vldb;	/* volume information DB record */
 	struct afs_volume	*vols[3];	/* volume access record pointer (index by type) */
@@ -302,8 +303,8 @@ struct afs_volume {
 	atomic_t		usage;
 	struct afs_cell		*cell;		/* cell to which belongs (unrefd ptr) */
 	struct afs_vlocation	*vlocation;	/* volume location */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 	afs_volid_t		vid;		/* volume ID */
 	afs_voltype_t		type;		/* type of volume */
@@ -333,8 +334,8 @@ struct afs_vnode {
 	struct afs_server	*server;	/* server currently supplying this file */
 	struct afs_fid		fid;		/* the file identifier for this inode */
 	struct afs_file_status	status;		/* AFS status info for this file */
-#ifdef AFS_CACHING_SUPPORT
-	struct cachefs_cookie	*cache;		/* caching cookie */
+#ifdef CONFIG_AFS_FSCACHE
+	struct fscache_cookie	*cache;		/* caching cookie */
 #endif
 	struct afs_permits	*permits;	/* cache of permits so far obtained */
 	struct mutex		permits_lock;	/* lock for altering permits list */
@@ -428,6 +429,22 @@ struct afs_uuid {
 
 /*****************************************************************************/
 /*
+ * cache.c
+ */
+#ifdef CONFIG_AFS_FSCACHE
+extern struct fscache_netfs afs_cache_netfs;
+extern struct fscache_cookie_def afs_cell_cache_index_def;
+extern struct fscache_cookie_def afs_vlocation_cache_index_def;
+extern struct fscache_cookie_def afs_volume_cache_index_def;
+extern struct fscache_cookie_def afs_vnode_cache_index_def;
+#else
+#define afs_cell_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#define afs_vlocation_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#define afs_volume_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#define afs_vnode_cache_index_def	(*(struct fscache_cookie_def *) NULL)
+#endif
+
+/*
  * callback.c
  */
 extern void afs_init_callback_state(struct afs_server *);
@@ -446,9 +463,6 @@ extern void afs_callback_update_kill(void);
  */
 extern struct rw_semaphore afs_proc_cells_sem;
 extern struct list_head afs_proc_cells;
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_cache_cell_index_def;
-#endif
 
 #define afs_get_cell(C) do { atomic_inc(&(C)->usage); } while(0)
 extern int afs_cell_init(char *);
@@ -554,9 +568,6 @@ extern void afs_clear_inode(struct inode *);
  * main.c
  */
 extern struct afs_uuid afs_uuid;
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_netfs afs_cache_netfs;
-#endif
 
 /*
  * misc.c
@@ -637,10 +648,6 @@ extern int afs_get_MAC_address(u8 *, size_t);
 /*
  * vlclient.c
  */
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_vlocation_cache_index_def;
-#endif
-
 extern int afs_vl_get_entry_by_name(struct in_addr *, struct key *,
 				    const char *, struct afs_cache_vlocation *,
 				    const struct afs_wait_mode *);
@@ -664,12 +671,6 @@ extern void afs_vlocation_purge(void);
 /*
  * vnode.c
  */
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_vnode_cache_index_def;
-#endif
-
-extern struct afs_timer_ops afs_vnode_cb_timed_out_ops;
-
 static inline struct afs_vnode *AFS_FS_I(struct inode *inode)
 {
 	return container_of(inode, struct afs_vnode, vfs_inode);
@@ -711,10 +712,6 @@ extern int afs_vnode_release_lock(struct afs_vnode *, struct key *);
 /*
  * volume.c
  */
-#ifdef AFS_CACHING_SUPPORT
-extern struct cachefs_index_def afs_volume_cache_index_def;
-#endif
-
 #define afs_get_volume(V) do { atomic_inc(&(V)->usage); } while(0)
 
 extern void afs_put_volume(struct afs_volume *);
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 2d3e5d4fb9f7..66d54d348c55 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -1,6 +1,6 @@
 /* AFS client file system
  *
- * Copyright (C) 2002 Red Hat, Inc. All Rights Reserved.
+ * Copyright (C) 2002,5 Red Hat, Inc. All Rights Reserved.
  * Written by David Howells (dhowells@redhat.com)
  *
  * This program is free software; you can redistribute it and/or
@@ -29,18 +29,6 @@ static char *rootcell;
 module_param(rootcell, charp, 0);
 MODULE_PARM_DESC(rootcell, "root AFS cell name and VL server IP addr list");
 
-#ifdef AFS_CACHING_SUPPORT
-static struct cachefs_netfs_operations afs_cache_ops = {
-	.get_page_cookie	= afs_cache_get_page_cookie,
-};
-
-struct cachefs_netfs afs_cache_netfs = {
-	.name			= "afs",
-	.version		= 0,
-	.ops			= &afs_cache_ops,
-};
-#endif
-
 struct afs_uuid afs_uuid;
 
 /*
@@ -104,10 +92,9 @@ static int __init afs_init(void)
 	if (ret < 0)
 		return ret;
 
-#ifdef AFS_CACHING_SUPPORT
+#ifdef CONFIG_AFS_FSCACHE
 	/* we want to be able to cache */
-	ret = cachefs_register_netfs(&afs_cache_netfs,
-				     &afs_cache_cell_index_def);
+	ret = fscache_register_netfs(&afs_cache_netfs);
 	if (ret < 0)
 		goto error_cache;
 #endif
@@ -142,8 +129,8 @@ error_fs:
 error_open_socket:
 error_vl_update_init:
 error_cell_init:
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_unregister_netfs(&afs_cache_netfs);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_unregister_netfs(&afs_cache_netfs);
 error_cache:
 #endif
 	afs_callback_update_kill();
@@ -175,8 +162,8 @@ static void __exit afs_exit(void)
 	afs_vlocation_purge();
 	flush_scheduled_work();
 	afs_cell_purge();
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_unregister_netfs(&afs_cache_netfs);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_unregister_netfs(&afs_cache_netfs);
 #endif
 	afs_proc_cleanup();
 	rcu_barrier();
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 78db4953a800..2b9e2d03a390 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -173,9 +173,9 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 	if (PageError(page))
 		goto error;
 
-	buf = kmap(page);
+	buf = kmap_atomic(page, KM_USER0);
 	memcpy(devname, buf, size);
-	kunmap(page);
+	kunmap_atomic(buf, KM_USER0);
 	page_cache_release(page);
 	page = NULL;
 
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index 849fc3160cb5..ec2a7431e458 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -281,9 +281,8 @@ static void afs_vlocation_apply_update(struct afs_vlocation *vl,
 
 	vl->vldb = *vldb;
 
-#ifdef AFS_CACHING_SUPPORT
-	/* update volume entry in local cache */
-	cachefs_update_cookie(vl->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_update_cookie(vl->cache);
 #endif
 }
 
@@ -304,11 +303,9 @@ static int afs_vlocation_fill_in_record(struct afs_vlocation *vl,
 	memset(&vldb, 0, sizeof(vldb));
 
 	/* see if we have an in-cache copy (will set vl->valid if there is) */
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_acquire_cookie(cell->cache,
-			       &afs_volume_cache_index_def,
-			       vlocation,
-			       &vl->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	vl->cache = fscache_acquire_cookie(vl->cell->cache,
+					   &afs_vlocation_cache_index_def, vl);
 #endif
 
 	if (vl->valid) {
@@ -420,6 +417,11 @@ fill_in_record:
 	spin_unlock(&vl->lock);
 	wake_up(&vl->waitq);
 
+	/* update volume entry in local cache */
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_update_cookie(vl->cache);
+#endif
+
 	/* schedule for regular updates */
 	afs_vlocation_queue_for_updates(vl);
 	goto success;
@@ -465,7 +467,7 @@ found_in_memory:
 	spin_unlock(&vl->lock);
 
 success:
-	_leave(" = %p",vl);
+	_leave(" = %p", vl);
 	return vl;
 
 error_abandon:
@@ -523,10 +525,9 @@ static void afs_vlocation_destroy(struct afs_vlocation *vl)
 {
 	_enter("%p", vl);
 
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(vl->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(vl->cache, 0);
 #endif
-
 	afs_put_cell(vl->cell);
 	kfree(vl);
 }
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index 8bab0e3437f9..a353e69e2391 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -124,13 +124,11 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 	}
 
 	/* attach the cache and volume location */
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_acquire_cookie(vlocation->cache,
-			       &afs_vnode_cache_index_def,
-			       volume,
-			       &volume->cache);
+#ifdef CONFIG_AFS_FSCACHE
+	volume->cache = fscache_acquire_cookie(vlocation->cache,
+					       &afs_volume_cache_index_def,
+					       volume);
 #endif
-
 	afs_get_vlocation(vlocation);
 	volume->vlocation = vlocation;
 
@@ -194,8 +192,8 @@ void afs_put_volume(struct afs_volume *volume)
 	up_write(&vlocation->cell->vl_sem);
 
 	/* finish cleaning up the volume */
-#ifdef AFS_CACHING_SUPPORT
-	cachefs_relinquish_cookie(volume->cache, 0);
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_relinquish_cookie(volume->cache, 0);
 #endif
 	afs_put_vlocation(vlocation);
 
diff --git a/fs/afs/write.c b/fs/afs/write.c
index 3fb36d433621..c2e7a7ff0080 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -780,3 +780,24 @@ int afs_fsync(struct file *file, struct dentry *dentry, int datasync)
 	_leave(" = %d", ret);
 	return ret;
 }
+
+/*
+ * notification that a previously read-only page is about to become writable
+ * - if it returns an error, the caller will deliver a bus error signal
+ */
+int afs_page_mkwrite(struct vm_area_struct *vma, struct page *page)
+{
+	struct afs_vnode *vnode = AFS_FS_I(vma->vm_file->f_mapping->host);
+
+	_enter("{{%x:%u}},{%lx}",
+	       vnode->fid.vid, vnode->fid.vnode, page->index);
+
+	/* wait for the page to be written to the cache before we allow it to
+	 * be modified */
+#ifdef CONFIG_AFS_FSCACHE
+	fscache_wait_on_page_write(vnode->cache, page);
+#endif
+
+	_leave(" = 0");
+	return 0;
+}
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index d06cb023ad02..76afd0d6b86c 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -900,6 +900,7 @@ static int
 befs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	befs_debug(sb, "---> befs_statfs()");
 
@@ -910,6 +911,8 @@ befs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0;	/* UNKNOWN */
 	buf->f_ffree = 0;	/* UNKNOWN */
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = BEFS_NAME_LEN;
 
 	befs_debug(sb, "<--- befs_statfs()");
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 33b7235f853b..40381df34869 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -12,8 +12,6 @@
 #include <linux/module.h>
 #include <linux/kernel.h>
 #include <linux/fs.h>
-#include <linux/stat.h>
-#include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/errno.h>
@@ -21,20 +19,15 @@
 #include <linux/binfmts.h>
 #include <linux/string.h>
 #include <linux/file.h>
-#include <linux/fcntl.h>
-#include <linux/ptrace.h>
 #include <linux/slab.h>
-#include <linux/shm.h>
 #include <linux/personality.h>
 #include <linux/elfcore.h>
 #include <linux/init.h>
 #include <linux/highuid.h>
-#include <linux/smp.h>
 #include <linux/compiler.h>
 #include <linux/highmem.h>
 #include <linux/pagemap.h>
 #include <linux/security.h>
-#include <linux/syscalls.h>
 #include <linux/random.h>
 #include <linux/elf.h>
 #include <linux/utsname.h>
@@ -576,7 +569,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 	unsigned long error;
 	struct elf_phdr *elf_ppnt, *elf_phdata;
 	unsigned long elf_bss, elf_brk;
-	int elf_exec_fileno;
 	int retval, i;
 	unsigned int size;
 	unsigned long elf_entry;
@@ -631,12 +623,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 		goto out_free_ph;
 	}
 
-	retval = get_unused_fd();
-	if (retval < 0)
-		goto out_free_ph;
-	get_file(bprm->file);
-	fd_install(elf_exec_fileno = retval, bprm->file);
-
 	elf_ppnt = elf_phdata;
 	elf_bss = 0;
 	elf_brk = 0;
@@ -655,13 +641,13 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 			retval = -ENOEXEC;
 			if (elf_ppnt->p_filesz > PATH_MAX || 
 			    elf_ppnt->p_filesz < 2)
-				goto out_free_file;
+				goto out_free_ph;
 
 			retval = -ENOMEM;
 			elf_interpreter = kmalloc(elf_ppnt->p_filesz,
 						  GFP_KERNEL);
 			if (!elf_interpreter)
-				goto out_free_file;
+				goto out_free_ph;
 
 			retval = kernel_read(bprm->file, elf_ppnt->p_offset,
 					     elf_interpreter,
@@ -956,8 +942,6 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs)
 
 	kfree(elf_phdata);
 
-	sys_close(elf_exec_fileno);
-
 	set_binfmt(&elf_format);
 
 #ifdef ARCH_HAS_SETUP_ADDITIONAL_PAGES
@@ -1028,8 +1012,6 @@ out_free_dentry:
 		fput(interpreter);
 out_free_interp:
 	kfree(elf_interpreter);
-out_free_file:
-	sys_close(elf_exec_fileno);
 out_free_ph:
 	kfree(elf_phdata);
 	goto out;
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index f3e72c5c19f5..70cfc4b84ae0 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -972,9 +972,12 @@ static int elf_fdpic_map_file_constdisp_on_uclinux(
 			params->elfhdr_addr = seg->addr;
 
 		/* clear any space allocated but not loaded */
-		if (phdr->p_filesz < phdr->p_memsz)
-			clear_user((void *) (seg->addr + phdr->p_filesz),
-				   phdr->p_memsz - phdr->p_filesz);
+		if (phdr->p_filesz < phdr->p_memsz) {
+			ret = clear_user((void *) (seg->addr + phdr->p_filesz),
+					 phdr->p_memsz - phdr->p_filesz);
+			if (ret)
+				return ret;
+		}
 
 		if (mm) {
 			if (phdr->p_flags & PF_X) {
@@ -1014,7 +1017,7 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 	struct elf32_fdpic_loadseg *seg;
 	struct elf32_phdr *phdr;
 	unsigned long load_addr, delta_vaddr;
-	int loop, dvset;
+	int loop, dvset, ret;
 
 	load_addr = params->load_addr;
 	delta_vaddr = 0;
@@ -1114,7 +1117,9 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 		 * PT_LOAD */
 		if (prot & PROT_WRITE && disp > 0) {
 			kdebug("clear[%d] ad=%lx sz=%lx", loop, maddr, disp);
-			clear_user((void __user *) maddr, disp);
+			ret = clear_user((void __user *) maddr, disp);
+			if (ret)
+				return ret;
 			maddr += disp;
 		}
 
@@ -1149,15 +1154,19 @@ static int elf_fdpic_map_file_by_direct_mmap(struct elf_fdpic_params *params,
 		if (prot & PROT_WRITE && excess1 > 0) {
 			kdebug("clear[%d] ad=%lx sz=%lx",
 			       loop, maddr + phdr->p_filesz, excess1);
-			clear_user((void __user *) maddr + phdr->p_filesz,
-				   excess1);
+			ret = clear_user((void __user *) maddr + phdr->p_filesz,
+					 excess1);
+			if (ret)
+				return ret;
 		}
 
 #else
 		if (excess > 0) {
 			kdebug("clear[%d] ad=%lx sz=%lx",
 			       loop, maddr + phdr->p_filesz, excess);
-			clear_user((void *) maddr + phdr->p_filesz, excess);
+			ret = clear_user((void *) maddr + phdr->p_filesz, excess);
+			if (ret)
+				return ret;
 		}
 #endif
 
diff --git a/fs/binfmt_som.c b/fs/binfmt_som.c
index 08644a61616e..eff74b9c9e77 100644
--- a/fs/binfmt_som.c
+++ b/fs/binfmt_som.c
@@ -188,7 +188,6 @@ out:
 static int
 load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 {
-	int som_exec_fileno;
 	int retval;
 	unsigned int size;
 	unsigned long som_entry;
@@ -220,12 +219,6 @@ load_som_binary(struct linux_binprm * bprm, struct pt_regs * regs)
 		goto out_free;
 	}
 
-	retval = get_unused_fd();
-	if (retval < 0)
-		goto out_free;
-	get_file(bprm->file);
-	fd_install(som_exec_fileno = retval, bprm->file);
-
 	/* Flush all traces of the currently running executable */
 	retval = flush_old_exec(bprm);
 	if (retval)
diff --git a/fs/bio.c b/fs/bio.c
index a040cde7f6fd..e0c9e545bbfa 100644
--- a/fs/bio.c
+++ b/fs/bio.c
@@ -1420,8 +1420,7 @@ static void bio_pair_end_2(struct bio *bi, int err)
 }
 
 /*
- * split a bio - only worry about a bio with a single page
- * in it's iovec
+ * split a bio - only worry about a bio with a single page in its iovec
  */
 struct bio_pair *bio_split(struct bio *bi, int first_sectors)
 {
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 8c3c6899ccf3..f45dbc18dd17 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -204,6 +204,7 @@ int fsync_bdev(struct block_device *bdev)
 	}
 	return sync_blockdev(bdev);
 }
+EXPORT_SYMBOL(fsync_bdev);
 
 /**
  * freeze_bdev  --  lock a filesystem and force it into a consistent state
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 1d53b62dbba5..7fdd184a528d 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -256,7 +256,7 @@ int btrfs_init_acl(struct inode *inode, struct inode *dir)
 		}
 
 		if (!acl)
-			inode->i_mode &= ~current->fs->umask;
+			inode->i_mode &= ~current_umask();
 	}
 
 	if (IS_POSIXACL(dir) && acl) {
diff --git a/fs/btrfs/async-thread.c b/fs/btrfs/async-thread.c
index c84ca1f5259a..51bfdfc8fcda 100644
--- a/fs/btrfs/async-thread.c
+++ b/fs/btrfs/async-thread.c
@@ -20,7 +20,6 @@
 #include <linux/list.h>
 #include <linux/spinlock.h>
 #include <linux/freezer.h>
-#include <linux/ftrace.h>
 #include "async-thread.h"
 
 #define WORK_QUEUED_BIT 0
@@ -195,6 +194,9 @@ again_locked:
 				if (!list_empty(&worker->pending))
 					continue;
 
+				if (kthread_should_stop())
+					break;
+
 				/* still no more work?, sleep for real */
 				spin_lock_irq(&worker->lock);
 				set_current_state(TASK_INTERRUPTIBLE);
@@ -208,7 +210,8 @@ again_locked:
 				worker->working = 0;
 				spin_unlock_irq(&worker->lock);
 
-				schedule();
+				if (!kthread_should_stop())
+					schedule();
 			}
 			__set_current_state(TASK_RUNNING);
 		}
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index dbb724124633..e5b2533b691a 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -1244,9 +1244,9 @@ static noinline int push_nodes_for_insert(struct btrfs_trans_handle *trans,
  * readahead one full node of leaves, finding things that are close
  * to the block in 'slot', and triggering ra on them.
  */
-static noinline void reada_for_search(struct btrfs_root *root,
-				      struct btrfs_path *path,
-				      int level, int slot, u64 objectid)
+static void reada_for_search(struct btrfs_root *root,
+			     struct btrfs_path *path,
+			     int level, int slot, u64 objectid)
 {
 	struct extent_buffer *node;
 	struct btrfs_disk_key disk_key;
@@ -1447,6 +1447,117 @@ noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
 }
 
 /*
+ * helper function for btrfs_search_slot.  The goal is to find a block
+ * in cache without setting the path to blocking.  If we find the block
+ * we return zero and the path is unchanged.
+ *
+ * If we can't find the block, we set the path blocking and do some
+ * reada.  -EAGAIN is returned and the search must be repeated.
+ */
+static int
+read_block_for_search(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, struct btrfs_path *p,
+		       struct extent_buffer **eb_ret, int level, int slot,
+		       struct btrfs_key *key)
+{
+	u64 blocknr;
+	u64 gen;
+	u32 blocksize;
+	struct extent_buffer *b = *eb_ret;
+	struct extent_buffer *tmp;
+
+	blocknr = btrfs_node_blockptr(b, slot);
+	gen = btrfs_node_ptr_generation(b, slot);
+	blocksize = btrfs_level_size(root, level - 1);
+
+	tmp = btrfs_find_tree_block(root, blocknr, blocksize);
+	if (tmp && btrfs_buffer_uptodate(tmp, gen)) {
+		*eb_ret = tmp;
+		return 0;
+	}
+
+	/*
+	 * reduce lock contention at high levels
+	 * of the btree by dropping locks before
+	 * we read.
+	 */
+	btrfs_release_path(NULL, p);
+	if (tmp)
+		free_extent_buffer(tmp);
+	if (p->reada)
+		reada_for_search(root, p, level, slot, key->objectid);
+
+	tmp = read_tree_block(root, blocknr, blocksize, gen);
+	if (tmp)
+		free_extent_buffer(tmp);
+	return -EAGAIN;
+}
+
+/*
+ * helper function for btrfs_search_slot.  This does all of the checks
+ * for node-level blocks and does any balancing required based on
+ * the ins_len.
+ *
+ * If no extra work was required, zero is returned.  If we had to
+ * drop the path, -EAGAIN is returned and btrfs_search_slot must
+ * start over
+ */
+static int
+setup_nodes_for_search(struct btrfs_trans_handle *trans,
+		       struct btrfs_root *root, struct btrfs_path *p,
+		       struct extent_buffer *b, int level, int ins_len)
+{
+	int ret;
+	if ((p->search_for_split || ins_len > 0) && btrfs_header_nritems(b) >=
+	    BTRFS_NODEPTRS_PER_BLOCK(root) - 3) {
+		int sret;
+
+		sret = reada_for_balance(root, p, level);
+		if (sret)
+			goto again;
+
+		btrfs_set_path_blocking(p);
+		sret = split_node(trans, root, p, level);
+		btrfs_clear_path_blocking(p, NULL);
+
+		BUG_ON(sret > 0);
+		if (sret) {
+			ret = sret;
+			goto done;
+		}
+		b = p->nodes[level];
+	} else if (ins_len < 0 && btrfs_header_nritems(b) <
+		   BTRFS_NODEPTRS_PER_BLOCK(root) / 4) {
+		int sret;
+
+		sret = reada_for_balance(root, p, level);
+		if (sret)
+			goto again;
+
+		btrfs_set_path_blocking(p);
+		sret = balance_level(trans, root, p, level);
+		btrfs_clear_path_blocking(p, NULL);
+
+		if (sret) {
+			ret = sret;
+			goto done;
+		}
+		b = p->nodes[level];
+		if (!b) {
+			btrfs_release_path(NULL, p);
+			goto again;
+		}
+		BUG_ON(btrfs_header_nritems(b) == 1);
+	}
+	return 0;
+
+again:
+	ret = -EAGAIN;
+done:
+	return ret;
+}
+
+/*
  * look for key in the tree.  path is filled in with nodes along the way
  * if key is found, we return zero and you can find the item in the leaf
  * level of the path (level 0)
@@ -1464,16 +1575,11 @@ int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
 		      ins_len, int cow)
 {
 	struct extent_buffer *b;
-	struct extent_buffer *tmp;
 	int slot;
 	int ret;
 	int level;
-	int should_reada = p->reada;
 	int lowest_unlock = 1;
-	int blocksize;
 	u8 lowest_level = 0;
-	u64 blocknr;
-	u64 gen;
 
 	lowest_level = p->lowest_level;
 	WARN_ON(lowest_level && ins_len > 0);
@@ -1502,7 +1608,11 @@ again:
 		if (cow) {
 			int wret;
 
-			/* is a cow on this block not required */
+			/*
+			 * if we don't really need to cow this block
+			 * then we don't want to set the path blocking,
+			 * so we test it here
+			 */
 			if (btrfs_header_generation(b) == trans->transid &&
 			    btrfs_header_owner(b) == root->root_key.objectid &&
 			    !btrfs_header_flag(b, BTRFS_HEADER_FLAG_WRITTEN)) {
@@ -1557,51 +1667,15 @@ cow_done:
 			if (ret && slot > 0)
 				slot -= 1;
 			p->slots[level] = slot;
-			if ((p->search_for_split || ins_len > 0) &&
-			    btrfs_header_nritems(b) >=
-			    BTRFS_NODEPTRS_PER_BLOCK(root) - 3) {
-				int sret;
-
-				sret = reada_for_balance(root, p, level);
-				if (sret)
-					goto again;
-
-				btrfs_set_path_blocking(p);
-				sret = split_node(trans, root, p, level);
-				btrfs_clear_path_blocking(p, NULL);
-
-				BUG_ON(sret > 0);
-				if (sret) {
-					ret = sret;
-					goto done;
-				}
-				b = p->nodes[level];
-				slot = p->slots[level];
-			} else if (ins_len < 0 &&
-				   btrfs_header_nritems(b) <
-				   BTRFS_NODEPTRS_PER_BLOCK(root) / 4) {
-				int sret;
-
-				sret = reada_for_balance(root, p, level);
-				if (sret)
-					goto again;
-
-				btrfs_set_path_blocking(p);
-				sret = balance_level(trans, root, p, level);
-				btrfs_clear_path_blocking(p, NULL);
+			ret = setup_nodes_for_search(trans, root, p, b, level,
+						     ins_len);
+			if (ret == -EAGAIN)
+				goto again;
+			else if (ret)
+				goto done;
+			b = p->nodes[level];
+			slot = p->slots[level];
 
-				if (sret) {
-					ret = sret;
-					goto done;
-				}
-				b = p->nodes[level];
-				if (!b) {
-					btrfs_release_path(NULL, p);
-					goto again;
-				}
-				slot = p->slots[level];
-				BUG_ON(btrfs_header_nritems(b) == 1);
-			}
 			unlock_up(p, level, lowest_unlock);
 
 			/* this is only true while dropping a snapshot */
@@ -1610,44 +1684,11 @@ cow_done:
 				goto done;
 			}
 
-			blocknr = btrfs_node_blockptr(b, slot);
-			gen = btrfs_node_ptr_generation(b, slot);
-			blocksize = btrfs_level_size(root, level - 1);
+			ret = read_block_for_search(trans, root, p,
+						    &b, level, slot, key);
+			if (ret == -EAGAIN)
+				goto again;
 
-			tmp = btrfs_find_tree_block(root, blocknr, blocksize);
-			if (tmp && btrfs_buffer_uptodate(tmp, gen)) {
-				b = tmp;
-			} else {
-				/*
-				 * reduce lock contention at high levels
-				 * of the btree by dropping locks before
-				 * we read.
-				 */
-				if (level > 0) {
-					btrfs_release_path(NULL, p);
-					if (tmp)
-						free_extent_buffer(tmp);
-					if (should_reada)
-						reada_for_search(root, p,
-								 level, slot,
-								 key->objectid);
-
-					tmp = read_tree_block(root, blocknr,
-							 blocksize, gen);
-					if (tmp)
-						free_extent_buffer(tmp);
-					goto again;
-				} else {
-					btrfs_set_path_blocking(p);
-					if (tmp)
-						free_extent_buffer(tmp);
-					if (should_reada)
-						reada_for_search(root, p,
-								 level, slot,
-								 key->objectid);
-					b = read_node_slot(root, b, slot);
-				}
-			}
 			if (!p->skip_locking) {
 				int lret;
 
@@ -2116,8 +2157,7 @@ static int insert_ptr(struct btrfs_trans_handle *trans, struct btrfs_root
 	BUG_ON(!path->nodes[level]);
 	lower = path->nodes[level];
 	nritems = btrfs_header_nritems(lower);
-	if (slot > nritems)
-		BUG();
+	BUG_ON(slot > nritems);
 	if (nritems == BTRFS_NODEPTRS_PER_BLOCK(root))
 		BUG();
 	if (slot != nritems) {
@@ -4086,28 +4126,44 @@ next:
 int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 {
 	int slot;
-	int level = 1;
+	int level;
 	struct extent_buffer *c;
-	struct extent_buffer *next = NULL;
+	struct extent_buffer *next;
 	struct btrfs_key key;
 	u32 nritems;
 	int ret;
+	int old_spinning = path->leave_spinning;
+	int force_blocking = 0;
 
 	nritems = btrfs_header_nritems(path->nodes[0]);
 	if (nritems == 0)
 		return 1;
 
-	btrfs_item_key_to_cpu(path->nodes[0], &key, nritems - 1);
+	/*
+	 * we take the blocks in an order that upsets lockdep.  Using
+	 * blocking mode is the only way around it.
+	 */
+#ifdef CONFIG_DEBUG_LOCK_ALLOC
+	force_blocking = 1;
+#endif
 
+	btrfs_item_key_to_cpu(path->nodes[0], &key, nritems - 1);
+again:
+	level = 1;
+	next = NULL;
 	btrfs_release_path(root, path);
+
 	path->keep_locks = 1;
+
+	if (!force_blocking)
+		path->leave_spinning = 1;
+
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	path->keep_locks = 0;
 
 	if (ret < 0)
 		return ret;
 
-	btrfs_set_path_blocking(path);
 	nritems = btrfs_header_nritems(path->nodes[0]);
 	/*
 	 * by releasing the path above we dropped all our locks.  A balance
@@ -4117,19 +4173,24 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 	 */
 	if (nritems > 0 && path->slots[0] < nritems - 1) {
 		path->slots[0]++;
+		ret = 0;
 		goto done;
 	}
 
 	while (level < BTRFS_MAX_LEVEL) {
-		if (!path->nodes[level])
-			return 1;
+		if (!path->nodes[level]) {
+			ret = 1;
+			goto done;
+		}
 
 		slot = path->slots[level] + 1;
 		c = path->nodes[level];
 		if (slot >= btrfs_header_nritems(c)) {
 			level++;
-			if (level == BTRFS_MAX_LEVEL)
-				return 1;
+			if (level == BTRFS_MAX_LEVEL) {
+				ret = 1;
+				goto done;
+			}
 			continue;
 		}
 
@@ -4138,16 +4199,22 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 			free_extent_buffer(next);
 		}
 
-		/* the path was set to blocking above */
-		if (level == 1 && (path->locks[1] || path->skip_locking) &&
-		    path->reada)
-			reada_for_search(root, path, level, slot, 0);
+		next = c;
+		ret = read_block_for_search(NULL, root, path, &next, level,
+					    slot, &key);
+		if (ret == -EAGAIN)
+			goto again;
 
-		next = read_node_slot(root, c, slot);
 		if (!path->skip_locking) {
-			btrfs_assert_tree_locked(c);
-			btrfs_tree_lock(next);
-			btrfs_set_lock_blocking(next);
+			ret = btrfs_try_spin_lock(next);
+			if (!ret) {
+				btrfs_set_path_blocking(path);
+				btrfs_tree_lock(next);
+				if (!force_blocking)
+					btrfs_clear_path_blocking(path, next);
+			}
+			if (force_blocking)
+				btrfs_set_lock_blocking(next);
 		}
 		break;
 	}
@@ -4157,27 +4224,42 @@ int btrfs_next_leaf(struct btrfs_root *root, struct btrfs_path *path)
 		c = path->nodes[level];
 		if (path->locks[level])
 			btrfs_tree_unlock(c);
+
 		free_extent_buffer(c);
 		path->nodes[level] = next;
 		path->slots[level] = 0;
 		if (!path->skip_locking)
 			path->locks[level] = 1;
+
 		if (!level)
 			break;
 
-		btrfs_set_path_blocking(path);
-		if (level == 1 && path->locks[1] && path->reada)
-			reada_for_search(root, path, level, slot, 0);
-		next = read_node_slot(root, next, 0);
+		ret = read_block_for_search(NULL, root, path, &next, level,
+					    0, &key);
+		if (ret == -EAGAIN)
+			goto again;
+
 		if (!path->skip_locking) {
 			btrfs_assert_tree_locked(path->nodes[level]);
-			btrfs_tree_lock(next);
-			btrfs_set_lock_blocking(next);
+			ret = btrfs_try_spin_lock(next);
+			if (!ret) {
+				btrfs_set_path_blocking(path);
+				btrfs_tree_lock(next);
+				if (!force_blocking)
+					btrfs_clear_path_blocking(path, next);
+			}
+			if (force_blocking)
+				btrfs_set_lock_blocking(next);
 		}
 	}
+	ret = 0;
 done:
 	unlock_up(path, 0, 1);
-	return 0;
+	path->leave_spinning = old_spinning;
+	if (!old_spinning)
+		btrfs_set_path_blocking(path);
+
+	return ret;
 }
 
 /*
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 9417713542a2..ad96495dedc5 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -143,12 +143,15 @@ static int btrfs_csum_sizes[] = { 4, 0 };
 #define BTRFS_FT_MAX		9
 
 /*
- * the key defines the order in the tree, and so it also defines (optimal)
- * block layout.  objectid corresonds to the inode number.  The flags
- * tells us things about the object, and is a kind of stream selector.
- * so for a given inode, keys with flags of 1 might refer to the inode
- * data, flags of 2 may point to file data in the btree and flags == 3
- * may point to extents.
+ * The key defines the order in the tree, and so it also defines (optimal)
+ * block layout.
+ *
+ * objectid corresponds to the inode number.
+ *
+ * type tells us things about the object, and is a kind of stream selector.
+ * so for a given inode, keys with type of 1 might refer to the inode data,
+ * type of 2 may point to file data in the btree and type == 3 may point to
+ * extents.
  *
  * offset is the starting byte offset for this key in the stream.
  *
@@ -200,7 +203,7 @@ struct btrfs_dev_item {
 
 	/*
 	 * starting byte of this partition on the device,
-	 * to allowr for stripe alignment in the future
+	 * to allow for stripe alignment in the future
 	 */
 	__le64 start_offset;
 
@@ -633,18 +636,35 @@ struct btrfs_space_info {
 	struct rw_semaphore groups_sem;
 };
 
-struct btrfs_free_space {
-	struct rb_node bytes_index;
-	struct rb_node offset_index;
-	u64 offset;
-	u64 bytes;
+/*
+ * free clusters are used to claim free space in relatively large chunks,
+ * allowing us to do less seeky writes.  They are used for all metadata
+ * allocations and data allocations in ssd mode.
+ */
+struct btrfs_free_cluster {
+	spinlock_t lock;
+	spinlock_t refill_lock;
+	struct rb_root root;
+
+	/* largest extent in this cluster */
+	u64 max_size;
+
+	/* first extent starting offset */
+	u64 window_start;
+
+	struct btrfs_block_group_cache *block_group;
+	/*
+	 * when a cluster is allocated from a block group, we put the
+	 * cluster onto a list in the block group so that it can
+	 * be freed before the block group is freed.
+	 */
+	struct list_head block_group_list;
 };
 
 struct btrfs_block_group_cache {
 	struct btrfs_key key;
 	struct btrfs_block_group_item item;
 	spinlock_t lock;
-	struct mutex alloc_mutex;
 	struct mutex cache_mutex;
 	u64 pinned;
 	u64 reserved;
@@ -656,6 +676,7 @@ struct btrfs_block_group_cache {
 	struct btrfs_space_info *space_info;
 
 	/* free space cache stuff */
+	spinlock_t tree_lock;
 	struct rb_root free_space_bytes;
 	struct rb_root free_space_offset;
 
@@ -667,6 +688,11 @@ struct btrfs_block_group_cache {
 
 	/* usage count */
 	atomic_t count;
+
+	/* List of struct btrfs_free_clusters for this block group.
+	 * Today it will only have one thing on it, but that may change
+	 */
+	struct list_head cluster_list;
 };
 
 struct btrfs_leaf_ref_tree {
@@ -728,7 +754,6 @@ struct btrfs_fs_info {
 	struct mutex tree_log_mutex;
 	struct mutex transaction_kthread_mutex;
 	struct mutex cleaner_mutex;
-	struct mutex pinned_mutex;
 	struct mutex chunk_mutex;
 	struct mutex drop_mutex;
 	struct mutex volume_mutex;
@@ -839,8 +864,12 @@ struct btrfs_fs_info {
 	spinlock_t delalloc_lock;
 	spinlock_t new_trans_lock;
 	u64 delalloc_bytes;
-	u64 last_alloc;
-	u64 last_data_alloc;
+
+	/* data_alloc_cluster is only used in ssd mode */
+	struct btrfs_free_cluster data_alloc_cluster;
+
+	/* all metadata allocations go through this cluster */
+	struct btrfs_free_cluster meta_alloc_cluster;
 
 	spinlock_t ref_cache_lock;
 	u64 total_ref_cache_size;
@@ -932,7 +961,6 @@ struct btrfs_root {
 };
 
 /*
-
  * inode items have the data typically returned from stat and store other
  * info about object characteristics.  There is one for every file and dir in
  * the FS
@@ -963,7 +991,7 @@ struct btrfs_root {
 #define BTRFS_EXTENT_CSUM_KEY	128
 
 /*
- * root items point to tree roots.  There are typically in the root
+ * root items point to tree roots.  They are typically in the root
  * tree used by the super block to find all the other trees
  */
 #define BTRFS_ROOT_ITEM_KEY	132
@@ -1010,6 +1038,8 @@ struct btrfs_root {
 #define BTRFS_MOUNT_SSD			(1 << 3)
 #define BTRFS_MOUNT_DEGRADED		(1 << 4)
 #define BTRFS_MOUNT_COMPRESS		(1 << 5)
+#define BTRFS_MOUNT_NOTREELOG           (1 << 6)
+#define BTRFS_MOUNT_FLUSHONCOMMIT       (1 << 7)
 
 #define btrfs_clear_opt(o, opt)		((o) &= ~BTRFS_MOUNT_##opt)
 #define btrfs_set_opt(o, opt)		((o) |= BTRFS_MOUNT_##opt)
@@ -1748,6 +1778,7 @@ static inline struct dentry *fdentry(struct file *file)
 }
 
 /* extent-tree.c */
+void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int btrfs_run_delayed_refs(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root, unsigned long count);
 int btrfs_lookup_extent(struct btrfs_root *root, u64 start, u64 len);
@@ -2174,21 +2205,4 @@ int btrfs_check_acl(struct inode *inode, int mask);
 int btrfs_init_acl(struct inode *inode, struct inode *dir);
 int btrfs_acl_chmod(struct inode *inode);
 
-/* free-space-cache.c */
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 bytenr, u64 size);
-int btrfs_add_free_space_lock(struct btrfs_block_group_cache *block_group,
-			      u64 offset, u64 bytes);
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
-			    u64 bytenr, u64 size);
-int btrfs_remove_free_space_lock(struct btrfs_block_group_cache *block_group,
-				 u64 offset, u64 bytes);
-void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
-				   *block_group);
-struct btrfs_free_space *btrfs_find_free_space(struct btrfs_block_group_cache
-					       *block_group, u64 offset,
-					       u64 bytes);
-void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
-			   u64 bytes);
-u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group);
 #endif
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index cbf7dc8ae3ec..d6c01c096a40 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -18,7 +18,6 @@
 
 #include <linux/sched.h>
 #include <linux/sort.h>
-#include <linux/ftrace.h>
 #include "ctree.h"
 #include "delayed-ref.h"
 #include "transaction.h"
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 92d73929d381..92caa8035f36 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -38,6 +38,7 @@
 #include "locking.h"
 #include "ref-cache.h"
 #include "tree-log.h"
+#include "free-space-cache.h"
 
 static struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
@@ -1412,8 +1413,6 @@ static int bio_ready_for_csum(struct bio *bio)
 
 	ret = extent_range_uptodate(io_tree, start + length,
 				    start + buf_len - 1);
-	if (ret == 1)
-		return ret;
 	return ret;
 }
 
@@ -1647,12 +1646,15 @@ struct btrfs_root *open_ctree(struct super_block *sb,
 	mutex_init(&fs_info->ordered_operations_mutex);
 	mutex_init(&fs_info->tree_log_mutex);
 	mutex_init(&fs_info->drop_mutex);
-	mutex_init(&fs_info->pinned_mutex);
 	mutex_init(&fs_info->chunk_mutex);
 	mutex_init(&fs_info->transaction_kthread_mutex);
 	mutex_init(&fs_info->cleaner_mutex);
 	mutex_init(&fs_info->volume_mutex);
 	mutex_init(&fs_info->tree_reloc_mutex);
+
+	btrfs_init_free_cluster(&fs_info->meta_alloc_cluster);
+	btrfs_init_free_cluster(&fs_info->data_alloc_cluster);
+
 	init_waitqueue_head(&fs_info->transaction_throttle);
 	init_waitqueue_head(&fs_info->transaction_wait);
 	init_waitqueue_head(&fs_info->async_submit_wait);
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index f5e7cae63d80..178df4c67de4 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -31,6 +31,7 @@
 #include "volumes.h"
 #include "locking.h"
 #include "ref-cache.h"
+#include "free-space-cache.h"
 
 #define PENDING_EXTENT_INSERT 0
 #define PENDING_EXTENT_DELETE 1
@@ -166,7 +167,6 @@ static int add_new_free_space(struct btrfs_block_group_cache *block_group,
 	u64 extent_start, extent_end, size;
 	int ret;
 
-	mutex_lock(&info->pinned_mutex);
 	while (start < end) {
 		ret = find_first_extent_bit(&info->pinned_extents, start,
 					    &extent_start, &extent_end,
@@ -192,7 +192,6 @@ static int add_new_free_space(struct btrfs_block_group_cache *block_group,
 		ret = btrfs_add_free_space(block_group, start, size);
 		BUG_ON(ret);
 	}
-	mutex_unlock(&info->pinned_mutex);
 
 	return 0;
 }
@@ -291,8 +290,8 @@ next:
 			   block_group->key.objectid +
 			   block_group->key.offset);
 
-	remove_sb_from_cache(root, block_group);
 	block_group->cached = 1;
+	remove_sb_from_cache(root, block_group);
 	ret = 0;
 err:
 	btrfs_free_path(path);
@@ -326,7 +325,7 @@ struct btrfs_block_group_cache *btrfs_lookup_block_group(
 	return cache;
 }
 
-static inline void put_block_group(struct btrfs_block_group_cache *cache)
+void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
 {
 	if (atomic_dec_and_test(&cache->count))
 		kfree(cache);
@@ -399,12 +398,12 @@ again:
 			    div_factor(cache->key.offset, factor)) {
 				group_start = cache->key.objectid;
 				spin_unlock(&cache->lock);
-				put_block_group(cache);
+				btrfs_put_block_group(cache);
 				goto found;
 			}
 		}
 		spin_unlock(&cache->lock);
-		put_block_group(cache);
+		btrfs_put_block_group(cache);
 		cond_resched();
 	}
 	if (!wrapped) {
@@ -1594,7 +1593,7 @@ int btrfs_extent_readonly(struct btrfs_root *root, u64 bytenr)
 	if (!block_group || block_group->ro)
 		readonly = 1;
 	if (block_group)
-		put_block_group(block_group);
+		btrfs_put_block_group(block_group);
 	return readonly;
 }
 
@@ -2018,7 +2017,7 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 				WARN_ON(ret);
 			}
 		}
-		put_block_group(cache);
+		btrfs_put_block_group(cache);
 		total -= num_bytes;
 		bytenr += num_bytes;
 	}
@@ -2035,7 +2034,7 @@ static u64 first_logical_byte(struct btrfs_root *root, u64 search_start)
 		return 0;
 
 	bytenr = cache->key.objectid;
-	put_block_group(cache);
+	btrfs_put_block_group(cache);
 
 	return bytenr;
 }
@@ -2047,7 +2046,6 @@ int btrfs_update_pinned_extents(struct btrfs_root *root,
 	struct btrfs_block_group_cache *cache;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
-	WARN_ON(!mutex_is_locked(&root->fs_info->pinned_mutex));
 	if (pin) {
 		set_extent_dirty(&fs_info->pinned_extents,
 				bytenr, bytenr + num - 1, GFP_NOFS);
@@ -2055,7 +2053,6 @@ int btrfs_update_pinned_extents(struct btrfs_root *root,
 		clear_extent_dirty(&fs_info->pinned_extents,
 				bytenr, bytenr + num - 1, GFP_NOFS);
 	}
-	mutex_unlock(&root->fs_info->pinned_mutex);
 
 	while (num > 0) {
 		cache = btrfs_lookup_block_group(fs_info, bytenr);
@@ -2081,7 +2078,7 @@ int btrfs_update_pinned_extents(struct btrfs_root *root,
 			if (cache->cached)
 				btrfs_add_free_space(cache, bytenr, len);
 		}
-		put_block_group(cache);
+		btrfs_put_block_group(cache);
 		bytenr += len;
 		num -= len;
 	}
@@ -2112,7 +2109,7 @@ static int update_reserved_extents(struct btrfs_root *root,
 		}
 		spin_unlock(&cache->lock);
 		spin_unlock(&cache->space_info->lock);
-		put_block_group(cache);
+		btrfs_put_block_group(cache);
 		bytenr += len;
 		num -= len;
 	}
@@ -2127,7 +2124,6 @@ int btrfs_copy_pinned(struct btrfs_root *root, struct extent_io_tree *copy)
 	struct extent_io_tree *pinned_extents = &root->fs_info->pinned_extents;
 	int ret;
 
-	mutex_lock(&root->fs_info->pinned_mutex);
 	while (1) {
 		ret = find_first_extent_bit(pinned_extents, last,
 					    &start, &end, EXTENT_DIRTY);
@@ -2136,7 +2132,6 @@ int btrfs_copy_pinned(struct btrfs_root *root, struct extent_io_tree *copy)
 		set_extent_dirty(copy, start, end, GFP_NOFS);
 		last = end + 1;
 	}
-	mutex_unlock(&root->fs_info->pinned_mutex);
 	return 0;
 }
 
@@ -2149,7 +2144,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 	int ret;
 
 	while (1) {
-		mutex_lock(&root->fs_info->pinned_mutex);
 		ret = find_first_extent_bit(unpin, 0, &start, &end,
 					    EXTENT_DIRTY);
 		if (ret)
@@ -2163,7 +2157,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 
 		cond_resched();
 	}
-	mutex_unlock(&root->fs_info->pinned_mutex);
 	return ret;
 }
 
@@ -2205,7 +2198,6 @@ static int pin_down_bytes(struct btrfs_trans_handle *trans,
 	free_extent_buffer(buf);
 pinit:
 	btrfs_set_path_blocking(path);
-	mutex_lock(&root->fs_info->pinned_mutex);
 	/* unlocks the pinned mutex */
 	btrfs_update_pinned_extents(root, bytenr, num_bytes, 1);
 
@@ -2511,8 +2503,6 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 	 */
 	if (root->root_key.objectid == BTRFS_TREE_LOG_OBJECTID &&
 	    owner_objectid < BTRFS_FIRST_FREE_OBJECTID) {
-		mutex_lock(&root->fs_info->pinned_mutex);
-
 		/* unlocks the pinned mutex */
 		btrfs_update_pinned_extents(root, bytenr, num_bytes, 1);
 		update_reserved_extents(root, bytenr, num_bytes, 0);
@@ -2554,228 +2544,237 @@ static noinline int find_free_extent(struct btrfs_trans_handle *trans,
 {
 	int ret = 0;
 	struct btrfs_root *root = orig_root->fs_info->extent_root;
-	u64 total_needed = num_bytes;
-	u64 *last_ptr = NULL;
-	u64 last_wanted = 0;
+	struct btrfs_free_cluster *last_ptr = NULL;
 	struct btrfs_block_group_cache *block_group = NULL;
-	int chunk_alloc_done = 0;
 	int empty_cluster = 2 * 1024 * 1024;
 	int allowed_chunk_alloc = 0;
-	struct list_head *head = NULL, *cur = NULL;
-	int loop = 0;
-	int extra_loop = 0;
 	struct btrfs_space_info *space_info;
+	int last_ptr_loop = 0;
+	int loop = 0;
 
 	WARN_ON(num_bytes < root->sectorsize);
 	btrfs_set_key_type(ins, BTRFS_EXTENT_ITEM_KEY);
 	ins->objectid = 0;
 	ins->offset = 0;
 
+	space_info = __find_space_info(root->fs_info, data);
+
 	if (orig_root->ref_cows || empty_size)
 		allowed_chunk_alloc = 1;
 
 	if (data & BTRFS_BLOCK_GROUP_METADATA) {
-		last_ptr = &root->fs_info->last_alloc;
+		last_ptr = &root->fs_info->meta_alloc_cluster;
 		if (!btrfs_test_opt(root, SSD))
 			empty_cluster = 64 * 1024;
 	}
 
-	if ((data & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(root, SSD))
-		last_ptr = &root->fs_info->last_data_alloc;
+	if ((data & BTRFS_BLOCK_GROUP_DATA) && btrfs_test_opt(root, SSD)) {
+		last_ptr = &root->fs_info->data_alloc_cluster;
+	}
 
 	if (last_ptr) {
-		if (*last_ptr) {
-			hint_byte = *last_ptr;
-			last_wanted = *last_ptr;
-		} else
-			empty_size += empty_cluster;
-	} else {
-		empty_cluster = 0;
+		spin_lock(&last_ptr->lock);
+		if (last_ptr->block_group)
+			hint_byte = last_ptr->window_start;
+		spin_unlock(&last_ptr->lock);
 	}
+
 	search_start = max(search_start, first_logical_byte(root, 0));
 	search_start = max(search_start, hint_byte);
 
-	if (last_wanted && search_start != last_wanted) {
-		last_wanted = 0;
-		empty_size += empty_cluster;
+	if (!last_ptr) {
+		empty_cluster = 0;
+		loop = 1;
 	}
 
-	total_needed += empty_size;
-	block_group = btrfs_lookup_block_group(root->fs_info, search_start);
-	if (!block_group)
-		block_group = btrfs_lookup_first_block_group(root->fs_info,
-							     search_start);
-	space_info = __find_space_info(root->fs_info, data);
+	if (search_start == hint_byte) {
+		block_group = btrfs_lookup_block_group(root->fs_info,
+						       search_start);
+		if (block_group && block_group_bits(block_group, data)) {
+			down_read(&space_info->groups_sem);
+			goto have_block_group;
+		} else if (block_group) {
+			btrfs_put_block_group(block_group);
+		}
+	}
 
+search:
 	down_read(&space_info->groups_sem);
-	while (1) {
-		struct btrfs_free_space *free_space;
-		/*
-		 * the only way this happens if our hint points to a block
-		 * group thats not of the proper type, while looping this
-		 * should never happen
-		 */
-		if (empty_size)
-			extra_loop = 1;
+	list_for_each_entry(block_group, &space_info->block_groups, list) {
+		u64 offset;
 
-		if (!block_group)
-			goto new_group_no_lock;
+		atomic_inc(&block_group->count);
+		search_start = block_group->key.objectid;
 
+have_block_group:
 		if (unlikely(!block_group->cached)) {
 			mutex_lock(&block_group->cache_mutex);
 			ret = cache_block_group(root, block_group);
 			mutex_unlock(&block_group->cache_mutex);
-			if (ret)
+			if (ret) {
+				btrfs_put_block_group(block_group);
 				break;
+			}
 		}
 
-		mutex_lock(&block_group->alloc_mutex);
-		if (unlikely(!block_group_bits(block_group, data)))
-			goto new_group;
-
 		if (unlikely(block_group->ro))
-			goto new_group;
+			goto loop;
 
-		free_space = btrfs_find_free_space(block_group, search_start,
-						   total_needed);
-		if (free_space) {
-			u64 start = block_group->key.objectid;
-			u64 end = block_group->key.objectid +
-				block_group->key.offset;
+		if (last_ptr) {
+			/*
+			 * the refill lock keeps out other
+			 * people trying to start a new cluster
+			 */
+			spin_lock(&last_ptr->refill_lock);
+			offset = btrfs_alloc_from_cluster(block_group, last_ptr,
+						 num_bytes, search_start);
+			if (offset) {
+				/* we have a block, we're done */
+				spin_unlock(&last_ptr->refill_lock);
+				goto checks;
+			}
 
-			search_start = stripe_align(root, free_space->offset);
+			spin_lock(&last_ptr->lock);
+			/*
+			 * whoops, this cluster doesn't actually point to
+			 * this block group.  Get a ref on the block
+			 * group is does point to and try again
+			 */
+			if (!last_ptr_loop && last_ptr->block_group &&
+			    last_ptr->block_group != block_group) {
+
+				btrfs_put_block_group(block_group);
+				block_group = last_ptr->block_group;
+				atomic_inc(&block_group->count);
+				spin_unlock(&last_ptr->lock);
+				spin_unlock(&last_ptr->refill_lock);
+
+				last_ptr_loop = 1;
+				search_start = block_group->key.objectid;
+				goto have_block_group;
+			}
+			spin_unlock(&last_ptr->lock);
 
-			/* move on to the next group */
-			if (search_start + num_bytes >= search_end)
-				goto new_group;
+			/*
+			 * this cluster didn't work out, free it and
+			 * start over
+			 */
+			btrfs_return_cluster_to_free_space(NULL, last_ptr);
 
-			/* move on to the next group */
-			if (search_start + num_bytes > end)
-				goto new_group;
+			last_ptr_loop = 0;
 
-			if (last_wanted && search_start != last_wanted) {
-				total_needed += empty_cluster;
-				empty_size += empty_cluster;
-				last_wanted = 0;
+			/* allocate a cluster in this block group */
+			ret = btrfs_find_space_cluster(trans,
+					       block_group, last_ptr,
+					       offset, num_bytes,
+					       empty_cluster + empty_size);
+			if (ret == 0) {
 				/*
-				 * if search_start is still in this block group
-				 * then we just re-search this block group
+				 * now pull our allocation out of this
+				 * cluster
 				 */
-				if (search_start >= start &&
-				    search_start < end) {
-					mutex_unlock(&block_group->alloc_mutex);
-					continue;
+				offset = btrfs_alloc_from_cluster(block_group,
+						  last_ptr, num_bytes,
+						  search_start);
+				if (offset) {
+					/* we found one, proceed */
+					spin_unlock(&last_ptr->refill_lock);
+					goto checks;
 				}
-
-				/* else we go to the next block group */
-				goto new_group;
 			}
-
-			if (exclude_nr > 0 &&
-			    (search_start + num_bytes > exclude_start &&
-			     search_start < exclude_start + exclude_nr)) {
-				search_start = exclude_start + exclude_nr;
-				/*
-				 * if search_start is still in this block group
-				 * then we just re-search this block group
-				 */
-				if (search_start >= start &&
-				    search_start < end) {
-					mutex_unlock(&block_group->alloc_mutex);
-					last_wanted = 0;
-					continue;
-				}
-
-				/* else we go to the next block group */
-				goto new_group;
+			/*
+			 * at this point we either didn't find a cluster
+			 * or we weren't able to allocate a block from our
+			 * cluster.  Free the cluster we've been trying
+			 * to use, and go to the next block group
+			 */
+			if (loop < 2) {
+				btrfs_return_cluster_to_free_space(NULL,
+								   last_ptr);
+				spin_unlock(&last_ptr->refill_lock);
+				goto loop;
 			}
+			spin_unlock(&last_ptr->refill_lock);
+		}
 
-			ins->objectid = search_start;
-			ins->offset = num_bytes;
+		offset = btrfs_find_space_for_alloc(block_group, search_start,
+						    num_bytes, empty_size);
+		if (!offset)
+			goto loop;
+checks:
+		search_start = stripe_align(root, offset);
+
+		/* move on to the next group */
+		if (search_start + num_bytes >= search_end) {
+			btrfs_add_free_space(block_group, offset, num_bytes);
+			goto loop;
+		}
 
-			btrfs_remove_free_space_lock(block_group, search_start,
-						     num_bytes);
-			/* we are all good, lets return */
-			mutex_unlock(&block_group->alloc_mutex);
-			break;
+		/* move on to the next group */
+		if (search_start + num_bytes >
+		    block_group->key.objectid + block_group->key.offset) {
+			btrfs_add_free_space(block_group, offset, num_bytes);
+			goto loop;
 		}
-new_group:
-		mutex_unlock(&block_group->alloc_mutex);
-		put_block_group(block_group);
-		block_group = NULL;
-new_group_no_lock:
-		/* don't try to compare new allocations against the
-		 * last allocation any more
-		 */
-		last_wanted = 0;
 
-		/*
-		 * Here's how this works.
-		 * loop == 0: we were searching a block group via a hint
-		 *		and didn't find anything, so we start at
-		 *		the head of the block groups and keep searching
-		 * loop == 1: we're searching through all of the block groups
-		 *		if we hit the head again we have searched
-		 *		all of the block groups for this space and we
-		 *		need to try and allocate, if we cant error out.
-		 * loop == 2: we allocated more space and are looping through
-		 *		all of the block groups again.
-		 */
-		if (loop == 0) {
-			head = &space_info->block_groups;
-			cur = head->next;
-			loop++;
-		} else if (loop == 1 && cur == head) {
-			int keep_going;
-
-			/* at this point we give up on the empty_size
-			 * allocations and just try to allocate the min
-			 * space.
-			 *
-			 * The extra_loop field was set if an empty_size
-			 * allocation was attempted above, and if this
-			 * is try we need to try the loop again without
-			 * the additional empty_size.
+		if (exclude_nr > 0 &&
+		    (search_start + num_bytes > exclude_start &&
+		     search_start < exclude_start + exclude_nr)) {
+			search_start = exclude_start + exclude_nr;
+
+			btrfs_add_free_space(block_group, offset, num_bytes);
+			/*
+			 * if search_start is still in this block group
+			 * then we just re-search this block group
 			 */
-			total_needed -= empty_size;
-			empty_size = 0;
-			keep_going = extra_loop;
-			loop++;
+			if (search_start >= block_group->key.objectid &&
+			    search_start < (block_group->key.objectid +
+					    block_group->key.offset))
+				goto have_block_group;
+			goto loop;
+		}
 
-			if (allowed_chunk_alloc && !chunk_alloc_done) {
-				up_read(&space_info->groups_sem);
-				ret = do_chunk_alloc(trans, root, num_bytes +
-						     2 * 1024 * 1024, data, 1);
-				down_read(&space_info->groups_sem);
-				if (ret < 0)
-					goto loop_check;
-				head = &space_info->block_groups;
-				/*
-				 * we've allocated a new chunk, keep
-				 * trying
-				 */
-				keep_going = 1;
-				chunk_alloc_done = 1;
-			} else if (!allowed_chunk_alloc) {
-				space_info->force_alloc = 1;
-			}
-loop_check:
-			if (keep_going) {
-				cur = head->next;
-				extra_loop = 0;
-			} else {
-				break;
-			}
-		} else if (cur == head) {
-			break;
+		ins->objectid = search_start;
+		ins->offset = num_bytes;
+
+		if (offset < search_start)
+			btrfs_add_free_space(block_group, offset,
+					     search_start - offset);
+		BUG_ON(offset > search_start);
+
+		/* we are all good, lets return */
+		break;
+loop:
+		btrfs_put_block_group(block_group);
+	}
+	up_read(&space_info->groups_sem);
+
+	/* loop == 0, try to find a clustered alloc in every block group
+	 * loop == 1, try again after forcing a chunk allocation
+	 * loop == 2, set empty_size and empty_cluster to 0 and try again
+	 */
+	if (!ins->objectid && loop < 3 &&
+	    (empty_size || empty_cluster || allowed_chunk_alloc)) {
+		if (loop >= 2) {
+			empty_size = 0;
+			empty_cluster = 0;
 		}
 
-		block_group = list_entry(cur, struct btrfs_block_group_cache,
-					 list);
-		atomic_inc(&block_group->count);
+		if (allowed_chunk_alloc) {
+			ret = do_chunk_alloc(trans, root, num_bytes +
+					     2 * 1024 * 1024, data, 1);
+			allowed_chunk_alloc = 0;
+		} else {
+			space_info->force_alloc = 1;
+		}
 
-		search_start = block_group->key.objectid;
-		cur = cur->next;
+		if (loop < 3) {
+			loop++;
+			goto search;
+		}
+		ret = -ENOSPC;
+	} else if (!ins->objectid) {
+		ret = -ENOSPC;
 	}
 
 	/* we found what we needed */
@@ -2783,21 +2782,10 @@ loop_check:
 		if (!(data & BTRFS_BLOCK_GROUP_DATA))
 			trans->block_group = block_group->key.objectid;
 
-		if (last_ptr)
-			*last_ptr = ins->objectid + ins->offset;
+		btrfs_put_block_group(block_group);
 		ret = 0;
-	} else if (!ret) {
-		printk(KERN_ERR "btrfs searching for %llu bytes, "
-		       "num_bytes %llu, loop %d, allowed_alloc %d\n",
-		       (unsigned long long)total_needed,
-		       (unsigned long long)num_bytes,
-		       loop, allowed_chunk_alloc);
-		ret = -ENOSPC;
 	}
-	if (block_group)
-		put_block_group(block_group);
 
-	up_read(&space_info->groups_sem);
 	return ret;
 }
 
@@ -2902,7 +2890,7 @@ int btrfs_free_reserved_extent(struct btrfs_root *root, u64 start, u64 len)
 	ret = btrfs_discard_extent(root, start, len);
 
 	btrfs_add_free_space(cache, start, len);
-	put_block_group(cache);
+	btrfs_put_block_group(cache);
 	update_reserved_extents(root, start, len, 0);
 
 	return ret;
@@ -3040,7 +3028,7 @@ int btrfs_alloc_logged_extent(struct btrfs_trans_handle *trans,
 	ret = btrfs_remove_free_space(block_group, ins->objectid,
 				      ins->offset);
 	BUG_ON(ret);
-	put_block_group(block_group);
+	btrfs_put_block_group(block_group);
 	ret = __btrfs_alloc_reserved_extent(trans, root, parent, root_objectid,
 					    ref_generation, owner, ins, 1);
 	return ret;
@@ -5729,7 +5717,7 @@ next:
 	WARN_ON(block_group->reserved > 0);
 	WARN_ON(btrfs_block_group_used(&block_group->item) > 0);
 	spin_unlock(&block_group->lock);
-	put_block_group(block_group);
+	btrfs_put_block_group(block_group);
 	ret = 0;
 out:
 	btrfs_free_path(path);
@@ -5856,9 +5844,10 @@ int btrfs_read_block_groups(struct btrfs_root *root)
 
 		atomic_set(&cache->count, 1);
 		spin_lock_init(&cache->lock);
-		mutex_init(&cache->alloc_mutex);
+		spin_lock_init(&cache->tree_lock);
 		mutex_init(&cache->cache_mutex);
 		INIT_LIST_HEAD(&cache->list);
+		INIT_LIST_HEAD(&cache->cluster_list);
 		read_extent_buffer(leaf, &cache->item,
 				   btrfs_item_ptr_offset(leaf, path->slots[0]),
 				   sizeof(cache->item));
@@ -5912,9 +5901,10 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	cache->key.type = BTRFS_BLOCK_GROUP_ITEM_KEY;
 	atomic_set(&cache->count, 1);
 	spin_lock_init(&cache->lock);
-	mutex_init(&cache->alloc_mutex);
+	spin_lock_init(&cache->tree_lock);
 	mutex_init(&cache->cache_mutex);
 	INIT_LIST_HEAD(&cache->list);
+	INIT_LIST_HEAD(&cache->cluster_list);
 
 	btrfs_set_block_group_used(&cache->item, bytes_used);
 	btrfs_set_block_group_chunk_objectid(&cache->item, chunk_objectid);
@@ -5974,8 +5964,8 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	spin_unlock(&block_group->space_info->lock);
 	block_group->space_info->full = 0;
 
-	put_block_group(block_group);
-	put_block_group(block_group);
+	btrfs_put_block_group(block_group);
+	btrfs_put_block_group(block_group);
 
 	ret = btrfs_search_slot(trans, root, &key, path, -1, 1);
 	if (ret > 0)
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 08085af089e2..eb2bee8b7fbf 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -2884,25 +2884,19 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		disko = 0;
 		flags = 0;
 
-		switch (em->block_start) {
-		case EXTENT_MAP_LAST_BYTE:
+		if (em->block_start == EXTENT_MAP_LAST_BYTE) {
 			end = 1;
 			flags |= FIEMAP_EXTENT_LAST;
-			break;
-		case EXTENT_MAP_HOLE:
+		} else if (em->block_start == EXTENT_MAP_HOLE) {
 			flags |= FIEMAP_EXTENT_UNWRITTEN;
-			break;
-		case EXTENT_MAP_INLINE:
+		} else if (em->block_start == EXTENT_MAP_INLINE) {
 			flags |= (FIEMAP_EXTENT_DATA_INLINE |
 				  FIEMAP_EXTENT_NOT_ALIGNED);
-			break;
-		case EXTENT_MAP_DELALLOC:
+		} else if (em->block_start == EXTENT_MAP_DELALLOC) {
 			flags |= (FIEMAP_EXTENT_DELALLOC |
 				  FIEMAP_EXTENT_UNKNOWN);
-			break;
-		default:
+		} else {
 			disko = em->block_start;
-			break;
 		}
 		if (test_bit(EXTENT_FLAG_COMPRESSED, &em->flags))
 			flags |= FIEMAP_EXTENT_ENCODED;
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 50da69da20ce..b187917b36fa 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -234,7 +234,6 @@ int add_extent_mapping(struct extent_map_tree *tree,
 	rb = tree_insert(&tree->map, em->start, &em->rb_node);
 	if (rb) {
 		ret = -EEXIST;
-		free_extent_map(merge);
 		goto out;
 	}
 	atomic_inc(&em->refs);
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index d1e5f0e84c58..768b9523662d 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -18,6 +18,15 @@
 
 #include <linux/sched.h>
 #include "ctree.h"
+#include "free-space-cache.h"
+#include "transaction.h"
+
+struct btrfs_free_space {
+	struct rb_node bytes_index;
+	struct rb_node offset_index;
+	u64 offset;
+	u64 bytes;
+};
 
 static int tree_insert_offset(struct rb_root *root, u64 offset,
 			      struct rb_node *node)
@@ -68,14 +77,24 @@ static int tree_insert_bytes(struct rb_root *root, u64 bytes,
 }
 
 /*
- * searches the tree for the given offset.  If contains is set we will return
- * the free space that contains the given offset.  If contains is not set we
- * will return the free space that starts at or after the given offset and is
- * at least bytes long.
+ * searches the tree for the given offset.
+ *
+ * fuzzy == 1: this is used for allocations where we are given a hint of where
+ * to look for free space.  Because the hint may not be completely on an offset
+ * mark, or the hint may no longer point to free space we need to fudge our
+ * results a bit.  So we look for free space starting at or after offset with at
+ * least bytes size.  We prefer to find as close to the given offset as we can.
+ * Also if the offset is within a free space range, then we will return the free
+ * space that contains the given offset, which means we can return a free space
+ * chunk with an offset before the provided offset.
+ *
+ * fuzzy == 0: this is just a normal tree search.  Give us the free space that
+ * starts at the given offset which is at least bytes size, and if its not there
+ * return NULL.
  */
 static struct btrfs_free_space *tree_search_offset(struct rb_root *root,
 						   u64 offset, u64 bytes,
-						   int contains)
+						   int fuzzy)
 {
 	struct rb_node *n = root->rb_node;
 	struct btrfs_free_space *entry, *ret = NULL;
@@ -84,13 +103,14 @@ static struct btrfs_free_space *tree_search_offset(struct rb_root *root,
 		entry = rb_entry(n, struct btrfs_free_space, offset_index);
 
 		if (offset < entry->offset) {
-			if (!contains &&
+			if (fuzzy &&
 			    (!ret || entry->offset < ret->offset) &&
 			    (bytes <= entry->bytes))
 				ret = entry;
 			n = n->rb_left;
 		} else if (offset > entry->offset) {
-			if ((entry->offset + entry->bytes - 1) >= offset &&
+			if (fuzzy &&
+			    (entry->offset + entry->bytes - 1) >= offset &&
 			    bytes <= entry->bytes) {
 				ret = entry;
 				break;
@@ -171,6 +191,7 @@ static int link_free_space(struct btrfs_block_group_cache *block_group,
 	int ret = 0;
 
 
+	BUG_ON(!info->bytes);
 	ret = tree_insert_offset(&block_group->free_space_offset, info->offset,
 				 &info->offset_index);
 	if (ret)
@@ -184,108 +205,70 @@ static int link_free_space(struct btrfs_block_group_cache *block_group,
 	return ret;
 }
 
-static int __btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-				  u64 offset, u64 bytes)
+int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+			 u64 offset, u64 bytes)
 {
 	struct btrfs_free_space *right_info;
 	struct btrfs_free_space *left_info;
 	struct btrfs_free_space *info = NULL;
-	struct btrfs_free_space *alloc_info;
 	int ret = 0;
 
-	alloc_info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
-	if (!alloc_info)
+	info = kzalloc(sizeof(struct btrfs_free_space), GFP_NOFS);
+	if (!info)
 		return -ENOMEM;
 
+	info->offset = offset;
+	info->bytes = bytes;
+
+	spin_lock(&block_group->tree_lock);
+
 	/*
 	 * first we want to see if there is free space adjacent to the range we
 	 * are adding, if there is remove that struct and add a new one to
 	 * cover the entire range
 	 */
 	right_info = tree_search_offset(&block_group->free_space_offset,
-					offset+bytes, 0, 1);
+					offset+bytes, 0, 0);
 	left_info = tree_search_offset(&block_group->free_space_offset,
 				       offset-1, 0, 1);
 
-	if (right_info && right_info->offset == offset+bytes) {
+	if (right_info) {
 		unlink_free_space(block_group, right_info);
-		info = right_info;
-		info->offset = offset;
-		info->bytes += bytes;
-	} else if (right_info && right_info->offset != offset+bytes) {
-		printk(KERN_ERR "btrfs adding space in the middle of an "
-		       "existing free space area. existing: "
-		       "offset=%llu, bytes=%llu. new: offset=%llu, "
-		       "bytes=%llu\n", (unsigned long long)right_info->offset,
-		       (unsigned long long)right_info->bytes,
-		       (unsigned long long)offset,
-		       (unsigned long long)bytes);
-		BUG();
+		info->bytes += right_info->bytes;
+		kfree(right_info);
 	}
 
-	if (left_info) {
+	if (left_info && left_info->offset + left_info->bytes == offset) {
 		unlink_free_space(block_group, left_info);
-
-		if (unlikely((left_info->offset + left_info->bytes) !=
-			     offset)) {
-			printk(KERN_ERR "btrfs free space to the left "
-			       "of new free space isn't "
-			       "quite right. existing: offset=%llu, "
-			       "bytes=%llu. new: offset=%llu, bytes=%llu\n",
-			       (unsigned long long)left_info->offset,
-			       (unsigned long long)left_info->bytes,
-			       (unsigned long long)offset,
-			       (unsigned long long)bytes);
-			BUG();
-		}
-
-		if (info) {
-			info->offset = left_info->offset;
-			info->bytes += left_info->bytes;
-			kfree(left_info);
-		} else {
-			info = left_info;
-			info->bytes += bytes;
-		}
+		info->offset = left_info->offset;
+		info->bytes += left_info->bytes;
+		kfree(left_info);
 	}
 
-	if (info) {
-		ret = link_free_space(block_group, info);
-		if (!ret)
-			info = NULL;
-		goto out;
-	}
-
-	info = alloc_info;
-	alloc_info = NULL;
-	info->offset = offset;
-	info->bytes = bytes;
-
 	ret = link_free_space(block_group, info);
 	if (ret)
 		kfree(info);
-out:
+
+	spin_unlock(&block_group->tree_lock);
+
 	if (ret) {
 		printk(KERN_ERR "btrfs: unable to add free space :%d\n", ret);
-		if (ret == -EEXIST)
-			BUG();
+		BUG_ON(ret == -EEXIST);
 	}
 
-	kfree(alloc_info);
-
 	return ret;
 }
 
-static int
-__btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
-			  u64 offset, u64 bytes)
+int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+			    u64 offset, u64 bytes)
 {
 	struct btrfs_free_space *info;
 	int ret = 0;
 
+	spin_lock(&block_group->tree_lock);
+
 	info = tree_search_offset(&block_group->free_space_offset, offset, 0,
 				  1);
-
 	if (info && info->offset == offset) {
 		if (info->bytes < bytes) {
 			printk(KERN_ERR "Found free space at %llu, size %llu,"
@@ -295,12 +278,14 @@ __btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 			       (unsigned long long)bytes);
 			WARN_ON(1);
 			ret = -EINVAL;
+			spin_unlock(&block_group->tree_lock);
 			goto out;
 		}
 		unlink_free_space(block_group, info);
 
 		if (info->bytes == bytes) {
 			kfree(info);
+			spin_unlock(&block_group->tree_lock);
 			goto out;
 		}
 
@@ -308,6 +293,7 @@ __btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 		info->bytes -= bytes;
 
 		ret = link_free_space(block_group, info);
+		spin_unlock(&block_group->tree_lock);
 		BUG_ON(ret);
 	} else if (info && info->offset < offset &&
 		   info->offset + info->bytes >= offset + bytes) {
@@ -333,70 +319,33 @@ __btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
 			 */
 			kfree(info);
 		}
-
+		spin_unlock(&block_group->tree_lock);
 		/* step two, insert a new info struct to cover anything
 		 * before the hole
 		 */
-		ret = __btrfs_add_free_space(block_group, old_start,
-					     offset - old_start);
+		ret = btrfs_add_free_space(block_group, old_start,
+					   offset - old_start);
 		BUG_ON(ret);
 	} else {
+		spin_unlock(&block_group->tree_lock);
+		if (!info) {
+			printk(KERN_ERR "couldn't find space %llu to free\n",
+			       (unsigned long long)offset);
+			printk(KERN_ERR "cached is %d, offset %llu bytes %llu\n",
+			       block_group->cached, block_group->key.objectid,
+			       block_group->key.offset);
+			btrfs_dump_free_space(block_group, bytes);
+		} else if (info) {
+			printk(KERN_ERR "hmm, found offset=%llu bytes=%llu, "
+			       "but wanted offset=%llu bytes=%llu\n",
+			       info->offset, info->bytes, offset, bytes);
+		}
 		WARN_ON(1);
 	}
 out:
 	return ret;
 }
 
-int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
-			 u64 offset, u64 bytes)
-{
-	int ret;
-	struct btrfs_free_space *sp;
-
-	mutex_lock(&block_group->alloc_mutex);
-	ret = __btrfs_add_free_space(block_group, offset, bytes);
-	sp = tree_search_offset(&block_group->free_space_offset, offset, 0, 1);
-	BUG_ON(!sp);
-	mutex_unlock(&block_group->alloc_mutex);
-
-	return ret;
-}
-
-int btrfs_add_free_space_lock(struct btrfs_block_group_cache *block_group,
-			      u64 offset, u64 bytes)
-{
-	int ret;
-	struct btrfs_free_space *sp;
-
-	ret = __btrfs_add_free_space(block_group, offset, bytes);
-	sp = tree_search_offset(&block_group->free_space_offset, offset, 0, 1);
-	BUG_ON(!sp);
-
-	return ret;
-}
-
-int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
-			    u64 offset, u64 bytes)
-{
-	int ret = 0;
-
-	mutex_lock(&block_group->alloc_mutex);
-	ret = __btrfs_remove_free_space(block_group, offset, bytes);
-	mutex_unlock(&block_group->alloc_mutex);
-
-	return ret;
-}
-
-int btrfs_remove_free_space_lock(struct btrfs_block_group_cache *block_group,
-				 u64 offset, u64 bytes)
-{
-	int ret;
-
-	ret = __btrfs_remove_free_space(block_group, offset, bytes);
-
-	return ret;
-}
-
 void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 			   u64 bytes)
 {
@@ -408,6 +357,8 @@ void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
 		info = rb_entry(n, struct btrfs_free_space, offset_index);
 		if (info->bytes >= bytes)
 			count++;
+		printk(KERN_ERR "entry offset %llu, bytes %llu\n", info->offset,
+		       info->bytes);
 	}
 	printk(KERN_INFO "%d blocks of free space at or bigger than bytes is"
 	       "\n", count);
@@ -428,68 +379,337 @@ u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group)
 	return ret;
 }
 
+/*
+ * for a given cluster, put all of its extents back into the free
+ * space cache.  If the block group passed doesn't match the block group
+ * pointed to by the cluster, someone else raced in and freed the
+ * cluster already.  In that case, we just return without changing anything
+ */
+static int
+__btrfs_return_cluster_to_free_space(
+			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_free_cluster *cluster)
+{
+	struct btrfs_free_space *entry;
+	struct rb_node *node;
+
+	spin_lock(&cluster->lock);
+	if (cluster->block_group != block_group)
+		goto out;
+
+	cluster->window_start = 0;
+	node = rb_first(&cluster->root);
+	while(node) {
+		entry = rb_entry(node, struct btrfs_free_space, offset_index);
+		node = rb_next(&entry->offset_index);
+		rb_erase(&entry->offset_index, &cluster->root);
+		link_free_space(block_group, entry);
+	}
+	list_del_init(&cluster->block_group_list);
+
+	btrfs_put_block_group(cluster->block_group);
+	cluster->block_group = NULL;
+	cluster->root.rb_node = NULL;
+out:
+	spin_unlock(&cluster->lock);
+	return 0;
+}
+
 void btrfs_remove_free_space_cache(struct btrfs_block_group_cache *block_group)
 {
 	struct btrfs_free_space *info;
 	struct rb_node *node;
+	struct btrfs_free_cluster *cluster;
+	struct btrfs_free_cluster *safe;
+
+	spin_lock(&block_group->tree_lock);
+
+	list_for_each_entry_safe(cluster, safe, &block_group->cluster_list,
+				 block_group_list) {
+
+		WARN_ON(cluster->block_group != block_group);
+		__btrfs_return_cluster_to_free_space(block_group, cluster);
+	}
 
-	mutex_lock(&block_group->alloc_mutex);
 	while ((node = rb_last(&block_group->free_space_bytes)) != NULL) {
 		info = rb_entry(node, struct btrfs_free_space, bytes_index);
 		unlink_free_space(block_group, info);
 		kfree(info);
 		if (need_resched()) {
-			mutex_unlock(&block_group->alloc_mutex);
+			spin_unlock(&block_group->tree_lock);
 			cond_resched();
-			mutex_lock(&block_group->alloc_mutex);
+			spin_lock(&block_group->tree_lock);
 		}
 	}
-	mutex_unlock(&block_group->alloc_mutex);
+	spin_unlock(&block_group->tree_lock);
 }
 
-#if 0
-static struct btrfs_free_space *btrfs_find_free_space_offset(struct
-						      btrfs_block_group_cache
-						      *block_group, u64 offset,
-						      u64 bytes)
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+			       u64 offset, u64 bytes, u64 empty_size)
 {
-	struct btrfs_free_space *ret;
+	struct btrfs_free_space *entry = NULL;
+	u64 ret = 0;
 
-	mutex_lock(&block_group->alloc_mutex);
-	ret = tree_search_offset(&block_group->free_space_offset, offset,
-				 bytes, 0);
-	mutex_unlock(&block_group->alloc_mutex);
+	spin_lock(&block_group->tree_lock);
+	entry = tree_search_offset(&block_group->free_space_offset, offset,
+				   bytes + empty_size, 1);
+	if (!entry)
+		entry = tree_search_bytes(&block_group->free_space_bytes,
+					  offset, bytes + empty_size);
+	if (entry) {
+		unlink_free_space(block_group, entry);
+		ret = entry->offset;
+		entry->offset += bytes;
+		entry->bytes -= bytes;
+
+		if (!entry->bytes)
+			kfree(entry);
+		else
+			link_free_space(block_group, entry);
+	}
+	spin_unlock(&block_group->tree_lock);
 
 	return ret;
 }
 
-static struct btrfs_free_space *btrfs_find_free_space_bytes(struct
-						     btrfs_block_group_cache
-						     *block_group, u64 offset,
-						     u64 bytes)
+/*
+ * given a cluster, put all of its extents back into the free space
+ * cache.  If a block group is passed, this function will only free
+ * a cluster that belongs to the passed block group.
+ *
+ * Otherwise, it'll get a reference on the block group pointed to by the
+ * cluster and remove the cluster from it.
+ */
+int btrfs_return_cluster_to_free_space(
+			       struct btrfs_block_group_cache *block_group,
+			       struct btrfs_free_cluster *cluster)
 {
-	struct btrfs_free_space *ret;
+	int ret;
 
-	mutex_lock(&block_group->alloc_mutex);
+	/* first, get a safe pointer to the block group */
+	spin_lock(&cluster->lock);
+	if (!block_group) {
+		block_group = cluster->block_group;
+		if (!block_group) {
+			spin_unlock(&cluster->lock);
+			return 0;
+		}
+	} else if (cluster->block_group != block_group) {
+		/* someone else has already freed it don't redo their work */
+		spin_unlock(&cluster->lock);
+		return 0;
+	}
+	atomic_inc(&block_group->count);
+	spin_unlock(&cluster->lock);
 
-	ret = tree_search_bytes(&block_group->free_space_bytes, offset, bytes);
-	mutex_unlock(&block_group->alloc_mutex);
+	/* now return any extents the cluster had on it */
+	spin_lock(&block_group->tree_lock);
+	ret = __btrfs_return_cluster_to_free_space(block_group, cluster);
+	spin_unlock(&block_group->tree_lock);
 
+	/* finally drop our ref */
+	btrfs_put_block_group(block_group);
 	return ret;
 }
-#endif
 
-struct btrfs_free_space *btrfs_find_free_space(struct btrfs_block_group_cache
-					       *block_group, u64 offset,
-					       u64 bytes)
+/*
+ * given a cluster, try to allocate 'bytes' from it, returns 0
+ * if it couldn't find anything suitably large, or a logical disk offset
+ * if things worked out
+ */
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+			     struct btrfs_free_cluster *cluster, u64 bytes,
+			     u64 min_start)
+{
+	struct btrfs_free_space *entry = NULL;
+	struct rb_node *node;
+	u64 ret = 0;
+
+	spin_lock(&cluster->lock);
+	if (bytes > cluster->max_size)
+		goto out;
+
+	if (cluster->block_group != block_group)
+		goto out;
+
+	node = rb_first(&cluster->root);
+	if (!node)
+		goto out;
+
+	entry = rb_entry(node, struct btrfs_free_space, offset_index);
+
+	while(1) {
+		if (entry->bytes < bytes || entry->offset < min_start) {
+			struct rb_node *node;
+
+			node = rb_next(&entry->offset_index);
+			if (!node)
+				break;
+			entry = rb_entry(node, struct btrfs_free_space,
+					 offset_index);
+			continue;
+		}
+		ret = entry->offset;
+
+		entry->offset += bytes;
+		entry->bytes -= bytes;
+
+		if (entry->bytes == 0) {
+			rb_erase(&entry->offset_index, &cluster->root);
+			kfree(entry);
+		}
+		break;
+	}
+out:
+	spin_unlock(&cluster->lock);
+	return ret;
+}
+
+/*
+ * here we try to find a cluster of blocks in a block group.  The goal
+ * is to find at least bytes free and up to empty_size + bytes free.
+ * We might not find them all in one contiguous area.
+ *
+ * returns zero and sets up cluster if things worked out, otherwise
+ * it returns -enospc
+ */
+int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
+			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_free_cluster *cluster,
+			     u64 offset, u64 bytes, u64 empty_size)
 {
-	struct btrfs_free_space *ret = NULL;
+	struct btrfs_free_space *entry = NULL;
+	struct rb_node *node;
+	struct btrfs_free_space *next;
+	struct btrfs_free_space *last;
+	u64 min_bytes;
+	u64 window_start;
+	u64 window_free;
+	u64 max_extent = 0;
+	int total_retries = 0;
+	int ret;
+
+	/* for metadata, allow allocates with more holes */
+	if (block_group->flags & BTRFS_BLOCK_GROUP_METADATA) {
+		/*
+		 * we want to do larger allocations when we are
+		 * flushing out the delayed refs, it helps prevent
+		 * making more work as we go along.
+		 */
+		if (trans->transaction->delayed_refs.flushing)
+			min_bytes = max(bytes, (bytes + empty_size) >> 1);
+		else
+			min_bytes = max(bytes, (bytes + empty_size) >> 4);
+	} else
+		min_bytes = max(bytes, (bytes + empty_size) >> 2);
+
+	spin_lock(&block_group->tree_lock);
+	spin_lock(&cluster->lock);
+
+	/* someone already found a cluster, hooray */
+	if (cluster->block_group) {
+		ret = 0;
+		goto out;
+	}
+again:
+	min_bytes = min(min_bytes, bytes + empty_size);
+	entry = tree_search_bytes(&block_group->free_space_bytes,
+				  offset, min_bytes);
+	if (!entry) {
+		ret = -ENOSPC;
+		goto out;
+	}
+	window_start = entry->offset;
+	window_free = entry->bytes;
+	last = entry;
+	max_extent = entry->bytes;
+
+	while(1) {
+		/* out window is just right, lets fill it */
+		if (window_free >= bytes + empty_size)
+			break;
 
-	ret = tree_search_offset(&block_group->free_space_offset, offset,
-				 bytes, 0);
-	if (!ret)
-		ret = tree_search_bytes(&block_group->free_space_bytes,
-					offset, bytes);
+		node = rb_next(&last->offset_index);
+		if (!node) {
+			ret = -ENOSPC;
+			goto out;
+		}
+		next = rb_entry(node, struct btrfs_free_space, offset_index);
+
+		/*
+		 * we haven't filled the empty size and the window is
+		 * very large.  reset and try again
+		 */
+		if (next->offset - window_start > (bytes + empty_size) * 2) {
+			entry = next;
+			window_start = entry->offset;
+			window_free = entry->bytes;
+			last = entry;
+			max_extent = 0;
+			total_retries++;
+			if (total_retries % 256 == 0) {
+				if (min_bytes >= (bytes + empty_size)) {
+					ret = -ENOSPC;
+					goto out;
+				}
+				/*
+				 * grow our allocation a bit, we're not having
+				 * much luck
+				 */
+				min_bytes *= 2;
+				goto again;
+			}
+		} else {
+			last = next;
+			window_free += next->bytes;
+			if (entry->bytes > max_extent)
+				max_extent = entry->bytes;
+		}
+	}
+
+	cluster->window_start = entry->offset;
+
+	/*
+	 * now we've found our entries, pull them out of the free space
+	 * cache and put them into the cluster rbtree
+	 *
+	 * The cluster includes an rbtree, but only uses the offset index
+	 * of each free space cache entry.
+	 */
+	while(1) {
+		node = rb_next(&entry->offset_index);
+		unlink_free_space(block_group, entry);
+		ret = tree_insert_offset(&cluster->root, entry->offset,
+					 &entry->offset_index);
+		BUG_ON(ret);
+
+		if (!node || entry == last)
+			break;
+
+		entry = rb_entry(node, struct btrfs_free_space, offset_index);
+	}
+	ret = 0;
+	cluster->max_size = max_extent;
+	atomic_inc(&block_group->count);
+	list_add_tail(&cluster->block_group_list, &block_group->cluster_list);
+	cluster->block_group = block_group;
+out:
+	spin_unlock(&cluster->lock);
+	spin_unlock(&block_group->tree_lock);
 
 	return ret;
 }
+
+/*
+ * simple code to zero out a cluster
+ */
+void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster)
+{
+	spin_lock_init(&cluster->lock);
+	spin_lock_init(&cluster->refill_lock);
+	cluster->root.rb_node = NULL;
+	cluster->max_size = 0;
+	INIT_LIST_HEAD(&cluster->block_group_list);
+	cluster->block_group = NULL;
+}
+
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
new file mode 100644
index 000000000000..ab0bdc0a63ce
--- /dev/null
+++ b/fs/btrfs/free-space-cache.h
@@ -0,0 +1,44 @@
+/*
+ * Copyright (C) 2009 Oracle.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public
+ * License v2 as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public
+ * License along with this program; if not, write to the
+ * Free Software Foundation, Inc., 59 Temple Place - Suite 330,
+ * Boston, MA 021110-1307, USA.
+ */
+
+#ifndef __BTRFS_FREE_SPACE_CACHE
+#define __BTRFS_FREE_SPACE_CACHE
+
+int btrfs_add_free_space(struct btrfs_block_group_cache *block_group,
+			 u64 bytenr, u64 size);
+int btrfs_remove_free_space(struct btrfs_block_group_cache *block_group,
+			    u64 bytenr, u64 size);
+void btrfs_remove_free_space_cache(struct btrfs_block_group_cache
+				   *block_group);
+u64 btrfs_find_space_for_alloc(struct btrfs_block_group_cache *block_group,
+			       u64 offset, u64 bytes, u64 empty_size);
+void btrfs_dump_free_space(struct btrfs_block_group_cache *block_group,
+			   u64 bytes);
+u64 btrfs_block_group_free_space(struct btrfs_block_group_cache *block_group);
+int btrfs_find_space_cluster(struct btrfs_trans_handle *trans,
+			     struct btrfs_block_group_cache *block_group,
+			     struct btrfs_free_cluster *cluster,
+			     u64 offset, u64 bytes, u64 empty_size);
+void btrfs_init_free_cluster(struct btrfs_free_cluster *cluster);
+u64 btrfs_alloc_from_cluster(struct btrfs_block_group_cache *block_group,
+			     struct btrfs_free_cluster *cluster, u64 bytes,
+			     u64 min_start);
+int btrfs_return_cluster_to_free_space(
+			       struct btrfs_block_group_cache *block_group,
+			       struct btrfs_free_cluster *cluster);
+#endif
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 06d8db5afb08..a0d1dd492a58 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -3481,8 +3481,10 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 
 	if (dir) {
 		ret = btrfs_set_inode_index(dir, index);
-		if (ret)
+		if (ret) {
+			iput(inode);
 			return ERR_PTR(ret);
+		}
 	}
 	/*
 	 * index_cnt is ignored for everything but a dir,
@@ -3565,6 +3567,7 @@ fail:
 	if (dir)
 		BTRFS_I(dir)->index_cnt--;
 	btrfs_free_path(path);
+	iput(inode);
 	return ERR_PTR(ret);
 }
 
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index bca729fc80c8..7594bec1be10 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -267,7 +267,7 @@ static noinline int btrfs_mksubvol(struct path *parent, char *name,
 		goto out_dput;
 
 	if (!IS_POSIXACL(parent->dentry->d_inode))
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 
 	error = mnt_want_write(parent->mnt);
 	if (error)
diff --git a/fs/btrfs/locking.c b/fs/btrfs/locking.c
index a5310c0f41e2..1c36e5cd8f55 100644
--- a/fs/btrfs/locking.c
+++ b/fs/btrfs/locking.c
@@ -60,8 +60,8 @@ void btrfs_clear_lock_blocking(struct extent_buffer *eb)
 
 /*
  * unfortunately, many of the places that currently set a lock to blocking
- * don't end up blocking for every long, and often they don't block
- * at all.  For a dbench 50 run, if we don't spin one the blocking bit
+ * don't end up blocking for very long, and often they don't block
+ * at all.  For a dbench 50 run, if we don't spin on the blocking bit
  * at all, the context switch rate can jump up to 400,000/sec or more.
  *
  * So, we're still stuck with this crummy spin on the blocking bit,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index 19a4daf03ccb..9744af9d71e9 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -24,6 +24,7 @@
 #include <linux/highmem.h>
 #include <linux/time.h>
 #include <linux/init.h>
+#include <linux/seq_file.h>
 #include <linux/string.h>
 #include <linux/smp_lock.h>
 #include <linux/backing-dev.h>
@@ -66,7 +67,8 @@ static void btrfs_put_super(struct super_block *sb)
 enum {
 	Opt_degraded, Opt_subvol, Opt_device, Opt_nodatasum, Opt_nodatacow,
 	Opt_max_extent, Opt_max_inline, Opt_alloc_start, Opt_nobarrier,
-	Opt_ssd, Opt_thread_pool, Opt_noacl,  Opt_compress, Opt_err,
+	Opt_ssd, Opt_thread_pool, Opt_noacl,  Opt_compress, Opt_notreelog,
+	Opt_flushoncommit, Opt_err,
 };
 
 static match_table_t tokens = {
@@ -83,6 +85,8 @@ static match_table_t tokens = {
 	{Opt_compress, "compress"},
 	{Opt_ssd, "ssd"},
 	{Opt_noacl, "noacl"},
+	{Opt_notreelog, "notreelog"},
+	{Opt_flushoncommit, "flushoncommit"},
 	{Opt_err, NULL},
 };
 
@@ -222,6 +226,14 @@ int btrfs_parse_options(struct btrfs_root *root, char *options)
 		case Opt_noacl:
 			root->fs_info->sb->s_flags &= ~MS_POSIXACL;
 			break;
+		case Opt_notreelog:
+			printk(KERN_INFO "btrfs: disabling tree log\n");
+			btrfs_set_opt(info->mount_opt, NOTREELOG);
+			break;
+		case Opt_flushoncommit:
+			printk(KERN_INFO "btrfs: turning on flush-on-commit\n");
+			btrfs_set_opt(info->mount_opt, FLUSHONCOMMIT);
+			break;
 		default:
 			break;
 		}
@@ -363,9 +375,8 @@ fail_close:
 int btrfs_sync_fs(struct super_block *sb, int wait)
 {
 	struct btrfs_trans_handle *trans;
-	struct btrfs_root *root;
+	struct btrfs_root *root = btrfs_sb(sb);
 	int ret;
-	root = btrfs_sb(sb);
 
 	if (sb->s_flags & MS_RDONLY)
 		return 0;
@@ -385,6 +396,41 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 	return ret;
 }
 
+static int btrfs_show_options(struct seq_file *seq, struct vfsmount *vfs)
+{
+	struct btrfs_root *root = btrfs_sb(vfs->mnt_sb);
+	struct btrfs_fs_info *info = root->fs_info;
+
+	if (btrfs_test_opt(root, DEGRADED))
+		seq_puts(seq, ",degraded");
+	if (btrfs_test_opt(root, NODATASUM))
+		seq_puts(seq, ",nodatasum");
+	if (btrfs_test_opt(root, NODATACOW))
+		seq_puts(seq, ",nodatacow");
+	if (btrfs_test_opt(root, NOBARRIER))
+		seq_puts(seq, ",nobarrier");
+	if (info->max_extent != (u64)-1)
+		seq_printf(seq, ",max_extent=%llu", info->max_extent);
+	if (info->max_inline != 8192 * 1024)
+		seq_printf(seq, ",max_inline=%llu", info->max_inline);
+	if (info->alloc_start != 0)
+		seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
+	if (info->thread_pool_size !=  min_t(unsigned long,
+					     num_online_cpus() + 2, 8))
+		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
+	if (btrfs_test_opt(root, COMPRESS))
+		seq_puts(seq, ",compress");
+	if (btrfs_test_opt(root, SSD))
+		seq_puts(seq, ",ssd");
+	if (btrfs_test_opt(root, NOTREELOG))
+		seq_puts(seq, ",no-treelog");
+	if (btrfs_test_opt(root, FLUSHONCOMMIT))
+		seq_puts(seq, ",flush-on-commit");
+	if (!(root->fs_info->sb->s_flags & MS_POSIXACL))
+		seq_puts(seq, ",noacl");
+	return 0;
+}
+
 static void btrfs_write_super(struct super_block *sb)
 {
 	sb->s_dirt = 0;
@@ -630,7 +676,7 @@ static struct super_operations btrfs_super_ops = {
 	.put_super	= btrfs_put_super,
 	.write_super	= btrfs_write_super,
 	.sync_fs	= btrfs_sync_fs,
-	.show_options	= generic_show_options,
+	.show_options	= btrfs_show_options,
 	.write_inode	= btrfs_write_inode,
 	.dirty_inode	= btrfs_dirty_inode,
 	.alloc_inode	= btrfs_alloc_inode,
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 664782c6a2df..2869b3361eb6 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -53,8 +53,6 @@ static noinline int join_transaction(struct btrfs_root *root)
 					     GFP_NOFS);
 		BUG_ON(!cur_trans);
 		root->fs_info->generation++;
-		root->fs_info->last_alloc = 0;
-		root->fs_info->last_data_alloc = 0;
 		cur_trans->num_writers = 1;
 		cur_trans->num_joined = 0;
 		cur_trans->transid = root->fs_info->generation;
@@ -974,6 +972,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 	int ret;
 	int should_grow = 0;
 	unsigned long now = get_seconds();
+	int flush_on_commit = btrfs_test_opt(root, FLUSHONCOMMIT);
 
 	btrfs_run_ordered_operations(root, 0);
 
@@ -1053,7 +1052,9 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans,
 
 		mutex_unlock(&root->fs_info->trans_mutex);
 
-		if (snap_pending) {
+		if (flush_on_commit || snap_pending) {
+			if (flush_on_commit)
+				btrfs_start_delalloc_inodes(root);
 			ret = btrfs_wait_ordered_extents(root, 1);
 			BUG_ON(ret);
 		}
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index fc9b87a7975b..25f20ea11f27 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -262,11 +262,9 @@ static int process_one_buffer(struct btrfs_root *log,
 			      struct extent_buffer *eb,
 			      struct walk_control *wc, u64 gen)
 {
-	if (wc->pin) {
-		mutex_lock(&log->fs_info->pinned_mutex);
+	if (wc->pin)
 		btrfs_update_pinned_extents(log->fs_info->extent_root,
 					    eb->start, eb->len, 1);
-	}
 
 	if (btrfs_buffer_uptodate(eb, gen)) {
 		if (wc->write)
@@ -1224,8 +1222,7 @@ insert:
 	ret = insert_one_name(trans, root, path, key->objectid, key->offset,
 			      name, name_len, log_type, &log_key);
 
-	if (ret && ret != -ENOENT)
-		BUG();
+	BUG_ON(ret && ret != -ENOENT);
 	goto out;
 }
 
@@ -2900,6 +2897,11 @@ int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 
 	sb = inode->i_sb;
 
+	if (btrfs_test_opt(root, NOTREELOG)) {
+		ret = 1;
+		goto end_no_trans;
+	}
+
 	if (root->fs_info->last_trans_log_full_commit >
 	    root->fs_info->last_trans_committed) {
 		ret = 1;
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index dd06e18e5aac..e0913e469728 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -20,6 +20,7 @@
 #include <linux/buffer_head.h>
 #include <linux/blkdev.h>
 #include <linux/random.h>
+#include <linux/iocontext.h>
 #include <asm/div64.h>
 #include "compat.h"
 #include "ctree.h"
@@ -145,8 +146,9 @@ static noinline int run_scheduled_bios(struct btrfs_device *device)
 	int again = 0;
 	unsigned long num_run = 0;
 	unsigned long limit;
+	unsigned long last_waited = 0;
 
-	bdi = device->bdev->bd_inode->i_mapping->backing_dev_info;
+	bdi = blk_get_backing_dev_info(device->bdev);
 	fs_info = device->dev_root->fs_info;
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
@@ -207,7 +209,32 @@ loop_lock:
 		if (pending && bdi_write_congested(bdi) && num_run > 16 &&
 		    fs_info->fs_devices->open_devices > 1) {
 			struct bio *old_head;
+			struct io_context *ioc;
 
+			ioc = current->io_context;
+
+			/*
+			 * the main goal here is that we don't want to
+			 * block if we're going to be able to submit
+			 * more requests without blocking.
+			 *
+			 * This code does two great things, it pokes into
+			 * the elevator code from a filesystem _and_
+			 * it makes assumptions about how batching works.
+			 */
+			if (ioc && ioc->nr_batch_requests > 0 &&
+			    time_before(jiffies, ioc->last_waited + HZ/50UL) &&
+			    (last_waited == 0 ||
+			     ioc->last_waited == last_waited)) {
+				/*
+				 * we want to go through our batch of
+				 * requests and stop.  So, we copy out
+				 * the ioc->last_waited time and test
+				 * against it before looping
+				 */
+				last_waited = ioc->last_waited;
+				continue;
+			}
 			spin_lock(&device->io_lock);
 
 			old_head = device->pending_bios;
@@ -231,6 +258,18 @@ loop_lock:
 	if (device->pending_bios)
 		goto loop_lock;
 	spin_unlock(&device->io_lock);
+
+	/*
+	 * IO has already been through a long path to get here.  Checksumming,
+	 * async helper threads, perhaps compression.  We've done a pretty
+	 * good job of collecting a batch of IO and should just unplug
+	 * the device right away.
+	 *
+	 * This will help anyone who is waiting on the IO, they might have
+	 * already unplugged, but managed to do so before the bio they
+	 * cared about found its way down here.
+	 */
+	blk_run_backing_dev(bdi, NULL);
 done:
 	return 0;
 }
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 86c44e9ae110..2185de72ff7d 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -76,7 +76,7 @@ struct btrfs_device {
 struct btrfs_fs_devices {
 	u8 fsid[BTRFS_FSID_SIZE]; /* FS specific uuid */
 
-	/* the device with this id has the most recent coyp of the super */
+	/* the device with this id has the most recent copy of the super */
 	u64 latest_devid;
 	u64 latest_trans;
 	u64 num_devices;
diff --git a/fs/buffer.c b/fs/buffer.c
index f5f8b15a6e40..5d55a896ff78 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -199,13 +199,13 @@ __find_get_block_slow(struct block_device *bdev, sector_t block)
 	head = page_buffers(page);
 	bh = head;
 	do {
-		if (bh->b_blocknr == block) {
+		if (!buffer_mapped(bh))
+			all_mapped = 0;
+		else if (bh->b_blocknr == block) {
 			ret = bh;
 			get_bh(bh);
 			goto out_unlock;
 		}
-		if (!buffer_mapped(bh))
-			all_mapped = 0;
 		bh = bh->b_this_page;
 	} while (bh != head);
 
@@ -1595,6 +1595,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	struct buffer_head *bh, *head;
 	const unsigned blocksize = 1 << inode->i_blkbits;
 	int nr_underway = 0;
+	int write_op = (wbc->sync_mode == WB_SYNC_ALL ? WRITE_SYNC : WRITE);
 
 	BUG_ON(!PageLocked(page));
 
@@ -1686,7 +1687,7 @@ static int __block_write_full_page(struct inode *inode, struct page *page,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh(WRITE, bh);
+			submit_bh(write_op, bh);
 			nr_underway++;
 		}
 		bh = next;
@@ -1740,7 +1741,7 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh(WRITE, bh);
+			submit_bh(write_op, bh);
 			nr_underway++;
 		}
 		bh = next;
@@ -3315,7 +3316,6 @@ EXPORT_SYMBOL(cont_write_begin);
 EXPORT_SYMBOL(end_buffer_read_sync);
 EXPORT_SYMBOL(end_buffer_write_sync);
 EXPORT_SYMBOL(file_fsync);
-EXPORT_SYMBOL(fsync_bdev);
 EXPORT_SYMBOL(generic_block_bmap);
 EXPORT_SYMBOL(generic_cont_expand_simple);
 EXPORT_SYMBOL(init_buffer);
diff --git a/fs/cachefiles/Kconfig b/fs/cachefiles/Kconfig
new file mode 100644
index 000000000000..80e9c6167f0b
--- /dev/null
+++ b/fs/cachefiles/Kconfig
@@ -0,0 +1,39 @@
+
+config CACHEFILES
+	tristate "Filesystem caching on files"
+	depends on FSCACHE && BLOCK
+	help
+	  This permits use of a mounted filesystem as a cache for other
+	  filesystems - primarily networking filesystems - thus allowing fast
+	  local disk to enhance the speed of slower devices.
+
+	  See Documentation/filesystems/caching/cachefiles.txt for more
+	  information.
+
+config CACHEFILES_DEBUG
+	bool "Debug CacheFiles"
+	depends on CACHEFILES
+	help
+	  This permits debugging to be dynamically enabled in the filesystem
+	  caching on files module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/cachefiles/parameter/debug or
+	  by including a debugging specifier in /etc/cachefilesd.conf.
+
+config CACHEFILES_HISTOGRAM
+	bool "Gather latency information on CacheFiles"
+	depends on CACHEFILES && PROC_FS
+	help
+
+	  This option causes latency information to be gathered on CacheFiles
+	  operation and exported through file:
+
+		/proc/fs/cachefiles/histogram
+
+	  The generation of this histogram adds a certain amount of overhead to
+	  execution as there are a number of points at which data is gathered,
+	  and on a multi-CPU system these may be on cachelines that keep
+	  bouncing between CPUs.  On the other hand, the histogram may be
+	  useful for debugging purposes.  Saying 'N' here is recommended.
+
+	  See Documentation/filesystems/caching/cachefiles.txt for more
+	  information.
diff --git a/fs/cachefiles/Makefile b/fs/cachefiles/Makefile
new file mode 100644
index 000000000000..32cbab0ffce3
--- /dev/null
+++ b/fs/cachefiles/Makefile
@@ -0,0 +1,18 @@
+#
+# Makefile for caching in a mounted filesystem
+#
+
+cachefiles-y := \
+	bind.o \
+	daemon.o \
+	interface.o \
+	key.o \
+	main.o \
+	namei.o \
+	rdwr.o \
+	security.o \
+	xattr.o
+
+cachefiles-$(CONFIG_CACHEFILES_HISTOGRAM) += proc.o
+
+obj-$(CONFIG_CACHEFILES) := cachefiles.o
diff --git a/fs/cachefiles/bind.c b/fs/cachefiles/bind.c
new file mode 100644
index 000000000000..3797e0077b35
--- /dev/null
+++ b/fs/cachefiles/bind.c
@@ -0,0 +1,286 @@
+/* Bind and unbind a cache from the filesystem backing it
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/ctype.h>
+#include "internal.h"
+
+static int cachefiles_daemon_add_cache(struct cachefiles_cache *caches);
+
+/*
+ * bind a directory as a cache
+ */
+int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args)
+{
+	_enter("{%u,%u,%u,%u,%u,%u},%s",
+	       cache->frun_percent,
+	       cache->fcull_percent,
+	       cache->fstop_percent,
+	       cache->brun_percent,
+	       cache->bcull_percent,
+	       cache->bstop_percent,
+	       args);
+
+	/* start by checking things over */
+	ASSERT(cache->fstop_percent >= 0 &&
+	       cache->fstop_percent < cache->fcull_percent &&
+	       cache->fcull_percent < cache->frun_percent &&
+	       cache->frun_percent  < 100);
+
+	ASSERT(cache->bstop_percent >= 0 &&
+	       cache->bstop_percent < cache->bcull_percent &&
+	       cache->bcull_percent < cache->brun_percent &&
+	       cache->brun_percent  < 100);
+
+	if (*args) {
+		kerror("'bind' command doesn't take an argument");
+		return -EINVAL;
+	}
+
+	if (!cache->rootdirname) {
+		kerror("No cache directory specified");
+		return -EINVAL;
+	}
+
+	/* don't permit already bound caches to be re-bound */
+	if (test_bit(CACHEFILES_READY, &cache->flags)) {
+		kerror("Cache already bound");
+		return -EBUSY;
+	}
+
+	/* make sure we have copies of the tag and dirname strings */
+	if (!cache->tag) {
+		/* the tag string is released by the fops->release()
+		 * function, so we don't release it on error here */
+		cache->tag = kstrdup("CacheFiles", GFP_KERNEL);
+		if (!cache->tag)
+			return -ENOMEM;
+	}
+
+	/* add the cache */
+	return cachefiles_daemon_add_cache(cache);
+}
+
+/*
+ * add a cache
+ */
+static int cachefiles_daemon_add_cache(struct cachefiles_cache *cache)
+{
+	struct cachefiles_object *fsdef;
+	struct nameidata nd;
+	struct kstatfs stats;
+	struct dentry *graveyard, *cachedir, *root;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("");
+
+	/* we want to work under the module's security ID */
+	ret = cachefiles_get_security_ID(cache);
+	if (ret < 0)
+		return ret;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+
+	/* allocate the root index object */
+	ret = -ENOMEM;
+
+	fsdef = kmem_cache_alloc(cachefiles_object_jar, GFP_KERNEL);
+	if (!fsdef)
+		goto error_root_object;
+
+	ASSERTCMP(fsdef->backer, ==, NULL);
+
+	atomic_set(&fsdef->usage, 1);
+	fsdef->type = FSCACHE_COOKIE_TYPE_INDEX;
+
+	_debug("- fsdef %p", fsdef);
+
+	/* look up the directory at the root of the cache */
+	memset(&nd, 0, sizeof(nd));
+
+	ret = path_lookup(cache->rootdirname, LOOKUP_DIRECTORY, &nd);
+	if (ret < 0)
+		goto error_open_root;
+
+	cache->mnt = mntget(nd.path.mnt);
+	root = dget(nd.path.dentry);
+	path_put(&nd.path);
+
+	/* check parameters */
+	ret = -EOPNOTSUPP;
+	if (!root->d_inode ||
+	    !root->d_inode->i_op ||
+	    !root->d_inode->i_op->lookup ||
+	    !root->d_inode->i_op->mkdir ||
+	    !root->d_inode->i_op->setxattr ||
+	    !root->d_inode->i_op->getxattr ||
+	    !root->d_sb ||
+	    !root->d_sb->s_op ||
+	    !root->d_sb->s_op->statfs ||
+	    !root->d_sb->s_op->sync_fs)
+		goto error_unsupported;
+
+	ret = -EROFS;
+	if (root->d_sb->s_flags & MS_RDONLY)
+		goto error_unsupported;
+
+	/* determine the security of the on-disk cache as this governs
+	 * security ID of files we create */
+	ret = cachefiles_determine_cache_security(cache, root, &saved_cred);
+	if (ret < 0)
+		goto error_unsupported;
+
+	/* get the cache size and blocksize */
+	ret = vfs_statfs(root, &stats);
+	if (ret < 0)
+		goto error_unsupported;
+
+	ret = -ERANGE;
+	if (stats.f_bsize <= 0)
+		goto error_unsupported;
+
+	ret = -EOPNOTSUPP;
+	if (stats.f_bsize > PAGE_SIZE)
+		goto error_unsupported;
+
+	cache->bsize = stats.f_bsize;
+	cache->bshift = 0;
+	if (stats.f_bsize < PAGE_SIZE)
+		cache->bshift = PAGE_SHIFT - ilog2(stats.f_bsize);
+
+	_debug("blksize %u (shift %u)",
+	       cache->bsize, cache->bshift);
+
+	_debug("size %llu, avail %llu",
+	       (unsigned long long) stats.f_blocks,
+	       (unsigned long long) stats.f_bavail);
+
+	/* set up caching limits */
+	do_div(stats.f_files, 100);
+	cache->fstop = stats.f_files * cache->fstop_percent;
+	cache->fcull = stats.f_files * cache->fcull_percent;
+	cache->frun  = stats.f_files * cache->frun_percent;
+
+	_debug("limits {%llu,%llu,%llu} files",
+	       (unsigned long long) cache->frun,
+	       (unsigned long long) cache->fcull,
+	       (unsigned long long) cache->fstop);
+
+	stats.f_blocks >>= cache->bshift;
+	do_div(stats.f_blocks, 100);
+	cache->bstop = stats.f_blocks * cache->bstop_percent;
+	cache->bcull = stats.f_blocks * cache->bcull_percent;
+	cache->brun  = stats.f_blocks * cache->brun_percent;
+
+	_debug("limits {%llu,%llu,%llu} blocks",
+	       (unsigned long long) cache->brun,
+	       (unsigned long long) cache->bcull,
+	       (unsigned long long) cache->bstop);
+
+	/* get the cache directory and check its type */
+	cachedir = cachefiles_get_directory(cache, root, "cache");
+	if (IS_ERR(cachedir)) {
+		ret = PTR_ERR(cachedir);
+		goto error_unsupported;
+	}
+
+	fsdef->dentry = cachedir;
+	fsdef->fscache.cookie = NULL;
+
+	ret = cachefiles_check_object_type(fsdef);
+	if (ret < 0)
+		goto error_unsupported;
+
+	/* get the graveyard directory */
+	graveyard = cachefiles_get_directory(cache, root, "graveyard");
+	if (IS_ERR(graveyard)) {
+		ret = PTR_ERR(graveyard);
+		goto error_unsupported;
+	}
+
+	cache->graveyard = graveyard;
+
+	/* publish the cache */
+	fscache_init_cache(&cache->cache,
+			   &cachefiles_cache_ops,
+			   "%s",
+			   fsdef->dentry->d_sb->s_id);
+
+	fscache_object_init(&fsdef->fscache, NULL, &cache->cache);
+
+	ret = fscache_add_cache(&cache->cache, &fsdef->fscache, cache->tag);
+	if (ret < 0)
+		goto error_add_cache;
+
+	/* done */
+	set_bit(CACHEFILES_READY, &cache->flags);
+	dput(root);
+
+	printk(KERN_INFO "CacheFiles:"
+	       " File cache on %s registered\n",
+	       cache->cache.identifier);
+
+	/* check how much space the cache has */
+	cachefiles_has_space(cache, 0, 0);
+	cachefiles_end_secure(cache, saved_cred);
+	return 0;
+
+error_add_cache:
+	dput(cache->graveyard);
+	cache->graveyard = NULL;
+error_unsupported:
+	mntput(cache->mnt);
+	cache->mnt = NULL;
+	dput(fsdef->dentry);
+	fsdef->dentry = NULL;
+	dput(root);
+error_open_root:
+	kmem_cache_free(cachefiles_object_jar, fsdef);
+error_root_object:
+	cachefiles_end_secure(cache, saved_cred);
+	kerror("Failed to register: %d", ret);
+	return ret;
+}
+
+/*
+ * unbind a cache on fd release
+ */
+void cachefiles_daemon_unbind(struct cachefiles_cache *cache)
+{
+	_enter("");
+
+	if (test_bit(CACHEFILES_READY, &cache->flags)) {
+		printk(KERN_INFO "CacheFiles:"
+		       " File cache on %s unregistering\n",
+		       cache->cache.identifier);
+
+		fscache_withdraw_cache(&cache->cache);
+	}
+
+	dput(cache->graveyard);
+	mntput(cache->mnt);
+
+	kfree(cache->rootdirname);
+	kfree(cache->secctx);
+	kfree(cache->tag);
+
+	_leave("");
+}
diff --git a/fs/cachefiles/daemon.c b/fs/cachefiles/daemon.c
new file mode 100644
index 000000000000..4618516dd994
--- /dev/null
+++ b/fs/cachefiles/daemon.c
@@ -0,0 +1,755 @@
+/* Daemon interface
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/poll.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/ctype.h>
+#include <linux/fs_struct.h>
+#include "internal.h"
+
+static int cachefiles_daemon_open(struct inode *, struct file *);
+static int cachefiles_daemon_release(struct inode *, struct file *);
+static ssize_t cachefiles_daemon_read(struct file *, char __user *, size_t,
+				      loff_t *);
+static ssize_t cachefiles_daemon_write(struct file *, const char __user *,
+				       size_t, loff_t *);
+static unsigned int cachefiles_daemon_poll(struct file *,
+					   struct poll_table_struct *);
+static int cachefiles_daemon_frun(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_fcull(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_fstop(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_brun(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_bcull(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_bstop(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_cull(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_debug(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_dir(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_inuse(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_secctx(struct cachefiles_cache *, char *);
+static int cachefiles_daemon_tag(struct cachefiles_cache *, char *);
+
+static unsigned long cachefiles_open;
+
+const struct file_operations cachefiles_daemon_fops = {
+	.owner		= THIS_MODULE,
+	.open		= cachefiles_daemon_open,
+	.release	= cachefiles_daemon_release,
+	.read		= cachefiles_daemon_read,
+	.write		= cachefiles_daemon_write,
+	.poll		= cachefiles_daemon_poll,
+};
+
+struct cachefiles_daemon_cmd {
+	char name[8];
+	int (*handler)(struct cachefiles_cache *cache, char *args);
+};
+
+static const struct cachefiles_daemon_cmd cachefiles_daemon_cmds[] = {
+	{ "bind",	cachefiles_daemon_bind		},
+	{ "brun",	cachefiles_daemon_brun		},
+	{ "bcull",	cachefiles_daemon_bcull		},
+	{ "bstop",	cachefiles_daemon_bstop		},
+	{ "cull",	cachefiles_daemon_cull		},
+	{ "debug",	cachefiles_daemon_debug		},
+	{ "dir",	cachefiles_daemon_dir		},
+	{ "frun",	cachefiles_daemon_frun		},
+	{ "fcull",	cachefiles_daemon_fcull		},
+	{ "fstop",	cachefiles_daemon_fstop		},
+	{ "inuse",	cachefiles_daemon_inuse		},
+	{ "secctx",	cachefiles_daemon_secctx	},
+	{ "tag",	cachefiles_daemon_tag		},
+	{ "",		NULL				}
+};
+
+
+/*
+ * do various checks
+ */
+static int cachefiles_daemon_open(struct inode *inode, struct file *file)
+{
+	struct cachefiles_cache *cache;
+
+	_enter("");
+
+	/* only the superuser may do this */
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	/* the cachefiles device may only be open once at a time */
+	if (xchg(&cachefiles_open, 1) == 1)
+		return -EBUSY;
+
+	/* allocate a cache record */
+	cache = kzalloc(sizeof(struct cachefiles_cache), GFP_KERNEL);
+	if (!cache) {
+		cachefiles_open = 0;
+		return -ENOMEM;
+	}
+
+	mutex_init(&cache->daemon_mutex);
+	cache->active_nodes = RB_ROOT;
+	rwlock_init(&cache->active_lock);
+	init_waitqueue_head(&cache->daemon_pollwq);
+
+	/* set default caching limits
+	 * - limit at 1% free space and/or free files
+	 * - cull below 5% free space and/or free files
+	 * - cease culling above 7% free space and/or free files
+	 */
+	cache->frun_percent = 7;
+	cache->fcull_percent = 5;
+	cache->fstop_percent = 1;
+	cache->brun_percent = 7;
+	cache->bcull_percent = 5;
+	cache->bstop_percent = 1;
+
+	file->private_data = cache;
+	cache->cachefilesd = file;
+	return 0;
+}
+
+/*
+ * release a cache
+ */
+static int cachefiles_daemon_release(struct inode *inode, struct file *file)
+{
+	struct cachefiles_cache *cache = file->private_data;
+
+	_enter("");
+
+	ASSERT(cache);
+
+	set_bit(CACHEFILES_DEAD, &cache->flags);
+
+	cachefiles_daemon_unbind(cache);
+
+	ASSERT(!cache->active_nodes.rb_node);
+
+	/* clean up the control file interface */
+	cache->cachefilesd = NULL;
+	file->private_data = NULL;
+	cachefiles_open = 0;
+
+	kfree(cache);
+
+	_leave("");
+	return 0;
+}
+
+/*
+ * read the cache state
+ */
+static ssize_t cachefiles_daemon_read(struct file *file, char __user *_buffer,
+				      size_t buflen, loff_t *pos)
+{
+	struct cachefiles_cache *cache = file->private_data;
+	char buffer[256];
+	int n;
+
+	//_enter(",,%zu,", buflen);
+
+	if (!test_bit(CACHEFILES_READY, &cache->flags))
+		return 0;
+
+	/* check how much space the cache has */
+	cachefiles_has_space(cache, 0, 0);
+
+	/* summarise */
+	clear_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
+
+	n = snprintf(buffer, sizeof(buffer),
+		     "cull=%c"
+		     " frun=%llx"
+		     " fcull=%llx"
+		     " fstop=%llx"
+		     " brun=%llx"
+		     " bcull=%llx"
+		     " bstop=%llx",
+		     test_bit(CACHEFILES_CULLING, &cache->flags) ? '1' : '0',
+		     (unsigned long long) cache->frun,
+		     (unsigned long long) cache->fcull,
+		     (unsigned long long) cache->fstop,
+		     (unsigned long long) cache->brun,
+		     (unsigned long long) cache->bcull,
+		     (unsigned long long) cache->bstop
+		     );
+
+	if (n > buflen)
+		return -EMSGSIZE;
+
+	if (copy_to_user(_buffer, buffer, n) != 0)
+		return -EFAULT;
+
+	return n;
+}
+
+/*
+ * command the cache
+ */
+static ssize_t cachefiles_daemon_write(struct file *file,
+				       const char __user *_data,
+				       size_t datalen,
+				       loff_t *pos)
+{
+	const struct cachefiles_daemon_cmd *cmd;
+	struct cachefiles_cache *cache = file->private_data;
+	ssize_t ret;
+	char *data, *args, *cp;
+
+	//_enter(",,%zu,", datalen);
+
+	ASSERT(cache);
+
+	if (test_bit(CACHEFILES_DEAD, &cache->flags))
+		return -EIO;
+
+	if (datalen < 0 || datalen > PAGE_SIZE - 1)
+		return -EOPNOTSUPP;
+
+	/* drag the command string into the kernel so we can parse it */
+	data = kmalloc(datalen + 1, GFP_KERNEL);
+	if (!data)
+		return -ENOMEM;
+
+	ret = -EFAULT;
+	if (copy_from_user(data, _data, datalen) != 0)
+		goto error;
+
+	data[datalen] = '\0';
+
+	ret = -EINVAL;
+	if (memchr(data, '\0', datalen))
+		goto error;
+
+	/* strip any newline */
+	cp = memchr(data, '\n', datalen);
+	if (cp) {
+		if (cp == data)
+			goto error;
+
+		*cp = '\0';
+	}
+
+	/* parse the command */
+	ret = -EOPNOTSUPP;
+
+	for (args = data; *args; args++)
+		if (isspace(*args))
+			break;
+	if (*args) {
+		if (args == data)
+			goto error;
+		*args = '\0';
+		for (args++; isspace(*args); args++)
+			continue;
+	}
+
+	/* run the appropriate command handler */
+	for (cmd = cachefiles_daemon_cmds; cmd->name[0]; cmd++)
+		if (strcmp(cmd->name, data) == 0)
+			goto found_command;
+
+error:
+	kfree(data);
+	//_leave(" = %zd", ret);
+	return ret;
+
+found_command:
+	mutex_lock(&cache->daemon_mutex);
+
+	ret = -EIO;
+	if (!test_bit(CACHEFILES_DEAD, &cache->flags))
+		ret = cmd->handler(cache, args);
+
+	mutex_unlock(&cache->daemon_mutex);
+
+	if (ret == 0)
+		ret = datalen;
+	goto error;
+}
+
+/*
+ * poll for culling state
+ * - use POLLOUT to indicate culling state
+ */
+static unsigned int cachefiles_daemon_poll(struct file *file,
+					   struct poll_table_struct *poll)
+{
+	struct cachefiles_cache *cache = file->private_data;
+	unsigned int mask;
+
+	poll_wait(file, &cache->daemon_pollwq, poll);
+	mask = 0;
+
+	if (test_bit(CACHEFILES_STATE_CHANGED, &cache->flags))
+		mask |= POLLIN;
+
+	if (test_bit(CACHEFILES_CULLING, &cache->flags))
+		mask |= POLLOUT;
+
+	return mask;
+}
+
+/*
+ * give a range error for cache space constraints
+ * - can be tail-called
+ */
+static int cachefiles_daemon_range_error(struct cachefiles_cache *cache,
+					 char *args)
+{
+	kerror("Free space limits must be in range"
+	       " 0%%<=stop<cull<run<100%%");
+
+	return -EINVAL;
+}
+
+/*
+ * set the percentage of files at which to stop culling
+ * - command: "frun <N>%"
+ */
+static int cachefiles_daemon_frun(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long frun;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	frun = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (frun <= cache->fcull_percent || frun >= 100)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->frun_percent = frun;
+	return 0;
+}
+
+/*
+ * set the percentage of files at which to start culling
+ * - command: "fcull <N>%"
+ */
+static int cachefiles_daemon_fcull(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long fcull;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	fcull = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (fcull <= cache->fstop_percent || fcull >= cache->frun_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->fcull_percent = fcull;
+	return 0;
+}
+
+/*
+ * set the percentage of files at which to stop allocating
+ * - command: "fstop <N>%"
+ */
+static int cachefiles_daemon_fstop(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long fstop;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	fstop = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (fstop < 0 || fstop >= cache->fcull_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->fstop_percent = fstop;
+	return 0;
+}
+
+/*
+ * set the percentage of blocks at which to stop culling
+ * - command: "brun <N>%"
+ */
+static int cachefiles_daemon_brun(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long brun;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	brun = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (brun <= cache->bcull_percent || brun >= 100)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->brun_percent = brun;
+	return 0;
+}
+
+/*
+ * set the percentage of blocks at which to start culling
+ * - command: "bcull <N>%"
+ */
+static int cachefiles_daemon_bcull(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long bcull;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	bcull = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (bcull <= cache->bstop_percent || bcull >= cache->brun_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->bcull_percent = bcull;
+	return 0;
+}
+
+/*
+ * set the percentage of blocks at which to stop allocating
+ * - command: "bstop <N>%"
+ */
+static int cachefiles_daemon_bstop(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long bstop;
+
+	_enter(",%s", args);
+
+	if (!*args)
+		return -EINVAL;
+
+	bstop = simple_strtoul(args, &args, 10);
+	if (args[0] != '%' || args[1] != '\0')
+		return -EINVAL;
+
+	if (bstop < 0 || bstop >= cache->bcull_percent)
+		return cachefiles_daemon_range_error(cache, args);
+
+	cache->bstop_percent = bstop;
+	return 0;
+}
+
+/*
+ * set the cache directory
+ * - command: "dir <name>"
+ */
+static int cachefiles_daemon_dir(struct cachefiles_cache *cache, char *args)
+{
+	char *dir;
+
+	_enter(",%s", args);
+
+	if (!*args) {
+		kerror("Empty directory specified");
+		return -EINVAL;
+	}
+
+	if (cache->rootdirname) {
+		kerror("Second cache directory specified");
+		return -EEXIST;
+	}
+
+	dir = kstrdup(args, GFP_KERNEL);
+	if (!dir)
+		return -ENOMEM;
+
+	cache->rootdirname = dir;
+	return 0;
+}
+
+/*
+ * set the cache security context
+ * - command: "secctx <ctx>"
+ */
+static int cachefiles_daemon_secctx(struct cachefiles_cache *cache, char *args)
+{
+	char *secctx;
+
+	_enter(",%s", args);
+
+	if (!*args) {
+		kerror("Empty security context specified");
+		return -EINVAL;
+	}
+
+	if (cache->secctx) {
+		kerror("Second security context specified");
+		return -EINVAL;
+	}
+
+	secctx = kstrdup(args, GFP_KERNEL);
+	if (!secctx)
+		return -ENOMEM;
+
+	cache->secctx = secctx;
+	return 0;
+}
+
+/*
+ * set the cache tag
+ * - command: "tag <name>"
+ */
+static int cachefiles_daemon_tag(struct cachefiles_cache *cache, char *args)
+{
+	char *tag;
+
+	_enter(",%s", args);
+
+	if (!*args) {
+		kerror("Empty tag specified");
+		return -EINVAL;
+	}
+
+	if (cache->tag)
+		return -EEXIST;
+
+	tag = kstrdup(args, GFP_KERNEL);
+	if (!tag)
+		return -ENOMEM;
+
+	cache->tag = tag;
+	return 0;
+}
+
+/*
+ * request a node in the cache be culled from the current working directory
+ * - command: "cull <name>"
+ */
+static int cachefiles_daemon_cull(struct cachefiles_cache *cache, char *args)
+{
+	struct fs_struct *fs;
+	struct dentry *dir;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter(",%s", args);
+
+	if (strchr(args, '/'))
+		goto inval;
+
+	if (!test_bit(CACHEFILES_READY, &cache->flags)) {
+		kerror("cull applied to unready cache");
+		return -EIO;
+	}
+
+	if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+		kerror("cull applied to dead cache");
+		return -EIO;
+	}
+
+	/* extract the directory dentry from the cwd */
+	fs = current->fs;
+	read_lock(&fs->lock);
+	dir = dget(fs->pwd.dentry);
+	read_unlock(&fs->lock);
+
+	if (!S_ISDIR(dir->d_inode->i_mode))
+		goto notdir;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_cull(cache, dir, args);
+	cachefiles_end_secure(cache, saved_cred);
+
+	dput(dir);
+	_leave(" = %d", ret);
+	return ret;
+
+notdir:
+	dput(dir);
+	kerror("cull command requires dirfd to be a directory");
+	return -ENOTDIR;
+
+inval:
+	kerror("cull command requires dirfd and filename");
+	return -EINVAL;
+}
+
+/*
+ * set debugging mode
+ * - command: "debug <mask>"
+ */
+static int cachefiles_daemon_debug(struct cachefiles_cache *cache, char *args)
+{
+	unsigned long mask;
+
+	_enter(",%s", args);
+
+	mask = simple_strtoul(args, &args, 0);
+	if (args[0] != '\0')
+		goto inval;
+
+	cachefiles_debug = mask;
+	_leave(" = 0");
+	return 0;
+
+inval:
+	kerror("debug command requires mask");
+	return -EINVAL;
+}
+
+/*
+ * find out whether an object in the current working directory is in use or not
+ * - command: "inuse <name>"
+ */
+static int cachefiles_daemon_inuse(struct cachefiles_cache *cache, char *args)
+{
+	struct fs_struct *fs;
+	struct dentry *dir;
+	const struct cred *saved_cred;
+	int ret;
+
+	//_enter(",%s", args);
+
+	if (strchr(args, '/'))
+		goto inval;
+
+	if (!test_bit(CACHEFILES_READY, &cache->flags)) {
+		kerror("inuse applied to unready cache");
+		return -EIO;
+	}
+
+	if (test_bit(CACHEFILES_DEAD, &cache->flags)) {
+		kerror("inuse applied to dead cache");
+		return -EIO;
+	}
+
+	/* extract the directory dentry from the cwd */
+	fs = current->fs;
+	read_lock(&fs->lock);
+	dir = dget(fs->pwd.dentry);
+	read_unlock(&fs->lock);
+
+	if (!S_ISDIR(dir->d_inode->i_mode))
+		goto notdir;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_check_in_use(cache, dir, args);
+	cachefiles_end_secure(cache, saved_cred);
+
+	dput(dir);
+	//_leave(" = %d", ret);
+	return ret;
+
+notdir:
+	dput(dir);
+	kerror("inuse command requires dirfd to be a directory");
+	return -ENOTDIR;
+
+inval:
+	kerror("inuse command requires dirfd and filename");
+	return -EINVAL;
+}
+
+/*
+ * see if we have space for a number of pages and/or a number of files in the
+ * cache
+ */
+int cachefiles_has_space(struct cachefiles_cache *cache,
+			 unsigned fnr, unsigned bnr)
+{
+	struct kstatfs stats;
+	int ret;
+
+	//_enter("{%llu,%llu,%llu,%llu,%llu,%llu},%u,%u",
+	//       (unsigned long long) cache->frun,
+	//       (unsigned long long) cache->fcull,
+	//       (unsigned long long) cache->fstop,
+	//       (unsigned long long) cache->brun,
+	//       (unsigned long long) cache->bcull,
+	//       (unsigned long long) cache->bstop,
+	//       fnr, bnr);
+
+	/* find out how many pages of blockdev are available */
+	memset(&stats, 0, sizeof(stats));
+
+	ret = vfs_statfs(cache->mnt->mnt_root, &stats);
+	if (ret < 0) {
+		if (ret == -EIO)
+			cachefiles_io_error(cache, "statfs failed");
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	stats.f_bavail >>= cache->bshift;
+
+	//_debug("avail %llu,%llu",
+	//       (unsigned long long) stats.f_ffree,
+	//       (unsigned long long) stats.f_bavail);
+
+	/* see if there is sufficient space */
+	if (stats.f_ffree > fnr)
+		stats.f_ffree -= fnr;
+	else
+		stats.f_ffree = 0;
+
+	if (stats.f_bavail > bnr)
+		stats.f_bavail -= bnr;
+	else
+		stats.f_bavail = 0;
+
+	ret = -ENOBUFS;
+	if (stats.f_ffree < cache->fstop ||
+	    stats.f_bavail < cache->bstop)
+		goto begin_cull;
+
+	ret = 0;
+	if (stats.f_ffree < cache->fcull ||
+	    stats.f_bavail < cache->bcull)
+		goto begin_cull;
+
+	if (test_bit(CACHEFILES_CULLING, &cache->flags) &&
+	    stats.f_ffree >= cache->frun &&
+	    stats.f_bavail >= cache->brun &&
+	    test_and_clear_bit(CACHEFILES_CULLING, &cache->flags)
+	    ) {
+		_debug("cease culling");
+		cachefiles_state_changed(cache);
+	}
+
+	//_leave(" = 0");
+	return 0;
+
+begin_cull:
+	if (!test_and_set_bit(CACHEFILES_CULLING, &cache->flags)) {
+		_debug("### CULL CACHE ###");
+		cachefiles_state_changed(cache);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/cachefiles/interface.c b/fs/cachefiles/interface.c
new file mode 100644
index 000000000000..1e962348d111
--- /dev/null
+++ b/fs/cachefiles/interface.c
@@ -0,0 +1,449 @@
+/* FS-Cache interface to CacheFiles
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/mount.h>
+#include <linux/buffer_head.h>
+#include "internal.h"
+
+#define list_to_page(head) (list_entry((head)->prev, struct page, lru))
+
+struct cachefiles_lookup_data {
+	struct cachefiles_xattr	*auxdata;	/* auxiliary data */
+	char			*key;		/* key path */
+};
+
+static int cachefiles_attr_changed(struct fscache_object *_object);
+
+/*
+ * allocate an object record for a cookie lookup and prepare the lookup data
+ */
+static struct fscache_object *cachefiles_alloc_object(
+	struct fscache_cache *_cache,
+	struct fscache_cookie *cookie)
+{
+	struct cachefiles_lookup_data *lookup_data;
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct cachefiles_xattr *auxdata;
+	unsigned keylen, auxlen;
+	void *buffer;
+	char *key;
+
+	cache = container_of(_cache, struct cachefiles_cache, cache);
+
+	_enter("{%s},%p,", cache->cache.identifier, cookie);
+
+	lookup_data = kmalloc(sizeof(*lookup_data), GFP_KERNEL);
+	if (!lookup_data)
+		goto nomem_lookup_data;
+
+	/* create a new object record and a temporary leaf image */
+	object = kmem_cache_alloc(cachefiles_object_jar, GFP_KERNEL);
+	if (!object)
+		goto nomem_object;
+
+	ASSERTCMP(object->backer, ==, NULL);
+
+	BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
+	atomic_set(&object->usage, 1);
+
+	fscache_object_init(&object->fscache, cookie, &cache->cache);
+
+	object->type = cookie->def->type;
+
+	/* get hold of the raw key
+	 * - stick the length on the front and leave space on the back for the
+	 *   encoder
+	 */
+	buffer = kmalloc((2 + 512) + 3, GFP_KERNEL);
+	if (!buffer)
+		goto nomem_buffer;
+
+	keylen = cookie->def->get_key(cookie->netfs_data, buffer + 2, 512);
+	ASSERTCMP(keylen, <, 512);
+
+	*(uint16_t *)buffer = keylen;
+	((char *)buffer)[keylen + 2] = 0;
+	((char *)buffer)[keylen + 3] = 0;
+	((char *)buffer)[keylen + 4] = 0;
+
+	/* turn the raw key into something that can work with as a filename */
+	key = cachefiles_cook_key(buffer, keylen + 2, object->type);
+	if (!key)
+		goto nomem_key;
+
+	/* get hold of the auxiliary data and prepend the object type */
+	auxdata = buffer;
+	auxlen = 0;
+	if (cookie->def->get_aux) {
+		auxlen = cookie->def->get_aux(cookie->netfs_data,
+					      auxdata->data, 511);
+		ASSERTCMP(auxlen, <, 511);
+	}
+
+	auxdata->len = auxlen + 1;
+	auxdata->type = cookie->def->type;
+
+	lookup_data->auxdata = auxdata;
+	lookup_data->key = key;
+	object->lookup_data = lookup_data;
+
+	_leave(" = %p [%p]", &object->fscache, lookup_data);
+	return &object->fscache;
+
+nomem_key:
+	kfree(buffer);
+nomem_buffer:
+	BUG_ON(test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
+	kmem_cache_free(cachefiles_object_jar, object);
+	fscache_object_destroyed(&cache->cache);
+nomem_object:
+	kfree(lookup_data);
+nomem_lookup_data:
+	_leave(" = -ENOMEM");
+	return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * attempt to look up the nominated node in this cache
+ */
+static void cachefiles_lookup_object(struct fscache_object *_object)
+{
+	struct cachefiles_lookup_data *lookup_data;
+	struct cachefiles_object *parent, *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("{OBJ%x}", _object->debug_id);
+
+	cache = container_of(_object->cache, struct cachefiles_cache, cache);
+	parent = container_of(_object->parent,
+			      struct cachefiles_object, fscache);
+	object = container_of(_object, struct cachefiles_object, fscache);
+	lookup_data = object->lookup_data;
+
+	ASSERTCMP(lookup_data, !=, NULL);
+
+	/* look up the key, creating any missing bits */
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = cachefiles_walk_to_object(parent, object,
+					lookup_data->key,
+					lookup_data->auxdata);
+	cachefiles_end_secure(cache, saved_cred);
+
+	/* polish off by setting the attributes of non-index files */
+	if (ret == 0 &&
+	    object->fscache.cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX)
+		cachefiles_attr_changed(&object->fscache);
+
+	if (ret < 0) {
+		printk(KERN_WARNING "CacheFiles: Lookup failed error %d\n",
+		       ret);
+		fscache_object_lookup_error(&object->fscache);
+	}
+
+	_leave(" [%d]", ret);
+}
+
+/*
+ * indication of lookup completion
+ */
+static void cachefiles_lookup_complete(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%p}", object->fscache.debug_id, object->lookup_data);
+
+	if (object->lookup_data) {
+		kfree(object->lookup_data->key);
+		kfree(object->lookup_data->auxdata);
+		kfree(object->lookup_data);
+		object->lookup_data = NULL;
+	}
+}
+
+/*
+ * increment the usage count on an inode object (may fail if unmounting)
+ */
+static
+struct fscache_object *cachefiles_grab_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object =
+		container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%d}", _object->debug_id, atomic_read(&object->usage));
+
+#ifdef CACHEFILES_DEBUG_SLAB
+	ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
+#endif
+
+	atomic_inc(&object->usage);
+	return &object->fscache;
+}
+
+/*
+ * update the auxilliary data for an object object on disk
+ */
+static void cachefiles_update_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_xattr *auxdata;
+	struct cachefiles_cache *cache;
+	struct fscache_cookie *cookie;
+	const struct cred *saved_cred;
+	unsigned auxlen;
+
+	_enter("{OBJ%x}", _object->debug_id);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache, struct cachefiles_cache,
+			     cache);
+	cookie = object->fscache.cookie;
+
+	if (!cookie->def->get_aux) {
+		_leave(" [no aux]");
+		return;
+	}
+
+	auxdata = kmalloc(2 + 512 + 3, GFP_KERNEL);
+	if (!auxdata) {
+		_leave(" [nomem]");
+		return;
+	}
+
+	auxlen = cookie->def->get_aux(cookie->netfs_data, auxdata->data, 511);
+	ASSERTCMP(auxlen, <, 511);
+
+	auxdata->len = auxlen + 1;
+	auxdata->type = cookie->def->type;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	cachefiles_update_object_xattr(object, auxdata);
+	cachefiles_end_secure(cache, saved_cred);
+	kfree(auxdata);
+	_leave("");
+}
+
+/*
+ * discard the resources pinned by an object and effect retirement if
+ * requested
+ */
+static void cachefiles_drop_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+
+	ASSERT(_object);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%d}",
+	       object->fscache.debug_id, atomic_read(&object->usage));
+
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+#ifdef CACHEFILES_DEBUG_SLAB
+	ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
+#endif
+
+	/* delete retired objects */
+	if (object->fscache.state == FSCACHE_OBJECT_RECYCLING &&
+	    _object != cache->cache.fsdef
+	    ) {
+		_debug("- retire object OBJ%x", object->fscache.debug_id);
+		cachefiles_begin_secure(cache, &saved_cred);
+		cachefiles_delete_object(cache, object);
+		cachefiles_end_secure(cache, saved_cred);
+	}
+
+	/* close the filesystem stuff attached to the object */
+	if (object->backer != object->dentry)
+		dput(object->backer);
+	object->backer = NULL;
+
+	/* note that the object is now inactive */
+	if (test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags)) {
+		write_lock(&cache->active_lock);
+		if (!test_and_clear_bit(CACHEFILES_OBJECT_ACTIVE,
+					&object->flags))
+			BUG();
+		rb_erase(&object->active_node, &cache->active_nodes);
+		wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+		write_unlock(&cache->active_lock);
+	}
+
+	dput(object->dentry);
+	object->dentry = NULL;
+
+	_leave("");
+}
+
+/*
+ * dispose of a reference to an object
+ */
+static void cachefiles_put_object(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct fscache_cache *cache;
+
+	ASSERT(_object);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+
+	_enter("{OBJ%x,%d}",
+	       object->fscache.debug_id, atomic_read(&object->usage));
+
+#ifdef CACHEFILES_DEBUG_SLAB
+	ASSERT((atomic_read(&object->usage) & 0xffff0000) != 0x6b6b0000);
+#endif
+
+	ASSERTIFCMP(object->fscache.parent,
+		    object->fscache.parent->n_children, >, 0);
+
+	if (atomic_dec_and_test(&object->usage)) {
+		_debug("- kill object OBJ%x", object->fscache.debug_id);
+
+		ASSERT(!test_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags));
+		ASSERTCMP(object->fscache.parent, ==, NULL);
+		ASSERTCMP(object->backer, ==, NULL);
+		ASSERTCMP(object->dentry, ==, NULL);
+		ASSERTCMP(object->fscache.n_ops, ==, 0);
+		ASSERTCMP(object->fscache.n_children, ==, 0);
+
+		if (object->lookup_data) {
+			kfree(object->lookup_data->key);
+			kfree(object->lookup_data->auxdata);
+			kfree(object->lookup_data);
+			object->lookup_data = NULL;
+		}
+
+		cache = object->fscache.cache;
+		kmem_cache_free(cachefiles_object_jar, object);
+		fscache_object_destroyed(cache);
+	}
+
+	_leave("");
+}
+
+/*
+ * sync a cache
+ */
+static void cachefiles_sync_cache(struct fscache_cache *_cache)
+{
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	int ret;
+
+	_enter("%p", _cache);
+
+	cache = container_of(_cache, struct cachefiles_cache, cache);
+
+	/* make sure all pages pinned by operations on behalf of the netfs are
+	 * written to disc */
+	cachefiles_begin_secure(cache, &saved_cred);
+	ret = fsync_super(cache->mnt->mnt_sb);
+	cachefiles_end_secure(cache, saved_cred);
+
+	if (ret == -EIO)
+		cachefiles_io_error(cache,
+				    "Attempt to sync backing fs superblock"
+				    " returned error %d",
+				    ret);
+}
+
+/*
+ * notification the attributes on an object have changed
+ * - called with reads/writes excluded by FS-Cache
+ */
+static int cachefiles_attr_changed(struct fscache_object *_object)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	const struct cred *saved_cred;
+	struct iattr newattrs;
+	uint64_t ni_size;
+	loff_t oi_size;
+	int ret;
+
+	_object->cookie->def->get_attr(_object->cookie->netfs_data, &ni_size);
+
+	_enter("{OBJ%x},[%llu]",
+	       _object->debug_id, (unsigned long long) ni_size);
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	if (ni_size == object->i_size)
+		return 0;
+
+	if (!object->backer)
+		return -ENOBUFS;
+
+	ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+
+	fscache_set_store_limit(&object->fscache, ni_size);
+
+	oi_size = i_size_read(object->backer->d_inode);
+	if (oi_size == ni_size)
+		return 0;
+
+	newattrs.ia_size = ni_size;
+	newattrs.ia_valid = ATTR_SIZE;
+
+	cachefiles_begin_secure(cache, &saved_cred);
+	mutex_lock(&object->backer->d_inode->i_mutex);
+	ret = notify_change(object->backer, &newattrs);
+	mutex_unlock(&object->backer->d_inode->i_mutex);
+	cachefiles_end_secure(cache, saved_cred);
+
+	if (ret == -EIO) {
+		fscache_set_store_limit(&object->fscache, 0);
+		cachefiles_io_error_obj(object, "Size set failed");
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * dissociate a cache from all the pages it was backing
+ */
+static void cachefiles_dissociate_pages(struct fscache_cache *cache)
+{
+	_enter("");
+}
+
+const struct fscache_cache_ops cachefiles_cache_ops = {
+	.name			= "cachefiles",
+	.alloc_object		= cachefiles_alloc_object,
+	.lookup_object		= cachefiles_lookup_object,
+	.lookup_complete	= cachefiles_lookup_complete,
+	.grab_object		= cachefiles_grab_object,
+	.update_object		= cachefiles_update_object,
+	.drop_object		= cachefiles_drop_object,
+	.put_object		= cachefiles_put_object,
+	.sync_cache		= cachefiles_sync_cache,
+	.attr_changed		= cachefiles_attr_changed,
+	.read_or_alloc_page	= cachefiles_read_or_alloc_page,
+	.read_or_alloc_pages	= cachefiles_read_or_alloc_pages,
+	.allocate_page		= cachefiles_allocate_page,
+	.allocate_pages		= cachefiles_allocate_pages,
+	.write_page		= cachefiles_write_page,
+	.uncache_page		= cachefiles_uncache_page,
+	.dissociate_pages	= cachefiles_dissociate_pages,
+};
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
new file mode 100644
index 000000000000..19218e1463d6
--- /dev/null
+++ b/fs/cachefiles/internal.h
@@ -0,0 +1,360 @@
+/* General netfs cache on cache files internal defs
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/fscache-cache.h>
+#include <linux/timer.h>
+#include <linux/wait.h>
+#include <linux/workqueue.h>
+#include <linux/security.h>
+
+struct cachefiles_cache;
+struct cachefiles_object;
+
+extern unsigned cachefiles_debug;
+#define CACHEFILES_DEBUG_KENTER	1
+#define CACHEFILES_DEBUG_KLEAVE	2
+#define CACHEFILES_DEBUG_KDEBUG	4
+
+/*
+ * node records
+ */
+struct cachefiles_object {
+	struct fscache_object		fscache;	/* fscache handle */
+	struct cachefiles_lookup_data	*lookup_data;	/* cached lookup data */
+	struct dentry			*dentry;	/* the file/dir representing this object */
+	struct dentry			*backer;	/* backing file */
+	loff_t				i_size;		/* object size */
+	unsigned long			flags;
+#define CACHEFILES_OBJECT_ACTIVE	0		/* T if marked active */
+	atomic_t			usage;		/* object usage count */
+	uint8_t				type;		/* object type */
+	uint8_t				new;		/* T if object new */
+	spinlock_t			work_lock;
+	struct rb_node			active_node;	/* link in active tree (dentry is key) */
+};
+
+extern struct kmem_cache *cachefiles_object_jar;
+
+/*
+ * Cache files cache definition
+ */
+struct cachefiles_cache {
+	struct fscache_cache		cache;		/* FS-Cache record */
+	struct vfsmount			*mnt;		/* mountpoint holding the cache */
+	struct dentry			*graveyard;	/* directory into which dead objects go */
+	struct file			*cachefilesd;	/* manager daemon handle */
+	const struct cred		*cache_cred;	/* security override for accessing cache */
+	struct mutex			daemon_mutex;	/* command serialisation mutex */
+	wait_queue_head_t		daemon_pollwq;	/* poll waitqueue for daemon */
+	struct rb_root			active_nodes;	/* active nodes (can't be culled) */
+	rwlock_t			active_lock;	/* lock for active_nodes */
+	atomic_t			gravecounter;	/* graveyard uniquifier */
+	unsigned			frun_percent;	/* when to stop culling (% files) */
+	unsigned			fcull_percent;	/* when to start culling (% files) */
+	unsigned			fstop_percent;	/* when to stop allocating (% files) */
+	unsigned			brun_percent;	/* when to stop culling (% blocks) */
+	unsigned			bcull_percent;	/* when to start culling (% blocks) */
+	unsigned			bstop_percent;	/* when to stop allocating (% blocks) */
+	unsigned			bsize;		/* cache's block size */
+	unsigned			bshift;		/* min(ilog2(PAGE_SIZE / bsize), 0) */
+	uint64_t			frun;		/* when to stop culling */
+	uint64_t			fcull;		/* when to start culling */
+	uint64_t			fstop;		/* when to stop allocating */
+	sector_t			brun;		/* when to stop culling */
+	sector_t			bcull;		/* when to start culling */
+	sector_t			bstop;		/* when to stop allocating */
+	unsigned long			flags;
+#define CACHEFILES_READY		0	/* T if cache prepared */
+#define CACHEFILES_DEAD			1	/* T if cache dead */
+#define CACHEFILES_CULLING		2	/* T if cull engaged */
+#define CACHEFILES_STATE_CHANGED	3	/* T if state changed (poll trigger) */
+	char				*rootdirname;	/* name of cache root directory */
+	char				*secctx;	/* LSM security context */
+	char				*tag;		/* cache binding tag */
+};
+
+/*
+ * backing file read tracking
+ */
+struct cachefiles_one_read {
+	wait_queue_t			monitor;	/* link into monitored waitqueue */
+	struct page			*back_page;	/* backing file page we're waiting for */
+	struct page			*netfs_page;	/* netfs page we're going to fill */
+	struct fscache_retrieval	*op;		/* retrieval op covering this */
+	struct list_head		op_link;	/* link in op's todo list */
+};
+
+/*
+ * backing file write tracking
+ */
+struct cachefiles_one_write {
+	struct page			*netfs_page;	/* netfs page to copy */
+	struct cachefiles_object	*object;
+	struct list_head		obj_link;	/* link in object's lists */
+	fscache_rw_complete_t		end_io_func;
+	void				*context;
+};
+
+/*
+ * auxiliary data xattr buffer
+ */
+struct cachefiles_xattr {
+	uint16_t			len;
+	uint8_t				type;
+	uint8_t				data[];
+};
+
+/*
+ * note change of state for daemon
+ */
+static inline void cachefiles_state_changed(struct cachefiles_cache *cache)
+{
+	set_bit(CACHEFILES_STATE_CHANGED, &cache->flags);
+	wake_up_all(&cache->daemon_pollwq);
+}
+
+/*
+ * cf-bind.c
+ */
+extern int cachefiles_daemon_bind(struct cachefiles_cache *cache, char *args);
+extern void cachefiles_daemon_unbind(struct cachefiles_cache *cache);
+
+/*
+ * cf-daemon.c
+ */
+extern const struct file_operations cachefiles_daemon_fops;
+
+extern int cachefiles_has_space(struct cachefiles_cache *cache,
+				unsigned fnr, unsigned bnr);
+
+/*
+ * cf-interface.c
+ */
+extern const struct fscache_cache_ops cachefiles_cache_ops;
+
+/*
+ * cf-key.c
+ */
+extern char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type);
+
+/*
+ * cf-namei.c
+ */
+extern int cachefiles_delete_object(struct cachefiles_cache *cache,
+				    struct cachefiles_object *object);
+extern int cachefiles_walk_to_object(struct cachefiles_object *parent,
+				     struct cachefiles_object *object,
+				     const char *key,
+				     struct cachefiles_xattr *auxdata);
+extern struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
+					       struct dentry *dir,
+					       const char *name);
+
+extern int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
+			   char *filename);
+
+extern int cachefiles_check_in_use(struct cachefiles_cache *cache,
+				   struct dentry *dir, char *filename);
+
+/*
+ * cf-proc.c
+ */
+#ifdef CONFIG_CACHEFILES_HISTOGRAM
+extern atomic_t cachefiles_lookup_histogram[HZ];
+extern atomic_t cachefiles_mkdir_histogram[HZ];
+extern atomic_t cachefiles_create_histogram[HZ];
+
+extern int __init cachefiles_proc_init(void);
+extern void cachefiles_proc_cleanup(void);
+static inline
+void cachefiles_hist(atomic_t histogram[], unsigned long start_jif)
+{
+	unsigned long jif = jiffies - start_jif;
+	if (jif >= HZ)
+		jif = HZ - 1;
+	atomic_inc(&histogram[jif]);
+}
+
+#else
+#define cachefiles_proc_init()		(0)
+#define cachefiles_proc_cleanup()	do {} while (0)
+#define cachefiles_hist(hist, start_jif) do {} while (0)
+#endif
+
+/*
+ * cf-rdwr.c
+ */
+extern int cachefiles_read_or_alloc_page(struct fscache_retrieval *,
+					 struct page *, gfp_t);
+extern int cachefiles_read_or_alloc_pages(struct fscache_retrieval *,
+					  struct list_head *, unsigned *,
+					  gfp_t);
+extern int cachefiles_allocate_page(struct fscache_retrieval *, struct page *,
+				    gfp_t);
+extern int cachefiles_allocate_pages(struct fscache_retrieval *,
+				     struct list_head *, unsigned *, gfp_t);
+extern int cachefiles_write_page(struct fscache_storage *, struct page *);
+extern void cachefiles_uncache_page(struct fscache_object *, struct page *);
+
+/*
+ * cf-security.c
+ */
+extern int cachefiles_get_security_ID(struct cachefiles_cache *cache);
+extern int cachefiles_determine_cache_security(struct cachefiles_cache *cache,
+					       struct dentry *root,
+					       const struct cred **_saved_cred);
+
+static inline void cachefiles_begin_secure(struct cachefiles_cache *cache,
+					   const struct cred **_saved_cred)
+{
+	*_saved_cred = override_creds(cache->cache_cred);
+}
+
+static inline void cachefiles_end_secure(struct cachefiles_cache *cache,
+					 const struct cred *saved_cred)
+{
+	revert_creds(saved_cred);
+}
+
+/*
+ * cf-xattr.c
+ */
+extern int cachefiles_check_object_type(struct cachefiles_object *object);
+extern int cachefiles_set_object_xattr(struct cachefiles_object *object,
+				       struct cachefiles_xattr *auxdata);
+extern int cachefiles_update_object_xattr(struct cachefiles_object *object,
+					  struct cachefiles_xattr *auxdata);
+extern int cachefiles_check_object_xattr(struct cachefiles_object *object,
+					 struct cachefiles_xattr *auxdata);
+extern int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
+					  struct dentry *dentry);
+
+
+/*
+ * error handling
+ */
+#define kerror(FMT, ...) printk(KERN_ERR "CacheFiles: "FMT"\n", ##__VA_ARGS__)
+
+#define cachefiles_io_error(___cache, FMT, ...)		\
+do {							\
+	kerror("I/O Error: " FMT, ##__VA_ARGS__);	\
+	fscache_io_error(&(___cache)->cache);		\
+	set_bit(CACHEFILES_DEAD, &(___cache)->flags);	\
+} while (0)
+
+#define cachefiles_io_error_obj(object, FMT, ...)			\
+do {									\
+	struct cachefiles_cache *___cache;				\
+									\
+	___cache = container_of((object)->fscache.cache,		\
+				struct cachefiles_cache, cache);	\
+	cachefiles_io_error(___cache, FMT, ##__VA_ARGS__);		\
+} while (0)
+
+
+/*
+ * debug tracing
+ */
+#define dbgprintk(FMT, ...) \
+	printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+
+/* make sure we maintain the format strings, even when debugging is disabled */
+static inline void _dbprintk(const char *fmt, ...)
+	__attribute__((format(printf, 1, 2)));
+static inline void _dbprintk(const char *fmt, ...)
+{
+}
+
+#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
+
+
+#if defined(__KDEBUG)
+#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
+#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
+#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
+
+#elif defined(CONFIG_CACHEFILES_DEBUG)
+#define _enter(FMT, ...)				\
+do {							\
+	if (cachefiles_debug & CACHEFILES_DEBUG_KENTER)	\
+		kenter(FMT, ##__VA_ARGS__);		\
+} while (0)
+
+#define _leave(FMT, ...)				\
+do {							\
+	if (cachefiles_debug & CACHEFILES_DEBUG_KLEAVE)	\
+		kleave(FMT, ##__VA_ARGS__);		\
+} while (0)
+
+#define _debug(FMT, ...)				\
+do {							\
+	if (cachefiles_debug & CACHEFILES_DEBUG_KDEBUG)	\
+		kdebug(FMT, ##__VA_ARGS__);		\
+} while (0)
+
+#else
+#define _enter(FMT, ...) _dbprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) _dbprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+#endif
+
+#if 1 /* defined(__KDEBUGALL) */
+
+#define ASSERT(X)							\
+do {									\
+	if (unlikely(!(X))) {						\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "CacheFiles: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "CacheFiles: Assertion failed\n");	\
+		printk(KERN_ERR "%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIF(C, X)							\
+do {									\
+	if (unlikely((C) && !(X))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "CacheFiles: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "CacheFiles: Assertion failed\n");	\
+		printk(KERN_ERR "%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#else
+
+#define ASSERT(X)			do {} while (0)
+#define ASSERTCMP(X, OP, Y)		do {} while (0)
+#define ASSERTIF(C, X)			do {} while (0)
+#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
+
+#endif
diff --git a/fs/cachefiles/key.c b/fs/cachefiles/key.c
new file mode 100644
index 000000000000..81b8b2b3a674
--- /dev/null
+++ b/fs/cachefiles/key.c
@@ -0,0 +1,159 @@
+/* Key to pathname encoder
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/slab.h>
+#include "internal.h"
+
+static const char cachefiles_charmap[64] =
+	"0123456789"			/* 0 - 9 */
+	"abcdefghijklmnopqrstuvwxyz"	/* 10 - 35 */
+	"ABCDEFGHIJKLMNOPQRSTUVWXYZ"	/* 36 - 61 */
+	"_-"				/* 62 - 63 */
+	;
+
+static const char cachefiles_filecharmap[256] = {
+	/* we skip space and tab and control chars */
+	[33 ... 46] = 1,		/* '!' -> '.' */
+	/* we skip '/' as it's significant to pathwalk */
+	[48 ... 127] = 1,		/* '0' -> '~' */
+};
+
+/*
+ * turn the raw key into something cooked
+ * - the raw key should include the length in the two bytes at the front
+ * - the key may be up to 514 bytes in length (including the length word)
+ *   - "base64" encode the strange keys, mapping 3 bytes of raw to four of
+ *     cooked
+ *   - need to cut the cooked key into 252 char lengths (189 raw bytes)
+ */
+char *cachefiles_cook_key(const u8 *raw, int keylen, uint8_t type)
+{
+	unsigned char csum, ch;
+	unsigned int acc;
+	char *key;
+	int loop, len, max, seg, mark, print;
+
+	_enter(",%d", keylen);
+
+	BUG_ON(keylen < 2 || keylen > 514);
+
+	csum = raw[0] + raw[1];
+	print = 1;
+	for (loop = 2; loop < keylen; loop++) {
+		ch = raw[loop];
+		csum += ch;
+		print &= cachefiles_filecharmap[ch];
+	}
+
+	if (print) {
+		/* if the path is usable ASCII, then we render it directly */
+		max = keylen - 2;
+		max += 2;	/* two base64'd length chars on the front */
+		max += 5;	/* @checksum/M */
+		max += 3 * 2;	/* maximum number of segment dividers (".../M")
+				 * is ((514 + 251) / 252) = 3
+				 */
+		max += 1;	/* NUL on end */
+	} else {
+		/* calculate the maximum length of the cooked key */
+		keylen = (keylen + 2) / 3;
+
+		max = keylen * 4;
+		max += 5;	/* @checksum/M */
+		max += 3 * 2;	/* maximum number of segment dividers (".../M")
+				 * is ((514 + 188) / 189) = 3
+				 */
+		max += 1;	/* NUL on end */
+	}
+
+	max += 1;	/* 2nd NUL on end */
+
+	_debug("max: %d", max);
+
+	key = kmalloc(max, GFP_KERNEL);
+	if (!key)
+		return NULL;
+
+	len = 0;
+
+	/* build the cooked key */
+	sprintf(key, "@%02x%c+", (unsigned) csum, 0);
+	len = 5;
+	mark = len - 1;
+
+	if (print) {
+		acc = *(uint16_t *) raw;
+		raw += 2;
+
+		key[len + 1] = cachefiles_charmap[acc & 63];
+		acc >>= 6;
+		key[len] = cachefiles_charmap[acc & 63];
+		len += 2;
+
+		seg = 250;
+		for (loop = keylen; loop > 0; loop--) {
+			if (seg <= 0) {
+				key[len++] = '\0';
+				mark = len;
+				key[len++] = '+';
+				seg = 252;
+			}
+
+			key[len++] = *raw++;
+			ASSERT(len < max);
+		}
+
+		switch (type) {
+		case FSCACHE_COOKIE_TYPE_INDEX:		type = 'I';	break;
+		case FSCACHE_COOKIE_TYPE_DATAFILE:	type = 'D';	break;
+		default:				type = 'S';	break;
+		}
+	} else {
+		seg = 252;
+		for (loop = keylen; loop > 0; loop--) {
+			if (seg <= 0) {
+				key[len++] = '\0';
+				mark = len;
+				key[len++] = '+';
+				seg = 252;
+			}
+
+			acc = *raw++;
+			acc |= *raw++ << 8;
+			acc |= *raw++ << 16;
+
+			_debug("acc: %06x", acc);
+
+			key[len++] = cachefiles_charmap[acc & 63];
+			acc >>= 6;
+			key[len++] = cachefiles_charmap[acc & 63];
+			acc >>= 6;
+			key[len++] = cachefiles_charmap[acc & 63];
+			acc >>= 6;
+			key[len++] = cachefiles_charmap[acc & 63];
+
+			ASSERT(len < max);
+		}
+
+		switch (type) {
+		case FSCACHE_COOKIE_TYPE_INDEX:		type = 'J';	break;
+		case FSCACHE_COOKIE_TYPE_DATAFILE:	type = 'E';	break;
+		default:				type = 'T';	break;
+		}
+	}
+
+	key[mark] = type;
+	key[len++] = 0;
+	key[len] = 0;
+
+	_leave(" = %p %d", key, len);
+	return key;
+}
diff --git a/fs/cachefiles/main.c b/fs/cachefiles/main.c
new file mode 100644
index 000000000000..4bfa8cf43bf5
--- /dev/null
+++ b/fs/cachefiles/main.c
@@ -0,0 +1,106 @@
+/* Network filesystem caching backend to use cache files on a premounted
+ * filesystem
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/file.h>
+#include <linux/namei.h>
+#include <linux/mount.h>
+#include <linux/statfs.h>
+#include <linux/sysctl.h>
+#include <linux/miscdevice.h>
+#include "internal.h"
+
+unsigned cachefiles_debug;
+module_param_named(debug, cachefiles_debug, uint, S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(cachefiles_debug, "CacheFiles debugging mask");
+
+MODULE_DESCRIPTION("Mounted-filesystem based cache");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+struct kmem_cache *cachefiles_object_jar;
+
+static struct miscdevice cachefiles_dev = {
+	.minor	= MISC_DYNAMIC_MINOR,
+	.name	= "cachefiles",
+	.fops	= &cachefiles_daemon_fops,
+};
+
+static void cachefiles_object_init_once(void *_object)
+{
+	struct cachefiles_object *object = _object;
+
+	memset(object, 0, sizeof(*object));
+	spin_lock_init(&object->work_lock);
+}
+
+/*
+ * initialise the fs caching module
+ */
+static int __init cachefiles_init(void)
+{
+	int ret;
+
+	ret = misc_register(&cachefiles_dev);
+	if (ret < 0)
+		goto error_dev;
+
+	/* create an object jar */
+	ret = -ENOMEM;
+	cachefiles_object_jar =
+		kmem_cache_create("cachefiles_object_jar",
+				  sizeof(struct cachefiles_object),
+				  0,
+				  SLAB_HWCACHE_ALIGN,
+				  cachefiles_object_init_once);
+	if (!cachefiles_object_jar) {
+		printk(KERN_NOTICE
+		       "CacheFiles: Failed to allocate an object jar\n");
+		goto error_object_jar;
+	}
+
+	ret = cachefiles_proc_init();
+	if (ret < 0)
+		goto error_proc;
+
+	printk(KERN_INFO "CacheFiles: Loaded\n");
+	return 0;
+
+error_proc:
+	kmem_cache_destroy(cachefiles_object_jar);
+error_object_jar:
+	misc_deregister(&cachefiles_dev);
+error_dev:
+	kerror("failed to register: %d", ret);
+	return ret;
+}
+
+fs_initcall(cachefiles_init);
+
+/*
+ * clean up on module removal
+ */
+static void __exit cachefiles_exit(void)
+{
+	printk(KERN_INFO "CacheFiles: Unloading\n");
+
+	cachefiles_proc_cleanup();
+	kmem_cache_destroy(cachefiles_object_jar);
+	misc_deregister(&cachefiles_dev);
+}
+
+module_exit(cachefiles_exit);
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
new file mode 100644
index 000000000000..4ce818ae39ea
--- /dev/null
+++ b/fs/cachefiles/namei.c
@@ -0,0 +1,771 @@
+/* CacheFiles path walking and related routines
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/quotaops.h>
+#include <linux/xattr.h>
+#include <linux/mount.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+#include "internal.h"
+
+static int cachefiles_wait_bit(void *flags)
+{
+	schedule();
+	return 0;
+}
+
+/*
+ * record the fact that an object is now active
+ */
+static void cachefiles_mark_object_active(struct cachefiles_cache *cache,
+					  struct cachefiles_object *object)
+{
+	struct cachefiles_object *xobject;
+	struct rb_node **_p, *_parent = NULL;
+	struct dentry *dentry;
+
+	_enter(",%p", object);
+
+try_again:
+	write_lock(&cache->active_lock);
+
+	if (test_and_set_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags))
+		BUG();
+
+	dentry = object->dentry;
+	_p = &cache->active_nodes.rb_node;
+	while (*_p) {
+		_parent = *_p;
+		xobject = rb_entry(_parent,
+				   struct cachefiles_object, active_node);
+
+		ASSERT(xobject != object);
+
+		if (xobject->dentry > dentry)
+			_p = &(*_p)->rb_left;
+		else if (xobject->dentry < dentry)
+			_p = &(*_p)->rb_right;
+		else
+			goto wait_for_old_object;
+	}
+
+	rb_link_node(&object->active_node, _parent, _p);
+	rb_insert_color(&object->active_node, &cache->active_nodes);
+
+	write_unlock(&cache->active_lock);
+	_leave("");
+	return;
+
+	/* an old object from a previous incarnation is hogging the slot - we
+	 * need to wait for it to be destroyed */
+wait_for_old_object:
+	if (xobject->fscache.state < FSCACHE_OBJECT_DYING) {
+		printk(KERN_ERR "\n");
+		printk(KERN_ERR "CacheFiles: Error:"
+		       " Unexpected object collision\n");
+		printk(KERN_ERR "xobject: OBJ%x\n",
+		       xobject->fscache.debug_id);
+		printk(KERN_ERR "xobjstate=%s\n",
+		       fscache_object_states[xobject->fscache.state]);
+		printk(KERN_ERR "xobjflags=%lx\n", xobject->fscache.flags);
+		printk(KERN_ERR "xobjevent=%lx [%lx]\n",
+		       xobject->fscache.events, xobject->fscache.event_mask);
+		printk(KERN_ERR "xops=%u inp=%u exc=%u\n",
+		       xobject->fscache.n_ops, xobject->fscache.n_in_progress,
+		       xobject->fscache.n_exclusive);
+		printk(KERN_ERR "xcookie=%p [pr=%p nd=%p fl=%lx]\n",
+		       xobject->fscache.cookie,
+		       xobject->fscache.cookie->parent,
+		       xobject->fscache.cookie->netfs_data,
+		       xobject->fscache.cookie->flags);
+		printk(KERN_ERR "xparent=%p\n",
+		       xobject->fscache.parent);
+		printk(KERN_ERR "object: OBJ%x\n",
+		       object->fscache.debug_id);
+		printk(KERN_ERR "cookie=%p [pr=%p nd=%p fl=%lx]\n",
+		       object->fscache.cookie,
+		       object->fscache.cookie->parent,
+		       object->fscache.cookie->netfs_data,
+		       object->fscache.cookie->flags);
+		printk(KERN_ERR "parent=%p\n",
+		       object->fscache.parent);
+		BUG();
+	}
+	atomic_inc(&xobject->usage);
+	write_unlock(&cache->active_lock);
+
+	_debug(">>> wait");
+	wait_on_bit(&xobject->flags, CACHEFILES_OBJECT_ACTIVE,
+		    cachefiles_wait_bit, TASK_UNINTERRUPTIBLE);
+	_debug("<<< waited");
+
+	cache->cache.ops->put_object(&xobject->fscache);
+	goto try_again;
+}
+
+/*
+ * delete an object representation from the cache
+ * - file backed objects are unlinked
+ * - directory backed objects are stuffed into the graveyard for userspace to
+ *   delete
+ * - unlocks the directory mutex
+ */
+static int cachefiles_bury_object(struct cachefiles_cache *cache,
+				  struct dentry *dir,
+				  struct dentry *rep)
+{
+	struct dentry *grave, *trap;
+	char nbuffer[8 + 8 + 1];
+	int ret;
+
+	_enter(",'%*.*s','%*.*s'",
+	       dir->d_name.len, dir->d_name.len, dir->d_name.name,
+	       rep->d_name.len, rep->d_name.len, rep->d_name.name);
+
+	/* non-directories can just be unlinked */
+	if (!S_ISDIR(rep->d_inode->i_mode)) {
+		_debug("unlink stale object");
+		ret = vfs_unlink(dir->d_inode, rep);
+
+		mutex_unlock(&dir->d_inode->i_mutex);
+
+		if (ret == -EIO)
+			cachefiles_io_error(cache, "Unlink failed");
+
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	/* directories have to be moved to the graveyard */
+	_debug("move stale object to graveyard");
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+try_again:
+	/* first step is to make up a grave dentry in the graveyard */
+	sprintf(nbuffer, "%08x%08x",
+		(uint32_t) get_seconds(),
+		(uint32_t) atomic_inc_return(&cache->gravecounter));
+
+	/* do the multiway lock magic */
+	trap = lock_rename(cache->graveyard, dir);
+
+	/* do some checks before getting the grave dentry */
+	if (rep->d_parent != dir) {
+		/* the entry was probably culled when we dropped the parent dir
+		 * lock */
+		unlock_rename(cache->graveyard, dir);
+		_leave(" = 0 [culled?]");
+		return 0;
+	}
+
+	if (!S_ISDIR(cache->graveyard->d_inode->i_mode)) {
+		unlock_rename(cache->graveyard, dir);
+		cachefiles_io_error(cache, "Graveyard no longer a directory");
+		return -EIO;
+	}
+
+	if (trap == rep) {
+		unlock_rename(cache->graveyard, dir);
+		cachefiles_io_error(cache, "May not make directory loop");
+		return -EIO;
+	}
+
+	if (d_mountpoint(rep)) {
+		unlock_rename(cache->graveyard, dir);
+		cachefiles_io_error(cache, "Mountpoint in cache");
+		return -EIO;
+	}
+
+	grave = lookup_one_len(nbuffer, cache->graveyard, strlen(nbuffer));
+	if (IS_ERR(grave)) {
+		unlock_rename(cache->graveyard, dir);
+
+		if (PTR_ERR(grave) == -ENOMEM) {
+			_leave(" = -ENOMEM");
+			return -ENOMEM;
+		}
+
+		cachefiles_io_error(cache, "Lookup error %ld",
+				    PTR_ERR(grave));
+		return -EIO;
+	}
+
+	if (grave->d_inode) {
+		unlock_rename(cache->graveyard, dir);
+		dput(grave);
+		grave = NULL;
+		cond_resched();
+		goto try_again;
+	}
+
+	if (d_mountpoint(grave)) {
+		unlock_rename(cache->graveyard, dir);
+		dput(grave);
+		cachefiles_io_error(cache, "Mountpoint in graveyard");
+		return -EIO;
+	}
+
+	/* target should not be an ancestor of source */
+	if (trap == grave) {
+		unlock_rename(cache->graveyard, dir);
+		dput(grave);
+		cachefiles_io_error(cache, "May not make directory loop");
+		return -EIO;
+	}
+
+	/* attempt the rename */
+	ret = vfs_rename(dir->d_inode, rep, cache->graveyard->d_inode, grave);
+	if (ret != 0 && ret != -ENOMEM)
+		cachefiles_io_error(cache, "Rename failed with error %d", ret);
+
+	unlock_rename(cache->graveyard, dir);
+	dput(grave);
+	_leave(" = 0");
+	return 0;
+}
+
+/*
+ * delete an object representation from the cache
+ */
+int cachefiles_delete_object(struct cachefiles_cache *cache,
+			     struct cachefiles_object *object)
+{
+	struct dentry *dir;
+	int ret;
+
+	_enter(",{%p}", object->dentry);
+
+	ASSERT(object->dentry);
+	ASSERT(object->dentry->d_inode);
+	ASSERT(object->dentry->d_parent);
+
+	dir = dget_parent(object->dentry);
+
+	mutex_lock(&dir->d_inode->i_mutex);
+	ret = cachefiles_bury_object(cache, dir, object->dentry);
+
+	dput(dir);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * walk from the parent object to the child object through the backing
+ * filesystem, creating directories as we go
+ */
+int cachefiles_walk_to_object(struct cachefiles_object *parent,
+			      struct cachefiles_object *object,
+			      const char *key,
+			      struct cachefiles_xattr *auxdata)
+{
+	struct cachefiles_cache *cache;
+	struct dentry *dir, *next = NULL;
+	unsigned long start;
+	const char *name;
+	int ret, nlen;
+
+	_enter("{%p},,%s,", parent->dentry, key);
+
+	cache = container_of(parent->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	ASSERT(parent->dentry);
+	ASSERT(parent->dentry->d_inode);
+
+	if (!(S_ISDIR(parent->dentry->d_inode->i_mode))) {
+		// TODO: convert file to dir
+		_leave("looking up in none directory");
+		return -ENOBUFS;
+	}
+
+	dir = dget(parent->dentry);
+
+advance:
+	/* attempt to transit the first directory component */
+	name = key;
+	nlen = strlen(key);
+
+	/* key ends in a double NUL */
+	key = key + nlen + 1;
+	if (!*key)
+		key = NULL;
+
+lookup_again:
+	/* search the current directory for the element name */
+	_debug("lookup '%s'", name);
+
+	mutex_lock(&dir->d_inode->i_mutex);
+
+	start = jiffies;
+	next = lookup_one_len(name, dir, nlen);
+	cachefiles_hist(cachefiles_lookup_histogram, start);
+	if (IS_ERR(next))
+		goto lookup_error;
+
+	_debug("next -> %p %s", next, next->d_inode ? "positive" : "negative");
+
+	if (!key)
+		object->new = !next->d_inode;
+
+	/* if this element of the path doesn't exist, then the lookup phase
+	 * failed, and we can release any readers in the certain knowledge that
+	 * there's nothing for them to actually read */
+	if (!next->d_inode)
+		fscache_object_lookup_negative(&object->fscache);
+
+	/* we need to create the object if it's negative */
+	if (key || object->type == FSCACHE_COOKIE_TYPE_INDEX) {
+		/* index objects and intervening tree levels must be subdirs */
+		if (!next->d_inode) {
+			ret = cachefiles_has_space(cache, 1, 0);
+			if (ret < 0)
+				goto create_error;
+
+			start = jiffies;
+			ret = vfs_mkdir(dir->d_inode, next, 0);
+			cachefiles_hist(cachefiles_mkdir_histogram, start);
+			if (ret < 0)
+				goto create_error;
+
+			ASSERT(next->d_inode);
+
+			_debug("mkdir -> %p{%p{ino=%lu}}",
+			       next, next->d_inode, next->d_inode->i_ino);
+
+		} else if (!S_ISDIR(next->d_inode->i_mode)) {
+			kerror("inode %lu is not a directory",
+			       next->d_inode->i_ino);
+			ret = -ENOBUFS;
+			goto error;
+		}
+
+	} else {
+		/* non-index objects start out life as files */
+		if (!next->d_inode) {
+			ret = cachefiles_has_space(cache, 1, 0);
+			if (ret < 0)
+				goto create_error;
+
+			start = jiffies;
+			ret = vfs_create(dir->d_inode, next, S_IFREG, NULL);
+			cachefiles_hist(cachefiles_create_histogram, start);
+			if (ret < 0)
+				goto create_error;
+
+			ASSERT(next->d_inode);
+
+			_debug("create -> %p{%p{ino=%lu}}",
+			       next, next->d_inode, next->d_inode->i_ino);
+
+		} else if (!S_ISDIR(next->d_inode->i_mode) &&
+			   !S_ISREG(next->d_inode->i_mode)
+			   ) {
+			kerror("inode %lu is not a file or directory",
+			       next->d_inode->i_ino);
+			ret = -ENOBUFS;
+			goto error;
+		}
+	}
+
+	/* process the next component */
+	if (key) {
+		_debug("advance");
+		mutex_unlock(&dir->d_inode->i_mutex);
+		dput(dir);
+		dir = next;
+		next = NULL;
+		goto advance;
+	}
+
+	/* we've found the object we were looking for */
+	object->dentry = next;
+
+	/* if we've found that the terminal object exists, then we need to
+	 * check its attributes and delete it if it's out of date */
+	if (!object->new) {
+		_debug("validate '%*.*s'",
+		       next->d_name.len, next->d_name.len, next->d_name.name);
+
+		ret = cachefiles_check_object_xattr(object, auxdata);
+		if (ret == -ESTALE) {
+			/* delete the object (the deleter drops the directory
+			 * mutex) */
+			object->dentry = NULL;
+
+			ret = cachefiles_bury_object(cache, dir, next);
+			dput(next);
+			next = NULL;
+
+			if (ret < 0)
+				goto delete_error;
+
+			_debug("redo lookup");
+			goto lookup_again;
+		}
+	}
+
+	/* note that we're now using this object */
+	cachefiles_mark_object_active(cache, object);
+
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(dir);
+	dir = NULL;
+
+	_debug("=== OBTAINED_OBJECT ===");
+
+	if (object->new) {
+		/* attach data to a newly constructed terminal object */
+		ret = cachefiles_set_object_xattr(object, auxdata);
+		if (ret < 0)
+			goto check_error;
+	} else {
+		/* always update the atime on an object we've just looked up
+		 * (this is used to keep track of culling, and atimes are only
+		 * updated by read, write and readdir but not lookup or
+		 * open) */
+		touch_atime(cache->mnt, next);
+	}
+
+	/* open a file interface onto a data file */
+	if (object->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		if (S_ISREG(object->dentry->d_inode->i_mode)) {
+			const struct address_space_operations *aops;
+
+			ret = -EPERM;
+			aops = object->dentry->d_inode->i_mapping->a_ops;
+			if (!aops->bmap)
+				goto check_error;
+
+			object->backer = object->dentry;
+		} else {
+			BUG(); // TODO: open file in data-class subdir
+		}
+	}
+
+	object->new = 0;
+	fscache_obtained_object(&object->fscache);
+
+	_leave(" = 0 [%lu]", object->dentry->d_inode->i_ino);
+	return 0;
+
+create_error:
+	_debug("create error %d", ret);
+	if (ret == -EIO)
+		cachefiles_io_error(cache, "Create/mkdir failed");
+	goto error;
+
+check_error:
+	_debug("check error %d", ret);
+	write_lock(&cache->active_lock);
+	rb_erase(&object->active_node, &cache->active_nodes);
+	clear_bit(CACHEFILES_OBJECT_ACTIVE, &object->flags);
+	wake_up_bit(&object->flags, CACHEFILES_OBJECT_ACTIVE);
+	write_unlock(&cache->active_lock);
+
+	dput(object->dentry);
+	object->dentry = NULL;
+	goto error_out;
+
+delete_error:
+	_debug("delete error %d", ret);
+	goto error_out2;
+
+lookup_error:
+	_debug("lookup error %ld", PTR_ERR(next));
+	ret = PTR_ERR(next);
+	if (ret == -EIO)
+		cachefiles_io_error(cache, "Lookup failed");
+	next = NULL;
+error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(next);
+error_out2:
+	dput(dir);
+error_out:
+	if (ret == -ENOSPC)
+		ret = -ENOBUFS;
+
+	_leave(" = error %d", -ret);
+	return ret;
+}
+
+/*
+ * get a subdirectory
+ */
+struct dentry *cachefiles_get_directory(struct cachefiles_cache *cache,
+					struct dentry *dir,
+					const char *dirname)
+{
+	struct dentry *subdir;
+	unsigned long start;
+	int ret;
+
+	_enter(",,%s", dirname);
+
+	/* search the current directory for the element name */
+	mutex_lock(&dir->d_inode->i_mutex);
+
+	start = jiffies;
+	subdir = lookup_one_len(dirname, dir, strlen(dirname));
+	cachefiles_hist(cachefiles_lookup_histogram, start);
+	if (IS_ERR(subdir)) {
+		if (PTR_ERR(subdir) == -ENOMEM)
+			goto nomem_d_alloc;
+		goto lookup_error;
+	}
+
+	_debug("subdir -> %p %s",
+	       subdir, subdir->d_inode ? "positive" : "negative");
+
+	/* we need to create the subdir if it doesn't exist yet */
+	if (!subdir->d_inode) {
+		ret = cachefiles_has_space(cache, 1, 0);
+		if (ret < 0)
+			goto mkdir_error;
+
+		_debug("attempt mkdir");
+
+		ret = vfs_mkdir(dir->d_inode, subdir, 0700);
+		if (ret < 0)
+			goto mkdir_error;
+
+		ASSERT(subdir->d_inode);
+
+		_debug("mkdir -> %p{%p{ino=%lu}}",
+		       subdir,
+		       subdir->d_inode,
+		       subdir->d_inode->i_ino);
+	}
+
+	mutex_unlock(&dir->d_inode->i_mutex);
+
+	/* we need to make sure the subdir is a directory */
+	ASSERT(subdir->d_inode);
+
+	if (!S_ISDIR(subdir->d_inode->i_mode)) {
+		kerror("%s is not a directory", dirname);
+		ret = -EIO;
+		goto check_error;
+	}
+
+	ret = -EPERM;
+	if (!subdir->d_inode->i_op ||
+	    !subdir->d_inode->i_op->setxattr ||
+	    !subdir->d_inode->i_op->getxattr ||
+	    !subdir->d_inode->i_op->lookup ||
+	    !subdir->d_inode->i_op->mkdir ||
+	    !subdir->d_inode->i_op->create ||
+	    !subdir->d_inode->i_op->rename ||
+	    !subdir->d_inode->i_op->rmdir ||
+	    !subdir->d_inode->i_op->unlink)
+		goto check_error;
+
+	_leave(" = [%lu]", subdir->d_inode->i_ino);
+	return subdir;
+
+check_error:
+	dput(subdir);
+	_leave(" = %d [check]", ret);
+	return ERR_PTR(ret);
+
+mkdir_error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(subdir);
+	kerror("mkdir %s failed with error %d", dirname, ret);
+	return ERR_PTR(ret);
+
+lookup_error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	ret = PTR_ERR(subdir);
+	kerror("Lookup %s failed with error %d", dirname, ret);
+	return ERR_PTR(ret);
+
+nomem_d_alloc:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	_leave(" = -ENOMEM");
+	return ERR_PTR(-ENOMEM);
+}
+
+/*
+ * find out if an object is in use or not
+ * - if finds object and it's not in use:
+ *   - returns a pointer to the object and a reference on it
+ *   - returns with the directory locked
+ */
+static struct dentry *cachefiles_check_active(struct cachefiles_cache *cache,
+					      struct dentry *dir,
+					      char *filename)
+{
+	struct cachefiles_object *object;
+	struct rb_node *_n;
+	struct dentry *victim;
+	unsigned long start;
+	int ret;
+
+	//_enter(",%*.*s/,%s",
+	//       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+
+	/* look up the victim */
+	mutex_lock_nested(&dir->d_inode->i_mutex, 1);
+
+	start = jiffies;
+	victim = lookup_one_len(filename, dir, strlen(filename));
+	cachefiles_hist(cachefiles_lookup_histogram, start);
+	if (IS_ERR(victim))
+		goto lookup_error;
+
+	//_debug("victim -> %p %s",
+	//       victim, victim->d_inode ? "positive" : "negative");
+
+	/* if the object is no longer there then we probably retired the object
+	 * at the netfs's request whilst the cull was in progress
+	 */
+	if (!victim->d_inode) {
+		mutex_unlock(&dir->d_inode->i_mutex);
+		dput(victim);
+		_leave(" = -ENOENT [absent]");
+		return ERR_PTR(-ENOENT);
+	}
+
+	/* check to see if we're using this object */
+	read_lock(&cache->active_lock);
+
+	_n = cache->active_nodes.rb_node;
+
+	while (_n) {
+		object = rb_entry(_n, struct cachefiles_object, active_node);
+
+		if (object->dentry > victim)
+			_n = _n->rb_left;
+		else if (object->dentry < victim)
+			_n = _n->rb_right;
+		else
+			goto object_in_use;
+	}
+
+	read_unlock(&cache->active_lock);
+
+	//_leave(" = %p", victim);
+	return victim;
+
+object_in_use:
+	read_unlock(&cache->active_lock);
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(victim);
+	//_leave(" = -EBUSY [in use]");
+	return ERR_PTR(-EBUSY);
+
+lookup_error:
+	mutex_unlock(&dir->d_inode->i_mutex);
+	ret = PTR_ERR(victim);
+	if (ret == -ENOENT) {
+		/* file or dir now absent - probably retired by netfs */
+		_leave(" = -ESTALE [absent]");
+		return ERR_PTR(-ESTALE);
+	}
+
+	if (ret == -EIO) {
+		cachefiles_io_error(cache, "Lookup failed");
+	} else if (ret != -ENOMEM) {
+		kerror("Internal error: %d", ret);
+		ret = -EIO;
+	}
+
+	_leave(" = %d", ret);
+	return ERR_PTR(ret);
+}
+
+/*
+ * cull an object if it's not in use
+ * - called only by cache manager daemon
+ */
+int cachefiles_cull(struct cachefiles_cache *cache, struct dentry *dir,
+		    char *filename)
+{
+	struct dentry *victim;
+	int ret;
+
+	_enter(",%*.*s/,%s",
+	       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+
+	victim = cachefiles_check_active(cache, dir, filename);
+	if (IS_ERR(victim))
+		return PTR_ERR(victim);
+
+	_debug("victim -> %p %s",
+	       victim, victim->d_inode ? "positive" : "negative");
+
+	/* okay... the victim is not being used so we can cull it
+	 * - start by marking it as stale
+	 */
+	_debug("victim is cullable");
+
+	ret = cachefiles_remove_object_xattr(cache, victim);
+	if (ret < 0)
+		goto error_unlock;
+
+	/*  actually remove the victim (drops the dir mutex) */
+	_debug("bury");
+
+	ret = cachefiles_bury_object(cache, dir, victim);
+	if (ret < 0)
+		goto error;
+
+	dput(victim);
+	_leave(" = 0");
+	return 0;
+
+error_unlock:
+	mutex_unlock(&dir->d_inode->i_mutex);
+error:
+	dput(victim);
+	if (ret == -ENOENT) {
+		/* file or dir now absent - probably retired by netfs */
+		_leave(" = -ESTALE [absent]");
+		return -ESTALE;
+	}
+
+	if (ret != -ENOMEM) {
+		kerror("Internal error: %d", ret);
+		ret = -EIO;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * find out if an object is in use or not
+ * - called only by cache manager daemon
+ * - returns -EBUSY or 0 to indicate whether an object is in use or not
+ */
+int cachefiles_check_in_use(struct cachefiles_cache *cache, struct dentry *dir,
+			    char *filename)
+{
+	struct dentry *victim;
+
+	//_enter(",%*.*s/,%s",
+	//       dir->d_name.len, dir->d_name.len, dir->d_name.name, filename);
+
+	victim = cachefiles_check_active(cache, dir, filename);
+	if (IS_ERR(victim))
+		return PTR_ERR(victim);
+
+	mutex_unlock(&dir->d_inode->i_mutex);
+	dput(victim);
+	//_leave(" = 0");
+	return 0;
+}
diff --git a/fs/cachefiles/proc.c b/fs/cachefiles/proc.c
new file mode 100644
index 000000000000..eccd33941199
--- /dev/null
+++ b/fs/cachefiles/proc.c
@@ -0,0 +1,134 @@
+/* CacheFiles statistics
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+atomic_t cachefiles_lookup_histogram[HZ];
+atomic_t cachefiles_mkdir_histogram[HZ];
+atomic_t cachefiles_create_histogram[HZ];
+
+/*
+ * display the latency histogram
+ */
+static int cachefiles_histogram_show(struct seq_file *m, void *v)
+{
+	unsigned long index;
+	unsigned x, y, z, t;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "JIFS  SECS  LOOKUPS   MKDIRS    CREATES\n");
+		return 0;
+	case 2:
+		seq_puts(m, "===== ===== ========= ========= =========\n");
+		return 0;
+	default:
+		index = (unsigned long) v - 3;
+		x = atomic_read(&cachefiles_lookup_histogram[index]);
+		y = atomic_read(&cachefiles_mkdir_histogram[index]);
+		z = atomic_read(&cachefiles_create_histogram[index]);
+		if (x == 0 && y == 0 && z == 0)
+			return 0;
+
+		t = (index * 1000) / HZ;
+
+		seq_printf(m, "%4lu  0.%03u %9u %9u %9u\n", index, t, x, y, z);
+		return 0;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *cachefiles_histogram_start(struct seq_file *m, loff_t *_pos)
+{
+	if ((unsigned long long)*_pos >= HZ + 2)
+		return NULL;
+	if (*_pos == 0)
+		*_pos = 1;
+	return (void *)(unsigned long) *_pos;
+}
+
+/*
+ * move to the next line
+ */
+static void *cachefiles_histogram_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return (unsigned long long)*pos > HZ + 2 ?
+		NULL : (void *)(unsigned long) *pos;
+}
+
+/*
+ * clean up after reading
+ */
+static void cachefiles_histogram_stop(struct seq_file *m, void *v)
+{
+}
+
+static const struct seq_operations cachefiles_histogram_ops = {
+	.start		= cachefiles_histogram_start,
+	.stop		= cachefiles_histogram_stop,
+	.next		= cachefiles_histogram_next,
+	.show		= cachefiles_histogram_show,
+};
+
+/*
+ * open "/proc/fs/cachefiles/XXX" which provide statistics summaries
+ */
+static int cachefiles_histogram_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &cachefiles_histogram_ops);
+}
+
+static const struct file_operations cachefiles_histogram_fops = {
+	.owner		= THIS_MODULE,
+	.open		= cachefiles_histogram_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
+
+/*
+ * initialise the /proc/fs/cachefiles/ directory
+ */
+int __init cachefiles_proc_init(void)
+{
+	_enter("");
+
+	if (!proc_mkdir("fs/cachefiles", NULL))
+		goto error_dir;
+
+	if (!proc_create("fs/cachefiles/histogram", S_IFREG | 0444, NULL,
+			 &cachefiles_histogram_fops))
+		goto error_histogram;
+
+	_leave(" = 0");
+	return 0;
+
+error_histogram:
+	remove_proc_entry("fs/cachefiles", NULL);
+error_dir:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/cachefiles/ directory
+ */
+void cachefiles_proc_cleanup(void)
+{
+	remove_proc_entry("fs/cachefiles/histogram", NULL);
+	remove_proc_entry("fs/cachefiles", NULL);
+}
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
new file mode 100644
index 000000000000..a69787e7dd96
--- /dev/null
+++ b/fs/cachefiles/rdwr.c
@@ -0,0 +1,879 @@
+/* Storage object read/write
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/mount.h>
+#include <linux/file.h>
+#include "internal.h"
+
+/*
+ * detect wake up events generated by the unlocking of pages in which we're
+ * interested
+ * - we use this to detect read completion of backing pages
+ * - the caller holds the waitqueue lock
+ */
+static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
+				  int sync, void *_key)
+{
+	struct cachefiles_one_read *monitor =
+		container_of(wait, struct cachefiles_one_read, monitor);
+	struct cachefiles_object *object;
+	struct wait_bit_key *key = _key;
+	struct page *page = wait->private;
+
+	ASSERT(key);
+
+	_enter("{%lu},%u,%d,{%p,%u}",
+	       monitor->netfs_page->index, mode, sync,
+	       key->flags, key->bit_nr);
+
+	if (key->flags != &page->flags ||
+	    key->bit_nr != PG_locked)
+		return 0;
+
+	_debug("--- monitor %p %lx ---", page, page->flags);
+
+	if (!PageUptodate(page) && !PageError(page))
+		dump_stack();
+
+	/* remove from the waitqueue */
+	list_del(&wait->task_list);
+
+	/* move onto the action list and queue for FS-Cache thread pool */
+	ASSERT(monitor->op);
+
+	object = container_of(monitor->op->op.object,
+			      struct cachefiles_object, fscache);
+
+	spin_lock(&object->work_lock);
+	list_add_tail(&monitor->op_link, &monitor->op->to_do);
+	spin_unlock(&object->work_lock);
+
+	fscache_enqueue_retrieval(monitor->op);
+	return 0;
+}
+
+/*
+ * copy data from backing pages to netfs pages to complete a read operation
+ * - driven by FS-Cache's thread pool
+ */
+static void cachefiles_read_copier(struct fscache_operation *_op)
+{
+	struct cachefiles_one_read *monitor;
+	struct cachefiles_object *object;
+	struct fscache_retrieval *op;
+	struct pagevec pagevec;
+	int error, max;
+
+	op = container_of(_op, struct fscache_retrieval, op);
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+
+	_enter("{ino=%lu}", object->backer->d_inode->i_ino);
+
+	pagevec_init(&pagevec, 0);
+
+	max = 8;
+	spin_lock_irq(&object->work_lock);
+
+	while (!list_empty(&op->to_do)) {
+		monitor = list_entry(op->to_do.next,
+				     struct cachefiles_one_read, op_link);
+		list_del(&monitor->op_link);
+
+		spin_unlock_irq(&object->work_lock);
+
+		_debug("- copy {%lu}", monitor->back_page->index);
+
+		error = -EIO;
+		if (PageUptodate(monitor->back_page)) {
+			copy_highpage(monitor->netfs_page, monitor->back_page);
+
+			pagevec_add(&pagevec, monitor->netfs_page);
+			fscache_mark_pages_cached(monitor->op, &pagevec);
+			error = 0;
+		}
+
+		if (error)
+			cachefiles_io_error_obj(
+				object,
+				"Readpage failed on backing file %lx",
+				(unsigned long) monitor->back_page->flags);
+
+		page_cache_release(monitor->back_page);
+
+		fscache_end_io(op, monitor->netfs_page, error);
+		page_cache_release(monitor->netfs_page);
+		fscache_put_retrieval(op);
+		kfree(monitor);
+
+		/* let the thread pool have some air occasionally */
+		max--;
+		if (max < 0 || need_resched()) {
+			if (!list_empty(&op->to_do))
+				fscache_enqueue_retrieval(op);
+			_leave(" [maxed out]");
+			return;
+		}
+
+		spin_lock_irq(&object->work_lock);
+	}
+
+	spin_unlock_irq(&object->work_lock);
+	_leave("");
+}
+
+/*
+ * read the corresponding page to the given set from the backing file
+ * - an uncertain page is simply discarded, to be tried again another time
+ */
+static int cachefiles_read_backing_file_one(struct cachefiles_object *object,
+					    struct fscache_retrieval *op,
+					    struct page *netpage,
+					    struct pagevec *pagevec)
+{
+	struct cachefiles_one_read *monitor;
+	struct address_space *bmapping;
+	struct page *newpage, *backpage;
+	int ret;
+
+	_enter("");
+
+	pagevec_reinit(pagevec);
+
+	_debug("read back %p{%lu,%d}",
+	       netpage, netpage->index, page_count(netpage));
+
+	monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+	if (!monitor)
+		goto nomem;
+
+	monitor->netfs_page = netpage;
+	monitor->op = fscache_get_retrieval(op);
+
+	init_waitqueue_func_entry(&monitor->monitor, cachefiles_read_waiter);
+
+	/* attempt to get hold of the backing page */
+	bmapping = object->backer->d_inode->i_mapping;
+	newpage = NULL;
+
+	for (;;) {
+		backpage = find_get_page(bmapping, netpage->index);
+		if (backpage)
+			goto backing_page_already_present;
+
+		if (!newpage) {
+			newpage = page_cache_alloc_cold(bmapping);
+			if (!newpage)
+				goto nomem_monitor;
+		}
+
+		ret = add_to_page_cache(newpage, bmapping,
+					netpage->index, GFP_KERNEL);
+		if (ret == 0)
+			goto installed_new_backing_page;
+		if (ret != -EEXIST)
+			goto nomem_page;
+	}
+
+	/* we've installed a new backing page, so now we need to add it
+	 * to the LRU list and start it reading */
+installed_new_backing_page:
+	_debug("- new %p", newpage);
+
+	backpage = newpage;
+	newpage = NULL;
+
+	page_cache_get(backpage);
+	pagevec_add(pagevec, backpage);
+	__pagevec_lru_add_file(pagevec);
+
+read_backing_page:
+	ret = bmapping->a_ops->readpage(NULL, backpage);
+	if (ret < 0)
+		goto read_error;
+
+	/* set the monitor to transfer the data across */
+monitor_backing_page:
+	_debug("- monitor add");
+
+	/* install the monitor */
+	page_cache_get(monitor->netfs_page);
+	page_cache_get(backpage);
+	monitor->back_page = backpage;
+	monitor->monitor.private = backpage;
+	add_page_wait_queue(backpage, &monitor->monitor);
+	monitor = NULL;
+
+	/* but the page may have been read before the monitor was installed, so
+	 * the monitor may miss the event - so we have to ensure that we do get
+	 * one in such a case */
+	if (trylock_page(backpage)) {
+		_debug("jumpstart %p {%lx}", backpage, backpage->flags);
+		unlock_page(backpage);
+	}
+	goto success;
+
+	/* if the backing page is already present, it can be in one of
+	 * three states: read in progress, read failed or read okay */
+backing_page_already_present:
+	_debug("- present");
+
+	if (newpage) {
+		page_cache_release(newpage);
+		newpage = NULL;
+	}
+
+	if (PageError(backpage))
+		goto io_error;
+
+	if (PageUptodate(backpage))
+		goto backing_page_already_uptodate;
+
+	if (!trylock_page(backpage))
+		goto monitor_backing_page;
+	_debug("read %p {%lx}", backpage, backpage->flags);
+	goto read_backing_page;
+
+	/* the backing page is already up to date, attach the netfs
+	 * page to the pagecache and LRU and copy the data across */
+backing_page_already_uptodate:
+	_debug("- uptodate");
+
+	pagevec_add(pagevec, netpage);
+	fscache_mark_pages_cached(op, pagevec);
+
+	copy_highpage(netpage, backpage);
+	fscache_end_io(op, netpage, 0);
+
+success:
+	_debug("success");
+	ret = 0;
+
+out:
+	if (backpage)
+		page_cache_release(backpage);
+	if (monitor) {
+		fscache_put_retrieval(monitor->op);
+		kfree(monitor);
+	}
+	_leave(" = %d", ret);
+	return ret;
+
+read_error:
+	_debug("read error %d", ret);
+	if (ret == -ENOMEM)
+		goto out;
+io_error:
+	cachefiles_io_error_obj(object, "Page read error on backing file");
+	ret = -ENOBUFS;
+	goto out;
+
+nomem_page:
+	page_cache_release(newpage);
+nomem_monitor:
+	fscache_put_retrieval(monitor->op);
+	kfree(monitor);
+nomem:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+
+/*
+ * read a page from the cache or allocate a block in which to store it
+ * - cache withdrawal is prevented by the caller
+ * - returns -EINTR if interrupted
+ * - returns -ENOMEM if ran out of memory
+ * - returns -ENOBUFS if no buffers can be made available
+ * - returns -ENOBUFS if page is beyond EOF
+ * - if the page is backed by a block in the cache:
+ *   - a read will be started which will call the callback on completion
+ *   - 0 will be returned
+ * - else if the page is unbacked:
+ *   - the metadata will be retained
+ *   - -ENODATA will be returned
+ */
+int cachefiles_read_or_alloc_page(struct fscache_retrieval *op,
+				  struct page *page,
+				  gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct pagevec pagevec;
+	struct inode *inode;
+	sector_t block0, block;
+	unsigned shift;
+	int ret;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("{%p},{%lx},,,", object, page->index);
+
+	if (!object->backer)
+		return -ENOBUFS;
+
+	inode = object->backer->d_inode;
+	ASSERT(S_ISREG(inode->i_mode));
+	ASSERT(inode->i_mapping->a_ops->bmap);
+	ASSERT(inode->i_mapping->a_ops->readpages);
+
+	/* calculate the shift required to use bmap */
+	if (inode->i_sb->s_blocksize > PAGE_SIZE)
+		return -ENOBUFS;
+
+	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
+
+	op->op.flags = FSCACHE_OP_FAST;
+	op->op.processor = cachefiles_read_copier;
+
+	pagevec_init(&pagevec, 0);
+
+	/* we assume the absence or presence of the first block is a good
+	 * enough indication for the page as a whole
+	 * - TODO: don't use bmap() for this as it is _not_ actually good
+	 *   enough for this as it doesn't indicate errors, but it's all we've
+	 *   got for the moment
+	 */
+	block0 = page->index;
+	block0 <<= shift;
+
+	block = inode->i_mapping->a_ops->bmap(inode->i_mapping, block0);
+	_debug("%llx -> %llx",
+	       (unsigned long long) block0,
+	       (unsigned long long) block);
+
+	if (block) {
+		/* submit the apparently valid page to the backing fs to be
+		 * read from disk */
+		ret = cachefiles_read_backing_file_one(object, op, page,
+						       &pagevec);
+	} else if (cachefiles_has_space(cache, 0, 1) == 0) {
+		/* there's space in the cache we can use */
+		pagevec_add(&pagevec, page);
+		fscache_mark_pages_cached(op, &pagevec);
+		ret = -ENODATA;
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * read the corresponding pages to the given set from the backing file
+ * - any uncertain pages are simply discarded, to be tried again another time
+ */
+static int cachefiles_read_backing_file(struct cachefiles_object *object,
+					struct fscache_retrieval *op,
+					struct list_head *list,
+					struct pagevec *mark_pvec)
+{
+	struct cachefiles_one_read *monitor = NULL;
+	struct address_space *bmapping = object->backer->d_inode->i_mapping;
+	struct pagevec lru_pvec;
+	struct page *newpage = NULL, *netpage, *_n, *backpage = NULL;
+	int ret = 0;
+
+	_enter("");
+
+	pagevec_init(&lru_pvec, 0);
+
+	list_for_each_entry_safe(netpage, _n, list, lru) {
+		list_del(&netpage->lru);
+
+		_debug("read back %p{%lu,%d}",
+		       netpage, netpage->index, page_count(netpage));
+
+		if (!monitor) {
+			monitor = kzalloc(sizeof(*monitor), GFP_KERNEL);
+			if (!monitor)
+				goto nomem;
+
+			monitor->op = fscache_get_retrieval(op);
+			init_waitqueue_func_entry(&monitor->monitor,
+						  cachefiles_read_waiter);
+		}
+
+		for (;;) {
+			backpage = find_get_page(bmapping, netpage->index);
+			if (backpage)
+				goto backing_page_already_present;
+
+			if (!newpage) {
+				newpage = page_cache_alloc_cold(bmapping);
+				if (!newpage)
+					goto nomem;
+			}
+
+			ret = add_to_page_cache(newpage, bmapping,
+						netpage->index, GFP_KERNEL);
+			if (ret == 0)
+				goto installed_new_backing_page;
+			if (ret != -EEXIST)
+				goto nomem;
+		}
+
+		/* we've installed a new backing page, so now we need to add it
+		 * to the LRU list and start it reading */
+	installed_new_backing_page:
+		_debug("- new %p", newpage);
+
+		backpage = newpage;
+		newpage = NULL;
+
+		page_cache_get(backpage);
+		if (!pagevec_add(&lru_pvec, backpage))
+			__pagevec_lru_add_file(&lru_pvec);
+
+	reread_backing_page:
+		ret = bmapping->a_ops->readpage(NULL, backpage);
+		if (ret < 0)
+			goto read_error;
+
+		/* add the netfs page to the pagecache and LRU, and set the
+		 * monitor to transfer the data across */
+	monitor_backing_page:
+		_debug("- monitor add");
+
+		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
+					GFP_KERNEL);
+		if (ret < 0) {
+			if (ret == -EEXIST) {
+				page_cache_release(netpage);
+				continue;
+			}
+			goto nomem;
+		}
+
+		page_cache_get(netpage);
+		if (!pagevec_add(&lru_pvec, netpage))
+			__pagevec_lru_add_file(&lru_pvec);
+
+		/* install a monitor */
+		page_cache_get(netpage);
+		monitor->netfs_page = netpage;
+
+		page_cache_get(backpage);
+		monitor->back_page = backpage;
+		monitor->monitor.private = backpage;
+		add_page_wait_queue(backpage, &monitor->monitor);
+		monitor = NULL;
+
+		/* but the page may have been read before the monitor was
+		 * installed, so the monitor may miss the event - so we have to
+		 * ensure that we do get one in such a case */
+		if (trylock_page(backpage)) {
+			_debug("2unlock %p {%lx}", backpage, backpage->flags);
+			unlock_page(backpage);
+		}
+
+		page_cache_release(backpage);
+		backpage = NULL;
+
+		page_cache_release(netpage);
+		netpage = NULL;
+		continue;
+
+		/* if the backing page is already present, it can be in one of
+		 * three states: read in progress, read failed or read okay */
+	backing_page_already_present:
+		_debug("- present %p", backpage);
+
+		if (PageError(backpage))
+			goto io_error;
+
+		if (PageUptodate(backpage))
+			goto backing_page_already_uptodate;
+
+		_debug("- not ready %p{%lx}", backpage, backpage->flags);
+
+		if (!trylock_page(backpage))
+			goto monitor_backing_page;
+
+		if (PageError(backpage)) {
+			_debug("error %lx", backpage->flags);
+			unlock_page(backpage);
+			goto io_error;
+		}
+
+		if (PageUptodate(backpage))
+			goto backing_page_already_uptodate_unlock;
+
+		/* we've locked a page that's neither up to date nor erroneous,
+		 * so we need to attempt to read it again */
+		goto reread_backing_page;
+
+		/* the backing page is already up to date, attach the netfs
+		 * page to the pagecache and LRU and copy the data across */
+	backing_page_already_uptodate_unlock:
+		_debug("uptodate %lx", backpage->flags);
+		unlock_page(backpage);
+	backing_page_already_uptodate:
+		_debug("- uptodate");
+
+		ret = add_to_page_cache(netpage, op->mapping, netpage->index,
+					GFP_KERNEL);
+		if (ret < 0) {
+			if (ret == -EEXIST) {
+				page_cache_release(netpage);
+				continue;
+			}
+			goto nomem;
+		}
+
+		copy_highpage(netpage, backpage);
+
+		page_cache_release(backpage);
+		backpage = NULL;
+
+		if (!pagevec_add(mark_pvec, netpage))
+			fscache_mark_pages_cached(op, mark_pvec);
+
+		page_cache_get(netpage);
+		if (!pagevec_add(&lru_pvec, netpage))
+			__pagevec_lru_add_file(&lru_pvec);
+
+		fscache_end_io(op, netpage, 0);
+		page_cache_release(netpage);
+		netpage = NULL;
+		continue;
+	}
+
+	netpage = NULL;
+
+	_debug("out");
+
+out:
+	/* tidy up */
+	pagevec_lru_add_file(&lru_pvec);
+
+	if (newpage)
+		page_cache_release(newpage);
+	if (netpage)
+		page_cache_release(netpage);
+	if (backpage)
+		page_cache_release(backpage);
+	if (monitor) {
+		fscache_put_retrieval(op);
+		kfree(monitor);
+	}
+
+	list_for_each_entry_safe(netpage, _n, list, lru) {
+		list_del(&netpage->lru);
+		page_cache_release(netpage);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+
+nomem:
+	_debug("nomem");
+	ret = -ENOMEM;
+	goto out;
+
+read_error:
+	_debug("read error %d", ret);
+	if (ret == -ENOMEM)
+		goto out;
+io_error:
+	cachefiles_io_error_obj(object, "Page read error on backing file");
+	ret = -ENOBUFS;
+	goto out;
+}
+
+/*
+ * read a list of pages from the cache or allocate blocks in which to store
+ * them
+ */
+int cachefiles_read_or_alloc_pages(struct fscache_retrieval *op,
+				   struct list_head *pages,
+				   unsigned *nr_pages,
+				   gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct list_head backpages;
+	struct pagevec pagevec;
+	struct inode *inode;
+	struct page *page, *_n;
+	unsigned shift, nrbackpages;
+	int ret, ret2, space;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("{OBJ%x,%d},,%d,,",
+	       object->fscache.debug_id, atomic_read(&op->op.usage),
+	       *nr_pages);
+
+	if (!object->backer)
+		return -ENOBUFS;
+
+	space = 1;
+	if (cachefiles_has_space(cache, 0, *nr_pages) < 0)
+		space = 0;
+
+	inode = object->backer->d_inode;
+	ASSERT(S_ISREG(inode->i_mode));
+	ASSERT(inode->i_mapping->a_ops->bmap);
+	ASSERT(inode->i_mapping->a_ops->readpages);
+
+	/* calculate the shift required to use bmap */
+	if (inode->i_sb->s_blocksize > PAGE_SIZE)
+		return -ENOBUFS;
+
+	shift = PAGE_SHIFT - inode->i_sb->s_blocksize_bits;
+
+	pagevec_init(&pagevec, 0);
+
+	op->op.flags = FSCACHE_OP_FAST;
+	op->op.processor = cachefiles_read_copier;
+
+	INIT_LIST_HEAD(&backpages);
+	nrbackpages = 0;
+
+	ret = space ? -ENODATA : -ENOBUFS;
+	list_for_each_entry_safe(page, _n, pages, lru) {
+		sector_t block0, block;
+
+		/* we assume the absence or presence of the first block is a
+		 * good enough indication for the page as a whole
+		 * - TODO: don't use bmap() for this as it is _not_ actually
+		 *   good enough for this as it doesn't indicate errors, but
+		 *   it's all we've got for the moment
+		 */
+		block0 = page->index;
+		block0 <<= shift;
+
+		block = inode->i_mapping->a_ops->bmap(inode->i_mapping,
+						      block0);
+		_debug("%llx -> %llx",
+		       (unsigned long long) block0,
+		       (unsigned long long) block);
+
+		if (block) {
+			/* we have data - add it to the list to give to the
+			 * backing fs */
+			list_move(&page->lru, &backpages);
+			(*nr_pages)--;
+			nrbackpages++;
+		} else if (space && pagevec_add(&pagevec, page) == 0) {
+			fscache_mark_pages_cached(op, &pagevec);
+			ret = -ENODATA;
+		}
+	}
+
+	if (pagevec_count(&pagevec) > 0)
+		fscache_mark_pages_cached(op, &pagevec);
+
+	if (list_empty(pages))
+		ret = 0;
+
+	/* submit the apparently valid pages to the backing fs to be read from
+	 * disk */
+	if (nrbackpages > 0) {
+		ret2 = cachefiles_read_backing_file(object, op, &backpages,
+						    &pagevec);
+		if (ret2 == -ENOMEM || ret2 == -EINTR)
+			ret = ret2;
+	}
+
+	if (pagevec_count(&pagevec) > 0)
+		fscache_mark_pages_cached(op, &pagevec);
+
+	_leave(" = %d [nr=%u%s]",
+	       ret, *nr_pages, list_empty(pages) ? " empty" : "");
+	return ret;
+}
+
+/*
+ * allocate a block in the cache in which to store a page
+ * - cache withdrawal is prevented by the caller
+ * - returns -EINTR if interrupted
+ * - returns -ENOMEM if ran out of memory
+ * - returns -ENOBUFS if no buffers can be made available
+ * - returns -ENOBUFS if page is beyond EOF
+ * - otherwise:
+ *   - the metadata will be retained
+ *   - 0 will be returned
+ */
+int cachefiles_allocate_page(struct fscache_retrieval *op,
+			     struct page *page,
+			     gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct pagevec pagevec;
+	int ret;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("%p,{%lx},", object, page->index);
+
+	ret = cachefiles_has_space(cache, 0, 1);
+	if (ret == 0) {
+		pagevec_init(&pagevec, 0);
+		pagevec_add(&pagevec, page);
+		fscache_mark_pages_cached(op, &pagevec);
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * allocate blocks in the cache in which to store a set of pages
+ * - cache withdrawal is prevented by the caller
+ * - returns -EINTR if interrupted
+ * - returns -ENOMEM if ran out of memory
+ * - returns -ENOBUFS if some buffers couldn't be made available
+ * - returns -ENOBUFS if some pages are beyond EOF
+ * - otherwise:
+ *   - -ENODATA will be returned
+ * - metadata will be retained for any page marked
+ */
+int cachefiles_allocate_pages(struct fscache_retrieval *op,
+			      struct list_head *pages,
+			      unsigned *nr_pages,
+			      gfp_t gfp)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	struct pagevec pagevec;
+	struct page *page;
+	int ret;
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("%p,,,%d,", object, *nr_pages);
+
+	ret = cachefiles_has_space(cache, 0, *nr_pages);
+	if (ret == 0) {
+		pagevec_init(&pagevec, 0);
+
+		list_for_each_entry(page, pages, lru) {
+			if (pagevec_add(&pagevec, page) == 0)
+				fscache_mark_pages_cached(op, &pagevec);
+		}
+
+		if (pagevec_count(&pagevec) > 0)
+			fscache_mark_pages_cached(op, &pagevec);
+		ret = -ENODATA;
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * request a page be stored in the cache
+ * - cache withdrawal is prevented by the caller
+ * - this request may be ignored if there's no cache block available, in which
+ *   case -ENOBUFS will be returned
+ * - if the op is in progress, 0 will be returned
+ */
+int cachefiles_write_page(struct fscache_storage *op, struct page *page)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+	mm_segment_t old_fs;
+	struct file *file;
+	loff_t pos;
+	void *data;
+	int ret;
+
+	ASSERT(op != NULL);
+	ASSERT(page != NULL);
+
+	object = container_of(op->op.object,
+			      struct cachefiles_object, fscache);
+
+	_enter("%p,%p{%lx},,,", object, page, page->index);
+
+	if (!object->backer) {
+		_leave(" = -ENOBUFS");
+		return -ENOBUFS;
+	}
+
+	ASSERT(S_ISREG(object->backer->d_inode->i_mode));
+
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	/* write the page to the backing filesystem and let it store it in its
+	 * own time */
+	dget(object->backer);
+	mntget(cache->mnt);
+	file = dentry_open(object->backer, cache->mnt, O_RDWR,
+			   cache->cache_cred);
+	if (IS_ERR(file)) {
+		ret = PTR_ERR(file);
+	} else {
+		ret = -EIO;
+		if (file->f_op->write) {
+			pos = (loff_t) page->index << PAGE_SHIFT;
+			data = kmap(page);
+			old_fs = get_fs();
+			set_fs(KERNEL_DS);
+			ret = file->f_op->write(
+				file, (const void __user *) data, PAGE_SIZE,
+				&pos);
+			set_fs(old_fs);
+			kunmap(page);
+			if (ret != PAGE_SIZE)
+				ret = -EIO;
+		}
+		fput(file);
+	}
+
+	if (ret < 0) {
+		if (ret == -EIO)
+			cachefiles_io_error_obj(
+				object, "Write page to backing file failed");
+		ret = -ENOBUFS;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * detach a backing block from a page
+ * - cache withdrawal is prevented by the caller
+ */
+void cachefiles_uncache_page(struct fscache_object *_object, struct page *page)
+{
+	struct cachefiles_object *object;
+	struct cachefiles_cache *cache;
+
+	object = container_of(_object, struct cachefiles_object, fscache);
+	cache = container_of(object->fscache.cache,
+			     struct cachefiles_cache, cache);
+
+	_enter("%p,{%lu}", object, page->index);
+
+	spin_unlock(&object->fscache.cookie->lock);
+}
diff --git a/fs/cachefiles/security.c b/fs/cachefiles/security.c
new file mode 100644
index 000000000000..b5808cdb2232
--- /dev/null
+++ b/fs/cachefiles/security.c
@@ -0,0 +1,116 @@
+/* CacheFiles security management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/fs.h>
+#include <linux/cred.h>
+#include "internal.h"
+
+/*
+ * determine the security context within which we access the cache from within
+ * the kernel
+ */
+int cachefiles_get_security_ID(struct cachefiles_cache *cache)
+{
+	struct cred *new;
+	int ret;
+
+	_enter("{%s}", cache->secctx);
+
+	new = prepare_kernel_cred(current);
+	if (!new) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	if (cache->secctx) {
+		ret = set_security_override_from_ctx(new, cache->secctx);
+		if (ret < 0) {
+			put_cred(new);
+			printk(KERN_ERR "CacheFiles:"
+			       " Security denies permission to nominate"
+			       " security context: error %d\n",
+			       ret);
+			goto error;
+		}
+	}
+
+	cache->cache_cred = new;
+	ret = 0;
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * see if mkdir and create can be performed in the root directory
+ */
+static int cachefiles_check_cache_dir(struct cachefiles_cache *cache,
+				      struct dentry *root)
+{
+	int ret;
+
+	ret = security_inode_mkdir(root->d_inode, root, 0);
+	if (ret < 0) {
+		printk(KERN_ERR "CacheFiles:"
+		       " Security denies permission to make dirs: error %d",
+		       ret);
+		return ret;
+	}
+
+	ret = security_inode_create(root->d_inode, root, 0);
+	if (ret < 0)
+		printk(KERN_ERR "CacheFiles:"
+		       " Security denies permission to create files: error %d",
+		       ret);
+
+	return ret;
+}
+
+/*
+ * check the security details of the on-disk cache
+ * - must be called with security override in force
+ */
+int cachefiles_determine_cache_security(struct cachefiles_cache *cache,
+					struct dentry *root,
+					const struct cred **_saved_cred)
+{
+	struct cred *new;
+	int ret;
+
+	_enter("");
+
+	/* duplicate the cache creds for COW (the override is currently in
+	 * force, so we can use prepare_creds() to do this) */
+	new = prepare_creds();
+	if (!new)
+		return -ENOMEM;
+
+	cachefiles_end_secure(cache, *_saved_cred);
+
+	/* use the cache root dir's security context as the basis with
+	 * which create files */
+	ret = set_create_files_as(new, root->d_inode);
+	if (ret < 0) {
+		_leave(" = %d [cfa]", ret);
+		return ret;
+	}
+
+	put_cred(cache->cache_cred);
+	cache->cache_cred = new;
+
+	cachefiles_begin_secure(cache, _saved_cred);
+	ret = cachefiles_check_cache_dir(cache, root);
+
+	if (ret == -EOPNOTSUPP)
+		ret = 0;
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/cachefiles/xattr.c b/fs/cachefiles/xattr.c
new file mode 100644
index 000000000000..f3e7a0bf068b
--- /dev/null
+++ b/fs/cachefiles/xattr.c
@@ -0,0 +1,291 @@
+/* CacheFiles extended attribute management
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/file.h>
+#include <linux/fs.h>
+#include <linux/fsnotify.h>
+#include <linux/quotaops.h>
+#include <linux/xattr.h>
+#include "internal.h"
+
+static const char cachefiles_xattr_cache[] =
+	XATTR_USER_PREFIX "CacheFiles.cache";
+
+/*
+ * check the type label on an object
+ * - done using xattrs
+ */
+int cachefiles_check_object_type(struct cachefiles_object *object)
+{
+	struct dentry *dentry = object->dentry;
+	char type[3], xtype[3];
+	int ret;
+
+	ASSERT(dentry);
+	ASSERT(dentry->d_inode);
+
+	if (!object->fscache.cookie)
+		strcpy(type, "C3");
+	else
+		snprintf(type, 3, "%02x", object->fscache.cookie->def->type);
+
+	_enter("%p{%s}", object, type);
+
+	/* attempt to install a type label directly */
+	ret = vfs_setxattr(dentry, cachefiles_xattr_cache, type, 2,
+			   XATTR_CREATE);
+	if (ret == 0) {
+		_debug("SET"); /* we succeeded */
+		goto error;
+	}
+
+	if (ret != -EEXIST) {
+		kerror("Can't set xattr on %*.*s [%lu] (err %d)",
+		       dentry->d_name.len, dentry->d_name.len,
+		       dentry->d_name.name, dentry->d_inode->i_ino,
+		       -ret);
+		goto error;
+	}
+
+	/* read the current type label */
+	ret = vfs_getxattr(dentry, cachefiles_xattr_cache, xtype, 3);
+	if (ret < 0) {
+		if (ret == -ERANGE)
+			goto bad_type_length;
+
+		kerror("Can't read xattr on %*.*s [%lu] (err %d)",
+		       dentry->d_name.len, dentry->d_name.len,
+		       dentry->d_name.name, dentry->d_inode->i_ino,
+		       -ret);
+		goto error;
+	}
+
+	/* check the type is what we're expecting */
+	if (ret != 2)
+		goto bad_type_length;
+
+	if (xtype[0] != type[0] || xtype[1] != type[1])
+		goto bad_type;
+
+	ret = 0;
+
+error:
+	_leave(" = %d", ret);
+	return ret;
+
+bad_type_length:
+	kerror("Cache object %lu type xattr length incorrect",
+	       dentry->d_inode->i_ino);
+	ret = -EIO;
+	goto error;
+
+bad_type:
+	xtype[2] = 0;
+	kerror("Cache object %*.*s [%lu] type %s not %s",
+	       dentry->d_name.len, dentry->d_name.len,
+	       dentry->d_name.name, dentry->d_inode->i_ino,
+	       xtype, type);
+	ret = -EIO;
+	goto error;
+}
+
+/*
+ * set the state xattr on a cache file
+ */
+int cachefiles_set_object_xattr(struct cachefiles_object *object,
+				struct cachefiles_xattr *auxdata)
+{
+	struct dentry *dentry = object->dentry;
+	int ret;
+
+	ASSERT(object->fscache.cookie);
+	ASSERT(dentry);
+
+	_enter("%p,#%d", object, auxdata->len);
+
+	/* attempt to install the cache metadata directly */
+	_debug("SET %s #%u", object->fscache.cookie->def->name, auxdata->len);
+
+	ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
+			   &auxdata->type, auxdata->len,
+			   XATTR_CREATE);
+	if (ret < 0 && ret != -ENOMEM)
+		cachefiles_io_error_obj(
+			object,
+			"Failed to set xattr with error %d", ret);
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * update the state xattr on a cache file
+ */
+int cachefiles_update_object_xattr(struct cachefiles_object *object,
+				   struct cachefiles_xattr *auxdata)
+{
+	struct dentry *dentry = object->dentry;
+	int ret;
+
+	ASSERT(object->fscache.cookie);
+	ASSERT(dentry);
+
+	_enter("%p,#%d", object, auxdata->len);
+
+	/* attempt to install the cache metadata directly */
+	_debug("SET %s #%u", object->fscache.cookie->def->name, auxdata->len);
+
+	ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
+			   &auxdata->type, auxdata->len,
+			   XATTR_REPLACE);
+	if (ret < 0 && ret != -ENOMEM)
+		cachefiles_io_error_obj(
+			object,
+			"Failed to update xattr with error %d", ret);
+
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * check the state xattr on a cache file
+ * - return -ESTALE if the object should be deleted
+ */
+int cachefiles_check_object_xattr(struct cachefiles_object *object,
+				  struct cachefiles_xattr *auxdata)
+{
+	struct cachefiles_xattr *auxbuf;
+	struct dentry *dentry = object->dentry;
+	int ret;
+
+	_enter("%p,#%d", object, auxdata->len);
+
+	ASSERT(dentry);
+	ASSERT(dentry->d_inode);
+
+	auxbuf = kmalloc(sizeof(struct cachefiles_xattr) + 512, GFP_KERNEL);
+	if (!auxbuf) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	/* read the current type label */
+	ret = vfs_getxattr(dentry, cachefiles_xattr_cache,
+			   &auxbuf->type, 512 + 1);
+	if (ret < 0) {
+		if (ret == -ENODATA)
+			goto stale; /* no attribute - power went off
+				     * mid-cull? */
+
+		if (ret == -ERANGE)
+			goto bad_type_length;
+
+		cachefiles_io_error_obj(object,
+					"Can't read xattr on %lu (err %d)",
+					dentry->d_inode->i_ino, -ret);
+		goto error;
+	}
+
+	/* check the on-disk object */
+	if (ret < 1)
+		goto bad_type_length;
+
+	if (auxbuf->type != auxdata->type)
+		goto stale;
+
+	auxbuf->len = ret;
+
+	/* consult the netfs */
+	if (object->fscache.cookie->def->check_aux) {
+		enum fscache_checkaux result;
+		unsigned int dlen;
+
+		dlen = auxbuf->len - 1;
+
+		_debug("checkaux %s #%u",
+		       object->fscache.cookie->def->name, dlen);
+
+		result = fscache_check_aux(&object->fscache,
+					   &auxbuf->data, dlen);
+
+		switch (result) {
+			/* entry okay as is */
+		case FSCACHE_CHECKAUX_OKAY:
+			goto okay;
+
+			/* entry requires update */
+		case FSCACHE_CHECKAUX_NEEDS_UPDATE:
+			break;
+
+			/* entry requires deletion */
+		case FSCACHE_CHECKAUX_OBSOLETE:
+			goto stale;
+
+		default:
+			BUG();
+		}
+
+		/* update the current label */
+		ret = vfs_setxattr(dentry, cachefiles_xattr_cache,
+				   &auxdata->type, auxdata->len,
+				   XATTR_REPLACE);
+		if (ret < 0) {
+			cachefiles_io_error_obj(object,
+						"Can't update xattr on %lu"
+						" (error %d)",
+						dentry->d_inode->i_ino, -ret);
+			goto error;
+		}
+	}
+
+okay:
+	ret = 0;
+
+error:
+	kfree(auxbuf);
+	_leave(" = %d", ret);
+	return ret;
+
+bad_type_length:
+	kerror("Cache object %lu xattr length incorrect",
+	       dentry->d_inode->i_ino);
+	ret = -EIO;
+	goto error;
+
+stale:
+	ret = -ESTALE;
+	goto error;
+}
+
+/*
+ * remove the object's xattr to mark it stale
+ */
+int cachefiles_remove_object_xattr(struct cachefiles_cache *cache,
+				   struct dentry *dentry)
+{
+	int ret;
+
+	ret = vfs_removexattr(dentry, cachefiles_xattr_cache);
+	if (ret < 0) {
+		if (ret == -ENOENT || ret == -ENODATA)
+			ret = 0;
+		else if (ret != -ENOMEM)
+			cachefiles_io_error(cache,
+					    "Can't remove xattr from %lu"
+					    " (error %d)",
+					    dentry->d_inode->i_ino, -ret);
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 2f35cccfcd8d..54dce78fbb73 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -254,7 +254,7 @@ cifs_create(struct inode *inode, struct dentry *direntry, int mode,
 		return -ENOMEM;
 	}
 
-	mode &= ~current->fs->umask;
+	mode &= ~current_umask();
 	if (oplockEnabled)
 		oplock = REQ_OPLOCK;
 
@@ -479,7 +479,7 @@ int cifs_mknod(struct inode *inode, struct dentry *direntry, int mode,
 		rc = -ENOMEM;
 	else if (pTcon->unix_ext) {
 		struct cifs_unix_set_info_args args = {
-			.mode	= mode & ~current->fs->umask,
+			.mode	= mode & ~current_umask(),
 			.ctime	= NO_CHANGE_64,
 			.atime	= NO_CHANGE_64,
 			.mtime	= NO_CHANGE_64,
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index a8797cc60805..f121a80fdd6f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -1125,7 +1125,7 @@ int cifs_mkdir(struct inode *inode, struct dentry *direntry, int mode)
 			goto mkdir_out;
 		}
 
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 		rc = CIFSPOSIXCreate(xid, pTcon, SMB_O_DIRECTORY | SMB_O_CREAT,
 				mode, NULL /* netfid */, pInfo, &oplock,
 				full_path, cifs_sb->local_nls,
@@ -1204,7 +1204,7 @@ mkdir_get_info:
 		if ((direntry->d_inode) && (direntry->d_inode->i_nlink < 2))
 				direntry->d_inode->i_nlink = 2;
 
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 		/* must turn on setgid bit if parent dir has it */
 		if (inode->i_mode & S_ISGID)
 			mode |= S_ISGID;
diff --git a/fs/compat.c b/fs/compat.c
index 55efdfebdf5a..3f84d5f15889 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -51,6 +51,7 @@
 #include <linux/poll.h>
 #include <linux/mm.h>
 #include <linux/eventpoll.h>
+#include <linux/fs_struct.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1195,16 +1196,12 @@ out:
 	return ret;
 }
 
-asmlinkage ssize_t
-compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen)
+static size_t compat_readv(struct file *file,
+			   const struct compat_iovec __user *vec,
+			   unsigned long vlen, loff_t *pos)
 {
-	struct file *file;
 	ssize_t ret = -EBADF;
 
-	file = fget(fd);
-	if (!file)
-		return -EBADF;
-
 	if (!(file->f_mode & FMODE_READ))
 		goto out;
 
@@ -1212,25 +1209,56 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign
 	if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read))
 		goto out;
 
-	ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos);
+	ret = compat_do_readv_writev(READ, file, vec, vlen, pos);
 
 out:
 	if (ret > 0)
 		add_rchar(current, ret);
 	inc_syscr(current);
-	fput(file);
 	return ret;
 }
 
 asmlinkage ssize_t
-compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen)
+compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec,
+		 unsigned long vlen)
 {
 	struct file *file;
-	ssize_t ret = -EBADF;
+	int fput_needed;
+	ssize_t ret;
 
-	file = fget(fd);
+	file = fget_light(fd, &fput_needed);
 	if (!file)
 		return -EBADF;
+	ret = compat_readv(file, vec, vlen, &file->f_pos);
+	fput_light(file, fput_needed);
+	return ret;
+}
+
+asmlinkage ssize_t
+compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec,
+		  unsigned long vlen, u32 pos_low, u32 pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	struct file *file;
+	int fput_needed;
+	ssize_t ret;
+
+	if (pos < 0)
+		return -EINVAL;
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		return -EBADF;
+	ret = compat_readv(file, vec, vlen, &pos);
+	fput_light(file, fput_needed);
+	return ret;
+}
+
+static size_t compat_writev(struct file *file,
+			    const struct compat_iovec __user *vec,
+			    unsigned long vlen, loff_t *pos)
+{
+	ssize_t ret = -EBADF;
+
 	if (!(file->f_mode & FMODE_WRITE))
 		goto out;
 
@@ -1238,13 +1266,47 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig
 	if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write))
 		goto out;
 
-	ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos);
+	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos);
 
 out:
 	if (ret > 0)
 		add_wchar(current, ret);
 	inc_syscw(current);
-	fput(file);
+	return ret;
+}
+
+asmlinkage ssize_t
+compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec,
+		  unsigned long vlen)
+{
+	struct file *file;
+	int fput_needed;
+	ssize_t ret;
+
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		return -EBADF;
+	ret = compat_writev(file, vec, vlen, &file->f_pos);
+	fput_light(file, fput_needed);
+	return ret;
+}
+
+asmlinkage ssize_t
+compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec,
+		   unsigned long vlen, u32 pos_low, u32 pos_high)
+{
+	loff_t pos = ((loff_t)pos_high << 32) | pos_low;
+	struct file *file;
+	int fput_needed;
+	ssize_t ret;
+
+	if (pos < 0)
+		return -EINVAL;
+	file = fget_light(fd, &fput_needed);
+	if (!file)
+		return -EBADF;
+	ret = compat_writev(file, vec, vlen, &pos);
+	fput_light(file, fput_needed);
 	return ret;
 }
 
@@ -1441,12 +1503,15 @@ int compat_do_execve(char * filename,
 	bprm->cred = prepare_exec_creds();
 	if (!bprm->cred)
 		goto out_unlock;
-	check_unsafe_exec(bprm);
+
+	retval = check_unsafe_exec(bprm);
+	if (retval)
+		goto out_unlock;
 
 	file = open_exec(filename);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
-		goto out_unlock;
+		goto out_unmark;
 
 	sched_exec();
 
@@ -1488,6 +1553,9 @@ int compat_do_execve(char * filename,
 		goto out;
 
 	/* execve succeeded */
+	write_lock(&current->fs->lock);
+	current->fs->in_exec = 0;
+	write_unlock(&current->fs->lock);
 	current->in_execve = 0;
 	mutex_unlock(&current->cred_exec_mutex);
 	acct_update_integrals(current);
@@ -1506,6 +1574,11 @@ out_file:
 		fput(bprm->file);
 	}
 
+out_unmark:
+	write_lock(&current->fs->lock);
+	current->fs->in_exec = 0;
+	write_unlock(&current->fs->lock);
+
 out_unlock:
 	current->in_execve = 0;
 	mutex_unlock(&current->cred_exec_mutex);
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index ff786687e93b..3e87ce443ea2 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -23,7 +23,7 @@
 #include <linux/if.h>
 #include <linux/if_bridge.h>
 #include <linux/slab.h>
-#include <linux/raid/md.h>
+#include <linux/raid/md_u.h>
 #include <linux/kd.h>
 #include <linux/route.h>
 #include <linux/in6.h>
diff --git a/fs/cramfs/inode.c b/fs/cramfs/inode.c
index a07338d2d140..dd3634e4c967 100644
--- a/fs/cramfs/inode.c
+++ b/fs/cramfs/inode.c
@@ -318,6 +318,7 @@ out:
 static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = CRAMFS_MAGIC;
 	buf->f_bsize = PAGE_CACHE_SIZE;
@@ -326,6 +327,8 @@ static int cramfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = 0;
 	buf->f_files = CRAMFS_SB(sb)->files;
 	buf->f_ffree = 0;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = CRAMFS_MAXPATHLEN;
 	return 0;
 }
@@ -459,11 +462,14 @@ static struct dentry * cramfs_lookup(struct inode *dir, struct dentry *dentry, s
 static int cramfs_readpage(struct file *file, struct page * page)
 {
 	struct inode *inode = page->mapping->host;
-	u32 maxblock, bytes_filled;
+	u32 maxblock;
+	int bytes_filled;
 	void *pgdata;
 
 	maxblock = (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	bytes_filled = 0;
+	pgdata = kmap(page);
+
 	if (page->index < maxblock) {
 		struct super_block *sb = inode->i_sb;
 		u32 blkptr_offset = OFFSET(inode) + page->index*4;
@@ -472,30 +478,43 @@ static int cramfs_readpage(struct file *file, struct page * page)
 		start_offset = OFFSET(inode) + maxblock*4;
 		mutex_lock(&read_mutex);
 		if (page->index)
-			start_offset = *(u32 *) cramfs_read(sb, blkptr_offset-4, 4);
-		compr_len = (*(u32 *) cramfs_read(sb, blkptr_offset, 4) - start_offset);
+			start_offset = *(u32 *) cramfs_read(sb, blkptr_offset-4,
+				4);
+		compr_len = (*(u32 *) cramfs_read(sb, blkptr_offset, 4) -
+			start_offset);
 		mutex_unlock(&read_mutex);
-		pgdata = kmap(page);
+
 		if (compr_len == 0)
 			; /* hole */
-		else if (compr_len > (PAGE_CACHE_SIZE << 1))
-			printk(KERN_ERR "cramfs: bad compressed blocksize %u\n", compr_len);
-		else {
+		else if (unlikely(compr_len > (PAGE_CACHE_SIZE << 1))) {
+			pr_err("cramfs: bad compressed blocksize %u\n",
+				compr_len);
+			goto err;
+		} else {
 			mutex_lock(&read_mutex);
 			bytes_filled = cramfs_uncompress_block(pgdata,
 				 PAGE_CACHE_SIZE,
 				 cramfs_read(sb, start_offset, compr_len),
 				 compr_len);
 			mutex_unlock(&read_mutex);
+			if (unlikely(bytes_filled < 0))
+				goto err;
 		}
-	} else
-		pgdata = kmap(page);
+	}
+
 	memset(pgdata + bytes_filled, 0, PAGE_CACHE_SIZE - bytes_filled);
-	kunmap(page);
 	flush_dcache_page(page);
+	kunmap(page);
 	SetPageUptodate(page);
 	unlock_page(page);
 	return 0;
+
+err:
+	kunmap(page);
+	ClearPageUptodate(page);
+	SetPageError(page);
+	unlock_page(page);
+	return 0;
 }
 
 static const struct address_space_operations cramfs_aops = {
diff --git a/fs/cramfs/uncompress.c b/fs/cramfs/uncompress.c
index fc3ccb74626f..023329800d2e 100644
--- a/fs/cramfs/uncompress.c
+++ b/fs/cramfs/uncompress.c
@@ -50,7 +50,7 @@ int cramfs_uncompress_block(void *dst, int dstlen, void *src, int srclen)
 err:
 	printk("Error %d while decompressing!\n", err);
 	printk("%p(%d)->%p(%d)\n", src, srclen, dst, dstlen);
-	return 0;
+	return -EIO;
 }
 
 int cramfs_uncompress_init(void)
diff --git a/fs/dcache.c b/fs/dcache.c
index 90bbd7e1b116..761d30be2683 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -17,7 +17,6 @@
 #include <linux/syscalls.h>
 #include <linux/string.h>
 #include <linux/mm.h>
-#include <linux/fdtable.h>
 #include <linux/fs.h>
 #include <linux/fsnotify.h>
 #include <linux/slab.h>
@@ -32,6 +31,7 @@
 #include <linux/seqlock.h>
 #include <linux/swap.h>
 #include <linux/bootmem.h>
+#include <linux/fs_struct.h>
 #include "internal.h"
 
 int sysctl_vfs_cache_pressure __read_mostly = 100;
diff --git a/fs/drop_caches.c b/fs/drop_caches.c
index 44d725f612cf..b6a719a909f8 100644
--- a/fs/drop_caches.c
+++ b/fs/drop_caches.c
@@ -18,7 +18,7 @@ static void drop_pagecache_sb(struct super_block *sb)
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
 			continue;
 		if (inode->i_mapping->nrpages == 0)
 			continue;
diff --git a/fs/efs/super.c b/fs/efs/super.c
index 73b19cfc91fc..f04942810818 100644
--- a/fs/efs/super.c
+++ b/fs/efs/super.c
@@ -329,18 +329,22 @@ out_no_fs:
 }
 
 static int efs_statfs(struct dentry *dentry, struct kstatfs *buf) {
-	struct efs_sb_info *sb = SUPER_INFO(dentry->d_sb);
+	struct super_block *sb = dentry->d_sb;
+	struct efs_sb_info *sbi = SUPER_INFO(sb);
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type    = EFS_SUPER_MAGIC;	/* efs magic number */
 	buf->f_bsize   = EFS_BLOCKSIZE;		/* blocksize */
-	buf->f_blocks  = sb->total_groups *	/* total data blocks */
-			(sb->group_size - sb->inode_blocks);
-	buf->f_bfree   = sb->data_free;		/* free data blocks */
-	buf->f_bavail  = sb->data_free;		/* free blocks for non-root */
-	buf->f_files   = sb->total_groups *	/* total inodes */
-			sb->inode_blocks *
+	buf->f_blocks  = sbi->total_groups *	/* total data blocks */
+			(sbi->group_size - sbi->inode_blocks);
+	buf->f_bfree   = sbi->data_free;	/* free data blocks */
+	buf->f_bavail  = sbi->data_free;	/* free blocks for non-root */
+	buf->f_files   = sbi->total_groups *	/* total inodes */
+			sbi->inode_blocks *
 			(EFS_BLOCKSIZE / sizeof(struct efs_dinode));
-	buf->f_ffree   = sb->inode_free;	/* free inodes */
+	buf->f_ffree   = sbi->inode_free;	/* free inodes */
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = EFS_MAXNAMELEN;	/* max filename length */
 
 	return 0;
diff --git a/fs/exec.c b/fs/exec.c
index c5128fbc9165..052a961e41aa 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -53,6 +53,7 @@
 #include <linux/tracehook.h>
 #include <linux/kmod.h>
 #include <linux/fsnotify.h>
+#include <linux/fs_struct.h>
 
 #include <asm/uaccess.h>
 #include <asm/mmu_context.h>
@@ -1056,28 +1057,35 @@ EXPORT_SYMBOL(install_exec_creds);
  * - the caller must hold current->cred_exec_mutex to protect against
  *   PTRACE_ATTACH
  */
-void check_unsafe_exec(struct linux_binprm *bprm)
+int check_unsafe_exec(struct linux_binprm *bprm)
 {
 	struct task_struct *p = current, *t;
 	unsigned long flags;
-	unsigned n_fs, n_sighand;
+	unsigned n_fs;
+	int res = 0;
 
 	bprm->unsafe = tracehook_unsafe_exec(p);
 
 	n_fs = 1;
-	n_sighand = 1;
+	write_lock(&p->fs->lock);
 	lock_task_sighand(p, &flags);
 	for (t = next_thread(p); t != p; t = next_thread(t)) {
 		if (t->fs == p->fs)
 			n_fs++;
-		n_sighand++;
 	}
 
-	if (atomic_read(&p->fs->count) > n_fs ||
-	    atomic_read(&p->sighand->count) > n_sighand)
+	if (p->fs->users > n_fs) {
 		bprm->unsafe |= LSM_UNSAFE_SHARE;
+	} else {
+		if (p->fs->in_exec)
+			res = -EAGAIN;
+		p->fs->in_exec = 1;
+	}
 
 	unlock_task_sighand(p, &flags);
+	write_unlock(&p->fs->lock);
+
+	return res;
 }
 
 /* 
@@ -1296,12 +1304,15 @@ int do_execve(char * filename,
 	bprm->cred = prepare_exec_creds();
 	if (!bprm->cred)
 		goto out_unlock;
-	check_unsafe_exec(bprm);
+
+	retval = check_unsafe_exec(bprm);
+	if (retval)
+		goto out_unlock;
 
 	file = open_exec(filename);
 	retval = PTR_ERR(file);
 	if (IS_ERR(file))
-		goto out_unlock;
+		goto out_unmark;
 
 	sched_exec();
 
@@ -1344,6 +1355,9 @@ int do_execve(char * filename,
 		goto out;
 
 	/* execve succeeded */
+	write_lock(&current->fs->lock);
+	current->fs->in_exec = 0;
+	write_unlock(&current->fs->lock);
 	current->in_execve = 0;
 	mutex_unlock(&current->cred_exec_mutex);
 	acct_update_integrals(current);
@@ -1362,6 +1376,11 @@ out_file:
 		fput(bprm->file);
 	}
 
+out_unmark:
+	write_lock(&current->fs->lock);
+	current->fs->in_exec = 0;
+	write_unlock(&current->fs->lock);
+
 out_unlock:
 	current->in_execve = 0;
 	mutex_unlock(&current->cred_exec_mutex);
diff --git a/fs/exofs/BUGS b/fs/exofs/BUGS
new file mode 100644
index 000000000000..1b2d4c63a579
--- /dev/null
+++ b/fs/exofs/BUGS
@@ -0,0 +1,3 @@
+- Out-of-space may cause a severe problem if the object (and directory entry)
+  were written, but the inode attributes failed. Then if the filesystem was
+  unmounted and mounted the kernel can get into an endless loop doing a readdir.
diff --git a/fs/exofs/Kbuild b/fs/exofs/Kbuild
new file mode 100644
index 000000000000..cc2d22db119c
--- /dev/null
+++ b/fs/exofs/Kbuild
@@ -0,0 +1,16 @@
+#
+# Kbuild for the EXOFS module
+#
+# Copyright (C) 2008 Panasas Inc.  All rights reserved.
+#
+# Authors:
+#   Boaz Harrosh <bharrosh@panasas.com>
+#
+# This program is free software; you can redistribute it and/or modify
+# it under the terms of the GNU General Public License version 2
+#
+# Kbuild - Gets included from the Kernels Makefile and build system
+#
+
+exofs-y := osd.o inode.o file.o symlink.o namei.o dir.o super.o
+obj-$(CONFIG_EXOFS_FS) += exofs.o
diff --git a/fs/exofs/Kconfig b/fs/exofs/Kconfig
new file mode 100644
index 000000000000..86194b2f799d
--- /dev/null
+++ b/fs/exofs/Kconfig
@@ -0,0 +1,13 @@
+config EXOFS_FS
+	tristate "exofs: OSD based file system support"
+	depends on SCSI_OSD_ULD
+	help
+	  EXOFS is a file system that uses an OSD storage device,
+	  as its backing storage.
+
+# Debugging-related stuff
+config EXOFS_DEBUG
+	bool "Enable debugging"
+	depends on EXOFS_FS
+	help
+	  This option enables EXOFS debug prints.
diff --git a/fs/exofs/common.h b/fs/exofs/common.h
new file mode 100644
index 000000000000..b1512c4bb8c7
--- /dev/null
+++ b/fs/exofs/common.h
@@ -0,0 +1,184 @@
+/*
+ * common.h - Common definitions for both Kernel and user-mode utilities
+ *
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#ifndef __EXOFS_COM_H__
+#define __EXOFS_COM_H__
+
+#include <linux/types.h>
+
+#include <scsi/osd_attributes.h>
+#include <scsi/osd_initiator.h>
+#include <scsi/osd_sec.h>
+
+/****************************************************************************
+ * Object ID related defines
+ * NOTE: inode# = object ID - EXOFS_OBJ_OFF
+ ****************************************************************************/
+#define EXOFS_MIN_PID   0x10000	/* Smallest partition ID */
+#define EXOFS_OBJ_OFF	0x10000	/* offset for objects */
+#define EXOFS_SUPER_ID	0x10000	/* object ID for on-disk superblock */
+#define EXOFS_ROOT_ID	0x10002	/* object ID for root directory */
+
+/* exofs Application specific page/attribute */
+# define EXOFS_APAGE_FS_DATA	(OSD_APAGE_APP_DEFINED_FIRST + 3)
+# define EXOFS_ATTR_INODE_DATA	1
+
+/*
+ * The maximum number of files we can have is limited by the size of the
+ * inode number.  This is the largest object ID that the file system supports.
+ * Object IDs 0, 1, and 2 are always in use (see above defines).
+ */
+enum {
+	EXOFS_MAX_INO_ID = (sizeof(ino_t) * 8 == 64) ? ULLONG_MAX :
+					(1ULL << (sizeof(ino_t) * 8ULL - 1ULL)),
+	EXOFS_MAX_ID	 = (EXOFS_MAX_INO_ID - 1 - EXOFS_OBJ_OFF),
+};
+
+/****************************************************************************
+ * Misc.
+ ****************************************************************************/
+#define EXOFS_BLKSHIFT	12
+#define EXOFS_BLKSIZE	(1UL << EXOFS_BLKSHIFT)
+
+/****************************************************************************
+ * superblock-related things
+ ****************************************************************************/
+#define EXOFS_SUPER_MAGIC	0x5DF5
+
+/*
+ * The file system control block - stored in an object's data (mainly, the one
+ * with ID EXOFS_SUPER_ID).  This is where the in-memory superblock is stored
+ * on disk.  Right now it just has a magic value, which is basically a sanity
+ * check on our ability to communicate with the object store.
+ */
+struct exofs_fscb {
+	__le64  s_nextid;	/* Highest object ID used */
+	__le32  s_numfiles;	/* Number of files on fs */
+	__le16  s_magic;	/* Magic signature */
+	__le16  s_newfs;	/* Non-zero if this is a new fs */
+};
+
+/****************************************************************************
+ * inode-related things
+ ****************************************************************************/
+#define EXOFS_IDATA		5
+
+/*
+ * The file control block - stored in an object's attributes.  This is where
+ * the in-memory inode is stored on disk.
+ */
+struct exofs_fcb {
+	__le64  i_size;			/* Size of the file */
+	__le16  i_mode;         	/* File mode */
+	__le16  i_links_count;  	/* Links count */
+	__le32  i_uid;          	/* Owner Uid */
+	__le32  i_gid;          	/* Group Id */
+	__le32  i_atime;        	/* Access time */
+	__le32  i_ctime;        	/* Creation time */
+	__le32  i_mtime;        	/* Modification time */
+	__le32  i_flags;        	/* File flags (unused for now)*/
+	__le32  i_generation;   	/* File version (for NFS) */
+	__le32  i_data[EXOFS_IDATA];	/* Short symlink names and device #s */
+};
+
+#define EXOFS_INO_ATTR_SIZE	sizeof(struct exofs_fcb)
+
+/* This is the Attribute the fcb is stored in */
+static const struct __weak osd_attr g_attr_inode_data = ATTR_DEF(
+	EXOFS_APAGE_FS_DATA,
+	EXOFS_ATTR_INODE_DATA,
+	EXOFS_INO_ATTR_SIZE);
+
+/****************************************************************************
+ * dentry-related things
+ ****************************************************************************/
+#define EXOFS_NAME_LEN	255
+
+/*
+ * The on-disk directory entry
+ */
+struct exofs_dir_entry {
+	__le64		inode_no;		/* inode number           */
+	__le16		rec_len;		/* directory entry length */
+	u8		name_len;		/* name length            */
+	u8		file_type;		/* umm...file type        */
+	char		name[EXOFS_NAME_LEN];	/* file name              */
+};
+
+enum {
+	EXOFS_FT_UNKNOWN,
+	EXOFS_FT_REG_FILE,
+	EXOFS_FT_DIR,
+	EXOFS_FT_CHRDEV,
+	EXOFS_FT_BLKDEV,
+	EXOFS_FT_FIFO,
+	EXOFS_FT_SOCK,
+	EXOFS_FT_SYMLINK,
+	EXOFS_FT_MAX
+};
+
+#define EXOFS_DIR_PAD			4
+#define EXOFS_DIR_ROUND			(EXOFS_DIR_PAD - 1)
+#define EXOFS_DIR_REC_LEN(name_len) \
+	(((name_len) + offsetof(struct exofs_dir_entry, name)  + \
+	  EXOFS_DIR_ROUND) & ~EXOFS_DIR_ROUND)
+
+/*************************
+ * function declarations *
+ *************************/
+/* osd.c                 */
+void exofs_make_credential(u8 cred_a[OSD_CAP_LEN],
+			   const struct osd_obj_id *obj);
+
+int exofs_check_ok_resid(struct osd_request *or, u64 *in_resid, u64 *out_resid);
+static inline int exofs_check_ok(struct osd_request *or)
+{
+	return exofs_check_ok_resid(or, NULL, NULL);
+}
+int exofs_sync_op(struct osd_request *or, int timeout, u8 *cred);
+int exofs_async_op(struct osd_request *or,
+	osd_req_done_fn *async_done, void *caller_context, u8 *cred);
+
+int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr);
+
+int osd_req_read_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
+
+int osd_req_write_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void *buff, u64 len);
+
+#endif /*ifndef __EXOFS_COM_H__*/
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
new file mode 100644
index 000000000000..65b0c8c776a1
--- /dev/null
+++ b/fs/exofs/dir.c
@@ -0,0 +1,672 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include "exofs.h"
+
+static inline unsigned exofs_chunk_size(struct inode *inode)
+{
+	return inode->i_sb->s_blocksize;
+}
+
+static inline void exofs_put_page(struct page *page)
+{
+	kunmap(page);
+	page_cache_release(page);
+}
+
+/* Accesses dir's inode->i_size must be called under inode lock */
+static inline unsigned long dir_pages(struct inode *inode)
+{
+	return (inode->i_size + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
+}
+
+static unsigned exofs_last_byte(struct inode *inode, unsigned long page_nr)
+{
+	loff_t last_byte = inode->i_size;
+
+	last_byte -= page_nr << PAGE_CACHE_SHIFT;
+	if (last_byte > PAGE_CACHE_SIZE)
+		last_byte = PAGE_CACHE_SIZE;
+	return last_byte;
+}
+
+static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *dir = mapping->host;
+	int err = 0;
+
+	dir->i_version++;
+
+	if (!PageUptodate(page))
+		SetPageUptodate(page);
+
+	if (pos+len > dir->i_size) {
+		i_size_write(dir, pos+len);
+		mark_inode_dirty(dir);
+	}
+	set_page_dirty(page);
+
+	if (IS_DIRSYNC(dir))
+		err = write_one_page(page, 1);
+	else
+		unlock_page(page);
+
+	return err;
+}
+
+static void exofs_check_page(struct page *page)
+{
+	struct inode *dir = page->mapping->host;
+	unsigned chunk_size = exofs_chunk_size(dir);
+	char *kaddr = page_address(page);
+	unsigned offs, rec_len;
+	unsigned limit = PAGE_CACHE_SIZE;
+	struct exofs_dir_entry *p;
+	char *error;
+
+	/* if the page is the last one in the directory */
+	if ((dir->i_size >> PAGE_CACHE_SHIFT) == page->index) {
+		limit = dir->i_size & ~PAGE_CACHE_MASK;
+		if (limit & (chunk_size - 1))
+			goto Ebadsize;
+		if (!limit)
+			goto out;
+	}
+	for (offs = 0; offs <= limit - EXOFS_DIR_REC_LEN(1); offs += rec_len) {
+		p = (struct exofs_dir_entry *)(kaddr + offs);
+		rec_len = le16_to_cpu(p->rec_len);
+
+		if (rec_len < EXOFS_DIR_REC_LEN(1))
+			goto Eshort;
+		if (rec_len & 3)
+			goto Ealign;
+		if (rec_len < EXOFS_DIR_REC_LEN(p->name_len))
+			goto Enamelen;
+		if (((offs + rec_len - 1) ^ offs) & ~(chunk_size-1))
+			goto Espan;
+	}
+	if (offs != limit)
+		goto Eend;
+out:
+	SetPageChecked(page);
+	return;
+
+Ebadsize:
+	EXOFS_ERR("ERROR [exofs_check_page]: "
+		"size of directory #%lu is not a multiple of chunk size",
+		dir->i_ino
+	);
+	goto fail;
+Eshort:
+	error = "rec_len is smaller than minimal";
+	goto bad_entry;
+Ealign:
+	error = "unaligned directory entry";
+	goto bad_entry;
+Enamelen:
+	error = "rec_len is too small for name_len";
+	goto bad_entry;
+Espan:
+	error = "directory entry across blocks";
+	goto bad_entry;
+bad_entry:
+	EXOFS_ERR(
+		"ERROR [exofs_check_page]: bad entry in directory #%lu: %s - "
+		"offset=%lu, inode=%llu, rec_len=%d, name_len=%d",
+		dir->i_ino, error, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		_LLU(le64_to_cpu(p->inode_no)),
+		rec_len, p->name_len);
+	goto fail;
+Eend:
+	p = (struct exofs_dir_entry *)(kaddr + offs);
+	EXOFS_ERR("ERROR [exofs_check_page]: "
+		"entry in directory #%lu spans the page boundary"
+		"offset=%lu, inode=%llu",
+		dir->i_ino, (page->index<<PAGE_CACHE_SHIFT)+offs,
+		_LLU(le64_to_cpu(p->inode_no)));
+fail:
+	SetPageChecked(page);
+	SetPageError(page);
+}
+
+static struct page *exofs_get_page(struct inode *dir, unsigned long n)
+{
+	struct address_space *mapping = dir->i_mapping;
+	struct page *page = read_mapping_page(mapping, n, NULL);
+
+	if (!IS_ERR(page)) {
+		kmap(page);
+		if (!PageChecked(page))
+			exofs_check_page(page);
+		if (PageError(page))
+			goto fail;
+	}
+	return page;
+
+fail:
+	exofs_put_page(page);
+	return ERR_PTR(-EIO);
+}
+
+static inline int exofs_match(int len, const unsigned char *name,
+					struct exofs_dir_entry *de)
+{
+	if (len != de->name_len)
+		return 0;
+	if (!de->inode_no)
+		return 0;
+	return !memcmp(name, de->name, len);
+}
+
+static inline
+struct exofs_dir_entry *exofs_next_entry(struct exofs_dir_entry *p)
+{
+	return (struct exofs_dir_entry *)((char *)p + le16_to_cpu(p->rec_len));
+}
+
+static inline unsigned
+exofs_validate_entry(char *base, unsigned offset, unsigned mask)
+{
+	struct exofs_dir_entry *de = (struct exofs_dir_entry *)(base + offset);
+	struct exofs_dir_entry *p =
+			(struct exofs_dir_entry *)(base + (offset&mask));
+	while ((char *)p < (char *)de) {
+		if (p->rec_len == 0)
+			break;
+		p = exofs_next_entry(p);
+	}
+	return (char *)p - base;
+}
+
+static unsigned char exofs_filetype_table[EXOFS_FT_MAX] = {
+	[EXOFS_FT_UNKNOWN]	= DT_UNKNOWN,
+	[EXOFS_FT_REG_FILE]	= DT_REG,
+	[EXOFS_FT_DIR]		= DT_DIR,
+	[EXOFS_FT_CHRDEV]	= DT_CHR,
+	[EXOFS_FT_BLKDEV]	= DT_BLK,
+	[EXOFS_FT_FIFO]		= DT_FIFO,
+	[EXOFS_FT_SOCK]		= DT_SOCK,
+	[EXOFS_FT_SYMLINK]	= DT_LNK,
+};
+
+#define S_SHIFT 12
+static unsigned char exofs_type_by_mode[S_IFMT >> S_SHIFT] = {
+	[S_IFREG >> S_SHIFT]	= EXOFS_FT_REG_FILE,
+	[S_IFDIR >> S_SHIFT]	= EXOFS_FT_DIR,
+	[S_IFCHR >> S_SHIFT]	= EXOFS_FT_CHRDEV,
+	[S_IFBLK >> S_SHIFT]	= EXOFS_FT_BLKDEV,
+	[S_IFIFO >> S_SHIFT]	= EXOFS_FT_FIFO,
+	[S_IFSOCK >> S_SHIFT]	= EXOFS_FT_SOCK,
+	[S_IFLNK >> S_SHIFT]	= EXOFS_FT_SYMLINK,
+};
+
+static inline
+void exofs_set_de_type(struct exofs_dir_entry *de, struct inode *inode)
+{
+	mode_t mode = inode->i_mode;
+	de->file_type = exofs_type_by_mode[(mode & S_IFMT) >> S_SHIFT];
+}
+
+static int
+exofs_readdir(struct file *filp, void *dirent, filldir_t filldir)
+{
+	loff_t pos = filp->f_pos;
+	struct inode *inode = filp->f_path.dentry->d_inode;
+	unsigned int offset = pos & ~PAGE_CACHE_MASK;
+	unsigned long n = pos >> PAGE_CACHE_SHIFT;
+	unsigned long npages = dir_pages(inode);
+	unsigned chunk_mask = ~(exofs_chunk_size(inode)-1);
+	unsigned char *types = NULL;
+	int need_revalidate = (filp->f_version != inode->i_version);
+
+	if (pos > inode->i_size - EXOFS_DIR_REC_LEN(1))
+		return 0;
+
+	types = exofs_filetype_table;
+
+	for ( ; n < npages; n++, offset = 0) {
+		char *kaddr, *limit;
+		struct exofs_dir_entry *de;
+		struct page *page = exofs_get_page(inode, n);
+
+		if (IS_ERR(page)) {
+			EXOFS_ERR("ERROR: "
+				   "bad page in #%lu",
+				   inode->i_ino);
+			filp->f_pos += PAGE_CACHE_SIZE - offset;
+			return PTR_ERR(page);
+		}
+		kaddr = page_address(page);
+		if (unlikely(need_revalidate)) {
+			if (offset) {
+				offset = exofs_validate_entry(kaddr, offset,
+								chunk_mask);
+				filp->f_pos = (n<<PAGE_CACHE_SHIFT) + offset;
+			}
+			filp->f_version = inode->i_version;
+			need_revalidate = 0;
+		}
+		de = (struct exofs_dir_entry *)(kaddr + offset);
+		limit = kaddr + exofs_last_byte(inode, n) -
+							EXOFS_DIR_REC_LEN(1);
+		for (; (char *)de <= limit; de = exofs_next_entry(de)) {
+			if (de->rec_len == 0) {
+				EXOFS_ERR("ERROR: "
+					"zero-length directory entry");
+				exofs_put_page(page);
+				return -EIO;
+			}
+			if (de->inode_no) {
+				int over;
+				unsigned char d_type = DT_UNKNOWN;
+
+				if (types && de->file_type < EXOFS_FT_MAX)
+					d_type = types[de->file_type];
+
+				offset = (char *)de - kaddr;
+				over = filldir(dirent, de->name, de->name_len,
+						(n<<PAGE_CACHE_SHIFT) | offset,
+						le64_to_cpu(de->inode_no),
+						d_type);
+				if (over) {
+					exofs_put_page(page);
+					return 0;
+				}
+			}
+			filp->f_pos += le16_to_cpu(de->rec_len);
+		}
+		exofs_put_page(page);
+	}
+
+	return 0;
+}
+
+struct exofs_dir_entry *exofs_find_entry(struct inode *dir,
+			struct dentry *dentry, struct page **res_page)
+{
+	const unsigned char *name = dentry->d_name.name;
+	int namelen = dentry->d_name.len;
+	unsigned reclen = EXOFS_DIR_REC_LEN(namelen);
+	unsigned long start, n;
+	unsigned long npages = dir_pages(dir);
+	struct page *page = NULL;
+	struct exofs_i_info *oi = exofs_i(dir);
+	struct exofs_dir_entry *de;
+
+	if (npages == 0)
+		goto out;
+
+	*res_page = NULL;
+
+	start = oi->i_dir_start_lookup;
+	if (start >= npages)
+		start = 0;
+	n = start;
+	do {
+		char *kaddr;
+		page = exofs_get_page(dir, n);
+		if (!IS_ERR(page)) {
+			kaddr = page_address(page);
+			de = (struct exofs_dir_entry *) kaddr;
+			kaddr += exofs_last_byte(dir, n) - reclen;
+			while ((char *) de <= kaddr) {
+				if (de->rec_len == 0) {
+					EXOFS_ERR(
+						"ERROR: exofs_find_entry: "
+						"zero-length directory entry");
+					exofs_put_page(page);
+					goto out;
+				}
+				if (exofs_match(namelen, name, de))
+					goto found;
+				de = exofs_next_entry(de);
+			}
+			exofs_put_page(page);
+		}
+		if (++n >= npages)
+			n = 0;
+	} while (n != start);
+out:
+	return NULL;
+
+found:
+	*res_page = page;
+	oi->i_dir_start_lookup = n;
+	return de;
+}
+
+struct exofs_dir_entry *exofs_dotdot(struct inode *dir, struct page **p)
+{
+	struct page *page = exofs_get_page(dir, 0);
+	struct exofs_dir_entry *de = NULL;
+
+	if (!IS_ERR(page)) {
+		de = exofs_next_entry(
+				(struct exofs_dir_entry *)page_address(page));
+		*p = page;
+	}
+	return de;
+}
+
+ino_t exofs_parent_ino(struct dentry *child)
+{
+	struct page *page;
+	struct exofs_dir_entry *de;
+	ino_t ino;
+
+	de = exofs_dotdot(child->d_inode, &page);
+	if (!de)
+		return 0;
+
+	ino = le64_to_cpu(de->inode_no);
+	exofs_put_page(page);
+	return ino;
+}
+
+ino_t exofs_inode_by_name(struct inode *dir, struct dentry *dentry)
+{
+	ino_t res = 0;
+	struct exofs_dir_entry *de;
+	struct page *page;
+
+	de = exofs_find_entry(dir, dentry, &page);
+	if (de) {
+		res = le64_to_cpu(de->inode_no);
+		exofs_put_page(page);
+	}
+	return res;
+}
+
+int exofs_set_link(struct inode *dir, struct exofs_dir_entry *de,
+			struct page *page, struct inode *inode)
+{
+	loff_t pos = page_offset(page) +
+			(char *) de - (char *) page_address(page);
+	unsigned len = le16_to_cpu(de->rec_len);
+	int err;
+
+	lock_page(page);
+	err = exofs_write_begin(NULL, page->mapping, pos, len,
+				AOP_FLAG_UNINTERRUPTIBLE, &page, NULL);
+	if (err)
+		EXOFS_ERR("exofs_set_link: exofs_write_begin FAILD => %d\n",
+			  err);
+
+	de->inode_no = cpu_to_le64(inode->i_ino);
+	exofs_set_de_type(de, inode);
+	if (likely(!err))
+		err = exofs_commit_chunk(page, pos, len);
+	exofs_put_page(page);
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	mark_inode_dirty(dir);
+	return err;
+}
+
+int exofs_add_link(struct dentry *dentry, struct inode *inode)
+{
+	struct inode *dir = dentry->d_parent->d_inode;
+	const unsigned char *name = dentry->d_name.name;
+	int namelen = dentry->d_name.len;
+	unsigned chunk_size = exofs_chunk_size(dir);
+	unsigned reclen = EXOFS_DIR_REC_LEN(namelen);
+	unsigned short rec_len, name_len;
+	struct page *page = NULL;
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+	struct exofs_dir_entry *de;
+	unsigned long npages = dir_pages(dir);
+	unsigned long n;
+	char *kaddr;
+	loff_t pos;
+	int err;
+
+	for (n = 0; n <= npages; n++) {
+		char *dir_end;
+
+		page = exofs_get_page(dir, n);
+		err = PTR_ERR(page);
+		if (IS_ERR(page))
+			goto out;
+		lock_page(page);
+		kaddr = page_address(page);
+		dir_end = kaddr + exofs_last_byte(dir, n);
+		de = (struct exofs_dir_entry *)kaddr;
+		kaddr += PAGE_CACHE_SIZE - reclen;
+		while ((char *)de <= kaddr) {
+			if ((char *)de == dir_end) {
+				name_len = 0;
+				rec_len = chunk_size;
+				de->rec_len = cpu_to_le16(chunk_size);
+				de->inode_no = 0;
+				goto got_it;
+			}
+			if (de->rec_len == 0) {
+				EXOFS_ERR("ERROR: exofs_add_link: "
+					"zero-length directory entry");
+				err = -EIO;
+				goto out_unlock;
+			}
+			err = -EEXIST;
+			if (exofs_match(namelen, name, de))
+				goto out_unlock;
+			name_len = EXOFS_DIR_REC_LEN(de->name_len);
+			rec_len = le16_to_cpu(de->rec_len);
+			if (!de->inode_no && rec_len >= reclen)
+				goto got_it;
+			if (rec_len >= name_len + reclen)
+				goto got_it;
+			de = (struct exofs_dir_entry *) ((char *) de + rec_len);
+		}
+		unlock_page(page);
+		exofs_put_page(page);
+	}
+
+	EXOFS_ERR("exofs_add_link: BAD dentry=%p or inode=%p", dentry, inode);
+	return -EINVAL;
+
+got_it:
+	pos = page_offset(page) +
+		(char *)de - (char *)page_address(page);
+	err = exofs_write_begin(NULL, page->mapping, pos, rec_len, 0,
+							&page, NULL);
+	if (err)
+		goto out_unlock;
+	if (de->inode_no) {
+		struct exofs_dir_entry *de1 =
+			(struct exofs_dir_entry *)((char *)de + name_len);
+		de1->rec_len = cpu_to_le16(rec_len - name_len);
+		de->rec_len = cpu_to_le16(name_len);
+		de = de1;
+	}
+	de->name_len = namelen;
+	memcpy(de->name, name, namelen);
+	de->inode_no = cpu_to_le64(inode->i_ino);
+	exofs_set_de_type(de, inode);
+	err = exofs_commit_chunk(page, pos, rec_len);
+	dir->i_mtime = dir->i_ctime = CURRENT_TIME;
+	mark_inode_dirty(dir);
+	sbi->s_numfiles++;
+
+out_put:
+	exofs_put_page(page);
+out:
+	return err;
+out_unlock:
+	unlock_page(page);
+	goto out_put;
+}
+
+int exofs_delete_entry(struct exofs_dir_entry *dir, struct page *page)
+{
+	struct address_space *mapping = page->mapping;
+	struct inode *inode = mapping->host;
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+	char *kaddr = page_address(page);
+	unsigned from = ((char *)dir - kaddr) & ~(exofs_chunk_size(inode)-1);
+	unsigned to = ((char *)dir - kaddr) + le16_to_cpu(dir->rec_len);
+	loff_t pos;
+	struct exofs_dir_entry *pde = NULL;
+	struct exofs_dir_entry *de = (struct exofs_dir_entry *) (kaddr + from);
+	int err;
+
+	while (de < dir) {
+		if (de->rec_len == 0) {
+			EXOFS_ERR("ERROR: exofs_delete_entry:"
+				"zero-length directory entry");
+			err = -EIO;
+			goto out;
+		}
+		pde = de;
+		de = exofs_next_entry(de);
+	}
+	if (pde)
+		from = (char *)pde - (char *)page_address(page);
+	pos = page_offset(page) + from;
+	lock_page(page);
+	err = exofs_write_begin(NULL, page->mapping, pos, to - from, 0,
+							&page, NULL);
+	if (err)
+		EXOFS_ERR("exofs_delete_entry: exofs_write_begin FAILD => %d\n",
+			  err);
+	if (pde)
+		pde->rec_len = cpu_to_le16(to - from);
+	dir->inode_no = 0;
+	if (likely(!err))
+		err = exofs_commit_chunk(page, pos, to - from);
+	inode->i_ctime = inode->i_mtime = CURRENT_TIME;
+	mark_inode_dirty(inode);
+	sbi->s_numfiles--;
+out:
+	exofs_put_page(page);
+	return err;
+}
+
+/* kept aligned on 4 bytes */
+#define THIS_DIR ".\0\0"
+#define PARENT_DIR "..\0"
+
+int exofs_make_empty(struct inode *inode, struct inode *parent)
+{
+	struct address_space *mapping = inode->i_mapping;
+	struct page *page = grab_cache_page(mapping, 0);
+	unsigned chunk_size = exofs_chunk_size(inode);
+	struct exofs_dir_entry *de;
+	int err;
+	void *kaddr;
+
+	if (!page)
+		return -ENOMEM;
+
+	err = exofs_write_begin(NULL, page->mapping, 0, chunk_size, 0,
+							&page, NULL);
+	if (err) {
+		unlock_page(page);
+		goto fail;
+	}
+
+	kaddr = kmap_atomic(page, KM_USER0);
+	de = (struct exofs_dir_entry *)kaddr;
+	de->name_len = 1;
+	de->rec_len = cpu_to_le16(EXOFS_DIR_REC_LEN(1));
+	memcpy(de->name, THIS_DIR, sizeof(THIS_DIR));
+	de->inode_no = cpu_to_le64(inode->i_ino);
+	exofs_set_de_type(de, inode);
+
+	de = (struct exofs_dir_entry *)(kaddr + EXOFS_DIR_REC_LEN(1));
+	de->name_len = 2;
+	de->rec_len = cpu_to_le16(chunk_size - EXOFS_DIR_REC_LEN(1));
+	de->inode_no = cpu_to_le64(parent->i_ino);
+	memcpy(de->name, PARENT_DIR, sizeof(PARENT_DIR));
+	exofs_set_de_type(de, inode);
+	kunmap_atomic(page, KM_USER0);
+	err = exofs_commit_chunk(page, 0, chunk_size);
+fail:
+	page_cache_release(page);
+	return err;
+}
+
+int exofs_empty_dir(struct inode *inode)
+{
+	struct page *page = NULL;
+	unsigned long i, npages = dir_pages(inode);
+
+	for (i = 0; i < npages; i++) {
+		char *kaddr;
+		struct exofs_dir_entry *de;
+		page = exofs_get_page(inode, i);
+
+		if (IS_ERR(page))
+			continue;
+
+		kaddr = page_address(page);
+		de = (struct exofs_dir_entry *)kaddr;
+		kaddr += exofs_last_byte(inode, i) - EXOFS_DIR_REC_LEN(1);
+
+		while ((char *)de <= kaddr) {
+			if (de->rec_len == 0) {
+				EXOFS_ERR("ERROR: exofs_empty_dir: "
+					  "zero-length directory entry"
+					  "kaddr=%p, de=%p\n", kaddr, de);
+				goto not_empty;
+			}
+			if (de->inode_no != 0) {
+				/* check for . and .. */
+				if (de->name[0] != '.')
+					goto not_empty;
+				if (de->name_len > 2)
+					goto not_empty;
+				if (de->name_len < 2) {
+					if (le64_to_cpu(de->inode_no) !=
+					    inode->i_ino)
+						goto not_empty;
+				} else if (de->name[1] != '.')
+					goto not_empty;
+			}
+			de = exofs_next_entry(de);
+		}
+		exofs_put_page(page);
+	}
+	return 1;
+
+not_empty:
+	exofs_put_page(page);
+	return 0;
+}
+
+const struct file_operations exofs_dir_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= generic_read_dir,
+	.readdir	= exofs_readdir,
+};
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
new file mode 100644
index 000000000000..0fd4c7859679
--- /dev/null
+++ b/fs/exofs/exofs.h
@@ -0,0 +1,180 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/fs.h>
+#include <linux/time.h>
+#include "common.h"
+
+#ifndef __EXOFS_H__
+#define __EXOFS_H__
+
+#define EXOFS_ERR(fmt, a...) printk(KERN_ERR "exofs: " fmt, ##a)
+
+#ifdef CONFIG_EXOFS_DEBUG
+#define EXOFS_DBGMSG(fmt, a...) \
+	printk(KERN_NOTICE "exofs @%s:%d: " fmt, __func__, __LINE__, ##a)
+#else
+#define EXOFS_DBGMSG(fmt, a...) \
+	do { if (0) printk(fmt, ##a); } while (0)
+#endif
+
+/* u64 has problems with printk this will cast it to unsigned long long */
+#define _LLU(x) (unsigned long long)(x)
+
+/*
+ * our extension to the in-memory superblock
+ */
+struct exofs_sb_info {
+	struct osd_dev	*s_dev;			/* returned by get_osd_dev    */
+	osd_id		s_pid;			/* partition ID of file system*/
+	int		s_timeout;		/* timeout for OSD operations */
+	uint64_t	s_nextid;		/* highest object ID used     */
+	uint32_t	s_numfiles;		/* number of files on fs      */
+	spinlock_t	s_next_gen_lock;	/* spinlock for gen # update  */
+	u32		s_next_generation;	/* next gen # to use          */
+	atomic_t	s_curr_pending;		/* number of pending commands */
+	uint8_t		s_cred[OSD_CAP_LEN];	/* all-powerful credential    */
+};
+
+/*
+ * our extension to the in-memory inode
+ */
+struct exofs_i_info {
+	unsigned long  i_flags;            /* various atomic flags            */
+	uint32_t       i_data[EXOFS_IDATA];/*short symlink names and device #s*/
+	uint32_t       i_dir_start_lookup; /* which page to start lookup      */
+	wait_queue_head_t i_wq;            /* wait queue for inode            */
+	uint64_t       i_commit_size;      /* the object's written length     */
+	uint8_t        i_cred[OSD_CAP_LEN];/* all-powerful credential         */
+	struct inode   vfs_inode;          /* normal in-memory inode          */
+};
+
+/*
+ * our inode flags
+ */
+#define OBJ_2BCREATED	0	/* object will be created soon*/
+#define OBJ_CREATED	1	/* object has been created on the osd*/
+
+static inline int obj_2bcreated(struct exofs_i_info *oi)
+{
+	return test_bit(OBJ_2BCREATED, &oi->i_flags);
+}
+
+static inline void set_obj_2bcreated(struct exofs_i_info *oi)
+{
+	set_bit(OBJ_2BCREATED, &oi->i_flags);
+}
+
+static inline int obj_created(struct exofs_i_info *oi)
+{
+	return test_bit(OBJ_CREATED, &oi->i_flags);
+}
+
+static inline void set_obj_created(struct exofs_i_info *oi)
+{
+	set_bit(OBJ_CREATED, &oi->i_flags);
+}
+
+int __exofs_wait_obj_created(struct exofs_i_info *oi);
+static inline int wait_obj_created(struct exofs_i_info *oi)
+{
+	if (likely(obj_created(oi)))
+		return 0;
+
+	return __exofs_wait_obj_created(oi);
+}
+
+/*
+ * get to our inode from the vfs inode
+ */
+static inline struct exofs_i_info *exofs_i(struct inode *inode)
+{
+	return container_of(inode, struct exofs_i_info, vfs_inode);
+}
+
+/*
+ * Maximum count of links to a file
+ */
+#define EXOFS_LINK_MAX           32000
+
+/*************************
+ * function declarations *
+ *************************/
+/* inode.c               */
+void exofs_truncate(struct inode *inode);
+int exofs_setattr(struct dentry *, struct iattr *);
+int exofs_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata);
+extern struct inode *exofs_iget(struct super_block *, unsigned long);
+struct inode *exofs_new_inode(struct inode *, int);
+extern int exofs_write_inode(struct inode *, int);
+extern void exofs_delete_inode(struct inode *);
+
+/* dir.c:                */
+int exofs_add_link(struct dentry *, struct inode *);
+ino_t exofs_inode_by_name(struct inode *, struct dentry *);
+int exofs_delete_entry(struct exofs_dir_entry *, struct page *);
+int exofs_make_empty(struct inode *, struct inode *);
+struct exofs_dir_entry *exofs_find_entry(struct inode *, struct dentry *,
+					 struct page **);
+int exofs_empty_dir(struct inode *);
+struct exofs_dir_entry *exofs_dotdot(struct inode *, struct page **);
+ino_t exofs_parent_ino(struct dentry *child);
+int exofs_set_link(struct inode *, struct exofs_dir_entry *, struct page *,
+		    struct inode *);
+
+/*********************
+ * operation vectors *
+ *********************/
+/* dir.c:            */
+extern const struct file_operations exofs_dir_operations;
+
+/* file.c            */
+extern const struct inode_operations exofs_file_inode_operations;
+extern const struct file_operations exofs_file_operations;
+
+/* inode.c           */
+extern const struct address_space_operations exofs_aops;
+
+/* namei.c           */
+extern const struct inode_operations exofs_dir_inode_operations;
+extern const struct inode_operations exofs_special_inode_operations;
+
+/* symlink.c         */
+extern const struct inode_operations exofs_symlink_inode_operations;
+extern const struct inode_operations exofs_fast_symlink_inode_operations;
+
+#endif
diff --git a/fs/exofs/file.c b/fs/exofs/file.c
new file mode 100644
index 000000000000..6ed7fe484752
--- /dev/null
+++ b/fs/exofs/file.c
@@ -0,0 +1,87 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/buffer_head.h>
+
+#include "exofs.h"
+
+static int exofs_release_file(struct inode *inode, struct file *filp)
+{
+	return 0;
+}
+
+static int exofs_file_fsync(struct file *filp, struct dentry *dentry,
+			    int datasync)
+{
+	int ret;
+	struct address_space *mapping = filp->f_mapping;
+
+	ret = filemap_write_and_wait(mapping);
+	if (ret)
+		return ret;
+
+	/*Note: file_fsync below also calles sync_blockdev, which is a no-op
+	 *      for exofs, but other then that it does sync_inode and
+	 *      sync_superblock which is what we need here.
+	 */
+	return file_fsync(filp, dentry, datasync);
+}
+
+static int exofs_flush(struct file *file, fl_owner_t id)
+{
+	exofs_file_fsync(file, file->f_path.dentry, 1);
+	/* TODO: Flush the OSD target */
+	return 0;
+}
+
+const struct file_operations exofs_file_operations = {
+	.llseek		= generic_file_llseek,
+	.read		= do_sync_read,
+	.write		= do_sync_write,
+	.aio_read	= generic_file_aio_read,
+	.aio_write	= generic_file_aio_write,
+	.mmap		= generic_file_mmap,
+	.open		= generic_file_open,
+	.release	= exofs_release_file,
+	.fsync		= exofs_file_fsync,
+	.flush		= exofs_flush,
+	.splice_read	= generic_file_splice_read,
+	.splice_write	= generic_file_splice_write,
+};
+
+const struct inode_operations exofs_file_inode_operations = {
+	.truncate	= exofs_truncate,
+	.setattr	= exofs_setattr,
+};
diff --git a/fs/exofs/inode.c b/fs/exofs/inode.c
new file mode 100644
index 000000000000..ba8d9fab4693
--- /dev/null
+++ b/fs/exofs/inode.c
@@ -0,0 +1,1303 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/writeback.h>
+#include <linux/buffer_head.h>
+#include <scsi/scsi_device.h>
+
+#include "exofs.h"
+
+#ifdef CONFIG_EXOFS_DEBUG
+#  define EXOFS_DEBUG_OBJ_ISIZE 1
+#endif
+
+struct page_collect {
+	struct exofs_sb_info *sbi;
+	struct request_queue *req_q;
+	struct inode *inode;
+	unsigned expected_pages;
+
+	struct bio *bio;
+	unsigned nr_pages;
+	unsigned long length;
+	loff_t pg_first; /* keep 64bit also in 32-arches */
+};
+
+static void _pcol_init(struct page_collect *pcol, unsigned expected_pages,
+		struct inode *inode)
+{
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+	struct request_queue *req_q = sbi->s_dev->scsi_device->request_queue;
+
+	pcol->sbi = sbi;
+	pcol->req_q = req_q;
+	pcol->inode = inode;
+	pcol->expected_pages = expected_pages;
+
+	pcol->bio = NULL;
+	pcol->nr_pages = 0;
+	pcol->length = 0;
+	pcol->pg_first = -1;
+
+	EXOFS_DBGMSG("_pcol_init ino=0x%lx expected_pages=%u\n", inode->i_ino,
+		     expected_pages);
+}
+
+static void _pcol_reset(struct page_collect *pcol)
+{
+	pcol->expected_pages -= min(pcol->nr_pages, pcol->expected_pages);
+
+	pcol->bio = NULL;
+	pcol->nr_pages = 0;
+	pcol->length = 0;
+	pcol->pg_first = -1;
+	EXOFS_DBGMSG("_pcol_reset ino=0x%lx expected_pages=%u\n",
+		     pcol->inode->i_ino, pcol->expected_pages);
+
+	/* this is probably the end of the loop but in writes
+	 * it might not end here. don't be left with nothing
+	 */
+	if (!pcol->expected_pages)
+		pcol->expected_pages = 128;
+}
+
+static int pcol_try_alloc(struct page_collect *pcol)
+{
+	int pages = min_t(unsigned, pcol->expected_pages, BIO_MAX_PAGES);
+
+	for (; pages; pages >>= 1) {
+		pcol->bio = bio_alloc(GFP_KERNEL, pages);
+		if (likely(pcol->bio))
+			return 0;
+	}
+
+	EXOFS_ERR("Failed to kcalloc expected_pages=%u\n",
+		  pcol->expected_pages);
+	return -ENOMEM;
+}
+
+static void pcol_free(struct page_collect *pcol)
+{
+	bio_put(pcol->bio);
+	pcol->bio = NULL;
+}
+
+static int pcol_add_page(struct page_collect *pcol, struct page *page,
+			 unsigned len)
+{
+	int added_len = bio_add_pc_page(pcol->req_q, pcol->bio, page, len, 0);
+	if (unlikely(len != added_len))
+		return -ENOMEM;
+
+	++pcol->nr_pages;
+	pcol->length += len;
+	return 0;
+}
+
+static int update_read_page(struct page *page, int ret)
+{
+	if (ret == 0) {
+		/* Everything is OK */
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+	} else if (ret == -EFAULT) {
+		/* In this case we were trying to read something that wasn't on
+		 * disk yet - return a page full of zeroes.  This should be OK,
+		 * because the object should be empty (if there was a write
+		 * before this read, the read would be waiting with the page
+		 * locked */
+		clear_highpage(page);
+
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+		ret = 0; /* recovered error */
+		EXOFS_DBGMSG("recovered read error\n");
+	} else /* Error */
+		SetPageError(page);
+
+	return ret;
+}
+
+static void update_write_page(struct page *page, int ret)
+{
+	if (ret) {
+		mapping_set_error(page->mapping, ret);
+		SetPageError(page);
+	}
+	end_page_writeback(page);
+}
+
+/* Called at the end of reads, to optionally unlock pages and update their
+ * status.
+ */
+static int __readpages_done(struct osd_request *or, struct page_collect *pcol,
+			    bool do_unlock)
+{
+	struct bio_vec *bvec;
+	int i;
+	u64 resid;
+	u64 good_bytes;
+	u64 length = 0;
+	int ret = exofs_check_ok_resid(or, &resid, NULL);
+
+	osd_end_request(or);
+
+	if (likely(!ret))
+		good_bytes = pcol->length;
+	else if (!resid)
+		good_bytes = 0;
+	else
+		good_bytes = pcol->length - resid;
+
+	EXOFS_DBGMSG("readpages_done(0x%lx) good_bytes=0x%llx"
+		     " length=0x%lx nr_pages=%u\n",
+		     pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
+		     pcol->nr_pages);
+
+	__bio_for_each_segment(bvec, pcol->bio, i, 0) {
+		struct page *page = bvec->bv_page;
+		struct inode *inode = page->mapping->host;
+		int page_stat;
+
+		if (inode != pcol->inode)
+			continue; /* osd might add more pages at end */
+
+		if (likely(length < good_bytes))
+			page_stat = 0;
+		else
+			page_stat = ret;
+
+		EXOFS_DBGMSG("    readpages_done(0x%lx, 0x%lx) %s\n",
+			  inode->i_ino, page->index,
+			  page_stat ? "bad_bytes" : "good_bytes");
+
+		ret = update_read_page(page, page_stat);
+		if (do_unlock)
+			unlock_page(page);
+		length += bvec->bv_len;
+	}
+
+	pcol_free(pcol);
+	EXOFS_DBGMSG("readpages_done END\n");
+	return ret;
+}
+
+/* callback of async reads */
+static void readpages_done(struct osd_request *or, void *p)
+{
+	struct page_collect *pcol = p;
+
+	__readpages_done(or, pcol, true);
+	atomic_dec(&pcol->sbi->s_curr_pending);
+	kfree(p);
+}
+
+static void _unlock_pcol_pages(struct page_collect *pcol, int ret, int rw)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	__bio_for_each_segment(bvec, pcol->bio, i, 0) {
+		struct page *page = bvec->bv_page;
+
+		if (rw == READ)
+			update_read_page(page, ret);
+		else
+			update_write_page(page, ret);
+
+		unlock_page(page);
+	}
+	pcol_free(pcol);
+}
+
+static int read_exec(struct page_collect *pcol, bool is_sync)
+{
+	struct exofs_i_info *oi = exofs_i(pcol->inode);
+	struct osd_obj_id obj = {pcol->sbi->s_pid,
+					pcol->inode->i_ino + EXOFS_OBJ_OFF};
+	struct osd_request *or = NULL;
+	struct page_collect *pcol_copy = NULL;
+	loff_t i_start = pcol->pg_first << PAGE_CACHE_SHIFT;
+	int ret;
+
+	if (!pcol->bio)
+		return 0;
+
+	/* see comment in _readpage() about sync reads */
+	WARN_ON(is_sync && (pcol->nr_pages != 1));
+
+	or = osd_start_request(pcol->sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	osd_req_read(or, &obj, pcol->bio, i_start);
+
+	if (is_sync) {
+		exofs_sync_op(or, pcol->sbi->s_timeout, oi->i_cred);
+		return __readpages_done(or, pcol, false);
+	}
+
+	pcol_copy = kmalloc(sizeof(*pcol_copy), GFP_KERNEL);
+	if (!pcol_copy) {
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	*pcol_copy = *pcol;
+	ret = exofs_async_op(or, readpages_done, pcol_copy, oi->i_cred);
+	if (unlikely(ret))
+		goto err;
+
+	atomic_inc(&pcol->sbi->s_curr_pending);
+
+	EXOFS_DBGMSG("read_exec obj=0x%llx start=0x%llx length=0x%lx\n",
+		  obj.id, _LLU(i_start), pcol->length);
+
+	/* pages ownership was passed to pcol_copy */
+	_pcol_reset(pcol);
+	return 0;
+
+err:
+	if (!is_sync)
+		_unlock_pcol_pages(pcol, ret, READ);
+	kfree(pcol_copy);
+	if (or)
+		osd_end_request(or);
+	return ret;
+}
+
+/* readpage_strip is called either directly from readpage() or by the VFS from
+ * within read_cache_pages(), to add one more page to be read. It will try to
+ * collect as many contiguous pages as posible. If a discontinuity is
+ * encountered, or it runs out of resources, it will submit the previous segment
+ * and will start a new collection. Eventually caller must submit the last
+ * segment if present.
+ */
+static int readpage_strip(void *data, struct page *page)
+{
+	struct page_collect *pcol = data;
+	struct inode *inode = pcol->inode;
+	struct exofs_i_info *oi = exofs_i(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	size_t len;
+	int ret;
+
+	/* FIXME: Just for debugging, will be removed */
+	if (PageUptodate(page))
+		EXOFS_ERR("PageUptodate(0x%lx, 0x%lx)\n", pcol->inode->i_ino,
+			  page->index);
+
+	if (page->index < end_index)
+		len = PAGE_CACHE_SIZE;
+	else if (page->index == end_index)
+		len = i_size & ~PAGE_CACHE_MASK;
+	else
+		len = 0;
+
+	if (!len || !obj_created(oi)) {
+		/* this will be out of bounds, or doesn't exist yet.
+		 * Current page is cleared and the request is split
+		 */
+		clear_highpage(page);
+
+		SetPageUptodate(page);
+		if (PageError(page))
+			ClearPageError(page);
+
+		unlock_page(page);
+		EXOFS_DBGMSG("readpage_strip(0x%lx, 0x%lx) empty page,"
+			     " splitting\n", inode->i_ino, page->index);
+
+		return read_exec(pcol, false);
+	}
+
+try_again:
+
+	if (unlikely(pcol->pg_first == -1)) {
+		pcol->pg_first = page->index;
+	} else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
+		   page->index)) {
+		/* Discontinuity detected, split the request */
+		ret = read_exec(pcol, false);
+		if (unlikely(ret))
+			goto fail;
+		goto try_again;
+	}
+
+	if (!pcol->bio) {
+		ret = pcol_try_alloc(pcol);
+		if (unlikely(ret))
+			goto fail;
+	}
+
+	if (len != PAGE_CACHE_SIZE)
+		zero_user(page, len, PAGE_CACHE_SIZE - len);
+
+	EXOFS_DBGMSG("    readpage_strip(0x%lx, 0x%lx) len=0x%zx\n",
+		     inode->i_ino, page->index, len);
+
+	ret = pcol_add_page(pcol, page, len);
+	if (ret) {
+		EXOFS_DBGMSG("Failed pcol_add_page pages[i]=%p "
+			  "this_len=0x%zx nr_pages=%u length=0x%lx\n",
+			  page, len, pcol->nr_pages, pcol->length);
+
+		/* split the request, and start again with current page */
+		ret = read_exec(pcol, false);
+		if (unlikely(ret))
+			goto fail;
+
+		goto try_again;
+	}
+
+	return 0;
+
+fail:
+	/* SetPageError(page); ??? */
+	unlock_page(page);
+	return ret;
+}
+
+static int exofs_readpages(struct file *file, struct address_space *mapping,
+			   struct list_head *pages, unsigned nr_pages)
+{
+	struct page_collect pcol;
+	int ret;
+
+	_pcol_init(&pcol, nr_pages, mapping->host);
+
+	ret = read_cache_pages(mapping, pages, readpage_strip, &pcol);
+	if (ret) {
+		EXOFS_ERR("read_cache_pages => %d\n", ret);
+		return ret;
+	}
+
+	return read_exec(&pcol, false);
+}
+
+static int _readpage(struct page *page, bool is_sync)
+{
+	struct page_collect pcol;
+	int ret;
+
+	_pcol_init(&pcol, 1, page->mapping->host);
+
+	/* readpage_strip might call read_exec(,async) inside at several places
+	 * but this is safe for is_async=0 since read_exec will not do anything
+	 * when we have a single page.
+	 */
+	ret = readpage_strip(&pcol, page);
+	if (ret) {
+		EXOFS_ERR("_readpage => %d\n", ret);
+		return ret;
+	}
+
+	return read_exec(&pcol, is_sync);
+}
+
+/*
+ * We don't need the file
+ */
+static int exofs_readpage(struct file *file, struct page *page)
+{
+	return _readpage(page, false);
+}
+
+/* Callback for osd_write. All writes are asynchronouse */
+static void writepages_done(struct osd_request *or, void *p)
+{
+	struct page_collect *pcol = p;
+	struct bio_vec *bvec;
+	int i;
+	u64 resid;
+	u64  good_bytes;
+	u64  length = 0;
+
+	int ret = exofs_check_ok_resid(or, NULL, &resid);
+
+	osd_end_request(or);
+	atomic_dec(&pcol->sbi->s_curr_pending);
+
+	if (likely(!ret))
+		good_bytes = pcol->length;
+	else if (!resid)
+		good_bytes = 0;
+	else
+		good_bytes = pcol->length - resid;
+
+	EXOFS_DBGMSG("writepages_done(0x%lx) good_bytes=0x%llx"
+		     " length=0x%lx nr_pages=%u\n",
+		     pcol->inode->i_ino, _LLU(good_bytes), pcol->length,
+		     pcol->nr_pages);
+
+	__bio_for_each_segment(bvec, pcol->bio, i, 0) {
+		struct page *page = bvec->bv_page;
+		struct inode *inode = page->mapping->host;
+		int page_stat;
+
+		if (inode != pcol->inode)
+			continue; /* osd might add more pages to a bio */
+
+		if (likely(length < good_bytes))
+			page_stat = 0;
+		else
+			page_stat = ret;
+
+		update_write_page(page, page_stat);
+		unlock_page(page);
+		EXOFS_DBGMSG("    writepages_done(0x%lx, 0x%lx) status=%d\n",
+			     inode->i_ino, page->index, page_stat);
+
+		length += bvec->bv_len;
+	}
+
+	pcol_free(pcol);
+	kfree(pcol);
+	EXOFS_DBGMSG("writepages_done END\n");
+}
+
+static int write_exec(struct page_collect *pcol)
+{
+	struct exofs_i_info *oi = exofs_i(pcol->inode);
+	struct osd_obj_id obj = {pcol->sbi->s_pid,
+					pcol->inode->i_ino + EXOFS_OBJ_OFF};
+	struct osd_request *or = NULL;
+	struct page_collect *pcol_copy = NULL;
+	loff_t i_start = pcol->pg_first << PAGE_CACHE_SHIFT;
+	int ret;
+
+	if (!pcol->bio)
+		return 0;
+
+	or = osd_start_request(pcol->sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_ERR("write_exec: Faild to osd_start_request()\n");
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	pcol_copy = kmalloc(sizeof(*pcol_copy), GFP_KERNEL);
+	if (!pcol_copy) {
+		EXOFS_ERR("write_exec: Faild to kmalloc(pcol)\n");
+		ret = -ENOMEM;
+		goto err;
+	}
+
+	*pcol_copy = *pcol;
+
+	osd_req_write(or, &obj, pcol_copy->bio, i_start);
+	ret = exofs_async_op(or, writepages_done, pcol_copy, oi->i_cred);
+	if (unlikely(ret)) {
+		EXOFS_ERR("write_exec: exofs_async_op() Faild\n");
+		goto err;
+	}
+
+	atomic_inc(&pcol->sbi->s_curr_pending);
+	EXOFS_DBGMSG("write_exec(0x%lx, 0x%llx) start=0x%llx length=0x%lx\n",
+		  pcol->inode->i_ino, pcol->pg_first, _LLU(i_start),
+		  pcol->length);
+	/* pages ownership was passed to pcol_copy */
+	_pcol_reset(pcol);
+	return 0;
+
+err:
+	_unlock_pcol_pages(pcol, ret, WRITE);
+	kfree(pcol_copy);
+	if (or)
+		osd_end_request(or);
+	return ret;
+}
+
+/* writepage_strip is called either directly from writepage() or by the VFS from
+ * within write_cache_pages(), to add one more page to be written to storage.
+ * It will try to collect as many contiguous pages as possible. If a
+ * discontinuity is encountered or it runs out of resources it will submit the
+ * previous segment and will start a new collection.
+ * Eventually caller must submit the last segment if present.
+ */
+static int writepage_strip(struct page *page,
+			   struct writeback_control *wbc_unused, void *data)
+{
+	struct page_collect *pcol = data;
+	struct inode *inode = pcol->inode;
+	struct exofs_i_info *oi = exofs_i(inode);
+	loff_t i_size = i_size_read(inode);
+	pgoff_t end_index = i_size >> PAGE_CACHE_SHIFT;
+	size_t len;
+	int ret;
+
+	BUG_ON(!PageLocked(page));
+
+	ret = wait_obj_created(oi);
+	if (unlikely(ret))
+		goto fail;
+
+	if (page->index < end_index)
+		/* in this case, the page is within the limits of the file */
+		len = PAGE_CACHE_SIZE;
+	else {
+		len = i_size & ~PAGE_CACHE_MASK;
+
+		if (page->index > end_index || !len) {
+			/* in this case, the page is outside the limits
+			 * (truncate in progress)
+			 */
+			ret = write_exec(pcol);
+			if (unlikely(ret))
+				goto fail;
+			if (PageError(page))
+				ClearPageError(page);
+			unlock_page(page);
+			return 0;
+		}
+	}
+
+try_again:
+
+	if (unlikely(pcol->pg_first == -1)) {
+		pcol->pg_first = page->index;
+	} else if (unlikely((pcol->pg_first + pcol->nr_pages) !=
+		   page->index)) {
+		/* Discontinuity detected, split the request */
+		ret = write_exec(pcol);
+		if (unlikely(ret))
+			goto fail;
+		goto try_again;
+	}
+
+	if (!pcol->bio) {
+		ret = pcol_try_alloc(pcol);
+		if (unlikely(ret))
+			goto fail;
+	}
+
+	EXOFS_DBGMSG("    writepage_strip(0x%lx, 0x%lx) len=0x%zx\n",
+		     inode->i_ino, page->index, len);
+
+	ret = pcol_add_page(pcol, page, len);
+	if (unlikely(ret)) {
+		EXOFS_DBGMSG("Failed pcol_add_page "
+			     "nr_pages=%u total_length=0x%lx\n",
+			     pcol->nr_pages, pcol->length);
+
+		/* split the request, next loop will start again */
+		ret = write_exec(pcol);
+		if (unlikely(ret)) {
+			EXOFS_DBGMSG("write_exec faild => %d", ret);
+			goto fail;
+		}
+
+		goto try_again;
+	}
+
+	BUG_ON(PageWriteback(page));
+	set_page_writeback(page);
+
+	return 0;
+
+fail:
+	set_bit(AS_EIO, &page->mapping->flags);
+	unlock_page(page);
+	return ret;
+}
+
+static int exofs_writepages(struct address_space *mapping,
+		       struct writeback_control *wbc)
+{
+	struct page_collect pcol;
+	long start, end, expected_pages;
+	int ret;
+
+	start = wbc->range_start >> PAGE_CACHE_SHIFT;
+	end = (wbc->range_end == LLONG_MAX) ?
+			start + mapping->nrpages :
+			wbc->range_end >> PAGE_CACHE_SHIFT;
+
+	if (start || end)
+		expected_pages = min(end - start + 1, 32L);
+	else
+		expected_pages = mapping->nrpages;
+
+	EXOFS_DBGMSG("inode(0x%lx) wbc->start=0x%llx wbc->end=0x%llx"
+		     " m->nrpages=%lu start=0x%lx end=0x%lx\n",
+		     mapping->host->i_ino, wbc->range_start, wbc->range_end,
+		     mapping->nrpages, start, end);
+
+	_pcol_init(&pcol, expected_pages, mapping->host);
+
+	ret = write_cache_pages(mapping, wbc, writepage_strip, &pcol);
+	if (ret) {
+		EXOFS_ERR("write_cache_pages => %d\n", ret);
+		return ret;
+	}
+
+	return write_exec(&pcol);
+}
+
+static int exofs_writepage(struct page *page, struct writeback_control *wbc)
+{
+	struct page_collect pcol;
+	int ret;
+
+	_pcol_init(&pcol, 1, page->mapping->host);
+
+	ret = writepage_strip(page, NULL, &pcol);
+	if (ret) {
+		EXOFS_ERR("exofs_writepage => %d\n", ret);
+		return ret;
+	}
+
+	return write_exec(&pcol);
+}
+
+int exofs_write_begin(struct file *file, struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
+{
+	int ret = 0;
+	struct page *page;
+
+	page = *pagep;
+	if (page == NULL) {
+		ret = simple_write_begin(file, mapping, pos, len, flags, pagep,
+					 fsdata);
+		if (ret) {
+			EXOFS_DBGMSG("simple_write_begin faild\n");
+			return ret;
+		}
+
+		page = *pagep;
+	}
+
+	 /* read modify write */
+	if (!PageUptodate(page) && (len != PAGE_CACHE_SIZE)) {
+		ret = _readpage(page, true);
+		if (ret) {
+			/*SetPageError was done by _readpage. Is it ok?*/
+			unlock_page(page);
+			EXOFS_DBGMSG("__readpage_filler faild\n");
+		}
+	}
+
+	return ret;
+}
+
+static int exofs_write_begin_export(struct file *file,
+		struct address_space *mapping,
+		loff_t pos, unsigned len, unsigned flags,
+		struct page **pagep, void **fsdata)
+{
+	*pagep = NULL;
+
+	return exofs_write_begin(file, mapping, pos, len, flags, pagep,
+					fsdata);
+}
+
+const struct address_space_operations exofs_aops = {
+	.readpage	= exofs_readpage,
+	.readpages	= exofs_readpages,
+	.writepage	= exofs_writepage,
+	.writepages	= exofs_writepages,
+	.write_begin	= exofs_write_begin_export,
+	.write_end	= simple_write_end,
+};
+
+/******************************************************************************
+ * INODE OPERATIONS
+ *****************************************************************************/
+
+/*
+ * Test whether an inode is a fast symlink.
+ */
+static inline int exofs_inode_is_fast_symlink(struct inode *inode)
+{
+	struct exofs_i_info *oi = exofs_i(inode);
+
+	return S_ISLNK(inode->i_mode) && (oi->i_data[0] != 0);
+}
+
+/*
+ * get_block_t - Fill in a buffer_head
+ * An OSD takes care of block allocation so we just fake an allocation by
+ * putting in the inode's sector_t in the buffer_head.
+ * TODO: What about the case of create==0 and @iblock does not exist in the
+ * object?
+ */
+static int exofs_get_block(struct inode *inode, sector_t iblock,
+		    struct buffer_head *bh_result, int create)
+{
+	map_bh(bh_result, inode->i_sb, iblock);
+	return 0;
+}
+
+const struct osd_attr g_attr_logical_length = ATTR_DEF(
+	OSD_APAGE_OBJECT_INFORMATION, OSD_ATTR_OI_LOGICAL_LENGTH, 8);
+
+/*
+ * Truncate a file to the specified size - all we have to do is set the size
+ * attribute.  We make sure the object exists first.
+ */
+void exofs_truncate(struct inode *inode)
+{
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+	struct exofs_i_info *oi = exofs_i(inode);
+	struct osd_obj_id obj = {sbi->s_pid, inode->i_ino + EXOFS_OBJ_OFF};
+	struct osd_request *or;
+	struct osd_attr attr;
+	loff_t isize = i_size_read(inode);
+	__be64 newsize;
+	int ret;
+
+	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode)
+	     || S_ISLNK(inode->i_mode)))
+		return;
+	if (exofs_inode_is_fast_symlink(inode))
+		return;
+	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
+		return;
+	inode->i_mtime = inode->i_ctime = CURRENT_TIME;
+
+	nobh_truncate_page(inode->i_mapping, isize, exofs_get_block);
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_ERR("ERROR: exofs_truncate: osd_start_request failed\n");
+		goto fail;
+	}
+
+	osd_req_set_attributes(or, &obj);
+
+	newsize = cpu_to_be64((u64)isize);
+	attr = g_attr_logical_length;
+	attr.val_ptr = &newsize;
+	osd_req_add_set_attr_list(or, &attr, 1);
+
+	/* if we are about to truncate an object, and it hasn't been
+	 * created yet, wait
+	 */
+	if (unlikely(wait_obj_created(oi)))
+		goto fail;
+
+	ret = exofs_sync_op(or, sbi->s_timeout, oi->i_cred);
+	osd_end_request(or);
+	if (ret)
+		goto fail;
+
+out:
+	mark_inode_dirty(inode);
+	return;
+fail:
+	make_bad_inode(inode);
+	goto out;
+}
+
+/*
+ * Set inode attributes - just call generic functions.
+ */
+int exofs_setattr(struct dentry *dentry, struct iattr *iattr)
+{
+	struct inode *inode = dentry->d_inode;
+	int error;
+
+	error = inode_change_ok(inode, iattr);
+	if (error)
+		return error;
+
+	error = inode_setattr(inode, iattr);
+	return error;
+}
+
+/*
+ * Read an inode from the OSD, and return it as is.  We also return the size
+ * attribute in the 'sanity' argument if we got compiled with debugging turned
+ * on.
+ */
+static int exofs_get_inode(struct super_block *sb, struct exofs_i_info *oi,
+		    struct exofs_fcb *inode, uint64_t *sanity)
+{
+	struct exofs_sb_info *sbi = sb->s_fs_info;
+	struct osd_request *or;
+	struct osd_attr attr;
+	struct osd_obj_id obj = {sbi->s_pid,
+				 oi->vfs_inode.i_ino + EXOFS_OBJ_OFF};
+	int ret;
+
+	exofs_make_credential(oi->i_cred, &obj);
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_ERR("exofs_get_inode: osd_start_request failed.\n");
+		return -ENOMEM;
+	}
+	osd_req_get_attributes(or, &obj);
+
+	/* we need the inode attribute */
+	osd_req_add_get_attr_list(or, &g_attr_inode_data, 1);
+
+#ifdef EXOFS_DEBUG_OBJ_ISIZE
+	/* we get the size attributes to do a sanity check */
+	osd_req_add_get_attr_list(or, &g_attr_logical_length, 1);
+#endif
+
+	ret = exofs_sync_op(or, sbi->s_timeout, oi->i_cred);
+	if (ret)
+		goto out;
+
+	attr = g_attr_inode_data;
+	ret = extract_attr_from_req(or, &attr);
+	if (ret) {
+		EXOFS_ERR("exofs_get_inode: extract_attr_from_req failed\n");
+		goto out;
+	}
+
+	WARN_ON(attr.len != EXOFS_INO_ATTR_SIZE);
+	memcpy(inode, attr.val_ptr, EXOFS_INO_ATTR_SIZE);
+
+#ifdef EXOFS_DEBUG_OBJ_ISIZE
+	attr = g_attr_logical_length;
+	ret = extract_attr_from_req(or, &attr);
+	if (ret) {
+		EXOFS_ERR("ERROR: extract attr from or failed\n");
+		goto out;
+	}
+	*sanity = get_unaligned_be64(attr.val_ptr);
+#endif
+
+out:
+	osd_end_request(or);
+	return ret;
+}
+
+/*
+ * Fill in an inode read from the OSD and set it up for use
+ */
+struct inode *exofs_iget(struct super_block *sb, unsigned long ino)
+{
+	struct exofs_i_info *oi;
+	struct exofs_fcb fcb;
+	struct inode *inode;
+	uint64_t uninitialized_var(sanity);
+	int ret;
+
+	inode = iget_locked(sb, ino);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+	if (!(inode->i_state & I_NEW))
+		return inode;
+	oi = exofs_i(inode);
+
+	/* read the inode from the osd */
+	ret = exofs_get_inode(sb, oi, &fcb, &sanity);
+	if (ret)
+		goto bad_inode;
+
+	init_waitqueue_head(&oi->i_wq);
+	set_obj_created(oi);
+
+	/* copy stuff from on-disk struct to in-memory struct */
+	inode->i_mode = le16_to_cpu(fcb.i_mode);
+	inode->i_uid = le32_to_cpu(fcb.i_uid);
+	inode->i_gid = le32_to_cpu(fcb.i_gid);
+	inode->i_nlink = le16_to_cpu(fcb.i_links_count);
+	inode->i_ctime.tv_sec = (signed)le32_to_cpu(fcb.i_ctime);
+	inode->i_atime.tv_sec = (signed)le32_to_cpu(fcb.i_atime);
+	inode->i_mtime.tv_sec = (signed)le32_to_cpu(fcb.i_mtime);
+	inode->i_ctime.tv_nsec =
+		inode->i_atime.tv_nsec = inode->i_mtime.tv_nsec = 0;
+	oi->i_commit_size = le64_to_cpu(fcb.i_size);
+	i_size_write(inode, oi->i_commit_size);
+	inode->i_blkbits = EXOFS_BLKSHIFT;
+	inode->i_generation = le32_to_cpu(fcb.i_generation);
+
+#ifdef EXOFS_DEBUG_OBJ_ISIZE
+	if ((inode->i_size != sanity) &&
+		(!exofs_inode_is_fast_symlink(inode))) {
+		EXOFS_ERR("WARNING: Size of object from inode and "
+			  "attributes differ (%lld != %llu)\n",
+			  inode->i_size, _LLU(sanity));
+	}
+#endif
+
+	oi->i_dir_start_lookup = 0;
+
+	if ((inode->i_nlink == 0) && (inode->i_mode == 0)) {
+		ret = -ESTALE;
+		goto bad_inode;
+	}
+
+	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+		if (fcb.i_data[0])
+			inode->i_rdev =
+				old_decode_dev(le32_to_cpu(fcb.i_data[0]));
+		else
+			inode->i_rdev =
+				new_decode_dev(le32_to_cpu(fcb.i_data[1]));
+	} else {
+		memcpy(oi->i_data, fcb.i_data, sizeof(fcb.i_data));
+	}
+
+	if (S_ISREG(inode->i_mode)) {
+		inode->i_op = &exofs_file_inode_operations;
+		inode->i_fop = &exofs_file_operations;
+		inode->i_mapping->a_ops = &exofs_aops;
+	} else if (S_ISDIR(inode->i_mode)) {
+		inode->i_op = &exofs_dir_inode_operations;
+		inode->i_fop = &exofs_dir_operations;
+		inode->i_mapping->a_ops = &exofs_aops;
+	} else if (S_ISLNK(inode->i_mode)) {
+		if (exofs_inode_is_fast_symlink(inode))
+			inode->i_op = &exofs_fast_symlink_inode_operations;
+		else {
+			inode->i_op = &exofs_symlink_inode_operations;
+			inode->i_mapping->a_ops = &exofs_aops;
+		}
+	} else {
+		inode->i_op = &exofs_special_inode_operations;
+		if (fcb.i_data[0])
+			init_special_inode(inode, inode->i_mode,
+			   old_decode_dev(le32_to_cpu(fcb.i_data[0])));
+		else
+			init_special_inode(inode, inode->i_mode,
+			   new_decode_dev(le32_to_cpu(fcb.i_data[1])));
+	}
+
+	unlock_new_inode(inode);
+	return inode;
+
+bad_inode:
+	iget_failed(inode);
+	return ERR_PTR(ret);
+}
+
+int __exofs_wait_obj_created(struct exofs_i_info *oi)
+{
+	if (!obj_created(oi)) {
+		BUG_ON(!obj_2bcreated(oi));
+		wait_event(oi->i_wq, obj_created(oi));
+	}
+	return unlikely(is_bad_inode(&oi->vfs_inode)) ? -EIO : 0;
+}
+/*
+ * Callback function from exofs_new_inode().  The important thing is that we
+ * set the obj_created flag so that other methods know that the object exists on
+ * the OSD.
+ */
+static void create_done(struct osd_request *or, void *p)
+{
+	struct inode *inode = p;
+	struct exofs_i_info *oi = exofs_i(inode);
+	struct exofs_sb_info *sbi = inode->i_sb->s_fs_info;
+	int ret;
+
+	ret = exofs_check_ok(or);
+	osd_end_request(or);
+	atomic_dec(&sbi->s_curr_pending);
+
+	if (unlikely(ret)) {
+		EXOFS_ERR("object=0x%llx creation faild in pid=0x%llx",
+			  _LLU(sbi->s_pid), _LLU(inode->i_ino + EXOFS_OBJ_OFF));
+		make_bad_inode(inode);
+	} else
+		set_obj_created(oi);
+
+	atomic_dec(&inode->i_count);
+	wake_up(&oi->i_wq);
+}
+
+/*
+ * Set up a new inode and create an object for it on the OSD
+ */
+struct inode *exofs_new_inode(struct inode *dir, int mode)
+{
+	struct super_block *sb;
+	struct inode *inode;
+	struct exofs_i_info *oi;
+	struct exofs_sb_info *sbi;
+	struct osd_request *or;
+	struct osd_obj_id obj;
+	int ret;
+
+	sb = dir->i_sb;
+	inode = new_inode(sb);
+	if (!inode)
+		return ERR_PTR(-ENOMEM);
+
+	oi = exofs_i(inode);
+
+	init_waitqueue_head(&oi->i_wq);
+	set_obj_2bcreated(oi);
+
+	sbi = sb->s_fs_info;
+
+	sb->s_dirt = 1;
+	inode->i_uid = current->cred->fsuid;
+	if (dir->i_mode & S_ISGID) {
+		inode->i_gid = dir->i_gid;
+		if (S_ISDIR(mode))
+			mode |= S_ISGID;
+	} else {
+		inode->i_gid = current->cred->fsgid;
+	}
+	inode->i_mode = mode;
+
+	inode->i_ino = sbi->s_nextid++;
+	inode->i_blkbits = EXOFS_BLKSHIFT;
+	inode->i_mtime = inode->i_atime = inode->i_ctime = CURRENT_TIME;
+	oi->i_commit_size = inode->i_size = 0;
+	spin_lock(&sbi->s_next_gen_lock);
+	inode->i_generation = sbi->s_next_generation++;
+	spin_unlock(&sbi->s_next_gen_lock);
+	insert_inode_hash(inode);
+
+	mark_inode_dirty(inode);
+
+	obj.partition = sbi->s_pid;
+	obj.id = inode->i_ino + EXOFS_OBJ_OFF;
+	exofs_make_credential(oi->i_cred, &obj);
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_ERR("exofs_new_inode: osd_start_request failed\n");
+		return ERR_PTR(-ENOMEM);
+	}
+
+	osd_req_create_object(or, &obj);
+
+	/* increment the refcount so that the inode will still be around when we
+	 * reach the callback
+	 */
+	atomic_inc(&inode->i_count);
+
+	ret = exofs_async_op(or, create_done, inode, oi->i_cred);
+	if (ret) {
+		atomic_dec(&inode->i_count);
+		osd_end_request(or);
+		return ERR_PTR(-EIO);
+	}
+	atomic_inc(&sbi->s_curr_pending);
+
+	return inode;
+}
+
+/*
+ * struct to pass two arguments to update_inode's callback
+ */
+struct updatei_args {
+	struct exofs_sb_info	*sbi;
+	struct exofs_fcb	fcb;
+};
+
+/*
+ * Callback function from exofs_update_inode().
+ */
+static void updatei_done(struct osd_request *or, void *p)
+{
+	struct updatei_args *args = p;
+
+	osd_end_request(or);
+
+	atomic_dec(&args->sbi->s_curr_pending);
+
+	kfree(args);
+}
+
+/*
+ * Write the inode to the OSD.  Just fill up the struct, and set the attribute
+ * synchronously or asynchronously depending on the do_sync flag.
+ */
+static int exofs_update_inode(struct inode *inode, int do_sync)
+{
+	struct exofs_i_info *oi = exofs_i(inode);
+	struct super_block *sb = inode->i_sb;
+	struct exofs_sb_info *sbi = sb->s_fs_info;
+	struct osd_obj_id obj = {sbi->s_pid, inode->i_ino + EXOFS_OBJ_OFF};
+	struct osd_request *or;
+	struct osd_attr attr;
+	struct exofs_fcb *fcb;
+	struct updatei_args *args;
+	int ret;
+
+	args = kzalloc(sizeof(*args), GFP_KERNEL);
+	if (!args)
+		return -ENOMEM;
+
+	fcb = &args->fcb;
+
+	fcb->i_mode = cpu_to_le16(inode->i_mode);
+	fcb->i_uid = cpu_to_le32(inode->i_uid);
+	fcb->i_gid = cpu_to_le32(inode->i_gid);
+	fcb->i_links_count = cpu_to_le16(inode->i_nlink);
+	fcb->i_ctime = cpu_to_le32(inode->i_ctime.tv_sec);
+	fcb->i_atime = cpu_to_le32(inode->i_atime.tv_sec);
+	fcb->i_mtime = cpu_to_le32(inode->i_mtime.tv_sec);
+	oi->i_commit_size = i_size_read(inode);
+	fcb->i_size = cpu_to_le64(oi->i_commit_size);
+	fcb->i_generation = cpu_to_le32(inode->i_generation);
+
+	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
+		if (old_valid_dev(inode->i_rdev)) {
+			fcb->i_data[0] =
+				cpu_to_le32(old_encode_dev(inode->i_rdev));
+			fcb->i_data[1] = 0;
+		} else {
+			fcb->i_data[0] = 0;
+			fcb->i_data[1] =
+				cpu_to_le32(new_encode_dev(inode->i_rdev));
+			fcb->i_data[2] = 0;
+		}
+	} else
+		memcpy(fcb->i_data, oi->i_data, sizeof(fcb->i_data));
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_ERR("exofs_update_inode: osd_start_request failed.\n");
+		ret = -ENOMEM;
+		goto free_args;
+	}
+
+	osd_req_set_attributes(or, &obj);
+
+	attr = g_attr_inode_data;
+	attr.val_ptr = fcb;
+	osd_req_add_set_attr_list(or, &attr, 1);
+
+	if (!obj_created(oi)) {
+		EXOFS_DBGMSG("!obj_created\n");
+		BUG_ON(!obj_2bcreated(oi));
+		wait_event(oi->i_wq, obj_created(oi));
+		EXOFS_DBGMSG("wait_event done\n");
+	}
+
+	if (do_sync) {
+		ret = exofs_sync_op(or, sbi->s_timeout, oi->i_cred);
+		osd_end_request(or);
+		goto free_args;
+	} else {
+		args->sbi = sbi;
+
+		ret = exofs_async_op(or, updatei_done, args, oi->i_cred);
+		if (ret) {
+			osd_end_request(or);
+			goto free_args;
+		}
+		atomic_inc(&sbi->s_curr_pending);
+		goto out; /* deallocation in updatei_done */
+	}
+
+free_args:
+	kfree(args);
+out:
+	EXOFS_DBGMSG("ret=>%d\n", ret);
+	return ret;
+}
+
+int exofs_write_inode(struct inode *inode, int wait)
+{
+	return exofs_update_inode(inode, wait);
+}
+
+/*
+ * Callback function from exofs_delete_inode() - don't have much cleaning up to
+ * do.
+ */
+static void delete_done(struct osd_request *or, void *p)
+{
+	struct exofs_sb_info *sbi;
+	osd_end_request(or);
+	sbi = p;
+	atomic_dec(&sbi->s_curr_pending);
+}
+
+/*
+ * Called when the refcount of an inode reaches zero.  We remove the object
+ * from the OSD here.  We make sure the object was created before we try and
+ * delete it.
+ */
+void exofs_delete_inode(struct inode *inode)
+{
+	struct exofs_i_info *oi = exofs_i(inode);
+	struct super_block *sb = inode->i_sb;
+	struct exofs_sb_info *sbi = sb->s_fs_info;
+	struct osd_obj_id obj = {sbi->s_pid, inode->i_ino + EXOFS_OBJ_OFF};
+	struct osd_request *or;
+	int ret;
+
+	truncate_inode_pages(&inode->i_data, 0);
+
+	if (is_bad_inode(inode))
+		goto no_delete;
+
+	mark_inode_dirty(inode);
+	exofs_update_inode(inode, inode_needs_sync(inode));
+
+	inode->i_size = 0;
+	if (inode->i_blocks)
+		exofs_truncate(inode);
+
+	clear_inode(inode);
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_ERR("exofs_delete_inode: osd_start_request failed\n");
+		return;
+	}
+
+	osd_req_remove_object(or, &obj);
+
+	/* if we are deleting an obj that hasn't been created yet, wait */
+	if (!obj_created(oi)) {
+		BUG_ON(!obj_2bcreated(oi));
+		wait_event(oi->i_wq, obj_created(oi));
+	}
+
+	ret = exofs_async_op(or, delete_done, sbi, oi->i_cred);
+	if (ret) {
+		EXOFS_ERR(
+		       "ERROR: @exofs_delete_inode exofs_async_op failed\n");
+		osd_end_request(or);
+		return;
+	}
+	atomic_inc(&sbi->s_curr_pending);
+
+	return;
+
+no_delete:
+	clear_inode(inode);
+}
diff --git a/fs/exofs/namei.c b/fs/exofs/namei.c
new file mode 100644
index 000000000000..77fdd765e76d
--- /dev/null
+++ b/fs/exofs/namei.c
@@ -0,0 +1,342 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include "exofs.h"
+
+static inline int exofs_add_nondir(struct dentry *dentry, struct inode *inode)
+{
+	int err = exofs_add_link(dentry, inode);
+	if (!err) {
+		d_instantiate(dentry, inode);
+		return 0;
+	}
+	inode_dec_link_count(inode);
+	iput(inode);
+	return err;
+}
+
+static struct dentry *exofs_lookup(struct inode *dir, struct dentry *dentry,
+				   struct nameidata *nd)
+{
+	struct inode *inode;
+	ino_t ino;
+
+	if (dentry->d_name.len > EXOFS_NAME_LEN)
+		return ERR_PTR(-ENAMETOOLONG);
+
+	ino = exofs_inode_by_name(dir, dentry);
+	inode = NULL;
+	if (ino) {
+		inode = exofs_iget(dir->i_sb, ino);
+		if (IS_ERR(inode))
+			return ERR_CAST(inode);
+	}
+	return d_splice_alias(inode, dentry);
+}
+
+static int exofs_create(struct inode *dir, struct dentry *dentry, int mode,
+			 struct nameidata *nd)
+{
+	struct inode *inode = exofs_new_inode(dir, mode);
+	int err = PTR_ERR(inode);
+	if (!IS_ERR(inode)) {
+		inode->i_op = &exofs_file_inode_operations;
+		inode->i_fop = &exofs_file_operations;
+		inode->i_mapping->a_ops = &exofs_aops;
+		mark_inode_dirty(inode);
+		err = exofs_add_nondir(dentry, inode);
+	}
+	return err;
+}
+
+static int exofs_mknod(struct inode *dir, struct dentry *dentry, int mode,
+		       dev_t rdev)
+{
+	struct inode *inode;
+	int err;
+
+	if (!new_valid_dev(rdev))
+		return -EINVAL;
+
+	inode = exofs_new_inode(dir, mode);
+	err = PTR_ERR(inode);
+	if (!IS_ERR(inode)) {
+		init_special_inode(inode, inode->i_mode, rdev);
+		mark_inode_dirty(inode);
+		err = exofs_add_nondir(dentry, inode);
+	}
+	return err;
+}
+
+static int exofs_symlink(struct inode *dir, struct dentry *dentry,
+			  const char *symname)
+{
+	struct super_block *sb = dir->i_sb;
+	int err = -ENAMETOOLONG;
+	unsigned l = strlen(symname)+1;
+	struct inode *inode;
+	struct exofs_i_info *oi;
+
+	if (l > sb->s_blocksize)
+		goto out;
+
+	inode = exofs_new_inode(dir, S_IFLNK | S_IRWXUGO);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out;
+
+	oi = exofs_i(inode);
+	if (l > sizeof(oi->i_data)) {
+		/* slow symlink */
+		inode->i_op = &exofs_symlink_inode_operations;
+		inode->i_mapping->a_ops = &exofs_aops;
+		memset(oi->i_data, 0, sizeof(oi->i_data));
+
+		err = page_symlink(inode, symname, l);
+		if (err)
+			goto out_fail;
+	} else {
+		/* fast symlink */
+		inode->i_op = &exofs_fast_symlink_inode_operations;
+		memcpy(oi->i_data, symname, l);
+		inode->i_size = l-1;
+	}
+	mark_inode_dirty(inode);
+
+	err = exofs_add_nondir(dentry, inode);
+out:
+	return err;
+
+out_fail:
+	inode_dec_link_count(inode);
+	iput(inode);
+	goto out;
+}
+
+static int exofs_link(struct dentry *old_dentry, struct inode *dir,
+		struct dentry *dentry)
+{
+	struct inode *inode = old_dentry->d_inode;
+
+	if (inode->i_nlink >= EXOFS_LINK_MAX)
+		return -EMLINK;
+
+	inode->i_ctime = CURRENT_TIME;
+	inode_inc_link_count(inode);
+	atomic_inc(&inode->i_count);
+
+	return exofs_add_nondir(dentry, inode);
+}
+
+static int exofs_mkdir(struct inode *dir, struct dentry *dentry, int mode)
+{
+	struct inode *inode;
+	int err = -EMLINK;
+
+	if (dir->i_nlink >= EXOFS_LINK_MAX)
+		goto out;
+
+	inode_inc_link_count(dir);
+
+	inode = exofs_new_inode(dir, S_IFDIR | mode);
+	err = PTR_ERR(inode);
+	if (IS_ERR(inode))
+		goto out_dir;
+
+	inode->i_op = &exofs_dir_inode_operations;
+	inode->i_fop = &exofs_dir_operations;
+	inode->i_mapping->a_ops = &exofs_aops;
+
+	inode_inc_link_count(inode);
+
+	err = exofs_make_empty(inode, dir);
+	if (err)
+		goto out_fail;
+
+	err = exofs_add_link(dentry, inode);
+	if (err)
+		goto out_fail;
+
+	d_instantiate(dentry, inode);
+out:
+	return err;
+
+out_fail:
+	inode_dec_link_count(inode);
+	inode_dec_link_count(inode);
+	iput(inode);
+out_dir:
+	inode_dec_link_count(dir);
+	goto out;
+}
+
+static int exofs_unlink(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	struct exofs_dir_entry *de;
+	struct page *page;
+	int err = -ENOENT;
+
+	de = exofs_find_entry(dir, dentry, &page);
+	if (!de)
+		goto out;
+
+	err = exofs_delete_entry(de, page);
+	if (err)
+		goto out;
+
+	inode->i_ctime = dir->i_ctime;
+	inode_dec_link_count(inode);
+	err = 0;
+out:
+	return err;
+}
+
+static int exofs_rmdir(struct inode *dir, struct dentry *dentry)
+{
+	struct inode *inode = dentry->d_inode;
+	int err = -ENOTEMPTY;
+
+	if (exofs_empty_dir(inode)) {
+		err = exofs_unlink(dir, dentry);
+		if (!err) {
+			inode->i_size = 0;
+			inode_dec_link_count(inode);
+			inode_dec_link_count(dir);
+		}
+	}
+	return err;
+}
+
+static int exofs_rename(struct inode *old_dir, struct dentry *old_dentry,
+		struct inode *new_dir, struct dentry *new_dentry)
+{
+	struct inode *old_inode = old_dentry->d_inode;
+	struct inode *new_inode = new_dentry->d_inode;
+	struct page *dir_page = NULL;
+	struct exofs_dir_entry *dir_de = NULL;
+	struct page *old_page;
+	struct exofs_dir_entry *old_de;
+	int err = -ENOENT;
+
+	old_de = exofs_find_entry(old_dir, old_dentry, &old_page);
+	if (!old_de)
+		goto out;
+
+	if (S_ISDIR(old_inode->i_mode)) {
+		err = -EIO;
+		dir_de = exofs_dotdot(old_inode, &dir_page);
+		if (!dir_de)
+			goto out_old;
+	}
+
+	if (new_inode) {
+		struct page *new_page;
+		struct exofs_dir_entry *new_de;
+
+		err = -ENOTEMPTY;
+		if (dir_de && !exofs_empty_dir(new_inode))
+			goto out_dir;
+
+		err = -ENOENT;
+		new_de = exofs_find_entry(new_dir, new_dentry, &new_page);
+		if (!new_de)
+			goto out_dir;
+		inode_inc_link_count(old_inode);
+		err = exofs_set_link(new_dir, new_de, new_page, old_inode);
+		new_inode->i_ctime = CURRENT_TIME;
+		if (dir_de)
+			drop_nlink(new_inode);
+		inode_dec_link_count(new_inode);
+		if (err)
+			goto out_dir;
+	} else {
+		if (dir_de) {
+			err = -EMLINK;
+			if (new_dir->i_nlink >= EXOFS_LINK_MAX)
+				goto out_dir;
+		}
+		inode_inc_link_count(old_inode);
+		err = exofs_add_link(new_dentry, old_inode);
+		if (err) {
+			inode_dec_link_count(old_inode);
+			goto out_dir;
+		}
+		if (dir_de)
+			inode_inc_link_count(new_dir);
+	}
+
+	old_inode->i_ctime = CURRENT_TIME;
+
+	exofs_delete_entry(old_de, old_page);
+	inode_dec_link_count(old_inode);
+
+	if (dir_de) {
+		err = exofs_set_link(old_inode, dir_de, dir_page, new_dir);
+		inode_dec_link_count(old_dir);
+		if (err)
+			goto out_dir;
+	}
+	return 0;
+
+
+out_dir:
+	if (dir_de) {
+		kunmap(dir_page);
+		page_cache_release(dir_page);
+	}
+out_old:
+	kunmap(old_page);
+	page_cache_release(old_page);
+out:
+	return err;
+}
+
+const struct inode_operations exofs_dir_inode_operations = {
+	.create 	= exofs_create,
+	.lookup 	= exofs_lookup,
+	.link   	= exofs_link,
+	.unlink 	= exofs_unlink,
+	.symlink	= exofs_symlink,
+	.mkdir  	= exofs_mkdir,
+	.rmdir  	= exofs_rmdir,
+	.mknod  	= exofs_mknod,
+	.rename 	= exofs_rename,
+	.setattr	= exofs_setattr,
+};
+
+const struct inode_operations exofs_special_inode_operations = {
+	.setattr	= exofs_setattr,
+};
diff --git a/fs/exofs/osd.c b/fs/exofs/osd.c
new file mode 100644
index 000000000000..b249ae97fb15
--- /dev/null
+++ b/fs/exofs/osd.c
@@ -0,0 +1,153 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <scsi/scsi_device.h>
+#include <scsi/osd_sense.h>
+
+#include "exofs.h"
+
+int exofs_check_ok_resid(struct osd_request *or, u64 *in_resid, u64 *out_resid)
+{
+	struct osd_sense_info osi;
+	int ret = osd_req_decode_sense(or, &osi);
+
+	if (ret) { /* translate to Linux codes */
+		if (osi.additional_code == scsi_invalid_field_in_cdb) {
+			if (osi.cdb_field_offset == OSD_CFO_STARTING_BYTE)
+				ret = -EFAULT;
+			if (osi.cdb_field_offset == OSD_CFO_OBJECT_ID)
+				ret = -ENOENT;
+			else
+				ret = -EINVAL;
+		} else if (osi.additional_code == osd_quota_error)
+			ret = -ENOSPC;
+		else
+			ret = -EIO;
+	}
+
+	/* FIXME: should be include in osd_sense_info */
+	if (in_resid)
+		*in_resid = or->in.req ? or->in.req->data_len : 0;
+
+	if (out_resid)
+		*out_resid = or->out.req ? or->out.req->data_len : 0;
+
+	return ret;
+}
+
+void exofs_make_credential(u8 cred_a[OSD_CAP_LEN], const struct osd_obj_id *obj)
+{
+	osd_sec_init_nosec_doall_caps(cred_a, obj, false, true);
+}
+
+/*
+ * Perform a synchronous OSD operation.
+ */
+int exofs_sync_op(struct osd_request *or, int timeout, uint8_t *credential)
+{
+	int ret;
+
+	or->timeout = timeout;
+	ret = osd_finalize_request(or, 0, credential, NULL);
+	if (ret) {
+		EXOFS_DBGMSG("Faild to osd_finalize_request() => %d\n", ret);
+		return ret;
+	}
+
+	ret = osd_execute_request(or);
+
+	if (ret)
+		EXOFS_DBGMSG("osd_execute_request() => %d\n", ret);
+	/* osd_req_decode_sense(or, ret); */
+	return ret;
+}
+
+/*
+ * Perform an asynchronous OSD operation.
+ */
+int exofs_async_op(struct osd_request *or, osd_req_done_fn *async_done,
+		   void *caller_context, u8 *cred)
+{
+	int ret;
+
+	ret = osd_finalize_request(or, 0, cred, NULL);
+	if (ret) {
+		EXOFS_DBGMSG("Faild to osd_finalize_request() => %d\n", ret);
+		return ret;
+	}
+
+	ret = osd_execute_request_async(or, async_done, caller_context);
+
+	if (ret)
+		EXOFS_DBGMSG("osd_execute_request_async() => %d\n", ret);
+	return ret;
+}
+
+int extract_attr_from_req(struct osd_request *or, struct osd_attr *attr)
+{
+	struct osd_attr cur_attr = {.attr_page = 0}; /* start with zeros */
+	void *iter = NULL;
+	int nelem;
+
+	do {
+		nelem = 1;
+		osd_req_decode_get_attr_list(or, &cur_attr, &nelem, &iter);
+		if ((cur_attr.attr_page == attr->attr_page) &&
+		    (cur_attr.attr_id == attr->attr_id)) {
+			attr->len = cur_attr.len;
+			attr->val_ptr = cur_attr.val_ptr;
+			return 0;
+		}
+	} while (iter);
+
+	return -EIO;
+}
+
+int osd_req_read_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void* buff, u64 len)
+{
+	struct request_queue *req_q = or->osd_dev->scsi_device->request_queue;
+	struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
+
+	if (!bio)
+		return -ENOMEM;
+
+	osd_req_read(or, obj, bio, offset);
+	return 0;
+}
+
+int osd_req_write_kern(struct osd_request *or,
+	const struct osd_obj_id *obj, u64 offset, void* buff, u64 len)
+{
+	struct request_queue *req_q = or->osd_dev->scsi_device->request_queue;
+	struct bio *bio = bio_map_kern(req_q, buff, len, GFP_KERNEL);
+
+	if (!bio)
+		return -ENOMEM;
+
+	osd_req_write(or, obj, bio, offset);
+	return 0;
+}
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
new file mode 100644
index 000000000000..9f1985e857e2
--- /dev/null
+++ b/fs/exofs/super.c
@@ -0,0 +1,584 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/string.h>
+#include <linux/parser.h>
+#include <linux/vfs.h>
+#include <linux/random.h>
+#include <linux/exportfs.h>
+
+#include "exofs.h"
+
+/******************************************************************************
+ * MOUNT OPTIONS
+ *****************************************************************************/
+
+/*
+ * struct to hold what we get from mount options
+ */
+struct exofs_mountopt {
+	const char *dev_name;
+	uint64_t pid;
+	int timeout;
+};
+
+/*
+ * exofs-specific mount-time options.
+ */
+enum { Opt_pid, Opt_to, Opt_mkfs, Opt_format, Opt_err };
+
+/*
+ * Our mount-time options.  These should ideally be 64-bit unsigned, but the
+ * kernel's parsing functions do not currently support that.  32-bit should be
+ * sufficient for most applications now.
+ */
+static match_table_t tokens = {
+	{Opt_pid, "pid=%u"},
+	{Opt_to, "to=%u"},
+	{Opt_err, NULL}
+};
+
+/*
+ * The main option parsing method.  Also makes sure that all of the mandatory
+ * mount options were set.
+ */
+static int parse_options(char *options, struct exofs_mountopt *opts)
+{
+	char *p;
+	substring_t args[MAX_OPT_ARGS];
+	int option;
+	bool s_pid = false;
+
+	EXOFS_DBGMSG("parse_options %s\n", options);
+	/* defaults */
+	memset(opts, 0, sizeof(*opts));
+	opts->timeout = BLK_DEFAULT_SG_TIMEOUT;
+
+	while ((p = strsep(&options, ",")) != NULL) {
+		int token;
+		char str[32];
+
+		if (!*p)
+			continue;
+
+		token = match_token(p, tokens, args);
+		switch (token) {
+		case Opt_pid:
+			if (0 == match_strlcpy(str, &args[0], sizeof(str)))
+				return -EINVAL;
+			opts->pid = simple_strtoull(str, NULL, 0);
+			if (opts->pid < EXOFS_MIN_PID) {
+				EXOFS_ERR("Partition ID must be >= %u",
+					  EXOFS_MIN_PID);
+				return -EINVAL;
+			}
+			s_pid = 1;
+			break;
+		case Opt_to:
+			if (match_int(&args[0], &option))
+				return -EINVAL;
+			if (option <= 0) {
+				EXOFS_ERR("Timout must be > 0");
+				return -EINVAL;
+			}
+			opts->timeout = option * HZ;
+			break;
+		}
+	}
+
+	if (!s_pid) {
+		EXOFS_ERR("Need to specify the following options:\n");
+		EXOFS_ERR("    -o pid=pid_no_to_use\n");
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+/******************************************************************************
+ * INODE CACHE
+ *****************************************************************************/
+
+/*
+ * Our inode cache.  Isn't it pretty?
+ */
+static struct kmem_cache *exofs_inode_cachep;
+
+/*
+ * Allocate an inode in the cache
+ */
+static struct inode *exofs_alloc_inode(struct super_block *sb)
+{
+	struct exofs_i_info *oi;
+
+	oi = kmem_cache_alloc(exofs_inode_cachep, GFP_KERNEL);
+	if (!oi)
+		return NULL;
+
+	oi->vfs_inode.i_version = 1;
+	return &oi->vfs_inode;
+}
+
+/*
+ * Remove an inode from the cache
+ */
+static void exofs_destroy_inode(struct inode *inode)
+{
+	kmem_cache_free(exofs_inode_cachep, exofs_i(inode));
+}
+
+/*
+ * Initialize the inode
+ */
+static void exofs_init_once(void *foo)
+{
+	struct exofs_i_info *oi = foo;
+
+	inode_init_once(&oi->vfs_inode);
+}
+
+/*
+ * Create and initialize the inode cache
+ */
+static int init_inodecache(void)
+{
+	exofs_inode_cachep = kmem_cache_create("exofs_inode_cache",
+				sizeof(struct exofs_i_info), 0,
+				SLAB_RECLAIM_ACCOUNT | SLAB_MEM_SPREAD,
+				exofs_init_once);
+	if (exofs_inode_cachep == NULL)
+		return -ENOMEM;
+	return 0;
+}
+
+/*
+ * Destroy the inode cache
+ */
+static void destroy_inodecache(void)
+{
+	kmem_cache_destroy(exofs_inode_cachep);
+}
+
+/******************************************************************************
+ * SUPERBLOCK FUNCTIONS
+ *****************************************************************************/
+static const struct super_operations exofs_sops;
+static const struct export_operations exofs_export_ops;
+
+/*
+ * Write the superblock to the OSD
+ */
+static void exofs_write_super(struct super_block *sb)
+{
+	struct exofs_sb_info *sbi;
+	struct exofs_fscb *fscb;
+	struct osd_request *or;
+	struct osd_obj_id obj;
+	int ret;
+
+	fscb = kzalloc(sizeof(struct exofs_fscb), GFP_KERNEL);
+	if (!fscb) {
+		EXOFS_ERR("exofs_write_super: memory allocation failed.\n");
+		return;
+	}
+
+	lock_kernel();
+	sbi = sb->s_fs_info;
+	fscb->s_nextid = cpu_to_le64(sbi->s_nextid);
+	fscb->s_numfiles = cpu_to_le32(sbi->s_numfiles);
+	fscb->s_magic = cpu_to_le16(sb->s_magic);
+	fscb->s_newfs = 0;
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_ERR("exofs_write_super: osd_start_request failed.\n");
+		goto out;
+	}
+
+	obj.partition = sbi->s_pid;
+	obj.id = EXOFS_SUPER_ID;
+	ret = osd_req_write_kern(or, &obj, 0, fscb, sizeof(*fscb));
+	if (unlikely(ret)) {
+		EXOFS_ERR("exofs_write_super: osd_req_write_kern failed.\n");
+		goto out;
+	}
+
+	ret = exofs_sync_op(or, sbi->s_timeout, sbi->s_cred);
+	if (unlikely(ret)) {
+		EXOFS_ERR("exofs_write_super: exofs_sync_op failed.\n");
+		goto out;
+	}
+	sb->s_dirt = 0;
+
+out:
+	if (or)
+		osd_end_request(or);
+	unlock_kernel();
+	kfree(fscb);
+}
+
+/*
+ * This function is called when the vfs is freeing the superblock.  We just
+ * need to free our own part.
+ */
+static void exofs_put_super(struct super_block *sb)
+{
+	int num_pend;
+	struct exofs_sb_info *sbi = sb->s_fs_info;
+
+	/* make sure there are no pending commands */
+	for (num_pend = atomic_read(&sbi->s_curr_pending); num_pend > 0;
+	     num_pend = atomic_read(&sbi->s_curr_pending)) {
+		wait_queue_head_t wq;
+		init_waitqueue_head(&wq);
+		wait_event_timeout(wq,
+				  (atomic_read(&sbi->s_curr_pending) == 0),
+				  msecs_to_jiffies(100));
+	}
+
+	osduld_put_device(sbi->s_dev);
+	kfree(sb->s_fs_info);
+	sb->s_fs_info = NULL;
+}
+
+/*
+ * Read the superblock from the OSD and fill in the fields
+ */
+static int exofs_fill_super(struct super_block *sb, void *data, int silent)
+{
+	struct inode *root;
+	struct exofs_mountopt *opts = data;
+	struct exofs_sb_info *sbi;	/*extended info                  */
+	struct exofs_fscb fscb;		/*on-disk superblock info        */
+	struct osd_request *or = NULL;
+	struct osd_obj_id obj;
+	int ret;
+
+	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
+	if (!sbi)
+		return -ENOMEM;
+	sb->s_fs_info = sbi;
+
+	/* use mount options to fill superblock */
+	sbi->s_dev = osduld_path_lookup(opts->dev_name);
+	if (IS_ERR(sbi->s_dev)) {
+		ret = PTR_ERR(sbi->s_dev);
+		sbi->s_dev = NULL;
+		goto free_sbi;
+	}
+
+	sbi->s_pid = opts->pid;
+	sbi->s_timeout = opts->timeout;
+
+	/* fill in some other data by hand */
+	memset(sb->s_id, 0, sizeof(sb->s_id));
+	strcpy(sb->s_id, "exofs");
+	sb->s_blocksize = EXOFS_BLKSIZE;
+	sb->s_blocksize_bits = EXOFS_BLKSHIFT;
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+	atomic_set(&sbi->s_curr_pending, 0);
+	sb->s_bdev = NULL;
+	sb->s_dev = 0;
+
+	/* read data from on-disk superblock object */
+	obj.partition = sbi->s_pid;
+	obj.id = EXOFS_SUPER_ID;
+	exofs_make_credential(sbi->s_cred, &obj);
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		if (!silent)
+			EXOFS_ERR(
+			       "exofs_fill_super: osd_start_request failed.\n");
+		ret = -ENOMEM;
+		goto free_sbi;
+	}
+	ret = osd_req_read_kern(or, &obj, 0, &fscb, sizeof(fscb));
+	if (unlikely(ret)) {
+		if (!silent)
+			EXOFS_ERR(
+			       "exofs_fill_super: osd_req_read_kern failed.\n");
+		ret = -ENOMEM;
+		goto free_sbi;
+	}
+
+	ret = exofs_sync_op(or, sbi->s_timeout, sbi->s_cred);
+	if (unlikely(ret)) {
+		if (!silent)
+			EXOFS_ERR("exofs_fill_super: exofs_sync_op failed.\n");
+		ret = -EIO;
+		goto free_sbi;
+	}
+
+	sb->s_magic = le16_to_cpu(fscb.s_magic);
+	sbi->s_nextid = le64_to_cpu(fscb.s_nextid);
+	sbi->s_numfiles = le32_to_cpu(fscb.s_numfiles);
+
+	/* make sure what we read from the object store is correct */
+	if (sb->s_magic != EXOFS_SUPER_MAGIC) {
+		if (!silent)
+			EXOFS_ERR("ERROR: Bad magic value\n");
+		ret = -EINVAL;
+		goto free_sbi;
+	}
+
+	/* start generation numbers from a random point */
+	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
+	spin_lock_init(&sbi->s_next_gen_lock);
+
+	/* set up operation vectors */
+	sb->s_op = &exofs_sops;
+	sb->s_export_op = &exofs_export_ops;
+	root = exofs_iget(sb, EXOFS_ROOT_ID - EXOFS_OBJ_OFF);
+	if (IS_ERR(root)) {
+		EXOFS_ERR("ERROR: exofs_iget failed\n");
+		ret = PTR_ERR(root);
+		goto free_sbi;
+	}
+	sb->s_root = d_alloc_root(root);
+	if (!sb->s_root) {
+		iput(root);
+		EXOFS_ERR("ERROR: get root inode failed\n");
+		ret = -ENOMEM;
+		goto free_sbi;
+	}
+
+	if (!S_ISDIR(root->i_mode)) {
+		dput(sb->s_root);
+		sb->s_root = NULL;
+		EXOFS_ERR("ERROR: corrupt root inode (mode = %hd)\n",
+		       root->i_mode);
+		ret = -EINVAL;
+		goto free_sbi;
+	}
+
+	ret = 0;
+out:
+	if (or)
+		osd_end_request(or);
+	return ret;
+
+free_sbi:
+	osduld_put_device(sbi->s_dev); /* NULL safe */
+	kfree(sbi);
+	goto out;
+}
+
+/*
+ * Set up the superblock (calls exofs_fill_super eventually)
+ */
+static int exofs_get_sb(struct file_system_type *type,
+			  int flags, const char *dev_name,
+			  void *data, struct vfsmount *mnt)
+{
+	struct exofs_mountopt opts;
+	int ret;
+
+	ret = parse_options(data, &opts);
+	if (ret)
+		return ret;
+
+	opts.dev_name = dev_name;
+	return get_sb_nodev(type, flags, &opts, exofs_fill_super, mnt);
+}
+
+/*
+ * Return information about the file system state in the buffer.  This is used
+ * by the 'df' command, for example.
+ */
+static int exofs_statfs(struct dentry *dentry, struct kstatfs *buf)
+{
+	struct super_block *sb = dentry->d_sb;
+	struct exofs_sb_info *sbi = sb->s_fs_info;
+	struct osd_obj_id obj = {sbi->s_pid, 0};
+	struct osd_attr attrs[] = {
+		ATTR_DEF(OSD_APAGE_PARTITION_QUOTAS,
+			OSD_ATTR_PQ_CAPACITY_QUOTA, sizeof(__be64)),
+		ATTR_DEF(OSD_APAGE_PARTITION_INFORMATION,
+			OSD_ATTR_PI_USED_CAPACITY, sizeof(__be64)),
+	};
+	uint64_t capacity = ULLONG_MAX;
+	uint64_t used = ULLONG_MAX;
+	struct osd_request *or;
+	uint8_t cred_a[OSD_CAP_LEN];
+	int ret;
+
+	/* get used/capacity attributes */
+	exofs_make_credential(cred_a, &obj);
+
+	or = osd_start_request(sbi->s_dev, GFP_KERNEL);
+	if (unlikely(!or)) {
+		EXOFS_DBGMSG("exofs_statfs: osd_start_request failed.\n");
+		return -ENOMEM;
+	}
+
+	osd_req_get_attributes(or, &obj);
+	osd_req_add_get_attr_list(or, attrs, ARRAY_SIZE(attrs));
+	ret = exofs_sync_op(or, sbi->s_timeout, cred_a);
+	if (unlikely(ret))
+		goto out;
+
+	ret = extract_attr_from_req(or, &attrs[0]);
+	if (likely(!ret))
+		capacity = get_unaligned_be64(attrs[0].val_ptr);
+	else
+		EXOFS_DBGMSG("exofs_statfs: get capacity failed.\n");
+
+	ret = extract_attr_from_req(or, &attrs[1]);
+	if (likely(!ret))
+		used = get_unaligned_be64(attrs[1].val_ptr);
+	else
+		EXOFS_DBGMSG("exofs_statfs: get used-space failed.\n");
+
+	/* fill in the stats buffer */
+	buf->f_type = EXOFS_SUPER_MAGIC;
+	buf->f_bsize = EXOFS_BLKSIZE;
+	buf->f_blocks = (capacity >> EXOFS_BLKSHIFT);
+	buf->f_bfree = ((capacity - used) >> EXOFS_BLKSHIFT);
+	buf->f_bavail = buf->f_bfree;
+	buf->f_files = sbi->s_numfiles;
+	buf->f_ffree = EXOFS_MAX_ID - sbi->s_numfiles;
+	buf->f_namelen = EXOFS_NAME_LEN;
+
+out:
+	osd_end_request(or);
+	return ret;
+}
+
+static const struct super_operations exofs_sops = {
+	.alloc_inode    = exofs_alloc_inode,
+	.destroy_inode  = exofs_destroy_inode,
+	.write_inode    = exofs_write_inode,
+	.delete_inode   = exofs_delete_inode,
+	.put_super      = exofs_put_super,
+	.write_super    = exofs_write_super,
+	.statfs         = exofs_statfs,
+};
+
+/******************************************************************************
+ * EXPORT OPERATIONS
+ *****************************************************************************/
+
+struct dentry *exofs_get_parent(struct dentry *child)
+{
+	unsigned long ino = exofs_parent_ino(child);
+
+	if (!ino)
+		return NULL;
+
+	return d_obtain_alias(exofs_iget(child->d_inode->i_sb, ino));
+}
+
+static struct inode *exofs_nfs_get_inode(struct super_block *sb,
+		u64 ino, u32 generation)
+{
+	struct inode *inode;
+
+	inode = exofs_iget(sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+	if (generation && inode->i_generation != generation) {
+		/* we didn't find the right inode.. */
+		iput(inode);
+		return ERR_PTR(-ESTALE);
+	}
+	return inode;
+}
+
+static struct dentry *exofs_fh_to_dentry(struct super_block *sb,
+				struct fid *fid, int fh_len, int fh_type)
+{
+	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+				    exofs_nfs_get_inode);
+}
+
+static struct dentry *exofs_fh_to_parent(struct super_block *sb,
+				struct fid *fid, int fh_len, int fh_type)
+{
+	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+				    exofs_nfs_get_inode);
+}
+
+static const struct export_operations exofs_export_ops = {
+	.fh_to_dentry = exofs_fh_to_dentry,
+	.fh_to_parent = exofs_fh_to_parent,
+	.get_parent = exofs_get_parent,
+};
+
+/******************************************************************************
+ * INSMOD/RMMOD
+ *****************************************************************************/
+
+/*
+ * struct that describes this file system
+ */
+static struct file_system_type exofs_type = {
+	.owner          = THIS_MODULE,
+	.name           = "exofs",
+	.get_sb         = exofs_get_sb,
+	.kill_sb        = generic_shutdown_super,
+};
+
+static int __init init_exofs(void)
+{
+	int err;
+
+	err = init_inodecache();
+	if (err)
+		goto out;
+
+	err = register_filesystem(&exofs_type);
+	if (err)
+		goto out_d;
+
+	return 0;
+out_d:
+	destroy_inodecache();
+out:
+	return err;
+}
+
+static void __exit exit_exofs(void)
+{
+	unregister_filesystem(&exofs_type);
+	destroy_inodecache();
+}
+
+MODULE_AUTHOR("Avishay Traeger <avishay@gmail.com>");
+MODULE_DESCRIPTION("exofs");
+MODULE_LICENSE("GPL");
+
+module_init(init_exofs)
+module_exit(exit_exofs)
diff --git a/fs/exofs/symlink.c b/fs/exofs/symlink.c
new file mode 100644
index 000000000000..36e2d7bc7f7b
--- /dev/null
+++ b/fs/exofs/symlink.c
@@ -0,0 +1,57 @@
+/*
+ * Copyright (C) 2005, 2006
+ * Avishay Traeger (avishay@gmail.com) (avishay@il.ibm.com)
+ * Copyright (C) 2005, 2006
+ * International Business Machines
+ * Copyright (C) 2008, 2009
+ * Boaz Harrosh <bharrosh@panasas.com>
+ *
+ * Copyrights for code taken from ext2:
+ *     Copyright (C) 1992, 1993, 1994, 1995
+ *     Remy Card (card@masi.ibp.fr)
+ *     Laboratoire MASI - Institut Blaise Pascal
+ *     Universite Pierre et Marie Curie (Paris VI)
+ *     from
+ *     linux/fs/minix/inode.c
+ *     Copyright (C) 1991, 1992  Linus Torvalds
+ *
+ * This file is part of exofs.
+ *
+ * exofs is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.  Since it is based on ext2, and the only
+ * valid version of GPL for the Linux kernel is version 2, the only valid
+ * version of GPL for exofs is version 2.
+ *
+ * exofs is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with exofs; if not, write to the Free Software
+ * Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+
+#include <linux/namei.h>
+
+#include "exofs.h"
+
+static void *exofs_follow_link(struct dentry *dentry, struct nameidata *nd)
+{
+	struct exofs_i_info *oi = exofs_i(dentry->d_inode);
+
+	nd_set_link(nd, (char *)oi->i_data);
+	return NULL;
+}
+
+const struct inode_operations exofs_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= page_follow_link_light,
+	.put_link	= page_put_link,
+};
+
+const struct inode_operations exofs_fast_symlink_inode_operations = {
+	.readlink	= generic_readlink,
+	.follow_link	= exofs_follow_link,
+};
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index ae8c4f850b27..d46e38cb85c5 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -318,7 +318,7 @@ ext2_init_acl(struct inode *inode, struct inode *dir)
 				return PTR_ERR(acl);
 		}
 		if (!acl)
-			inode->i_mode &= ~current->fs->umask;
+			inode->i_mode &= ~current_umask();
 	}
 	if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
                struct posix_acl *clone;
diff --git a/fs/ext3/acl.c b/fs/ext3/acl.c
index b60bb241880c..d81ef2fdb08e 100644
--- a/fs/ext3/acl.c
+++ b/fs/ext3/acl.c
@@ -323,7 +323,7 @@ ext3_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 				return PTR_ERR(acl);
 		}
 		if (!acl)
-			inode->i_mode &= ~current->fs->umask;
+			inode->i_mode &= ~current_umask();
 	}
 	if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
 		struct posix_acl *clone;
diff --git a/fs/ext3/dir.c b/fs/ext3/dir.c
index 5853f4440af4..3d724a95882f 100644
--- a/fs/ext3/dir.c
+++ b/fs/ext3/dir.c
@@ -42,7 +42,7 @@ const struct file_operations ext3_dir_operations = {
 	.llseek		= generic_file_llseek,
 	.read		= generic_read_dir,
 	.readdir	= ext3_readdir,		/* we take BKL. needed?*/
-	.ioctl		= ext3_ioctl,		/* BKL held */
+	.unlocked_ioctl	= ext3_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext3_compat_ioctl,
 #endif
diff --git a/fs/ext3/file.c b/fs/ext3/file.c
index 3be1e0689c9a..5b49704b231b 100644
--- a/fs/ext3/file.c
+++ b/fs/ext3/file.c
@@ -33,6 +33,10 @@
  */
 static int ext3_release_file (struct inode * inode, struct file * filp)
 {
+	if (EXT3_I(inode)->i_state & EXT3_STATE_FLUSH_ON_CLOSE) {
+		filemap_flush(inode->i_mapping);
+		EXT3_I(inode)->i_state &= ~EXT3_STATE_FLUSH_ON_CLOSE;
+	}
 	/* if we are the last writer on the inode, drop the block reservation */
 	if ((filp->f_mode & FMODE_WRITE) &&
 			(atomic_read(&inode->i_writecount) == 1))
@@ -112,7 +116,7 @@ const struct file_operations ext3_file_operations = {
 	.write		= do_sync_write,
 	.aio_read	= generic_file_aio_read,
 	.aio_write	= ext3_file_write,
-	.ioctl		= ext3_ioctl,
+	.unlocked_ioctl	= ext3_ioctl,
 #ifdef CONFIG_COMPAT
 	.compat_ioctl	= ext3_compat_ioctl,
 #endif
diff --git a/fs/ext3/inode.c b/fs/ext3/inode.c
index 4a09ff169870..466a332e0bd1 100644
--- a/fs/ext3/inode.c
+++ b/fs/ext3/inode.c
@@ -1149,12 +1149,15 @@ static int ext3_write_begin(struct file *file, struct address_space *mapping,
 				struct page **pagep, void **fsdata)
 {
 	struct inode *inode = mapping->host;
-	int ret, needed_blocks = ext3_writepage_trans_blocks(inode);
+	int ret;
 	handle_t *handle;
 	int retries = 0;
 	struct page *page;
 	pgoff_t index;
 	unsigned from, to;
+	/* Reserve one block more for addition to orphan list in case
+	 * we allocate blocks but write fails for some reason */
+	int needed_blocks = ext3_writepage_trans_blocks(inode) + 1;
 
 	index = pos >> PAGE_CACHE_SHIFT;
 	from = pos & (PAGE_CACHE_SIZE - 1);
@@ -1184,15 +1187,20 @@ retry:
 	}
 write_begin_failed:
 	if (ret) {
-		ext3_journal_stop(handle);
-		unlock_page(page);
-		page_cache_release(page);
 		/*
 		 * block_write_begin may have instantiated a few blocks
 		 * outside i_size.  Trim these off again. Don't need
 		 * i_size_read because we hold i_mutex.
+		 *
+		 * Add inode to orphan list in case we crash before truncate
+		 * finishes.
 		 */
 		if (pos + len > inode->i_size)
+			ext3_orphan_add(handle, inode);
+		ext3_journal_stop(handle);
+		unlock_page(page);
+		page_cache_release(page);
+		if (pos + len > inode->i_size)
 			vmtruncate(inode, inode->i_size);
 	}
 	if (ret == -ENOSPC && ext3_should_retry_alloc(inode->i_sb, &retries))
@@ -1211,6 +1219,18 @@ int ext3_journal_dirty_data(handle_t *handle, struct buffer_head *bh)
 	return err;
 }
 
+/* For ordered writepage and write_end functions */
+static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
+{
+	/*
+	 * Write could have mapped the buffer but it didn't copy the data in
+	 * yet. So avoid filing such buffer into a transaction.
+	 */
+	if (buffer_mapped(bh) && buffer_uptodate(bh))
+		return ext3_journal_dirty_data(handle, bh);
+	return 0;
+}
+
 /* For write_end() in data=journal mode */
 static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 {
@@ -1221,26 +1241,20 @@ static int write_end_fn(handle_t *handle, struct buffer_head *bh)
 }
 
 /*
- * Generic write_end handler for ordered and writeback ext3 journal modes.
- * We can't use generic_write_end, because that unlocks the page and we need to
- * unlock the page after ext3_journal_stop, but ext3_journal_stop must run
- * after block_write_end.
+ * This is nasty and subtle: ext3_write_begin() could have allocated blocks
+ * for the whole page but later we failed to copy the data in. Update inode
+ * size according to what we managed to copy. The rest is going to be
+ * truncated in write_end function.
  */
-static int ext3_generic_write_end(struct file *file,
-				struct address_space *mapping,
-				loff_t pos, unsigned len, unsigned copied,
-				struct page *page, void *fsdata)
+static void update_file_sizes(struct inode *inode, loff_t pos, unsigned copied)
 {
-	struct inode *inode = file->f_mapping->host;
-
-	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
-
-	if (pos+copied > inode->i_size) {
-		i_size_write(inode, pos+copied);
+	/* What matters to us is i_disksize. We don't write i_size anywhere */
+	if (pos + copied > inode->i_size)
+		i_size_write(inode, pos + copied);
+	if (pos + copied > EXT3_I(inode)->i_disksize) {
+		EXT3_I(inode)->i_disksize = pos + copied;
 		mark_inode_dirty(inode);
 	}
-
-	return copied;
 }
 
 /*
@@ -1260,35 +1274,29 @@ static int ext3_ordered_write_end(struct file *file,
 	unsigned from, to;
 	int ret = 0, ret2;
 
-	from = pos & (PAGE_CACHE_SIZE - 1);
-	to = from + len;
+	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
 
+	from = pos & (PAGE_CACHE_SIZE - 1);
+	to = from + copied;
 	ret = walk_page_buffers(handle, page_buffers(page),
-		from, to, NULL, ext3_journal_dirty_data);
+		from, to, NULL, journal_dirty_data_fn);
 
-	if (ret == 0) {
-		/*
-		 * generic_write_end() will run mark_inode_dirty() if i_size
-		 * changes.  So let's piggyback the i_disksize mark_inode_dirty
-		 * into that.
-		 */
-		loff_t new_i_size;
-
-		new_i_size = pos + copied;
-		if (new_i_size > EXT3_I(inode)->i_disksize)
-			EXT3_I(inode)->i_disksize = new_i_size;
-		ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
-							page, fsdata);
-		copied = ret2;
-		if (ret2 < 0)
-			ret = ret2;
-	}
+	if (ret == 0)
+		update_file_sizes(inode, pos, copied);
+	/*
+	 * There may be allocated blocks outside of i_size because
+	 * we failed to copy some data. Prepare for truncate.
+	 */
+	if (pos + len > inode->i_size)
+		ext3_orphan_add(handle, inode);
 	ret2 = ext3_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (pos + len > inode->i_size)
+		vmtruncate(inode, inode->i_size);
 	return ret ? ret : copied;
 }
 
@@ -1299,25 +1307,22 @@ static int ext3_writeback_write_end(struct file *file,
 {
 	handle_t *handle = ext3_journal_current_handle();
 	struct inode *inode = file->f_mapping->host;
-	int ret = 0, ret2;
-	loff_t new_i_size;
-
-	new_i_size = pos + copied;
-	if (new_i_size > EXT3_I(inode)->i_disksize)
-		EXT3_I(inode)->i_disksize = new_i_size;
-
-	ret2 = ext3_generic_write_end(file, mapping, pos, len, copied,
-							page, fsdata);
-	copied = ret2;
-	if (ret2 < 0)
-		ret = ret2;
+	int ret;
 
-	ret2 = ext3_journal_stop(handle);
-	if (!ret)
-		ret = ret2;
+	copied = block_write_end(file, mapping, pos, len, copied, page, fsdata);
+	update_file_sizes(inode, pos, copied);
+	/*
+	 * There may be allocated blocks outside of i_size because
+	 * we failed to copy some data. Prepare for truncate.
+	 */
+	if (pos + len > inode->i_size)
+		ext3_orphan_add(handle, inode);
+	ret = ext3_journal_stop(handle);
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (pos + len > inode->i_size)
+		vmtruncate(inode, inode->i_size);
 	return ret ? ret : copied;
 }
 
@@ -1338,15 +1343,23 @@ static int ext3_journalled_write_end(struct file *file,
 	if (copied < len) {
 		if (!PageUptodate(page))
 			copied = 0;
-		page_zero_new_buffers(page, from+copied, to);
+		page_zero_new_buffers(page, from + copied, to);
+		to = from + copied;
 	}
 
 	ret = walk_page_buffers(handle, page_buffers(page), from,
 				to, &partial, write_end_fn);
 	if (!partial)
 		SetPageUptodate(page);
-	if (pos+copied > inode->i_size)
-		i_size_write(inode, pos+copied);
+
+	if (pos + copied > inode->i_size)
+		i_size_write(inode, pos + copied);
+	/*
+	 * There may be allocated blocks outside of i_size because
+	 * we failed to copy some data. Prepare for truncate.
+	 */
+	if (pos + len > inode->i_size)
+		ext3_orphan_add(handle, inode);
 	EXT3_I(inode)->i_state |= EXT3_STATE_JDATA;
 	if (inode->i_size > EXT3_I(inode)->i_disksize) {
 		EXT3_I(inode)->i_disksize = inode->i_size;
@@ -1361,6 +1374,8 @@ static int ext3_journalled_write_end(struct file *file,
 	unlock_page(page);
 	page_cache_release(page);
 
+	if (pos + len > inode->i_size)
+		vmtruncate(inode, inode->i_size);
 	return ret ? ret : copied;
 }
 
@@ -1428,17 +1443,11 @@ static int bput_one(handle_t *handle, struct buffer_head *bh)
 	return 0;
 }
 
-static int journal_dirty_data_fn(handle_t *handle, struct buffer_head *bh)
-{
-	if (buffer_mapped(bh))
-		return ext3_journal_dirty_data(handle, bh);
-	return 0;
-}
-
 static int buffer_unmapped(handle_t *handle, struct buffer_head *bh)
 {
 	return !buffer_mapped(bh);
 }
+
 /*
  * Note that we always start a transaction even if we're not journalling
  * data.  This is to preserve ordering: any hole instantiation within
@@ -2354,6 +2363,9 @@ void ext3_truncate(struct inode *inode)
 	if (!ext3_can_truncate(inode))
 		return;
 
+	if (inode->i_size == 0 && ext3_should_writeback_data(inode))
+		ei->i_state |= EXT3_STATE_FLUSH_ON_CLOSE;
+
 	/*
 	 * We have to lock the EOF page here, because lock_page() nests
 	 * outside journal_start().
diff --git a/fs/ext3/ioctl.c b/fs/ext3/ioctl.c
index 5e86ce9a86e0..88974814783a 100644
--- a/fs/ext3/ioctl.c
+++ b/fs/ext3/ioctl.c
@@ -15,12 +15,11 @@
 #include <linux/mount.h>
 #include <linux/time.h>
 #include <linux/compat.h>
-#include <linux/smp_lock.h>
 #include <asm/uaccess.h>
 
-int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
-		unsigned long arg)
+long ext3_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
+	struct inode *inode = filp->f_dentry->d_inode;
 	struct ext3_inode_info *ei = EXT3_I(inode);
 	unsigned int flags;
 	unsigned short rsv_window_size;
@@ -39,29 +38,25 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		unsigned int oldflags;
 		unsigned int jflag;
 
+		if (!is_owner_or_cap(inode))
+			return -EACCES;
+
+		if (get_user(flags, (int __user *) arg))
+			return -EFAULT;
+
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
 			return err;
 
-		if (!is_owner_or_cap(inode)) {
-			err = -EACCES;
-			goto flags_out;
-		}
-
-		if (get_user(flags, (int __user *) arg)) {
-			err = -EFAULT;
-			goto flags_out;
-		}
-
 		flags = ext3_mask_flags(inode->i_mode, flags);
 
 		mutex_lock(&inode->i_mutex);
+
 		/* Is it quota file? Do not allow user to mess with it */
-		if (IS_NOQUOTA(inode)) {
-			mutex_unlock(&inode->i_mutex);
-			err = -EPERM;
+		err = -EPERM;
+		if (IS_NOQUOTA(inode))
 			goto flags_out;
-		}
+
 		oldflags = ei->i_flags;
 
 		/* The JOURNAL_DATA flag is modifiable only by root */
@@ -74,11 +69,8 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		 * This test looks nicer. Thanks to Pauline Middelink
 		 */
 		if ((flags ^ oldflags) & (EXT3_APPEND_FL | EXT3_IMMUTABLE_FL)) {
-			if (!capable(CAP_LINUX_IMMUTABLE)) {
-				mutex_unlock(&inode->i_mutex);
-				err = -EPERM;
+			if (!capable(CAP_LINUX_IMMUTABLE))
 				goto flags_out;
-			}
 		}
 
 		/*
@@ -86,17 +78,12 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		 * the relevant capability.
 		 */
 		if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL)) {
-			if (!capable(CAP_SYS_RESOURCE)) {
-				mutex_unlock(&inode->i_mutex);
-				err = -EPERM;
+			if (!capable(CAP_SYS_RESOURCE))
 				goto flags_out;
-			}
 		}
 
-
 		handle = ext3_journal_start(inode, 1);
 		if (IS_ERR(handle)) {
-			mutex_unlock(&inode->i_mutex);
 			err = PTR_ERR(handle);
 			goto flags_out;
 		}
@@ -116,15 +103,13 @@ int ext3_ioctl (struct inode * inode, struct file * filp, unsigned int cmd,
 		err = ext3_mark_iloc_dirty(handle, inode, &iloc);
 flags_err:
 		ext3_journal_stop(handle);
-		if (err) {
-			mutex_unlock(&inode->i_mutex);
-			return err;
-		}
+		if (err)
+			goto flags_out;
 
 		if ((jflag ^ oldflags) & (EXT3_JOURNAL_DATA_FL))
 			err = ext3_change_inode_journal_flag(inode, jflag);
-		mutex_unlock(&inode->i_mutex);
 flags_out:
+		mutex_unlock(&inode->i_mutex);
 		mnt_drop_write(filp->f_path.mnt);
 		return err;
 	}
@@ -140,6 +125,7 @@ flags_out:
 
 		if (!is_owner_or_cap(inode))
 			return -EPERM;
+
 		err = mnt_want_write(filp->f_path.mnt);
 		if (err)
 			return err;
@@ -147,6 +133,7 @@ flags_out:
 			err = -EFAULT;
 			goto setversion_out;
 		}
+
 		handle = ext3_journal_start(inode, 1);
 		if (IS_ERR(handle)) {
 			err = PTR_ERR(handle);
@@ -299,9 +286,6 @@ group_add_out:
 #ifdef CONFIG_COMPAT
 long ext3_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
-	struct inode *inode = file->f_path.dentry->d_inode;
-	int ret;
-
 	/* These are just misnamed, they actually get/put from/to user an int */
 	switch (cmd) {
 	case EXT3_IOC32_GETFLAGS:
@@ -341,9 +325,6 @@ long ext3_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	default:
 		return -ENOIOCTLCMD;
 	}
-	lock_kernel();
-	ret = ext3_ioctl(inode, file, cmd, (unsigned long) compat_ptr(arg));
-	unlock_kernel();
-	return ret;
+	return ext3_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
 }
 #endif
diff --git a/fs/ext3/namei.c b/fs/ext3/namei.c
index e2fc63cbba8b..6ff7b9730234 100644
--- a/fs/ext3/namei.c
+++ b/fs/ext3/namei.c
@@ -161,12 +161,12 @@ static struct dx_frame *dx_probe(struct qstr *entry,
 				 struct dx_frame *frame,
 				 int *err);
 static void dx_release (struct dx_frame *frames);
-static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
+static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize,
 			struct dx_hash_info *hinfo, struct dx_map_entry map[]);
 static void dx_sort_map(struct dx_map_entry *map, unsigned count);
 static struct ext3_dir_entry_2 *dx_move_dirents (char *from, char *to,
 		struct dx_map_entry *offsets, int count);
-static struct ext3_dir_entry_2* dx_pack_dirents (char *base, int size);
+static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize);
 static void dx_insert_block (struct dx_frame *frame, u32 hash, u32 block);
 static int ext3_htree_next_block(struct inode *dir, __u32 hash,
 				 struct dx_frame *frame,
@@ -708,14 +708,14 @@ errout:
  * Create map of hash values, offsets, and sizes, stored at end of block.
  * Returns number of entries mapped.
  */
-static int dx_make_map (struct ext3_dir_entry_2 *de, int size,
-			struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
+static int dx_make_map(struct ext3_dir_entry_2 *de, unsigned blocksize,
+		struct dx_hash_info *hinfo, struct dx_map_entry *map_tail)
 {
 	int count = 0;
 	char *base = (char *) de;
 	struct dx_hash_info h = *hinfo;
 
-	while ((char *) de < base + size)
+	while ((char *) de < base + blocksize)
 	{
 		if (de->name_len && de->inode) {
 			ext3fs_dirhash(de->name, de->name_len, &h);
@@ -1047,8 +1047,16 @@ static struct dentry *ext3_lookup(struct inode * dir, struct dentry *dentry, str
 			return ERR_PTR(-EIO);
 		}
 		inode = ext3_iget(dir->i_sb, ino);
-		if (IS_ERR(inode))
-			return ERR_CAST(inode);
+		if (unlikely(IS_ERR(inode))) {
+			if (PTR_ERR(inode) == -ESTALE) {
+				ext3_error(dir->i_sb, __func__,
+						"deleted inode referenced: %lu",
+						ino);
+				return ERR_PTR(-EIO);
+			} else {
+				return ERR_CAST(inode);
+			}
+		}
 	}
 	return d_splice_alias(inode, dentry);
 }
@@ -1120,13 +1128,14 @@ dx_move_dirents(char *from, char *to, struct dx_map_entry *map, int count)
  * Compact each dir entry in the range to the minimal rec_len.
  * Returns pointer to last entry in range.
  */
-static struct ext3_dir_entry_2* dx_pack_dirents(char *base, int size)
+static struct ext3_dir_entry_2 *dx_pack_dirents(char *base, unsigned blocksize)
 {
-	struct ext3_dir_entry_2 *next, *to, *prev, *de = (struct ext3_dir_entry_2 *) base;
+	struct ext3_dir_entry_2 *next, *to, *prev;
+	struct ext3_dir_entry_2 *de = (struct ext3_dir_entry_2 *)base;
 	unsigned rec_len = 0;
 
 	prev = to = de;
-	while ((char*)de < base + size) {
+	while ((char *)de < base + blocksize) {
 		next = ext3_next_entry(de);
 		if (de->inode && de->name_len) {
 			rec_len = EXT3_DIR_REC_LEN(de->name_len);
@@ -2265,7 +2274,7 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 	struct inode * old_inode, * new_inode;
 	struct buffer_head * old_bh, * new_bh, * dir_bh;
 	struct ext3_dir_entry_2 * old_de, * new_de;
-	int retval;
+	int retval, flush_file = 0;
 
 	old_bh = new_bh = dir_bh = NULL;
 
@@ -2401,6 +2410,8 @@ static int ext3_rename (struct inode * old_dir, struct dentry *old_dentry,
 		ext3_mark_inode_dirty(handle, new_inode);
 		if (!new_inode->i_nlink)
 			ext3_orphan_add(handle, new_inode);
+		if (ext3_should_writeback_data(new_inode))
+			flush_file = 1;
 	}
 	retval = 0;
 
@@ -2409,6 +2420,8 @@ end_rename:
 	brelse (old_bh);
 	brelse (new_bh);
 	ext3_journal_stop(handle);
+	if (retval == 0 && flush_file)
+		filemap_flush(old_inode->i_mapping);
 	return retval;
 }
 
diff --git a/fs/ext4/Kconfig b/fs/ext4/Kconfig
index 7505482a08fa..418b6f3b0ae8 100644
--- a/fs/ext4/Kconfig
+++ b/fs/ext4/Kconfig
@@ -18,7 +18,7 @@ config EXT4_FS
 	  filesystem; while there will be some performance gains from
 	  the delayed allocation and inode table readahead, the best
 	  performance gains will require enabling ext4 features in the
-	  filesystem, or formating a new filesystem as an ext4
+	  filesystem, or formatting a new filesystem as an ext4
 	  filesystem initially.
 
 	  To compile this file system support as a module, choose M here. The
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index 694ed6fadcc8..647e0d65a284 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -323,7 +323,7 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 				return PTR_ERR(acl);
 		}
 		if (!acl)
-			inode->i_mode &= ~current->fs->umask;
+			inode->i_mode &= ~current_umask();
 	}
 	if (test_opt(inode->i_sb, POSIX_ACL) && acl) {
 		struct posix_acl *clone;
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index de0004fe6e00..296785a0dec8 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -523,7 +523,9 @@ static int fat_remount(struct super_block *sb, int *flags, char *data)
 
 static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct msdos_sb_info *sbi = MSDOS_SB(dentry->d_sb);
+	struct super_block *sb = dentry->d_sb;
+	struct msdos_sb_info *sbi = MSDOS_SB(sb);
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	/* If the count of free cluster is still unknown, counts it here. */
 	if (sbi->free_clusters == -1 || !sbi->free_clus_valid) {
@@ -537,6 +539,8 @@ static int fat_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_blocks = sbi->max_cluster - FAT_START_ENT;
 	buf->f_bfree = sbi->free_clusters;
 	buf->f_bavail = sbi->free_clusters;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = sbi->options.isvfat ? 260 : 12;
 
 	return 0;
@@ -930,7 +934,7 @@ static int parse_options(char *options, int is_vfat, int silent, int *debug,
 
 	opts->fs_uid = current_uid();
 	opts->fs_gid = current_gid();
-	opts->fs_fmask = opts->fs_dmask = current->fs->umask;
+	opts->fs_fmask = current_umask();
 	opts->allow_utime = -1;
 	opts->codepage = fat_default_codepage;
 	opts->iocharset = fat_default_iocharset;
diff --git a/fs/file_table.c b/fs/file_table.c
index b74a8e1da913..54018fe48840 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -169,7 +169,6 @@ struct file *alloc_file(struct vfsmount *mnt, struct dentry *dentry,
 		fmode_t mode, const struct file_operations *fop)
 {
 	struct file *file;
-	struct path;
 
 	file = get_empty_filp();
 	if (!file)
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index e3fe9918faaf..91013ff7dd53 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -196,7 +196,7 @@ static void redirty_tail(struct inode *inode)
 		struct inode *tail_inode;
 
 		tail_inode = list_entry(sb->s_dirty.next, struct inode, i_list);
-		if (!time_after_eq(inode->dirtied_when,
+		if (time_before(inode->dirtied_when,
 				tail_inode->dirtied_when))
 			inode->dirtied_when = jiffies;
 	}
@@ -220,6 +220,21 @@ static void inode_sync_complete(struct inode *inode)
 	wake_up_bit(&inode->i_state, __I_SYNC);
 }
 
+static bool inode_dirtied_after(struct inode *inode, unsigned long t)
+{
+	bool ret = time_after(inode->dirtied_when, t);
+#ifndef CONFIG_64BIT
+	/*
+	 * For inodes being constantly redirtied, dirtied_when can get stuck.
+	 * It _appears_ to be in the future, but is actually in distant past.
+	 * This test is necessary to prevent such wrapped-around relative times
+	 * from permanently stopping the whole pdflush writeback.
+	 */
+	ret = ret && time_before_eq(inode->dirtied_when, jiffies);
+#endif
+	return ret;
+}
+
 /*
  * Move expired dirty inodes from @delaying_queue to @dispatch_queue.
  */
@@ -231,7 +246,7 @@ static void move_expired_inodes(struct list_head *delaying_queue,
 		struct inode *inode = list_entry(delaying_queue->prev,
 						struct inode, i_list);
 		if (older_than_this &&
-			time_after(inode->dirtied_when, *older_than_this))
+		    inode_dirtied_after(inode, *older_than_this))
 			break;
 		list_move(&inode->i_list, dispatch_queue);
 	}
@@ -420,7 +435,7 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc)
  * If older_than_this is non-NULL, then only write out inodes which
  * had their first dirtying at a time earlier than *older_than_this.
  *
- * If we're a pdlfush thread, then implement pdflush collision avoidance
+ * If we're a pdflush thread, then implement pdflush collision avoidance
  * against the entire list.
  *
  * If `bdi' is non-zero then we're being asked to writeback a specific queue.
@@ -492,8 +507,11 @@ void generic_sync_sb_inodes(struct super_block *sb,
 			continue;		/* blockdev has wrong queue */
 		}
 
-		/* Was this inode dirtied after sync_sb_inodes was called? */
-		if (time_after(inode->dirtied_when, start))
+		/*
+		 * Was this inode dirtied after sync_sb_inodes was called?
+		 * This keeps sync from extra jobs and livelock.
+		 */
+		if (inode_dirtied_after(inode, start))
 			break;
 
 		/* Is another pdflush already flushing this queue? */
@@ -538,7 +556,8 @@ void generic_sync_sb_inodes(struct super_block *sb,
 		list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
 			struct address_space *mapping;
 
-			if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+			if (inode->i_state &
+					(I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
 				continue;
 			mapping = inode->i_mapping;
 			if (mapping->nrpages == 0)
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
new file mode 100644
index 000000000000..eee059052db5
--- /dev/null
+++ b/fs/fs_struct.c
@@ -0,0 +1,177 @@
+#include <linux/module.h>
+#include <linux/sched.h>
+#include <linux/fs.h>
+#include <linux/path.h>
+#include <linux/slab.h>
+#include <linux/fs_struct.h>
+
+/*
+ * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
+ * It can block.
+ */
+void set_fs_root(struct fs_struct *fs, struct path *path)
+{
+	struct path old_root;
+
+	write_lock(&fs->lock);
+	old_root = fs->root;
+	fs->root = *path;
+	path_get(path);
+	write_unlock(&fs->lock);
+	if (old_root.dentry)
+		path_put(&old_root);
+}
+
+/*
+ * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
+ * It can block.
+ */
+void set_fs_pwd(struct fs_struct *fs, struct path *path)
+{
+	struct path old_pwd;
+
+	write_lock(&fs->lock);
+	old_pwd = fs->pwd;
+	fs->pwd = *path;
+	path_get(path);
+	write_unlock(&fs->lock);
+
+	if (old_pwd.dentry)
+		path_put(&old_pwd);
+}
+
+void chroot_fs_refs(struct path *old_root, struct path *new_root)
+{
+	struct task_struct *g, *p;
+	struct fs_struct *fs;
+	int count = 0;
+
+	read_lock(&tasklist_lock);
+	do_each_thread(g, p) {
+		task_lock(p);
+		fs = p->fs;
+		if (fs) {
+			write_lock(&fs->lock);
+			if (fs->root.dentry == old_root->dentry
+			    && fs->root.mnt == old_root->mnt) {
+				path_get(new_root);
+				fs->root = *new_root;
+				count++;
+			}
+			if (fs->pwd.dentry == old_root->dentry
+			    && fs->pwd.mnt == old_root->mnt) {
+				path_get(new_root);
+				fs->pwd = *new_root;
+				count++;
+			}
+			write_unlock(&fs->lock);
+		}
+		task_unlock(p);
+	} while_each_thread(g, p);
+	read_unlock(&tasklist_lock);
+	while (count--)
+		path_put(old_root);
+}
+
+void free_fs_struct(struct fs_struct *fs)
+{
+	path_put(&fs->root);
+	path_put(&fs->pwd);
+	kmem_cache_free(fs_cachep, fs);
+}
+
+void exit_fs(struct task_struct *tsk)
+{
+	struct fs_struct *fs = tsk->fs;
+
+	if (fs) {
+		int kill;
+		task_lock(tsk);
+		write_lock(&fs->lock);
+		tsk->fs = NULL;
+		kill = !--fs->users;
+		write_unlock(&fs->lock);
+		task_unlock(tsk);
+		if (kill)
+			free_fs_struct(fs);
+	}
+}
+
+struct fs_struct *copy_fs_struct(struct fs_struct *old)
+{
+	struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
+	/* We don't need to lock fs - think why ;-) */
+	if (fs) {
+		fs->users = 1;
+		fs->in_exec = 0;
+		rwlock_init(&fs->lock);
+		fs->umask = old->umask;
+		read_lock(&old->lock);
+		fs->root = old->root;
+		path_get(&old->root);
+		fs->pwd = old->pwd;
+		path_get(&old->pwd);
+		read_unlock(&old->lock);
+	}
+	return fs;
+}
+
+int unshare_fs_struct(void)
+{
+	struct fs_struct *fs = current->fs;
+	struct fs_struct *new_fs = copy_fs_struct(fs);
+	int kill;
+
+	if (!new_fs)
+		return -ENOMEM;
+
+	task_lock(current);
+	write_lock(&fs->lock);
+	kill = !--fs->users;
+	current->fs = new_fs;
+	write_unlock(&fs->lock);
+	task_unlock(current);
+
+	if (kill)
+		free_fs_struct(fs);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(unshare_fs_struct);
+
+int current_umask(void)
+{
+	return current->fs->umask;
+}
+EXPORT_SYMBOL(current_umask);
+
+/* to be mentioned only in INIT_TASK */
+struct fs_struct init_fs = {
+	.users		= 1,
+	.lock		= __RW_LOCK_UNLOCKED(init_fs.lock),
+	.umask		= 0022,
+};
+
+void daemonize_fs_struct(void)
+{
+	struct fs_struct *fs = current->fs;
+
+	if (fs) {
+		int kill;
+
+		task_lock(current);
+
+		write_lock(&init_fs.lock);
+		init_fs.users++;
+		write_unlock(&init_fs.lock);
+
+		write_lock(&fs->lock);
+		current->fs = &init_fs;
+		kill = !--fs->users;
+		write_unlock(&fs->lock);
+
+		task_unlock(current);
+		if (kill)
+			free_fs_struct(fs);
+	}
+}
diff --git a/fs/fscache/Kconfig b/fs/fscache/Kconfig
new file mode 100644
index 000000000000..9bbb8ce7bea0
--- /dev/null
+++ b/fs/fscache/Kconfig
@@ -0,0 +1,56 @@
+
+config FSCACHE
+	tristate "General filesystem local caching manager"
+	depends on EXPERIMENTAL
+	select SLOW_WORK
+	help
+	  This option enables a generic filesystem caching manager that can be
+	  used by various network and other filesystems to cache data locally.
+	  Different sorts of caches can be plugged in, depending on the
+	  resources available.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_STATS
+	bool "Gather statistical information on local caching"
+	depends on FSCACHE && PROC_FS
+	help
+	  This option causes statistical information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/stats
+
+	  The gathering of statistics adds a certain amount of overhead to
+	  execution as there are a quite a few stats gathered, and on a
+	  multi-CPU system these may be on cachelines that keep bouncing
+	  between CPUs.  On the other hand, the stats are very useful for
+	  debugging purposes.  Saying 'Y' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_HISTOGRAM
+	bool "Gather latency information on local caching"
+	depends on FSCACHE && PROC_FS
+	help
+	  This option causes latency information to be gathered on local
+	  caching and exported through file:
+
+		/proc/fs/fscache/histogram
+
+	  The generation of this histogram adds a certain amount of overhead to
+	  execution as there are a number of points at which data is gathered,
+	  and on a multi-CPU system these may be on cachelines that keep
+	  bouncing between CPUs.  On the other hand, the histogram may be
+	  useful for debugging purposes.  Saying 'N' here is recommended.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
+
+config FSCACHE_DEBUG
+	bool "Debug FS-Cache"
+	depends on FSCACHE
+	help
+	  This permits debugging to be dynamically enabled in the local caching
+	  management module.  If this is set, the debugging output may be
+	  enabled by setting bits in /sys/modules/fscache/parameter/debug.
+
+	  See Documentation/filesystems/caching/fscache.txt for more information.
diff --git a/fs/fscache/Makefile b/fs/fscache/Makefile
new file mode 100644
index 000000000000..91571b95aacc
--- /dev/null
+++ b/fs/fscache/Makefile
@@ -0,0 +1,19 @@
+#
+# Makefile for general filesystem caching code
+#
+
+fscache-y := \
+	cache.o \
+	cookie.o \
+	fsdef.o \
+	main.o \
+	netfs.o \
+	object.o \
+	operation.o \
+	page.o
+
+fscache-$(CONFIG_PROC_FS) += proc.o
+fscache-$(CONFIG_FSCACHE_STATS) += stats.o
+fscache-$(CONFIG_FSCACHE_HISTOGRAM) += histogram.o
+
+obj-$(CONFIG_FSCACHE) := fscache.o
diff --git a/fs/fscache/cache.c b/fs/fscache/cache.c
new file mode 100644
index 000000000000..e21985bbb1fb
--- /dev/null
+++ b/fs/fscache/cache.c
@@ -0,0 +1,415 @@
+/* FS-Cache cache handling
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+LIST_HEAD(fscache_cache_list);
+DECLARE_RWSEM(fscache_addremove_sem);
+DECLARE_WAIT_QUEUE_HEAD(fscache_cache_cleared_wq);
+EXPORT_SYMBOL(fscache_cache_cleared_wq);
+
+static LIST_HEAD(fscache_cache_tag_list);
+
+/*
+ * look up a cache tag
+ */
+struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *name)
+{
+	struct fscache_cache_tag *tag, *xtag;
+
+	/* firstly check for the existence of the tag under read lock */
+	down_read(&fscache_addremove_sem);
+
+	list_for_each_entry(tag, &fscache_cache_tag_list, link) {
+		if (strcmp(tag->name, name) == 0) {
+			atomic_inc(&tag->usage);
+			up_read(&fscache_addremove_sem);
+			return tag;
+		}
+	}
+
+	up_read(&fscache_addremove_sem);
+
+	/* the tag does not exist - create a candidate */
+	xtag = kzalloc(sizeof(*xtag) + strlen(name) + 1, GFP_KERNEL);
+	if (!xtag)
+		/* return a dummy tag if out of memory */
+		return ERR_PTR(-ENOMEM);
+
+	atomic_set(&xtag->usage, 1);
+	strcpy(xtag->name, name);
+
+	/* write lock, search again and add if still not present */
+	down_write(&fscache_addremove_sem);
+
+	list_for_each_entry(tag, &fscache_cache_tag_list, link) {
+		if (strcmp(tag->name, name) == 0) {
+			atomic_inc(&tag->usage);
+			up_write(&fscache_addremove_sem);
+			kfree(xtag);
+			return tag;
+		}
+	}
+
+	list_add_tail(&xtag->link, &fscache_cache_tag_list);
+	up_write(&fscache_addremove_sem);
+	return xtag;
+}
+
+/*
+ * release a reference to a cache tag
+ */
+void __fscache_release_cache_tag(struct fscache_cache_tag *tag)
+{
+	if (tag != ERR_PTR(-ENOMEM)) {
+		down_write(&fscache_addremove_sem);
+
+		if (atomic_dec_and_test(&tag->usage))
+			list_del_init(&tag->link);
+		else
+			tag = NULL;
+
+		up_write(&fscache_addremove_sem);
+
+		kfree(tag);
+	}
+}
+
+/*
+ * select a cache in which to store an object
+ * - the cache addremove semaphore must be at least read-locked by the caller
+ * - the object will never be an index
+ */
+struct fscache_cache *fscache_select_cache_for_object(
+	struct fscache_cookie *cookie)
+{
+	struct fscache_cache_tag *tag;
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+
+	_enter("");
+
+	if (list_empty(&fscache_cache_list)) {
+		_leave(" = NULL [no cache]");
+		return NULL;
+	}
+
+	/* we check the parent to determine the cache to use */
+	spin_lock(&cookie->lock);
+
+	/* the first in the parent's backing list should be the preferred
+	 * cache */
+	if (!hlist_empty(&cookie->backing_objects)) {
+		object = hlist_entry(cookie->backing_objects.first,
+				     struct fscache_object, cookie_link);
+
+		cache = object->cache;
+		if (object->state >= FSCACHE_OBJECT_DYING ||
+		    test_bit(FSCACHE_IOERROR, &cache->flags))
+			cache = NULL;
+
+		spin_unlock(&cookie->lock);
+		_leave(" = %p [parent]", cache);
+		return cache;
+	}
+
+	/* the parent is unbacked */
+	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		/* cookie not an index and is unbacked */
+		spin_unlock(&cookie->lock);
+		_leave(" = NULL [cookie ub,ni]");
+		return NULL;
+	}
+
+	spin_unlock(&cookie->lock);
+
+	if (!cookie->def->select_cache)
+		goto no_preference;
+
+	/* ask the netfs for its preference */
+	tag = cookie->def->select_cache(cookie->parent->netfs_data,
+					cookie->netfs_data);
+	if (!tag)
+		goto no_preference;
+
+	if (tag == ERR_PTR(-ENOMEM)) {
+		_leave(" = NULL [nomem tag]");
+		return NULL;
+	}
+
+	if (!tag->cache) {
+		_leave(" = NULL [unbacked tag]");
+		return NULL;
+	}
+
+	if (test_bit(FSCACHE_IOERROR, &tag->cache->flags))
+		return NULL;
+
+	_leave(" = %p [specific]", tag->cache);
+	return tag->cache;
+
+no_preference:
+	/* netfs has no preference - just select first cache */
+	cache = list_entry(fscache_cache_list.next,
+			   struct fscache_cache, link);
+	_leave(" = %p [first]", cache);
+	return cache;
+}
+
+/**
+ * fscache_init_cache - Initialise a cache record
+ * @cache: The cache record to be initialised
+ * @ops: The cache operations to be installed in that record
+ * @idfmt: Format string to define identifier
+ * @...: sprintf-style arguments
+ *
+ * Initialise a record of a cache and fill in the name.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_init_cache(struct fscache_cache *cache,
+			const struct fscache_cache_ops *ops,
+			const char *idfmt,
+			...)
+{
+	va_list va;
+
+	memset(cache, 0, sizeof(*cache));
+
+	cache->ops = ops;
+
+	va_start(va, idfmt);
+	vsnprintf(cache->identifier, sizeof(cache->identifier), idfmt, va);
+	va_end(va);
+
+	INIT_WORK(&cache->op_gc, fscache_operation_gc);
+	INIT_LIST_HEAD(&cache->link);
+	INIT_LIST_HEAD(&cache->object_list);
+	INIT_LIST_HEAD(&cache->op_gc_list);
+	spin_lock_init(&cache->object_list_lock);
+	spin_lock_init(&cache->op_gc_list_lock);
+}
+EXPORT_SYMBOL(fscache_init_cache);
+
+/**
+ * fscache_add_cache - Declare a cache as being open for business
+ * @cache: The record describing the cache
+ * @ifsdef: The record of the cache object describing the top-level index
+ * @tagname: The tag describing this cache
+ *
+ * Add a cache to the system, making it available for netfs's to use.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+int fscache_add_cache(struct fscache_cache *cache,
+		      struct fscache_object *ifsdef,
+		      const char *tagname)
+{
+	struct fscache_cache_tag *tag;
+
+	BUG_ON(!cache->ops);
+	BUG_ON(!ifsdef);
+
+	cache->flags = 0;
+	ifsdef->event_mask = ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+	ifsdef->state = FSCACHE_OBJECT_ACTIVE;
+
+	if (!tagname)
+		tagname = cache->identifier;
+
+	BUG_ON(!tagname[0]);
+
+	_enter("{%s.%s},,%s", cache->ops->name, cache->identifier, tagname);
+
+	/* we use the cache tag to uniquely identify caches */
+	tag = __fscache_lookup_cache_tag(tagname);
+	if (IS_ERR(tag))
+		goto nomem;
+
+	if (test_and_set_bit(FSCACHE_TAG_RESERVED, &tag->flags))
+		goto tag_in_use;
+
+	cache->kobj = kobject_create_and_add(tagname, fscache_root);
+	if (!cache->kobj)
+		goto error;
+
+	ifsdef->cookie = &fscache_fsdef_index;
+	ifsdef->cache = cache;
+	cache->fsdef = ifsdef;
+
+	down_write(&fscache_addremove_sem);
+
+	tag->cache = cache;
+	cache->tag = tag;
+
+	/* add the cache to the list */
+	list_add(&cache->link, &fscache_cache_list);
+
+	/* add the cache's netfs definition index object to the cache's
+	 * list */
+	spin_lock(&cache->object_list_lock);
+	list_add_tail(&ifsdef->cache_link, &cache->object_list);
+	spin_unlock(&cache->object_list_lock);
+
+	/* add the cache's netfs definition index object to the top level index
+	 * cookie as a known backing object */
+	spin_lock(&fscache_fsdef_index.lock);
+
+	hlist_add_head(&ifsdef->cookie_link,
+		       &fscache_fsdef_index.backing_objects);
+
+	atomic_inc(&fscache_fsdef_index.usage);
+
+	/* done */
+	spin_unlock(&fscache_fsdef_index.lock);
+	up_write(&fscache_addremove_sem);
+
+	printk(KERN_NOTICE "FS-Cache: Cache \"%s\" added (type %s)\n",
+	       cache->tag->name, cache->ops->name);
+	kobject_uevent(cache->kobj, KOBJ_ADD);
+
+	_leave(" = 0 [%s]", cache->identifier);
+	return 0;
+
+tag_in_use:
+	printk(KERN_ERR "FS-Cache: Cache tag '%s' already in use\n", tagname);
+	__fscache_release_cache_tag(tag);
+	_leave(" = -EXIST");
+	return -EEXIST;
+
+error:
+	__fscache_release_cache_tag(tag);
+	_leave(" = -EINVAL");
+	return -EINVAL;
+
+nomem:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(fscache_add_cache);
+
+/**
+ * fscache_io_error - Note a cache I/O error
+ * @cache: The record describing the cache
+ *
+ * Note that an I/O error occurred in a cache and that it should no longer be
+ * used for anything.  This also reports the error into the kernel log.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_io_error(struct fscache_cache *cache)
+{
+	set_bit(FSCACHE_IOERROR, &cache->flags);
+
+	printk(KERN_ERR "FS-Cache: Cache %s stopped due to I/O error\n",
+	       cache->ops->name);
+}
+EXPORT_SYMBOL(fscache_io_error);
+
+/*
+ * request withdrawal of all the objects in a cache
+ * - all the objects being withdrawn are moved onto the supplied list
+ */
+static void fscache_withdraw_all_objects(struct fscache_cache *cache,
+					 struct list_head *dying_objects)
+{
+	struct fscache_object *object;
+
+	spin_lock(&cache->object_list_lock);
+
+	while (!list_empty(&cache->object_list)) {
+		object = list_entry(cache->object_list.next,
+				    struct fscache_object, cache_link);
+		list_move_tail(&object->cache_link, dying_objects);
+
+		_debug("withdraw %p", object->cookie);
+
+		spin_lock(&object->lock);
+		spin_unlock(&cache->object_list_lock);
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_WITHDRAW);
+		spin_unlock(&object->lock);
+
+		cond_resched();
+		spin_lock(&cache->object_list_lock);
+	}
+
+	spin_unlock(&cache->object_list_lock);
+}
+
+/**
+ * fscache_withdraw_cache - Withdraw a cache from the active service
+ * @cache: The record describing the cache
+ *
+ * Withdraw a cache from service, unbinding all its cache objects from the
+ * netfs cookies they're currently representing.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+void fscache_withdraw_cache(struct fscache_cache *cache)
+{
+	LIST_HEAD(dying_objects);
+
+	_enter("");
+
+	printk(KERN_NOTICE "FS-Cache: Withdrawing cache \"%s\"\n",
+	       cache->tag->name);
+
+	/* make the cache unavailable for cookie acquisition */
+	if (test_and_set_bit(FSCACHE_CACHE_WITHDRAWN, &cache->flags))
+		BUG();
+
+	down_write(&fscache_addremove_sem);
+	list_del_init(&cache->link);
+	cache->tag->cache = NULL;
+	up_write(&fscache_addremove_sem);
+
+	/* make sure all pages pinned by operations on behalf of the netfs are
+	 * written to disk */
+	cache->ops->sync_cache(cache);
+
+	/* dissociate all the netfs pages backed by this cache from the block
+	 * mappings in the cache */
+	cache->ops->dissociate_pages(cache);
+
+	/* we now have to destroy all the active objects pertaining to this
+	 * cache - which we do by passing them off to thread pool to be
+	 * disposed of */
+	_debug("destroy");
+
+	fscache_withdraw_all_objects(cache, &dying_objects);
+
+	/* wait for all extant objects to finish their outstanding operations
+	 * and go away */
+	_debug("wait for finish");
+	wait_event(fscache_cache_cleared_wq,
+		   atomic_read(&cache->object_count) == 0);
+	_debug("wait for clearance");
+	wait_event(fscache_cache_cleared_wq,
+		   list_empty(&cache->object_list));
+	_debug("cleared");
+	ASSERT(list_empty(&dying_objects));
+
+	kobject_put(cache->kobj);
+
+	clear_bit(FSCACHE_TAG_RESERVED, &cache->tag->flags);
+	fscache_release_cache_tag(cache->tag);
+	cache->tag = NULL;
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_withdraw_cache);
diff --git a/fs/fscache/cookie.c b/fs/fscache/cookie.c
new file mode 100644
index 000000000000..72fd18f6c71f
--- /dev/null
+++ b/fs/fscache/cookie.c
@@ -0,0 +1,500 @@
+/* netfs cookie management
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for more information on
+ * the netfs API.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+struct kmem_cache *fscache_cookie_jar;
+
+static atomic_t fscache_object_debug_id = ATOMIC_INIT(0);
+
+static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie);
+static int fscache_alloc_object(struct fscache_cache *cache,
+				struct fscache_cookie *cookie);
+static int fscache_attach_object(struct fscache_cookie *cookie,
+				 struct fscache_object *object);
+
+/*
+ * initialise an cookie jar slab element prior to any use
+ */
+void fscache_cookie_init_once(void *_cookie)
+{
+	struct fscache_cookie *cookie = _cookie;
+
+	memset(cookie, 0, sizeof(*cookie));
+	spin_lock_init(&cookie->lock);
+	INIT_HLIST_HEAD(&cookie->backing_objects);
+}
+
+/*
+ * request a cookie to represent an object (index, datafile, xattr, etc)
+ * - parent specifies the parent object
+ *   - the top level index cookie for each netfs is stored in the fscache_netfs
+ *     struct upon registration
+ * - def points to the definition
+ * - the netfs_data will be passed to the functions pointed to in *def
+ * - all attached caches will be searched to see if they contain this object
+ * - index objects aren't stored on disk until there's a dependent file that
+ *   needs storing
+ * - other objects are stored in a selected cache immediately, and all the
+ *   indices forming the path to it are instantiated if necessary
+ * - we never let on to the netfs about errors
+ *   - we may set a negative cookie pointer, but that's okay
+ */
+struct fscache_cookie *__fscache_acquire_cookie(
+	struct fscache_cookie *parent,
+	const struct fscache_cookie_def *def,
+	void *netfs_data)
+{
+	struct fscache_cookie *cookie;
+
+	BUG_ON(!def);
+
+	_enter("{%s},{%s},%p",
+	       parent ? (char *) parent->def->name : "<no-parent>",
+	       def->name, netfs_data);
+
+	fscache_stat(&fscache_n_acquires);
+
+	/* if there's no parent cookie, then we don't create one here either */
+	if (!parent) {
+		fscache_stat(&fscache_n_acquires_null);
+		_leave(" [no parent]");
+		return NULL;
+	}
+
+	/* validate the definition */
+	BUG_ON(!def->get_key);
+	BUG_ON(!def->name[0]);
+
+	BUG_ON(def->type == FSCACHE_COOKIE_TYPE_INDEX &&
+	       parent->def->type != FSCACHE_COOKIE_TYPE_INDEX);
+
+	/* allocate and initialise a cookie */
+	cookie = kmem_cache_alloc(fscache_cookie_jar, GFP_KERNEL);
+	if (!cookie) {
+		fscache_stat(&fscache_n_acquires_oom);
+		_leave(" [ENOMEM]");
+		return NULL;
+	}
+
+	atomic_set(&cookie->usage, 1);
+	atomic_set(&cookie->n_children, 0);
+
+	atomic_inc(&parent->usage);
+	atomic_inc(&parent->n_children);
+
+	cookie->def		= def;
+	cookie->parent		= parent;
+	cookie->netfs_data	= netfs_data;
+	cookie->flags		= 0;
+
+	INIT_RADIX_TREE(&cookie->stores, GFP_NOFS);
+
+	switch (cookie->def->type) {
+	case FSCACHE_COOKIE_TYPE_INDEX:
+		fscache_stat(&fscache_n_cookie_index);
+		break;
+	case FSCACHE_COOKIE_TYPE_DATAFILE:
+		fscache_stat(&fscache_n_cookie_data);
+		break;
+	default:
+		fscache_stat(&fscache_n_cookie_special);
+		break;
+	}
+
+	/* if the object is an index then we need do nothing more here - we
+	 * create indices on disk when we need them as an index may exist in
+	 * multiple caches */
+	if (cookie->def->type != FSCACHE_COOKIE_TYPE_INDEX) {
+		if (fscache_acquire_non_index_cookie(cookie) < 0) {
+			atomic_dec(&parent->n_children);
+			__fscache_cookie_put(cookie);
+			fscache_stat(&fscache_n_acquires_nobufs);
+			_leave(" = NULL");
+			return NULL;
+		}
+	}
+
+	fscache_stat(&fscache_n_acquires_ok);
+	_leave(" = %p", cookie);
+	return cookie;
+}
+EXPORT_SYMBOL(__fscache_acquire_cookie);
+
+/*
+ * acquire a non-index cookie
+ * - this must make sure the index chain is instantiated and instantiate the
+ *   object representation too
+ */
+static int fscache_acquire_non_index_cookie(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+	uint64_t i_size;
+	int ret;
+
+	_enter("");
+
+	cookie->flags = 1 << FSCACHE_COOKIE_UNAVAILABLE;
+
+	/* now we need to see whether the backing objects for this cookie yet
+	 * exist, if not there'll be nothing to search */
+	down_read(&fscache_addremove_sem);
+
+	if (list_empty(&fscache_cache_list)) {
+		up_read(&fscache_addremove_sem);
+		_leave(" = 0 [no caches]");
+		return 0;
+	}
+
+	/* select a cache in which to store the object */
+	cache = fscache_select_cache_for_object(cookie->parent);
+	if (!cache) {
+		up_read(&fscache_addremove_sem);
+		fscache_stat(&fscache_n_acquires_no_cache);
+		_leave(" = -ENOMEDIUM [no cache]");
+		return -ENOMEDIUM;
+	}
+
+	_debug("cache %s", cache->tag->name);
+
+	cookie->flags =
+		(1 << FSCACHE_COOKIE_LOOKING_UP) |
+		(1 << FSCACHE_COOKIE_CREATING) |
+		(1 << FSCACHE_COOKIE_NO_DATA_YET);
+
+	/* ask the cache to allocate objects for this cookie and its parent
+	 * chain */
+	ret = fscache_alloc_object(cache, cookie);
+	if (ret < 0) {
+		up_read(&fscache_addremove_sem);
+		_leave(" = %d", ret);
+		return ret;
+	}
+
+	/* pass on how big the object we're caching is supposed to be */
+	cookie->def->get_attr(cookie->netfs_data, &i_size);
+
+	spin_lock(&cookie->lock);
+	if (hlist_empty(&cookie->backing_objects)) {
+		spin_unlock(&cookie->lock);
+		goto unavailable;
+	}
+
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	fscache_set_store_limit(object, i_size);
+
+	/* initiate the process of looking up all the objects in the chain
+	 * (done by fscache_initialise_object()) */
+	fscache_enqueue_object(object);
+
+	spin_unlock(&cookie->lock);
+
+	/* we may be required to wait for lookup to complete at this point */
+	if (!fscache_defer_lookup) {
+		_debug("non-deferred lookup %p", &cookie->flags);
+		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("complete");
+		if (test_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags))
+			goto unavailable;
+	}
+
+	up_read(&fscache_addremove_sem);
+	_leave(" = 0 [deferred]");
+	return 0;
+
+unavailable:
+	up_read(&fscache_addremove_sem);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+
+/*
+ * recursively allocate cache object records for a cookie/cache combination
+ * - caller must be holding the addremove sem
+ */
+static int fscache_alloc_object(struct fscache_cache *cache,
+				struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	struct hlist_node *_n;
+	int ret;
+
+	_enter("%p,%p{%s}", cache, cookie, cookie->def->name);
+
+	spin_lock(&cookie->lock);
+	hlist_for_each_entry(object, _n, &cookie->backing_objects,
+			     cookie_link) {
+		if (object->cache == cache)
+			goto object_already_extant;
+	}
+	spin_unlock(&cookie->lock);
+
+	/* ask the cache to allocate an object (we may end up with duplicate
+	 * objects at this stage, but we sort that out later) */
+	object = cache->ops->alloc_object(cache, cookie);
+	if (IS_ERR(object)) {
+		fscache_stat(&fscache_n_object_no_alloc);
+		ret = PTR_ERR(object);
+		goto error;
+	}
+
+	fscache_stat(&fscache_n_object_alloc);
+
+	object->debug_id = atomic_inc_return(&fscache_object_debug_id);
+
+	_debug("ALLOC OBJ%x: %s {%lx}",
+	       object->debug_id, cookie->def->name, object->events);
+
+	ret = fscache_alloc_object(cache, cookie->parent);
+	if (ret < 0)
+		goto error_put;
+
+	/* only attach if we managed to allocate all we needed, otherwise
+	 * discard the object we just allocated and instead use the one
+	 * attached to the cookie */
+	if (fscache_attach_object(cookie, object) < 0)
+		cache->ops->put_object(object);
+
+	_leave(" = 0");
+	return 0;
+
+object_already_extant:
+	ret = -ENOBUFS;
+	if (object->state >= FSCACHE_OBJECT_DYING) {
+		spin_unlock(&cookie->lock);
+		goto error;
+	}
+	spin_unlock(&cookie->lock);
+	_leave(" = 0 [found]");
+	return 0;
+
+error_put:
+	cache->ops->put_object(object);
+error:
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * attach a cache object to a cookie
+ */
+static int fscache_attach_object(struct fscache_cookie *cookie,
+				 struct fscache_object *object)
+{
+	struct fscache_object *p;
+	struct fscache_cache *cache = object->cache;
+	struct hlist_node *_n;
+	int ret;
+
+	_enter("{%s},{OBJ%x}", cookie->def->name, object->debug_id);
+
+	spin_lock(&cookie->lock);
+
+	/* there may be multiple initial creations of this object, but we only
+	 * want one */
+	ret = -EEXIST;
+	hlist_for_each_entry(p, _n, &cookie->backing_objects, cookie_link) {
+		if (p->cache == object->cache) {
+			if (p->state >= FSCACHE_OBJECT_DYING)
+				ret = -ENOBUFS;
+			goto cant_attach_object;
+		}
+	}
+
+	/* pin the parent object */
+	spin_lock_nested(&cookie->parent->lock, 1);
+	hlist_for_each_entry(p, _n, &cookie->parent->backing_objects,
+			     cookie_link) {
+		if (p->cache == object->cache) {
+			if (p->state >= FSCACHE_OBJECT_DYING) {
+				ret = -ENOBUFS;
+				spin_unlock(&cookie->parent->lock);
+				goto cant_attach_object;
+			}
+			object->parent = p;
+			spin_lock(&p->lock);
+			p->n_children++;
+			spin_unlock(&p->lock);
+			break;
+		}
+	}
+	spin_unlock(&cookie->parent->lock);
+
+	/* attach to the cache's object list */
+	if (list_empty(&object->cache_link)) {
+		spin_lock(&cache->object_list_lock);
+		list_add(&object->cache_link, &cache->object_list);
+		spin_unlock(&cache->object_list_lock);
+	}
+
+	/* attach to the cookie */
+	object->cookie = cookie;
+	atomic_inc(&cookie->usage);
+	hlist_add_head(&object->cookie_link, &cookie->backing_objects);
+	ret = 0;
+
+cant_attach_object:
+	spin_unlock(&cookie->lock);
+	_leave(" = %d", ret);
+	return ret;
+}
+
+/*
+ * update the index entries backing a cookie
+ */
+void __fscache_update_cookie(struct fscache_cookie *cookie)
+{
+	struct fscache_object *object;
+	struct hlist_node *_p;
+
+	fscache_stat(&fscache_n_updates);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_updates_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("{%s}", cookie->def->name);
+
+	BUG_ON(!cookie->def->get_aux);
+
+	spin_lock(&cookie->lock);
+
+	/* update the index entry on disk in each cache backing this cookie */
+	hlist_for_each_entry(object, _p,
+			     &cookie->backing_objects, cookie_link) {
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_UPDATE);
+	}
+
+	spin_unlock(&cookie->lock);
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_update_cookie);
+
+/*
+ * release a cookie back to the cache
+ * - the object will be marked as recyclable on disk if retire is true
+ * - all dependents of this cookie must have already been unregistered
+ *   (indices/files/pages)
+ */
+void __fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+{
+	struct fscache_cache *cache;
+	struct fscache_object *object;
+	unsigned long event;
+
+	fscache_stat(&fscache_n_relinquishes);
+
+	if (!cookie) {
+		fscache_stat(&fscache_n_relinquishes_null);
+		_leave(" [no cookie]");
+		return;
+	}
+
+	_enter("%p{%s,%p},%d",
+	       cookie, cookie->def->name, cookie->netfs_data, retire);
+
+	if (atomic_read(&cookie->n_children) != 0) {
+		printk(KERN_ERR "FS-Cache: Cookie '%s' still has children\n",
+		       cookie->def->name);
+		BUG();
+	}
+
+	/* wait for the cookie to finish being instantiated (or to fail) */
+	if (test_bit(FSCACHE_COOKIE_CREATING, &cookie->flags)) {
+		fscache_stat(&fscache_n_relinquishes_waitcrt);
+		wait_on_bit(&cookie->flags, FSCACHE_COOKIE_CREATING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+	}
+
+	event = retire ? FSCACHE_OBJECT_EV_RETIRE : FSCACHE_OBJECT_EV_RELEASE;
+
+	/* detach pointers back to the netfs */
+	spin_lock(&cookie->lock);
+
+	cookie->netfs_data	= NULL;
+	cookie->def		= NULL;
+
+	/* break links with all the active objects */
+	while (!hlist_empty(&cookie->backing_objects)) {
+		object = hlist_entry(cookie->backing_objects.first,
+				     struct fscache_object,
+				     cookie_link);
+
+		_debug("RELEASE OBJ%x", object->debug_id);
+
+		/* detach each cache object from the object cookie */
+		spin_lock(&object->lock);
+		hlist_del_init(&object->cookie_link);
+
+		cache = object->cache;
+		object->cookie = NULL;
+		fscache_raise_event(object, event);
+		spin_unlock(&object->lock);
+
+		if (atomic_dec_and_test(&cookie->usage))
+			/* the cookie refcount shouldn't be reduced to 0 yet */
+			BUG();
+	}
+
+	spin_unlock(&cookie->lock);
+
+	if (cookie->parent) {
+		ASSERTCMP(atomic_read(&cookie->parent->usage), >, 0);
+		ASSERTCMP(atomic_read(&cookie->parent->n_children), >, 0);
+		atomic_dec(&cookie->parent->n_children);
+	}
+
+	/* finally dispose of the cookie */
+	ASSERTCMP(atomic_read(&cookie->usage), >, 0);
+	fscache_cookie_put(cookie);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_relinquish_cookie);
+
+/*
+ * destroy a cookie
+ */
+void __fscache_cookie_put(struct fscache_cookie *cookie)
+{
+	struct fscache_cookie *parent;
+
+	_enter("%p", cookie);
+
+	for (;;) {
+		_debug("FREE COOKIE %p", cookie);
+		parent = cookie->parent;
+		BUG_ON(!hlist_empty(&cookie->backing_objects));
+		kmem_cache_free(fscache_cookie_jar, cookie);
+
+		if (!parent)
+			break;
+
+		cookie = parent;
+		BUG_ON(atomic_read(&cookie->usage) <= 0);
+		if (!atomic_dec_and_test(&cookie->usage))
+			break;
+	}
+
+	_leave("");
+}
diff --git a/fs/fscache/fsdef.c b/fs/fscache/fsdef.c
new file mode 100644
index 000000000000..f5b4baee7352
--- /dev/null
+++ b/fs/fscache/fsdef.c
@@ -0,0 +1,144 @@
+/* Filesystem index definition
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include "internal.h"
+
+static uint16_t fscache_fsdef_netfs_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax);
+
+static uint16_t fscache_fsdef_netfs_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax);
+
+static
+enum fscache_checkaux fscache_fsdef_netfs_check_aux(void *cookie_netfs_data,
+						    const void *data,
+						    uint16_t datalen);
+
+/*
+ * The root index is owned by FS-Cache itself.
+ *
+ * When a netfs requests caching facilities, FS-Cache will, if one doesn't
+ * already exist, create an entry in the root index with the key being the name
+ * of the netfs ("AFS" for example), and the auxiliary data holding the index
+ * structure version supplied by the netfs:
+ *
+ *				     FSDEF
+ *				       |
+ *				 +-----------+
+ *				 |           |
+ *				NFS         AFS
+ *			       [v=1]       [v=1]
+ *
+ * If an entry with the appropriate name does already exist, the version is
+ * compared.  If the version is different, the entire subtree from that entry
+ * will be discarded and a new entry created.
+ *
+ * The new entry will be an index, and a cookie referring to it will be passed
+ * to the netfs.  This is then the root handle by which the netfs accesses the
+ * cache.  It can create whatever objects it likes in that index, including
+ * further indices.
+ */
+static struct fscache_cookie_def fscache_fsdef_index_def = {
+	.name		= ".FS-Cache",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+};
+
+struct fscache_cookie fscache_fsdef_index = {
+	.usage		= ATOMIC_INIT(1),
+	.lock		= __SPIN_LOCK_UNLOCKED(fscache_fsdef_index.lock),
+	.backing_objects = HLIST_HEAD_INIT,
+	.def		= &fscache_fsdef_index_def,
+};
+EXPORT_SYMBOL(fscache_fsdef_index);
+
+/*
+ * Definition of an entry in the root index.  Each entry is an index, keyed to
+ * a specific netfs and only applicable to a particular version of the index
+ * structure used by that netfs.
+ */
+struct fscache_cookie_def fscache_fsdef_netfs_def = {
+	.name		= "FSDEF.netfs",
+	.type		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= fscache_fsdef_netfs_get_key,
+	.get_aux	= fscache_fsdef_netfs_get_aux,
+	.check_aux	= fscache_fsdef_netfs_check_aux,
+};
+
+/*
+ * get the key data for an FSDEF index record - this is the name of the netfs
+ * for which this entry is created
+ */
+static uint16_t fscache_fsdef_netfs_get_key(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct fscache_netfs *netfs = cookie_netfs_data;
+	unsigned klen;
+
+	_enter("{%s.%u},", netfs->name, netfs->version);
+
+	klen = strlen(netfs->name);
+	if (klen > bufmax)
+		return 0;
+
+	memcpy(buffer, netfs->name, klen);
+	return klen;
+}
+
+/*
+ * get the auxiliary data for an FSDEF index record - this is the index
+ * structure version number of the netfs for which this version is created
+ */
+static uint16_t fscache_fsdef_netfs_get_aux(const void *cookie_netfs_data,
+					    void *buffer, uint16_t bufmax)
+{
+	const struct fscache_netfs *netfs = cookie_netfs_data;
+	unsigned dlen;
+
+	_enter("{%s.%u},", netfs->name, netfs->version);
+
+	dlen = sizeof(uint32_t);
+	if (dlen > bufmax)
+		return 0;
+
+	memcpy(buffer, &netfs->version, dlen);
+	return dlen;
+}
+
+/*
+ * check that the index structure version number stored in the auxiliary data
+ * matches the one the netfs gave us
+ */
+static enum fscache_checkaux fscache_fsdef_netfs_check_aux(
+	void *cookie_netfs_data,
+	const void *data,
+	uint16_t datalen)
+{
+	struct fscache_netfs *netfs = cookie_netfs_data;
+	uint32_t version;
+
+	_enter("{%s},,%hu", netfs->name, datalen);
+
+	if (datalen != sizeof(version)) {
+		_leave(" = OBSOLETE [dl=%d v=%zu]", datalen, sizeof(version));
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	memcpy(&version, data, sizeof(version));
+	if (version != netfs->version) {
+		_leave(" = OBSOLETE [ver=%x net=%x]", version, netfs->version);
+		return FSCACHE_CHECKAUX_OBSOLETE;
+	}
+
+	_leave(" = OKAY");
+	return FSCACHE_CHECKAUX_OKAY;
+}
diff --git a/fs/fscache/histogram.c b/fs/fscache/histogram.c
new file mode 100644
index 000000000000..bad496748a59
--- /dev/null
+++ b/fs/fscache/histogram.c
@@ -0,0 +1,109 @@
+/* FS-Cache latency histogram
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL THREAD
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+atomic_t fscache_obj_instantiate_histogram[HZ];
+atomic_t fscache_objs_histogram[HZ];
+atomic_t fscache_ops_histogram[HZ];
+atomic_t fscache_retrieval_delay_histogram[HZ];
+atomic_t fscache_retrieval_histogram[HZ];
+
+/*
+ * display the time-taken histogram
+ */
+static int fscache_histogram_show(struct seq_file *m, void *v)
+{
+	unsigned long index;
+	unsigned n[5], t;
+
+	switch ((unsigned long) v) {
+	case 1:
+		seq_puts(m, "JIFS  SECS  OBJ INST  OP RUNS   OBJ RUNS "
+			 " RETRV DLY RETRIEVLS\n");
+		return 0;
+	case 2:
+		seq_puts(m, "===== ===== ========= ========= ========="
+			 " ========= =========\n");
+		return 0;
+	default:
+		index = (unsigned long) v - 3;
+		n[0] = atomic_read(&fscache_obj_instantiate_histogram[index]);
+		n[1] = atomic_read(&fscache_ops_histogram[index]);
+		n[2] = atomic_read(&fscache_objs_histogram[index]);
+		n[3] = atomic_read(&fscache_retrieval_delay_histogram[index]);
+		n[4] = atomic_read(&fscache_retrieval_histogram[index]);
+		if (!(n[0] | n[1] | n[2] | n[3] | n[4]))
+			return 0;
+
+		t = (index * 1000) / HZ;
+
+		seq_printf(m, "%4lu  0.%03u %9u %9u %9u %9u %9u\n",
+			   index, t, n[0], n[1], n[2], n[3], n[4]);
+		return 0;
+	}
+}
+
+/*
+ * set up the iterator to start reading from the first line
+ */
+static void *fscache_histogram_start(struct seq_file *m, loff_t *_pos)
+{
+	if ((unsigned long long)*_pos >= HZ + 2)
+		return NULL;
+	if (*_pos == 0)
+		*_pos = 1;
+	return (void *)(unsigned long) *_pos;
+}
+
+/*
+ * move to the next line
+ */
+static void *fscache_histogram_next(struct seq_file *m, void *v, loff_t *pos)
+{
+	(*pos)++;
+	return (unsigned long long)*pos > HZ + 2 ?
+		NULL : (void *)(unsigned long) *pos;
+}
+
+/*
+ * clean up after reading
+ */
+static void fscache_histogram_stop(struct seq_file *m, void *v)
+{
+}
+
+static const struct seq_operations fscache_histogram_ops = {
+	.start		= fscache_histogram_start,
+	.stop		= fscache_histogram_stop,
+	.next		= fscache_histogram_next,
+	.show		= fscache_histogram_show,
+};
+
+/*
+ * open "/proc/fs/fscache/histogram" to provide latency data
+ */
+static int fscache_histogram_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &fscache_histogram_ops);
+}
+
+const struct file_operations fscache_histogram_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_histogram_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
diff --git a/fs/fscache/internal.h b/fs/fscache/internal.h
new file mode 100644
index 000000000000..e0cbd16f6dc9
--- /dev/null
+++ b/fs/fscache/internal.h
@@ -0,0 +1,380 @@
+/* Internal definitions for FS-Cache
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+/*
+ * Lock order, in the order in which multiple locks should be obtained:
+ * - fscache_addremove_sem
+ * - cookie->lock
+ * - cookie->parent->lock
+ * - cache->object_list_lock
+ * - object->lock
+ * - object->parent->lock
+ * - fscache_thread_lock
+ *
+ */
+
+#include <linux/fscache-cache.h>
+#include <linux/sched.h>
+
+#define FSCACHE_MIN_THREADS	4
+#define FSCACHE_MAX_THREADS	32
+
+/*
+ * fsc-cache.c
+ */
+extern struct list_head fscache_cache_list;
+extern struct rw_semaphore fscache_addremove_sem;
+
+extern struct fscache_cache *fscache_select_cache_for_object(
+	struct fscache_cookie *);
+
+/*
+ * fsc-cookie.c
+ */
+extern struct kmem_cache *fscache_cookie_jar;
+
+extern void fscache_cookie_init_once(void *);
+extern void __fscache_cookie_put(struct fscache_cookie *);
+
+/*
+ * fsc-fsdef.c
+ */
+extern struct fscache_cookie fscache_fsdef_index;
+extern struct fscache_cookie_def fscache_fsdef_netfs_def;
+
+/*
+ * fsc-histogram.c
+ */
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+extern atomic_t fscache_obj_instantiate_histogram[HZ];
+extern atomic_t fscache_objs_histogram[HZ];
+extern atomic_t fscache_ops_histogram[HZ];
+extern atomic_t fscache_retrieval_delay_histogram[HZ];
+extern atomic_t fscache_retrieval_histogram[HZ];
+
+static inline void fscache_hist(atomic_t histogram[], unsigned long start_jif)
+{
+	unsigned long jif = jiffies - start_jif;
+	if (jif >= HZ)
+		jif = HZ - 1;
+	atomic_inc(&histogram[jif]);
+}
+
+extern const struct file_operations fscache_histogram_fops;
+
+#else
+#define fscache_hist(hist, start_jif) do {} while (0)
+#endif
+
+/*
+ * fsc-main.c
+ */
+extern unsigned fscache_defer_lookup;
+extern unsigned fscache_defer_create;
+extern unsigned fscache_debug;
+extern struct kobject *fscache_root;
+
+extern int fscache_wait_bit(void *);
+extern int fscache_wait_bit_interruptible(void *);
+
+/*
+ * fsc-object.c
+ */
+extern void fscache_withdrawing_object(struct fscache_cache *,
+				       struct fscache_object *);
+extern void fscache_enqueue_object(struct fscache_object *);
+
+/*
+ * fsc-operation.c
+ */
+extern int fscache_submit_exclusive_op(struct fscache_object *,
+				       struct fscache_operation *);
+extern int fscache_submit_op(struct fscache_object *,
+			     struct fscache_operation *);
+extern void fscache_abort_object(struct fscache_object *);
+extern void fscache_start_operations(struct fscache_object *);
+extern void fscache_operation_gc(struct work_struct *);
+
+/*
+ * fsc-proc.c
+ */
+#ifdef CONFIG_PROC_FS
+extern int __init fscache_proc_init(void);
+extern void fscache_proc_cleanup(void);
+#else
+#define fscache_proc_init()	(0)
+#define fscache_proc_cleanup()	do {} while (0)
+#endif
+
+/*
+ * fsc-stats.c
+ */
+#ifdef CONFIG_FSCACHE_STATS
+extern atomic_t fscache_n_ops_processed[FSCACHE_MAX_THREADS];
+extern atomic_t fscache_n_objs_processed[FSCACHE_MAX_THREADS];
+
+extern atomic_t fscache_n_op_pend;
+extern atomic_t fscache_n_op_run;
+extern atomic_t fscache_n_op_enqueue;
+extern atomic_t fscache_n_op_deferred_release;
+extern atomic_t fscache_n_op_release;
+extern atomic_t fscache_n_op_gc;
+
+extern atomic_t fscache_n_attr_changed;
+extern atomic_t fscache_n_attr_changed_ok;
+extern atomic_t fscache_n_attr_changed_nobufs;
+extern atomic_t fscache_n_attr_changed_nomem;
+extern atomic_t fscache_n_attr_changed_calls;
+
+extern atomic_t fscache_n_allocs;
+extern atomic_t fscache_n_allocs_ok;
+extern atomic_t fscache_n_allocs_wait;
+extern atomic_t fscache_n_allocs_nobufs;
+extern atomic_t fscache_n_alloc_ops;
+extern atomic_t fscache_n_alloc_op_waits;
+
+extern atomic_t fscache_n_retrievals;
+extern atomic_t fscache_n_retrievals_ok;
+extern atomic_t fscache_n_retrievals_wait;
+extern atomic_t fscache_n_retrievals_nodata;
+extern atomic_t fscache_n_retrievals_nobufs;
+extern atomic_t fscache_n_retrievals_intr;
+extern atomic_t fscache_n_retrievals_nomem;
+extern atomic_t fscache_n_retrieval_ops;
+extern atomic_t fscache_n_retrieval_op_waits;
+
+extern atomic_t fscache_n_stores;
+extern atomic_t fscache_n_stores_ok;
+extern atomic_t fscache_n_stores_again;
+extern atomic_t fscache_n_stores_nobufs;
+extern atomic_t fscache_n_stores_oom;
+extern atomic_t fscache_n_store_ops;
+extern atomic_t fscache_n_store_calls;
+
+extern atomic_t fscache_n_marks;
+extern atomic_t fscache_n_uncaches;
+
+extern atomic_t fscache_n_acquires;
+extern atomic_t fscache_n_acquires_null;
+extern atomic_t fscache_n_acquires_no_cache;
+extern atomic_t fscache_n_acquires_ok;
+extern atomic_t fscache_n_acquires_nobufs;
+extern atomic_t fscache_n_acquires_oom;
+
+extern atomic_t fscache_n_updates;
+extern atomic_t fscache_n_updates_null;
+extern atomic_t fscache_n_updates_run;
+
+extern atomic_t fscache_n_relinquishes;
+extern atomic_t fscache_n_relinquishes_null;
+extern atomic_t fscache_n_relinquishes_waitcrt;
+
+extern atomic_t fscache_n_cookie_index;
+extern atomic_t fscache_n_cookie_data;
+extern atomic_t fscache_n_cookie_special;
+
+extern atomic_t fscache_n_object_alloc;
+extern atomic_t fscache_n_object_no_alloc;
+extern atomic_t fscache_n_object_lookups;
+extern atomic_t fscache_n_object_lookups_negative;
+extern atomic_t fscache_n_object_lookups_positive;
+extern atomic_t fscache_n_object_created;
+extern atomic_t fscache_n_object_avail;
+extern atomic_t fscache_n_object_dead;
+
+extern atomic_t fscache_n_checkaux_none;
+extern atomic_t fscache_n_checkaux_okay;
+extern atomic_t fscache_n_checkaux_update;
+extern atomic_t fscache_n_checkaux_obsolete;
+
+static inline void fscache_stat(atomic_t *stat)
+{
+	atomic_inc(stat);
+}
+
+extern const struct file_operations fscache_stats_fops;
+#else
+
+#define fscache_stat(stat) do {} while (0)
+#endif
+
+/*
+ * raise an event on an object
+ * - if the event is not masked for that object, then the object is
+ *   queued for attention by the thread pool.
+ */
+static inline void fscache_raise_event(struct fscache_object *object,
+				       unsigned event)
+{
+	if (!test_and_set_bit(event, &object->events) &&
+	    test_bit(event, &object->event_mask))
+		fscache_enqueue_object(object);
+}
+
+/*
+ * drop a reference to a cookie
+ */
+static inline void fscache_cookie_put(struct fscache_cookie *cookie)
+{
+	BUG_ON(atomic_read(&cookie->usage) <= 0);
+	if (atomic_dec_and_test(&cookie->usage))
+		__fscache_cookie_put(cookie);
+}
+
+/*
+ * get an extra reference to a netfs retrieval context
+ */
+static inline
+void *fscache_get_context(struct fscache_cookie *cookie, void *context)
+{
+	if (cookie->def->get_context)
+		cookie->def->get_context(cookie->netfs_data, context);
+	return context;
+}
+
+/*
+ * release a reference to a netfs retrieval context
+ */
+static inline
+void fscache_put_context(struct fscache_cookie *cookie, void *context)
+{
+	if (cookie->def->put_context)
+		cookie->def->put_context(cookie->netfs_data, context);
+}
+
+/*****************************************************************************/
+/*
+ * debug tracing
+ */
+#define dbgprintk(FMT, ...) \
+	printk(KERN_DEBUG "[%-6.6s] "FMT"\n", current->comm, ##__VA_ARGS__)
+
+/* make sure we maintain the format strings, even when debugging is disabled */
+static inline __attribute__((format(printf, 1, 2)))
+void _dbprintk(const char *fmt, ...)
+{
+}
+
+#define kenter(FMT, ...) dbgprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define kleave(FMT, ...) dbgprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define kdebug(FMT, ...) dbgprintk(FMT, ##__VA_ARGS__)
+
+#define kjournal(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+
+#ifdef __KDEBUG
+#define _enter(FMT, ...) kenter(FMT, ##__VA_ARGS__)
+#define _leave(FMT, ...) kleave(FMT, ##__VA_ARGS__)
+#define _debug(FMT, ...) kdebug(FMT, ##__VA_ARGS__)
+
+#elif defined(CONFIG_FSCACHE_DEBUG)
+#define _enter(FMT, ...)			\
+do {						\
+	if (__do_kdebug(ENTER))			\
+		kenter(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _leave(FMT, ...)			\
+do {						\
+	if (__do_kdebug(LEAVE))			\
+		kleave(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#define _debug(FMT, ...)			\
+do {						\
+	if (__do_kdebug(DEBUG))			\
+		kdebug(FMT, ##__VA_ARGS__);	\
+} while (0)
+
+#else
+#define _enter(FMT, ...) _dbprintk("==> %s("FMT")", __func__, ##__VA_ARGS__)
+#define _leave(FMT, ...) _dbprintk("<== %s()"FMT"", __func__, ##__VA_ARGS__)
+#define _debug(FMT, ...) _dbprintk(FMT, ##__VA_ARGS__)
+#endif
+
+/*
+ * determine whether a particular optional debugging point should be logged
+ * - we need to go through three steps to persuade cpp to correctly join the
+ *   shorthand in FSCACHE_DEBUG_LEVEL with its prefix
+ */
+#define ____do_kdebug(LEVEL, POINT) \
+	unlikely((fscache_debug & \
+		  (FSCACHE_POINT_##POINT << (FSCACHE_DEBUG_ ## LEVEL * 3))))
+#define ___do_kdebug(LEVEL, POINT) \
+	____do_kdebug(LEVEL, POINT)
+#define __do_kdebug(POINT) \
+	___do_kdebug(FSCACHE_DEBUG_LEVEL, POINT)
+
+#define FSCACHE_DEBUG_CACHE	0
+#define FSCACHE_DEBUG_COOKIE	1
+#define FSCACHE_DEBUG_PAGE	2
+#define FSCACHE_DEBUG_OPERATION	3
+
+#define FSCACHE_POINT_ENTER	1
+#define FSCACHE_POINT_LEAVE	2
+#define FSCACHE_POINT_DEBUG	4
+
+#ifndef FSCACHE_DEBUG_LEVEL
+#define FSCACHE_DEBUG_LEVEL CACHE
+#endif
+
+/*
+ * assertions
+ */
+#if 1 /* defined(__KDEBUGALL) */
+
+#define ASSERT(X)							\
+do {									\
+	if (unlikely(!(X))) {						\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTCMP(X, OP, Y)						\
+do {									\
+	if (unlikely(!((X) OP (Y)))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		printk(KERN_ERR "%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIF(C, X)							\
+do {									\
+	if (unlikely((C) && !(X))) {					\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		BUG();							\
+	}								\
+} while (0)
+
+#define ASSERTIFCMP(C, X, OP, Y)					\
+do {									\
+	if (unlikely((C) && !((X) OP (Y)))) {				\
+		printk(KERN_ERR "\n");					\
+		printk(KERN_ERR "FS-Cache: Assertion failed\n");	\
+		printk(KERN_ERR "%lx " #OP " %lx is false\n",		\
+		       (unsigned long)(X), (unsigned long)(Y));		\
+		BUG();							\
+	}								\
+} while (0)
+
+#else
+
+#define ASSERT(X)			do {} while (0)
+#define ASSERTCMP(X, OP, Y)		do {} while (0)
+#define ASSERTIF(C, X)			do {} while (0)
+#define ASSERTIFCMP(C, X, OP, Y)	do {} while (0)
+
+#endif /* assert or not */
diff --git a/fs/fscache/main.c b/fs/fscache/main.c
new file mode 100644
index 000000000000..4de41b597499
--- /dev/null
+++ b/fs/fscache/main.c
@@ -0,0 +1,124 @@
+/* General filesystem local caching manager
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL CACHE
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/completion.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+MODULE_DESCRIPTION("FS Cache Manager");
+MODULE_AUTHOR("Red Hat, Inc.");
+MODULE_LICENSE("GPL");
+
+unsigned fscache_defer_lookup = 1;
+module_param_named(defer_lookup, fscache_defer_lookup, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_defer_lookup,
+		 "Defer cookie lookup to background thread");
+
+unsigned fscache_defer_create = 1;
+module_param_named(defer_create, fscache_defer_create, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_defer_create,
+		 "Defer cookie creation to background thread");
+
+unsigned fscache_debug;
+module_param_named(debug, fscache_debug, uint,
+		   S_IWUSR | S_IRUGO);
+MODULE_PARM_DESC(fscache_debug,
+		 "FS-Cache debugging mask");
+
+struct kobject *fscache_root;
+
+/*
+ * initialise the fs caching module
+ */
+static int __init fscache_init(void)
+{
+	int ret;
+
+	ret = slow_work_register_user();
+	if (ret < 0)
+		goto error_slow_work;
+
+	ret = fscache_proc_init();
+	if (ret < 0)
+		goto error_proc;
+
+	fscache_cookie_jar = kmem_cache_create("fscache_cookie_jar",
+					       sizeof(struct fscache_cookie),
+					       0,
+					       0,
+					       fscache_cookie_init_once);
+	if (!fscache_cookie_jar) {
+		printk(KERN_NOTICE
+		       "FS-Cache: Failed to allocate a cookie jar\n");
+		ret = -ENOMEM;
+		goto error_cookie_jar;
+	}
+
+	fscache_root = kobject_create_and_add("fscache", kernel_kobj);
+	if (!fscache_root)
+		goto error_kobj;
+
+	printk(KERN_NOTICE "FS-Cache: Loaded\n");
+	return 0;
+
+error_kobj:
+	kmem_cache_destroy(fscache_cookie_jar);
+error_cookie_jar:
+	fscache_proc_cleanup();
+error_proc:
+	slow_work_unregister_user();
+error_slow_work:
+	return ret;
+}
+
+fs_initcall(fscache_init);
+
+/*
+ * clean up on module removal
+ */
+static void __exit fscache_exit(void)
+{
+	_enter("");
+
+	kobject_put(fscache_root);
+	kmem_cache_destroy(fscache_cookie_jar);
+	fscache_proc_cleanup();
+	slow_work_unregister_user();
+	printk(KERN_NOTICE "FS-Cache: Unloaded\n");
+}
+
+module_exit(fscache_exit);
+
+/*
+ * wait_on_bit() sleep function for uninterruptible waiting
+ */
+int fscache_wait_bit(void *flags)
+{
+	schedule();
+	return 0;
+}
+EXPORT_SYMBOL(fscache_wait_bit);
+
+/*
+ * wait_on_bit() sleep function for interruptible waiting
+ */
+int fscache_wait_bit_interruptible(void *flags)
+{
+	schedule();
+	return signal_pending(current);
+}
+EXPORT_SYMBOL(fscache_wait_bit_interruptible);
diff --git a/fs/fscache/netfs.c b/fs/fscache/netfs.c
new file mode 100644
index 000000000000..e028b8eb1c40
--- /dev/null
+++ b/fs/fscache/netfs.c
@@ -0,0 +1,103 @@
+/* FS-Cache netfs (client) registration
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include <linux/slab.h>
+#include "internal.h"
+
+static LIST_HEAD(fscache_netfs_list);
+
+/*
+ * register a network filesystem for caching
+ */
+int __fscache_register_netfs(struct fscache_netfs *netfs)
+{
+	struct fscache_netfs *ptr;
+	int ret;
+
+	_enter("{%s}", netfs->name);
+
+	INIT_LIST_HEAD(&netfs->link);
+
+	/* allocate a cookie for the primary index */
+	netfs->primary_index =
+		kmem_cache_zalloc(fscache_cookie_jar, GFP_KERNEL);
+
+	if (!netfs->primary_index) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	/* initialise the primary index cookie */
+	atomic_set(&netfs->primary_index->usage, 1);
+	atomic_set(&netfs->primary_index->n_children, 0);
+
+	netfs->primary_index->def		= &fscache_fsdef_netfs_def;
+	netfs->primary_index->parent		= &fscache_fsdef_index;
+	netfs->primary_index->netfs_data	= netfs;
+
+	atomic_inc(&netfs->primary_index->parent->usage);
+	atomic_inc(&netfs->primary_index->parent->n_children);
+
+	spin_lock_init(&netfs->primary_index->lock);
+	INIT_HLIST_HEAD(&netfs->primary_index->backing_objects);
+
+	/* check the netfs type is not already present */
+	down_write(&fscache_addremove_sem);
+
+	ret = -EEXIST;
+	list_for_each_entry(ptr, &fscache_netfs_list, link) {
+		if (strcmp(ptr->name, netfs->name) == 0)
+			goto already_registered;
+	}
+
+	list_add(&netfs->link, &fscache_netfs_list);
+	ret = 0;
+
+	printk(KERN_NOTICE "FS-Cache: Netfs '%s' registered for caching\n",
+	       netfs->name);
+
+already_registered:
+	up_write(&fscache_addremove_sem);
+
+	if (ret < 0) {
+		netfs->primary_index->parent = NULL;
+		__fscache_cookie_put(netfs->primary_index);
+		netfs->primary_index = NULL;
+	}
+
+	_leave(" = %d", ret);
+	return ret;
+}
+EXPORT_SYMBOL(__fscache_register_netfs);
+
+/*
+ * unregister a network filesystem from the cache
+ * - all cookies must have been released first
+ */
+void __fscache_unregister_netfs(struct fscache_netfs *netfs)
+{
+	_enter("{%s.%u}", netfs->name, netfs->version);
+
+	down_write(&fscache_addremove_sem);
+
+	list_del(&netfs->link);
+	fscache_relinquish_cookie(netfs->primary_index, 0);
+
+	up_write(&fscache_addremove_sem);
+
+	printk(KERN_NOTICE "FS-Cache: Netfs '%s' unregistered from caching\n",
+	       netfs->name);
+
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_unregister_netfs);
diff --git a/fs/fscache/object.c b/fs/fscache/object.c
new file mode 100644
index 000000000000..392a41b1b79d
--- /dev/null
+++ b/fs/fscache/object.c
@@ -0,0 +1,810 @@
+/* FS-Cache object state machine handler
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/object.txt for a description of the
+ * object state machine and the in-kernel representations.
+ */
+
+#define FSCACHE_DEBUG_LEVEL COOKIE
+#include <linux/module.h>
+#include "internal.h"
+
+const char *fscache_object_states[] = {
+	[FSCACHE_OBJECT_INIT]		= "OBJECT_INIT",
+	[FSCACHE_OBJECT_LOOKING_UP]	= "OBJECT_LOOKING_UP",
+	[FSCACHE_OBJECT_CREATING]	= "OBJECT_CREATING",
+	[FSCACHE_OBJECT_AVAILABLE]	= "OBJECT_AVAILABLE",
+	[FSCACHE_OBJECT_ACTIVE]		= "OBJECT_ACTIVE",
+	[FSCACHE_OBJECT_UPDATING]	= "OBJECT_UPDATING",
+	[FSCACHE_OBJECT_DYING]		= "OBJECT_DYING",
+	[FSCACHE_OBJECT_LC_DYING]	= "OBJECT_LC_DYING",
+	[FSCACHE_OBJECT_ABORT_INIT]	= "OBJECT_ABORT_INIT",
+	[FSCACHE_OBJECT_RELEASING]	= "OBJECT_RELEASING",
+	[FSCACHE_OBJECT_RECYCLING]	= "OBJECT_RECYCLING",
+	[FSCACHE_OBJECT_WITHDRAWING]	= "OBJECT_WITHDRAWING",
+	[FSCACHE_OBJECT_DEAD]		= "OBJECT_DEAD",
+};
+EXPORT_SYMBOL(fscache_object_states);
+
+static void fscache_object_slow_work_put_ref(struct slow_work *);
+static int  fscache_object_slow_work_get_ref(struct slow_work *);
+static void fscache_object_slow_work_execute(struct slow_work *);
+static void fscache_initialise_object(struct fscache_object *);
+static void fscache_lookup_object(struct fscache_object *);
+static void fscache_object_available(struct fscache_object *);
+static void fscache_release_object(struct fscache_object *);
+static void fscache_withdraw_object(struct fscache_object *);
+static void fscache_enqueue_dependents(struct fscache_object *);
+static void fscache_dequeue_object(struct fscache_object *);
+
+const struct slow_work_ops fscache_object_slow_work_ops = {
+	.get_ref	= fscache_object_slow_work_get_ref,
+	.put_ref	= fscache_object_slow_work_put_ref,
+	.execute	= fscache_object_slow_work_execute,
+};
+EXPORT_SYMBOL(fscache_object_slow_work_ops);
+
+/*
+ * we need to notify the parent when an op completes that we had outstanding
+ * upon it
+ */
+static inline void fscache_done_parent_op(struct fscache_object *object)
+{
+	struct fscache_object *parent = object->parent;
+
+	_enter("OBJ%x {OBJ%x,%x}",
+	       object->debug_id, parent->debug_id, parent->n_ops);
+
+	spin_lock_nested(&parent->lock, 1);
+	parent->n_ops--;
+	parent->n_obj_ops--;
+	if (parent->n_ops == 0)
+		fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
+	spin_unlock(&parent->lock);
+}
+
+/*
+ * process events that have been sent to an object's state machine
+ * - initiates parent lookup
+ * - does object lookup
+ * - does object creation
+ * - does object recycling and retirement
+ * - does object withdrawal
+ */
+static void fscache_object_state_machine(struct fscache_object *object)
+{
+	enum fscache_object_state new_state;
+
+	ASSERT(object != NULL);
+
+	_enter("{OBJ%x,%s,%lx}",
+	       object->debug_id, fscache_object_states[object->state],
+	       object->events);
+
+	switch (object->state) {
+		/* wait for the parent object to become ready */
+	case FSCACHE_OBJECT_INIT:
+		object->event_mask =
+			ULONG_MAX & ~(1 << FSCACHE_OBJECT_EV_CLEARED);
+		fscache_initialise_object(object);
+		goto done;
+
+		/* look up the object metadata on disk */
+	case FSCACHE_OBJECT_LOOKING_UP:
+		fscache_lookup_object(object);
+		goto lookup_transit;
+
+		/* create the object metadata on disk */
+	case FSCACHE_OBJECT_CREATING:
+		fscache_lookup_object(object);
+		goto lookup_transit;
+
+		/* handle an object becoming available; start pending
+		 * operations and queue dependent operations for processing */
+	case FSCACHE_OBJECT_AVAILABLE:
+		fscache_object_available(object);
+		goto active_transit;
+
+		/* normal running state */
+	case FSCACHE_OBJECT_ACTIVE:
+		goto active_transit;
+
+		/* update the object metadata on disk */
+	case FSCACHE_OBJECT_UPDATING:
+		clear_bit(FSCACHE_OBJECT_EV_UPDATE, &object->events);
+		fscache_stat(&fscache_n_updates_run);
+		object->cache->ops->update_object(object);
+		goto active_transit;
+
+		/* handle an object dying during lookup or creation */
+	case FSCACHE_OBJECT_LC_DYING:
+		object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
+		object->cache->ops->lookup_complete(object);
+
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DYING;
+		if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+				       &object->cookie->flags))
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_CREATING);
+		spin_unlock(&object->lock);
+
+		fscache_done_parent_op(object);
+
+		/* wait for completion of all active operations on this object
+		 * and the death of all child objects of this object */
+	case FSCACHE_OBJECT_DYING:
+	dying:
+		clear_bit(FSCACHE_OBJECT_EV_CLEARED, &object->events);
+		spin_lock(&object->lock);
+		_debug("dying OBJ%x {%d,%d}",
+		       object->debug_id, object->n_ops, object->n_children);
+		if (object->n_ops == 0 && object->n_children == 0) {
+			object->event_mask &=
+				~(1 << FSCACHE_OBJECT_EV_CLEARED);
+			object->event_mask |=
+				(1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+				(1 << FSCACHE_OBJECT_EV_RETIRE) |
+				(1 << FSCACHE_OBJECT_EV_RELEASE) |
+				(1 << FSCACHE_OBJECT_EV_ERROR);
+		} else {
+			object->event_mask &=
+				~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+				  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+				  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+				  (1 << FSCACHE_OBJECT_EV_ERROR));
+			object->event_mask |=
+				1 << FSCACHE_OBJECT_EV_CLEARED;
+		}
+		spin_unlock(&object->lock);
+		fscache_enqueue_dependents(object);
+		goto terminal_transit;
+
+		/* handle an abort during initialisation */
+	case FSCACHE_OBJECT_ABORT_INIT:
+		_debug("handle abort init %lx", object->events);
+		object->event_mask &= ~(1 << FSCACHE_OBJECT_EV_UPDATE);
+
+		spin_lock(&object->lock);
+		fscache_dequeue_object(object);
+
+		object->state = FSCACHE_OBJECT_DYING;
+		if (test_and_clear_bit(FSCACHE_COOKIE_CREATING,
+				       &object->cookie->flags))
+			wake_up_bit(&object->cookie->flags,
+				    FSCACHE_COOKIE_CREATING);
+		spin_unlock(&object->lock);
+		goto dying;
+
+		/* handle the netfs releasing an object and possibly marking it
+		 * obsolete too */
+	case FSCACHE_OBJECT_RELEASING:
+	case FSCACHE_OBJECT_RECYCLING:
+		object->event_mask &=
+			~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+			  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			  (1 << FSCACHE_OBJECT_EV_ERROR));
+		fscache_release_object(object);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DEAD;
+		spin_unlock(&object->lock);
+		fscache_stat(&fscache_n_object_dead);
+		goto terminal_transit;
+
+		/* handle the parent cache of this object being withdrawn from
+		 * active service */
+	case FSCACHE_OBJECT_WITHDRAWING:
+		object->event_mask &=
+			~((1 << FSCACHE_OBJECT_EV_WITHDRAW) |
+			  (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			  (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			  (1 << FSCACHE_OBJECT_EV_ERROR));
+		fscache_withdraw_object(object);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_DEAD;
+		spin_unlock(&object->lock);
+		fscache_stat(&fscache_n_object_dead);
+		goto terminal_transit;
+
+		/* complain about the object being woken up once it is
+		 * deceased */
+	case FSCACHE_OBJECT_DEAD:
+		printk(KERN_ERR "FS-Cache:"
+		       " Unexpected event in dead state %lx\n",
+		       object->events & object->event_mask);
+		BUG();
+
+	default:
+		printk(KERN_ERR "FS-Cache: Unknown object state %u\n",
+		       object->state);
+		BUG();
+	}
+
+	/* determine the transition from a lookup state */
+lookup_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+	case FSCACHE_OBJECT_EV_RETIRE:
+	case FSCACHE_OBJECT_EV_RELEASE:
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_LC_DYING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_REQUEUE:
+		goto done;
+	case -1:
+		goto done; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+	/* determine the transition from an active state */
+active_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+	case FSCACHE_OBJECT_EV_RETIRE:
+	case FSCACHE_OBJECT_EV_RELEASE:
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_DYING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_UPDATE:
+		new_state = FSCACHE_OBJECT_UPDATING;
+		goto change_state;
+	case -1:
+		new_state = FSCACHE_OBJECT_ACTIVE;
+		goto change_state; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+	/* determine the transition from a terminal state */
+terminal_transit:
+	switch (fls(object->events & object->event_mask) - 1) {
+	case FSCACHE_OBJECT_EV_WITHDRAW:
+		new_state = FSCACHE_OBJECT_WITHDRAWING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_RETIRE:
+		new_state = FSCACHE_OBJECT_RECYCLING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_RELEASE:
+		new_state = FSCACHE_OBJECT_RELEASING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_ERROR:
+		new_state = FSCACHE_OBJECT_WITHDRAWING;
+		goto change_state;
+	case FSCACHE_OBJECT_EV_CLEARED:
+		new_state = FSCACHE_OBJECT_DYING;
+		goto change_state;
+	case -1:
+		goto done; /* sleep until event */
+	default:
+		goto unsupported_event;
+	}
+
+change_state:
+	spin_lock(&object->lock);
+	object->state = new_state;
+	spin_unlock(&object->lock);
+
+done:
+	_leave(" [->%s]", fscache_object_states[object->state]);
+	return;
+
+unsupported_event:
+	printk(KERN_ERR "FS-Cache:"
+	       " Unsupported event %lx [mask %lx] in state %s\n",
+	       object->events, object->event_mask,
+	       fscache_object_states[object->state]);
+	BUG();
+}
+
+/*
+ * execute an object
+ */
+static void fscache_object_slow_work_execute(struct slow_work *work)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+	unsigned long start;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	clear_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+
+	start = jiffies;
+	fscache_object_state_machine(object);
+	fscache_hist(fscache_objs_histogram, start);
+	if (object->events & object->event_mask)
+		fscache_enqueue_object(object);
+}
+
+/*
+ * initialise an object
+ * - check the specified object's parent to see if we can make use of it
+ *   immediately to do a creation
+ * - we may need to start the process of creating a parent and we need to wait
+ *   for the parent's lookup and creation to complete if it's not there yet
+ * - an object's cookie is pinned until we clear FSCACHE_COOKIE_CREATING on the
+ *   leaf-most cookies of the object and all its children
+ */
+static void fscache_initialise_object(struct fscache_object *object)
+{
+	struct fscache_object *parent;
+
+	_enter("");
+	ASSERT(object->cookie != NULL);
+	ASSERT(object->cookie->parent != NULL);
+	ASSERT(list_empty(&object->work.link));
+
+	if (object->events & ((1 << FSCACHE_OBJECT_EV_ERROR) |
+			      (1 << FSCACHE_OBJECT_EV_RELEASE) |
+			      (1 << FSCACHE_OBJECT_EV_RETIRE) |
+			      (1 << FSCACHE_OBJECT_EV_WITHDRAW))) {
+		_debug("abort init %lx", object->events);
+		spin_lock(&object->lock);
+		object->state = FSCACHE_OBJECT_ABORT_INIT;
+		spin_unlock(&object->lock);
+		return;
+	}
+
+	spin_lock(&object->cookie->lock);
+	spin_lock_nested(&object->cookie->parent->lock, 1);
+
+	parent = object->parent;
+	if (!parent) {
+		_debug("no parent");
+		set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+	} else {
+		spin_lock(&object->lock);
+		spin_lock_nested(&parent->lock, 1);
+		_debug("parent %s", fscache_object_states[parent->state]);
+
+		if (parent->state >= FSCACHE_OBJECT_DYING) {
+			_debug("bad parent");
+			set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+		} else if (parent->state < FSCACHE_OBJECT_AVAILABLE) {
+			_debug("wait");
+
+			/* we may get woken up in this state by child objects
+			 * binding on to us, so we need to make sure we don't
+			 * add ourself to the list multiple times */
+			if (list_empty(&object->dep_link)) {
+				object->cache->ops->grab_object(object);
+				list_add(&object->dep_link,
+					 &parent->dependents);
+
+				/* fscache_acquire_non_index_cookie() uses this
+				 * to wake the chain up */
+				if (parent->state == FSCACHE_OBJECT_INIT)
+					fscache_enqueue_object(parent);
+			}
+		} else {
+			_debug("go");
+			parent->n_ops++;
+			parent->n_obj_ops++;
+			object->lookup_jif = jiffies;
+			object->state = FSCACHE_OBJECT_LOOKING_UP;
+			set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+		}
+
+		spin_unlock(&parent->lock);
+		spin_unlock(&object->lock);
+	}
+
+	spin_unlock(&object->cookie->parent->lock);
+	spin_unlock(&object->cookie->lock);
+	_leave("");
+}
+
+/*
+ * look an object up in the cache from which it was allocated
+ * - we hold an "access lock" on the parent object, so the parent object cannot
+ *   be withdrawn by either party till we've finished
+ * - an object's cookie is pinned until we clear FSCACHE_COOKIE_CREATING on the
+ *   leaf-most cookies of the object and all its children
+ */
+static void fscache_lookup_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+	struct fscache_object *parent;
+
+	_enter("");
+
+	parent = object->parent;
+	ASSERT(parent != NULL);
+	ASSERTCMP(parent->n_ops, >, 0);
+	ASSERTCMP(parent->n_obj_ops, >, 0);
+
+	/* make sure the parent is still available */
+	ASSERTCMP(parent->state, >=, FSCACHE_OBJECT_AVAILABLE);
+
+	if (parent->state >= FSCACHE_OBJECT_DYING ||
+	    test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
+		_debug("unavailable");
+		set_bit(FSCACHE_OBJECT_EV_WITHDRAW, &object->events);
+		_leave("");
+		return;
+	}
+
+	_debug("LOOKUP \"%s/%s\" in \"%s\"",
+	       parent->cookie->def->name, cookie->def->name,
+	       object->cache->tag->name);
+
+	fscache_stat(&fscache_n_object_lookups);
+	object->cache->ops->lookup_object(object);
+
+	if (test_bit(FSCACHE_OBJECT_EV_ERROR, &object->events))
+		set_bit(FSCACHE_COOKIE_UNAVAILABLE, &cookie->flags);
+
+	_leave("");
+}
+
+/**
+ * fscache_object_lookup_negative - Note negative cookie lookup
+ * @object: Object pointing to cookie to mark
+ *
+ * Note negative lookup, permitting those waiting to read data from an already
+ * existing backing object to continue as there's no data for them to read.
+ */
+void fscache_object_lookup_negative(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x,%s}",
+	       object->debug_id, fscache_object_states[object->state]);
+
+	spin_lock(&object->lock);
+	if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
+		fscache_stat(&fscache_n_object_lookups_negative);
+
+		/* transit here to allow write requests to begin stacking up
+		 * and read requests to begin returning ENODATA */
+		object->state = FSCACHE_OBJECT_CREATING;
+		spin_unlock(&object->lock);
+
+		set_bit(FSCACHE_COOKIE_PENDING_FILL, &cookie->flags);
+		set_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+		_debug("wake up lookup %p", &cookie->flags);
+		smp_mb__before_clear_bit();
+		clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	} else {
+		ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
+		spin_unlock(&object->lock);
+	}
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_object_lookup_negative);
+
+/**
+ * fscache_obtained_object - Note successful object lookup or creation
+ * @object: Object pointing to cookie to mark
+ *
+ * Note successful lookup and/or creation, permitting those waiting to write
+ * data to a backing object to continue.
+ *
+ * Note that after calling this, an object's cookie may be relinquished by the
+ * netfs, and so must be accessed with object lock held.
+ */
+void fscache_obtained_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie = object->cookie;
+
+	_enter("{OBJ%x,%s}",
+	       object->debug_id, fscache_object_states[object->state]);
+
+	/* if we were still looking up, then we must have a positive lookup
+	 * result, in which case there may be data available */
+	spin_lock(&object->lock);
+	if (object->state == FSCACHE_OBJECT_LOOKING_UP) {
+		fscache_stat(&fscache_n_object_lookups_positive);
+
+		clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+		object->state = FSCACHE_OBJECT_AVAILABLE;
+		spin_unlock(&object->lock);
+
+		smp_mb__before_clear_bit();
+		clear_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags);
+		smp_mb__after_clear_bit();
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+	} else {
+		ASSERTCMP(object->state, ==, FSCACHE_OBJECT_CREATING);
+		fscache_stat(&fscache_n_object_created);
+
+		object->state = FSCACHE_OBJECT_AVAILABLE;
+		spin_unlock(&object->lock);
+		set_bit(FSCACHE_OBJECT_EV_REQUEUE, &object->events);
+		smp_wmb();
+	}
+
+	if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &cookie->flags))
+		wake_up_bit(&cookie->flags, FSCACHE_COOKIE_CREATING);
+
+	_leave("");
+}
+EXPORT_SYMBOL(fscache_obtained_object);
+
+/*
+ * handle an object that has just become available
+ */
+static void fscache_object_available(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	spin_lock(&object->lock);
+
+	if (test_and_clear_bit(FSCACHE_COOKIE_CREATING, &object->cookie->flags))
+		wake_up_bit(&object->cookie->flags, FSCACHE_COOKIE_CREATING);
+
+	fscache_done_parent_op(object);
+	if (object->n_in_progress == 0) {
+		if (object->n_ops > 0) {
+			ASSERTCMP(object->n_ops, >=, object->n_obj_ops);
+			ASSERTIF(object->n_ops > object->n_obj_ops,
+				 !list_empty(&object->pending_ops));
+			fscache_start_operations(object);
+		} else {
+			ASSERT(list_empty(&object->pending_ops));
+		}
+	}
+	spin_unlock(&object->lock);
+
+	object->cache->ops->lookup_complete(object);
+	fscache_enqueue_dependents(object);
+
+	fscache_hist(fscache_obj_instantiate_histogram, object->lookup_jif);
+	fscache_stat(&fscache_n_object_avail);
+
+	_leave("");
+}
+
+/*
+ * drop an object's attachments
+ */
+static void fscache_drop_object(struct fscache_object *object)
+{
+	struct fscache_object *parent = object->parent;
+	struct fscache_cache *cache = object->cache;
+
+	_enter("{OBJ%x,%d}", object->debug_id, object->n_children);
+
+	spin_lock(&cache->object_list_lock);
+	list_del_init(&object->cache_link);
+	spin_unlock(&cache->object_list_lock);
+
+	cache->ops->drop_object(object);
+
+	if (parent) {
+		_debug("release parent OBJ%x {%d}",
+		       parent->debug_id, parent->n_children);
+
+		spin_lock(&parent->lock);
+		parent->n_children--;
+		if (parent->n_children == 0)
+			fscache_raise_event(parent, FSCACHE_OBJECT_EV_CLEARED);
+		spin_unlock(&parent->lock);
+		object->parent = NULL;
+	}
+
+	/* this just shifts the object release to the slow work processor */
+	object->cache->ops->put_object(object);
+
+	_leave("");
+}
+
+/*
+ * release or recycle an object that the netfs has discarded
+ */
+static void fscache_release_object(struct fscache_object *object)
+{
+	_enter("");
+
+	fscache_drop_object(object);
+}
+
+/*
+ * withdraw an object from active service
+ */
+static void fscache_withdraw_object(struct fscache_object *object)
+{
+	struct fscache_cookie *cookie;
+	bool detached;
+
+	_enter("");
+
+	spin_lock(&object->lock);
+	cookie = object->cookie;
+	if (cookie) {
+		/* need to get the cookie lock before the object lock, starting
+		 * from the object pointer */
+		atomic_inc(&cookie->usage);
+		spin_unlock(&object->lock);
+
+		detached = false;
+		spin_lock(&cookie->lock);
+		spin_lock(&object->lock);
+
+		if (object->cookie == cookie) {
+			hlist_del_init(&object->cookie_link);
+			object->cookie = NULL;
+			detached = true;
+		}
+		spin_unlock(&cookie->lock);
+		fscache_cookie_put(cookie);
+		if (detached)
+			fscache_cookie_put(cookie);
+	}
+
+	spin_unlock(&object->lock);
+
+	fscache_drop_object(object);
+}
+
+/*
+ * withdraw an object from active service at the behest of the cache
+ * - need break the links to a cached object cookie
+ * - called under two situations:
+ *   (1) recycler decides to reclaim an in-use object
+ *   (2) a cache is unmounted
+ * - have to take care as the cookie can be being relinquished by the netfs
+ *   simultaneously
+ * - the object is pinned by the caller holding a refcount on it
+ */
+void fscache_withdrawing_object(struct fscache_cache *cache,
+				struct fscache_object *object)
+{
+	bool enqueue = false;
+
+	_enter(",OBJ%x", object->debug_id);
+
+	spin_lock(&object->lock);
+	if (object->state < FSCACHE_OBJECT_WITHDRAWING) {
+		object->state = FSCACHE_OBJECT_WITHDRAWING;
+		enqueue = true;
+	}
+	spin_unlock(&object->lock);
+
+	if (enqueue)
+		fscache_enqueue_object(object);
+
+	_leave("");
+}
+
+/*
+ * allow the slow work item processor to get a ref on an object
+ */
+static int fscache_object_slow_work_get_ref(struct slow_work *work)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+
+	return object->cache->ops->grab_object(object) ? 0 : -EAGAIN;
+}
+
+/*
+ * allow the slow work item processor to discard a ref on a work item
+ */
+static void fscache_object_slow_work_put_ref(struct slow_work *work)
+{
+	struct fscache_object *object =
+		container_of(work, struct fscache_object, work);
+
+	return object->cache->ops->put_object(object);
+}
+
+/*
+ * enqueue an object for metadata-type processing
+ */
+void fscache_enqueue_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	slow_work_enqueue(&object->work);
+}
+
+/*
+ * enqueue the dependents of an object for metadata-type processing
+ * - the caller must hold the object's lock
+ * - this may cause an already locked object to wind up being processed again
+ */
+static void fscache_enqueue_dependents(struct fscache_object *object)
+{
+	struct fscache_object *dep;
+
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (list_empty(&object->dependents))
+		return;
+
+	spin_lock(&object->lock);
+
+	while (!list_empty(&object->dependents)) {
+		dep = list_entry(object->dependents.next,
+				 struct fscache_object, dep_link);
+		list_del_init(&dep->dep_link);
+
+
+		/* sort onto appropriate lists */
+		fscache_enqueue_object(dep);
+		dep->cache->ops->put_object(dep);
+
+		if (!list_empty(&object->dependents))
+			cond_resched_lock(&object->lock);
+	}
+
+	spin_unlock(&object->lock);
+}
+
+/*
+ * remove an object from whatever queue it's waiting on
+ * - the caller must hold object->lock
+ */
+void fscache_dequeue_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	if (!list_empty(&object->dep_link)) {
+		spin_lock(&object->parent->lock);
+		list_del_init(&object->dep_link);
+		spin_unlock(&object->parent->lock);
+	}
+
+	_leave("");
+}
+
+/**
+ * fscache_check_aux - Ask the netfs whether an object on disk is still valid
+ * @object: The object to ask about
+ * @data: The auxiliary data for the object
+ * @datalen: The size of the auxiliary data
+ *
+ * This function consults the netfs about the coherency state of an object
+ */
+enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+					const void *data, uint16_t datalen)
+{
+	enum fscache_checkaux result;
+
+	if (!object->cookie->def->check_aux) {
+		fscache_stat(&fscache_n_checkaux_none);
+		return FSCACHE_CHECKAUX_OKAY;
+	}
+
+	result = object->cookie->def->check_aux(object->cookie->netfs_data,
+						data, datalen);
+	switch (result) {
+		/* entry okay as is */
+	case FSCACHE_CHECKAUX_OKAY:
+		fscache_stat(&fscache_n_checkaux_okay);
+		break;
+
+		/* entry requires update */
+	case FSCACHE_CHECKAUX_NEEDS_UPDATE:
+		fscache_stat(&fscache_n_checkaux_update);
+		break;
+
+		/* entry requires deletion */
+	case FSCACHE_CHECKAUX_OBSOLETE:
+		fscache_stat(&fscache_n_checkaux_obsolete);
+		break;
+
+	default:
+		BUG();
+	}
+
+	return result;
+}
+EXPORT_SYMBOL(fscache_check_aux);
diff --git a/fs/fscache/operation.c b/fs/fscache/operation.c
new file mode 100644
index 000000000000..e7f8d53b8b6b
--- /dev/null
+++ b/fs/fscache/operation.c
@@ -0,0 +1,459 @@
+/* FS-Cache worker operation management routines
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * See Documentation/filesystems/caching/operations.txt
+ */
+
+#define FSCACHE_DEBUG_LEVEL OPERATION
+#include <linux/module.h>
+#include "internal.h"
+
+atomic_t fscache_op_debug_id;
+EXPORT_SYMBOL(fscache_op_debug_id);
+
+/**
+ * fscache_enqueue_operation - Enqueue an operation for processing
+ * @op: The operation to enqueue
+ *
+ * Enqueue an operation for processing by the FS-Cache thread pool.
+ *
+ * This will get its own ref on the object.
+ */
+void fscache_enqueue_operation(struct fscache_operation *op)
+{
+	_enter("{OBJ%x OP%x,%u}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERT(op->processor != NULL);
+	ASSERTCMP(op->object->state, >=, FSCACHE_OBJECT_AVAILABLE);
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	if (list_empty(&op->pend_link)) {
+		switch (op->flags & FSCACHE_OP_TYPE) {
+		case FSCACHE_OP_FAST:
+			_debug("queue fast");
+			atomic_inc(&op->usage);
+			if (!schedule_work(&op->fast_work))
+				fscache_put_operation(op);
+			break;
+		case FSCACHE_OP_SLOW:
+			_debug("queue slow");
+			slow_work_enqueue(&op->slow_work);
+			break;
+		case FSCACHE_OP_MYTHREAD:
+			_debug("queue for caller's attention");
+			break;
+		default:
+			printk(KERN_ERR "FS-Cache: Unexpected op type %lx",
+			       op->flags);
+			BUG();
+			break;
+		}
+		fscache_stat(&fscache_n_op_enqueue);
+	}
+}
+EXPORT_SYMBOL(fscache_enqueue_operation);
+
+/*
+ * start an op running
+ */
+static void fscache_run_op(struct fscache_object *object,
+			   struct fscache_operation *op)
+{
+	object->n_in_progress++;
+	if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+		wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+	if (op->processor)
+		fscache_enqueue_operation(op);
+	fscache_stat(&fscache_n_op_run);
+}
+
+/*
+ * submit an exclusive operation for an object
+ * - other ops are excluded from running simultaneously with this one
+ * - this gets any extra refs it needs on an op
+ */
+int fscache_submit_exclusive_op(struct fscache_object *object,
+				struct fscache_operation *op)
+{
+	int ret;
+
+	_enter("{OBJ%x OP%x},", object->debug_id, op->debug_id);
+
+	spin_lock(&object->lock);
+	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
+	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+
+	ret = -ENOBUFS;
+	if (fscache_object_is_active(object)) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+
+		if (object->n_ops > 0) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+		} else if (!list_empty(&object->pending_ops)) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+			fscache_start_operations(object);
+		} else {
+			ASSERTCMP(object->n_in_progress, ==, 0);
+			fscache_run_op(object, op);
+		}
+
+		/* need to issue a new write op after this */
+		clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+		ret = 0;
+	} else if (object->state == FSCACHE_OBJECT_CREATING) {
+		op->object = object;
+		object->n_ops++;
+		object->n_exclusive++;	/* reads and writes must wait */
+		atomic_inc(&op->usage);
+		list_add_tail(&op->pend_link, &object->pending_ops);
+		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
+	} else {
+		/* not allowed to submit ops in any other state */
+		BUG();
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * report an unexpected submission
+ */
+static void fscache_report_unexpected_submission(struct fscache_object *object,
+						 struct fscache_operation *op,
+						 unsigned long ostate)
+{
+	static bool once_only;
+	struct fscache_operation *p;
+	unsigned n;
+
+	if (once_only)
+		return;
+	once_only = true;
+
+	kdebug("unexpected submission OP%x [OBJ%x %s]",
+	       op->debug_id, object->debug_id,
+	       fscache_object_states[object->state]);
+	kdebug("objstate=%s [%s]",
+	       fscache_object_states[object->state],
+	       fscache_object_states[ostate]);
+	kdebug("objflags=%lx", object->flags);
+	kdebug("objevent=%lx [%lx]", object->events, object->event_mask);
+	kdebug("ops=%u inp=%u exc=%u",
+	       object->n_ops, object->n_in_progress, object->n_exclusive);
+
+	if (!list_empty(&object->pending_ops)) {
+		n = 0;
+		list_for_each_entry(p, &object->pending_ops, pend_link) {
+			ASSERTCMP(p->object, ==, object);
+			kdebug("%p %p", op->processor, op->release);
+			n++;
+		}
+
+		kdebug("n=%u", n);
+	}
+
+	dump_stack();
+}
+
+/*
+ * submit an operation for an object
+ * - objects may be submitted only in the following states:
+ *   - during object creation (write ops may be submitted)
+ *   - whilst the object is active
+ *   - after an I/O error incurred in one of the two above states (op rejected)
+ * - this gets any extra refs it needs on an op
+ */
+int fscache_submit_op(struct fscache_object *object,
+		      struct fscache_operation *op)
+{
+	unsigned long ostate;
+	int ret;
+
+	_enter("{OBJ%x OP%x},{%u}",
+	       object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	spin_lock(&object->lock);
+	ASSERTCMP(object->n_ops, >=, object->n_in_progress);
+	ASSERTCMP(object->n_ops, >=, object->n_exclusive);
+
+	ostate = object->state;
+	smp_rmb();
+
+	if (fscache_object_is_active(object)) {
+		op->object = object;
+		object->n_ops++;
+
+		if (object->n_exclusive > 0) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+		} else if (!list_empty(&object->pending_ops)) {
+			atomic_inc(&op->usage);
+			list_add_tail(&op->pend_link, &object->pending_ops);
+			fscache_stat(&fscache_n_op_pend);
+			fscache_start_operations(object);
+		} else {
+			ASSERTCMP(object->n_exclusive, ==, 0);
+			fscache_run_op(object, op);
+		}
+		ret = 0;
+	} else if (object->state == FSCACHE_OBJECT_CREATING) {
+		op->object = object;
+		object->n_ops++;
+		atomic_inc(&op->usage);
+		list_add_tail(&op->pend_link, &object->pending_ops);
+		fscache_stat(&fscache_n_op_pend);
+		ret = 0;
+	} else if (!test_bit(FSCACHE_IOERROR, &object->cache->flags)) {
+		fscache_report_unexpected_submission(object, op, ostate);
+		ASSERT(!fscache_object_is_active(object));
+		ret = -ENOBUFS;
+	} else {
+		ret = -ENOBUFS;
+	}
+
+	spin_unlock(&object->lock);
+	return ret;
+}
+
+/*
+ * queue an object for withdrawal on error, aborting all following asynchronous
+ * operations
+ */
+void fscache_abort_object(struct fscache_object *object)
+{
+	_enter("{OBJ%x}", object->debug_id);
+
+	fscache_raise_event(object, FSCACHE_OBJECT_EV_ERROR);
+}
+
+/*
+ * jump start the operation processing on an object
+ * - caller must hold object->lock
+ */
+void fscache_start_operations(struct fscache_object *object)
+{
+	struct fscache_operation *op;
+	bool stop = false;
+
+	while (!list_empty(&object->pending_ops) && !stop) {
+		op = list_entry(object->pending_ops.next,
+				struct fscache_operation, pend_link);
+
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+			if (object->n_in_progress > 0)
+				break;
+			stop = true;
+		}
+		list_del_init(&op->pend_link);
+		object->n_in_progress++;
+
+		if (test_and_clear_bit(FSCACHE_OP_WAITING, &op->flags))
+			wake_up_bit(&op->flags, FSCACHE_OP_WAITING);
+		if (op->processor)
+			fscache_enqueue_operation(op);
+
+		/* the pending queue was holding a ref on the object */
+		fscache_put_operation(op);
+	}
+
+	ASSERTCMP(object->n_in_progress, <=, object->n_ops);
+
+	_debug("woke %d ops on OBJ%x",
+	       object->n_in_progress, object->debug_id);
+}
+
+/*
+ * release an operation
+ * - queues pending ops if this is the last in-progress op
+ */
+void fscache_put_operation(struct fscache_operation *op)
+{
+	struct fscache_object *object;
+	struct fscache_cache *cache;
+
+	_enter("{OBJ%x OP%x,%d}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERTCMP(atomic_read(&op->usage), >, 0);
+
+	if (!atomic_dec_and_test(&op->usage))
+		return;
+
+	_debug("PUT OP");
+	if (test_and_set_bit(FSCACHE_OP_DEAD, &op->flags))
+		BUG();
+
+	fscache_stat(&fscache_n_op_release);
+
+	if (op->release) {
+		op->release(op);
+		op->release = NULL;
+	}
+
+	object = op->object;
+
+	/* now... we may get called with the object spinlock held, so we
+	 * complete the cleanup here only if we can immediately acquire the
+	 * lock, and defer it otherwise */
+	if (!spin_trylock(&object->lock)) {
+		_debug("defer put");
+		fscache_stat(&fscache_n_op_deferred_release);
+
+		cache = object->cache;
+		spin_lock(&cache->op_gc_list_lock);
+		list_add_tail(&op->pend_link, &cache->op_gc_list);
+		spin_unlock(&cache->op_gc_list_lock);
+		schedule_work(&cache->op_gc);
+		_leave(" [defer]");
+		return;
+	}
+
+	if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+		ASSERTCMP(object->n_exclusive, >, 0);
+		object->n_exclusive--;
+	}
+
+	ASSERTCMP(object->n_in_progress, >, 0);
+	object->n_in_progress--;
+	if (object->n_in_progress == 0)
+		fscache_start_operations(object);
+
+	ASSERTCMP(object->n_ops, >, 0);
+	object->n_ops--;
+	if (object->n_ops == 0)
+		fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
+
+	spin_unlock(&object->lock);
+
+	kfree(op);
+	_leave(" [done]");
+}
+EXPORT_SYMBOL(fscache_put_operation);
+
+/*
+ * garbage collect operations that have had their release deferred
+ */
+void fscache_operation_gc(struct work_struct *work)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+	struct fscache_cache *cache =
+		container_of(work, struct fscache_cache, op_gc);
+	int count = 0;
+
+	_enter("");
+
+	do {
+		spin_lock(&cache->op_gc_list_lock);
+		if (list_empty(&cache->op_gc_list)) {
+			spin_unlock(&cache->op_gc_list_lock);
+			break;
+		}
+
+		op = list_entry(cache->op_gc_list.next,
+				struct fscache_operation, pend_link);
+		list_del(&op->pend_link);
+		spin_unlock(&cache->op_gc_list_lock);
+
+		object = op->object;
+
+		_debug("GC DEFERRED REL OBJ%x OP%x",
+		       object->debug_id, op->debug_id);
+		fscache_stat(&fscache_n_op_gc);
+
+		ASSERTCMP(atomic_read(&op->usage), ==, 0);
+
+		spin_lock(&object->lock);
+		if (test_bit(FSCACHE_OP_EXCLUSIVE, &op->flags)) {
+			ASSERTCMP(object->n_exclusive, >, 0);
+			object->n_exclusive--;
+		}
+
+		ASSERTCMP(object->n_in_progress, >, 0);
+		object->n_in_progress--;
+		if (object->n_in_progress == 0)
+			fscache_start_operations(object);
+
+		ASSERTCMP(object->n_ops, >, 0);
+		object->n_ops--;
+		if (object->n_ops == 0)
+			fscache_raise_event(object, FSCACHE_OBJECT_EV_CLEARED);
+
+		spin_unlock(&object->lock);
+
+	} while (count++ < 20);
+
+	if (!list_empty(&cache->op_gc_list))
+		schedule_work(&cache->op_gc);
+
+	_leave("");
+}
+
+/*
+ * allow the slow work item processor to get a ref on an operation
+ */
+static int fscache_op_get_ref(struct slow_work *work)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, slow_work);
+
+	atomic_inc(&op->usage);
+	return 0;
+}
+
+/*
+ * allow the slow work item processor to discard a ref on an operation
+ */
+static void fscache_op_put_ref(struct slow_work *work)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, slow_work);
+
+	fscache_put_operation(op);
+}
+
+/*
+ * execute an operation using the slow thread pool to provide processing context
+ * - the caller holds a ref to this object, so we don't need to hold one
+ */
+static void fscache_op_execute(struct slow_work *work)
+{
+	struct fscache_operation *op =
+		container_of(work, struct fscache_operation, slow_work);
+	unsigned long start;
+
+	_enter("{OBJ%x OP%x,%d}",
+	       op->object->debug_id, op->debug_id, atomic_read(&op->usage));
+
+	ASSERT(op->processor != NULL);
+	start = jiffies;
+	op->processor(op);
+	fscache_hist(fscache_ops_histogram, start);
+
+	_leave("");
+}
+
+const struct slow_work_ops fscache_op_slow_work_ops = {
+	.get_ref	= fscache_op_get_ref,
+	.put_ref	= fscache_op_put_ref,
+	.execute	= fscache_op_execute,
+};
diff --git a/fs/fscache/page.c b/fs/fscache/page.c
new file mode 100644
index 000000000000..2568e0eb644f
--- /dev/null
+++ b/fs/fscache/page.c
@@ -0,0 +1,816 @@
+/* Cache page management and data I/O routines
+ *
+ * Copyright (C) 2004-2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL PAGE
+#include <linux/module.h>
+#include <linux/fscache-cache.h>
+#include <linux/buffer_head.h>
+#include <linux/pagevec.h>
+#include "internal.h"
+
+/*
+ * check to see if a page is being written to the cache
+ */
+bool __fscache_check_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	void *val;
+
+	rcu_read_lock();
+	val = radix_tree_lookup(&cookie->stores, page->index);
+	rcu_read_unlock();
+
+	return val != NULL;
+}
+EXPORT_SYMBOL(__fscache_check_page_write);
+
+/*
+ * wait for a page to finish being written to the cache
+ */
+void __fscache_wait_on_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&cookie->flags, 0);
+
+	wait_event(*wq, !__fscache_check_page_write(cookie, page));
+}
+EXPORT_SYMBOL(__fscache_wait_on_page_write);
+
+/*
+ * note that a page has finished being written to the cache
+ */
+static void fscache_end_page_write(struct fscache_cookie *cookie, struct page *page)
+{
+	struct page *xpage;
+
+	spin_lock(&cookie->lock);
+	xpage = radix_tree_delete(&cookie->stores, page->index);
+	spin_unlock(&cookie->lock);
+	ASSERT(xpage != NULL);
+
+	wake_up_bit(&cookie->flags, 0);
+}
+
+/*
+ * actually apply the changed attributes to a cache object
+ */
+static void fscache_attr_changed_op(struct fscache_operation *op)
+{
+	struct fscache_object *object = op->object;
+
+	_enter("{OBJ%x OP%x}", object->debug_id, op->debug_id);
+
+	fscache_stat(&fscache_n_attr_changed_calls);
+
+	if (fscache_object_is_active(object) &&
+	    object->cache->ops->attr_changed(object) < 0)
+		fscache_abort_object(object);
+
+	_leave("");
+}
+
+/*
+ * notification that the attributes on an object have changed
+ */
+int __fscache_attr_changed(struct fscache_cookie *cookie)
+{
+	struct fscache_operation *op;
+	struct fscache_object *object;
+
+	_enter("%p", cookie);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+
+	fscache_stat(&fscache_n_attr_changed);
+
+	op = kzalloc(sizeof(*op), GFP_KERNEL);
+	if (!op) {
+		fscache_stat(&fscache_n_attr_changed_nomem);
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	fscache_operation_init(op, NULL);
+	fscache_operation_init_slow(op, fscache_attr_changed_op);
+	op->flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_EXCLUSIVE);
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_exclusive_op(object, op) < 0)
+		goto nobufs;
+	spin_unlock(&cookie->lock);
+	fscache_stat(&fscache_n_attr_changed_ok);
+	fscache_put_operation(op);
+	_leave(" = 0");
+	return 0;
+
+nobufs:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+	fscache_stat(&fscache_n_attr_changed_nobufs);
+	_leave(" = %d", -ENOBUFS);
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_attr_changed);
+
+/*
+ * handle secondary execution given to a retrieval op on behalf of the
+ * cache
+ */
+static void fscache_retrieval_work(struct work_struct *work)
+{
+	struct fscache_retrieval *op =
+		container_of(work, struct fscache_retrieval, op.fast_work);
+	unsigned long start;
+
+	_enter("{OP%x}", op->op.debug_id);
+
+	start = jiffies;
+	op->op.processor(&op->op);
+	fscache_hist(fscache_ops_histogram, start);
+	fscache_put_operation(&op->op);
+}
+
+/*
+ * release a retrieval op reference
+ */
+static void fscache_release_retrieval_op(struct fscache_operation *_op)
+{
+	struct fscache_retrieval *op =
+		container_of(_op, struct fscache_retrieval, op);
+
+	_enter("{OP%x}", op->op.debug_id);
+
+	fscache_hist(fscache_retrieval_histogram, op->start_time);
+	if (op->context)
+		fscache_put_context(op->op.object->cookie, op->context);
+
+	_leave("");
+}
+
+/*
+ * allocate a retrieval op
+ */
+static struct fscache_retrieval *fscache_alloc_retrieval(
+	struct address_space *mapping,
+	fscache_rw_complete_t end_io_func,
+	void *context)
+{
+	struct fscache_retrieval *op;
+
+	/* allocate a retrieval operation and attempt to submit it */
+	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (!op) {
+		fscache_stat(&fscache_n_retrievals_nomem);
+		return NULL;
+	}
+
+	fscache_operation_init(&op->op, fscache_release_retrieval_op);
+	op->op.flags	= FSCACHE_OP_MYTHREAD | (1 << FSCACHE_OP_WAITING);
+	op->mapping	= mapping;
+	op->end_io_func	= end_io_func;
+	op->context	= context;
+	op->start_time	= jiffies;
+	INIT_WORK(&op->op.fast_work, fscache_retrieval_work);
+	INIT_LIST_HEAD(&op->to_do);
+	return op;
+}
+
+/*
+ * wait for a deferred lookup to complete
+ */
+static int fscache_wait_for_deferred_lookup(struct fscache_cookie *cookie)
+{
+	unsigned long jif;
+
+	_enter("");
+
+	if (!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags)) {
+		_leave(" = 0 [imm]");
+		return 0;
+	}
+
+	fscache_stat(&fscache_n_retrievals_wait);
+
+	jif = jiffies;
+	if (wait_on_bit(&cookie->flags, FSCACHE_COOKIE_LOOKING_UP,
+			fscache_wait_bit_interruptible,
+			TASK_INTERRUPTIBLE) != 0) {
+		fscache_stat(&fscache_n_retrievals_intr);
+		_leave(" = -ERESTARTSYS");
+		return -ERESTARTSYS;
+	}
+
+	ASSERT(!test_bit(FSCACHE_COOKIE_LOOKING_UP, &cookie->flags));
+
+	smp_rmb();
+	fscache_hist(fscache_retrieval_delay_histogram, jif);
+	_leave(" = 0 [dly]");
+	return 0;
+}
+
+/*
+ * read a page from the cache or allocate a block in which to store it
+ * - we return:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ERESTARTSYS - interrupted
+ *   -ENOBUFS	- no backing object available in which to cache the block
+ *   -ENODATA	- no data available in the backing object for this block
+ *   0		- dispatched a read - it'll call end_io_func() when finished
+ */
+int __fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+				 struct page *page,
+				 fscache_rw_complete_t end_io_func,
+				 void *context,
+				 gfp_t gfp)
+{
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,%p,,,", cookie, page);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(page->mapping, end_io_func, context);
+	if (!op) {
+		_leave(" = -ENOMEM");
+		return -ENOMEM;
+	}
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	ASSERTCMP(object->state, >, FSCACHE_OBJECT_LOOKING_UP);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure */
+	fscache_get_context(object->cookie, op->context);
+
+	/* we wait for the operation to become active, and then process it
+	 * *here*, in this thread, and not in the thread pool */
+	if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
+		_debug(">>> WT");
+		fscache_stat(&fscache_n_retrieval_op_waits);
+		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("<<< GO");
+	}
+
+	/* ask the cache to honour the operation */
+	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags)) {
+		ret = object->cache->ops->allocate_page(op, page, gfp);
+		if (ret == 0)
+			ret = -ENODATA;
+	} else {
+		ret = object->cache->ops->read_or_alloc_page(op, page, gfp);
+	}
+
+	if (ret == -ENOMEM)
+		fscache_stat(&fscache_n_retrievals_nomem);
+	else if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_retrievals_intr);
+	else if (ret == -ENODATA)
+		fscache_stat(&fscache_n_retrievals_nodata);
+	else if (ret < 0)
+		fscache_stat(&fscache_n_retrievals_nobufs);
+	else
+		fscache_stat(&fscache_n_retrievals_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+nobufs:
+	fscache_stat(&fscache_n_retrievals_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_read_or_alloc_page);
+
+/*
+ * read a list of page from the cache or allocate a block in which to store
+ * them
+ * - we return:
+ *   -ENOMEM	- out of memory, some pages may be being read
+ *   -ERESTARTSYS - interrupted, some pages may be being read
+ *   -ENOBUFS	- no backing object or space available in which to cache any
+ *                pages not being read
+ *   -ENODATA	- no data available in the backing object for some or all of
+ *                the pages
+ *   0		- dispatched a read on all pages
+ *
+ * end_io_func() will be called for each page read from the cache as it is
+ * finishes being read
+ *
+ * any pages for which a read is dispatched will be removed from pages and
+ * nr_pages
+ */
+int __fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+				  struct address_space *mapping,
+				  struct list_head *pages,
+				  unsigned *nr_pages,
+				  fscache_rw_complete_t end_io_func,
+				  void *context,
+				  gfp_t gfp)
+{
+	fscache_pages_retrieval_func_t func;
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,,%d,,,", cookie, *nr_pages);
+
+	fscache_stat(&fscache_n_retrievals);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(*nr_pages, >, 0);
+	ASSERT(!list_empty(pages));
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(mapping, end_io_func, context);
+	if (!op)
+		return -ENOMEM;
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_retrieval_ops);
+
+	/* pin the netfs read context in case we need to do the actual netfs
+	 * read because we've encountered a cache read failure */
+	fscache_get_context(object->cookie, op->context);
+
+	/* we wait for the operation to become active, and then process it
+	 * *here*, in this thread, and not in the thread pool */
+	if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
+		_debug(">>> WT");
+		fscache_stat(&fscache_n_retrieval_op_waits);
+		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("<<< GO");
+	}
+
+	/* ask the cache to honour the operation */
+	if (test_bit(FSCACHE_COOKIE_NO_DATA_YET, &object->cookie->flags))
+		func = object->cache->ops->allocate_pages;
+	else
+		func = object->cache->ops->read_or_alloc_pages;
+	ret = func(op, pages, nr_pages, gfp);
+
+	if (ret == -ENOMEM)
+		fscache_stat(&fscache_n_retrievals_nomem);
+	else if (ret == -ERESTARTSYS)
+		fscache_stat(&fscache_n_retrievals_intr);
+	else if (ret == -ENODATA)
+		fscache_stat(&fscache_n_retrievals_nodata);
+	else if (ret < 0)
+		fscache_stat(&fscache_n_retrievals_nobufs);
+	else
+		fscache_stat(&fscache_n_retrievals_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+nobufs:
+	fscache_stat(&fscache_n_retrievals_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_read_or_alloc_pages);
+
+/*
+ * allocate a block in the cache on which to store a page
+ * - we return:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ERESTARTSYS - interrupted
+ *   -ENOBUFS	- no backing object available in which to cache the block
+ *   0		- block allocated
+ */
+int __fscache_alloc_page(struct fscache_cookie *cookie,
+			 struct page *page,
+			 gfp_t gfp)
+{
+	struct fscache_retrieval *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,%p,,,", cookie, page);
+
+	fscache_stat(&fscache_n_allocs);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	if (fscache_wait_for_deferred_lookup(cookie) < 0)
+		return -ERESTARTSYS;
+
+	op = fscache_alloc_retrieval(page->mapping, NULL, NULL);
+	if (!op)
+		return -ENOMEM;
+
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs_unlock;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto nobufs_unlock;
+	spin_unlock(&cookie->lock);
+
+	fscache_stat(&fscache_n_alloc_ops);
+
+	if (test_bit(FSCACHE_OP_WAITING, &op->op.flags)) {
+		_debug(">>> WT");
+		fscache_stat(&fscache_n_alloc_op_waits);
+		wait_on_bit(&op->op.flags, FSCACHE_OP_WAITING,
+			    fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+		_debug("<<< GO");
+	}
+
+	/* ask the cache to honour the operation */
+	ret = object->cache->ops->allocate_page(op, page, gfp);
+
+	if (ret < 0)
+		fscache_stat(&fscache_n_allocs_nobufs);
+	else
+		fscache_stat(&fscache_n_allocs_ok);
+
+	fscache_put_retrieval(op);
+	_leave(" = %d", ret);
+	return ret;
+
+nobufs_unlock:
+	spin_unlock(&cookie->lock);
+	kfree(op);
+nobufs:
+	fscache_stat(&fscache_n_allocs_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+}
+EXPORT_SYMBOL(__fscache_alloc_page);
+
+/*
+ * release a write op reference
+ */
+static void fscache_release_write_op(struct fscache_operation *_op)
+{
+	_enter("{OP%x}", _op->debug_id);
+}
+
+/*
+ * perform the background storage of a page into the cache
+ */
+static void fscache_write_op(struct fscache_operation *_op)
+{
+	struct fscache_storage *op =
+		container_of(_op, struct fscache_storage, op);
+	struct fscache_object *object = op->op.object;
+	struct fscache_cookie *cookie = object->cookie;
+	struct page *page;
+	unsigned n;
+	void *results[1];
+	int ret;
+
+	_enter("{OP%x,%d}", op->op.debug_id, atomic_read(&op->op.usage));
+
+	spin_lock(&cookie->lock);
+	spin_lock(&object->lock);
+
+	if (!fscache_object_is_active(object)) {
+		spin_unlock(&object->lock);
+		spin_unlock(&cookie->lock);
+		_leave("");
+		return;
+	}
+
+	fscache_stat(&fscache_n_store_calls);
+
+	/* find a page to store */
+	page = NULL;
+	n = radix_tree_gang_lookup_tag(&cookie->stores, results, 0, 1,
+				       FSCACHE_COOKIE_PENDING_TAG);
+	if (n != 1)
+		goto superseded;
+	page = results[0];
+	_debug("gang %d [%lx]", n, page->index);
+	if (page->index > op->store_limit)
+		goto superseded;
+
+	radix_tree_tag_clear(&cookie->stores, page->index,
+			     FSCACHE_COOKIE_PENDING_TAG);
+
+	spin_unlock(&object->lock);
+	spin_unlock(&cookie->lock);
+
+	if (page) {
+		ret = object->cache->ops->write_page(op, page);
+		fscache_end_page_write(cookie, page);
+		page_cache_release(page);
+		if (ret < 0)
+			fscache_abort_object(object);
+		else
+			fscache_enqueue_operation(&op->op);
+	}
+
+	_leave("");
+	return;
+
+superseded:
+	/* this writer is going away and there aren't any more things to
+	 * write */
+	_debug("cease");
+	clear_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags);
+	spin_unlock(&object->lock);
+	spin_unlock(&cookie->lock);
+	_leave("");
+}
+
+/*
+ * request a page be stored in the cache
+ * - returns:
+ *   -ENOMEM	- out of memory, nothing done
+ *   -ENOBUFS	- no backing object available in which to cache the page
+ *   0		- dispatched a write - it'll call end_io_func() when finished
+ *
+ * if the cookie still has a backing object at this point, that object can be
+ * in one of a few states with respect to storage processing:
+ *
+ *  (1) negative lookup, object not yet created (FSCACHE_COOKIE_CREATING is
+ *      set)
+ *
+ *	(a) no writes yet (set FSCACHE_COOKIE_PENDING_FILL and queue deferred
+ *	    fill op)
+ *
+ *	(b) writes deferred till post-creation (mark page for writing and
+ *	    return immediately)
+ *
+ *  (2) negative lookup, object created, initial fill being made from netfs
+ *      (FSCACHE_COOKIE_INITIAL_FILL is set)
+ *
+ *	(a) fill point not yet reached this page (mark page for writing and
+ *          return)
+ *
+ *	(b) fill point passed this page (queue op to store this page)
+ *
+ *  (3) object extant (queue op to store this page)
+ *
+ * any other state is invalid
+ */
+int __fscache_write_page(struct fscache_cookie *cookie,
+			 struct page *page,
+			 gfp_t gfp)
+{
+	struct fscache_storage *op;
+	struct fscache_object *object;
+	int ret;
+
+	_enter("%p,%x,", cookie, (u32) page->flags);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERT(PageFsCache(page));
+
+	fscache_stat(&fscache_n_stores);
+
+	op = kzalloc(sizeof(*op), GFP_NOIO);
+	if (!op)
+		goto nomem;
+
+	fscache_operation_init(&op->op, fscache_release_write_op);
+	fscache_operation_init_slow(&op->op, fscache_write_op);
+	op->op.flags = FSCACHE_OP_SLOW | (1 << FSCACHE_OP_WAITING);
+
+	ret = radix_tree_preload(gfp & ~__GFP_HIGHMEM);
+	if (ret < 0)
+		goto nomem_free;
+
+	ret = -ENOBUFS;
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects))
+		goto nobufs;
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+	if (test_bit(FSCACHE_IOERROR, &object->cache->flags))
+		goto nobufs;
+
+	/* add the page to the pending-storage radix tree on the backing
+	 * object */
+	spin_lock(&object->lock);
+
+	_debug("store limit %llx", (unsigned long long) object->store_limit);
+
+	ret = radix_tree_insert(&cookie->stores, page->index, page);
+	if (ret < 0) {
+		if (ret == -EEXIST)
+			goto already_queued;
+		_debug("insert failed %d", ret);
+		goto nobufs_unlock_obj;
+	}
+
+	radix_tree_tag_set(&cookie->stores, page->index,
+			   FSCACHE_COOKIE_PENDING_TAG);
+	page_cache_get(page);
+
+	/* we only want one writer at a time, but we do need to queue new
+	 * writers after exclusive ops */
+	if (test_and_set_bit(FSCACHE_OBJECT_PENDING_WRITE, &object->flags))
+		goto already_pending;
+
+	spin_unlock(&object->lock);
+
+	op->op.debug_id	= atomic_inc_return(&fscache_op_debug_id);
+	op->store_limit = object->store_limit;
+
+	if (fscache_submit_op(object, &op->op) < 0)
+		goto submit_failed;
+
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	fscache_stat(&fscache_n_store_ops);
+	fscache_stat(&fscache_n_stores_ok);
+
+	/* the slow work queue now carries its own ref on the object */
+	fscache_put_operation(&op->op);
+	_leave(" = 0");
+	return 0;
+
+already_queued:
+	fscache_stat(&fscache_n_stores_again);
+already_pending:
+	spin_unlock(&object->lock);
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	kfree(op);
+	fscache_stat(&fscache_n_stores_ok);
+	_leave(" = 0");
+	return 0;
+
+submit_failed:
+	radix_tree_delete(&cookie->stores, page->index);
+	page_cache_release(page);
+	ret = -ENOBUFS;
+	goto nobufs;
+
+nobufs_unlock_obj:
+	spin_unlock(&object->lock);
+nobufs:
+	spin_unlock(&cookie->lock);
+	radix_tree_preload_end();
+	kfree(op);
+	fscache_stat(&fscache_n_stores_nobufs);
+	_leave(" = -ENOBUFS");
+	return -ENOBUFS;
+
+nomem_free:
+	kfree(op);
+nomem:
+	fscache_stat(&fscache_n_stores_oom);
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(__fscache_write_page);
+
+/*
+ * remove a page from the cache
+ */
+void __fscache_uncache_page(struct fscache_cookie *cookie, struct page *page)
+{
+	struct fscache_object *object;
+
+	_enter(",%p", page);
+
+	ASSERTCMP(cookie->def->type, !=, FSCACHE_COOKIE_TYPE_INDEX);
+	ASSERTCMP(page, !=, NULL);
+
+	fscache_stat(&fscache_n_uncaches);
+
+	/* cache withdrawal may beat us to it */
+	if (!PageFsCache(page))
+		goto done;
+
+	/* get the object */
+	spin_lock(&cookie->lock);
+
+	if (hlist_empty(&cookie->backing_objects)) {
+		ClearPageFsCache(page);
+		goto done_unlock;
+	}
+
+	object = hlist_entry(cookie->backing_objects.first,
+			     struct fscache_object, cookie_link);
+
+	/* there might now be stuff on disk we could read */
+	clear_bit(FSCACHE_COOKIE_NO_DATA_YET, &cookie->flags);
+
+	/* only invoke the cache backend if we managed to mark the page
+	 * uncached here; this deals with synchronisation vs withdrawal */
+	if (TestClearPageFsCache(page) &&
+	    object->cache->ops->uncache_page) {
+		/* the cache backend releases the cookie lock */
+		object->cache->ops->uncache_page(object, page);
+		goto done;
+	}
+
+done_unlock:
+	spin_unlock(&cookie->lock);
+done:
+	_leave("");
+}
+EXPORT_SYMBOL(__fscache_uncache_page);
+
+/**
+ * fscache_mark_pages_cached - Mark pages as being cached
+ * @op: The retrieval op pages are being marked for
+ * @pagevec: The pages to be marked
+ *
+ * Mark a bunch of netfs pages as being cached.  After this is called,
+ * the netfs must call fscache_uncache_page() to remove the mark.
+ */
+void fscache_mark_pages_cached(struct fscache_retrieval *op,
+			       struct pagevec *pagevec)
+{
+	struct fscache_cookie *cookie = op->op.object->cookie;
+	unsigned long loop;
+
+#ifdef CONFIG_FSCACHE_STATS
+	atomic_add(pagevec->nr, &fscache_n_marks);
+#endif
+
+	for (loop = 0; loop < pagevec->nr; loop++) {
+		struct page *page = pagevec->pages[loop];
+
+		_debug("- mark %p{%lx}", page, page->index);
+		if (TestSetPageFsCache(page)) {
+			static bool once_only;
+			if (!once_only) {
+				once_only = true;
+				printk(KERN_WARNING "FS-Cache:"
+				       " Cookie type %s marked page %lx"
+				       " multiple times\n",
+				       cookie->def->name, page->index);
+			}
+		}
+	}
+
+	if (cookie->def->mark_pages_cached)
+		cookie->def->mark_pages_cached(cookie->netfs_data,
+					       op->mapping, pagevec);
+	pagevec_reinit(pagevec);
+}
+EXPORT_SYMBOL(fscache_mark_pages_cached);
diff --git a/fs/fscache/proc.c b/fs/fscache/proc.c
new file mode 100644
index 000000000000..beeab44bc31a
--- /dev/null
+++ b/fs/fscache/proc.c
@@ -0,0 +1,68 @@
+/* FS-Cache statistics viewing interface
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL OPERATION
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * initialise the /proc/fs/fscache/ directory
+ */
+int __init fscache_proc_init(void)
+{
+	_enter("");
+
+	if (!proc_mkdir("fs/fscache", NULL))
+		goto error_dir;
+
+#ifdef CONFIG_FSCACHE_STATS
+	if (!proc_create("fs/fscache/stats", S_IFREG | 0444, NULL,
+			 &fscache_stats_fops))
+		goto error_stats;
+#endif
+
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	if (!proc_create("fs/fscache/histogram", S_IFREG | 0444, NULL,
+			 &fscache_histogram_fops))
+		goto error_histogram;
+#endif
+
+	_leave(" = 0");
+	return 0;
+
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+error_histogram:
+#endif
+#ifdef CONFIG_FSCACHE_STATS
+	remove_proc_entry("fs/fscache/stats", NULL);
+error_stats:
+#endif
+	remove_proc_entry("fs/fscache", NULL);
+error_dir:
+	_leave(" = -ENOMEM");
+	return -ENOMEM;
+}
+
+/*
+ * clean up the /proc/fs/fscache/ directory
+ */
+void fscache_proc_cleanup(void)
+{
+#ifdef CONFIG_FSCACHE_HISTOGRAM
+	remove_proc_entry("fs/fscache/histogram", NULL);
+#endif
+#ifdef CONFIG_FSCACHE_STATS
+	remove_proc_entry("fs/fscache/stats", NULL);
+#endif
+	remove_proc_entry("fs/fscache", NULL);
+}
diff --git a/fs/fscache/stats.c b/fs/fscache/stats.c
new file mode 100644
index 000000000000..65deb99e756b
--- /dev/null
+++ b/fs/fscache/stats.c
@@ -0,0 +1,212 @@
+/* FS-Cache statistics
+ *
+ * Copyright (C) 2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ */
+
+#define FSCACHE_DEBUG_LEVEL THREAD
+#include <linux/module.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include "internal.h"
+
+/*
+ * operation counters
+ */
+atomic_t fscache_n_op_pend;
+atomic_t fscache_n_op_run;
+atomic_t fscache_n_op_enqueue;
+atomic_t fscache_n_op_requeue;
+atomic_t fscache_n_op_deferred_release;
+atomic_t fscache_n_op_release;
+atomic_t fscache_n_op_gc;
+
+atomic_t fscache_n_attr_changed;
+atomic_t fscache_n_attr_changed_ok;
+atomic_t fscache_n_attr_changed_nobufs;
+atomic_t fscache_n_attr_changed_nomem;
+atomic_t fscache_n_attr_changed_calls;
+
+atomic_t fscache_n_allocs;
+atomic_t fscache_n_allocs_ok;
+atomic_t fscache_n_allocs_wait;
+atomic_t fscache_n_allocs_nobufs;
+atomic_t fscache_n_alloc_ops;
+atomic_t fscache_n_alloc_op_waits;
+
+atomic_t fscache_n_retrievals;
+atomic_t fscache_n_retrievals_ok;
+atomic_t fscache_n_retrievals_wait;
+atomic_t fscache_n_retrievals_nodata;
+atomic_t fscache_n_retrievals_nobufs;
+atomic_t fscache_n_retrievals_intr;
+atomic_t fscache_n_retrievals_nomem;
+atomic_t fscache_n_retrieval_ops;
+atomic_t fscache_n_retrieval_op_waits;
+
+atomic_t fscache_n_stores;
+atomic_t fscache_n_stores_ok;
+atomic_t fscache_n_stores_again;
+atomic_t fscache_n_stores_nobufs;
+atomic_t fscache_n_stores_oom;
+atomic_t fscache_n_store_ops;
+atomic_t fscache_n_store_calls;
+
+atomic_t fscache_n_marks;
+atomic_t fscache_n_uncaches;
+
+atomic_t fscache_n_acquires;
+atomic_t fscache_n_acquires_null;
+atomic_t fscache_n_acquires_no_cache;
+atomic_t fscache_n_acquires_ok;
+atomic_t fscache_n_acquires_nobufs;
+atomic_t fscache_n_acquires_oom;
+
+atomic_t fscache_n_updates;
+atomic_t fscache_n_updates_null;
+atomic_t fscache_n_updates_run;
+
+atomic_t fscache_n_relinquishes;
+atomic_t fscache_n_relinquishes_null;
+atomic_t fscache_n_relinquishes_waitcrt;
+
+atomic_t fscache_n_cookie_index;
+atomic_t fscache_n_cookie_data;
+atomic_t fscache_n_cookie_special;
+
+atomic_t fscache_n_object_alloc;
+atomic_t fscache_n_object_no_alloc;
+atomic_t fscache_n_object_lookups;
+atomic_t fscache_n_object_lookups_negative;
+atomic_t fscache_n_object_lookups_positive;
+atomic_t fscache_n_object_created;
+atomic_t fscache_n_object_avail;
+atomic_t fscache_n_object_dead;
+
+atomic_t fscache_n_checkaux_none;
+atomic_t fscache_n_checkaux_okay;
+atomic_t fscache_n_checkaux_update;
+atomic_t fscache_n_checkaux_obsolete;
+
+/*
+ * display the general statistics
+ */
+static int fscache_stats_show(struct seq_file *m, void *v)
+{
+	seq_puts(m, "FS-Cache statistics\n");
+
+	seq_printf(m, "Cookies: idx=%u dat=%u spc=%u\n",
+		   atomic_read(&fscache_n_cookie_index),
+		   atomic_read(&fscache_n_cookie_data),
+		   atomic_read(&fscache_n_cookie_special));
+
+	seq_printf(m, "Objects: alc=%u nal=%u avl=%u ded=%u\n",
+		   atomic_read(&fscache_n_object_alloc),
+		   atomic_read(&fscache_n_object_no_alloc),
+		   atomic_read(&fscache_n_object_avail),
+		   atomic_read(&fscache_n_object_dead));
+	seq_printf(m, "ChkAux : non=%u ok=%u upd=%u obs=%u\n",
+		   atomic_read(&fscache_n_checkaux_none),
+		   atomic_read(&fscache_n_checkaux_okay),
+		   atomic_read(&fscache_n_checkaux_update),
+		   atomic_read(&fscache_n_checkaux_obsolete));
+
+	seq_printf(m, "Pages  : mrk=%u unc=%u\n",
+		   atomic_read(&fscache_n_marks),
+		   atomic_read(&fscache_n_uncaches));
+
+	seq_printf(m, "Acquire: n=%u nul=%u noc=%u ok=%u nbf=%u"
+		   " oom=%u\n",
+		   atomic_read(&fscache_n_acquires),
+		   atomic_read(&fscache_n_acquires_null),
+		   atomic_read(&fscache_n_acquires_no_cache),
+		   atomic_read(&fscache_n_acquires_ok),
+		   atomic_read(&fscache_n_acquires_nobufs),
+		   atomic_read(&fscache_n_acquires_oom));
+
+	seq_printf(m, "Lookups: n=%u neg=%u pos=%u crt=%u\n",
+		   atomic_read(&fscache_n_object_lookups),
+		   atomic_read(&fscache_n_object_lookups_negative),
+		   atomic_read(&fscache_n_object_lookups_positive),
+		   atomic_read(&fscache_n_object_created));
+
+	seq_printf(m, "Updates: n=%u nul=%u run=%u\n",
+		   atomic_read(&fscache_n_updates),
+		   atomic_read(&fscache_n_updates_null),
+		   atomic_read(&fscache_n_updates_run));
+
+	seq_printf(m, "Relinqs: n=%u nul=%u wcr=%u\n",
+		   atomic_read(&fscache_n_relinquishes),
+		   atomic_read(&fscache_n_relinquishes_null),
+		   atomic_read(&fscache_n_relinquishes_waitcrt));
+
+	seq_printf(m, "AttrChg: n=%u ok=%u nbf=%u oom=%u run=%u\n",
+		   atomic_read(&fscache_n_attr_changed),
+		   atomic_read(&fscache_n_attr_changed_ok),
+		   atomic_read(&fscache_n_attr_changed_nobufs),
+		   atomic_read(&fscache_n_attr_changed_nomem),
+		   atomic_read(&fscache_n_attr_changed_calls));
+
+	seq_printf(m, "Allocs : n=%u ok=%u wt=%u nbf=%u\n",
+		   atomic_read(&fscache_n_allocs),
+		   atomic_read(&fscache_n_allocs_ok),
+		   atomic_read(&fscache_n_allocs_wait),
+		   atomic_read(&fscache_n_allocs_nobufs));
+	seq_printf(m, "Allocs : ops=%u owt=%u\n",
+		   atomic_read(&fscache_n_alloc_ops),
+		   atomic_read(&fscache_n_alloc_op_waits));
+
+	seq_printf(m, "Retrvls: n=%u ok=%u wt=%u nod=%u nbf=%u"
+		   " int=%u oom=%u\n",
+		   atomic_read(&fscache_n_retrievals),
+		   atomic_read(&fscache_n_retrievals_ok),
+		   atomic_read(&fscache_n_retrievals_wait),
+		   atomic_read(&fscache_n_retrievals_nodata),
+		   atomic_read(&fscache_n_retrievals_nobufs),
+		   atomic_read(&fscache_n_retrievals_intr),
+		   atomic_read(&fscache_n_retrievals_nomem));
+	seq_printf(m, "Retrvls: ops=%u owt=%u\n",
+		   atomic_read(&fscache_n_retrieval_ops),
+		   atomic_read(&fscache_n_retrieval_op_waits));
+
+	seq_printf(m, "Stores : n=%u ok=%u agn=%u nbf=%u oom=%u\n",
+		   atomic_read(&fscache_n_stores),
+		   atomic_read(&fscache_n_stores_ok),
+		   atomic_read(&fscache_n_stores_again),
+		   atomic_read(&fscache_n_stores_nobufs),
+		   atomic_read(&fscache_n_stores_oom));
+	seq_printf(m, "Stores : ops=%u run=%u\n",
+		   atomic_read(&fscache_n_store_ops),
+		   atomic_read(&fscache_n_store_calls));
+
+	seq_printf(m, "Ops    : pend=%u run=%u enq=%u\n",
+		   atomic_read(&fscache_n_op_pend),
+		   atomic_read(&fscache_n_op_run),
+		   atomic_read(&fscache_n_op_enqueue));
+	seq_printf(m, "Ops    : dfr=%u rel=%u gc=%u\n",
+		   atomic_read(&fscache_n_op_deferred_release),
+		   atomic_read(&fscache_n_op_release),
+		   atomic_read(&fscache_n_op_gc));
+	return 0;
+}
+
+/*
+ * open "/proc/fs/fscache/stats" allowing provision of a statistical summary
+ */
+static int fscache_stats_open(struct inode *inode, struct file *file)
+{
+	return single_open(file, fscache_stats_show, NULL);
+}
+
+const struct file_operations fscache_stats_fops = {
+	.owner		= THIS_MODULE,
+	.open		= fscache_stats_open,
+	.read		= seq_read,
+	.llseek		= seq_lseek,
+	.release	= seq_release,
+};
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 06da05261e04..8b8eebc5614b 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -1032,6 +1032,7 @@ static int fuse_readdir(struct file *file, void *dstbuf, filldir_t filldir)
 		fuse_put_request(fc, req);
 		return -ENOMEM;
 	}
+	req->out.argpages = 1;
 	req->num_pages = 1;
 	req->pages[0] = page;
 	fuse_read_fill(req, file, inode, file->f_pos, PAGE_SIZE, FUSE_READDIR);
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 4e340fedf768..2b25133524a3 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -386,7 +386,6 @@ void fuse_read_fill(struct fuse_req *req, struct file *file,
 	req->in.numargs = 1;
 	req->in.args[0].size = sizeof(struct fuse_read_in);
 	req->in.args[0].value = inarg;
-	req->out.argpages = 1;
 	req->out.argvar = 1;
 	req->out.numargs = 1;
 	req->out.args[0].size = count;
@@ -453,6 +452,7 @@ static int fuse_readpage(struct file *file, struct page *page)
 	attr_ver = fuse_get_attr_version(fc);
 
 	req->out.page_zeroing = 1;
+	req->out.argpages = 1;
 	req->num_pages = 1;
 	req->pages[0] = page;
 	num_read = fuse_send_read(req, file, inode, pos, count, NULL);
@@ -510,6 +510,8 @@ static void fuse_send_readpages(struct fuse_req *req, struct file *file,
 	struct fuse_conn *fc = get_fuse_conn(inode);
 	loff_t pos = page_offset(req->pages[0]);
 	size_t count = req->num_pages << PAGE_CACHE_SHIFT;
+
+	req->out.argpages = 1;
 	req->out.page_zeroing = 1;
 	fuse_read_fill(req, file, inode, pos, count, FUSE_READ);
 	req->misc.read.attr_ver = fuse_get_attr_version(fc);
@@ -621,7 +623,6 @@ static void fuse_write_fill(struct fuse_req *req, struct file *file,
 	inarg->flags = file ? file->f_flags : 0;
 	req->in.h.opcode = FUSE_WRITE;
 	req->in.h.nodeid = get_node_id(inode);
-	req->in.argpages = 1;
 	req->in.numargs = 2;
 	if (fc->minor < 9)
 		req->in.args[0].size = FUSE_COMPAT_WRITE_IN_SIZE;
@@ -695,6 +696,7 @@ static int fuse_buffered_write(struct file *file, struct inode *inode,
 	if (IS_ERR(req))
 		return PTR_ERR(req);
 
+	req->in.argpages = 1;
 	req->num_pages = 1;
 	req->pages[0] = page;
 	req->page_offset = offset;
@@ -771,6 +773,7 @@ static ssize_t fuse_fill_write_pages(struct fuse_req *req,
 	size_t count = 0;
 	int err;
 
+	req->in.argpages = 1;
 	req->page_offset = offset;
 
 	do {
@@ -935,21 +938,28 @@ static void fuse_release_user_pages(struct fuse_req *req, int write)
 }
 
 static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf,
-			       unsigned nbytes, int write)
+			       unsigned *nbytesp, int write)
 {
+	unsigned nbytes = *nbytesp;
 	unsigned long user_addr = (unsigned long) buf;
 	unsigned offset = user_addr & ~PAGE_MASK;
 	int npages;
 
-	/* This doesn't work with nfsd */
-	if (!current->mm)
-		return -EPERM;
+	/* Special case for kernel I/O: can copy directly into the buffer */
+	if (segment_eq(get_fs(), KERNEL_DS)) {
+		if (write)
+			req->in.args[1].value = (void *) user_addr;
+		else
+			req->out.args[0].value = (void *) user_addr;
+
+		return 0;
+	}
 
 	nbytes = min(nbytes, (unsigned) FUSE_MAX_PAGES_PER_REQ << PAGE_SHIFT);
 	npages = (nbytes + offset + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	npages = clamp(npages, 1, FUSE_MAX_PAGES_PER_REQ);
 	down_read(&current->mm->mmap_sem);
-	npages = get_user_pages(current, current->mm, user_addr, npages, write,
+	npages = get_user_pages(current, current->mm, user_addr, npages, !write,
 				0, req->pages, NULL);
 	up_read(&current->mm->mmap_sem);
 	if (npages < 0)
@@ -957,6 +967,15 @@ static int fuse_get_user_pages(struct fuse_req *req, const char __user *buf,
 
 	req->num_pages = npages;
 	req->page_offset = offset;
+
+	if (write)
+		req->in.argpages = 1;
+	else
+		req->out.argpages = 1;
+
+	nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset;
+	*nbytesp = min(*nbytesp, nbytes);
+
 	return 0;
 }
 
@@ -979,15 +998,13 @@ static ssize_t fuse_direct_io(struct file *file, const char __user *buf,
 
 	while (count) {
 		size_t nres;
-		size_t nbytes_limit = min(count, nmax);
-		size_t nbytes;
-		int err = fuse_get_user_pages(req, buf, nbytes_limit, !write);
+		size_t nbytes = min(count, nmax);
+		int err = fuse_get_user_pages(req, buf, &nbytes, write);
 		if (err) {
 			res = err;
 			break;
 		}
-		nbytes = (req->num_pages << PAGE_SHIFT) - req->page_offset;
-		nbytes = min(nbytes_limit, nbytes);
+
 		if (write)
 			nres = fuse_send_write(req, file, inode, pos, nbytes,
 					       current->files);
@@ -1163,6 +1180,7 @@ static int fuse_writepage_locked(struct page *page)
 	fuse_write_fill(req, NULL, ff, inode, page_offset(page), 0, 1);
 
 	copy_highpage(tmp_page, page);
+	req->in.argpages = 1;
 	req->num_pages = 1;
 	req->pages[0] = tmp_page;
 	req->page_offset = 0;
@@ -1274,6 +1292,15 @@ static int fuse_file_mmap(struct file *file, struct vm_area_struct *vma)
 	return 0;
 }
 
+static int fuse_direct_mmap(struct file *file, struct vm_area_struct *vma)
+{
+	/* Can't provide the coherency needed for MAP_SHARED */
+	if (vma->vm_flags & VM_MAYSHARE)
+		return -ENODEV;
+
+	return generic_file_mmap(file, vma);
+}
+
 static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,
 				  struct file_lock *fl)
 {
@@ -1908,6 +1935,7 @@ static const struct file_operations fuse_direct_io_file_operations = {
 	.llseek		= fuse_file_llseek,
 	.read		= fuse_direct_read,
 	.write		= fuse_direct_write,
+	.mmap		= fuse_direct_mmap,
 	.open		= fuse_open,
 	.flush		= fuse_flush,
 	.release	= fuse_release,
@@ -1917,7 +1945,7 @@ static const struct file_operations fuse_direct_io_file_operations = {
 	.unlocked_ioctl	= fuse_file_ioctl,
 	.compat_ioctl	= fuse_file_compat_ioctl,
 	.poll		= fuse_file_poll,
-	/* no mmap and splice_read */
+	/* no splice_read */
 };
 
 static const struct address_space_operations fuse_file_aops  = {
diff --git a/fs/generic_acl.c b/fs/generic_acl.c
index 995d63b2e747..e0b53aa7bbec 100644
--- a/fs/generic_acl.c
+++ b/fs/generic_acl.c
@@ -134,7 +134,7 @@ generic_acl_init(struct inode *inode, struct inode *dir,
 	mode_t mode = inode->i_mode;
 	int error;
 
-	inode->i_mode = mode & ~current->fs->umask;
+	inode->i_mode = mode & ~current_umask();
 	if (!S_ISLNK(inode->i_mode))
 		acl = ops->getacl(dir, ACL_TYPE_DEFAULT);
 	if (acl) {
diff --git a/fs/gfs2/acl.c b/fs/gfs2/acl.c
index 43764f4fa763..fa881bdc3d85 100644
--- a/fs/gfs2/acl.c
+++ b/fs/gfs2/acl.c
@@ -215,7 +215,7 @@ int gfs2_acl_create(struct gfs2_inode *dip, struct gfs2_inode *ip)
 	if (error)
 		return error;
 	if (!acl) {
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 		if (mode != ip->i_inode.i_mode)
 			error = munge_mode(ip, mode);
 		return error;
diff --git a/fs/hfs/super.c b/fs/hfs/super.c
index c8b5acf4b0b7..a36bb749926d 100644
--- a/fs/hfs/super.c
+++ b/fs/hfs/super.c
@@ -82,6 +82,7 @@ static void hfs_put_super(struct super_block *sb)
 static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = HFS_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
@@ -90,6 +91,8 @@ static int hfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = HFS_SB(sb)->fs_ablocks;
 	buf->f_ffree = HFS_SB(sb)->free_ablocks;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = HFS_NAMELEN;
 
 	return 0;
diff --git a/fs/hfsplus/options.c b/fs/hfsplus/options.c
index bab7f8d1bdfa..3fcbb0e1f6fc 100644
--- a/fs/hfsplus/options.c
+++ b/fs/hfsplus/options.c
@@ -48,7 +48,7 @@ void hfsplus_fill_defaults(struct hfsplus_sb_info *opts)
 
 	opts->creator = HFSPLUS_DEF_CR_TYPE;
 	opts->type = HFSPLUS_DEF_CR_TYPE;
-	opts->umask = current->fs->umask;
+	opts->umask = current_umask();
 	opts->uid = current_uid();
 	opts->gid = current_gid();
 	opts->part = -1;
diff --git a/fs/hfsplus/super.c b/fs/hfsplus/super.c
index eb74531a0a8e..f2a64020f42e 100644
--- a/fs/hfsplus/super.c
+++ b/fs/hfsplus/super.c
@@ -223,6 +223,7 @@ static void hfsplus_put_super(struct super_block *sb)
 static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = HFSPLUS_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
@@ -231,6 +232,8 @@ static int hfsplus_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = 0xFFFFFFFF;
 	buf->f_ffree = 0xFFFFFFFF - HFSPLUS_SB(sb).next_cnid;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = HFSPLUS_MAX_STRLEN;
 
 	return 0;
diff --git a/fs/hpfs/super.c b/fs/hpfs/super.c
index 0d049b8919c4..fecf402d7b8a 100644
--- a/fs/hpfs/super.c
+++ b/fs/hpfs/super.c
@@ -136,6 +136,7 @@ static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *s = dentry->d_sb;
 	struct hpfs_sb_info *sbi = hpfs_sb(s);
+	u64 id = huge_encode_dev(s->s_bdev->bd_dev);
 	lock_kernel();
 
 	/*if (sbi->sb_n_free == -1) {*/
@@ -149,6 +150,8 @@ static int hpfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = sbi->sb_n_free;
 	buf->f_files = sbi->sb_dirband_size / 4;
 	buf->f_ffree = sbi->sb_n_free_dnodes;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = 254;
 
 	unlock_kernel();
@@ -477,7 +480,7 @@ static int hpfs_fill_super(struct super_block *s, void *options, int silent)
 
 	uid = current_uid();
 	gid = current_gid();
-	umask = current->fs->umask;
+	umask = current_umask();
 	lowercase = 0;
 	conv = CONV_BINARY;
 	eas = 2;
diff --git a/fs/hppfs/hppfs.c b/fs/hppfs/hppfs.c
index b278f7f52024..a5089a6dd67a 100644
--- a/fs/hppfs/hppfs.c
+++ b/fs/hppfs/hppfs.c
@@ -280,7 +280,12 @@ static ssize_t hppfs_read(struct file *file, char __user *buf, size_t count,
 			       "errno = %d\n", err);
 			return err;
 		}
-		count = hppfs_read_file(hppfs->host_fd, buf, count);
+		err = hppfs_read_file(hppfs->host_fd, buf, count);
+		if (err < 0) {
+			printk(KERN_ERR "hppfs_read: read failed: %d\n", err);
+			return err;
+		}
+		count = err;
 		if (count > 0)
 			*ppos += count;
 	}
diff --git a/fs/internal.h b/fs/internal.h
index 53af885f1732..b4dac4fb6b61 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -11,6 +11,7 @@
 
 struct super_block;
 struct linux_binprm;
+struct path;
 
 /*
  * block_dev.c
@@ -43,7 +44,7 @@ extern void __init chrdev_init(void);
 /*
  * exec.c
  */
-extern void check_unsafe_exec(struct linux_binprm *);
+extern int check_unsafe_exec(struct linux_binprm *);
 
 /*
  * namespace.c
@@ -60,3 +61,8 @@ extern void umount_tree(struct vfsmount *, int, struct list_head *);
 extern struct vfsmount *copy_tree(struct vfsmount *, struct dentry *, int);
 
 extern void __init mnt_init(void);
+
+/*
+ * fs_struct.c
+ */
+extern void chroot_fs_refs(struct path *, struct path *);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 13d2eddd0692..b4cbe9603c7d 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -923,6 +923,7 @@ out_freesbi:
 static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = ISOFS_SUPER_MAGIC;
 	buf->f_bsize = sb->s_blocksize;
@@ -932,6 +933,8 @@ static int isofs_statfs (struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bavail = 0;
 	buf->f_files = ISOFS_SB(sb)->s_ninodes;
 	buf->f_ffree = 0;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	buf->f_namelen = NAME_MAX;
 	return 0;
 }
diff --git a/fs/jbd/commit.c b/fs/jbd/commit.c
index 3fbffb1ea714..f8077b9c8981 100644
--- a/fs/jbd/commit.c
+++ b/fs/jbd/commit.c
@@ -20,6 +20,7 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/pagemap.h>
+#include <linux/bio.h>
 
 /*
  * Default IO end handler for temporary BJ_IO buffer_heads.
@@ -171,14 +172,15 @@ static int journal_write_commit_record(journal_t *journal,
 	return (ret == -EIO);
 }
 
-static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
+static void journal_do_submit_data(struct buffer_head **wbuf, int bufs,
+				   int write_op)
 {
 	int i;
 
 	for (i = 0; i < bufs; i++) {
 		wbuf[i]->b_end_io = end_buffer_write_sync;
 		/* We use-up our safety reference in submit_bh() */
-		submit_bh(WRITE, wbuf[i]);
+		submit_bh(write_op, wbuf[i]);
 	}
 }
 
@@ -186,7 +188,8 @@ static void journal_do_submit_data(struct buffer_head **wbuf, int bufs)
  *  Submit all the data buffers to disk
  */
 static int journal_submit_data_buffers(journal_t *journal,
-				transaction_t *commit_transaction)
+				       transaction_t *commit_transaction,
+				       int write_op)
 {
 	struct journal_head *jh;
 	struct buffer_head *bh;
@@ -225,7 +228,7 @@ write_out_data:
 				BUFFER_TRACE(bh, "needs blocking lock");
 				spin_unlock(&journal->j_list_lock);
 				/* Write out all data to prevent deadlocks */
-				journal_do_submit_data(wbuf, bufs);
+				journal_do_submit_data(wbuf, bufs, write_op);
 				bufs = 0;
 				lock_buffer(bh);
 				spin_lock(&journal->j_list_lock);
@@ -256,7 +259,7 @@ write_out_data:
 			jbd_unlock_bh_state(bh);
 			if (bufs == journal->j_wbufsize) {
 				spin_unlock(&journal->j_list_lock);
-				journal_do_submit_data(wbuf, bufs);
+				journal_do_submit_data(wbuf, bufs, write_op);
 				bufs = 0;
 				goto write_out_data;
 			}
@@ -286,7 +289,7 @@ write_out_data:
 		}
 	}
 	spin_unlock(&journal->j_list_lock);
-	journal_do_submit_data(wbuf, bufs);
+	journal_do_submit_data(wbuf, bufs, write_op);
 
 	return err;
 }
@@ -315,6 +318,7 @@ void journal_commit_transaction(journal_t *journal)
 	int first_tag = 0;
 	int tag_flag;
 	int i;
+	int write_op = WRITE;
 
 	/*
 	 * First job: lock down the current transaction and wait for
@@ -347,6 +351,8 @@ void journal_commit_transaction(journal_t *journal)
 	spin_lock(&journal->j_state_lock);
 	commit_transaction->t_state = T_LOCKED;
 
+	if (commit_transaction->t_synchronous_commit)
+		write_op = WRITE_SYNC;
 	spin_lock(&commit_transaction->t_handle_lock);
 	while (commit_transaction->t_updates) {
 		DEFINE_WAIT(wait);
@@ -431,7 +437,8 @@ void journal_commit_transaction(journal_t *journal)
 	 * Now start flushing things to disk, in the order they appear
 	 * on the transaction lists.  Data blocks go first.
 	 */
-	err = journal_submit_data_buffers(journal, commit_transaction);
+	err = journal_submit_data_buffers(journal, commit_transaction,
+					  write_op);
 
 	/*
 	 * Wait for all previously submitted IO to complete.
@@ -660,7 +667,7 @@ start_journal_io:
 				clear_buffer_dirty(bh);
 				set_buffer_uptodate(bh);
 				bh->b_end_io = journal_end_buffer_io_sync;
-				submit_bh(WRITE, bh);
+				submit_bh(write_op, bh);
 			}
 			cond_resched();
 
diff --git a/fs/jbd/journal.c b/fs/jbd/journal.c
index e79c07812afa..737f7246a4b5 100644
--- a/fs/jbd/journal.c
+++ b/fs/jbd/journal.c
@@ -637,6 +637,8 @@ struct journal_head *journal_get_descriptor_buffer(journal_t *journal)
 		return NULL;
 
 	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
+	if (!bh)
+		return NULL;
 	lock_buffer(bh);
 	memset(bh->b_data, 0, journal->j_blocksize);
 	set_buffer_uptodate(bh);
@@ -733,9 +735,7 @@ journal_t * journal_init_dev(struct block_device *bdev,
 	if (!journal->j_wbuf) {
 		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
 			__func__);
-		kfree(journal);
-		journal = NULL;
-		goto out;
+		goto out_err;
 	}
 	journal->j_dev = bdev;
 	journal->j_fs_dev = fs_dev;
@@ -743,11 +743,19 @@ journal_t * journal_init_dev(struct block_device *bdev,
 	journal->j_maxlen = len;
 
 	bh = __getblk(journal->j_dev, start, journal->j_blocksize);
-	J_ASSERT(bh != NULL);
+	if (!bh) {
+		printk(KERN_ERR
+		       "%s: Cannot get buffer for journal superblock\n",
+		       __func__);
+		goto out_err;
+	}
 	journal->j_sb_buffer = bh;
 	journal->j_superblock = (journal_superblock_t *)bh->b_data;
-out:
+
 	return journal;
+out_err:
+	kfree(journal);
+	return NULL;
 }
 
 /**
@@ -787,8 +795,7 @@ journal_t * journal_init_inode (struct inode *inode)
 	if (!journal->j_wbuf) {
 		printk(KERN_ERR "%s: Cant allocate bhs for commit thread\n",
 			__func__);
-		kfree(journal);
-		return NULL;
+		goto out_err;
 	}
 
 	err = journal_bmap(journal, 0, &blocknr);
@@ -796,16 +803,23 @@ journal_t * journal_init_inode (struct inode *inode)
 	if (err) {
 		printk(KERN_ERR "%s: Cannnot locate journal superblock\n",
 		       __func__);
-		kfree(journal);
-		return NULL;
+		goto out_err;
 	}
 
 	bh = __getblk(journal->j_dev, blocknr, journal->j_blocksize);
-	J_ASSERT(bh != NULL);
+	if (!bh) {
+		printk(KERN_ERR
+		       "%s: Cannot get buffer for journal superblock\n",
+		       __func__);
+		goto out_err;
+	}
 	journal->j_sb_buffer = bh;
 	journal->j_superblock = (journal_superblock_t *)bh->b_data;
 
 	return journal;
+out_err:
+	kfree(journal);
+	return NULL;
 }
 
 /*
diff --git a/fs/jbd/transaction.c b/fs/jbd/transaction.c
index e6a117431277..ed886e6db399 100644
--- a/fs/jbd/transaction.c
+++ b/fs/jbd/transaction.c
@@ -1440,6 +1440,8 @@ int journal_stop(handle_t *handle)
 		}
 	}
 
+	if (handle->h_sync)
+		transaction->t_synchronous_commit = 1;
 	current->journal_info = NULL;
 	spin_lock(&journal->j_state_lock);
 	spin_lock(&transaction->t_handle_lock);
diff --git a/fs/jffs2/acl.c b/fs/jffs2/acl.c
index d98713777a1b..77ccf8cb0823 100644
--- a/fs/jffs2/acl.c
+++ b/fs/jffs2/acl.c
@@ -336,7 +336,7 @@ int jffs2_init_acl_pre(struct inode *dir_i, struct inode *inode, int *i_mode)
 		return PTR_ERR(acl);
 
 	if (!acl) {
-		*i_mode &= ~current->fs->umask;
+		*i_mode &= ~current_umask();
 	} else {
 		if (S_ISDIR(*i_mode))
 			jffs2_iset_acl(inode, &f->i_acl_default, acl);
diff --git a/fs/jfs/acl.c b/fs/jfs/acl.c
index a166c1669e82..06ca1b8d2054 100644
--- a/fs/jfs/acl.c
+++ b/fs/jfs/acl.c
@@ -182,7 +182,7 @@ int jfs_init_acl(tid_t tid, struct inode *inode, struct inode *dir)
 cleanup:
 		posix_acl_release(acl);
 	} else
-		inode->i_mode &= ~current->fs->umask;
+		inode->i_mode &= ~current_umask();
 
 	JFS_IP(inode)->mode2 = (JFS_IP(inode)->mode2 & 0xffff0000) |
 			       inode->i_mode;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index 618865b3128b..daad3c2740db 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -321,15 +321,20 @@ out:
 
 static int minix_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
-	struct minix_sb_info *sbi = minix_sb(dentry->d_sb);
-	buf->f_type = dentry->d_sb->s_magic;
-	buf->f_bsize = dentry->d_sb->s_blocksize;
+	struct super_block *sb = dentry->d_sb;
+	struct minix_sb_info *sbi = minix_sb(sb);
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
+	buf->f_type = sb->s_magic;
+	buf->f_bsize = sb->s_blocksize;
 	buf->f_blocks = (sbi->s_nzones - sbi->s_firstdatazone) << sbi->s_log_zone_size;
 	buf->f_bfree = minix_count_free_blocks(sbi);
 	buf->f_bavail = buf->f_bfree;
 	buf->f_files = sbi->s_ninodes;
 	buf->f_ffree = minix_count_free_inodes(sbi);
 	buf->f_namelen = sbi->s_namelen;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
+
 	return 0;
 }
 
diff --git a/fs/mpage.c b/fs/mpage.c
index 16c3ef37eae3..680ba60863ff 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -82,7 +82,7 @@ static void mpage_end_io_write(struct bio *bio, int err)
 	bio_put(bio);
 }
 
-struct bio *mpage_bio_submit(int rw, struct bio *bio)
+static struct bio *mpage_bio_submit(int rw, struct bio *bio)
 {
 	bio->bi_end_io = mpage_end_io_read;
 	if (rw == WRITE)
@@ -90,7 +90,6 @@ struct bio *mpage_bio_submit(int rw, struct bio *bio)
 	submit_bio(rw, bio);
 	return NULL;
 }
-EXPORT_SYMBOL(mpage_bio_submit);
 
 static struct bio *
 mpage_alloc(struct block_device *bdev,
@@ -439,7 +438,14 @@ EXPORT_SYMBOL(mpage_readpage);
  * just allocate full-size (16-page) BIOs.
  */
 
-int __mpage_writepage(struct page *page, struct writeback_control *wbc,
+struct mpage_data {
+	struct bio *bio;
+	sector_t last_block_in_bio;
+	get_block_t *get_block;
+	unsigned use_writepage;
+};
+
+static int __mpage_writepage(struct page *page, struct writeback_control *wbc,
 		      void *data)
 {
 	struct mpage_data *mpd = data;
@@ -648,7 +654,6 @@ out:
 	mpd->bio = bio;
 	return ret;
 }
-EXPORT_SYMBOL(__mpage_writepage);
 
 /**
  * mpage_writepages - walk the list of dirty pages of the given address space & writepage() all of them
diff --git a/fs/namei.c b/fs/namei.c
index d040ce11785d..b8433ebfae05 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -32,6 +32,7 @@
 #include <linux/file.h>
 #include <linux/fcntl.h>
 #include <linux/device_cgroup.h>
+#include <linux/fs_struct.h>
 #include <asm/uaccess.h>
 
 #define ACC_MODE(x) ("\000\004\002\006"[(x)&O_ACCMODE])
@@ -1578,7 +1579,7 @@ static int __open_namei_create(struct nameidata *nd, struct path *path,
 	struct dentry *dir = nd->path.dentry;
 
 	if (!IS_POSIXACL(dir->d_inode))
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 	error = security_path_mknod(&nd->path, path->dentry, mode, 0);
 	if (error)
 		goto out_unlock;
@@ -1989,7 +1990,7 @@ SYSCALL_DEFINE4(mknodat, int, dfd, const char __user *, filename, int, mode,
 		goto out_unlock;
 	}
 	if (!IS_POSIXACL(nd.path.dentry->d_inode))
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 	error = may_mknod(mode);
 	if (error)
 		goto out_dput;
@@ -2067,7 +2068,7 @@ SYSCALL_DEFINE3(mkdirat, int, dfd, const char __user *, pathname, int, mode)
 		goto out_unlock;
 
 	if (!IS_POSIXACL(nd.path.dentry->d_inode))
-		mode &= ~current->fs->umask;
+		mode &= ~current_umask();
 	error = mnt_want_write(nd.path.mnt);
 	if (error)
 		goto out_dput;
@@ -2897,10 +2898,3 @@ EXPORT_SYMBOL(vfs_symlink);
 EXPORT_SYMBOL(vfs_unlink);
 EXPORT_SYMBOL(dentry_unhash);
 EXPORT_SYMBOL(generic_readlink);
-
-/* to be mentioned only in INIT_TASK */
-struct fs_struct init_fs = {
-	.count		= ATOMIC_INIT(1),
-	.lock		= __RW_LOCK_UNLOCKED(init_fs.lock),
-	.umask		= 0022,
-};
diff --git a/fs/namespace.c b/fs/namespace.c
index 0a42e0e96027..c6f54e4c4290 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -27,6 +27,7 @@
 #include <linux/ramfs.h>
 #include <linux/log2.h>
 #include <linux/idr.h>
+#include <linux/fs_struct.h>
 #include <asm/uaccess.h>
 #include <asm/unistd.h>
 #include "pnode.h"
@@ -2093,66 +2094,6 @@ out1:
 }
 
 /*
- * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values.
- * It can block. Requires the big lock held.
- */
-void set_fs_root(struct fs_struct *fs, struct path *path)
-{
-	struct path old_root;
-
-	write_lock(&fs->lock);
-	old_root = fs->root;
-	fs->root = *path;
-	path_get(path);
-	write_unlock(&fs->lock);
-	if (old_root.dentry)
-		path_put(&old_root);
-}
-
-/*
- * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values.
- * It can block. Requires the big lock held.
- */
-void set_fs_pwd(struct fs_struct *fs, struct path *path)
-{
-	struct path old_pwd;
-
-	write_lock(&fs->lock);
-	old_pwd = fs->pwd;
-	fs->pwd = *path;
-	path_get(path);
-	write_unlock(&fs->lock);
-
-	if (old_pwd.dentry)
-		path_put(&old_pwd);
-}
-
-static void chroot_fs_refs(struct path *old_root, struct path *new_root)
-{
-	struct task_struct *g, *p;
-	struct fs_struct *fs;
-
-	read_lock(&tasklist_lock);
-	do_each_thread(g, p) {
-		task_lock(p);
-		fs = p->fs;
-		if (fs) {
-			atomic_inc(&fs->count);
-			task_unlock(p);
-			if (fs->root.dentry == old_root->dentry
-			    && fs->root.mnt == old_root->mnt)
-				set_fs_root(fs, new_root);
-			if (fs->pwd.dentry == old_root->dentry
-			    && fs->pwd.mnt == old_root->mnt)
-				set_fs_pwd(fs, new_root);
-			put_fs_struct(fs);
-		} else
-			task_unlock(p);
-	} while_each_thread(g, p);
-	read_unlock(&tasklist_lock);
-}
-
-/*
  * pivot_root Semantics:
  * Moves the root file system of the current process to the directory put_old,
  * makes new_root as the new root file system of the current process, and sets
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index 36fe20d6eba2..e67f3ec07736 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -84,3 +84,11 @@ config ROOT_NFS
 	  <file:Documentation/filesystems/nfsroot.txt>.
 
 	  Most people say N here.
+
+config NFS_FSCACHE
+	bool "Provide NFS client caching support (EXPERIMENTAL)"
+	depends on EXPERIMENTAL
+	depends on NFS_FS=m && FSCACHE || NFS_FS=y && FSCACHE=y
+	help
+	  Say Y here if you want NFS data to be cached locally on disc through
+	  the general filesystem cache manager
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index ac6170c594a3..845159814de2 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -15,3 +15,4 @@ nfs-$(CONFIG_NFS_V4)	+= nfs4proc.o nfs4xdr.o nfs4state.o nfs4renewd.o \
 			   callback.o callback_xdr.o callback_proc.o \
 			   nfs4namespace.o
 nfs-$(CONFIG_SYSCTL) += sysctl.o
+nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index aba38017bdef..75c9cd2aa119 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -45,6 +45,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_CLIENT
 
@@ -154,6 +155,8 @@ static struct nfs_client *nfs_alloc_client(const struct nfs_client_initdata *cl_
 	if (!IS_ERR(cred))
 		clp->cl_machine_cred = cred;
 
+	nfs_fscache_get_client_cookie(clp);
+
 	return clp;
 
 error_3:
@@ -187,6 +190,8 @@ static void nfs_free_client(struct nfs_client *clp)
 
 	nfs4_shutdown_client(clp);
 
+	nfs_fscache_release_client_cookie(clp);
+
 	/* -EIO all pending I/O */
 	if (!IS_ERR(clp->cl_rpcclient))
 		rpc_shutdown_client(clp->cl_rpcclient);
@@ -760,6 +765,7 @@ static int nfs_init_server(struct nfs_server *server,
 
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
+	server->options = data->options;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1148,6 +1154,7 @@ static int nfs4_init_server(struct nfs_server *server,
 	/* Initialise the client representation from the mount data */
 	server->flags = data->flags;
 	server->caps |= NFS_CAP_ATOMIC_OPEN;
+	server->options = data->options;
 
 	/* Get a client record */
 	error = nfs4_set_client(server,
@@ -1559,7 +1566,7 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 
 	/* display header on line 1 */
 	if (v == &nfs_volume_list) {
-		seq_puts(m, "NV SERVER   PORT DEV     FSID\n");
+		seq_puts(m, "NV SERVER   PORT DEV     FSID              FSC\n");
 		return 0;
 	}
 	/* display one transport per line on subsequent lines */
@@ -1573,12 +1580,13 @@ static int nfs_volume_list_show(struct seq_file *m, void *v)
 		 (unsigned long long) server->fsid.major,
 		 (unsigned long long) server->fsid.minor);
 
-	seq_printf(m, "v%u %s %s %-7s %-17s\n",
+	seq_printf(m, "v%u %s %s %-7s %-17s %s\n",
 		   clp->rpc_ops->version,
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_ADDR),
 		   rpc_peeraddr2str(clp->cl_rpcclient, RPC_DISPLAY_HEX_PORT),
 		   dev,
-		   fsid);
+		   fsid,
+		   nfs_server_fscache_state(server));
 
 	return 0;
 }
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 0abf3f331f56..3523b895eb4b 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -35,6 +35,7 @@
 #include "delegation.h"
 #include "internal.h"
 #include "iostat.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_FILE
 
@@ -409,6 +410,13 @@ static int nfs_write_end(struct file *file, struct address_space *mapping,
 	return copied;
 }
 
+/*
+ * Partially or wholly invalidate a page
+ * - Release the private state associated with a page if undergoing complete
+ *   page invalidation
+ * - Called if either PG_private or PG_fscache is set on the page
+ * - Caller holds page lock
+ */
 static void nfs_invalidate_page(struct page *page, unsigned long offset)
 {
 	dfprintk(PAGECACHE, "NFS: invalidate_page(%p, %lu)\n", page, offset);
@@ -417,23 +425,43 @@ static void nfs_invalidate_page(struct page *page, unsigned long offset)
 		return;
 	/* Cancel any unstarted writes on this page */
 	nfs_wb_page_cancel(page->mapping->host, page);
+
+	nfs_fscache_invalidate_page(page, page->mapping->host);
 }
 
+/*
+ * Attempt to release the private state associated with a page
+ * - Called if either PG_private or PG_fscache is set on the page
+ * - Caller holds page lock
+ * - Return true (may release page) or false (may not)
+ */
 static int nfs_release_page(struct page *page, gfp_t gfp)
 {
 	dfprintk(PAGECACHE, "NFS: release_page(%p)\n", page);
 
 	/* If PagePrivate() is set, then the page is not freeable */
-	return 0;
+	if (PagePrivate(page))
+		return 0;
+	return nfs_fscache_release_page(page, gfp);
 }
 
+/*
+ * Attempt to clear the private state associated with a page when an error
+ * occurs that requires the cached contents of an inode to be written back or
+ * destroyed
+ * - Called if either PG_private or fscache is set on the page
+ * - Caller holds page lock
+ * - Return 0 if successful, -error otherwise
+ */
 static int nfs_launder_page(struct page *page)
 {
 	struct inode *inode = page->mapping->host;
+	struct nfs_inode *nfsi = NFS_I(inode);
 
 	dfprintk(PAGECACHE, "NFS: launder_page(%ld, %llu)\n",
 		inode->i_ino, (long long)page_offset(page));
 
+	nfs_fscache_wait_on_page_write(nfsi, page);
 	return nfs_wb_page(inode, page);
 }
 
@@ -451,6 +479,11 @@ const struct address_space_operations nfs_file_aops = {
 	.launder_page = nfs_launder_page,
 };
 
+/*
+ * Notification that a PTE pointing to an NFS page is about to be made
+ * writable, implying that someone is about to modify the page through a
+ * shared-writable mapping
+ */
 static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
@@ -465,6 +498,9 @@ static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		filp->f_mapping->host->i_ino,
 		(long long)page_offset(page));
 
+	/* make sure the cache has finished storing the page */
+	nfs_fscache_wait_on_page_write(NFS_I(dentry->d_inode), page);
+
 	lock_page(page);
 	mapping = page->mapping;
 	if (mapping != dentry->d_inode->i_mapping)
diff --git a/fs/nfs/fscache-index.c b/fs/nfs/fscache-index.c
new file mode 100644
index 000000000000..5b1006480bc2
--- /dev/null
+++ b/fs/nfs/fscache-index.c
@@ -0,0 +1,337 @@
+/* NFS FS-Cache index structure definition
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/in6.h>
+
+#include "internal.h"
+#include "fscache.h"
+
+#define NFSDBG_FACILITY		NFSDBG_FSCACHE
+
+/*
+ * Define the NFS filesystem for FS-Cache.  Upon registration FS-Cache sticks
+ * the cookie for the top-level index object for NFS into here.  The top-level
+ * index can than have other cache objects inserted into it.
+ */
+struct fscache_netfs nfs_fscache_netfs = {
+	.name		= "nfs",
+	.version	= 0,
+};
+
+/*
+ * Register NFS for caching
+ */
+int nfs_fscache_register(void)
+{
+	return fscache_register_netfs(&nfs_fscache_netfs);
+}
+
+/*
+ * Unregister NFS for caching
+ */
+void nfs_fscache_unregister(void)
+{
+	fscache_unregister_netfs(&nfs_fscache_netfs);
+}
+
+/*
+ * Layout of the key for an NFS server cache object.
+ */
+struct nfs_server_key {
+	uint16_t	nfsversion;		/* NFS protocol version */
+	uint16_t	family;			/* address family */
+	uint16_t	port;			/* IP port */
+	union {
+		struct in_addr	ipv4_addr;	/* IPv4 address */
+		struct in6_addr ipv6_addr;	/* IPv6 address */
+	} addr[0];
+};
+
+/*
+ * Generate a key to describe a server in the main NFS index
+ * - We return the length of the key, or 0 if we can't generate one
+ */
+static uint16_t nfs_server_get_key(const void *cookie_netfs_data,
+				   void *buffer, uint16_t bufmax)
+{
+	const struct nfs_client *clp = cookie_netfs_data;
+	const struct sockaddr_in6 *sin6 = (struct sockaddr_in6 *) &clp->cl_addr;
+	const struct sockaddr_in *sin = (struct sockaddr_in *) &clp->cl_addr;
+	struct nfs_server_key *key = buffer;
+	uint16_t len = sizeof(struct nfs_server_key);
+
+	key->nfsversion = clp->rpc_ops->version;
+	key->family = clp->cl_addr.ss_family;
+
+	memset(key, 0, len);
+
+	switch (clp->cl_addr.ss_family) {
+	case AF_INET:
+		key->port = sin->sin_port;
+		key->addr[0].ipv4_addr = sin->sin_addr;
+		len += sizeof(key->addr[0].ipv4_addr);
+		break;
+
+	case AF_INET6:
+		key->port = sin6->sin6_port;
+		key->addr[0].ipv6_addr = sin6->sin6_addr;
+		len += sizeof(key->addr[0].ipv6_addr);
+		break;
+
+	default:
+		printk(KERN_WARNING "NFS: Unknown network family '%d'\n",
+		       clp->cl_addr.ss_family);
+		len = 0;
+		break;
+	}
+
+	return len;
+}
+
+/*
+ * Define the server object for FS-Cache.  This is used to describe a server
+ * object to fscache_acquire_cookie().  It is keyed by the NFS protocol and
+ * server address parameters.
+ */
+const struct fscache_cookie_def nfs_fscache_server_index_def = {
+	.name		= "NFS.server",
+	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= nfs_server_get_key,
+};
+
+/*
+ * Generate a key to describe a superblock key in the main NFS index
+ */
+static uint16_t nfs_super_get_key(const void *cookie_netfs_data,
+				  void *buffer, uint16_t bufmax)
+{
+	const struct nfs_fscache_key *key;
+	const struct nfs_server *nfss = cookie_netfs_data;
+	uint16_t len;
+
+	key = nfss->fscache_key;
+	len = sizeof(key->key) + key->key.uniq_len;
+	if (len > bufmax) {
+		len = 0;
+	} else {
+		memcpy(buffer, &key->key, sizeof(key->key));
+		memcpy(buffer + sizeof(key->key),
+		       key->key.uniquifier, key->key.uniq_len);
+	}
+
+	return len;
+}
+
+/*
+ * Define the superblock object for FS-Cache.  This is used to describe a
+ * superblock object to fscache_acquire_cookie().  It is keyed by all the NFS
+ * parameters that might cause a separate superblock.
+ */
+const struct fscache_cookie_def nfs_fscache_super_index_def = {
+	.name		= "NFS.super",
+	.type 		= FSCACHE_COOKIE_TYPE_INDEX,
+	.get_key	= nfs_super_get_key,
+};
+
+/*
+ * Definition of the auxiliary data attached to NFS inode storage objects
+ * within the cache.
+ *
+ * The contents of this struct are recorded in the on-disk local cache in the
+ * auxiliary data attached to the data storage object backing an inode.  This
+ * permits coherency to be managed when a new inode binds to an already extant
+ * cache object.
+ */
+struct nfs_fscache_inode_auxdata {
+	struct timespec	mtime;
+	struct timespec	ctime;
+	loff_t		size;
+	u64		change_attr;
+};
+
+/*
+ * Generate a key to describe an NFS inode in an NFS server's index
+ */
+static uint16_t nfs_fscache_inode_get_key(const void *cookie_netfs_data,
+					  void *buffer, uint16_t bufmax)
+{
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+	uint16_t nsize;
+
+	/* use the inode's NFS filehandle as the key */
+	nsize = nfsi->fh.size;
+	memcpy(buffer, nfsi->fh.data, nsize);
+	return nsize;
+}
+
+/*
+ * Get certain file attributes from the netfs data
+ * - This function can be absent for an index
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static void nfs_fscache_inode_get_attr(const void *cookie_netfs_data,
+				       uint64_t *size)
+{
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+
+	*size = nfsi->vfs_inode.i_size;
+}
+
+/*
+ * Get the auxiliary data from netfs data
+ * - This function can be absent if the index carries no state data
+ * - Should store the auxiliary data in the buffer
+ * - Should return the amount of amount stored
+ * - Not permitted to return an error
+ * - The netfs data from the cookie being used as the source is presented
+ */
+static uint16_t nfs_fscache_inode_get_aux(const void *cookie_netfs_data,
+					  void *buffer, uint16_t bufmax)
+{
+	struct nfs_fscache_inode_auxdata auxdata;
+	const struct nfs_inode *nfsi = cookie_netfs_data;
+
+	memset(&auxdata, 0, sizeof(auxdata));
+	auxdata.size = nfsi->vfs_inode.i_size;
+	auxdata.mtime = nfsi->vfs_inode.i_mtime;
+	auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+		auxdata.change_attr = nfsi->change_attr;
+
+	if (bufmax > sizeof(auxdata))
+		bufmax = sizeof(auxdata);
+
+	memcpy(buffer, &auxdata, bufmax);
+	return bufmax;
+}
+
+/*
+ * Consult the netfs about the state of an object
+ * - This function can be absent if the index carries no state data
+ * - The netfs data from the cookie being used as the target is
+ *   presented, as is the auxiliary data
+ */
+static
+enum fscache_checkaux nfs_fscache_inode_check_aux(void *cookie_netfs_data,
+						  const void *data,
+						  uint16_t datalen)
+{
+	struct nfs_fscache_inode_auxdata auxdata;
+	struct nfs_inode *nfsi = cookie_netfs_data;
+
+	if (datalen != sizeof(auxdata))
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	memset(&auxdata, 0, sizeof(auxdata));
+	auxdata.size = nfsi->vfs_inode.i_size;
+	auxdata.mtime = nfsi->vfs_inode.i_mtime;
+	auxdata.ctime = nfsi->vfs_inode.i_ctime;
+
+	if (NFS_SERVER(&nfsi->vfs_inode)->nfs_client->rpc_ops->version == 4)
+		auxdata.change_attr = nfsi->change_attr;
+
+	if (memcmp(data, &auxdata, datalen) != 0)
+		return FSCACHE_CHECKAUX_OBSOLETE;
+
+	return FSCACHE_CHECKAUX_OKAY;
+}
+
+/*
+ * Indication from FS-Cache that the cookie is no longer cached
+ * - This function is called when the backing store currently caching a cookie
+ *   is removed
+ * - The netfs should use this to clean up any markers indicating cached pages
+ * - This is mandatory for any object that may have data
+ */
+static void nfs_fscache_inode_now_uncached(void *cookie_netfs_data)
+{
+	struct nfs_inode *nfsi = cookie_netfs_data;
+	struct pagevec pvec;
+	pgoff_t first;
+	int loop, nr_pages;
+
+	pagevec_init(&pvec, 0);
+	first = 0;
+
+	dprintk("NFS: nfs_inode_now_uncached: nfs_inode 0x%p\n", nfsi);
+
+	for (;;) {
+		/* grab a bunch of pages to unmark */
+		nr_pages = pagevec_lookup(&pvec,
+					  nfsi->vfs_inode.i_mapping,
+					  first,
+					  PAGEVEC_SIZE - pagevec_count(&pvec));
+		if (!nr_pages)
+			break;
+
+		for (loop = 0; loop < nr_pages; loop++)
+			ClearPageFsCache(pvec.pages[loop]);
+
+		first = pvec.pages[nr_pages - 1]->index + 1;
+
+		pvec.nr = nr_pages;
+		pagevec_release(&pvec);
+		cond_resched();
+	}
+}
+
+/*
+ * Get an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ *   context.
+ * - The read context is passed back to NFS in the event that a data read on the
+ *   cache fails with EIO - in which case the server must be contacted to
+ *   retrieve the data, which requires the read context for security.
+ */
+static void nfs_fh_get_context(void *cookie_netfs_data, void *context)
+{
+	get_nfs_open_context(context);
+}
+
+/*
+ * Release an extra reference on a read context.
+ * - This function can be absent if the completion function doesn't require a
+ *   context.
+ */
+static void nfs_fh_put_context(void *cookie_netfs_data, void *context)
+{
+	if (context)
+		put_nfs_open_context(context);
+}
+
+/*
+ * Define the inode object for FS-Cache.  This is used to describe an inode
+ * object to fscache_acquire_cookie().  It is keyed by the NFS file handle for
+ * an inode.
+ *
+ * Coherency is managed by comparing the copies of i_size, i_mtime and i_ctime
+ * held in the cache auxiliary data for the data storage object with those in
+ * the inode struct in memory.
+ */
+const struct fscache_cookie_def nfs_fscache_inode_object_def = {
+	.name		= "NFS.fh",
+	.type		= FSCACHE_COOKIE_TYPE_DATAFILE,
+	.get_key	= nfs_fscache_inode_get_key,
+	.get_attr	= nfs_fscache_inode_get_attr,
+	.get_aux	= nfs_fscache_inode_get_aux,
+	.check_aux	= nfs_fscache_inode_check_aux,
+	.now_uncached	= nfs_fscache_inode_now_uncached,
+	.get_context	= nfs_fh_get_context,
+	.put_context	= nfs_fh_put_context,
+};
diff --git a/fs/nfs/fscache.c b/fs/nfs/fscache.c
new file mode 100644
index 000000000000..379be678cb7e
--- /dev/null
+++ b/fs/nfs/fscache.c
@@ -0,0 +1,523 @@
+/* NFS filesystem cache interface
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_fs_sb.h>
+#include <linux/in6.h>
+#include <linux/seq_file.h>
+
+#include "internal.h"
+#include "iostat.h"
+#include "fscache.h"
+
+#define NFSDBG_FACILITY		NFSDBG_FSCACHE
+
+static struct rb_root nfs_fscache_keys = RB_ROOT;
+static DEFINE_SPINLOCK(nfs_fscache_keys_lock);
+
+/*
+ * Get the per-client index cookie for an NFS client if the appropriate mount
+ * flag was set
+ * - We always try and get an index cookie for the client, but get filehandle
+ *   cookies on a per-superblock basis, depending on the mount flags
+ */
+void nfs_fscache_get_client_cookie(struct nfs_client *clp)
+{
+	/* create a cache index for looking up filehandles */
+	clp->fscache = fscache_acquire_cookie(nfs_fscache_netfs.primary_index,
+					      &nfs_fscache_server_index_def,
+					      clp);
+	dfprintk(FSCACHE, "NFS: get client cookie (0x%p/0x%p)\n",
+		 clp, clp->fscache);
+}
+
+/*
+ * Dispose of a per-client cookie
+ */
+void nfs_fscache_release_client_cookie(struct nfs_client *clp)
+{
+	dfprintk(FSCACHE, "NFS: releasing client cookie (0x%p/0x%p)\n",
+		 clp, clp->fscache);
+
+	fscache_relinquish_cookie(clp->fscache, 0);
+	clp->fscache = NULL;
+}
+
+/*
+ * Get the cache cookie for an NFS superblock.  We have to handle
+ * uniquification here because the cache doesn't do it for us.
+ */
+void nfs_fscache_get_super_cookie(struct super_block *sb,
+				  struct nfs_parsed_mount_data *data)
+{
+	struct nfs_fscache_key *key, *xkey;
+	struct nfs_server *nfss = NFS_SB(sb);
+	struct rb_node **p, *parent;
+	const char *uniq = data->fscache_uniq ?: "";
+	int diff, ulen;
+
+	ulen = strlen(uniq);
+	key = kzalloc(sizeof(*key) + ulen, GFP_KERNEL);
+	if (!key)
+		return;
+
+	key->nfs_client = nfss->nfs_client;
+	key->key.super.s_flags = sb->s_flags & NFS_MS_MASK;
+	key->key.nfs_server.flags = nfss->flags;
+	key->key.nfs_server.rsize = nfss->rsize;
+	key->key.nfs_server.wsize = nfss->wsize;
+	key->key.nfs_server.acregmin = nfss->acregmin;
+	key->key.nfs_server.acregmax = nfss->acregmax;
+	key->key.nfs_server.acdirmin = nfss->acdirmin;
+	key->key.nfs_server.acdirmax = nfss->acdirmax;
+	key->key.nfs_server.fsid = nfss->fsid;
+	key->key.rpc_auth.au_flavor = nfss->client->cl_auth->au_flavor;
+
+	key->key.uniq_len = ulen;
+	memcpy(key->key.uniquifier, uniq, ulen);
+
+	spin_lock(&nfs_fscache_keys_lock);
+	p = &nfs_fscache_keys.rb_node;
+	parent = NULL;
+	while (*p) {
+		parent = *p;
+		xkey = rb_entry(parent, struct nfs_fscache_key, node);
+
+		if (key->nfs_client < xkey->nfs_client)
+			goto go_left;
+		if (key->nfs_client > xkey->nfs_client)
+			goto go_right;
+
+		diff = memcmp(&key->key, &xkey->key, sizeof(key->key));
+		if (diff < 0)
+			goto go_left;
+		if (diff > 0)
+			goto go_right;
+
+		if (key->key.uniq_len == 0)
+			goto non_unique;
+		diff = memcmp(key->key.uniquifier,
+			      xkey->key.uniquifier,
+			      key->key.uniq_len);
+		if (diff < 0)
+			goto go_left;
+		if (diff > 0)
+			goto go_right;
+		goto non_unique;
+
+	go_left:
+		p = &(*p)->rb_left;
+		continue;
+	go_right:
+		p = &(*p)->rb_right;
+	}
+
+	rb_link_node(&key->node, parent, p);
+	rb_insert_color(&key->node, &nfs_fscache_keys);
+	spin_unlock(&nfs_fscache_keys_lock);
+	nfss->fscache_key = key;
+
+	/* create a cache index for looking up filehandles */
+	nfss->fscache = fscache_acquire_cookie(nfss->nfs_client->fscache,
+					       &nfs_fscache_super_index_def,
+					       nfss);
+	dfprintk(FSCACHE, "NFS: get superblock cookie (0x%p/0x%p)\n",
+		 nfss, nfss->fscache);
+	return;
+
+non_unique:
+	spin_unlock(&nfs_fscache_keys_lock);
+	kfree(key);
+	nfss->fscache_key = NULL;
+	nfss->fscache = NULL;
+	printk(KERN_WARNING "NFS:"
+	       " Cache request denied due to non-unique superblock keys\n");
+}
+
+/*
+ * release a per-superblock cookie
+ */
+void nfs_fscache_release_super_cookie(struct super_block *sb)
+{
+	struct nfs_server *nfss = NFS_SB(sb);
+
+	dfprintk(FSCACHE, "NFS: releasing superblock cookie (0x%p/0x%p)\n",
+		 nfss, nfss->fscache);
+
+	fscache_relinquish_cookie(nfss->fscache, 0);
+	nfss->fscache = NULL;
+
+	if (nfss->fscache_key) {
+		spin_lock(&nfs_fscache_keys_lock);
+		rb_erase(&nfss->fscache_key->node, &nfs_fscache_keys);
+		spin_unlock(&nfs_fscache_keys_lock);
+		kfree(nfss->fscache_key);
+		nfss->fscache_key = NULL;
+	}
+}
+
+/*
+ * Initialise the per-inode cache cookie pointer for an NFS inode.
+ */
+void nfs_fscache_init_inode_cookie(struct inode *inode)
+{
+	NFS_I(inode)->fscache = NULL;
+	if (S_ISREG(inode->i_mode))
+		set_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
+/*
+ * Get the per-inode cache cookie for an NFS inode.
+ */
+static void nfs_fscache_enable_inode_cookie(struct inode *inode)
+{
+	struct super_block *sb = inode->i_sb;
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	if (nfsi->fscache || !NFS_FSCACHE(inode))
+		return;
+
+	if ((NFS_SB(sb)->options & NFS_OPTION_FSCACHE)) {
+		nfsi->fscache = fscache_acquire_cookie(
+			NFS_SB(sb)->fscache,
+			&nfs_fscache_inode_object_def,
+			nfsi);
+
+		dfprintk(FSCACHE, "NFS: get FH cookie (0x%p/0x%p/0x%p)\n",
+			 sb, nfsi, nfsi->fscache);
+	}
+}
+
+/*
+ * Release a per-inode cookie.
+ */
+void nfs_fscache_release_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	dfprintk(FSCACHE, "NFS: clear cookie (0x%p/0x%p)\n",
+		 nfsi, nfsi->fscache);
+
+	fscache_relinquish_cookie(nfsi->fscache, 0);
+	nfsi->fscache = NULL;
+}
+
+/*
+ * Retire a per-inode cookie, destroying the data attached to it.
+ */
+void nfs_fscache_zap_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	dfprintk(FSCACHE, "NFS: zapping cookie (0x%p/0x%p)\n",
+		 nfsi, nfsi->fscache);
+
+	fscache_relinquish_cookie(nfsi->fscache, 1);
+	nfsi->fscache = NULL;
+}
+
+/*
+ * Turn off the cache with regard to a per-inode cookie if opened for writing,
+ * invalidating all the pages in the page cache relating to the associated
+ * inode to clear the per-page caching.
+ */
+static void nfs_fscache_disable_inode_cookie(struct inode *inode)
+{
+	clear_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+
+	if (NFS_I(inode)->fscache) {
+		dfprintk(FSCACHE,
+			 "NFS: nfsi 0x%p turning cache off\n", NFS_I(inode));
+
+		/* Need to invalidate any mapped pages that were read in before
+		 * turning off the cache.
+		 */
+		if (inode->i_mapping && inode->i_mapping->nrpages)
+			invalidate_inode_pages2(inode->i_mapping);
+
+		nfs_fscache_zap_inode_cookie(inode);
+	}
+}
+
+/*
+ * wait_on_bit() sleep function for uninterruptible waiting
+ */
+static int nfs_fscache_wait_bit(void *flags)
+{
+	schedule();
+	return 0;
+}
+
+/*
+ * Lock against someone else trying to also acquire or relinquish a cookie
+ */
+static inline void nfs_fscache_inode_lock(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	while (test_and_set_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags))
+		wait_on_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK,
+			    nfs_fscache_wait_bit, TASK_UNINTERRUPTIBLE);
+}
+
+/*
+ * Unlock cookie management lock
+ */
+static inline void nfs_fscache_inode_unlock(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+
+	smp_mb__before_clear_bit();
+	clear_bit(NFS_INO_FSCACHE_LOCK, &nfsi->flags);
+	smp_mb__after_clear_bit();
+	wake_up_bit(&nfsi->flags, NFS_INO_FSCACHE_LOCK);
+}
+
+/*
+ * Decide if we should enable or disable local caching for this inode.
+ * - For now, with NFS, only regular files that are open read-only will be able
+ *   to use the cache.
+ * - May be invoked multiple times in parallel by parallel nfs_open() functions.
+ */
+void nfs_fscache_set_inode_cookie(struct inode *inode, struct file *filp)
+{
+	if (NFS_FSCACHE(inode)) {
+		nfs_fscache_inode_lock(inode);
+		if ((filp->f_flags & O_ACCMODE) != O_RDONLY)
+			nfs_fscache_disable_inode_cookie(inode);
+		else
+			nfs_fscache_enable_inode_cookie(inode);
+		nfs_fscache_inode_unlock(inode);
+	}
+}
+
+/*
+ * Replace a per-inode cookie due to revalidation detecting a file having
+ * changed on the server.
+ */
+void nfs_fscache_reset_inode_cookie(struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct nfs_server *nfss = NFS_SERVER(inode);
+	struct fscache_cookie *old = nfsi->fscache;
+
+	nfs_fscache_inode_lock(inode);
+	if (nfsi->fscache) {
+		/* retire the current fscache cache and get a new one */
+		fscache_relinquish_cookie(nfsi->fscache, 1);
+
+		nfsi->fscache = fscache_acquire_cookie(
+			nfss->nfs_client->fscache,
+			&nfs_fscache_inode_object_def,
+			nfsi);
+
+		dfprintk(FSCACHE,
+			 "NFS: revalidation new cookie (0x%p/0x%p/0x%p/0x%p)\n",
+			 nfss, nfsi, old, nfsi->fscache);
+	}
+	nfs_fscache_inode_unlock(inode);
+}
+
+/*
+ * Release the caching state associated with a page, if the page isn't busy
+ * interacting with the cache.
+ * - Returns true (can release page) or false (page busy).
+ */
+int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	struct nfs_inode *nfsi = NFS_I(page->mapping->host);
+	struct fscache_cookie *cookie = nfsi->fscache;
+
+	BUG_ON(!cookie);
+
+	if (fscache_check_page_write(cookie, page)) {
+		if (!(gfp & __GFP_WAIT))
+			return 0;
+		fscache_wait_on_page_write(cookie, page);
+	}
+
+	if (PageFsCache(page)) {
+		dfprintk(FSCACHE, "NFS: fscache releasepage (0x%p/0x%p/0x%p)\n",
+			 cookie, page, nfsi);
+
+		fscache_uncache_page(cookie, page);
+		nfs_add_fscache_stats(page->mapping->host,
+				      NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+	}
+
+	return 1;
+}
+
+/*
+ * Release the caching state associated with a page if undergoing complete page
+ * invalidation.
+ */
+void __nfs_fscache_invalidate_page(struct page *page, struct inode *inode)
+{
+	struct nfs_inode *nfsi = NFS_I(inode);
+	struct fscache_cookie *cookie = nfsi->fscache;
+
+	BUG_ON(!cookie);
+
+	dfprintk(FSCACHE, "NFS: fscache invalidatepage (0x%p/0x%p/0x%p)\n",
+		 cookie, page, nfsi);
+
+	fscache_wait_on_page_write(cookie, page);
+
+	BUG_ON(!PageLocked(page));
+	fscache_uncache_page(cookie, page);
+	nfs_add_fscache_stats(page->mapping->host,
+			      NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+}
+
+/*
+ * Handle completion of a page being read from the cache.
+ * - Called in process (keventd) context.
+ */
+static void nfs_readpage_from_fscache_complete(struct page *page,
+					       void *context,
+					       int error)
+{
+	dfprintk(FSCACHE,
+		 "NFS: readpage_from_fscache_complete (0x%p/0x%p/%d)\n",
+		 page, context, error);
+
+	/* if the read completes with an error, we just unlock the page and let
+	 * the VM reissue the readpage */
+	if (!error) {
+		SetPageUptodate(page);
+		unlock_page(page);
+	} else {
+		error = nfs_readpage_async(context, page->mapping->host, page);
+		if (error)
+			unlock_page(page);
+	}
+}
+
+/*
+ * Retrieve a page from fscache
+ */
+int __nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+				struct inode *inode, struct page *page)
+{
+	int ret;
+
+	dfprintk(FSCACHE,
+		 "NFS: readpage_from_fscache(fsc:%p/p:%p(i:%lx f:%lx)/0x%p)\n",
+		 NFS_I(inode)->fscache, page, page->index, page->flags, inode);
+
+	ret = fscache_read_or_alloc_page(NFS_I(inode)->fscache,
+					 page,
+					 nfs_readpage_from_fscache_complete,
+					 ctx,
+					 GFP_KERNEL);
+
+	switch (ret) {
+	case 0: /* read BIO submitted (page in fscache) */
+		dfprintk(FSCACHE,
+			 "NFS:    readpage_from_fscache: BIO submitted\n");
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK, 1);
+		return ret;
+
+	case -ENOBUFS: /* inode not in cache */
+	case -ENODATA: /* page not in cache */
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
+		dfprintk(FSCACHE,
+			 "NFS:    readpage_from_fscache %d\n", ret);
+		return 1;
+
+	default:
+		dfprintk(FSCACHE, "NFS:    readpage_from_fscache %d\n", ret);
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL, 1);
+	}
+	return ret;
+}
+
+/*
+ * Retrieve a set of pages from fscache
+ */
+int __nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+				 struct inode *inode,
+				 struct address_space *mapping,
+				 struct list_head *pages,
+				 unsigned *nr_pages)
+{
+	int ret, npages = *nr_pages;
+
+	dfprintk(FSCACHE, "NFS: nfs_getpages_from_fscache (0x%p/%u/0x%p)\n",
+		 NFS_I(inode)->fscache, npages, inode);
+
+	ret = fscache_read_or_alloc_pages(NFS_I(inode)->fscache,
+					  mapping, pages, nr_pages,
+					  nfs_readpage_from_fscache_complete,
+					  ctx,
+					  mapping_gfp_mask(mapping));
+	if (*nr_pages < npages)
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_OK,
+				      npages);
+	if (*nr_pages > 0)
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_READ_FAIL,
+				      *nr_pages);
+
+	switch (ret) {
+	case 0: /* read submitted to the cache for all pages */
+		BUG_ON(!list_empty(pages));
+		BUG_ON(*nr_pages != 0);
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: submitted\n");
+
+		return ret;
+
+	case -ENOBUFS: /* some pages aren't cached and can't be */
+	case -ENODATA: /* some pages aren't cached */
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: no page: %d\n", ret);
+		return 1;
+
+	default:
+		dfprintk(FSCACHE,
+			 "NFS: nfs_getpages_from_fscache: ret  %d\n", ret);
+	}
+
+	return ret;
+}
+
+/*
+ * Store a newly fetched page in fscache
+ * - PG_fscache must be set on the page
+ */
+void __nfs_readpage_to_fscache(struct inode *inode, struct page *page, int sync)
+{
+	int ret;
+
+	dfprintk(FSCACHE,
+		 "NFS: readpage_to_fscache(fsc:%p/p:%p(i:%lx f:%lx)/%d)\n",
+		 NFS_I(inode)->fscache, page, page->index, page->flags, sync);
+
+	ret = fscache_write_page(NFS_I(inode)->fscache, page, GFP_KERNEL);
+	dfprintk(FSCACHE,
+		 "NFS:     readpage_to_fscache: p:%p(i:%lu f:%lx) ret %d\n",
+		 page, page->index, page->flags, ret);
+
+	if (ret != 0) {
+		fscache_uncache_page(NFS_I(inode)->fscache, page);
+		nfs_add_fscache_stats(inode,
+				      NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL, 1);
+		nfs_add_fscache_stats(inode, NFSIOS_FSCACHE_PAGES_UNCACHED, 1);
+	} else {
+		nfs_add_fscache_stats(inode,
+				      NFSIOS_FSCACHE_PAGES_WRITTEN_OK, 1);
+	}
+}
diff --git a/fs/nfs/fscache.h b/fs/nfs/fscache.h
new file mode 100644
index 000000000000..6e809bb0ff08
--- /dev/null
+++ b/fs/nfs/fscache.h
@@ -0,0 +1,220 @@
+/* NFS filesystem cache interface definitions
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#ifndef _NFS_FSCACHE_H
+#define _NFS_FSCACHE_H
+
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/nfs4_mount.h>
+#include <linux/fscache.h>
+
+#ifdef CONFIG_NFS_FSCACHE
+
+/*
+ * set of NFS FS-Cache objects that form a superblock key
+ */
+struct nfs_fscache_key {
+	struct rb_node		node;
+	struct nfs_client	*nfs_client;	/* the server */
+
+	/* the elements of the unique key - as used by nfs_compare_super() and
+	 * nfs_compare_mount_options() to distinguish superblocks */
+	struct {
+		struct {
+			unsigned long	s_flags;	/* various flags
+							 * (& NFS_MS_MASK) */
+		} super;
+
+		struct {
+			struct nfs_fsid fsid;
+			int		flags;
+			unsigned int	rsize;		/* read size */
+			unsigned int	wsize;		/* write size */
+			unsigned int	acregmin;	/* attr cache timeouts */
+			unsigned int	acregmax;
+			unsigned int	acdirmin;
+			unsigned int	acdirmax;
+		} nfs_server;
+
+		struct {
+			rpc_authflavor_t au_flavor;
+		} rpc_auth;
+
+		/* uniquifier - can be used if nfs_server.flags includes
+		 * NFS_MOUNT_UNSHARED  */
+		u8 uniq_len;
+		char uniquifier[0];
+	} key;
+};
+
+/*
+ * fscache-index.c
+ */
+extern struct fscache_netfs nfs_fscache_netfs;
+extern const struct fscache_cookie_def nfs_fscache_server_index_def;
+extern const struct fscache_cookie_def nfs_fscache_super_index_def;
+extern const struct fscache_cookie_def nfs_fscache_inode_object_def;
+
+extern int nfs_fscache_register(void);
+extern void nfs_fscache_unregister(void);
+
+/*
+ * fscache.c
+ */
+extern void nfs_fscache_get_client_cookie(struct nfs_client *);
+extern void nfs_fscache_release_client_cookie(struct nfs_client *);
+
+extern void nfs_fscache_get_super_cookie(struct super_block *,
+					 struct nfs_parsed_mount_data *);
+extern void nfs_fscache_release_super_cookie(struct super_block *);
+
+extern void nfs_fscache_init_inode_cookie(struct inode *);
+extern void nfs_fscache_release_inode_cookie(struct inode *);
+extern void nfs_fscache_zap_inode_cookie(struct inode *);
+extern void nfs_fscache_set_inode_cookie(struct inode *, struct file *);
+extern void nfs_fscache_reset_inode_cookie(struct inode *);
+
+extern void __nfs_fscache_invalidate_page(struct page *, struct inode *);
+extern int nfs_fscache_release_page(struct page *, gfp_t);
+
+extern int __nfs_readpage_from_fscache(struct nfs_open_context *,
+				       struct inode *, struct page *);
+extern int __nfs_readpages_from_fscache(struct nfs_open_context *,
+					struct inode *, struct address_space *,
+					struct list_head *, unsigned *);
+extern void __nfs_readpage_to_fscache(struct inode *, struct page *, int);
+
+/*
+ * wait for a page to complete writing to the cache
+ */
+static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
+						  struct page *page)
+{
+	if (PageFsCache(page))
+		fscache_wait_on_page_write(nfsi->fscache, page);
+}
+
+/*
+ * release the caching state associated with a page if undergoing complete page
+ * invalidation
+ */
+static inline void nfs_fscache_invalidate_page(struct page *page,
+					       struct inode *inode)
+{
+	if (PageFsCache(page))
+		__nfs_fscache_invalidate_page(page, inode);
+}
+
+/*
+ * Retrieve a page from an inode data storage object.
+ */
+static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+					    struct inode *inode,
+					    struct page *page)
+{
+	if (NFS_I(inode)->fscache)
+		return __nfs_readpage_from_fscache(ctx, inode, page);
+	return -ENOBUFS;
+}
+
+/*
+ * Retrieve a set of pages from an inode data storage object.
+ */
+static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+					     struct inode *inode,
+					     struct address_space *mapping,
+					     struct list_head *pages,
+					     unsigned *nr_pages)
+{
+	if (NFS_I(inode)->fscache)
+		return __nfs_readpages_from_fscache(ctx, inode, mapping, pages,
+						    nr_pages);
+	return -ENOBUFS;
+}
+
+/*
+ * Store a page newly fetched from the server in an inode data storage object
+ * in the cache.
+ */
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+					   struct page *page,
+					   int sync)
+{
+	if (PageFsCache(page))
+		__nfs_readpage_to_fscache(inode, page, sync);
+}
+
+/*
+ * indicate the client caching state as readable text
+ */
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+	if (server->fscache && (server->options & NFS_OPTION_FSCACHE))
+		return "yes";
+	return "no ";
+}
+
+
+#else /* CONFIG_NFS_FSCACHE */
+static inline int nfs_fscache_register(void) { return 0; }
+static inline void nfs_fscache_unregister(void) {}
+
+static inline void nfs_fscache_get_client_cookie(struct nfs_client *clp) {}
+static inline void nfs_fscache_release_client_cookie(struct nfs_client *clp) {}
+
+static inline void nfs_fscache_get_super_cookie(
+	struct super_block *sb,
+	struct nfs_parsed_mount_data *data)
+{
+}
+static inline void nfs_fscache_release_super_cookie(struct super_block *sb) {}
+
+static inline void nfs_fscache_init_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_release_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_zap_inode_cookie(struct inode *inode) {}
+static inline void nfs_fscache_set_inode_cookie(struct inode *inode,
+						struct file *filp) {}
+static inline void nfs_fscache_reset_inode_cookie(struct inode *inode) {}
+
+static inline int nfs_fscache_release_page(struct page *page, gfp_t gfp)
+{
+	return 1; /* True: may release page */
+}
+static inline void nfs_fscache_invalidate_page(struct page *page,
+					       struct inode *inode) {}
+static inline void nfs_fscache_wait_on_page_write(struct nfs_inode *nfsi,
+						  struct page *page) {}
+
+static inline int nfs_readpage_from_fscache(struct nfs_open_context *ctx,
+					    struct inode *inode,
+					    struct page *page)
+{
+	return -ENOBUFS;
+}
+static inline int nfs_readpages_from_fscache(struct nfs_open_context *ctx,
+					     struct inode *inode,
+					     struct address_space *mapping,
+					     struct list_head *pages,
+					     unsigned *nr_pages)
+{
+	return -ENOBUFS;
+}
+static inline void nfs_readpage_to_fscache(struct inode *inode,
+					   struct page *page, int sync) {}
+
+static inline const char *nfs_server_fscache_state(struct nfs_server *server)
+{
+	return "no ";
+}
+
+#endif /* CONFIG_NFS_FSCACHE */
+#endif /* _NFS_FSCACHE_H */
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index a834d1d850b7..64f87194d390 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -46,6 +46,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -121,6 +122,7 @@ void nfs_clear_inode(struct inode *inode)
 	BUG_ON(!list_empty(&NFS_I(inode)->open_files));
 	nfs_zap_acl_cache(inode);
 	nfs_access_zap_cache(inode);
+	nfs_fscache_release_inode_cookie(inode);
 }
 
 /**
@@ -355,6 +357,8 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr)
 		nfsi->attrtimeo_timestamp = now;
 		nfsi->access_cache = RB_ROOT;
 
+		nfs_fscache_init_inode_cookie(inode);
+
 		unlock_new_inode(inode);
 	} else
 		nfs_refresh_inode(inode, fattr);
@@ -686,6 +690,7 @@ int nfs_open(struct inode *inode, struct file *filp)
 	ctx->mode = filp->f_mode;
 	nfs_file_set_open_context(filp, ctx);
 	put_nfs_open_context(ctx);
+	nfs_fscache_set_inode_cookie(inode, filp);
 	return 0;
 }
 
@@ -786,6 +791,7 @@ static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_spa
 		memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf));
 	spin_unlock(&inode->i_lock);
 	nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE);
+	nfs_fscache_reset_inode_cookie(inode);
 	dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n",
 			inode->i_sb->s_id, (long long)NFS_FILEID(inode));
 	return 0;
@@ -1030,6 +1036,7 @@ int nfs_refresh_inode(struct inode *inode, struct nfs_fattr *fattr)
 	spin_lock(&inode->i_lock);
 	status = nfs_refresh_inode_locked(inode, fattr);
 	spin_unlock(&inode->i_lock);
+
 	return status;
 }
 
@@ -1436,6 +1443,10 @@ static int __init init_nfs_fs(void)
 {
 	int err;
 
+	err = nfs_fscache_register();
+	if (err < 0)
+		goto out7;
+
 	err = nfsiod_start();
 	if (err)
 		goto out6;
@@ -1488,6 +1499,8 @@ out4:
 out5:
 	nfsiod_stop();
 out6:
+	nfs_fscache_unregister();
+out7:
 	return err;
 }
 
@@ -1498,6 +1511,7 @@ static void __exit exit_nfs_fs(void)
 	nfs_destroy_readpagecache();
 	nfs_destroy_inodecache();
 	nfs_destroy_nfspagecache();
+	nfs_fscache_unregister();
 #ifdef CONFIG_PROC_FS
 	rpc_proc_unregister("nfs");
 #endif
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 2041f68ff1cc..e4d6a8348adf 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -5,6 +5,8 @@
 #include <linux/mount.h>
 #include <linux/security.h>
 
+#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
+
 struct nfs_string;
 
 /* Maximum number of readahead requests
@@ -37,10 +39,12 @@ struct nfs_parsed_mount_data {
 	int			acregmin, acregmax,
 				acdirmin, acdirmax;
 	int			namlen;
+	unsigned int		options;
 	unsigned int		bsize;
 	unsigned int		auth_flavor_len;
 	rpc_authflavor_t	auth_flavors[1];
 	char			*client_address;
+	char			*fscache_uniq;
 
 	struct {
 		struct sockaddr_storage	address;
diff --git a/fs/nfs/iostat.h b/fs/nfs/iostat.h
index a36952810032..a2ab2529b5ca 100644
--- a/fs/nfs/iostat.h
+++ b/fs/nfs/iostat.h
@@ -16,6 +16,9 @@
 
 struct nfs_iostats {
 	unsigned long long	bytes[__NFSIOS_BYTESMAX];
+#ifdef CONFIG_NFS_FSCACHE
+	unsigned long long	fscache[__NFSIOS_FSCACHEMAX];
+#endif
 	unsigned long		events[__NFSIOS_COUNTSMAX];
 } ____cacheline_aligned;
 
@@ -57,6 +60,21 @@ static inline void nfs_add_stats(const struct inode *inode,
 	nfs_add_server_stats(NFS_SERVER(inode), stat, addend);
 }
 
+#ifdef CONFIG_NFS_FSCACHE
+static inline void nfs_add_fscache_stats(struct inode *inode,
+					 enum nfs_stat_fscachecounters stat,
+					 unsigned long addend)
+{
+	struct nfs_iostats *iostats;
+	int cpu;
+
+	cpu = get_cpu();
+	iostats = per_cpu_ptr(NFS_SERVER(inode)->io_stats, cpu);
+	iostats->fscache[stat] += addend;
+	put_cpu_no_resched();
+}
+#endif
+
 static inline struct nfs_iostats *nfs_alloc_iostats(void)
 {
 	return alloc_percpu(struct nfs_iostats);
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index b82fe6847f14..d0cc5ce0edfe 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -328,7 +328,7 @@ nfs3_proc_create(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 		data->arg.create.verifier[1] = current->pid;
 	}
 
-	sattr->ia_mode &= ~current->fs->umask;
+	sattr->ia_mode &= ~current_umask();
 
 	for (;;) {
 		status = nfs3_do_create(dir, dentry, data);
@@ -528,7 +528,7 @@ nfs3_proc_mkdir(struct inode *dir, struct dentry *dentry, struct iattr *sattr)
 
 	dprintk("NFS call  mkdir %s\n", dentry->d_name.name);
 
-	sattr->ia_mode &= ~current->fs->umask;
+	sattr->ia_mode &= ~current_umask();
 
 	data = nfs3_alloc_createdata();
 	if (data == NULL)
@@ -639,7 +639,7 @@ nfs3_proc_mknod(struct inode *dir, struct dentry *dentry, struct iattr *sattr,
 	dprintk("NFS call  mknod %s %u:%u\n", dentry->d_name.name,
 			MAJOR(rdev), MINOR(rdev));
 
-	sattr->ia_mode &= ~current->fs->umask;
+	sattr->ia_mode &= ~current_umask();
 
 	data = nfs3_alloc_createdata();
 	if (data == NULL)
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 97bacccff579..a4d242680299 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -1501,7 +1501,7 @@ nfs4_atomic_open(struct inode *dir, struct dentry *dentry, struct nameidata *nd)
 		attr.ia_mode = nd->intent.open.create_mode;
 		attr.ia_valid = ATTR_MODE;
 		if (!IS_POSIXACL(dir))
-			attr.ia_mode &= ~current->fs->umask;
+			attr.ia_mode &= ~current_umask();
 	} else {
 		attr.ia_valid = 0;
 		BUG_ON(nd->intent.open.flags & O_CREAT);
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index f856004bb7fa..4ace3c50a8eb 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -24,6 +24,7 @@
 
 #include "internal.h"
 #include "iostat.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_PAGECACHE
 
@@ -111,8 +112,8 @@ static void nfs_readpage_truncate_uninitialised_page(struct nfs_read_data *data)
 	}
 }
 
-static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
-		struct page *page)
+int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
+		       struct page *page)
 {
 	LIST_HEAD(one_request);
 	struct nfs_page	*new;
@@ -139,6 +140,11 @@ static int nfs_readpage_async(struct nfs_open_context *ctx, struct inode *inode,
 
 static void nfs_readpage_release(struct nfs_page *req)
 {
+	struct inode *d_inode = req->wb_context->path.dentry->d_inode;
+
+	if (PageUptodate(req->wb_page))
+		nfs_readpage_to_fscache(d_inode, req->wb_page, 0);
+
 	unlock_page(req->wb_page);
 
 	dprintk("NFS: read done (%s/%Ld %d@%Ld)\n",
@@ -510,8 +516,15 @@ int nfs_readpage(struct file *file, struct page *page)
 	} else
 		ctx = get_nfs_open_context(nfs_file_open_context(file));
 
+	if (!IS_SYNC(inode)) {
+		error = nfs_readpage_from_fscache(ctx, inode, page);
+		if (error == 0)
+			goto out;
+	}
+
 	error = nfs_readpage_async(ctx, inode, page);
 
+out:
 	put_nfs_open_context(ctx);
 	return error;
 out_unlock:
@@ -584,6 +597,15 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 			return -EBADF;
 	} else
 		desc.ctx = get_nfs_open_context(nfs_file_open_context(filp));
+
+	/* attempt to read as many of the pages as possible from the cache
+	 * - this returns -ENOBUFS immediately if the cookie is negative
+	 */
+	ret = nfs_readpages_from_fscache(desc.ctx, inode, mapping,
+					 pages, &nr_pages);
+	if (ret == 0)
+		goto read_complete; /* all pages were read */
+
 	if (rsize < PAGE_CACHE_SIZE)
 		nfs_pageio_init(&pgio, inode, nfs_pagein_multi, rsize, 0);
 	else
@@ -594,6 +616,7 @@ int nfs_readpages(struct file *filp, struct address_space *mapping,
 	nfs_pageio_complete(&pgio);
 	npages = (pgio.pg_bytes_written + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT;
 	nfs_add_stats(inode, NFSIOS_READPAGES, npages);
+read_complete:
 	put_nfs_open_context(desc.ctx);
 out:
 	return ret;
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 0942fcbbad3c..82eaadbff408 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -60,6 +60,7 @@
 #include "delegation.h"
 #include "iostat.h"
 #include "internal.h"
+#include "fscache.h"
 
 #define NFSDBG_FACILITY		NFSDBG_VFS
 
@@ -76,6 +77,7 @@ enum {
 	Opt_rdirplus, Opt_nordirplus,
 	Opt_sharecache, Opt_nosharecache,
 	Opt_resvport, Opt_noresvport,
+	Opt_fscache, Opt_nofscache,
 
 	/* Mount options that take integer arguments */
 	Opt_port,
@@ -93,6 +95,7 @@ enum {
 	Opt_sec, Opt_proto, Opt_mountproto, Opt_mounthost,
 	Opt_addr, Opt_mountaddr, Opt_clientaddr,
 	Opt_lookupcache,
+	Opt_fscache_uniq,
 
 	/* Special mount options */
 	Opt_userspace, Opt_deprecated, Opt_sloppy,
@@ -132,6 +135,9 @@ static const match_table_t nfs_mount_option_tokens = {
 	{ Opt_nosharecache, "nosharecache" },
 	{ Opt_resvport, "resvport" },
 	{ Opt_noresvport, "noresvport" },
+	{ Opt_fscache, "fsc" },
+	{ Opt_fscache_uniq, "fsc=%s" },
+	{ Opt_nofscache, "nofsc" },
 
 	{ Opt_port, "port=%u" },
 	{ Opt_rsize, "rsize=%u" },
@@ -563,6 +569,8 @@ static void nfs_show_mount_options(struct seq_file *m, struct nfs_server *nfss,
 	if (clp->rpc_ops->version == 4)
 		seq_printf(m, ",clientaddr=%s", clp->cl_ipaddr);
 #endif
+	if (nfss->options & NFS_OPTION_FSCACHE)
+		seq_printf(m, ",fsc");
 }
 
 /*
@@ -641,6 +649,10 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
 			totals.events[i] += stats->events[i];
 		for (i = 0; i < __NFSIOS_BYTESMAX; i++)
 			totals.bytes[i] += stats->bytes[i];
+#ifdef CONFIG_NFS_FSCACHE
+		for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
+			totals.fscache[i] += stats->fscache[i];
+#endif
 
 		preempt_enable();
 	}
@@ -651,6 +663,13 @@ static int nfs_show_stats(struct seq_file *m, struct vfsmount *mnt)
 	seq_printf(m, "\n\tbytes:\t");
 	for (i = 0; i < __NFSIOS_BYTESMAX; i++)
 		seq_printf(m, "%Lu ", totals.bytes[i]);
+#ifdef CONFIG_NFS_FSCACHE
+	if (nfss->options & NFS_OPTION_FSCACHE) {
+		seq_printf(m, "\n\tfsc:\t");
+		for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
+			seq_printf(m, "%Lu ", totals.bytes[i]);
+	}
+#endif
 	seq_printf(m, "\n");
 
 	rpc_print_iostats(m, nfss->client);
@@ -1044,6 +1063,24 @@ static int nfs_parse_mount_options(char *raw,
 		case Opt_noresvport:
 			mnt->flags |= NFS_MOUNT_NORESVPORT;
 			break;
+		case Opt_fscache:
+			mnt->options |= NFS_OPTION_FSCACHE;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = NULL;
+			break;
+		case Opt_nofscache:
+			mnt->options &= ~NFS_OPTION_FSCACHE;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = NULL;
+			break;
+		case Opt_fscache_uniq:
+			string = match_strdup(args);
+			if (!string)
+				goto out_nomem;
+			kfree(mnt->fscache_uniq);
+			mnt->fscache_uniq = string;
+			mnt->options |= NFS_OPTION_FSCACHE;
+			break;
 
 		/*
 		 * options that take numeric values
@@ -1870,8 +1907,6 @@ static void nfs_clone_super(struct super_block *sb,
  	nfs_initialise_sb(sb);
 }
 
-#define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
-
 static int nfs_compare_mount_options(const struct super_block *s, const struct nfs_server *b, int flags)
 {
 	const struct nfs_server *a = s->s_fs_info;
@@ -2036,6 +2071,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 	if (!s->s_root) {
 		/* initial superblock/root creation */
 		nfs_fill_super(s, data);
+		nfs_fscache_get_super_cookie(s, data);
 	}
 
 	mntroot = nfs_get_root(s, mntfh);
@@ -2056,6 +2092,7 @@ static int nfs_get_sb(struct file_system_type *fs_type,
 out:
 	kfree(data->nfs_server.hostname);
 	kfree(data->mount_server.hostname);
+	kfree(data->fscache_uniq);
 	security_free_mnt_opts(&data->lsm_opts);
 out_free_fh:
 	kfree(mntfh);
@@ -2083,6 +2120,7 @@ static void nfs_kill_super(struct super_block *s)
 
 	bdi_unregister(&server->backing_dev_info);
 	kill_anon_super(s);
+	nfs_fscache_release_super_cookie(s);
 	nfs_free_server(server);
 }
 
@@ -2390,6 +2428,7 @@ static int nfs4_get_sb(struct file_system_type *fs_type,
 	if (!s->s_root) {
 		/* initial superblock/root creation */
 		nfs4_fill_super(s);
+		nfs_fscache_get_super_cookie(s, data);
 	}
 
 	mntroot = nfs4_get_root(s, mntfh);
@@ -2411,6 +2450,7 @@ out:
 	kfree(data->client_address);
 	kfree(data->nfs_server.export_path);
 	kfree(data->nfs_server.hostname);
+	kfree(data->fscache_uniq);
 	security_free_mnt_opts(&data->lsm_opts);
 out_free_fh:
 	kfree(mntfh);
@@ -2437,6 +2477,7 @@ static void nfs4_kill_super(struct super_block *sb)
 	kill_anon_super(sb);
 
 	nfs4_renewd_prepare_shutdown(server);
+	nfs_fscache_release_super_cookie(sb);
 	nfs_free_server(server);
 }
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index bc3567bab8c4..7c09852be713 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -403,7 +403,6 @@ static int
 nfsd(void *vrqstp)
 {
 	struct svc_rqst *rqstp = (struct svc_rqst *) vrqstp;
-	struct fs_struct *fsp;
 	int err, preverr = 0;
 
 	/* Lock module and set up kernel thread */
@@ -412,13 +411,11 @@ nfsd(void *vrqstp)
 	/* At this point, the thread shares current->fs
 	 * with the init process. We need to create files with a
 	 * umask of 0 instead of init's umask. */
-	fsp = copy_fs_struct(current->fs);
-	if (!fsp) {
+	if (unshare_fs_struct() < 0) {
 		printk("Unable to start nfsd thread: out of memory\n");
 		goto out;
 	}
-	exit_fs(current);
-	current->fs = fsp;
+
 	current->fs->umask = 0;
 
 	/*
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index 12dfb44c22e5..fbeaec762103 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -296,7 +296,7 @@ int ocfs2_init_acl(handle_t *handle,
 				return PTR_ERR(acl);
 		}
 		if (!acl)
-			inode->i_mode &= ~current->fs->umask;
+			inode->i_mode &= ~current_umask();
 	}
 	if ((osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL) && acl) {
 		struct posix_acl *clone;
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index 19e3a96aa02c..678a067d9251 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -294,6 +294,55 @@ static struct ocfs2_extent_tree_operations ocfs2_xattr_tree_et_ops = {
 	.eo_fill_max_leaf_clusters = ocfs2_xattr_tree_fill_max_leaf_clusters,
 };
 
+static void ocfs2_dx_root_set_last_eb_blk(struct ocfs2_extent_tree *et,
+					  u64 blkno)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	dx_root->dr_last_eb_blk = cpu_to_le64(blkno);
+}
+
+static u64 ocfs2_dx_root_get_last_eb_blk(struct ocfs2_extent_tree *et)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	return le64_to_cpu(dx_root->dr_last_eb_blk);
+}
+
+static void ocfs2_dx_root_update_clusters(struct inode *inode,
+					  struct ocfs2_extent_tree *et,
+					  u32 clusters)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	le32_add_cpu(&dx_root->dr_clusters, clusters);
+}
+
+static int ocfs2_dx_root_sanity_check(struct inode *inode,
+				      struct ocfs2_extent_tree *et)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	BUG_ON(!OCFS2_IS_VALID_DX_ROOT(dx_root));
+
+	return 0;
+}
+
+static void ocfs2_dx_root_fill_root_el(struct ocfs2_extent_tree *et)
+{
+	struct ocfs2_dx_root_block *dx_root = et->et_object;
+
+	et->et_root_el = &dx_root->dr_list;
+}
+
+static struct ocfs2_extent_tree_operations ocfs2_dx_root_et_ops = {
+	.eo_set_last_eb_blk	= ocfs2_dx_root_set_last_eb_blk,
+	.eo_get_last_eb_blk	= ocfs2_dx_root_get_last_eb_blk,
+	.eo_update_clusters	= ocfs2_dx_root_update_clusters,
+	.eo_sanity_check	= ocfs2_dx_root_sanity_check,
+	.eo_fill_root_el	= ocfs2_dx_root_fill_root_el,
+};
+
 static void __ocfs2_init_extent_tree(struct ocfs2_extent_tree *et,
 				     struct inode *inode,
 				     struct buffer_head *bh,
@@ -339,6 +388,14 @@ void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
 				 &ocfs2_xattr_value_et_ops);
 }
 
+void ocfs2_init_dx_root_extent_tree(struct ocfs2_extent_tree *et,
+				    struct inode *inode,
+				    struct buffer_head *bh)
+{
+	__ocfs2_init_extent_tree(et, inode, bh, ocfs2_journal_access_dr,
+				 NULL, &ocfs2_dx_root_et_ops);
+}
+
 static inline void ocfs2_et_set_last_eb_blk(struct ocfs2_extent_tree *et,
 					    u64 new_last_eb_blk)
 {
diff --git a/fs/ocfs2/alloc.h b/fs/ocfs2/alloc.h
index cceff5c37f47..353254ba29e1 100644
--- a/fs/ocfs2/alloc.h
+++ b/fs/ocfs2/alloc.h
@@ -75,6 +75,9 @@ struct ocfs2_xattr_value_buf;
 void ocfs2_init_xattr_value_extent_tree(struct ocfs2_extent_tree *et,
 					struct inode *inode,
 					struct ocfs2_xattr_value_buf *vb);
+void ocfs2_init_dx_root_extent_tree(struct ocfs2_extent_tree *et,
+				    struct inode *inode,
+				    struct buffer_head *bh);
 
 /*
  * Read an extent block into *bh.  If *bh is NULL, a bh will be
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 8e1709a679b7..b2c52b3a1484 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -1956,15 +1956,16 @@ static int ocfs2_write_end(struct file *file, struct address_space *mapping,
 }
 
 const struct address_space_operations ocfs2_aops = {
-	.readpage	= ocfs2_readpage,
-	.readpages	= ocfs2_readpages,
-	.writepage	= ocfs2_writepage,
-	.write_begin	= ocfs2_write_begin,
-	.write_end	= ocfs2_write_end,
-	.bmap		= ocfs2_bmap,
-	.sync_page	= block_sync_page,
-	.direct_IO	= ocfs2_direct_IO,
-	.invalidatepage	= ocfs2_invalidatepage,
-	.releasepage	= ocfs2_releasepage,
-	.migratepage	= buffer_migrate_page,
+	.readpage		= ocfs2_readpage,
+	.readpages		= ocfs2_readpages,
+	.writepage		= ocfs2_writepage,
+	.write_begin		= ocfs2_write_begin,
+	.write_end		= ocfs2_write_end,
+	.bmap			= ocfs2_bmap,
+	.sync_page		= block_sync_page,
+	.direct_IO		= ocfs2_direct_IO,
+	.invalidatepage		= ocfs2_invalidatepage,
+	.releasepage		= ocfs2_releasepage,
+	.migratepage		= buffer_migrate_page,
+	.is_partially_uptodate	= block_is_partially_uptodate,
 };
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index 04697ba7f73e..4f85eceab376 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -33,6 +33,7 @@
 #include <linux/random.h>
 #include <linux/crc32.h>
 #include <linux/time.h>
+#include <linux/debugfs.h>
 
 #include "heartbeat.h"
 #include "tcp.h"
@@ -60,6 +61,11 @@ static unsigned long o2hb_live_node_bitmap[BITS_TO_LONGS(O2NM_MAX_NODES)];
 static LIST_HEAD(o2hb_node_events);
 static DECLARE_WAIT_QUEUE_HEAD(o2hb_steady_queue);
 
+#define O2HB_DEBUG_DIR			"o2hb"
+#define O2HB_DEBUG_LIVENODES		"livenodes"
+static struct dentry *o2hb_debug_dir;
+static struct dentry *o2hb_debug_livenodes;
+
 static LIST_HEAD(o2hb_all_regions);
 
 static struct o2hb_callback {
@@ -905,7 +911,77 @@ static int o2hb_thread(void *data)
 	return 0;
 }
 
-void o2hb_init(void)
+#ifdef CONFIG_DEBUG_FS
+static int o2hb_debug_open(struct inode *inode, struct file *file)
+{
+	unsigned long map[BITS_TO_LONGS(O2NM_MAX_NODES)];
+	char *buf = NULL;
+	int i = -1;
+	int out = 0;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		goto bail;
+
+	o2hb_fill_node_map(map, sizeof(map));
+
+	while ((i = find_next_bit(map, O2NM_MAX_NODES, i + 1)) < O2NM_MAX_NODES)
+		out += snprintf(buf + out, PAGE_SIZE - out, "%d ", i);
+	out += snprintf(buf + out, PAGE_SIZE - out, "\n");
+
+	i_size_write(inode, out);
+
+	file->private_data = buf;
+
+	return 0;
+bail:
+	return -ENOMEM;
+}
+
+static int o2hb_debug_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static ssize_t o2hb_debug_read(struct file *file, char __user *buf,
+				 size_t nbytes, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, nbytes, ppos, file->private_data,
+				       i_size_read(file->f_mapping->host));
+}
+#else
+static int o2hb_debug_open(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+static int o2hb_debug_release(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+static ssize_t o2hb_debug_read(struct file *file, char __user *buf,
+			       size_t nbytes, loff_t *ppos)
+{
+	return 0;
+}
+#endif  /* CONFIG_DEBUG_FS */
+
+static struct file_operations o2hb_debug_fops = {
+	.open =		o2hb_debug_open,
+	.release =	o2hb_debug_release,
+	.read =		o2hb_debug_read,
+	.llseek =	generic_file_llseek,
+};
+
+void o2hb_exit(void)
+{
+	if (o2hb_debug_livenodes)
+		debugfs_remove(o2hb_debug_livenodes);
+	if (o2hb_debug_dir)
+		debugfs_remove(o2hb_debug_dir);
+}
+
+int o2hb_init(void)
 {
 	int i;
 
@@ -918,6 +994,24 @@ void o2hb_init(void)
 	INIT_LIST_HEAD(&o2hb_node_events);
 
 	memset(o2hb_live_node_bitmap, 0, sizeof(o2hb_live_node_bitmap));
+
+	o2hb_debug_dir = debugfs_create_dir(O2HB_DEBUG_DIR, NULL);
+	if (!o2hb_debug_dir) {
+		mlog_errno(-ENOMEM);
+		return -ENOMEM;
+	}
+
+	o2hb_debug_livenodes = debugfs_create_file(O2HB_DEBUG_LIVENODES,
+						   S_IFREG|S_IRUSR,
+						   o2hb_debug_dir, NULL,
+						   &o2hb_debug_fops);
+	if (!o2hb_debug_livenodes) {
+		mlog_errno(-ENOMEM);
+		debugfs_remove(o2hb_debug_dir);
+		return -ENOMEM;
+	}
+
+	return 0;
 }
 
 /* if we're already in a callback then we're already serialized by the sem */
diff --git a/fs/ocfs2/cluster/heartbeat.h b/fs/ocfs2/cluster/heartbeat.h
index e511339886b3..2f1649253b49 100644
--- a/fs/ocfs2/cluster/heartbeat.h
+++ b/fs/ocfs2/cluster/heartbeat.h
@@ -75,7 +75,8 @@ void o2hb_unregister_callback(const char *region_uuid,
 			      struct o2hb_callback_func *hc);
 void o2hb_fill_node_map(unsigned long *map,
 			unsigned bytes);
-void o2hb_init(void);
+void o2hb_exit(void);
+int o2hb_init(void);
 int o2hb_check_node_heartbeating(u8 node_num);
 int o2hb_check_node_heartbeating_from_callback(u8 node_num);
 int o2hb_check_local_node_heartbeating(void);
diff --git a/fs/ocfs2/cluster/nodemanager.c b/fs/ocfs2/cluster/nodemanager.c
index 70e8fa9e2539..7ee6188bc79a 100644
--- a/fs/ocfs2/cluster/nodemanager.c
+++ b/fs/ocfs2/cluster/nodemanager.c
@@ -881,6 +881,7 @@ static void __exit exit_o2nm(void)
 	o2cb_sys_shutdown();
 
 	o2net_exit();
+	o2hb_exit();
 }
 
 static int __init init_o2nm(void)
@@ -889,11 +890,13 @@ static int __init init_o2nm(void)
 
 	cluster_print_version();
 
-	o2hb_init();
+	ret = o2hb_init();
+	if (ret)
+		goto out;
 
 	ret = o2net_init();
 	if (ret)
-		goto out;
+		goto out_o2hb;
 
 	ret = o2net_register_hb_callbacks();
 	if (ret)
@@ -916,6 +919,8 @@ out_callbacks:
 	o2net_unregister_hb_callbacks();
 out_o2net:
 	o2net_exit();
+out_o2hb:
+	o2hb_exit();
 out:
 	return ret;
 }
diff --git a/fs/ocfs2/dir.c b/fs/ocfs2/dir.c
index f2c4098cf337..e71160cda110 100644
--- a/fs/ocfs2/dir.c
+++ b/fs/ocfs2/dir.c
@@ -41,6 +41,7 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/quotaops.h>
+#include <linux/sort.h>
 
 #define MLOG_MASK_PREFIX ML_NAMEI
 #include <cluster/masklog.h>
@@ -58,6 +59,7 @@
 #include "namei.h"
 #include "suballoc.h"
 #include "super.h"
+#include "sysfile.h"
 #include "uptodate.h"
 
 #include "buffer_head_io.h"
@@ -71,11 +73,6 @@ static unsigned char ocfs2_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
 };
 
-static int ocfs2_extend_dir(struct ocfs2_super *osb,
-			    struct inode *dir,
-			    struct buffer_head *parent_fe_bh,
-			    unsigned int blocks_wanted,
-			    struct buffer_head **new_de_bh);
 static int ocfs2_do_extend_dir(struct super_block *sb,
 			       handle_t *handle,
 			       struct inode *dir,
@@ -83,22 +80,36 @@ static int ocfs2_do_extend_dir(struct super_block *sb,
 			       struct ocfs2_alloc_context *data_ac,
 			       struct ocfs2_alloc_context *meta_ac,
 			       struct buffer_head **new_bh);
+static int ocfs2_dir_indexed(struct inode *inode);
 
 /*
  * These are distinct checks because future versions of the file system will
  * want to have a trailing dirent structure independent of indexing.
  */
-static int ocfs2_dir_has_trailer(struct inode *dir)
+static int ocfs2_supports_dir_trailer(struct inode *dir)
 {
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
 	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return 0;
 
-	return ocfs2_meta_ecc(OCFS2_SB(dir->i_sb));
+	return ocfs2_meta_ecc(osb) || ocfs2_dir_indexed(dir);
 }
 
-static int ocfs2_supports_dir_trailer(struct ocfs2_super *osb)
+/*
+ * "new' here refers to the point at which we're creating a new
+ * directory via "mkdir()", but also when we're expanding an inline
+ * directory. In either case, we don't yet have the indexing bit set
+ * on the directory, so the standard checks will fail in when metaecc
+ * is turned off. Only directory-initialization type functions should
+ * use this then. Everything else wants ocfs2_supports_dir_trailer()
+ */
+static int ocfs2_new_dir_wants_trailer(struct inode *dir)
 {
-	return ocfs2_meta_ecc(osb);
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
+	return ocfs2_meta_ecc(osb) ||
+		ocfs2_supports_indexed_dirs(osb);
 }
 
 static inline unsigned int ocfs2_dir_trailer_blk_off(struct super_block *sb)
@@ -130,7 +141,7 @@ static int ocfs2_skip_dir_trailer(struct inode *dir,
 {
 	unsigned long toff = blklen - sizeof(struct ocfs2_dir_block_trailer);
 
-	if (!ocfs2_dir_has_trailer(dir))
+	if (!ocfs2_supports_dir_trailer(dir))
 		return 0;
 
 	if (offset != toff)
@@ -140,7 +151,7 @@ static int ocfs2_skip_dir_trailer(struct inode *dir,
 }
 
 static void ocfs2_init_dir_trailer(struct inode *inode,
-				   struct buffer_head *bh)
+				   struct buffer_head *bh, u16 rec_len)
 {
 	struct ocfs2_dir_block_trailer *trailer;
 
@@ -150,6 +161,153 @@ static void ocfs2_init_dir_trailer(struct inode *inode,
 			cpu_to_le16(sizeof(struct ocfs2_dir_block_trailer));
 	trailer->db_parent_dinode = cpu_to_le64(OCFS2_I(inode)->ip_blkno);
 	trailer->db_blkno = cpu_to_le64(bh->b_blocknr);
+	trailer->db_free_rec_len = cpu_to_le16(rec_len);
+}
+/*
+ * Link an unindexed block with a dir trailer structure into the index free
+ * list. This function will modify dirdata_bh, but assumes you've already
+ * passed it to the journal.
+ */
+static int ocfs2_dx_dir_link_trailer(struct inode *dir, handle_t *handle,
+				     struct buffer_head *dx_root_bh,
+				     struct buffer_head *dirdata_bh)
+{
+	int ret;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dir_block_trailer *trailer;
+
+	ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	trailer = ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb);
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+	trailer->db_free_next = dx_root->dr_free_blk;
+	dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr);
+
+	ocfs2_journal_dirty(handle, dx_root_bh);
+
+out:
+	return ret;
+}
+
+static int ocfs2_free_list_at_root(struct ocfs2_dir_lookup_result *res)
+{
+	return res->dl_prev_leaf_bh == NULL;
+}
+
+void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res)
+{
+	brelse(res->dl_dx_root_bh);
+	brelse(res->dl_leaf_bh);
+	brelse(res->dl_dx_leaf_bh);
+	brelse(res->dl_prev_leaf_bh);
+}
+
+static int ocfs2_dir_indexed(struct inode *inode)
+{
+	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INDEXED_DIR_FL)
+		return 1;
+	return 0;
+}
+
+static inline int ocfs2_dx_root_inline(struct ocfs2_dx_root_block *dx_root)
+{
+	return dx_root->dr_flags & OCFS2_DX_FLAG_INLINE;
+}
+
+/*
+ * Hashing code adapted from ext3
+ */
+#define DELTA 0x9E3779B9
+
+static void TEA_transform(__u32 buf[4], __u32 const in[])
+{
+	__u32	sum = 0;
+	__u32	b0 = buf[0], b1 = buf[1];
+	__u32	a = in[0], b = in[1], c = in[2], d = in[3];
+	int	n = 16;
+
+	do {
+		sum += DELTA;
+		b0 += ((b1 << 4)+a) ^ (b1+sum) ^ ((b1 >> 5)+b);
+		b1 += ((b0 << 4)+c) ^ (b0+sum) ^ ((b0 >> 5)+d);
+	} while (--n);
+
+	buf[0] += b0;
+	buf[1] += b1;
+}
+
+static void str2hashbuf(const char *msg, int len, __u32 *buf, int num)
+{
+	__u32	pad, val;
+	int	i;
+
+	pad = (__u32)len | ((__u32)len << 8);
+	pad |= pad << 16;
+
+	val = pad;
+	if (len > num*4)
+		len = num * 4;
+	for (i = 0; i < len; i++) {
+		if ((i % 4) == 0)
+			val = pad;
+		val = msg[i] + (val << 8);
+		if ((i % 4) == 3) {
+			*buf++ = val;
+			val = pad;
+			num--;
+		}
+	}
+	if (--num >= 0)
+		*buf++ = val;
+	while (--num >= 0)
+		*buf++ = pad;
+}
+
+static void ocfs2_dx_dir_name_hash(struct inode *dir, const char *name, int len,
+				   struct ocfs2_dx_hinfo *hinfo)
+{
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	const char	*p;
+	__u32		in[8], buf[4];
+
+	/*
+	 * XXX: Is this really necessary, if the index is never looked
+	 * at by readdir? Is a hash value of '0' a bad idea?
+	 */
+	if ((len == 1 && !strncmp(".", name, 1)) ||
+	    (len == 2 && !strncmp("..", name, 2))) {
+		buf[0] = buf[1] = 0;
+		goto out;
+	}
+
+#ifdef OCFS2_DEBUG_DX_DIRS
+	/*
+	 * This makes it very easy to debug indexing problems. We
+	 * should never allow this to be selected without hand editing
+	 * this file though.
+	 */
+	buf[0] = buf[1] = len;
+	goto out;
+#endif
+
+	memcpy(buf, osb->osb_dx_seed, sizeof(buf));
+
+	p = name;
+	while (len > 0) {
+		str2hashbuf(p, len, in, 4);
+		TEA_transform(buf, in);
+		len -= 16;
+		p += 16;
+	}
+
+out:
+	hinfo->major_hash = buf[0];
+	hinfo->minor_hash = buf[1];
 }
 
 /*
@@ -312,6 +470,52 @@ static int ocfs2_validate_dir_block(struct super_block *sb,
 }
 
 /*
+ * Validate a directory trailer.
+ *
+ * We check the trailer here rather than in ocfs2_validate_dir_block()
+ * because that function doesn't have the inode to test.
+ */
+static int ocfs2_check_dir_trailer(struct inode *dir, struct buffer_head *bh)
+{
+	int rc = 0;
+	struct ocfs2_dir_block_trailer *trailer;
+
+	trailer = ocfs2_trailer_from_bh(bh, dir->i_sb);
+	if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) {
+		rc = -EINVAL;
+		ocfs2_error(dir->i_sb,
+			    "Invalid dirblock #%llu: "
+			    "signature = %.*s\n",
+			    (unsigned long long)bh->b_blocknr, 7,
+			    trailer->db_signature);
+		goto out;
+	}
+	if (le64_to_cpu(trailer->db_blkno) != bh->b_blocknr) {
+		rc = -EINVAL;
+		ocfs2_error(dir->i_sb,
+			    "Directory block #%llu has an invalid "
+			    "db_blkno of %llu",
+			    (unsigned long long)bh->b_blocknr,
+			    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+		goto out;
+	}
+	if (le64_to_cpu(trailer->db_parent_dinode) !=
+	    OCFS2_I(dir)->ip_blkno) {
+		rc = -EINVAL;
+		ocfs2_error(dir->i_sb,
+			    "Directory block #%llu on dinode "
+			    "#%llu has an invalid parent_dinode "
+			    "of %llu",
+			    (unsigned long long)bh->b_blocknr,
+			    (unsigned long long)OCFS2_I(dir)->ip_blkno,
+			    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+		goto out;
+	}
+out:
+	return rc;
+}
+
+/*
  * This function forces all errors to -EIO for consistency with its
  * predecessor, ocfs2_bread().  We haven't audited what returning the
  * real error codes would do to callers.  We log the real codes with
@@ -322,7 +526,6 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block,
 {
 	int rc = 0;
 	struct buffer_head *tmp = *bh;
-	struct ocfs2_dir_block_trailer *trailer;
 
 	rc = ocfs2_read_virt_blocks(inode, v_block, 1, &tmp, flags,
 				    ocfs2_validate_dir_block);
@@ -331,42 +534,13 @@ static int ocfs2_read_dir_block(struct inode *inode, u64 v_block,
 		goto out;
 	}
 
-	/*
-	 * We check the trailer here rather than in
-	 * ocfs2_validate_dir_block() because that function doesn't have
-	 * the inode to test.
-	 */
 	if (!(flags & OCFS2_BH_READAHEAD) &&
-	    ocfs2_dir_has_trailer(inode)) {
-		trailer = ocfs2_trailer_from_bh(tmp, inode->i_sb);
-		if (!OCFS2_IS_VALID_DIR_TRAILER(trailer)) {
-			rc = -EINVAL;
-			ocfs2_error(inode->i_sb,
-				    "Invalid dirblock #%llu: "
-				    "signature = %.*s\n",
-				    (unsigned long long)tmp->b_blocknr, 7,
-				    trailer->db_signature);
-			goto out;
-		}
-		if (le64_to_cpu(trailer->db_blkno) != tmp->b_blocknr) {
-			rc = -EINVAL;
-			ocfs2_error(inode->i_sb,
-				    "Directory block #%llu has an invalid "
-				    "db_blkno of %llu",
-				    (unsigned long long)tmp->b_blocknr,
-				    (unsigned long long)le64_to_cpu(trailer->db_blkno));
-			goto out;
-		}
-		if (le64_to_cpu(trailer->db_parent_dinode) !=
-		    OCFS2_I(inode)->ip_blkno) {
-			rc = -EINVAL;
-			ocfs2_error(inode->i_sb,
-				    "Directory block #%llu on dinode "
-				    "#%llu has an invalid parent_dinode "
-				    "of %llu",
-				    (unsigned long long)tmp->b_blocknr,
-				    (unsigned long long)OCFS2_I(inode)->ip_blkno,
-				    (unsigned long long)le64_to_cpu(trailer->db_blkno));
+	    ocfs2_supports_dir_trailer(inode)) {
+		rc = ocfs2_check_dir_trailer(inode, tmp);
+		if (rc) {
+			if (!*bh)
+				brelse(tmp);
+			mlog_errno(rc);
 			goto out;
 		}
 	}
@@ -379,6 +553,141 @@ out:
 	return rc ? -EIO : 0;
 }
 
+/*
+ * Read the block at 'phys' which belongs to this directory
+ * inode. This function does no virtual->physical block translation -
+ * what's passed in is assumed to be a valid directory block.
+ */
+static int ocfs2_read_dir_block_direct(struct inode *dir, u64 phys,
+				       struct buffer_head **bh)
+{
+	int ret;
+	struct buffer_head *tmp = *bh;
+
+	ret = ocfs2_read_block(dir, phys, &tmp, ocfs2_validate_dir_block);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ocfs2_supports_dir_trailer(dir)) {
+		ret = ocfs2_check_dir_trailer(dir, tmp);
+		if (ret) {
+			if (!*bh)
+				brelse(tmp);
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	if (!ret && !*bh)
+		*bh = tmp;
+out:
+	return ret;
+}
+
+static int ocfs2_validate_dx_root(struct super_block *sb,
+				  struct buffer_head *bh)
+{
+	int ret;
+	struct ocfs2_dx_root_block *dx_root;
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	dx_root = (struct ocfs2_dx_root_block *) bh->b_data;
+
+	ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_root->dr_check);
+	if (ret) {
+		mlog(ML_ERROR,
+		     "Checksum failed for dir index root block %llu\n",
+		     (unsigned long long)bh->b_blocknr);
+		return ret;
+	}
+
+	if (!OCFS2_IS_VALID_DX_ROOT(dx_root)) {
+		ocfs2_error(sb,
+			    "Dir Index Root # %llu has bad signature %.*s",
+			    (unsigned long long)le64_to_cpu(dx_root->dr_blkno),
+			    7, dx_root->dr_signature);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int ocfs2_read_dx_root(struct inode *dir, struct ocfs2_dinode *di,
+			      struct buffer_head **dx_root_bh)
+{
+	int ret;
+	u64 blkno = le64_to_cpu(di->i_dx_root);
+	struct buffer_head *tmp = *dx_root_bh;
+
+	ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_root);
+
+	/* If ocfs2_read_block() got us a new bh, pass it up. */
+	if (!ret && !*dx_root_bh)
+		*dx_root_bh = tmp;
+
+	return ret;
+}
+
+static int ocfs2_validate_dx_leaf(struct super_block *sb,
+				  struct buffer_head *bh)
+{
+	int ret;
+	struct ocfs2_dx_leaf *dx_leaf = (struct ocfs2_dx_leaf *)bh->b_data;
+
+	BUG_ON(!buffer_uptodate(bh));
+
+	ret = ocfs2_validate_meta_ecc(sb, bh->b_data, &dx_leaf->dl_check);
+	if (ret) {
+		mlog(ML_ERROR,
+		     "Checksum failed for dir index leaf block %llu\n",
+		     (unsigned long long)bh->b_blocknr);
+		return ret;
+	}
+
+	if (!OCFS2_IS_VALID_DX_LEAF(dx_leaf)) {
+		ocfs2_error(sb, "Dir Index Leaf has bad signature %.*s",
+			    7, dx_leaf->dl_signature);
+		return -EROFS;
+	}
+
+	return 0;
+}
+
+static int ocfs2_read_dx_leaf(struct inode *dir, u64 blkno,
+			      struct buffer_head **dx_leaf_bh)
+{
+	int ret;
+	struct buffer_head *tmp = *dx_leaf_bh;
+
+	ret = ocfs2_read_block(dir, blkno, &tmp, ocfs2_validate_dx_leaf);
+
+	/* If ocfs2_read_block() got us a new bh, pass it up. */
+	if (!ret && !*dx_leaf_bh)
+		*dx_leaf_bh = tmp;
+
+	return ret;
+}
+
+/*
+ * Read a series of dx_leaf blocks. This expects all buffer_head
+ * pointers to be NULL on function entry.
+ */
+static int ocfs2_read_dx_leaves(struct inode *dir, u64 start, int num,
+				struct buffer_head **dx_leaf_bhs)
+{
+	int ret;
+
+	ret = ocfs2_read_blocks(dir, start, num, dx_leaf_bhs, 0,
+				ocfs2_validate_dx_leaf);
+	if (ret)
+		mlog_errno(ret);
+
+	return ret;
+}
+
 static struct buffer_head *ocfs2_find_entry_el(const char *name, int namelen,
 					       struct inode *dir,
 					       struct ocfs2_dir_entry **res_dir)
@@ -480,39 +789,340 @@ cleanup_and_exit:
 	return ret;
 }
 
+static int ocfs2_dx_dir_lookup_rec(struct inode *inode,
+				   struct ocfs2_extent_list *el,
+				   u32 major_hash,
+				   u32 *ret_cpos,
+				   u64 *ret_phys_blkno,
+				   unsigned int *ret_clen)
+{
+	int ret = 0, i, found;
+	struct buffer_head *eb_bh = NULL;
+	struct ocfs2_extent_block *eb;
+	struct ocfs2_extent_rec *rec = NULL;
+
+	if (el->l_tree_depth) {
+		ret = ocfs2_find_leaf(inode, el, major_hash, &eb_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		eb = (struct ocfs2_extent_block *) eb_bh->b_data;
+		el = &eb->h_list;
+
+		if (el->l_tree_depth) {
+			ocfs2_error(inode->i_sb,
+				    "Inode %lu has non zero tree depth in "
+				    "btree tree block %llu\n", inode->i_ino,
+				    (unsigned long long)eb_bh->b_blocknr);
+			ret = -EROFS;
+			goto out;
+		}
+	}
+
+	found = 0;
+	for (i = le16_to_cpu(el->l_next_free_rec) - 1; i >= 0; i--) {
+		rec = &el->l_recs[i];
+
+		if (le32_to_cpu(rec->e_cpos) <= major_hash) {
+			found = 1;
+			break;
+		}
+	}
+
+	if (!found) {
+		ocfs2_error(inode->i_sb, "Inode %lu has bad extent "
+			    "record (%u, %u, 0) in btree", inode->i_ino,
+			    le32_to_cpu(rec->e_cpos),
+			    ocfs2_rec_clusters(el, rec));
+		ret = -EROFS;
+		goto out;
+	}
+
+	if (ret_phys_blkno)
+		*ret_phys_blkno = le64_to_cpu(rec->e_blkno);
+	if (ret_cpos)
+		*ret_cpos = le32_to_cpu(rec->e_cpos);
+	if (ret_clen)
+		*ret_clen = le16_to_cpu(rec->e_leaf_clusters);
+
+out:
+	brelse(eb_bh);
+	return ret;
+}
+
+/*
+ * Returns the block index, from the start of the cluster which this
+ * hash belongs too.
+ */
+static inline unsigned int __ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb,
+						   u32 minor_hash)
+{
+	return minor_hash & osb->osb_dx_mask;
+}
+
+static inline unsigned int ocfs2_dx_dir_hash_idx(struct ocfs2_super *osb,
+					  struct ocfs2_dx_hinfo *hinfo)
+{
+	return __ocfs2_dx_dir_hash_idx(osb, hinfo->minor_hash);
+}
+
+static int ocfs2_dx_dir_lookup(struct inode *inode,
+			       struct ocfs2_extent_list *el,
+			       struct ocfs2_dx_hinfo *hinfo,
+			       u32 *ret_cpos,
+			       u64 *ret_phys_blkno)
+{
+	int ret = 0;
+	unsigned int cend, uninitialized_var(clen);
+	u32 uninitialized_var(cpos);
+	u64 uninitialized_var(blkno);
+	u32 name_hash = hinfo->major_hash;
+
+	ret = ocfs2_dx_dir_lookup_rec(inode, el, name_hash, &cpos, &blkno,
+				      &clen);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	cend = cpos + clen;
+	if (name_hash >= cend) {
+		/* We want the last cluster */
+		blkno += ocfs2_clusters_to_blocks(inode->i_sb, clen - 1);
+		cpos += clen - 1;
+	} else {
+		blkno += ocfs2_clusters_to_blocks(inode->i_sb,
+						  name_hash - cpos);
+		cpos = name_hash;
+	}
+
+	/*
+	 * We now have the cluster which should hold our entry. To
+	 * find the exact block from the start of the cluster to
+	 * search, we take the lower bits of the hash.
+	 */
+	blkno += ocfs2_dx_dir_hash_idx(OCFS2_SB(inode->i_sb), hinfo);
+
+	if (ret_phys_blkno)
+		*ret_phys_blkno = blkno;
+	if (ret_cpos)
+		*ret_cpos = cpos;
+
+out:
+
+	return ret;
+}
+
+static int ocfs2_dx_dir_search(const char *name, int namelen,
+			       struct inode *dir,
+			       struct ocfs2_dx_root_block *dx_root,
+			       struct ocfs2_dir_lookup_result *res)
+{
+	int ret, i, found;
+	u64 uninitialized_var(phys);
+	struct buffer_head *dx_leaf_bh = NULL;
+	struct ocfs2_dx_leaf *dx_leaf;
+	struct ocfs2_dx_entry *dx_entry = NULL;
+	struct buffer_head *dir_ent_bh = NULL;
+	struct ocfs2_dir_entry *dir_ent = NULL;
+	struct ocfs2_dx_hinfo *hinfo = &res->dl_hinfo;
+	struct ocfs2_extent_list *dr_el;
+	struct ocfs2_dx_entry_list *entry_list;
+
+	ocfs2_dx_dir_name_hash(dir, name, namelen, &res->dl_hinfo);
+
+	if (ocfs2_dx_root_inline(dx_root)) {
+		entry_list = &dx_root->dr_entries;
+		goto search;
+	}
+
+	dr_el = &dx_root->dr_list;
+
+	ret = ocfs2_dx_dir_lookup(dir, dr_el, hinfo, NULL, &phys);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	mlog(0, "Dir %llu: name: \"%.*s\", lookup of hash: %u.0x%x "
+	     "returns: %llu\n",
+	     (unsigned long long)OCFS2_I(dir)->ip_blkno,
+	     namelen, name, hinfo->major_hash, hinfo->minor_hash,
+	     (unsigned long long)phys);
+
+	ret = ocfs2_read_dx_leaf(dir, phys, &dx_leaf_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	dx_leaf = (struct ocfs2_dx_leaf *) dx_leaf_bh->b_data;
+
+	mlog(0, "leaf info: num_used: %d, count: %d\n",
+	     le16_to_cpu(dx_leaf->dl_list.de_num_used),
+	     le16_to_cpu(dx_leaf->dl_list.de_count));
+
+	entry_list = &dx_leaf->dl_list;
+
+search:
+	/*
+	 * Empty leaf is legal, so no need to check for that.
+	 */
+	found = 0;
+	for (i = 0; i < le16_to_cpu(entry_list->de_num_used); i++) {
+		dx_entry = &entry_list->de_entries[i];
+
+		if (hinfo->major_hash != le32_to_cpu(dx_entry->dx_major_hash)
+		    || hinfo->minor_hash != le32_to_cpu(dx_entry->dx_minor_hash))
+			continue;
+
+		/*
+		 * Search unindexed leaf block now. We're not
+		 * guaranteed to find anything.
+		 */
+		ret = ocfs2_read_dir_block_direct(dir,
+					  le64_to_cpu(dx_entry->dx_dirent_blk),
+					  &dir_ent_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		/*
+		 * XXX: We should check the unindexed block here,
+		 * before using it.
+		 */
+
+		found = ocfs2_search_dirblock(dir_ent_bh, dir, name, namelen,
+					      0, dir_ent_bh->b_data,
+					      dir->i_sb->s_blocksize, &dir_ent);
+		if (found == 1)
+			break;
+
+		if (found == -1) {
+			/* This means we found a bad directory entry. */
+			ret = -EIO;
+			mlog_errno(ret);
+			goto out;
+		}
+
+		brelse(dir_ent_bh);
+		dir_ent_bh = NULL;
+	}
+
+	if (found <= 0) {
+		ret = -ENOENT;
+		goto out;
+	}
+
+	res->dl_leaf_bh = dir_ent_bh;
+	res->dl_entry = dir_ent;
+	res->dl_dx_leaf_bh = dx_leaf_bh;
+	res->dl_dx_entry = dx_entry;
+
+	ret = 0;
+out:
+	if (ret) {
+		brelse(dx_leaf_bh);
+		brelse(dir_ent_bh);
+	}
+	return ret;
+}
+
+static int ocfs2_find_entry_dx(const char *name, int namelen,
+			       struct inode *dir,
+			       struct ocfs2_dir_lookup_result *lookup)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct buffer_head *dx_root_bh = NULL;
+	struct ocfs2_dx_root_block *dx_root;
+
+	ret = ocfs2_read_inode_block(dir, &di_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+
+	ret = ocfs2_read_dx_root(dir, di, &dx_root_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data;
+
+	ret = ocfs2_dx_dir_search(name, namelen, dir, dx_root, lookup);
+	if (ret) {
+		if (ret != -ENOENT)
+			mlog_errno(ret);
+		goto out;
+	}
+
+	lookup->dl_dx_root_bh = dx_root_bh;
+	dx_root_bh = NULL;
+out:
+	brelse(di_bh);
+	brelse(dx_root_bh);
+	return ret;
+}
+
 /*
  * Try to find an entry of the provided name within 'dir'.
  *
- * If nothing was found, NULL is returned. Otherwise, a buffer_head
- * and pointer to the dir entry are passed back.
+ * If nothing was found, -ENOENT is returned. Otherwise, zero is
+ * returned and the struct 'res' will contain information useful to
+ * other directory manipulation functions.
  *
  * Caller can NOT assume anything about the contents of the
- * buffer_head - it is passed back only so that it can be passed into
- * any one of the manipulation functions (add entry, delete entry,
- * etc). As an example, bh in the extent directory case is a data
- * block, in the inline-data case it actually points to an inode.
+ * buffer_heads - they are passed back only so that it can be passed
+ * into any one of the manipulation functions (add entry, delete
+ * entry, etc). As an example, bh in the extent directory case is a
+ * data block, in the inline-data case it actually points to an inode,
+ * in the indexed directory case, multiple buffers are involved.
  */
-struct buffer_head *ocfs2_find_entry(const char *name, int namelen,
-				     struct inode *dir,
-				     struct ocfs2_dir_entry **res_dir)
+int ocfs2_find_entry(const char *name, int namelen,
+		     struct inode *dir, struct ocfs2_dir_lookup_result *lookup)
 {
-	*res_dir = NULL;
+	struct buffer_head *bh;
+	struct ocfs2_dir_entry *res_dir = NULL;
 
+	if (ocfs2_dir_indexed(dir))
+		return ocfs2_find_entry_dx(name, namelen, dir, lookup);
+
+	/*
+	 * The unindexed dir code only uses part of the lookup
+	 * structure, so there's no reason to push it down further
+	 * than this.
+	 */
 	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-		return ocfs2_find_entry_id(name, namelen, dir, res_dir);
+		bh = ocfs2_find_entry_id(name, namelen, dir, &res_dir);
+	else
+		bh = ocfs2_find_entry_el(name, namelen, dir, &res_dir);
+
+	if (bh == NULL)
+		return -ENOENT;
 
-	return ocfs2_find_entry_el(name, namelen, dir, res_dir);
+	lookup->dl_leaf_bh = bh;
+	lookup->dl_entry = res_dir;
+	return 0;
 }
 
 /*
  * Update inode number and type of a previously found directory entry.
  */
 int ocfs2_update_entry(struct inode *dir, handle_t *handle,
-		       struct buffer_head *de_bh, struct ocfs2_dir_entry *de,
+		       struct ocfs2_dir_lookup_result *res,
 		       struct inode *new_entry_inode)
 {
 	int ret;
 	ocfs2_journal_access_func access = ocfs2_journal_access_db;
+	struct ocfs2_dir_entry *de = res->dl_entry;
+	struct buffer_head *de_bh = res->dl_leaf_bh;
 
 	/*
 	 * The same code works fine for both inline-data and extent
@@ -538,6 +1148,10 @@ out:
 	return ret;
 }
 
+/*
+ * __ocfs2_delete_entry deletes a directory entry by merging it with the
+ * previous entry
+ */
 static int __ocfs2_delete_entry(handle_t *handle, struct inode *dir,
 				struct ocfs2_dir_entry *de_del,
 				struct buffer_head *bh, char *first_de,
@@ -587,6 +1201,181 @@ bail:
 	return status;
 }
 
+static unsigned int ocfs2_figure_dirent_hole(struct ocfs2_dir_entry *de)
+{
+	unsigned int hole;
+
+	if (le64_to_cpu(de->inode) == 0)
+		hole = le16_to_cpu(de->rec_len);
+	else
+		hole = le16_to_cpu(de->rec_len) -
+			OCFS2_DIR_REC_LEN(de->name_len);
+
+	return hole;
+}
+
+static int ocfs2_find_max_rec_len(struct super_block *sb,
+				  struct buffer_head *dirblock_bh)
+{
+	int size, this_hole, largest_hole = 0;
+	char *trailer, *de_buf, *limit, *start = dirblock_bh->b_data;
+	struct ocfs2_dir_entry *de;
+
+	trailer = (char *)ocfs2_trailer_from_bh(dirblock_bh, sb);
+	size = ocfs2_dir_trailer_blk_off(sb);
+	limit = start + size;
+	de_buf = start;
+	de = (struct ocfs2_dir_entry *)de_buf;
+	do {
+		if (de_buf != trailer) {
+			this_hole = ocfs2_figure_dirent_hole(de);
+			if (this_hole > largest_hole)
+				largest_hole = this_hole;
+		}
+
+		de_buf += le16_to_cpu(de->rec_len);
+		de = (struct ocfs2_dir_entry *)de_buf;
+	} while (de_buf < limit);
+
+	if (largest_hole >= OCFS2_DIR_MIN_REC_LEN)
+		return largest_hole;
+	return 0;
+}
+
+static void ocfs2_dx_list_remove_entry(struct ocfs2_dx_entry_list *entry_list,
+				       int index)
+{
+	int num_used = le16_to_cpu(entry_list->de_num_used);
+
+	if (num_used == 1 || index == (num_used - 1))
+		goto clear;
+
+	memmove(&entry_list->de_entries[index],
+		&entry_list->de_entries[index + 1],
+		(num_used - index - 1)*sizeof(struct ocfs2_dx_entry));
+clear:
+	num_used--;
+	memset(&entry_list->de_entries[num_used], 0,
+	       sizeof(struct ocfs2_dx_entry));
+	entry_list->de_num_used = cpu_to_le16(num_used);
+}
+
+static int ocfs2_delete_entry_dx(handle_t *handle, struct inode *dir,
+				 struct ocfs2_dir_lookup_result *lookup)
+{
+	int ret, index, max_rec_len, add_to_free_list = 0;
+	struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh;
+	struct buffer_head *leaf_bh = lookup->dl_leaf_bh;
+	struct ocfs2_dx_leaf *dx_leaf;
+	struct ocfs2_dx_entry *dx_entry = lookup->dl_dx_entry;
+	struct ocfs2_dir_block_trailer *trailer;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dx_entry_list *entry_list;
+
+	/*
+	 * This function gets a bit messy because we might have to
+	 * modify the root block, regardless of whether the indexed
+	 * entries are stored inline.
+	 */
+
+	/*
+	 * *Only* set 'entry_list' here, based on where we're looking
+	 * for the indexed entries. Later, we might still want to
+	 * journal both blocks, based on free list state.
+	 */
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+	if (ocfs2_dx_root_inline(dx_root)) {
+		entry_list = &dx_root->dr_entries;
+	} else {
+		dx_leaf = (struct ocfs2_dx_leaf *) lookup->dl_dx_leaf_bh->b_data;
+		entry_list = &dx_leaf->dl_list;
+	}
+
+	/* Neither of these are a disk corruption - that should have
+	 * been caught by lookup, before we got here. */
+	BUG_ON(le16_to_cpu(entry_list->de_count) <= 0);
+	BUG_ON(le16_to_cpu(entry_list->de_num_used) <= 0);
+
+	index = (char *)dx_entry - (char *)entry_list->de_entries;
+	index /= sizeof(*dx_entry);
+
+	if (index >= le16_to_cpu(entry_list->de_num_used)) {
+		mlog(ML_ERROR, "Dir %llu: Bad dx_entry ptr idx %d, (%p, %p)\n",
+		     (unsigned long long)OCFS2_I(dir)->ip_blkno, index,
+		     entry_list, dx_entry);
+		return -EIO;
+	}
+
+	/*
+	 * We know that removal of this dirent will leave enough room
+	 * for a new one, so add this block to the free list if it
+	 * isn't already there.
+	 */
+	trailer = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb);
+	if (trailer->db_free_rec_len == 0)
+		add_to_free_list = 1;
+
+	/*
+	 * Add the block holding our index into the journal before
+	 * removing the unindexed entry. If we get an error return
+	 * from __ocfs2_delete_entry(), then it hasn't removed the
+	 * entry yet. Likewise, successful return means we *must*
+	 * remove the indexed entry.
+	 *
+	 * We're also careful to journal the root tree block here as
+	 * the entry count needs to be updated. Also, we might be
+	 * adding to the start of the free list.
+	 */
+	ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (!ocfs2_dx_root_inline(dx_root)) {
+		ret = ocfs2_journal_access_dl(handle, dir,
+					      lookup->dl_dx_leaf_bh,
+					      OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	mlog(0, "Dir %llu: delete entry at index: %d\n",
+	     (unsigned long long)OCFS2_I(dir)->ip_blkno, index);
+
+	ret = __ocfs2_delete_entry(handle, dir, lookup->dl_entry,
+				   leaf_bh, leaf_bh->b_data, leaf_bh->b_size);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, leaf_bh);
+	trailer->db_free_rec_len = cpu_to_le16(max_rec_len);
+	if (add_to_free_list) {
+		trailer->db_free_next = dx_root->dr_free_blk;
+		dx_root->dr_free_blk = cpu_to_le64(leaf_bh->b_blocknr);
+		ocfs2_journal_dirty(handle, dx_root_bh);
+	}
+
+	/* leaf_bh was journal_accessed for us in __ocfs2_delete_entry */
+	ocfs2_journal_dirty(handle, leaf_bh);
+
+	le32_add_cpu(&dx_root->dr_num_entries, -1);
+	ocfs2_journal_dirty(handle, dx_root_bh);
+
+	ocfs2_dx_list_remove_entry(entry_list, index);
+
+	if (!ocfs2_dx_root_inline(dx_root))
+		ocfs2_journal_dirty(handle, lookup->dl_dx_leaf_bh);
+
+out:
+	return ret;
+}
+
 static inline int ocfs2_delete_entry_id(handle_t *handle,
 					struct inode *dir,
 					struct ocfs2_dir_entry *de_del,
@@ -624,18 +1413,22 @@ static inline int ocfs2_delete_entry_el(handle_t *handle,
 }
 
 /*
- * ocfs2_delete_entry deletes a directory entry by merging it with the
- * previous entry
+ * Delete a directory entry. Hide the details of directory
+ * implementation from the caller.
  */
 int ocfs2_delete_entry(handle_t *handle,
 		       struct inode *dir,
-		       struct ocfs2_dir_entry *de_del,
-		       struct buffer_head *bh)
+		       struct ocfs2_dir_lookup_result *res)
 {
+	if (ocfs2_dir_indexed(dir))
+		return ocfs2_delete_entry_dx(handle, dir, res);
+
 	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
-		return ocfs2_delete_entry_id(handle, dir, de_del, bh);
+		return ocfs2_delete_entry_id(handle, dir, res->dl_entry,
+					     res->dl_leaf_bh);
 
-	return ocfs2_delete_entry_el(handle, dir, de_del, bh);
+	return ocfs2_delete_entry_el(handle, dir, res->dl_entry,
+				     res->dl_leaf_bh);
 }
 
 /*
@@ -663,18 +1456,166 @@ static inline int ocfs2_dirent_would_fit(struct ocfs2_dir_entry *de,
 	return 0;
 }
 
+static void ocfs2_dx_dir_leaf_insert_tail(struct ocfs2_dx_leaf *dx_leaf,
+					  struct ocfs2_dx_entry *dx_new_entry)
+{
+	int i;
+
+	i = le16_to_cpu(dx_leaf->dl_list.de_num_used);
+	dx_leaf->dl_list.de_entries[i] = *dx_new_entry;
+
+	le16_add_cpu(&dx_leaf->dl_list.de_num_used, 1);
+}
+
+static void ocfs2_dx_entry_list_insert(struct ocfs2_dx_entry_list *entry_list,
+				       struct ocfs2_dx_hinfo *hinfo,
+				       u64 dirent_blk)
+{
+	int i;
+	struct ocfs2_dx_entry *dx_entry;
+
+	i = le16_to_cpu(entry_list->de_num_used);
+	dx_entry = &entry_list->de_entries[i];
+
+	memset(dx_entry, 0, sizeof(*dx_entry));
+	dx_entry->dx_major_hash = cpu_to_le32(hinfo->major_hash);
+	dx_entry->dx_minor_hash = cpu_to_le32(hinfo->minor_hash);
+	dx_entry->dx_dirent_blk = cpu_to_le64(dirent_blk);
+
+	le16_add_cpu(&entry_list->de_num_used, 1);
+}
+
+static int __ocfs2_dx_dir_leaf_insert(struct inode *dir, handle_t *handle,
+				      struct ocfs2_dx_hinfo *hinfo,
+				      u64 dirent_blk,
+				      struct buffer_head *dx_leaf_bh)
+{
+	int ret;
+	struct ocfs2_dx_leaf *dx_leaf;
+
+	ret = ocfs2_journal_access_dl(handle, dir, dx_leaf_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data;
+	ocfs2_dx_entry_list_insert(&dx_leaf->dl_list, hinfo, dirent_blk);
+	ocfs2_journal_dirty(handle, dx_leaf_bh);
+
+out:
+	return ret;
+}
+
+static void ocfs2_dx_inline_root_insert(struct inode *dir, handle_t *handle,
+					struct ocfs2_dx_hinfo *hinfo,
+					u64 dirent_blk,
+					struct ocfs2_dx_root_block *dx_root)
+{
+	ocfs2_dx_entry_list_insert(&dx_root->dr_entries, hinfo, dirent_blk);
+}
+
+static int ocfs2_dx_dir_insert(struct inode *dir, handle_t *handle,
+			       struct ocfs2_dir_lookup_result *lookup)
+{
+	int ret = 0;
+	struct ocfs2_dx_root_block *dx_root;
+	struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh;
+
+	ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	dx_root = (struct ocfs2_dx_root_block *)lookup->dl_dx_root_bh->b_data;
+	if (ocfs2_dx_root_inline(dx_root)) {
+		ocfs2_dx_inline_root_insert(dir, handle,
+					    &lookup->dl_hinfo,
+					    lookup->dl_leaf_bh->b_blocknr,
+					    dx_root);
+	} else {
+		ret = __ocfs2_dx_dir_leaf_insert(dir, handle, &lookup->dl_hinfo,
+						 lookup->dl_leaf_bh->b_blocknr,
+						 lookup->dl_dx_leaf_bh);
+		if (ret)
+			goto out;
+	}
+
+	le32_add_cpu(&dx_root->dr_num_entries, 1);
+	ocfs2_journal_dirty(handle, dx_root_bh);
+
+out:
+	return ret;
+}
+
+static void ocfs2_remove_block_from_free_list(struct inode *dir,
+				       handle_t *handle,
+				       struct ocfs2_dir_lookup_result *lookup)
+{
+	struct ocfs2_dir_block_trailer *trailer, *prev;
+	struct ocfs2_dx_root_block *dx_root;
+	struct buffer_head *bh;
+
+	trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb);
+
+	if (ocfs2_free_list_at_root(lookup)) {
+		bh = lookup->dl_dx_root_bh;
+		dx_root = (struct ocfs2_dx_root_block *)bh->b_data;
+		dx_root->dr_free_blk = trailer->db_free_next;
+	} else {
+		bh = lookup->dl_prev_leaf_bh;
+		prev = ocfs2_trailer_from_bh(bh, dir->i_sb);
+		prev->db_free_next = trailer->db_free_next;
+	}
+
+	trailer->db_free_rec_len = cpu_to_le16(0);
+	trailer->db_free_next = cpu_to_le64(0);
+
+	ocfs2_journal_dirty(handle, bh);
+	ocfs2_journal_dirty(handle, lookup->dl_leaf_bh);
+}
+
+/*
+ * This expects that a journal write has been reserved on
+ * lookup->dl_prev_leaf_bh or lookup->dl_dx_root_bh
+ */
+static void ocfs2_recalc_free_list(struct inode *dir, handle_t *handle,
+				   struct ocfs2_dir_lookup_result *lookup)
+{
+	int max_rec_len;
+	struct ocfs2_dir_block_trailer *trailer;
+
+	/* Walk dl_leaf_bh to figure out what the new free rec_len is. */
+	max_rec_len = ocfs2_find_max_rec_len(dir->i_sb, lookup->dl_leaf_bh);
+	if (max_rec_len) {
+		/*
+		 * There's still room in this block, so no need to remove it
+		 * from the free list. In this case, we just want to update
+		 * the rec len accounting.
+		 */
+		trailer = ocfs2_trailer_from_bh(lookup->dl_leaf_bh, dir->i_sb);
+		trailer->db_free_rec_len = cpu_to_le16(max_rec_len);
+		ocfs2_journal_dirty(handle, lookup->dl_leaf_bh);
+	} else {
+		ocfs2_remove_block_from_free_list(dir, handle, lookup);
+	}
+}
+
 /* we don't always have a dentry for what we want to add, so people
  * like orphan dir can call this instead.
  *
- * If you pass me insert_bh, I'll skip the search of the other dir
- * blocks and put the record in there.
+ * The lookup context must have been filled from
+ * ocfs2_prepare_dir_for_insert.
  */
 int __ocfs2_add_entry(handle_t *handle,
 		      struct inode *dir,
 		      const char *name, int namelen,
 		      struct inode *inode, u64 blkno,
 		      struct buffer_head *parent_fe_bh,
-		      struct buffer_head *insert_bh)
+		      struct ocfs2_dir_lookup_result *lookup)
 {
 	unsigned long offset;
 	unsigned short rec_len;
@@ -683,6 +1624,7 @@ int __ocfs2_add_entry(handle_t *handle,
 	struct super_block *sb = dir->i_sb;
 	int retval, status;
 	unsigned int size = sb->s_blocksize;
+	struct buffer_head *insert_bh = lookup->dl_leaf_bh;
 	char *data_start = insert_bh->b_data;
 
 	mlog_entry_void();
@@ -690,7 +1632,31 @@ int __ocfs2_add_entry(handle_t *handle,
 	if (!namelen)
 		return -EINVAL;
 
-	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+	if (ocfs2_dir_indexed(dir)) {
+		struct buffer_head *bh;
+
+		/*
+		 * An indexed dir may require that we update the free space
+		 * list. Reserve a write to the previous node in the list so
+		 * that we don't fail later.
+		 *
+		 * XXX: This can be either a dx_root_block, or an unindexed
+		 * directory tree leaf block.
+		 */
+		if (ocfs2_free_list_at_root(lookup)) {
+			bh = lookup->dl_dx_root_bh;
+			retval = ocfs2_journal_access_dr(handle, dir, bh,
+						 OCFS2_JOURNAL_ACCESS_WRITE);
+		} else {
+			bh = lookup->dl_prev_leaf_bh;
+			retval = ocfs2_journal_access_db(handle, dir, bh,
+						 OCFS2_JOURNAL_ACCESS_WRITE);
+		}
+		if (retval) {
+			mlog_errno(retval);
+			return retval;
+		}
+	} else if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
 		data_start = di->id2.i_data.id_data;
 		size = i_size_read(dir);
 
@@ -737,10 +1703,22 @@ int __ocfs2_add_entry(handle_t *handle,
 				status = ocfs2_journal_access_di(handle, dir,
 								 insert_bh,
 								 OCFS2_JOURNAL_ACCESS_WRITE);
-			else
+			else {
 				status = ocfs2_journal_access_db(handle, dir,
 								 insert_bh,
-								 OCFS2_JOURNAL_ACCESS_WRITE);
+					      OCFS2_JOURNAL_ACCESS_WRITE);
+
+				if (ocfs2_dir_indexed(dir)) {
+					status = ocfs2_dx_dir_insert(dir,
+								handle,
+								lookup);
+					if (status) {
+						mlog_errno(status);
+						goto bail;
+					}
+				}
+			}
+
 			/* By now the buffer is marked for journaling */
 			offset += le16_to_cpu(de->rec_len);
 			if (le64_to_cpu(de->inode)) {
@@ -761,6 +1739,9 @@ int __ocfs2_add_entry(handle_t *handle,
 			de->name_len = namelen;
 			memcpy(de->name, name, namelen);
 
+			if (ocfs2_dir_indexed(dir))
+				ocfs2_recalc_free_list(dir, handle, lookup);
+
 			dir->i_version++;
 			status = ocfs2_journal_dirty(handle, insert_bh);
 			retval = 0;
@@ -870,6 +1851,10 @@ out:
 	return 0;
 }
 
+/*
+ * NOTE: This function can be called against unindexed directories,
+ * and indexed ones.
+ */
 static int ocfs2_dir_foreach_blk_el(struct inode *inode,
 				    u64 *f_version,
 				    loff_t *f_pos, void *priv,
@@ -1071,31 +2056,22 @@ int ocfs2_find_files_on_disk(const char *name,
 			     int namelen,
 			     u64 *blkno,
 			     struct inode *inode,
-			     struct buffer_head **dirent_bh,
-			     struct ocfs2_dir_entry **dirent)
+			     struct ocfs2_dir_lookup_result *lookup)
 {
 	int status = -ENOENT;
 
-	mlog_entry("(name=%.*s, blkno=%p, inode=%p, dirent_bh=%p, dirent=%p)\n",
-		   namelen, name, blkno, inode, dirent_bh, dirent);
+	mlog(0, "name=%.*s, blkno=%p, inode=%llu\n", namelen, name, blkno,
+	     (unsigned long long)OCFS2_I(inode)->ip_blkno);
 
-	*dirent_bh = ocfs2_find_entry(name, namelen, inode, dirent);
-	if (!*dirent_bh || !*dirent) {
-		status = -ENOENT;
+	status = ocfs2_find_entry(name, namelen, inode, lookup);
+	if (status)
 		goto leave;
-	}
 
-	*blkno = le64_to_cpu((*dirent)->inode);
+	*blkno = le64_to_cpu(lookup->dl_entry->inode);
 
 	status = 0;
 leave:
-	if (status < 0) {
-		*dirent = NULL;
-		brelse(*dirent_bh);
-		*dirent_bh = NULL;
-	}
 
-	mlog_exit(status);
 	return status;
 }
 
@@ -1107,11 +2083,10 @@ int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
 			       int namelen, u64 *blkno)
 {
 	int ret;
-	struct buffer_head *bh = NULL;
-	struct ocfs2_dir_entry *dirent = NULL;
+	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
-	ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &bh, &dirent);
-	brelse(bh);
+	ret = ocfs2_find_files_on_disk(name, namelen, blkno, dir, &lookup);
+	ocfs2_free_dir_lookup_result(&lookup);
 
 	return ret;
 }
@@ -1128,20 +2103,18 @@ int ocfs2_check_dir_for_entry(struct inode *dir,
 			      int namelen)
 {
 	int ret;
-	struct buffer_head *dirent_bh = NULL;
-	struct ocfs2_dir_entry *dirent = NULL;
+	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
 	mlog_entry("dir %llu, name '%.*s'\n",
 		   (unsigned long long)OCFS2_I(dir)->ip_blkno, namelen, name);
 
 	ret = -EEXIST;
-	dirent_bh = ocfs2_find_entry(name, namelen, dir, &dirent);
-	if (dirent_bh)
+	if (ocfs2_find_entry(name, namelen, dir, &lookup) == 0)
 		goto bail;
 
 	ret = 0;
 bail:
-	brelse(dirent_bh);
+	ocfs2_free_dir_lookup_result(&lookup);
 
 	mlog_exit(ret);
 	return ret;
@@ -1151,6 +2124,7 @@ struct ocfs2_empty_dir_priv {
 	unsigned seen_dot;
 	unsigned seen_dot_dot;
 	unsigned seen_other;
+	unsigned dx_dir;
 };
 static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
 				   loff_t pos, u64 ino, unsigned type)
@@ -1160,6 +2134,13 @@ static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
 	/*
 	 * Check the positions of "." and ".." records to be sure
 	 * they're in the correct place.
+	 *
+	 * Indexed directories don't need to proceed past the first
+	 * two entries, so we end the scan after seeing '..'. Despite
+	 * that, we allow the scan to proceed In the event that we
+	 * have a corrupted indexed directory (no dot or dot dot
+	 * entries). This allows us to double check for existing
+	 * entries which might not have been found in the index.
 	 */
 	if (name_len == 1 && !strncmp(".", name, 1) && pos == 0) {
 		p->seen_dot = 1;
@@ -1169,16 +2150,57 @@ static int ocfs2_empty_dir_filldir(void *priv, const char *name, int name_len,
 	if (name_len == 2 && !strncmp("..", name, 2) &&
 	    pos == OCFS2_DIR_REC_LEN(1)) {
 		p->seen_dot_dot = 1;
+
+		if (p->dx_dir && p->seen_dot)
+			return 1;
+
 		return 0;
 	}
 
 	p->seen_other = 1;
 	return 1;
 }
+
+static int ocfs2_empty_dir_dx(struct inode *inode,
+			      struct ocfs2_empty_dir_priv *priv)
+{
+	int ret;
+	struct buffer_head *di_bh = NULL;
+	struct buffer_head *dx_root_bh = NULL;
+	struct ocfs2_dinode *di;
+	struct ocfs2_dx_root_block *dx_root;
+
+	priv->dx_dir = 1;
+
+	ret = ocfs2_read_inode_block(inode, &di_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	di = (struct ocfs2_dinode *)di_bh->b_data;
+
+	ret = ocfs2_read_dx_root(inode, di, &dx_root_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+	if (le32_to_cpu(dx_root->dr_num_entries) != 2)
+		priv->seen_other = 1;
+
+out:
+	brelse(di_bh);
+	brelse(dx_root_bh);
+	return ret;
+}
+
 /*
  * routine to check that the specified directory is empty (for rmdir)
  *
  * Returns 1 if dir is empty, zero otherwise.
+ *
+ * XXX: This is a performance problem for unindexed directories.
  */
 int ocfs2_empty_dir(struct inode *inode)
 {
@@ -1188,6 +2210,16 @@ int ocfs2_empty_dir(struct inode *inode)
 
 	memset(&priv, 0, sizeof(priv));
 
+	if (ocfs2_dir_indexed(inode)) {
+		ret = ocfs2_empty_dir_dx(inode, &priv);
+		if (ret)
+			mlog_errno(ret);
+		/*
+		 * We still run ocfs2_dir_foreach to get the checks
+		 * for "." and "..".
+		 */
+	}
+
 	ret = ocfs2_dir_foreach(inode, &start, &priv, ocfs2_empty_dir_filldir);
 	if (ret)
 		mlog_errno(ret);
@@ -1280,7 +2312,8 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb,
 				 struct inode *parent,
 				 struct inode *inode,
 				 struct buffer_head *fe_bh,
-				 struct ocfs2_alloc_context *data_ac)
+				 struct ocfs2_alloc_context *data_ac,
+				 struct buffer_head **ret_new_bh)
 {
 	int status;
 	unsigned int size = osb->sb->s_blocksize;
@@ -1289,7 +2322,7 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb,
 
 	mlog_entry_void();
 
-	if (ocfs2_supports_dir_trailer(osb))
+	if (ocfs2_new_dir_wants_trailer(inode))
 		size = ocfs2_dir_trailer_blk_off(parent->i_sb);
 
 	status = ocfs2_do_extend_dir(osb->sb, handle, inode, fe_bh,
@@ -1310,8 +2343,19 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb,
 	memset(new_bh->b_data, 0, osb->sb->s_blocksize);
 
 	de = ocfs2_fill_initial_dirents(inode, parent, new_bh->b_data, size);
-	if (ocfs2_supports_dir_trailer(osb))
-		ocfs2_init_dir_trailer(inode, new_bh);
+	if (ocfs2_new_dir_wants_trailer(inode)) {
+		int size = le16_to_cpu(de->rec_len);
+
+		/*
+		 * Figure out the size of the hole left over after
+		 * insertion of '.' and '..'. The trailer wants this
+		 * information.
+		 */
+		size -= OCFS2_DIR_REC_LEN(2);
+		size -= sizeof(struct ocfs2_dir_block_trailer);
+
+		ocfs2_init_dir_trailer(inode, new_bh, size);
+	}
 
 	status = ocfs2_journal_dirty(handle, new_bh);
 	if (status < 0) {
@@ -1329,6 +2373,10 @@ static int ocfs2_fill_new_dir_el(struct ocfs2_super *osb,
 	}
 
 	status = 0;
+	if (ret_new_bh) {
+		*ret_new_bh = new_bh;
+		new_bh = NULL;
+	}
 bail:
 	brelse(new_bh);
 
@@ -1336,20 +2384,427 @@ bail:
 	return status;
 }
 
+static int ocfs2_dx_dir_attach_index(struct ocfs2_super *osb,
+				     handle_t *handle, struct inode *dir,
+				     struct buffer_head *di_bh,
+				     struct buffer_head *dirdata_bh,
+				     struct ocfs2_alloc_context *meta_ac,
+				     int dx_inline, u32 num_entries,
+				     struct buffer_head **ret_dx_root_bh)
+{
+	int ret;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *) di_bh->b_data;
+	u16 dr_suballoc_bit;
+	u64 dr_blkno;
+	unsigned int num_bits;
+	struct buffer_head *dx_root_bh = NULL;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dir_block_trailer *trailer =
+		ocfs2_trailer_from_bh(dirdata_bh, dir->i_sb);
+
+	ret = ocfs2_claim_metadata(osb, handle, meta_ac, 1, &dr_suballoc_bit,
+				   &num_bits, &dr_blkno);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	mlog(0, "Dir %llu, attach new index block: %llu\n",
+	     (unsigned long long)OCFS2_I(dir)->ip_blkno,
+	     (unsigned long long)dr_blkno);
+
+	dx_root_bh = sb_getblk(osb->sb, dr_blkno);
+	if (dx_root_bh == NULL) {
+		ret = -EIO;
+		goto out;
+	}
+	ocfs2_set_new_buffer_uptodate(dir, dx_root_bh);
+
+	ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+				      OCFS2_JOURNAL_ACCESS_CREATE);
+	if (ret < 0) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+	memset(dx_root, 0, osb->sb->s_blocksize);
+	strcpy(dx_root->dr_signature, OCFS2_DX_ROOT_SIGNATURE);
+	dx_root->dr_suballoc_slot = cpu_to_le16(osb->slot_num);
+	dx_root->dr_suballoc_bit = cpu_to_le16(dr_suballoc_bit);
+	dx_root->dr_fs_generation = cpu_to_le32(osb->fs_generation);
+	dx_root->dr_blkno = cpu_to_le64(dr_blkno);
+	dx_root->dr_dir_blkno = cpu_to_le64(OCFS2_I(dir)->ip_blkno);
+	dx_root->dr_num_entries = cpu_to_le32(num_entries);
+	if (le16_to_cpu(trailer->db_free_rec_len))
+		dx_root->dr_free_blk = cpu_to_le64(dirdata_bh->b_blocknr);
+	else
+		dx_root->dr_free_blk = cpu_to_le64(0);
+
+	if (dx_inline) {
+		dx_root->dr_flags |= OCFS2_DX_FLAG_INLINE;
+		dx_root->dr_entries.de_count =
+			cpu_to_le16(ocfs2_dx_entries_per_root(osb->sb));
+	} else {
+		dx_root->dr_list.l_count =
+			cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb));
+	}
+
+	ret = ocfs2_journal_dirty(handle, dx_root_bh);
+	if (ret)
+		mlog_errno(ret);
+
+	ret = ocfs2_journal_access_di(handle, dir, di_bh,
+				      OCFS2_JOURNAL_ACCESS_CREATE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	di->i_dx_root = cpu_to_le64(dr_blkno);
+
+	OCFS2_I(dir)->ip_dyn_features |= OCFS2_INDEXED_DIR_FL;
+	di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features);
+
+	ret = ocfs2_journal_dirty(handle, di_bh);
+	if (ret)
+		mlog_errno(ret);
+
+	*ret_dx_root_bh = dx_root_bh;
+	dx_root_bh = NULL;
+
+out:
+	brelse(dx_root_bh);
+	return ret;
+}
+
+static int ocfs2_dx_dir_format_cluster(struct ocfs2_super *osb,
+				       handle_t *handle, struct inode *dir,
+				       struct buffer_head **dx_leaves,
+				       int num_dx_leaves, u64 start_blk)
+{
+	int ret, i;
+	struct ocfs2_dx_leaf *dx_leaf;
+	struct buffer_head *bh;
+
+	for (i = 0; i < num_dx_leaves; i++) {
+		bh = sb_getblk(osb->sb, start_blk + i);
+		if (bh == NULL) {
+			ret = -EIO;
+			goto out;
+		}
+		dx_leaves[i] = bh;
+
+		ocfs2_set_new_buffer_uptodate(dir, bh);
+
+		ret = ocfs2_journal_access_dl(handle, dir, bh,
+					      OCFS2_JOURNAL_ACCESS_CREATE);
+		if (ret < 0) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		dx_leaf = (struct ocfs2_dx_leaf *) bh->b_data;
+
+		memset(dx_leaf, 0, osb->sb->s_blocksize);
+		strcpy(dx_leaf->dl_signature, OCFS2_DX_LEAF_SIGNATURE);
+		dx_leaf->dl_fs_generation = cpu_to_le32(osb->fs_generation);
+		dx_leaf->dl_blkno = cpu_to_le64(bh->b_blocknr);
+		dx_leaf->dl_list.de_count =
+			cpu_to_le16(ocfs2_dx_entries_per_leaf(osb->sb));
+
+		mlog(0,
+		     "Dir %llu, format dx_leaf: %llu, entry count: %u\n",
+		     (unsigned long long)OCFS2_I(dir)->ip_blkno,
+		     (unsigned long long)bh->b_blocknr,
+		     le16_to_cpu(dx_leaf->dl_list.de_count));
+
+		ocfs2_journal_dirty(handle, bh);
+	}
+
+	ret = 0;
+out:
+	return ret;
+}
+
+/*
+ * Allocates and formats a new cluster for use in an indexed dir
+ * leaf. This version will not do the extent insert, so that it can be
+ * used by operations which need careful ordering.
+ */
+static int __ocfs2_dx_dir_new_cluster(struct inode *dir,
+				      u32 cpos, handle_t *handle,
+				      struct ocfs2_alloc_context *data_ac,
+				      struct buffer_head **dx_leaves,
+				      int num_dx_leaves, u64 *ret_phys_blkno)
+{
+	int ret;
+	u32 phys, num;
+	u64 phys_blkno;
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
+	/*
+	 * XXX: For create, this should claim cluster for the index
+	 * *before* the unindexed insert so that we have a better
+	 * chance of contiguousness as the directory grows in number
+	 * of entries.
+	 */
+	ret = __ocfs2_claim_clusters(osb, handle, data_ac, 1, 1, &phys, &num);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/*
+	 * Format the new cluster first. That way, we're inserting
+	 * valid data.
+	 */
+	phys_blkno = ocfs2_clusters_to_blocks(osb->sb, phys);
+	ret = ocfs2_dx_dir_format_cluster(osb, handle, dir, dx_leaves,
+					  num_dx_leaves, phys_blkno);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	*ret_phys_blkno = phys_blkno;
+out:
+	return ret;
+}
+
+static int ocfs2_dx_dir_new_cluster(struct inode *dir,
+				    struct ocfs2_extent_tree *et,
+				    u32 cpos, handle_t *handle,
+				    struct ocfs2_alloc_context *data_ac,
+				    struct ocfs2_alloc_context *meta_ac,
+				    struct buffer_head **dx_leaves,
+				    int num_dx_leaves)
+{
+	int ret;
+	u64 phys_blkno;
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+
+	ret = __ocfs2_dx_dir_new_cluster(dir, cpos, handle, data_ac, dx_leaves,
+					 num_dx_leaves, &phys_blkno);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_insert_extent(osb, handle, dir, et, cpos, phys_blkno, 1, 0,
+				  meta_ac);
+	if (ret)
+		mlog_errno(ret);
+out:
+	return ret;
+}
+
+static struct buffer_head **ocfs2_dx_dir_kmalloc_leaves(struct super_block *sb,
+							int *ret_num_leaves)
+{
+	int num_dx_leaves = ocfs2_clusters_to_blocks(sb, 1);
+	struct buffer_head **dx_leaves;
+
+	dx_leaves = kcalloc(num_dx_leaves, sizeof(struct buffer_head *),
+			    GFP_NOFS);
+	if (dx_leaves && ret_num_leaves)
+		*ret_num_leaves = num_dx_leaves;
+
+	return dx_leaves;
+}
+
+static int ocfs2_fill_new_dir_dx(struct ocfs2_super *osb,
+				 handle_t *handle,
+				 struct inode *parent,
+				 struct inode *inode,
+				 struct buffer_head *di_bh,
+				 struct ocfs2_alloc_context *data_ac,
+				 struct ocfs2_alloc_context *meta_ac)
+{
+	int ret;
+	struct buffer_head *leaf_bh = NULL;
+	struct buffer_head *dx_root_bh = NULL;
+	struct ocfs2_dx_hinfo hinfo;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dx_entry_list *entry_list;
+
+	/*
+	 * Our strategy is to create the directory as though it were
+	 * unindexed, then add the index block. This works with very
+	 * little complication since the state of a new directory is a
+	 * very well known quantity.
+	 *
+	 * Essentially, we have two dirents ("." and ".."), in the 1st
+	 * block which need indexing. These are easily inserted into
+	 * the index block.
+	 */
+
+	ret = ocfs2_fill_new_dir_el(osb, handle, parent, inode, di_bh,
+				    data_ac, &leaf_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_dx_dir_attach_index(osb, handle, inode, di_bh, leaf_bh,
+					meta_ac, 1, 2, &dx_root_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+	entry_list = &dx_root->dr_entries;
+
+	/* Buffer has been journaled for us by ocfs2_dx_dir_attach_index */
+	ocfs2_dx_dir_name_hash(inode, ".", 1, &hinfo);
+	ocfs2_dx_entry_list_insert(entry_list, &hinfo, leaf_bh->b_blocknr);
+
+	ocfs2_dx_dir_name_hash(inode, "..", 2, &hinfo);
+	ocfs2_dx_entry_list_insert(entry_list, &hinfo, leaf_bh->b_blocknr);
+
+out:
+	brelse(dx_root_bh);
+	brelse(leaf_bh);
+	return ret;
+}
+
 int ocfs2_fill_new_dir(struct ocfs2_super *osb,
 		       handle_t *handle,
 		       struct inode *parent,
 		       struct inode *inode,
 		       struct buffer_head *fe_bh,
-		       struct ocfs2_alloc_context *data_ac)
+		       struct ocfs2_alloc_context *data_ac,
+		       struct ocfs2_alloc_context *meta_ac)
+
 {
 	BUG_ON(!ocfs2_supports_inline_data(osb) && data_ac == NULL);
 
 	if (OCFS2_I(inode)->ip_dyn_features & OCFS2_INLINE_DATA_FL)
 		return ocfs2_fill_new_dir_id(osb, handle, parent, inode, fe_bh);
 
+	if (ocfs2_supports_indexed_dirs(osb))
+		return ocfs2_fill_new_dir_dx(osb, handle, parent, inode, fe_bh,
+					     data_ac, meta_ac);
+
 	return ocfs2_fill_new_dir_el(osb, handle, parent, inode, fe_bh,
-				     data_ac);
+				     data_ac, NULL);
+}
+
+static int ocfs2_dx_dir_index_block(struct inode *dir,
+				    handle_t *handle,
+				    struct buffer_head **dx_leaves,
+				    int num_dx_leaves,
+				    u32 *num_dx_entries,
+				    struct buffer_head *dirent_bh)
+{
+	int ret, namelen, i;
+	char *de_buf, *limit;
+	struct ocfs2_dir_entry *de;
+	struct buffer_head *dx_leaf_bh;
+	struct ocfs2_dx_hinfo hinfo;
+	u64 dirent_blk = dirent_bh->b_blocknr;
+
+	de_buf = dirent_bh->b_data;
+	limit = de_buf + dir->i_sb->s_blocksize;
+
+	while (de_buf < limit) {
+		de = (struct ocfs2_dir_entry *)de_buf;
+
+		namelen = de->name_len;
+		if (!namelen || !de->inode)
+			goto inc;
+
+		ocfs2_dx_dir_name_hash(dir, de->name, namelen, &hinfo);
+
+		i = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb), &hinfo);
+		dx_leaf_bh = dx_leaves[i];
+
+		ret = __ocfs2_dx_dir_leaf_insert(dir, handle, &hinfo,
+						 dirent_blk, dx_leaf_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		*num_dx_entries = *num_dx_entries + 1;
+
+inc:
+		de_buf += le16_to_cpu(de->rec_len);
+	}
+
+out:
+	return ret;
+}
+
+/*
+ * XXX: This expects dx_root_bh to already be part of the transaction.
+ */
+static void ocfs2_dx_dir_index_root_block(struct inode *dir,
+					 struct buffer_head *dx_root_bh,
+					 struct buffer_head *dirent_bh)
+{
+	char *de_buf, *limit;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dir_entry *de;
+	struct ocfs2_dx_hinfo hinfo;
+	u64 dirent_blk = dirent_bh->b_blocknr;
+
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+	de_buf = dirent_bh->b_data;
+	limit = de_buf + dir->i_sb->s_blocksize;
+
+	while (de_buf < limit) {
+		de = (struct ocfs2_dir_entry *)de_buf;
+
+		if (!de->name_len || !de->inode)
+			goto inc;
+
+		ocfs2_dx_dir_name_hash(dir, de->name, de->name_len, &hinfo);
+
+		mlog(0,
+		     "dir: %llu, major: 0x%x minor: 0x%x, index: %u, name: %.*s\n",
+		     (unsigned long long)dir->i_ino, hinfo.major_hash,
+		     hinfo.minor_hash,
+		     le16_to_cpu(dx_root->dr_entries.de_num_used),
+		     de->name_len, de->name);
+
+		ocfs2_dx_entry_list_insert(&dx_root->dr_entries, &hinfo,
+					   dirent_blk);
+
+		le32_add_cpu(&dx_root->dr_num_entries, 1);
+inc:
+		de_buf += le16_to_cpu(de->rec_len);
+	}
+}
+
+/*
+ * Count the number of inline directory entries in di_bh and compare
+ * them against the number of entries we can hold in an inline dx root
+ * block.
+ */
+static int ocfs2_new_dx_should_be_inline(struct inode *dir,
+					 struct buffer_head *di_bh)
+{
+	int dirent_count = 0;
+	char *de_buf, *limit;
+	struct ocfs2_dir_entry *de;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+
+	de_buf = di->id2.i_data.id_data;
+	limit = de_buf + i_size_read(dir);
+
+	while (de_buf < limit) {
+		de = (struct ocfs2_dir_entry *)de_buf;
+
+		if (de->name_len && de->inode)
+			dirent_count++;
+
+		de_buf += le16_to_cpu(de->rec_len);
+	}
+
+	/* We are careful to leave room for one extra record. */
+	return dirent_count < ocfs2_dx_entries_per_root(dir->i_sb);
 }
 
 /*
@@ -1358,18 +2813,26 @@ int ocfs2_fill_new_dir(struct ocfs2_super *osb,
  * expansion from an inline directory to one with extents. The first dir block
  * in that case is taken from the inline data portion of the inode block.
  *
+ * This will also return the largest amount of contiguous space for a dirent
+ * in the block. That value is *not* necessarily the last dirent, even after
+ * expansion. The directory indexing code wants this value for free space
+ * accounting. We do this here since we're already walking the entire dir
+ * block.
+ *
  * We add the dir trailer if this filesystem wants it.
  */
-static void ocfs2_expand_last_dirent(char *start, unsigned int old_size,
-				     struct super_block *sb)
+static unsigned int ocfs2_expand_last_dirent(char *start, unsigned int old_size,
+					     struct inode *dir)
 {
+	struct super_block *sb = dir->i_sb;
 	struct ocfs2_dir_entry *de;
 	struct ocfs2_dir_entry *prev_de;
 	char *de_buf, *limit;
 	unsigned int new_size = sb->s_blocksize;
-	unsigned int bytes;
+	unsigned int bytes, this_hole;
+	unsigned int largest_hole = 0;
 
-	if (ocfs2_supports_dir_trailer(OCFS2_SB(sb)))
+	if (ocfs2_new_dir_wants_trailer(dir))
 		new_size = ocfs2_dir_trailer_blk_off(sb);
 
 	bytes = new_size - old_size;
@@ -1378,12 +2841,26 @@ static void ocfs2_expand_last_dirent(char *start, unsigned int old_size,
 	de_buf = start;
 	de = (struct ocfs2_dir_entry *)de_buf;
 	do {
+		this_hole = ocfs2_figure_dirent_hole(de);
+		if (this_hole > largest_hole)
+			largest_hole = this_hole;
+
 		prev_de = de;
 		de_buf += le16_to_cpu(de->rec_len);
 		de = (struct ocfs2_dir_entry *)de_buf;
 	} while (de_buf < limit);
 
 	le16_add_cpu(&prev_de->rec_len, bytes);
+
+	/* We need to double check this after modification of the final
+	 * dirent. */
+	this_hole = ocfs2_figure_dirent_hole(prev_de);
+	if (this_hole > largest_hole)
+		largest_hole = this_hole;
+
+	if (largest_hole >= OCFS2_DIR_MIN_REC_LEN)
+		return largest_hole;
+	return 0;
 }
 
 /*
@@ -1396,29 +2873,61 @@ static void ocfs2_expand_last_dirent(char *start, unsigned int old_size,
  */
 static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 				   unsigned int blocks_wanted,
+				   struct ocfs2_dir_lookup_result *lookup,
 				   struct buffer_head **first_block_bh)
 {
-	u32 alloc, bit_off, len;
+	u32 alloc, dx_alloc, bit_off, len, num_dx_entries = 0;
 	struct super_block *sb = dir->i_sb;
-	int ret, credits = ocfs2_inline_to_extents_credits(sb);
-	u64 blkno, bytes = blocks_wanted << sb->s_blocksize_bits;
+	int ret, i, num_dx_leaves = 0, dx_inline = 0,
+		credits = ocfs2_inline_to_extents_credits(sb);
+	u64 dx_insert_blkno, blkno,
+		bytes = blocks_wanted << sb->s_blocksize_bits;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
 	struct ocfs2_inode_info *oi = OCFS2_I(dir);
 	struct ocfs2_alloc_context *data_ac;
+	struct ocfs2_alloc_context *meta_ac = NULL;
 	struct buffer_head *dirdata_bh = NULL;
+	struct buffer_head *dx_root_bh = NULL;
+	struct buffer_head **dx_leaves = NULL;
 	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
 	handle_t *handle;
 	struct ocfs2_extent_tree et;
-	int did_quota = 0;
+	struct ocfs2_extent_tree dx_et;
+	int did_quota = 0, bytes_allocated = 0;
 
 	ocfs2_init_dinode_extent_tree(&et, dir, di_bh);
 
 	alloc = ocfs2_clusters_for_bytes(sb, bytes);
+	dx_alloc = 0;
+
+	if (ocfs2_supports_indexed_dirs(osb)) {
+		credits += ocfs2_add_dir_index_credits(sb);
+
+		dx_inline = ocfs2_new_dx_should_be_inline(dir, di_bh);
+		if (!dx_inline) {
+			/* Add one more cluster for an index leaf */
+			dx_alloc++;
+			dx_leaves = ocfs2_dx_dir_kmalloc_leaves(sb,
+								&num_dx_leaves);
+			if (!dx_leaves) {
+				ret = -ENOMEM;
+				mlog_errno(ret);
+				goto out;
+			}
+		}
+
+		/* This gets us the dx_root */
+		ret = ocfs2_reserve_new_metadata_blocks(osb, 1, &meta_ac);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
 
 	/*
-	 * We should never need more than 2 clusters for this -
-	 * maximum dirent size is far less than one block. In fact,
-	 * the only time we'd need more than one cluster is if
+	 * We should never need more than 2 clusters for the unindexed
+	 * tree - maximum dirent size is far less than one block. In
+	 * fact, the only time we'd need more than one cluster is if
 	 * blocksize == clustersize and the dirent won't fit in the
 	 * extra space that the expansion to a single block gives. As
 	 * of today, that only happens on 4k/4k file systems.
@@ -1435,7 +2944,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 
 	/*
 	 * Prepare for worst case allocation scenario of two separate
-	 * extents.
+	 * extents in the unindexed tree.
 	 */
 	if (alloc == 2)
 		credits += OCFS2_SUBALLOC_ALLOC;
@@ -1448,11 +2957,29 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 	}
 
 	if (vfs_dq_alloc_space_nodirty(dir,
-				ocfs2_clusters_to_bytes(osb->sb, alloc))) {
+				ocfs2_clusters_to_bytes(osb->sb,
+							alloc + dx_alloc))) {
 		ret = -EDQUOT;
 		goto out_commit;
 	}
 	did_quota = 1;
+
+	if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) {
+		/*
+		 * Allocate our index cluster first, to maximize the
+		 * possibility that unindexed leaves grow
+		 * contiguously.
+		 */
+		ret = __ocfs2_dx_dir_new_cluster(dir, 0, handle, data_ac,
+						 dx_leaves, num_dx_leaves,
+						 &dx_insert_blkno);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+		bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1);
+	}
+
 	/*
 	 * Try to claim as many clusters as the bitmap can give though
 	 * if we only get one now, that's enough to continue. The rest
@@ -1463,6 +2990,7 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 		mlog_errno(ret);
 		goto out_commit;
 	}
+	bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1);
 
 	/*
 	 * Operations are carefully ordered so that we set up the new
@@ -1489,9 +3017,16 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 	memcpy(dirdata_bh->b_data, di->id2.i_data.id_data, i_size_read(dir));
 	memset(dirdata_bh->b_data + i_size_read(dir), 0,
 	       sb->s_blocksize - i_size_read(dir));
-	ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), sb);
-	if (ocfs2_supports_dir_trailer(osb))
-		ocfs2_init_dir_trailer(dir, dirdata_bh);
+	i = ocfs2_expand_last_dirent(dirdata_bh->b_data, i_size_read(dir), dir);
+	if (ocfs2_new_dir_wants_trailer(dir)) {
+		/*
+		 * Prepare the dir trailer up front. It will otherwise look
+		 * like a valid dirent. Even if inserting the index fails
+		 * (unlikely), then all we'll have done is given first dir
+		 * block a small amount of fragmentation.
+		 */
+		ocfs2_init_dir_trailer(dir, dirdata_bh, i);
+	}
 
 	ret = ocfs2_journal_dirty(handle, dirdata_bh);
 	if (ret) {
@@ -1499,6 +3034,24 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 		goto out_commit;
 	}
 
+	if (ocfs2_supports_indexed_dirs(osb) && !dx_inline) {
+		/*
+		 * Dx dirs with an external cluster need to do this up
+		 * front. Inline dx root's get handled later, after
+		 * we've allocated our root block. We get passed back
+		 * a total number of items so that dr_num_entries can
+		 * be correctly set once the dx_root has been
+		 * allocated.
+		 */
+		ret = ocfs2_dx_dir_index_block(dir, handle, dx_leaves,
+					       num_dx_leaves, &num_dx_entries,
+					       dirdata_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+	}
+
 	/*
 	 * Set extent, i_size, etc on the directory. After this, the
 	 * inode should contain the same exact dirents as before and
@@ -1551,6 +3104,27 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 		goto out_commit;
 	}
 
+	if (ocfs2_supports_indexed_dirs(osb)) {
+		ret = ocfs2_dx_dir_attach_index(osb, handle, dir, di_bh,
+						dirdata_bh, meta_ac, dx_inline,
+						num_dx_entries, &dx_root_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+
+		if (dx_inline) {
+			ocfs2_dx_dir_index_root_block(dir, dx_root_bh,
+						      dirdata_bh);
+		} else {
+			ocfs2_init_dx_root_extent_tree(&dx_et, dir, dx_root_bh);
+			ret = ocfs2_insert_extent(osb, handle, dir, &dx_et, 0,
+						  dx_insert_blkno, 1, 0, NULL);
+			if (ret)
+				mlog_errno(ret);
+		}
+	}
+
 	/*
 	 * We asked for two clusters, but only got one in the 1st
 	 * pass. Claim the 2nd cluster as a separate extent.
@@ -1570,15 +3144,32 @@ static int ocfs2_expand_inline_dir(struct inode *dir, struct buffer_head *di_bh,
 			mlog_errno(ret);
 			goto out_commit;
 		}
+		bytes_allocated += ocfs2_clusters_to_bytes(dir->i_sb, 1);
 	}
 
 	*first_block_bh = dirdata_bh;
 	dirdata_bh = NULL;
+	if (ocfs2_supports_indexed_dirs(osb)) {
+		unsigned int off;
+
+		if (!dx_inline) {
+			/*
+			 * We need to return the correct block within the
+			 * cluster which should hold our entry.
+			 */
+			off = ocfs2_dx_dir_hash_idx(OCFS2_SB(dir->i_sb),
+						    &lookup->dl_hinfo);
+			get_bh(dx_leaves[off]);
+			lookup->dl_dx_leaf_bh = dx_leaves[off];
+		}
+		lookup->dl_dx_root_bh = dx_root_bh;
+		dx_root_bh = NULL;
+	}
 
 out_commit:
 	if (ret < 0 && did_quota)
-		vfs_dq_free_space_nodirty(dir,
-			ocfs2_clusters_to_bytes(osb->sb, 2));
+		vfs_dq_free_space_nodirty(dir, bytes_allocated);
+
 	ocfs2_commit_trans(osb, handle);
 
 out_sem:
@@ -1587,8 +3178,17 @@ out_sem:
 out:
 	if (data_ac)
 		ocfs2_free_alloc_context(data_ac);
+	if (meta_ac)
+		ocfs2_free_alloc_context(meta_ac);
+
+	if (dx_leaves) {
+		for (i = 0; i < num_dx_leaves; i++)
+			brelse(dx_leaves[i]);
+		kfree(dx_leaves);
+	}
 
 	brelse(dirdata_bh);
+	brelse(dx_root_bh);
 
 	return ret;
 }
@@ -1658,11 +3258,14 @@ bail:
  * is to be turned into an extent based one. The size of the dirent to
  * insert might be larger than the space gained by growing to just one
  * block, so we may have to grow the inode by two blocks in that case.
+ *
+ * If the directory is already indexed, dx_root_bh must be provided.
  */
 static int ocfs2_extend_dir(struct ocfs2_super *osb,
 			    struct inode *dir,
 			    struct buffer_head *parent_fe_bh,
 			    unsigned int blocks_wanted,
+			    struct ocfs2_dir_lookup_result *lookup,
 			    struct buffer_head **new_de_bh)
 {
 	int status = 0;
@@ -1677,17 +3280,29 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 	struct ocfs2_dir_entry * de;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_extent_tree et;
+	struct buffer_head *dx_root_bh = lookup->dl_dx_root_bh;
 
 	mlog_entry_void();
 
 	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
+		/*
+		 * This would be a code error as an inline directory should
+		 * never have an index root.
+		 */
+		BUG_ON(dx_root_bh);
+
 		status = ocfs2_expand_inline_dir(dir, parent_fe_bh,
-						 blocks_wanted, &new_bh);
+						 blocks_wanted, lookup,
+						 &new_bh);
 		if (status) {
 			mlog_errno(status);
 			goto bail;
 		}
 
+		/* Expansion from inline to an indexed directory will
+		 * have given us this. */
+		dx_root_bh = lookup->dl_dx_root_bh;
+
 		if (blocks_wanted == 1) {
 			/*
 			 * If the new dirent will fit inside the space
@@ -1751,6 +3366,10 @@ static int ocfs2_extend_dir(struct ocfs2_super *osb,
 	}
 
 do_extend:
+	if (ocfs2_dir_indexed(dir))
+		credits++; /* For attaching the new dirent block to the
+			    * dx_root */
+
 	down_write(&OCFS2_I(dir)->ip_alloc_sem);
 	drop_alloc_sem = 1;
 
@@ -1781,9 +3400,19 @@ do_extend:
 
 	de = (struct ocfs2_dir_entry *) new_bh->b_data;
 	de->inode = 0;
-	if (ocfs2_dir_has_trailer(dir)) {
+	if (ocfs2_supports_dir_trailer(dir)) {
 		de->rec_len = cpu_to_le16(ocfs2_dir_trailer_blk_off(sb));
-		ocfs2_init_dir_trailer(dir, new_bh);
+
+		ocfs2_init_dir_trailer(dir, new_bh, le16_to_cpu(de->rec_len));
+
+		if (ocfs2_dir_indexed(dir)) {
+			status = ocfs2_dx_dir_link_trailer(dir, handle,
+							   dx_root_bh, new_bh);
+			if (status) {
+				mlog_errno(status);
+				goto bail;
+			}
+		}
 	} else {
 		de->rec_len = cpu_to_le16(sb->s_blocksize);
 	}
@@ -1839,7 +3468,7 @@ static int ocfs2_find_dir_space_id(struct inode *dir, struct buffer_head *di_bh,
 	 * This calculates how many free bytes we'd have in block zero, should
 	 * this function force expansion to an extent tree.
 	 */
-	if (ocfs2_supports_dir_trailer(OCFS2_SB(sb)))
+	if (ocfs2_new_dir_wants_trailer(dir))
 		free_space = ocfs2_dir_trailer_blk_off(sb) - i_size_read(dir);
 	else
 		free_space = dir->i_sb->s_blocksize - i_size_read(dir);
@@ -1970,12 +3599,766 @@ bail:
 	return status;
 }
 
+static int dx_leaf_sort_cmp(const void *a, const void *b)
+{
+	const struct ocfs2_dx_entry *entry1 = a;
+	const struct ocfs2_dx_entry *entry2 = b;
+	u32 major_hash1 = le32_to_cpu(entry1->dx_major_hash);
+	u32 major_hash2 = le32_to_cpu(entry2->dx_major_hash);
+	u32 minor_hash1 = le32_to_cpu(entry1->dx_minor_hash);
+	u32 minor_hash2 = le32_to_cpu(entry2->dx_minor_hash);
+
+	if (major_hash1 > major_hash2)
+		return 1;
+	if (major_hash1 < major_hash2)
+		return -1;
+
+	/*
+	 * It is not strictly necessary to sort by minor
+	 */
+	if (minor_hash1 > minor_hash2)
+		return 1;
+	if (minor_hash1 < minor_hash2)
+		return -1;
+	return 0;
+}
+
+static void dx_leaf_sort_swap(void *a, void *b, int size)
+{
+	struct ocfs2_dx_entry *entry1 = a;
+	struct ocfs2_dx_entry *entry2 = b;
+	struct ocfs2_dx_entry tmp;
+
+	BUG_ON(size != sizeof(*entry1));
+
+	tmp = *entry1;
+	*entry1 = *entry2;
+	*entry2 = tmp;
+}
+
+static int ocfs2_dx_leaf_same_major(struct ocfs2_dx_leaf *dx_leaf)
+{
+	struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list;
+	int i, num = le16_to_cpu(dl_list->de_num_used);
+
+	for (i = 0; i < (num - 1); i++) {
+		if (le32_to_cpu(dl_list->de_entries[i].dx_major_hash) !=
+		    le32_to_cpu(dl_list->de_entries[i + 1].dx_major_hash))
+			return 0;
+	}
+
+	return 1;
+}
+
+/*
+ * Find the optimal value to split this leaf on. This expects the leaf
+ * entries to be in sorted order.
+ *
+ * leaf_cpos is the cpos of the leaf we're splitting. insert_hash is
+ * the hash we want to insert.
+ *
+ * This function is only concerned with the major hash - that which
+ * determines which cluster an item belongs to.
+ */
+static int ocfs2_dx_dir_find_leaf_split(struct ocfs2_dx_leaf *dx_leaf,
+					u32 leaf_cpos, u32 insert_hash,
+					u32 *split_hash)
+{
+	struct ocfs2_dx_entry_list *dl_list = &dx_leaf->dl_list;
+	int i, num_used = le16_to_cpu(dl_list->de_num_used);
+	int allsame;
+
+	/*
+	 * There's a couple rare, but nasty corner cases we have to
+	 * check for here. All of them involve a leaf where all value
+	 * have the same hash, which is what we look for first.
+	 *
+	 * Most of the time, all of the above is false, and we simply
+	 * pick the median value for a split.
+	 */
+	allsame = ocfs2_dx_leaf_same_major(dx_leaf);
+	if (allsame) {
+		u32 val = le32_to_cpu(dl_list->de_entries[0].dx_major_hash);
+
+		if (val == insert_hash) {
+			/*
+			 * No matter where we would choose to split,
+			 * the new entry would want to occupy the same
+			 * block as these. Since there's no space left
+			 * in their existing block, we know there
+			 * won't be space after the split.
+			 */
+			return -ENOSPC;
+		}
+
+		if (val == leaf_cpos) {
+			/*
+			 * Because val is the same as leaf_cpos (which
+			 * is the smallest value this leaf can have),
+			 * yet is not equal to insert_hash, then we
+			 * know that insert_hash *must* be larger than
+			 * val (and leaf_cpos). At least cpos+1 in value.
+			 *
+			 * We also know then, that there cannot be an
+			 * adjacent extent (otherwise we'd be looking
+			 * at it). Choosing this value gives us a
+			 * chance to get some contiguousness.
+			 */
+			*split_hash = leaf_cpos + 1;
+			return 0;
+		}
+
+		if (val > insert_hash) {
+			/*
+			 * val can not be the same as insert hash, and
+			 * also must be larger than leaf_cpos. Also,
+			 * we know that there can't be a leaf between
+			 * cpos and val, otherwise the entries with
+			 * hash 'val' would be there.
+			 */
+			*split_hash = val;
+			return 0;
+		}
+
+		*split_hash = insert_hash;
+		return 0;
+	}
+
+	/*
+	 * Since the records are sorted and the checks above
+	 * guaranteed that not all records in this block are the same,
+	 * we simple travel forward, from the median, and pick the 1st
+	 * record whose value is larger than leaf_cpos.
+	 */
+	for (i = (num_used / 2); i < num_used; i++)
+		if (le32_to_cpu(dl_list->de_entries[i].dx_major_hash) >
+		    leaf_cpos)
+			break;
+
+	BUG_ON(i == num_used); /* Should be impossible */
+	*split_hash = le32_to_cpu(dl_list->de_entries[i].dx_major_hash);
+	return 0;
+}
+
+/*
+ * Transfer all entries in orig_dx_leaves whose major hash is equal to or
+ * larger than split_hash into new_dx_leaves. We use a temporary
+ * buffer (tmp_dx_leaf) to make the changes to the original leaf blocks.
+ *
+ * Since the block offset inside a leaf (cluster) is a constant mask
+ * of minor_hash, we can optimize - an item at block offset X within
+ * the original cluster, will be at offset X within the new cluster.
+ */
+static void ocfs2_dx_dir_transfer_leaf(struct inode *dir, u32 split_hash,
+				       handle_t *handle,
+				       struct ocfs2_dx_leaf *tmp_dx_leaf,
+				       struct buffer_head **orig_dx_leaves,
+				       struct buffer_head **new_dx_leaves,
+				       int num_dx_leaves)
+{
+	int i, j, num_used;
+	u32 major_hash;
+	struct ocfs2_dx_leaf *orig_dx_leaf, *new_dx_leaf;
+	struct ocfs2_dx_entry_list *orig_list, *new_list, *tmp_list;
+	struct ocfs2_dx_entry *dx_entry;
+
+	tmp_list = &tmp_dx_leaf->dl_list;
+
+	for (i = 0; i < num_dx_leaves; i++) {
+		orig_dx_leaf = (struct ocfs2_dx_leaf *) orig_dx_leaves[i]->b_data;
+		orig_list = &orig_dx_leaf->dl_list;
+		new_dx_leaf = (struct ocfs2_dx_leaf *) new_dx_leaves[i]->b_data;
+		new_list = &new_dx_leaf->dl_list;
+
+		num_used = le16_to_cpu(orig_list->de_num_used);
+
+		memcpy(tmp_dx_leaf, orig_dx_leaf, dir->i_sb->s_blocksize);
+		tmp_list->de_num_used = cpu_to_le16(0);
+		memset(&tmp_list->de_entries, 0, sizeof(*dx_entry)*num_used);
+
+		for (j = 0; j < num_used; j++) {
+			dx_entry = &orig_list->de_entries[j];
+			major_hash = le32_to_cpu(dx_entry->dx_major_hash);
+			if (major_hash >= split_hash)
+				ocfs2_dx_dir_leaf_insert_tail(new_dx_leaf,
+							      dx_entry);
+			else
+				ocfs2_dx_dir_leaf_insert_tail(tmp_dx_leaf,
+							      dx_entry);
+		}
+		memcpy(orig_dx_leaf, tmp_dx_leaf, dir->i_sb->s_blocksize);
+
+		ocfs2_journal_dirty(handle, orig_dx_leaves[i]);
+		ocfs2_journal_dirty(handle, new_dx_leaves[i]);
+	}
+}
+
+static int ocfs2_dx_dir_rebalance_credits(struct ocfs2_super *osb,
+					  struct ocfs2_dx_root_block *dx_root)
+{
+	int credits = ocfs2_clusters_to_blocks(osb->sb, 2);
+
+	credits += ocfs2_calc_extend_credits(osb->sb, &dx_root->dr_list, 1);
+	credits += ocfs2_quota_trans_credits(osb->sb);
+	return credits;
+}
+
+/*
+ * Find the median value in dx_leaf_bh and allocate a new leaf to move
+ * half our entries into.
+ */
+static int ocfs2_dx_dir_rebalance(struct ocfs2_super *osb, struct inode *dir,
+				  struct buffer_head *dx_root_bh,
+				  struct buffer_head *dx_leaf_bh,
+				  struct ocfs2_dx_hinfo *hinfo, u32 leaf_cpos,
+				  u64 leaf_blkno)
+{
+	struct ocfs2_dx_leaf *dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data;
+	int credits, ret, i, num_used, did_quota = 0;
+	u32 cpos, split_hash, insert_hash = hinfo->major_hash;
+	u64 orig_leaves_start;
+	int num_dx_leaves;
+	struct buffer_head **orig_dx_leaves = NULL;
+	struct buffer_head **new_dx_leaves = NULL;
+	struct ocfs2_alloc_context *data_ac = NULL, *meta_ac = NULL;
+	struct ocfs2_extent_tree et;
+	handle_t *handle = NULL;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dx_leaf *tmp_dx_leaf = NULL;
+
+	mlog(0, "DX Dir: %llu, rebalance leaf leaf_blkno: %llu insert: %u\n",
+	     (unsigned long long)OCFS2_I(dir)->ip_blkno,
+	     (unsigned long long)leaf_blkno, insert_hash);
+
+	ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh);
+
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+	/*
+	 * XXX: This is a rather large limit. We should use a more
+	 * realistic value.
+	 */
+	if (le32_to_cpu(dx_root->dr_clusters) == UINT_MAX)
+		return -ENOSPC;
+
+	num_used = le16_to_cpu(dx_leaf->dl_list.de_num_used);
+	if (num_used < le16_to_cpu(dx_leaf->dl_list.de_count)) {
+		mlog(ML_ERROR, "DX Dir: %llu, Asked to rebalance empty leaf: "
+		     "%llu, %d\n", (unsigned long long)OCFS2_I(dir)->ip_blkno,
+		     (unsigned long long)leaf_blkno, num_used);
+		ret = -EIO;
+		goto out;
+	}
+
+	orig_dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, &num_dx_leaves);
+	if (!orig_dx_leaves) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	new_dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, NULL);
+	if (!new_dx_leaves) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_lock_allocators(dir, &et, 1, 0, &data_ac, &meta_ac);
+	if (ret) {
+		if (ret != -ENOSPC)
+			mlog_errno(ret);
+		goto out;
+	}
+
+	credits = ocfs2_dx_dir_rebalance_credits(osb, dx_root);
+	handle = ocfs2_start_trans(osb, credits);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		handle = NULL;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (vfs_dq_alloc_space_nodirty(dir,
+				       ocfs2_clusters_to_bytes(dir->i_sb, 1))) {
+		ret = -EDQUOT;
+		goto out_commit;
+	}
+	did_quota = 1;
+
+	ret = ocfs2_journal_access_dl(handle, dir, dx_leaf_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * This block is changing anyway, so we can sort it in place.
+	 */
+	sort(dx_leaf->dl_list.de_entries, num_used,
+	     sizeof(struct ocfs2_dx_entry), dx_leaf_sort_cmp,
+	     dx_leaf_sort_swap);
+
+	ret = ocfs2_journal_dirty(handle, dx_leaf_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	ret = ocfs2_dx_dir_find_leaf_split(dx_leaf, leaf_cpos, insert_hash,
+					   &split_hash);
+	if (ret) {
+		mlog_errno(ret);
+		goto  out_commit;
+	}
+
+	mlog(0, "Split leaf (%u) at %u, insert major hash is %u\n",
+	     leaf_cpos, split_hash, insert_hash);
+
+	/*
+	 * We have to carefully order operations here. There are items
+	 * which want to be in the new cluster before insert, but in
+	 * order to put those items in the new cluster, we alter the
+	 * old cluster. A failure to insert gets nasty.
+	 *
+	 * So, start by reserving writes to the old
+	 * cluster. ocfs2_dx_dir_new_cluster will reserve writes on
+	 * the new cluster for us, before inserting it. The insert
+	 * won't happen if there's an error before that. Once the
+	 * insert is done then, we can transfer from one leaf into the
+	 * other without fear of hitting any error.
+	 */
+
+	/*
+	 * The leaf transfer wants some scratch space so that we don't
+	 * wind up doing a bunch of expensive memmove().
+	 */
+	tmp_dx_leaf = kmalloc(osb->sb->s_blocksize, GFP_NOFS);
+	if (!tmp_dx_leaf) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	orig_leaves_start = ocfs2_block_to_cluster_start(dir->i_sb, leaf_blkno);
+	ret = ocfs2_read_dx_leaves(dir, orig_leaves_start, num_dx_leaves,
+				   orig_dx_leaves);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	for (i = 0; i < num_dx_leaves; i++) {
+		ret = ocfs2_journal_access_dl(handle, dir, orig_dx_leaves[i],
+					      OCFS2_JOURNAL_ACCESS_WRITE);
+		if (ret) {
+			mlog_errno(ret);
+			goto out_commit;
+		}
+	}
+
+	cpos = split_hash;
+	ret = ocfs2_dx_dir_new_cluster(dir, &et, cpos, handle,
+				       data_ac, meta_ac, new_dx_leaves,
+				       num_dx_leaves);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	ocfs2_dx_dir_transfer_leaf(dir, split_hash, handle, tmp_dx_leaf,
+				   orig_dx_leaves, new_dx_leaves, num_dx_leaves);
+
+out_commit:
+	if (ret < 0 && did_quota)
+		vfs_dq_free_space_nodirty(dir,
+				ocfs2_clusters_to_bytes(dir->i_sb, 1));
+
+	ocfs2_commit_trans(osb, handle);
+
+out:
+	if (orig_dx_leaves || new_dx_leaves) {
+		for (i = 0; i < num_dx_leaves; i++) {
+			if (orig_dx_leaves)
+				brelse(orig_dx_leaves[i]);
+			if (new_dx_leaves)
+				brelse(new_dx_leaves[i]);
+		}
+		kfree(orig_dx_leaves);
+		kfree(new_dx_leaves);
+	}
+
+	if (meta_ac)
+		ocfs2_free_alloc_context(meta_ac);
+	if (data_ac)
+		ocfs2_free_alloc_context(data_ac);
+
+	kfree(tmp_dx_leaf);
+	return ret;
+}
+
+static int ocfs2_find_dir_space_dx(struct ocfs2_super *osb, struct inode *dir,
+				   struct buffer_head *di_bh,
+				   struct buffer_head *dx_root_bh,
+				   const char *name, int namelen,
+				   struct ocfs2_dir_lookup_result *lookup)
+{
+	int ret, rebalanced = 0;
+	struct ocfs2_dx_root_block *dx_root;
+	struct buffer_head *dx_leaf_bh = NULL;
+	struct ocfs2_dx_leaf *dx_leaf;
+	u64 blkno;
+	u32 leaf_cpos;
+
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+restart_search:
+	ret = ocfs2_dx_dir_lookup(dir, &dx_root->dr_list, &lookup->dl_hinfo,
+				  &leaf_cpos, &blkno);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ret = ocfs2_read_dx_leaf(dir, blkno, &dx_leaf_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	dx_leaf = (struct ocfs2_dx_leaf *)dx_leaf_bh->b_data;
+
+	if (le16_to_cpu(dx_leaf->dl_list.de_num_used) >=
+	    le16_to_cpu(dx_leaf->dl_list.de_count)) {
+		if (rebalanced) {
+			/*
+			 * Rebalancing should have provided us with
+			 * space in an appropriate leaf.
+			 *
+			 * XXX: Is this an abnormal condition then?
+			 * Should we print a message here?
+			 */
+			ret = -ENOSPC;
+			goto out;
+		}
+
+		ret = ocfs2_dx_dir_rebalance(osb, dir, dx_root_bh, dx_leaf_bh,
+					     &lookup->dl_hinfo, leaf_cpos,
+					     blkno);
+		if (ret) {
+			if (ret != -ENOSPC)
+				mlog_errno(ret);
+			goto out;
+		}
+
+		/*
+		 * Restart the lookup. The rebalance might have
+		 * changed which block our item fits into. Mark our
+		 * progress, so we only execute this once.
+		 */
+		brelse(dx_leaf_bh);
+		dx_leaf_bh = NULL;
+		rebalanced = 1;
+		goto restart_search;
+	}
+
+	lookup->dl_dx_leaf_bh = dx_leaf_bh;
+	dx_leaf_bh = NULL;
+
+out:
+	brelse(dx_leaf_bh);
+	return ret;
+}
+
+static int ocfs2_search_dx_free_list(struct inode *dir,
+				     struct buffer_head *dx_root_bh,
+				     int namelen,
+				     struct ocfs2_dir_lookup_result *lookup)
+{
+	int ret = -ENOSPC;
+	struct buffer_head *leaf_bh = NULL, *prev_leaf_bh = NULL;
+	struct ocfs2_dir_block_trailer *db;
+	u64 next_block;
+	int rec_len = OCFS2_DIR_REC_LEN(namelen);
+	struct ocfs2_dx_root_block *dx_root;
+
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+	next_block = le64_to_cpu(dx_root->dr_free_blk);
+
+	while (next_block) {
+		brelse(prev_leaf_bh);
+		prev_leaf_bh = leaf_bh;
+		leaf_bh = NULL;
+
+		ret = ocfs2_read_dir_block_direct(dir, next_block, &leaf_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		db = ocfs2_trailer_from_bh(leaf_bh, dir->i_sb);
+		if (rec_len <= le16_to_cpu(db->db_free_rec_len)) {
+			lookup->dl_leaf_bh = leaf_bh;
+			lookup->dl_prev_leaf_bh = prev_leaf_bh;
+			leaf_bh = NULL;
+			prev_leaf_bh = NULL;
+			break;
+		}
+
+		next_block = le64_to_cpu(db->db_free_next);
+	}
+
+	if (!next_block)
+		ret = -ENOSPC;
+
+out:
+
+	brelse(leaf_bh);
+	brelse(prev_leaf_bh);
+	return ret;
+}
+
+static int ocfs2_expand_inline_dx_root(struct inode *dir,
+				       struct buffer_head *dx_root_bh)
+{
+	int ret, num_dx_leaves, i, j, did_quota = 0;
+	struct buffer_head **dx_leaves = NULL;
+	struct ocfs2_extent_tree et;
+	u64 insert_blkno;
+	struct ocfs2_alloc_context *data_ac = NULL;
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	handle_t *handle = NULL;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dx_entry_list *entry_list;
+	struct ocfs2_dx_entry *dx_entry;
+	struct ocfs2_dx_leaf *target_leaf;
+
+	ret = ocfs2_reserve_clusters(osb, 1, &data_ac);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	dx_leaves = ocfs2_dx_dir_kmalloc_leaves(osb->sb, &num_dx_leaves);
+	if (!dx_leaves) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	handle = ocfs2_start_trans(osb, ocfs2_calc_dxi_expand_credits(osb->sb));
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (vfs_dq_alloc_space_nodirty(dir,
+				       ocfs2_clusters_to_bytes(osb->sb, 1))) {
+		ret = -EDQUOT;
+		goto out_commit;
+	}
+	did_quota = 1;
+
+	/*
+	 * We do this up front, before the allocation, so that a
+	 * failure to add the dx_root_bh to the journal won't result
+	 * us losing clusters.
+	 */
+	ret = ocfs2_journal_access_dr(handle, dir, dx_root_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	ret = __ocfs2_dx_dir_new_cluster(dir, 0, handle, data_ac, dx_leaves,
+					 num_dx_leaves, &insert_blkno);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	/*
+	 * Transfer the entries from our dx_root into the appropriate
+	 * block
+	 */
+	dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data;
+	entry_list = &dx_root->dr_entries;
+
+	for (i = 0; i < le16_to_cpu(entry_list->de_num_used); i++) {
+		dx_entry = &entry_list->de_entries[i];
+
+		j = __ocfs2_dx_dir_hash_idx(osb,
+					    le32_to_cpu(dx_entry->dx_minor_hash));
+		target_leaf = (struct ocfs2_dx_leaf *)dx_leaves[j]->b_data;
+
+		ocfs2_dx_dir_leaf_insert_tail(target_leaf, dx_entry);
+
+		/* Each leaf has been passed to the journal already
+		 * via __ocfs2_dx_dir_new_cluster() */
+	}
+
+	dx_root->dr_flags &= ~OCFS2_DX_FLAG_INLINE;
+	memset(&dx_root->dr_list, 0, osb->sb->s_blocksize -
+	       offsetof(struct ocfs2_dx_root_block, dr_list));
+	dx_root->dr_list.l_count =
+		cpu_to_le16(ocfs2_extent_recs_per_dx_root(osb->sb));
+
+	/* This should never fail considering we start with an empty
+	 * dx_root. */
+	ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh);
+	ret = ocfs2_insert_extent(osb, handle, dir, &et, 0,
+				  insert_blkno, 1, 0, NULL);
+	if (ret)
+		mlog_errno(ret);
+	did_quota = 0;
+
+	ocfs2_journal_dirty(handle, dx_root_bh);
+
+out_commit:
+	if (ret < 0 && did_quota)
+		vfs_dq_free_space_nodirty(dir,
+					  ocfs2_clusters_to_bytes(dir->i_sb, 1));
+
+	ocfs2_commit_trans(osb, handle);
+
+out:
+	if (data_ac)
+		ocfs2_free_alloc_context(data_ac);
+
+	if (dx_leaves) {
+		for (i = 0; i < num_dx_leaves; i++)
+			brelse(dx_leaves[i]);
+		kfree(dx_leaves);
+	}
+	return ret;
+}
+
+static int ocfs2_inline_dx_has_space(struct buffer_head *dx_root_bh)
+{
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dx_entry_list *entry_list;
+
+	dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data;
+	entry_list = &dx_root->dr_entries;
+
+	if (le16_to_cpu(entry_list->de_num_used) >=
+	    le16_to_cpu(entry_list->de_count))
+		return -ENOSPC;
+
+	return 0;
+}
+
+static int ocfs2_prepare_dx_dir_for_insert(struct inode *dir,
+					   struct buffer_head *di_bh,
+					   const char *name,
+					   int namelen,
+					   struct ocfs2_dir_lookup_result *lookup)
+{
+	int ret, free_dx_root = 1;
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	struct buffer_head *dx_root_bh = NULL;
+	struct buffer_head *leaf_bh = NULL;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_dx_root_block *dx_root;
+
+	ret = ocfs2_read_dx_root(dir, di, &dx_root_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+	if (le32_to_cpu(dx_root->dr_num_entries) == OCFS2_DX_ENTRIES_MAX) {
+		ret = -ENOSPC;
+		mlog_errno(ret);
+		goto out;
+	}
+
+	if (ocfs2_dx_root_inline(dx_root)) {
+		ret = ocfs2_inline_dx_has_space(dx_root_bh);
+
+		if (ret == 0)
+			goto search_el;
+
+		/*
+		 * We ran out of room in the root block. Expand it to
+		 * an extent, then allow ocfs2_find_dir_space_dx to do
+		 * the rest.
+		 */
+		ret = ocfs2_expand_inline_dx_root(dir, dx_root_bh);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+	}
+
+	/*
+	 * Insert preparation for an indexed directory is split into two
+	 * steps. The call to find_dir_space_dx reserves room in the index for
+	 * an additional item. If we run out of space there, it's a real error
+	 * we can't continue on.
+	 */
+	ret = ocfs2_find_dir_space_dx(osb, dir, di_bh, dx_root_bh, name,
+				      namelen, lookup);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+search_el:
+	/*
+	 * Next, we need to find space in the unindexed tree. This call
+	 * searches using the free space linked list. If the unindexed tree
+	 * lacks sufficient space, we'll expand it below. The expansion code
+	 * is smart enough to add any new blocks to the free space list.
+	 */
+	ret = ocfs2_search_dx_free_list(dir, dx_root_bh, namelen, lookup);
+	if (ret && ret != -ENOSPC) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	/* Do this up here - ocfs2_extend_dir might need the dx_root */
+	lookup->dl_dx_root_bh = dx_root_bh;
+	free_dx_root = 0;
+
+	if (ret == -ENOSPC) {
+		ret = ocfs2_extend_dir(osb, dir, di_bh, 1, lookup, &leaf_bh);
+
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		/*
+		 * We make the assumption here that new leaf blocks are added
+		 * to the front of our free list.
+		 */
+		lookup->dl_prev_leaf_bh = NULL;
+		lookup->dl_leaf_bh = leaf_bh;
+	}
+
+out:
+	if (free_dx_root)
+		brelse(dx_root_bh);
+	return ret;
+}
+
+/*
+ * Get a directory ready for insert. Any directory allocation required
+ * happens here. Success returns zero, and enough context in the dir
+ * lookup result that ocfs2_add_entry() will be able complete the task
+ * with minimal performance impact.
+ */
 int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 				 struct inode *dir,
 				 struct buffer_head *parent_fe_bh,
 				 const char *name,
 				 int namelen,
-				 struct buffer_head **ret_de_bh)
+				 struct ocfs2_dir_lookup_result *lookup)
 {
 	int ret;
 	unsigned int blocks_wanted = 1;
@@ -1984,14 +4367,34 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 	mlog(0, "getting ready to insert namelen %d into dir %llu\n",
 	     namelen, (unsigned long long)OCFS2_I(dir)->ip_blkno);
 
-	*ret_de_bh = NULL;
-
 	if (!namelen) {
 		ret = -EINVAL;
 		mlog_errno(ret);
 		goto out;
 	}
 
+	/*
+	 * Do this up front to reduce confusion.
+	 *
+	 * The directory might start inline, then be turned into an
+	 * indexed one, in which case we'd need to hash deep inside
+	 * ocfs2_find_dir_space_id(). Since
+	 * ocfs2_prepare_dx_dir_for_insert() also needs this hash
+	 * done, there seems no point in spreading out the calls. We
+	 * can optimize away the case where the file system doesn't
+	 * support indexing.
+	 */
+	if (ocfs2_supports_indexed_dirs(osb))
+		ocfs2_dx_dir_name_hash(dir, name, namelen, &lookup->dl_hinfo);
+
+	if (ocfs2_dir_indexed(dir)) {
+		ret = ocfs2_prepare_dx_dir_for_insert(dir, parent_fe_bh,
+						      name, namelen, lookup);
+		if (ret)
+			mlog_errno(ret);
+		goto out;
+	}
+
 	if (OCFS2_I(dir)->ip_dyn_features & OCFS2_INLINE_DATA_FL) {
 		ret = ocfs2_find_dir_space_id(dir, parent_fe_bh, name,
 					      namelen, &bh, &blocks_wanted);
@@ -2010,7 +4413,7 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 		BUG_ON(bh);
 
 		ret = ocfs2_extend_dir(osb, dir, parent_fe_bh, blocks_wanted,
-				       &bh);
+				       lookup, &bh);
 		if (ret) {
 			if (ret != -ENOSPC)
 				mlog_errno(ret);
@@ -2020,9 +4423,154 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 		BUG_ON(!bh);
 	}
 
-	*ret_de_bh = bh;
+	lookup->dl_leaf_bh = bh;
 	bh = NULL;
 out:
 	brelse(bh);
 	return ret;
 }
+
+static int ocfs2_dx_dir_remove_index(struct inode *dir,
+				     struct buffer_head *di_bh,
+				     struct buffer_head *dx_root_bh)
+{
+	int ret;
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_dx_root_block *dx_root;
+	struct inode *dx_alloc_inode = NULL;
+	struct buffer_head *dx_alloc_bh = NULL;
+	handle_t *handle;
+	u64 blk;
+	u16 bit;
+	u64 bg_blkno;
+
+	dx_root = (struct ocfs2_dx_root_block *) dx_root_bh->b_data;
+
+	dx_alloc_inode = ocfs2_get_system_file_inode(osb,
+					EXTENT_ALLOC_SYSTEM_INODE,
+					le16_to_cpu(dx_root->dr_suballoc_slot));
+	if (!dx_alloc_inode) {
+		ret = -ENOMEM;
+		mlog_errno(ret);
+		goto out;
+	}
+	mutex_lock(&dx_alloc_inode->i_mutex);
+
+	ret = ocfs2_inode_lock(dx_alloc_inode, &dx_alloc_bh, 1);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_mutex;
+	}
+
+	handle = ocfs2_start_trans(osb, OCFS2_DX_ROOT_REMOVE_CREDITS);
+	if (IS_ERR(handle)) {
+		ret = PTR_ERR(handle);
+		mlog_errno(ret);
+		goto out_unlock;
+	}
+
+	ret = ocfs2_journal_access_di(handle, dir, di_bh,
+				      OCFS2_JOURNAL_ACCESS_WRITE);
+	if (ret) {
+		mlog_errno(ret);
+		goto out_commit;
+	}
+
+	OCFS2_I(dir)->ip_dyn_features &= ~OCFS2_INDEXED_DIR_FL;
+	di->i_dyn_features = cpu_to_le16(OCFS2_I(dir)->ip_dyn_features);
+	di->i_dx_root = cpu_to_le64(0ULL);
+
+	ocfs2_journal_dirty(handle, di_bh);
+
+	blk = le64_to_cpu(dx_root->dr_blkno);
+	bit = le16_to_cpu(dx_root->dr_suballoc_bit);
+	bg_blkno = ocfs2_which_suballoc_group(blk, bit);
+	ret = ocfs2_free_suballoc_bits(handle, dx_alloc_inode, dx_alloc_bh,
+				       bit, bg_blkno, 1);
+	if (ret)
+		mlog_errno(ret);
+
+out_commit:
+	ocfs2_commit_trans(osb, handle);
+
+out_unlock:
+	ocfs2_inode_unlock(dx_alloc_inode, 1);
+
+out_mutex:
+	mutex_unlock(&dx_alloc_inode->i_mutex);
+	brelse(dx_alloc_bh);
+out:
+	iput(dx_alloc_inode);
+	return ret;
+}
+
+int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh)
+{
+	int ret;
+	unsigned int uninitialized_var(clen);
+	u32 major_hash = UINT_MAX, p_cpos, uninitialized_var(cpos);
+	u64 uninitialized_var(blkno);
+	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	struct buffer_head *dx_root_bh = NULL;
+	struct ocfs2_dx_root_block *dx_root;
+	struct ocfs2_dinode *di = (struct ocfs2_dinode *)di_bh->b_data;
+	struct ocfs2_cached_dealloc_ctxt dealloc;
+	struct ocfs2_extent_tree et;
+
+	ocfs2_init_dealloc_ctxt(&dealloc);
+
+	if (!ocfs2_dir_indexed(dir))
+		return 0;
+
+	ret = ocfs2_read_dx_root(dir, di, &dx_root_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+	dx_root = (struct ocfs2_dx_root_block *)dx_root_bh->b_data;
+
+	if (ocfs2_dx_root_inline(dx_root))
+		goto remove_index;
+
+	ocfs2_init_dx_root_extent_tree(&et, dir, dx_root_bh);
+
+	/* XXX: What if dr_clusters is too large? */
+	while (le32_to_cpu(dx_root->dr_clusters)) {
+		ret = ocfs2_dx_dir_lookup_rec(dir, &dx_root->dr_list,
+					      major_hash, &cpos, &blkno, &clen);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		p_cpos = ocfs2_blocks_to_clusters(dir->i_sb, blkno);
+
+		ret = ocfs2_remove_btree_range(dir, &et, cpos, p_cpos, clen,
+					       &dealloc);
+		if (ret) {
+			mlog_errno(ret);
+			goto out;
+		}
+
+		if (cpos == 0)
+			break;
+
+		major_hash = cpos - 1;
+	}
+
+remove_index:
+	ret = ocfs2_dx_dir_remove_index(dir, di_bh, dx_root_bh);
+	if (ret) {
+		mlog_errno(ret);
+		goto out;
+	}
+
+	ocfs2_remove_from_cache(dir, dx_root_bh);
+out:
+	ocfs2_schedule_truncate_log_flush(osb, 1);
+	ocfs2_run_deallocs(osb, &dealloc);
+
+	brelse(dx_root_bh);
+	return ret;
+}
diff --git a/fs/ocfs2/dir.h b/fs/ocfs2/dir.h
index c511e2e18e9f..e683f3deb645 100644
--- a/fs/ocfs2/dir.h
+++ b/fs/ocfs2/dir.h
@@ -26,44 +26,70 @@
 #ifndef OCFS2_DIR_H
 #define OCFS2_DIR_H
 
-struct buffer_head *ocfs2_find_entry(const char *name,
-				     int namelen,
-				     struct inode *dir,
-				     struct ocfs2_dir_entry **res_dir);
+struct ocfs2_dx_hinfo {
+	u32	major_hash;
+	u32	minor_hash;
+};
+
+struct ocfs2_dir_lookup_result {
+	struct buffer_head		*dl_leaf_bh;	/* Unindexed leaf
+							 * block */
+	struct ocfs2_dir_entry		*dl_entry;	/* Target dirent in
+							 * unindexed leaf */
+
+	struct buffer_head		*dl_dx_root_bh;	/* Root of indexed
+							 * tree */
+
+	struct buffer_head		*dl_dx_leaf_bh;	/* Indexed leaf block */
+	struct ocfs2_dx_entry		*dl_dx_entry;	/* Target dx_entry in
+							 * indexed leaf */
+	struct ocfs2_dx_hinfo		dl_hinfo;	/* Name hash results */
+
+	struct buffer_head		*dl_prev_leaf_bh;/* Previous entry in
+							  * dir free space
+							  * list. NULL if
+							  * previous entry is
+							  * dx root block. */
+};
+
+void ocfs2_free_dir_lookup_result(struct ocfs2_dir_lookup_result *res);
+
+int ocfs2_find_entry(const char *name, int namelen,
+		     struct inode *dir,
+		     struct ocfs2_dir_lookup_result *lookup);
 int ocfs2_delete_entry(handle_t *handle,
 		       struct inode *dir,
-		       struct ocfs2_dir_entry *de_del,
-		       struct buffer_head *bh);
+		       struct ocfs2_dir_lookup_result *res);
 int __ocfs2_add_entry(handle_t *handle,
 		      struct inode *dir,
 		      const char *name, int namelen,
 		      struct inode *inode, u64 blkno,
 		      struct buffer_head *parent_fe_bh,
-		      struct buffer_head *insert_bh);
+		      struct ocfs2_dir_lookup_result *lookup);
 static inline int ocfs2_add_entry(handle_t *handle,
 				  struct dentry *dentry,
 				  struct inode *inode, u64 blkno,
 				  struct buffer_head *parent_fe_bh,
-				  struct buffer_head *insert_bh)
+				  struct ocfs2_dir_lookup_result *lookup)
 {
 	return __ocfs2_add_entry(handle, dentry->d_parent->d_inode,
 				 dentry->d_name.name, dentry->d_name.len,
-				 inode, blkno, parent_fe_bh, insert_bh);
+				 inode, blkno, parent_fe_bh, lookup);
 }
 int ocfs2_update_entry(struct inode *dir, handle_t *handle,
-		       struct buffer_head *de_bh, struct ocfs2_dir_entry *de,
+		       struct ocfs2_dir_lookup_result *res,
 		       struct inode *new_entry_inode);
 
 int ocfs2_check_dir_for_entry(struct inode *dir,
 			      const char *name,
 			      int namelen);
 int ocfs2_empty_dir(struct inode *inode);
+
 int ocfs2_find_files_on_disk(const char *name,
 			     int namelen,
 			     u64 *blkno,
 			     struct inode *inode,
-			     struct buffer_head **dirent_bh,
-			     struct ocfs2_dir_entry **dirent);
+			     struct ocfs2_dir_lookup_result *res);
 int ocfs2_lookup_ino_from_name(struct inode *dir, const char *name,
 			       int namelen, u64 *blkno);
 int ocfs2_readdir(struct file *filp, void *dirent, filldir_t filldir);
@@ -74,14 +100,17 @@ int ocfs2_prepare_dir_for_insert(struct ocfs2_super *osb,
 				 struct buffer_head *parent_fe_bh,
 				 const char *name,
 				 int namelen,
-				 struct buffer_head **ret_de_bh);
+				 struct ocfs2_dir_lookup_result *lookup);
 struct ocfs2_alloc_context;
 int ocfs2_fill_new_dir(struct ocfs2_super *osb,
 		       handle_t *handle,
 		       struct inode *parent,
 		       struct inode *inode,
 		       struct buffer_head *fe_bh,
-		       struct ocfs2_alloc_context *data_ac);
+		       struct ocfs2_alloc_context *data_ac,
+		       struct ocfs2_alloc_context *meta_ac);
+
+int ocfs2_dx_dir_truncate(struct inode *dir, struct buffer_head *di_bh);
 
 struct ocfs2_dir_block_trailer *ocfs2_dir_trailer_from_size(int blocksize,
 							    void *data);
diff --git a/fs/ocfs2/dlm/dlmcommon.h b/fs/ocfs2/dlm/dlmcommon.h
index bb53714813ab..0102be35980c 100644
--- a/fs/ocfs2/dlm/dlmcommon.h
+++ b/fs/ocfs2/dlm/dlmcommon.h
@@ -52,16 +52,12 @@
 enum dlm_mle_type {
 	DLM_MLE_BLOCK,
 	DLM_MLE_MASTER,
-	DLM_MLE_MIGRATION
-};
-
-struct dlm_lock_name {
-	u8 len;
-	u8 name[DLM_LOCKID_NAME_MAX];
+	DLM_MLE_MIGRATION,
+	DLM_MLE_NUM_TYPES
 };
 
 struct dlm_master_list_entry {
-	struct list_head list;
+	struct hlist_node master_hash_node;
 	struct list_head hb_events;
 	struct dlm_ctxt *dlm;
 	spinlock_t spinlock;
@@ -78,10 +74,10 @@ struct dlm_master_list_entry {
 	enum dlm_mle_type type;
 	struct o2hb_callback_func mle_hb_up;
 	struct o2hb_callback_func mle_hb_down;
-	union {
-		struct dlm_lock_resource *res;
-		struct dlm_lock_name name;
-	} u;
+	struct dlm_lock_resource *mleres;
+	unsigned char mname[DLM_LOCKID_NAME_MAX];
+	unsigned int mnamelen;
+	unsigned int mnamehash;
 };
 
 enum dlm_ast_type {
@@ -151,13 +147,14 @@ struct dlm_ctxt
 	unsigned long recovery_map[BITS_TO_LONGS(O2NM_MAX_NODES)];
 	struct dlm_recovery_ctxt reco;
 	spinlock_t master_lock;
-	struct list_head master_list;
+	struct hlist_head **master_hash;
 	struct list_head mle_hb_events;
 
 	/* these give a really vague idea of the system load */
-	atomic_t local_resources;
-	atomic_t remote_resources;
-	atomic_t unknown_resources;
+	atomic_t mle_tot_count[DLM_MLE_NUM_TYPES];
+	atomic_t mle_cur_count[DLM_MLE_NUM_TYPES];
+	atomic_t res_tot_count;
+	atomic_t res_cur_count;
 
 	struct dlm_debug_ctxt *dlm_debug_ctxt;
 	struct dentry *dlm_debugfs_subroot;
@@ -195,6 +192,13 @@ static inline struct hlist_head *dlm_lockres_hash(struct dlm_ctxt *dlm, unsigned
 	return dlm->lockres_hash[(i / DLM_BUCKETS_PER_PAGE) % DLM_HASH_PAGES] + (i % DLM_BUCKETS_PER_PAGE);
 }
 
+static inline struct hlist_head *dlm_master_hash(struct dlm_ctxt *dlm,
+						 unsigned i)
+{
+	return dlm->master_hash[(i / DLM_BUCKETS_PER_PAGE) % DLM_HASH_PAGES] +
+			(i % DLM_BUCKETS_PER_PAGE);
+}
+
 /* these keventd work queue items are for less-frequently
  * called functions that cannot be directly called from the
  * net message handlers for some reason, usually because
@@ -848,9 +852,7 @@ struct dlm_lock_resource * dlm_lookup_lockres(struct dlm_ctxt *dlm,
 					      unsigned int len);
 
 int dlm_is_host_down(int errno);
-void dlm_change_lockres_owner(struct dlm_ctxt *dlm,
-			      struct dlm_lock_resource *res,
-			      u8 owner);
+
 struct dlm_lock_resource * dlm_get_lock_resource(struct dlm_ctxt *dlm,
 						 const char *lockid,
 						 int namelen,
@@ -1008,6 +1010,9 @@ static inline void __dlm_wait_on_lockres(struct dlm_lock_resource *res)
 					  DLM_LOCK_RES_MIGRATING));
 }
 
+void __dlm_unlink_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle);
+void __dlm_insert_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle);
+
 /* create/destroy slab caches */
 int dlm_init_master_caches(void);
 void dlm_destroy_master_caches(void);
@@ -1110,6 +1115,23 @@ static inline int dlm_node_iter_next(struct dlm_node_iter *iter)
 	return bit;
 }
 
+static inline void dlm_set_lockres_owner(struct dlm_ctxt *dlm,
+					 struct dlm_lock_resource *res,
+					 u8 owner)
+{
+	assert_spin_locked(&res->spinlock);
+
+	res->owner = owner;
+}
 
+static inline void dlm_change_lockres_owner(struct dlm_ctxt *dlm,
+					    struct dlm_lock_resource *res,
+					    u8 owner)
+{
+	assert_spin_locked(&res->spinlock);
+
+	if (owner != res->owner)
+		dlm_set_lockres_owner(dlm, res, owner);
+}
 
 #endif /* DLMCOMMON_H */
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index b32f60a5acfb..df52f706f669 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -287,18 +287,8 @@ static int stringify_nodemap(unsigned long *nodemap, int maxnodes,
 static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
 {
 	int out = 0;
-	unsigned int namelen;
-	const char *name;
 	char *mle_type;
 
-	if (mle->type != DLM_MLE_MASTER) {
-		namelen = mle->u.name.len;
-		name = mle->u.name.name;
-	} else {
-		namelen = mle->u.res->lockname.len;
-		name = mle->u.res->lockname.name;
-	}
-
 	if (mle->type == DLM_MLE_BLOCK)
 		mle_type = "BLK";
 	else if (mle->type == DLM_MLE_MASTER)
@@ -306,7 +296,7 @@ static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
 	else
 		mle_type = "MIG";
 
-	out += stringify_lockname(name, namelen, buf + out, len - out);
+	out += stringify_lockname(mle->mname, mle->mnamelen, buf + out, len - out);
 	out += snprintf(buf + out, len - out,
 			"\t%3s\tmas=%3u\tnew=%3u\tevt=%1d\tuse=%1d\tref=%3d\n",
 			mle_type, mle->master, mle->new_master,
@@ -501,23 +491,33 @@ static struct file_operations debug_purgelist_fops = {
 static int debug_mle_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
 {
 	struct dlm_master_list_entry *mle;
-	int out = 0;
-	unsigned long total = 0;
+	struct hlist_head *bucket;
+	struct hlist_node *list;
+	int i, out = 0;
+	unsigned long total = 0, longest = 0, bktcnt;
 
 	out += snprintf(db->buf + out, db->len - out,
 			"Dumping MLEs for Domain: %s\n", dlm->name);
 
 	spin_lock(&dlm->master_lock);
-	list_for_each_entry(mle, &dlm->master_list, list) {
-		++total;
-		if (db->len - out < 200)
-			continue;
-		out += dump_mle(mle, db->buf + out, db->len - out);
+	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
+		bucket = dlm_master_hash(dlm, i);
+		hlist_for_each(list, bucket) {
+			mle = hlist_entry(list, struct dlm_master_list_entry,
+					  master_hash_node);
+			++total;
+			++bktcnt;
+			if (db->len - out < 200)
+				continue;
+			out += dump_mle(mle, db->buf + out, db->len - out);
+		}
+		longest = max(longest, bktcnt);
+		bktcnt = 0;
 	}
 	spin_unlock(&dlm->master_lock);
 
 	out += snprintf(db->buf + out, db->len - out,
-			"Total on list: %ld\n", total);
+			"Total: %ld, Longest: %ld\n", total, longest);
 	return out;
 }
 
@@ -756,12 +756,8 @@ static int debug_state_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
 	int out = 0;
 	struct dlm_reco_node_data *node;
 	char *state;
-	int lres, rres, ures, tres;
-
-	lres = atomic_read(&dlm->local_resources);
-	rres = atomic_read(&dlm->remote_resources);
-	ures = atomic_read(&dlm->unknown_resources);
-	tres = lres + rres + ures;
+	int cur_mles = 0, tot_mles = 0;
+	int i;
 
 	spin_lock(&dlm->spinlock);
 
@@ -804,21 +800,48 @@ static int debug_state_print(struct dlm_ctxt *dlm, struct debug_buffer *db)
 				 db->buf + out, db->len - out);
 	out += snprintf(db->buf + out, db->len - out, "\n");
 
-	/* Mastered Resources Total: xxx  Locally: xxx  Remotely: ... */
+	/* Lock Resources: xxx (xxx) */
+	out += snprintf(db->buf + out, db->len - out,
+			"Lock Resources: %d (%d)\n",
+			atomic_read(&dlm->res_cur_count),
+			atomic_read(&dlm->res_tot_count));
+
+	for (i = 0; i < DLM_MLE_NUM_TYPES; ++i)
+		tot_mles += atomic_read(&dlm->mle_tot_count[i]);
+
+	for (i = 0; i < DLM_MLE_NUM_TYPES; ++i)
+		cur_mles += atomic_read(&dlm->mle_cur_count[i]);
+
+	/* MLEs: xxx (xxx) */
+	out += snprintf(db->buf + out, db->len - out,
+			"MLEs: %d (%d)\n", cur_mles, tot_mles);
+
+	/*  Blocking: xxx (xxx) */
+	out += snprintf(db->buf + out, db->len - out,
+			"  Blocking: %d (%d)\n",
+			atomic_read(&dlm->mle_cur_count[DLM_MLE_BLOCK]),
+			atomic_read(&dlm->mle_tot_count[DLM_MLE_BLOCK]));
+
+	/*  Mastery: xxx (xxx) */
+	out += snprintf(db->buf + out, db->len - out,
+			"  Mastery: %d (%d)\n",
+			atomic_read(&dlm->mle_cur_count[DLM_MLE_MASTER]),
+			atomic_read(&dlm->mle_tot_count[DLM_MLE_MASTER]));
+
+	/*  Migration: xxx (xxx) */
 	out += snprintf(db->buf + out, db->len - out,
-			"Mastered Resources Total: %d  Locally: %d  "
-			"Remotely: %d  Unknown: %d\n",
-			tres, lres, rres, ures);
+			"  Migration: %d (%d)\n",
+			atomic_read(&dlm->mle_cur_count[DLM_MLE_MIGRATION]),
+			atomic_read(&dlm->mle_tot_count[DLM_MLE_MIGRATION]));
 
 	/* Lists: Dirty=Empty  Purge=InUse  PendingASTs=Empty  ... */
 	out += snprintf(db->buf + out, db->len - out,
 			"Lists: Dirty=%s  Purge=%s  PendingASTs=%s  "
-			"PendingBASTs=%s  Master=%s\n",
+			"PendingBASTs=%s\n",
 			(list_empty(&dlm->dirty_list) ? "Empty" : "InUse"),
 			(list_empty(&dlm->purge_list) ? "Empty" : "InUse"),
 			(list_empty(&dlm->pending_asts) ? "Empty" : "InUse"),
-			(list_empty(&dlm->pending_basts) ? "Empty" : "InUse"),
-			(list_empty(&dlm->master_list) ? "Empty" : "InUse"));
+			(list_empty(&dlm->pending_basts) ? "Empty" : "InUse"));
 
 	/* Purge Count: xxx  Refs: xxx */
 	out += snprintf(db->buf + out, db->len - out,
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index d8d578f45613..4d9e6b288dd8 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -304,6 +304,9 @@ static void dlm_free_ctxt_mem(struct dlm_ctxt *dlm)
 	if (dlm->lockres_hash)
 		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
 
+	if (dlm->master_hash)
+		dlm_free_pagevec((void **)dlm->master_hash, DLM_HASH_PAGES);
+
 	if (dlm->name)
 		kfree(dlm->name);
 
@@ -1534,12 +1537,27 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	for (i = 0; i < DLM_HASH_BUCKETS; i++)
 		INIT_HLIST_HEAD(dlm_lockres_hash(dlm, i));
 
+	dlm->master_hash = (struct hlist_head **)
+				dlm_alloc_pagevec(DLM_HASH_PAGES);
+	if (!dlm->master_hash) {
+		mlog_errno(-ENOMEM);
+		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
+		kfree(dlm->name);
+		kfree(dlm);
+		dlm = NULL;
+		goto leave;
+	}
+
+	for (i = 0; i < DLM_HASH_BUCKETS; i++)
+		INIT_HLIST_HEAD(dlm_master_hash(dlm, i));
+
 	strcpy(dlm->name, domain);
 	dlm->key = key;
 	dlm->node_num = o2nm_this_node();
 
 	ret = dlm_create_debugfs_subroot(dlm);
 	if (ret < 0) {
+		dlm_free_pagevec((void **)dlm->master_hash, DLM_HASH_PAGES);
 		dlm_free_pagevec((void **)dlm->lockres_hash, DLM_HASH_PAGES);
 		kfree(dlm->name);
 		kfree(dlm);
@@ -1579,7 +1597,6 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	init_waitqueue_head(&dlm->reco.event);
 	init_waitqueue_head(&dlm->ast_wq);
 	init_waitqueue_head(&dlm->migration_wq);
-	INIT_LIST_HEAD(&dlm->master_list);
 	INIT_LIST_HEAD(&dlm->mle_hb_events);
 
 	dlm->joining_node = DLM_LOCK_RES_OWNER_UNKNOWN;
@@ -1587,9 +1604,13 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 
 	dlm->reco.new_master = O2NM_INVALID_NODE_NUM;
 	dlm->reco.dead_node = O2NM_INVALID_NODE_NUM;
-	atomic_set(&dlm->local_resources, 0);
-	atomic_set(&dlm->remote_resources, 0);
-	atomic_set(&dlm->unknown_resources, 0);
+
+	atomic_set(&dlm->res_tot_count, 0);
+	atomic_set(&dlm->res_cur_count, 0);
+	for (i = 0; i < DLM_MLE_NUM_TYPES; ++i) {
+		atomic_set(&dlm->mle_tot_count[i], 0);
+		atomic_set(&dlm->mle_cur_count[i], 0);
+	}
 
 	spin_lock_init(&dlm->work_lock);
 	INIT_LIST_HEAD(&dlm->work_list);
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index 0a2813947853..f8b653fcd4dd 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -73,22 +73,13 @@ static inline int dlm_mle_equal(struct dlm_ctxt *dlm,
 				const char *name,
 				unsigned int namelen)
 {
-	struct dlm_lock_resource *res;
-
 	if (dlm != mle->dlm)
 		return 0;
 
-	if (mle->type == DLM_MLE_BLOCK ||
-	    mle->type == DLM_MLE_MIGRATION) {
-		if (namelen != mle->u.name.len ||
-    	    	    memcmp(name, mle->u.name.name, namelen)!=0)
-			return 0;
-	} else {
-		res = mle->u.res;
-		if (namelen != res->lockname.len ||
-		    memcmp(res->lockname.name, name, namelen) != 0)
-			return 0;
-	}
+	if (namelen != mle->mnamelen ||
+	    memcmp(name, mle->mname, namelen) != 0)
+		return 0;
+
 	return 1;
 }
 
@@ -283,7 +274,7 @@ static void dlm_init_mle(struct dlm_master_list_entry *mle,
 
 	mle->dlm = dlm;
 	mle->type = type;
-	INIT_LIST_HEAD(&mle->list);
+	INIT_HLIST_NODE(&mle->master_hash_node);
 	INIT_LIST_HEAD(&mle->hb_events);
 	memset(mle->maybe_map, 0, sizeof(mle->maybe_map));
 	spin_lock_init(&mle->spinlock);
@@ -295,19 +286,27 @@ static void dlm_init_mle(struct dlm_master_list_entry *mle,
 	mle->new_master = O2NM_MAX_NODES;
 	mle->inuse = 0;
 
+	BUG_ON(mle->type != DLM_MLE_BLOCK &&
+	       mle->type != DLM_MLE_MASTER &&
+	       mle->type != DLM_MLE_MIGRATION);
+
 	if (mle->type == DLM_MLE_MASTER) {
 		BUG_ON(!res);
-		mle->u.res = res;
-	} else if (mle->type == DLM_MLE_BLOCK) {
-		BUG_ON(!name);
-		memcpy(mle->u.name.name, name, namelen);
-		mle->u.name.len = namelen;
-	} else /* DLM_MLE_MIGRATION */ {
+		mle->mleres = res;
+		memcpy(mle->mname, res->lockname.name, res->lockname.len);
+		mle->mnamelen = res->lockname.len;
+		mle->mnamehash = res->lockname.hash;
+	} else {
 		BUG_ON(!name);
-		memcpy(mle->u.name.name, name, namelen);
-		mle->u.name.len = namelen;
+		mle->mleres = NULL;
+		memcpy(mle->mname, name, namelen);
+		mle->mnamelen = namelen;
+		mle->mnamehash = dlm_lockid_hash(name, namelen);
 	}
 
+	atomic_inc(&dlm->mle_tot_count[mle->type]);
+	atomic_inc(&dlm->mle_cur_count[mle->type]);
+
 	/* copy off the node_map and register hb callbacks on our copy */
 	memcpy(mle->node_map, dlm->domain_map, sizeof(mle->node_map));
 	memcpy(mle->vote_map, dlm->domain_map, sizeof(mle->vote_map));
@@ -318,6 +317,24 @@ static void dlm_init_mle(struct dlm_master_list_entry *mle,
 	__dlm_mle_attach_hb_events(dlm, mle);
 }
 
+void __dlm_unlink_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle)
+{
+	assert_spin_locked(&dlm->spinlock);
+	assert_spin_locked(&dlm->master_lock);
+
+	if (!hlist_unhashed(&mle->master_hash_node))
+		hlist_del_init(&mle->master_hash_node);
+}
+
+void __dlm_insert_mle(struct dlm_ctxt *dlm, struct dlm_master_list_entry *mle)
+{
+	struct hlist_head *bucket;
+
+	assert_spin_locked(&dlm->master_lock);
+
+	bucket = dlm_master_hash(dlm, mle->mnamehash);
+	hlist_add_head(&mle->master_hash_node, bucket);
+}
 
 /* returns 1 if found, 0 if not */
 static int dlm_find_mle(struct dlm_ctxt *dlm,
@@ -325,10 +342,17 @@ static int dlm_find_mle(struct dlm_ctxt *dlm,
 			char *name, unsigned int namelen)
 {
 	struct dlm_master_list_entry *tmpmle;
+	struct hlist_head *bucket;
+	struct hlist_node *list;
+	unsigned int hash;
 
 	assert_spin_locked(&dlm->master_lock);
 
-	list_for_each_entry(tmpmle, &dlm->master_list, list) {
+	hash = dlm_lockid_hash(name, namelen);
+	bucket = dlm_master_hash(dlm, hash);
+	hlist_for_each(list, bucket) {
+		tmpmle = hlist_entry(list, struct dlm_master_list_entry,
+				     master_hash_node);
 		if (!dlm_mle_equal(dlm, tmpmle, name, namelen))
 			continue;
 		dlm_get_mle(tmpmle);
@@ -408,24 +432,20 @@ static void dlm_mle_release(struct kref *kref)
 	mle = container_of(kref, struct dlm_master_list_entry, mle_refs);
 	dlm = mle->dlm;
 
-	if (mle->type != DLM_MLE_MASTER) {
-		mlog(0, "calling mle_release for %.*s, type %d\n",
-		     mle->u.name.len, mle->u.name.name, mle->type);
-	} else {
-		mlog(0, "calling mle_release for %.*s, type %d\n",
-		     mle->u.res->lockname.len,
-		     mle->u.res->lockname.name, mle->type);
-	}
 	assert_spin_locked(&dlm->spinlock);
 	assert_spin_locked(&dlm->master_lock);
 
+	mlog(0, "Releasing mle for %.*s, type %d\n", mle->mnamelen, mle->mname,
+	     mle->type);
+
 	/* remove from list if not already */
-	if (!list_empty(&mle->list))
-		list_del_init(&mle->list);
+	__dlm_unlink_mle(dlm, mle);
 
 	/* detach the mle from the domain node up/down events */
 	__dlm_mle_detach_hb_events(dlm, mle);
 
+	atomic_dec(&dlm->mle_cur_count[mle->type]);
+
 	/* NOTE: kfree under spinlock here.
 	 * if this is bad, we can move this to a freelist. */
 	kmem_cache_free(dlm_mle_cache, mle);
@@ -465,43 +485,6 @@ void dlm_destroy_master_caches(void)
 		kmem_cache_destroy(dlm_lockres_cache);
 }
 
-static void dlm_set_lockres_owner(struct dlm_ctxt *dlm,
-				  struct dlm_lock_resource *res,
-				  u8 owner)
-{
-	assert_spin_locked(&res->spinlock);
-
-	mlog_entry("%.*s, %u\n", res->lockname.len, res->lockname.name, owner);
-
-	if (owner == dlm->node_num)
-		atomic_inc(&dlm->local_resources);
-	else if (owner == DLM_LOCK_RES_OWNER_UNKNOWN)
-		atomic_inc(&dlm->unknown_resources);
-	else
-		atomic_inc(&dlm->remote_resources);
-
-	res->owner = owner;
-}
-
-void dlm_change_lockres_owner(struct dlm_ctxt *dlm,
-			      struct dlm_lock_resource *res, u8 owner)
-{
-	assert_spin_locked(&res->spinlock);
-
-	if (owner == res->owner)
-		return;
-
-	if (res->owner == dlm->node_num)
-		atomic_dec(&dlm->local_resources);
-	else if (res->owner == DLM_LOCK_RES_OWNER_UNKNOWN)
-		atomic_dec(&dlm->unknown_resources);
-	else
-		atomic_dec(&dlm->remote_resources);
-
-	dlm_set_lockres_owner(dlm, res, owner);
-}
-
-
 static void dlm_lockres_release(struct kref *kref)
 {
 	struct dlm_lock_resource *res;
@@ -527,6 +510,8 @@ static void dlm_lockres_release(struct kref *kref)
 	}
 	spin_unlock(&dlm->track_lock);
 
+	atomic_dec(&dlm->res_cur_count);
+
 	dlm_put(dlm);
 
 	if (!hlist_unhashed(&res->hash_node) ||
@@ -607,6 +592,9 @@ static void dlm_init_lockres(struct dlm_ctxt *dlm,
 
 	kref_init(&res->refs);
 
+	atomic_inc(&dlm->res_tot_count);
+	atomic_inc(&dlm->res_cur_count);
+
 	/* just for consistency */
 	spin_lock(&res->spinlock);
 	dlm_set_lockres_owner(dlm, res, DLM_LOCK_RES_OWNER_UNKNOWN);
@@ -843,7 +831,7 @@ lookup:
 		alloc_mle = NULL;
 		dlm_init_mle(mle, DLM_MLE_MASTER, dlm, res, NULL, 0);
 		set_bit(dlm->node_num, mle->maybe_map);
-		list_add(&mle->list, &dlm->master_list);
+		__dlm_insert_mle(dlm, mle);
 
 		/* still holding the dlm spinlock, check the recovery map
 		 * to see if there are any nodes that still need to be 
@@ -1270,7 +1258,7 @@ static int dlm_restart_lock_mastery(struct dlm_ctxt *dlm,
 						     res->lockname.len,
 						     res->lockname.name);
 						mle->type = DLM_MLE_MASTER;
-						mle->u.res = res;
+						mle->mleres = res;
 					}
 				}
 			}
@@ -1315,14 +1303,8 @@ static int dlm_do_master_request(struct dlm_lock_resource *res,
 
 	BUG_ON(mle->type == DLM_MLE_MIGRATION);
 
-	if (mle->type != DLM_MLE_MASTER) {
-		request.namelen = mle->u.name.len;
-		memcpy(request.name, mle->u.name.name, request.namelen);
-	} else {
-		request.namelen = mle->u.res->lockname.len;
-		memcpy(request.name, mle->u.res->lockname.name,
-			request.namelen);
-	}
+	request.namelen = (u8)mle->mnamelen;
+	memcpy(request.name, mle->mname, request.namelen);
 
 again:
 	ret = o2net_send_message(DLM_MASTER_REQUEST_MSG, dlm->key, &request,
@@ -1575,7 +1557,7 @@ way_up_top:
 		// "add the block.\n");
 		dlm_init_mle(mle, DLM_MLE_BLOCK, dlm, NULL, name, namelen);
 		set_bit(request->node_idx, mle->maybe_map);
-		list_add(&mle->list, &dlm->master_list);
+		__dlm_insert_mle(dlm, mle);
 		response = DLM_MASTER_RESP_NO;
 	} else {
 		// mlog(0, "mle was found\n");
@@ -1967,7 +1949,7 @@ ok:
 			     assert->node_idx, rr, extra_ref, mle->inuse);
 			dlm_print_one_mle(mle);
 		}
-		list_del_init(&mle->list);
+		__dlm_unlink_mle(dlm, mle);
 		__dlm_mle_detach_hb_events(dlm, mle);
 		__dlm_put_mle(mle);
 		if (extra_ref) {
@@ -3159,10 +3141,8 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
 			tmp->master = master;
 			atomic_set(&tmp->woken, 1);
 			wake_up(&tmp->wq);
-			/* remove it from the list so that only one
-			 * mle will be found */
-			list_del_init(&tmp->list);
-			/* this was obviously WRONG.  mle is uninited here.  should be tmp. */
+			/* remove it so that only one mle will be found */
+			__dlm_unlink_mle(dlm, tmp);
 			__dlm_mle_detach_hb_events(dlm, tmp);
 			ret = DLM_MIGRATE_RESPONSE_MASTERY_REF;
 			mlog(0, "%s:%.*s: master=%u, newmaster=%u, "
@@ -3181,137 +3161,164 @@ static int dlm_add_migration_mle(struct dlm_ctxt *dlm,
 	mle->master = master;
 	/* do this for consistency with other mle types */
 	set_bit(new_master, mle->maybe_map);
-	list_add(&mle->list, &dlm->master_list);
+	__dlm_insert_mle(dlm, mle);
 
 	return ret;
 }
 
-
-void dlm_clean_master_list(struct dlm_ctxt *dlm, u8 dead_node)
+/*
+ * Sets the owner of the lockres, associated to the mle, to UNKNOWN
+ */
+static struct dlm_lock_resource *dlm_reset_mleres_owner(struct dlm_ctxt *dlm,
+					struct dlm_master_list_entry *mle)
 {
-	struct dlm_master_list_entry *mle, *next;
 	struct dlm_lock_resource *res;
-	unsigned int hash;
 
-	mlog_entry("dlm=%s, dead node=%u\n", dlm->name, dead_node);
-top:
-	assert_spin_locked(&dlm->spinlock);
+	/* Find the lockres associated to the mle and set its owner to UNK */
+	res = __dlm_lookup_lockres(dlm, mle->mname, mle->mnamelen,
+				   mle->mnamehash);
+	if (res) {
+		spin_unlock(&dlm->master_lock);
 
-	/* clean the master list */
-	spin_lock(&dlm->master_lock);
-	list_for_each_entry_safe(mle, next, &dlm->master_list, list) {
-		BUG_ON(mle->type != DLM_MLE_BLOCK &&
-		       mle->type != DLM_MLE_MASTER &&
-		       mle->type != DLM_MLE_MIGRATION);
-
-		/* MASTER mles are initiated locally.  the waiting
-		 * process will notice the node map change
-		 * shortly.  let that happen as normal. */
-		if (mle->type == DLM_MLE_MASTER)
-			continue;
+		/* move lockres onto recovery list */
+		spin_lock(&res->spinlock);
+		dlm_set_lockres_owner(dlm, res, DLM_LOCK_RES_OWNER_UNKNOWN);
+		dlm_move_lockres_to_recovery_list(dlm, res);
+		spin_unlock(&res->spinlock);
+		dlm_lockres_put(res);
 
+		/* about to get rid of mle, detach from heartbeat */
+		__dlm_mle_detach_hb_events(dlm, mle);
 
-		/* BLOCK mles are initiated by other nodes.
-		 * need to clean up if the dead node would have
-		 * been the master. */
-		if (mle->type == DLM_MLE_BLOCK) {
-			int bit;
+		/* dump the mle */
+		spin_lock(&dlm->master_lock);
+		__dlm_put_mle(mle);
+		spin_unlock(&dlm->master_lock);
+	}
 
-			spin_lock(&mle->spinlock);
-			bit = find_next_bit(mle->maybe_map, O2NM_MAX_NODES, 0);
-			if (bit != dead_node) {
-				mlog(0, "mle found, but dead node %u would "
-				     "not have been master\n", dead_node);
-				spin_unlock(&mle->spinlock);
-			} else {
-				/* must drop the refcount by one since the
-				 * assert_master will never arrive.  this
-				 * may result in the mle being unlinked and
-				 * freed, but there may still be a process
-				 * waiting in the dlmlock path which is fine. */
-				mlog(0, "node %u was expected master\n",
-				     dead_node);
-				atomic_set(&mle->woken, 1);
-				spin_unlock(&mle->spinlock);
-				wake_up(&mle->wq);
-				/* do not need events any longer, so detach 
-				 * from heartbeat */
-				__dlm_mle_detach_hb_events(dlm, mle);
-				__dlm_put_mle(mle);
-			}
-			continue;
-		}
+	return res;
+}
 
-		/* everything else is a MIGRATION mle */
-
-		/* the rule for MIGRATION mles is that the master
-		 * becomes UNKNOWN if *either* the original or
-		 * the new master dies.  all UNKNOWN lockreses
-		 * are sent to whichever node becomes the recovery
-		 * master.  the new master is responsible for
-		 * determining if there is still a master for
-		 * this lockres, or if he needs to take over
-		 * mastery.  either way, this node should expect
-		 * another message to resolve this. */
-		if (mle->master != dead_node &&
-		    mle->new_master != dead_node)
-			continue;
+static void dlm_clean_migration_mle(struct dlm_ctxt *dlm,
+				    struct dlm_master_list_entry *mle)
+{
+	__dlm_mle_detach_hb_events(dlm, mle);
 
-		/* if we have reached this point, this mle needs to
-		 * be removed from the list and freed. */
+	spin_lock(&mle->spinlock);
+	__dlm_unlink_mle(dlm, mle);
+	atomic_set(&mle->woken, 1);
+	spin_unlock(&mle->spinlock);
 
-		/* remove from the list early.  NOTE: unlinking
-		 * list_head while in list_for_each_safe */
-		__dlm_mle_detach_hb_events(dlm, mle);
-		spin_lock(&mle->spinlock);
-		list_del_init(&mle->list);
+	wake_up(&mle->wq);
+}
+
+static void dlm_clean_block_mle(struct dlm_ctxt *dlm,
+				struct dlm_master_list_entry *mle, u8 dead_node)
+{
+	int bit;
+
+	BUG_ON(mle->type != DLM_MLE_BLOCK);
+
+	spin_lock(&mle->spinlock);
+	bit = find_next_bit(mle->maybe_map, O2NM_MAX_NODES, 0);
+	if (bit != dead_node) {
+		mlog(0, "mle found, but dead node %u would not have been "
+		     "master\n", dead_node);
+		spin_unlock(&mle->spinlock);
+	} else {
+		/* Must drop the refcount by one since the assert_master will
+		 * never arrive. This may result in the mle being unlinked and
+		 * freed, but there may still be a process waiting in the
+		 * dlmlock path which is fine. */
+		mlog(0, "node %u was expected master\n", dead_node);
 		atomic_set(&mle->woken, 1);
 		spin_unlock(&mle->spinlock);
 		wake_up(&mle->wq);
 
-		mlog(0, "%s: node %u died during migration from "
-		     "%u to %u!\n", dlm->name, dead_node,
-		     mle->master, mle->new_master);
-		/* if there is a lockres associated with this
-	 	 * mle, find it and set its owner to UNKNOWN */
-		hash = dlm_lockid_hash(mle->u.name.name, mle->u.name.len);
-		res = __dlm_lookup_lockres(dlm, mle->u.name.name,
-					   mle->u.name.len, hash);
-		if (res) {
-			/* unfortunately if we hit this rare case, our
-		 	 * lock ordering is messed.  we need to drop
-		 	 * the master lock so that we can take the
-		  	 * lockres lock, meaning that we will have to
-			 * restart from the head of list. */
-			spin_unlock(&dlm->master_lock);
+		/* Do not need events any longer, so detach from heartbeat */
+		__dlm_mle_detach_hb_events(dlm, mle);
+		__dlm_put_mle(mle);
+	}
+}
 
-			/* move lockres onto recovery list */
-			spin_lock(&res->spinlock);
-			dlm_set_lockres_owner(dlm, res,
-				      	DLM_LOCK_RES_OWNER_UNKNOWN);
-			dlm_move_lockres_to_recovery_list(dlm, res);
-			spin_unlock(&res->spinlock);
-			dlm_lockres_put(res);
+void dlm_clean_master_list(struct dlm_ctxt *dlm, u8 dead_node)
+{
+	struct dlm_master_list_entry *mle;
+	struct dlm_lock_resource *res;
+	struct hlist_head *bucket;
+	struct hlist_node *list;
+	unsigned int i;
 
-			/* about to get rid of mle, detach from heartbeat */
-			__dlm_mle_detach_hb_events(dlm, mle);
+	mlog_entry("dlm=%s, dead node=%u\n", dlm->name, dead_node);
+top:
+	assert_spin_locked(&dlm->spinlock);
 
-			/* dump the mle */
-			spin_lock(&dlm->master_lock);
-			__dlm_put_mle(mle);
-			spin_unlock(&dlm->master_lock);
+	/* clean the master list */
+	spin_lock(&dlm->master_lock);
+	for (i = 0; i < DLM_HASH_BUCKETS; i++) {
+		bucket = dlm_master_hash(dlm, i);
+		hlist_for_each(list, bucket) {
+			mle = hlist_entry(list, struct dlm_master_list_entry,
+					  master_hash_node);
+
+			BUG_ON(mle->type != DLM_MLE_BLOCK &&
+			       mle->type != DLM_MLE_MASTER &&
+			       mle->type != DLM_MLE_MIGRATION);
+
+			/* MASTER mles are initiated locally. The waiting
+			 * process will notice the node map change shortly.
+			 * Let that happen as normal. */
+			if (mle->type == DLM_MLE_MASTER)
+				continue;
+
+			/* BLOCK mles are initiated by other nodes. Need to
+			 * clean up if the dead node would have been the
+			 * master. */
+			if (mle->type == DLM_MLE_BLOCK) {
+				dlm_clean_block_mle(dlm, mle, dead_node);
+				continue;
+			}
 
-			/* restart */
-			goto top;
-		}
+			/* Everything else is a MIGRATION mle */
+
+			/* The rule for MIGRATION mles is that the master
+			 * becomes UNKNOWN if *either* the original or the new
+			 * master dies. All UNKNOWN lockres' are sent to
+			 * whichever node becomes the recovery master. The new
+			 * master is responsible for determining if there is
+			 * still a master for this lockres, or if he needs to
+			 * take over mastery. Either way, this node should
+			 * expect another message to resolve this. */
+
+			if (mle->master != dead_node &&
+			    mle->new_master != dead_node)
+				continue;
+
+			/* If we have reached this point, this mle needs to be
+			 * removed from the list and freed. */
+			dlm_clean_migration_mle(dlm, mle);
+
+			mlog(0, "%s: node %u died during migration from "
+			     "%u to %u!\n", dlm->name, dead_node, mle->master,
+			     mle->new_master);
+
+			/* If we find a lockres associated with the mle, we've
+			 * hit this rare case that messes up our lock ordering.
+			 * If so, we need to drop the master lock so that we can
+			 * take the lockres lock, meaning that we will have to
+			 * restart from the head of list. */
+			res = dlm_reset_mleres_owner(dlm, mle);
+			if (res)
+				/* restart */
+				goto top;
 
-		/* this may be the last reference */
-		__dlm_put_mle(mle);
+			/* This may be the last reference */
+			__dlm_put_mle(mle);
+		}
 	}
 	spin_unlock(&dlm->master_lock);
 }
 
-
 int dlm_finish_migration(struct dlm_ctxt *dlm, struct dlm_lock_resource *res,
 			 u8 old_master)
 {
diff --git a/fs/ocfs2/dlm/dlmthread.c b/fs/ocfs2/dlm/dlmthread.c
index 4060bb328bc8..d490b66ad9d7 100644
--- a/fs/ocfs2/dlm/dlmthread.c
+++ b/fs/ocfs2/dlm/dlmthread.c
@@ -162,12 +162,28 @@ static int dlm_purge_lockres(struct dlm_ctxt *dlm,
 
 	spin_lock(&res->spinlock);
 	if (!__dlm_lockres_unused(res)) {
-		spin_unlock(&res->spinlock);
 		mlog(0, "%s:%.*s: tried to purge but not unused\n",
 		     dlm->name, res->lockname.len, res->lockname.name);
-		return -ENOTEMPTY;
+		__dlm_print_one_lock_resource(res);
+		spin_unlock(&res->spinlock);
+		BUG();
 	}
+
+	if (res->state & DLM_LOCK_RES_MIGRATING) {
+		mlog(0, "%s:%.*s: Delay dropref as this lockres is "
+		     "being remastered\n", dlm->name, res->lockname.len,
+		     res->lockname.name);
+		/* Re-add the lockres to the end of the purge list */
+		if (!list_empty(&res->purge)) {
+			list_del_init(&res->purge);
+			list_add_tail(&res->purge, &dlm->purge_list);
+		}
+		spin_unlock(&res->spinlock);
+		return 0;
+	}
+
 	master = (res->owner == dlm->node_num);
+
 	if (!master)
 		res->state |= DLM_LOCK_RES_DROPPING_REF;
 	spin_unlock(&res->spinlock);
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 7219a86d34cc..e15fc7d50827 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -244,6 +244,10 @@ static struct ocfs2_lock_res_ops ocfs2_rename_lops = {
 	.flags		= 0,
 };
 
+static struct ocfs2_lock_res_ops ocfs2_nfs_sync_lops = {
+	.flags		= 0,
+};
+
 static struct ocfs2_lock_res_ops ocfs2_dentry_lops = {
 	.get_osb	= ocfs2_get_dentry_osb,
 	.post_unlock	= ocfs2_dentry_post_unlock,
@@ -622,6 +626,17 @@ static void ocfs2_rename_lock_res_init(struct ocfs2_lock_res *res,
 				   &ocfs2_rename_lops, osb);
 }
 
+static void ocfs2_nfs_sync_lock_res_init(struct ocfs2_lock_res *res,
+					 struct ocfs2_super *osb)
+{
+	/* nfs_sync lockres doesn't come from a slab so we call init
+	 * once on it manually.  */
+	ocfs2_lock_res_init_once(res);
+	ocfs2_build_lock_name(OCFS2_LOCK_TYPE_NFS_SYNC, 0, 0, res->l_name);
+	ocfs2_lock_res_init_common(osb, res, OCFS2_LOCK_TYPE_NFS_SYNC,
+				   &ocfs2_nfs_sync_lops, osb);
+}
+
 void ocfs2_file_lock_res_init(struct ocfs2_lock_res *lockres,
 			      struct ocfs2_file_private *fp)
 {
@@ -2417,6 +2432,34 @@ void ocfs2_rename_unlock(struct ocfs2_super *osb)
 		ocfs2_cluster_unlock(osb, lockres, DLM_LOCK_EX);
 }
 
+int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex)
+{
+	int status;
+	struct ocfs2_lock_res *lockres = &osb->osb_nfs_sync_lockres;
+
+	if (ocfs2_is_hard_readonly(osb))
+		return -EROFS;
+
+	if (ocfs2_mount_local(osb))
+		return 0;
+
+	status = ocfs2_cluster_lock(osb, lockres, ex ? LKM_EXMODE : LKM_PRMODE,
+				    0, 0);
+	if (status < 0)
+		mlog(ML_ERROR, "lock on nfs sync lock failed %d\n", status);
+
+	return status;
+}
+
+void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex)
+{
+	struct ocfs2_lock_res *lockres = &osb->osb_nfs_sync_lockres;
+
+	if (!ocfs2_mount_local(osb))
+		ocfs2_cluster_unlock(osb, lockres,
+				     ex ? LKM_EXMODE : LKM_PRMODE);
+}
+
 int ocfs2_dentry_lock(struct dentry *dentry, int ex)
 {
 	int ret;
@@ -2798,6 +2841,7 @@ int ocfs2_dlm_init(struct ocfs2_super *osb)
 local:
 	ocfs2_super_lock_res_init(&osb->osb_super_lockres, osb);
 	ocfs2_rename_lock_res_init(&osb->osb_rename_lockres, osb);
+	ocfs2_nfs_sync_lock_res_init(&osb->osb_nfs_sync_lockres, osb);
 
 	osb->cconn = conn;
 
@@ -2833,6 +2877,7 @@ void ocfs2_dlm_shutdown(struct ocfs2_super *osb,
 
 	ocfs2_lock_res_free(&osb->osb_super_lockres);
 	ocfs2_lock_res_free(&osb->osb_rename_lockres);
+	ocfs2_lock_res_free(&osb->osb_nfs_sync_lockres);
 
 	ocfs2_cluster_disconnect(osb->cconn, hangup_pending);
 	osb->cconn = NULL;
@@ -3015,6 +3060,7 @@ static void ocfs2_drop_osb_locks(struct ocfs2_super *osb)
 {
 	ocfs2_simple_drop_lockres(osb, &osb->osb_super_lockres);
 	ocfs2_simple_drop_lockres(osb, &osb->osb_rename_lockres);
+	ocfs2_simple_drop_lockres(osb, &osb->osb_nfs_sync_lockres);
 }
 
 int ocfs2_drop_inode_locks(struct inode *inode)
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index 3f8d9986b8e0..e1fd5721cd7f 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -115,6 +115,8 @@ void ocfs2_super_unlock(struct ocfs2_super *osb,
 			int ex);
 int ocfs2_rename_lock(struct ocfs2_super *osb);
 void ocfs2_rename_unlock(struct ocfs2_super *osb);
+int ocfs2_nfs_sync_lock(struct ocfs2_super *osb, int ex);
+void ocfs2_nfs_sync_unlock(struct ocfs2_super *osb, int ex);
 int ocfs2_dentry_lock(struct dentry *dentry, int ex);
 void ocfs2_dentry_unlock(struct dentry *dentry, int ex);
 int ocfs2_file_lock(struct file *file, int ex, int trylock);
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 2f27b332d8b3..de3da8eb558c 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -31,6 +31,7 @@
 
 #include "ocfs2.h"
 
+#include "alloc.h"
 #include "dir.h"
 #include "dlmglue.h"
 #include "dcache.h"
@@ -38,6 +39,7 @@
 #include "inode.h"
 
 #include "buffer_head_io.h"
+#include "suballoc.h"
 
 struct ocfs2_inode_handle
 {
@@ -49,29 +51,97 @@ static struct dentry *ocfs2_get_dentry(struct super_block *sb,
 		struct ocfs2_inode_handle *handle)
 {
 	struct inode *inode;
+	struct ocfs2_super *osb = OCFS2_SB(sb);
+	u64 blkno = handle->ih_blkno;
+	int status, set;
 	struct dentry *result;
 
 	mlog_entry("(0x%p, 0x%p)\n", sb, handle);
 
-	if (handle->ih_blkno == 0) {
-		mlog_errno(-ESTALE);
-		return ERR_PTR(-ESTALE);
+	if (blkno == 0) {
+		mlog(0, "nfs wants inode with blkno: 0\n");
+		result = ERR_PTR(-ESTALE);
+		goto bail;
+	}
+
+	inode = ocfs2_ilookup(sb, blkno);
+	/*
+	 * If the inode exists in memory, we only need to check it's
+	 * generation number
+	 */
+	if (inode)
+		goto check_gen;
+
+	/*
+	 * This will synchronize us against ocfs2_delete_inode() on
+	 * all nodes
+	 */
+	status = ocfs2_nfs_sync_lock(osb, 1);
+	if (status < 0) {
+		mlog(ML_ERROR, "getting nfs sync lock(EX) failed %d\n", status);
+		goto check_err;
+	}
+
+	status = ocfs2_test_inode_bit(osb, blkno, &set);
+	if (status < 0) {
+		if (status == -EINVAL) {
+			/*
+			 * The blkno NFS gave us doesn't even show up
+			 * as an inode, we return -ESTALE to be
+			 * nice
+			 */
+			mlog(0, "test inode bit failed %d\n", status);
+			status = -ESTALE;
+		} else {
+			mlog(ML_ERROR, "test inode bit failed %d\n", status);
+		}
+		goto unlock_nfs_sync;
+	}
+
+	/* If the inode allocator bit is clear, this inode must be stale */
+	if (!set) {
+		mlog(0, "inode %llu suballoc bit is clear\n", blkno);
+		status = -ESTALE;
+		goto unlock_nfs_sync;
 	}
 
-	inode = ocfs2_iget(OCFS2_SB(sb), handle->ih_blkno, 0, 0);
+	inode = ocfs2_iget(osb, blkno, 0, 0);
 
-	if (IS_ERR(inode))
-		return (void *)inode;
+unlock_nfs_sync:
+	ocfs2_nfs_sync_unlock(osb, 1);
 
+check_err:
+	if (status < 0) {
+		if (status == -ESTALE) {
+			mlog(0, "stale inode ino: %llu generation: %u\n",
+			     blkno, handle->ih_generation);
+		}
+		result = ERR_PTR(status);
+		goto bail;
+	}
+
+	if (IS_ERR(inode)) {
+		mlog_errno(PTR_ERR(inode));
+		result = (void *)inode;
+		goto bail;
+	}
+
+check_gen:
 	if (handle->ih_generation != inode->i_generation) {
 		iput(inode);
-		return ERR_PTR(-ESTALE);
+		mlog(0, "stale inode ino: %llu generation: %u\n", blkno,
+		     handle->ih_generation);
+		result = ERR_PTR(-ESTALE);
+		goto bail;
 	}
 
 	result = d_obtain_alias(inode);
 	if (!IS_ERR(result))
 		result->d_op = &ocfs2_dentry_ops;
+	else
+		mlog_errno(PTR_ERR(result));
 
+bail:
 	mlog_exit_ptr(result);
 	return result;
 }
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 229e707bc050..10e1fa87396a 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -38,6 +38,7 @@
 #include "ocfs2.h"
 
 #include "alloc.h"
+#include "dir.h"
 #include "blockcheck.h"
 #include "dlmglue.h"
 #include "extent_map.h"
@@ -112,6 +113,17 @@ void ocfs2_get_inode_flags(struct ocfs2_inode_info *oi)
 		oi->ip_attr |= OCFS2_DIRSYNC_FL;
 }
 
+struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno)
+{
+	struct ocfs2_find_inode_args args;
+
+	args.fi_blkno = blkno;
+	args.fi_flags = 0;
+	args.fi_ino = ino_from_blkno(sb, blkno);
+	args.fi_sysfile_type = 0;
+
+	return ilookup5(sb, blkno, ocfs2_find_actor, &args);
+}
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 			 int sysfile_type)
 {
@@ -275,7 +287,7 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 		     (unsigned long long)OCFS2_I(inode)->ip_blkno,
 		     (unsigned long long)le64_to_cpu(fe->i_blkno));
 
-	inode->i_nlink = le16_to_cpu(fe->i_links_count);
+	inode->i_nlink = ocfs2_read_links_count(fe);
 
 	if (fe->i_flags & cpu_to_le32(OCFS2_SYSTEM_FL)) {
 		OCFS2_I(inode)->ip_flags |= OCFS2_INODE_SYSTEM_FILE;
@@ -351,6 +363,8 @@ void ocfs2_populate_inode(struct inode *inode, struct ocfs2_dinode *fe,
 
 	ocfs2_set_inode_flags(inode);
 
+	OCFS2_I(inode)->ip_last_used_slot = 0;
+	OCFS2_I(inode)->ip_last_used_group = 0;
 	mlog_exit_void();
 }
 
@@ -606,7 +620,7 @@ static int ocfs2_remove_inode(struct inode *inode,
 	}
 
 	handle = ocfs2_start_trans(osb, OCFS2_DELETE_INODE_CREDITS +
-					ocfs2_quota_trans_credits(inode->i_sb));
+				   ocfs2_quota_trans_credits(inode->i_sb));
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		mlog_errno(status);
@@ -740,6 +754,15 @@ static int ocfs2_wipe_inode(struct inode *inode,
 		goto bail_unlock_dir;
 	}
 
+	/* Remove any dir index tree */
+	if (S_ISDIR(inode->i_mode)) {
+		status = ocfs2_dx_dir_truncate(inode, di_bh);
+		if (status) {
+			mlog_errno(status);
+			goto bail_unlock_dir;
+		}
+	}
+
 	/*Free extended attribute resources associated with this inode.*/
 	status = ocfs2_xattr_remove(inode, di_bh);
 	if (status < 0) {
@@ -949,6 +972,17 @@ void ocfs2_delete_inode(struct inode *inode)
 		goto bail;
 	}
 
+	/*
+	 * Synchronize us against ocfs2_get_dentry. We take this in
+	 * shared mode so that all nodes can still concurrently
+	 * process deletes.
+	 */
+	status = ocfs2_nfs_sync_lock(OCFS2_SB(inode->i_sb), 0);
+	if (status < 0) {
+		mlog(ML_ERROR, "getting nfs sync lock(PR) failed %d\n", status);
+		ocfs2_cleanup_delete_inode(inode, 0);
+		goto bail_unblock;
+	}
 	/* Lock down the inode. This gives us an up to date view of
 	 * it's metadata (for verification), and allows us to
 	 * serialize delete_inode on multiple nodes.
@@ -962,7 +996,7 @@ void ocfs2_delete_inode(struct inode *inode)
 		if (status != -ENOENT)
 			mlog_errno(status);
 		ocfs2_cleanup_delete_inode(inode, 0);
-		goto bail_unblock;
+		goto bail_unlock_nfs_sync;
 	}
 
 	/* Query the cluster. This will be the final decision made
@@ -1005,6 +1039,10 @@ void ocfs2_delete_inode(struct inode *inode)
 bail_unlock_inode:
 	ocfs2_inode_unlock(inode, 1);
 	brelse(di_bh);
+
+bail_unlock_nfs_sync:
+	ocfs2_nfs_sync_unlock(OCFS2_SB(inode->i_sb), 0);
+
 bail_unblock:
 	status = sigprocmask(SIG_SETMASK, &oldset, NULL);
 	if (status < 0)
@@ -1205,7 +1243,7 @@ int ocfs2_mark_inode_dirty(handle_t *handle,
 	spin_unlock(&OCFS2_I(inode)->ip_lock);
 
 	fe->i_size = cpu_to_le64(i_size_read(inode));
-	fe->i_links_count = cpu_to_le16(inode->i_nlink);
+	ocfs2_set_links_count(fe, inode->i_nlink);
 	fe->i_uid = cpu_to_le32(inode->i_uid);
 	fe->i_gid = cpu_to_le32(inode->i_gid);
 	fe->i_mode = cpu_to_le16(inode->i_mode);
@@ -1242,7 +1280,7 @@ void ocfs2_refresh_inode(struct inode *inode,
 	OCFS2_I(inode)->ip_dyn_features = le16_to_cpu(fe->i_dyn_features);
 	ocfs2_set_inode_flags(inode);
 	i_size_write(inode, le64_to_cpu(fe->i_size));
-	inode->i_nlink = le16_to_cpu(fe->i_links_count);
+	inode->i_nlink = ocfs2_read_links_count(fe);
 	inode->i_uid = le32_to_cpu(fe->i_uid);
 	inode->i_gid = le32_to_cpu(fe->i_gid);
 	inode->i_mode = le16_to_cpu(fe->i_mode);
diff --git a/fs/ocfs2/inode.h b/fs/ocfs2/inode.h
index eb3c302b38d3..ea71525aad41 100644
--- a/fs/ocfs2/inode.h
+++ b/fs/ocfs2/inode.h
@@ -72,6 +72,10 @@ struct ocfs2_inode_info
 
 	struct inode			vfs_inode;
 	struct jbd2_inode		ip_jinode;
+
+	/* Only valid if the inode is the dir. */
+	u32				ip_last_used_slot;
+	u64				ip_last_used_group;
 };
 
 /*
@@ -124,6 +128,7 @@ void ocfs2_drop_inode(struct inode *inode);
 /* Flags for ocfs2_iget() */
 #define OCFS2_FI_FLAG_SYSFILE		0x1
 #define OCFS2_FI_FLAG_ORPHAN_RECOVERY	0x2
+struct inode *ocfs2_ilookup(struct super_block *sb, u64 feoff);
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 feoff, unsigned flags,
 			 int sysfile_type);
 int ocfs2_inode_init_private(struct inode *inode);
diff --git a/fs/ocfs2/journal.c b/fs/ocfs2/journal.c
index 57d7d25a2b9a..a20a0f1e37fd 100644
--- a/fs/ocfs2/journal.c
+++ b/fs/ocfs2/journal.c
@@ -65,6 +65,11 @@ static int ocfs2_trylock_journal(struct ocfs2_super *osb,
 static int ocfs2_recover_orphans(struct ocfs2_super *osb,
 				 int slot);
 static int ocfs2_commit_thread(void *arg);
+static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
+					    int slot_num,
+					    struct ocfs2_dinode *la_dinode,
+					    struct ocfs2_dinode *tl_dinode,
+					    struct ocfs2_quota_recovery *qrec);
 
 static inline int ocfs2_wait_on_mount(struct ocfs2_super *osb)
 {
@@ -76,18 +81,97 @@ static inline int ocfs2_wait_on_quotas(struct ocfs2_super *osb)
 	return __ocfs2_wait_on_mount(osb, 1);
 }
 
-
-
 /*
- * The recovery_list is a simple linked list of node numbers to recover.
- * It is protected by the recovery_lock.
+ * This replay_map is to track online/offline slots, so we could recover
+ * offline slots during recovery and mount
  */
 
-struct ocfs2_recovery_map {
-	unsigned int rm_used;
-	unsigned int *rm_entries;
+enum ocfs2_replay_state {
+	REPLAY_UNNEEDED = 0,	/* Replay is not needed, so ignore this map */
+	REPLAY_NEEDED, 		/* Replay slots marked in rm_replay_slots */
+	REPLAY_DONE 		/* Replay was already queued */
 };
 
+struct ocfs2_replay_map {
+	unsigned int rm_slots;
+	enum ocfs2_replay_state rm_state;
+	unsigned char rm_replay_slots[0];
+};
+
+void ocfs2_replay_map_set_state(struct ocfs2_super *osb, int state)
+{
+	if (!osb->replay_map)
+		return;
+
+	/* If we've already queued the replay, we don't have any more to do */
+	if (osb->replay_map->rm_state == REPLAY_DONE)
+		return;
+
+	osb->replay_map->rm_state = state;
+}
+
+int ocfs2_compute_replay_slots(struct ocfs2_super *osb)
+{
+	struct ocfs2_replay_map *replay_map;
+	int i, node_num;
+
+	/* If replay map is already set, we don't do it again */
+	if (osb->replay_map)
+		return 0;
+
+	replay_map = kzalloc(sizeof(struct ocfs2_replay_map) +
+			     (osb->max_slots * sizeof(char)), GFP_KERNEL);
+
+	if (!replay_map) {
+		mlog_errno(-ENOMEM);
+		return -ENOMEM;
+	}
+
+	spin_lock(&osb->osb_lock);
+
+	replay_map->rm_slots = osb->max_slots;
+	replay_map->rm_state = REPLAY_UNNEEDED;
+
+	/* set rm_replay_slots for offline slot(s) */
+	for (i = 0; i < replay_map->rm_slots; i++) {
+		if (ocfs2_slot_to_node_num_locked(osb, i, &node_num) == -ENOENT)
+			replay_map->rm_replay_slots[i] = 1;
+	}
+
+	osb->replay_map = replay_map;
+	spin_unlock(&osb->osb_lock);
+	return 0;
+}
+
+void ocfs2_queue_replay_slots(struct ocfs2_super *osb)
+{
+	struct ocfs2_replay_map *replay_map = osb->replay_map;
+	int i;
+
+	if (!replay_map)
+		return;
+
+	if (replay_map->rm_state != REPLAY_NEEDED)
+		return;
+
+	for (i = 0; i < replay_map->rm_slots; i++)
+		if (replay_map->rm_replay_slots[i])
+			ocfs2_queue_recovery_completion(osb->journal, i, NULL,
+							NULL, NULL);
+	replay_map->rm_state = REPLAY_DONE;
+}
+
+void ocfs2_free_replay_slots(struct ocfs2_super *osb)
+{
+	struct ocfs2_replay_map *replay_map = osb->replay_map;
+
+	if (!osb->replay_map)
+		return;
+
+	kfree(replay_map);
+	osb->replay_map = NULL;
+}
+
 int ocfs2_recovery_init(struct ocfs2_super *osb)
 {
 	struct ocfs2_recovery_map *rm;
@@ -496,6 +580,22 @@ static struct ocfs2_triggers dq_triggers = {
 	},
 };
 
+static struct ocfs2_triggers dr_triggers = {
+	.ot_triggers = {
+		.t_commit = ocfs2_commit_trigger,
+		.t_abort = ocfs2_abort_trigger,
+	},
+	.ot_offset	= offsetof(struct ocfs2_dx_root_block, dr_check),
+};
+
+static struct ocfs2_triggers dl_triggers = {
+	.ot_triggers = {
+		.t_commit = ocfs2_commit_trigger,
+		.t_abort = ocfs2_abort_trigger,
+	},
+	.ot_offset	= offsetof(struct ocfs2_dx_leaf, dl_check),
+};
+
 static int __ocfs2_journal_access(handle_t *handle,
 				  struct inode *inode,
 				  struct buffer_head *bh,
@@ -600,6 +700,20 @@ int ocfs2_journal_access_dq(handle_t *handle, struct inode *inode,
 				      type);
 }
 
+int ocfs2_journal_access_dr(handle_t *handle, struct inode *inode,
+			    struct buffer_head *bh, int type)
+{
+	return __ocfs2_journal_access(handle, inode, bh, &dr_triggers,
+				      type);
+}
+
+int ocfs2_journal_access_dl(handle_t *handle, struct inode *inode,
+			    struct buffer_head *bh, int type)
+{
+	return __ocfs2_journal_access(handle, inode, bh, &dl_triggers,
+				      type);
+}
+
 int ocfs2_journal_access(handle_t *handle, struct inode *inode,
 			 struct buffer_head *bh, int type)
 {
@@ -1176,24 +1290,24 @@ static void ocfs2_queue_recovery_completion(struct ocfs2_journal *journal,
 }
 
 /* Called by the mount code to queue recovery the last part of
- * recovery for it's own slot. */
+ * recovery for it's own and offline slot(s). */
 void ocfs2_complete_mount_recovery(struct ocfs2_super *osb)
 {
 	struct ocfs2_journal *journal = osb->journal;
 
-	if (osb->dirty) {
-		/* No need to queue up our truncate_log as regular
-		 * cleanup will catch that. */
-		ocfs2_queue_recovery_completion(journal,
-						osb->slot_num,
-						osb->local_alloc_copy,
-						NULL,
-						NULL);
-		ocfs2_schedule_truncate_log_flush(osb, 0);
+	/* No need to queue up our truncate_log as regular cleanup will catch
+	 * that */
+	ocfs2_queue_recovery_completion(journal, osb->slot_num,
+					osb->local_alloc_copy, NULL, NULL);
+	ocfs2_schedule_truncate_log_flush(osb, 0);
 
-		osb->local_alloc_copy = NULL;
-		osb->dirty = 0;
-	}
+	osb->local_alloc_copy = NULL;
+	osb->dirty = 0;
+
+	/* queue to recover orphan slots for all offline slots */
+	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
+	ocfs2_queue_replay_slots(osb);
+	ocfs2_free_replay_slots(osb);
 }
 
 void ocfs2_complete_quota_recovery(struct ocfs2_super *osb)
@@ -1236,6 +1350,14 @@ restart:
 		goto bail;
 	}
 
+	status = ocfs2_compute_replay_slots(osb);
+	if (status < 0)
+		mlog_errno(status);
+
+	/* queue recovery for our own slot */
+	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
+					NULL, NULL);
+
 	spin_lock(&osb->osb_lock);
 	while (rm->rm_used) {
 		/* It's always safe to remove entry zero, as we won't
@@ -1301,11 +1423,8 @@ skip_recovery:
 
 	ocfs2_super_unlock(osb, 1);
 
-	/* We always run recovery on our own orphan dir - the dead
-	 * node(s) may have disallowd a previos inode delete. Re-processing
-	 * is therefore required. */
-	ocfs2_queue_recovery_completion(osb->journal, osb->slot_num, NULL,
-					NULL, NULL);
+	/* queue recovery for offline slots */
+	ocfs2_queue_replay_slots(osb);
 
 bail:
 	mutex_lock(&osb->recovery_lock);
@@ -1314,6 +1433,7 @@ bail:
 		goto restart;
 	}
 
+	ocfs2_free_replay_slots(osb);
 	osb->recovery_thread_task = NULL;
 	mb(); /* sync with ocfs2_recovery_thread_running */
 	wake_up(&osb->recovery_event);
@@ -1465,6 +1585,9 @@ static int ocfs2_replay_journal(struct ocfs2_super *osb,
 		goto done;
 	}
 
+	/* we need to run complete recovery for offline orphan slots */
+	ocfs2_replay_map_set_state(osb, REPLAY_NEEDED);
+
 	mlog(ML_NOTICE, "Recovering node %d from slot %d on device (%u,%u)\n",
 	     node_num, slot_num,
 	     MAJOR(osb->sb->s_dev), MINOR(osb->sb->s_dev));
diff --git a/fs/ocfs2/journal.h b/fs/ocfs2/journal.h
index 172850a9a12a..619dd7f6c053 100644
--- a/fs/ocfs2/journal.h
+++ b/fs/ocfs2/journal.h
@@ -38,6 +38,17 @@ enum ocfs2_journal_state {
 struct ocfs2_super;
 struct ocfs2_dinode;
 
+/*
+ * The recovery_list is a simple linked list of node numbers to recover.
+ * It is protected by the recovery_lock.
+ */
+
+struct ocfs2_recovery_map {
+	unsigned int rm_used;
+	unsigned int *rm_entries;
+};
+
+
 struct ocfs2_journal {
 	enum ocfs2_journal_state   j_state;    /* Journals current state   */
 
@@ -139,6 +150,7 @@ void ocfs2_wait_for_recovery(struct ocfs2_super *osb);
 int ocfs2_recovery_init(struct ocfs2_super *osb);
 void ocfs2_recovery_exit(struct ocfs2_super *osb);
 
+int ocfs2_compute_replay_slots(struct ocfs2_super *osb);
 /*
  *  Journal Control:
  *  Initialize, Load, Shutdown, Wipe a journal.
@@ -266,6 +278,12 @@ int ocfs2_journal_access_dq(handle_t *handle, struct inode *inode,
 /* dirblock */
 int ocfs2_journal_access_db(handle_t *handle, struct inode *inode,
 			    struct buffer_head *bh, int type);
+/* ocfs2_dx_root_block */
+int ocfs2_journal_access_dr(handle_t *handle, struct inode *inode,
+			    struct buffer_head *bh, int type);
+/* ocfs2_dx_leaf */
+int ocfs2_journal_access_dl(handle_t *handle, struct inode *inode,
+			    struct buffer_head *bh, int type);
 /* Anything that has no ecc */
 int ocfs2_journal_access(handle_t *handle, struct inode *inode,
 			 struct buffer_head *bh, int type);
@@ -368,14 +386,29 @@ static inline int ocfs2_remove_extent_credits(struct super_block *sb)
 }
 
 /* data block for new dir/symlink, 2 for bitmap updates (bitmap fe +
- * bitmap block for the new bit) */
-#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + 2)
+ * bitmap block for the new bit) dx_root update for free list */
+#define OCFS2_DIR_LINK_ADDITIONAL_CREDITS (1 + 2 + 1)
+
+static inline int ocfs2_add_dir_index_credits(struct super_block *sb)
+{
+	/* 1 block for index, 2 allocs (data, metadata), 1 clusters
+	 * worth of blocks for initial extent. */
+	return 1 + 2 * OCFS2_SUBALLOC_ALLOC +
+		ocfs2_clusters_to_blocks(sb, 1);
+}
 
-/* parent fe, parent block, new file entry, inode alloc fe, inode alloc
- * group descriptor + mkdir/symlink blocks + quota update */
-static inline int ocfs2_mknod_credits(struct super_block *sb)
+/* parent fe, parent block, new file entry, index leaf, inode alloc fe, inode
+ * alloc group descriptor + mkdir/symlink blocks + dir blocks + xattr
+ * blocks + quota update */
+static inline int ocfs2_mknod_credits(struct super_block *sb, int is_dir,
+				      int xattr_credits)
 {
-	return 3 + OCFS2_SUBALLOC_ALLOC + OCFS2_DIR_LINK_ADDITIONAL_CREDITS +
+	int dir_credits = OCFS2_DIR_LINK_ADDITIONAL_CREDITS;
+
+	if (is_dir)
+		dir_credits += ocfs2_add_dir_index_credits(sb);
+
+	return 4 + OCFS2_SUBALLOC_ALLOC + dir_credits + xattr_credits +
 	       ocfs2_quota_trans_credits(sb);
 }
 
@@ -388,31 +421,31 @@ static inline int ocfs2_mknod_credits(struct super_block *sb)
 #define OCFS2_SIMPLE_DIR_EXTEND_CREDITS (2)
 
 /* file update (nlink, etc) + directory mtime/ctime + dir entry block + quota
- * update on dir */
+ * update on dir + index leaf + dx root update for free list */
 static inline int ocfs2_link_credits(struct super_block *sb)
 {
-	return 2*OCFS2_INODE_UPDATE_CREDITS + 1 +
+	return 2*OCFS2_INODE_UPDATE_CREDITS + 3 +
 	       ocfs2_quota_trans_credits(sb);
 }
 
 /* inode + dir inode (if we unlink a dir), + dir entry block + orphan
- * dir inode link */
+ * dir inode link + dir inode index leaf + dir index root */
 static inline int ocfs2_unlink_credits(struct super_block *sb)
 {
 	/* The quota update from ocfs2_link_credits is unused here... */
-	return 2 * OCFS2_INODE_UPDATE_CREDITS + 1 + ocfs2_link_credits(sb);
+	return 2 * OCFS2_INODE_UPDATE_CREDITS + 3 + ocfs2_link_credits(sb);
 }
 
 /* dinode + orphan dir dinode + inode alloc dinode + orphan dir entry +
- * inode alloc group descriptor */
-#define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 1 + 1)
+ * inode alloc group descriptor + orphan dir index leaf */
+#define OCFS2_DELETE_INODE_CREDITS (3 * OCFS2_INODE_UPDATE_CREDITS + 3)
 
 /* dinode update, old dir dinode update, new dir dinode update, old
  * dir dir entry, new dir dir entry, dir entry update for renaming
- * directory + target unlink */
+ * directory + target unlink + 3 x dir index leaves */
 static inline int ocfs2_rename_credits(struct super_block *sb)
 {
-	return 3 * OCFS2_INODE_UPDATE_CREDITS + 3 + ocfs2_unlink_credits(sb);
+	return 3 * OCFS2_INODE_UPDATE_CREDITS + 6 + ocfs2_unlink_credits(sb);
 }
 
 /* global bitmap dinode, group desc., relinked group,
@@ -422,6 +455,20 @@ static inline int ocfs2_rename_credits(struct super_block *sb)
 					  + OCFS2_INODE_UPDATE_CREDITS \
 					  + OCFS2_XATTR_BLOCK_UPDATE_CREDITS)
 
+/* inode update, removal of dx root block from allocator */
+#define OCFS2_DX_ROOT_REMOVE_CREDITS (OCFS2_INODE_UPDATE_CREDITS +	\
+				      OCFS2_SUBALLOC_FREE)
+
+static inline int ocfs2_calc_dxi_expand_credits(struct super_block *sb)
+{
+	int credits = 1 + OCFS2_SUBALLOC_ALLOC;
+
+	credits += ocfs2_clusters_to_blocks(sb, 1);
+	credits += ocfs2_quota_trans_credits(sb);
+
+	return credits;
+}
+
 /*
  * Please note that the caller must make sure that root_el is the root
  * of extent tree. So for an inode, it should be &fe->id2.i_list. Otherwise
@@ -457,7 +504,7 @@ static inline int ocfs2_calc_extend_credits(struct super_block *sb,
 
 static inline int ocfs2_calc_symlink_credits(struct super_block *sb)
 {
-	int blocks = ocfs2_mknod_credits(sb);
+	int blocks = ocfs2_mknod_credits(sb, 0, 0);
 
 	/* links can be longer than one block so we may update many
 	 * within our single allocated extent. */
diff --git a/fs/ocfs2/localalloc.c b/fs/ocfs2/localalloc.c
index ec70cdbe77fc..bac7e6abaf47 100644
--- a/fs/ocfs2/localalloc.c
+++ b/fs/ocfs2/localalloc.c
@@ -28,7 +28,6 @@
 #include <linux/slab.h>
 #include <linux/highmem.h>
 #include <linux/bitops.h>
-#include <linux/debugfs.h>
 
 #define MLOG_MASK_PREFIX ML_DISK_ALLOC
 #include <cluster/masklog.h>
@@ -75,84 +74,6 @@ static int ocfs2_local_alloc_new_window(struct ocfs2_super *osb,
 static int ocfs2_local_alloc_slide_window(struct ocfs2_super *osb,
 					  struct inode *local_alloc_inode);
 
-#ifdef CONFIG_OCFS2_FS_STATS
-
-static int ocfs2_la_debug_open(struct inode *inode, struct file *file)
-{
-	file->private_data = inode->i_private;
-	return 0;
-}
-
-#define LA_DEBUG_BUF_SZ	PAGE_CACHE_SIZE
-#define LA_DEBUG_VER	1
-static ssize_t ocfs2_la_debug_read(struct file *file, char __user *userbuf,
-				   size_t count, loff_t *ppos)
-{
-	static DEFINE_MUTEX(la_debug_mutex);
-	struct ocfs2_super *osb = file->private_data;
-	int written, ret;
-	char *buf = osb->local_alloc_debug_buf;
-
-	mutex_lock(&la_debug_mutex);
-	memset(buf, 0, LA_DEBUG_BUF_SZ);
-
-	written = snprintf(buf, LA_DEBUG_BUF_SZ,
-			   "0x%x\t0x%llx\t%u\t%u\t0x%x\n",
-			   LA_DEBUG_VER,
-			   (unsigned long long)osb->la_last_gd,
-			   osb->local_alloc_default_bits,
-			   osb->local_alloc_bits, osb->local_alloc_state);
-
-	ret = simple_read_from_buffer(userbuf, count, ppos, buf, written);
-
-	mutex_unlock(&la_debug_mutex);
-	return ret;
-}
-
-static const struct file_operations ocfs2_la_debug_fops = {
-	.open =		ocfs2_la_debug_open,
-	.read =		ocfs2_la_debug_read,
-};
-
-static void ocfs2_init_la_debug(struct ocfs2_super *osb)
-{
-	osb->local_alloc_debug_buf = kmalloc(LA_DEBUG_BUF_SZ, GFP_NOFS);
-	if (!osb->local_alloc_debug_buf)
-		return;
-
-	osb->local_alloc_debug = debugfs_create_file("local_alloc_stats",
-						     S_IFREG|S_IRUSR,
-						     osb->osb_debug_root,
-						     osb,
-						     &ocfs2_la_debug_fops);
-	if (!osb->local_alloc_debug) {
-		kfree(osb->local_alloc_debug_buf);
-		osb->local_alloc_debug_buf = NULL;
-	}
-}
-
-static void ocfs2_shutdown_la_debug(struct ocfs2_super *osb)
-{
-	if (osb->local_alloc_debug)
-		debugfs_remove(osb->local_alloc_debug);
-
-	if (osb->local_alloc_debug_buf)
-		kfree(osb->local_alloc_debug_buf);
-
-	osb->local_alloc_debug_buf = NULL;
-	osb->local_alloc_debug = NULL;
-}
-#else	/* CONFIG_OCFS2_FS_STATS */
-static void ocfs2_init_la_debug(struct ocfs2_super *osb)
-{
-	return;
-}
-static void ocfs2_shutdown_la_debug(struct ocfs2_super *osb)
-{
-	return;
-}
-#endif
-
 static inline int ocfs2_la_state_enabled(struct ocfs2_super *osb)
 {
 	return (osb->local_alloc_state == OCFS2_LA_THROTTLED ||
@@ -226,8 +147,6 @@ int ocfs2_load_local_alloc(struct ocfs2_super *osb)
 
 	mlog_entry_void();
 
-	ocfs2_init_la_debug(osb);
-
 	if (osb->local_alloc_bits == 0)
 		goto bail;
 
@@ -299,9 +218,6 @@ bail:
 	if (inode)
 		iput(inode);
 
-	if (status < 0)
-		ocfs2_shutdown_la_debug(osb);
-
 	mlog(0, "Local alloc window bits = %d\n", osb->local_alloc_bits);
 
 	mlog_exit(status);
@@ -331,8 +247,6 @@ void ocfs2_shutdown_local_alloc(struct ocfs2_super *osb)
 	cancel_delayed_work(&osb->la_enable_wq);
 	flush_workqueue(ocfs2_wq);
 
-	ocfs2_shutdown_la_debug(osb);
-
 	if (osb->local_alloc_state == OCFS2_LA_UNUSED)
 		goto out;
 
diff --git a/fs/ocfs2/namei.c b/fs/ocfs2/namei.c
index 4b11762f249e..2220f93f668b 100644
--- a/fs/ocfs2/namei.c
+++ b/fs/ocfs2/namei.c
@@ -80,14 +80,14 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    struct inode *inode,
 				    char *name,
-				    struct buffer_head **de_bh);
+				    struct ocfs2_dir_lookup_result *lookup);
 
 static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    handle_t *handle,
 			    struct inode *inode,
 			    struct ocfs2_dinode *fe,
 			    char *name,
-			    struct buffer_head *de_bh,
+			    struct ocfs2_dir_lookup_result *lookup,
 			    struct inode *orphan_dir_inode);
 
 static int ocfs2_create_symlink_data(struct ocfs2_super *osb,
@@ -228,17 +228,18 @@ static int ocfs2_mknod(struct inode *dir,
 	struct ocfs2_super *osb;
 	struct ocfs2_dinode *dirfe;
 	struct buffer_head *new_fe_bh = NULL;
-	struct buffer_head *de_bh = NULL;
 	struct inode *inode = NULL;
 	struct ocfs2_alloc_context *inode_ac = NULL;
 	struct ocfs2_alloc_context *data_ac = NULL;
-	struct ocfs2_alloc_context *xattr_ac = NULL;
+	struct ocfs2_alloc_context *meta_ac = NULL;
 	int want_clusters = 0;
+	int want_meta = 0;
 	int xattr_credits = 0;
 	struct ocfs2_security_xattr_info si = {
 		.enable = 1,
 	};
 	int did_quota_inode = 0;
+	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
 	mlog_entry("(0x%p, 0x%p, %d, %lu, '%.*s')\n", dir, dentry, mode,
 		   (unsigned long)dev, dentry->d_name.len,
@@ -254,13 +255,13 @@ static int ocfs2_mknod(struct inode *dir,
 		return status;
 	}
 
-	if (S_ISDIR(mode) && (dir->i_nlink >= OCFS2_LINK_MAX)) {
+	if (S_ISDIR(mode) && (dir->i_nlink >= ocfs2_link_max(osb))) {
 		status = -EMLINK;
 		goto leave;
 	}
 
 	dirfe = (struct ocfs2_dinode *) parent_fe_bh->b_data;
-	if (!dirfe->i_links_count) {
+	if (!ocfs2_read_links_count(dirfe)) {
 		/* can't make a file in a deleted directory. */
 		status = -ENOENT;
 		goto leave;
@@ -274,7 +275,7 @@ static int ocfs2_mknod(struct inode *dir,
 	/* get a spot inside the dir. */
 	status = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh,
 					      dentry->d_name.name,
-					      dentry->d_name.len, &de_bh);
+					      dentry->d_name.len, &lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -308,17 +309,29 @@ static int ocfs2_mknod(struct inode *dir,
 
 	/* calculate meta data/clusters for setting security and acl xattr */
 	status = ocfs2_calc_xattr_init(dir, parent_fe_bh, mode,
-					&si, &want_clusters,
-					&xattr_credits, &xattr_ac);
+				       &si, &want_clusters,
+				       &xattr_credits, &want_meta);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
 	}
 
 	/* Reserve a cluster if creating an extent based directory. */
-	if (S_ISDIR(mode) && !ocfs2_supports_inline_data(osb))
+	if (S_ISDIR(mode) && !ocfs2_supports_inline_data(osb)) {
 		want_clusters += 1;
 
+		/* Dir indexing requires extra space as well */
+		if (ocfs2_supports_indexed_dirs(osb))
+			want_meta++;
+	}
+
+	status = ocfs2_reserve_new_metadata_blocks(osb, want_meta, &meta_ac);
+	if (status < 0) {
+		if (status != -ENOSPC)
+			mlog_errno(status);
+		goto leave;
+	}
+
 	status = ocfs2_reserve_clusters(osb, want_clusters, &data_ac);
 	if (status < 0) {
 		if (status != -ENOSPC)
@@ -326,8 +339,9 @@ static int ocfs2_mknod(struct inode *dir,
 		goto leave;
 	}
 
-	handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb) +
-				   xattr_credits);
+	handle = ocfs2_start_trans(osb, ocfs2_mknod_credits(osb->sb,
+							    S_ISDIR(mode),
+							    xattr_credits));
 	if (IS_ERR(handle)) {
 		status = PTR_ERR(handle);
 		handle = NULL;
@@ -355,7 +369,7 @@ static int ocfs2_mknod(struct inode *dir,
 
 	if (S_ISDIR(mode)) {
 		status = ocfs2_fill_new_dir(osb, handle, dir, inode,
-					    new_fe_bh, data_ac);
+					    new_fe_bh, data_ac, meta_ac);
 		if (status < 0) {
 			mlog_errno(status);
 			goto leave;
@@ -367,7 +381,7 @@ static int ocfs2_mknod(struct inode *dir,
 			mlog_errno(status);
 			goto leave;
 		}
-		le16_add_cpu(&dirfe->i_links_count, 1);
+		ocfs2_add_links_count(dirfe, 1);
 		status = ocfs2_journal_dirty(handle, parent_fe_bh);
 		if (status < 0) {
 			mlog_errno(status);
@@ -377,7 +391,7 @@ static int ocfs2_mknod(struct inode *dir,
 	}
 
 	status = ocfs2_init_acl(handle, inode, dir, new_fe_bh, parent_fe_bh,
-				xattr_ac, data_ac);
+				meta_ac, data_ac);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -385,7 +399,7 @@ static int ocfs2_mknod(struct inode *dir,
 
 	if (si.enable) {
 		status = ocfs2_init_security_set(handle, inode, new_fe_bh, &si,
-						 xattr_ac, data_ac);
+						 meta_ac, data_ac);
 		if (status < 0) {
 			mlog_errno(status);
 			goto leave;
@@ -394,7 +408,7 @@ static int ocfs2_mknod(struct inode *dir,
 
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 OCFS2_I(inode)->ip_blkno, parent_fe_bh,
-				 de_bh);
+				 &lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -423,11 +437,12 @@ leave:
 		mlog(0, "Disk is full\n");
 
 	brelse(new_fe_bh);
-	brelse(de_bh);
 	brelse(parent_fe_bh);
 	kfree(si.name);
 	kfree(si.value);
 
+	ocfs2_free_dir_lookup_result(&lookup);
+
 	if ((status < 0) && inode) {
 		clear_nlink(inode);
 		iput(inode);
@@ -439,8 +454,8 @@ leave:
 	if (data_ac)
 		ocfs2_free_alloc_context(data_ac);
 
-	if (xattr_ac)
-		ocfs2_free_alloc_context(xattr_ac);
+	if (meta_ac)
+		ocfs2_free_alloc_context(meta_ac);
 
 	mlog_exit(status);
 
@@ -462,6 +477,7 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 	struct ocfs2_extent_list *fel;
 	u64 fe_blkno = 0;
 	u16 suballoc_bit;
+	u16 feat;
 
 	mlog_entry("(0x%p, 0x%p, %d, %lu, '%.*s')\n", dir, dentry,
 		   inode->i_mode, (unsigned long)dev, dentry->d_name.len,
@@ -469,8 +485,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 
 	*new_fe_bh = NULL;
 
-	status = ocfs2_claim_new_inode(osb, handle, inode_ac, &suballoc_bit,
-				       &fe_blkno);
+	status = ocfs2_claim_new_inode(osb, handle, dir, parent_fe_bh,
+				       inode_ac, &suballoc_bit, &fe_blkno);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -513,7 +529,8 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 	fe->i_mode = cpu_to_le16(inode->i_mode);
 	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode))
 		fe->id1.dev1.i_rdev = cpu_to_le64(huge_encode_dev(dev));
-	fe->i_links_count = cpu_to_le16(inode->i_nlink);
+
+	ocfs2_set_links_count(fe, inode->i_nlink);
 
 	fe->i_last_eb_blk = 0;
 	strcpy(fe->i_signature, OCFS2_INODE_SIGNATURE);
@@ -525,11 +542,11 @@ static int ocfs2_mknod_locked(struct ocfs2_super *osb,
 	fe->i_dtime = 0;
 
 	/*
-	 * If supported, directories start with inline data.
+	 * If supported, directories start with inline data. If inline
+	 * isn't supported, but indexing is, we start them as indexed.
 	 */
+	feat = le16_to_cpu(fe->i_dyn_features);
 	if (S_ISDIR(inode->i_mode) && ocfs2_supports_inline_data(osb)) {
-		u16 feat = le16_to_cpu(fe->i_dyn_features);
-
 		fe->i_dyn_features = cpu_to_le16(feat | OCFS2_INLINE_DATA_FL);
 
 		fe->id2.i_data.id_count = cpu_to_le16(
@@ -608,9 +625,9 @@ static int ocfs2_link(struct dentry *old_dentry,
 	int err;
 	struct buffer_head *fe_bh = NULL;
 	struct buffer_head *parent_fe_bh = NULL;
-	struct buffer_head *de_bh = NULL;
 	struct ocfs2_dinode *fe = NULL;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
+	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
 	mlog_entry("(inode=%lu, old='%.*s' new='%.*s')\n", inode->i_ino,
 		   old_dentry->d_name.len, old_dentry->d_name.name,
@@ -638,7 +655,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 
 	err = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh,
 					   dentry->d_name.name,
-					   dentry->d_name.len, &de_bh);
+					   dentry->d_name.len, &lookup);
 	if (err < 0) {
 		mlog_errno(err);
 		goto out;
@@ -652,7 +669,7 @@ static int ocfs2_link(struct dentry *old_dentry,
 	}
 
 	fe = (struct ocfs2_dinode *) fe_bh->b_data;
-	if (le16_to_cpu(fe->i_links_count) >= OCFS2_LINK_MAX) {
+	if (ocfs2_read_links_count(fe) >= ocfs2_link_max(osb)) {
 		err = -EMLINK;
 		goto out_unlock_inode;
 	}
@@ -674,13 +691,13 @@ static int ocfs2_link(struct dentry *old_dentry,
 
 	inc_nlink(inode);
 	inode->i_ctime = CURRENT_TIME;
-	fe->i_links_count = cpu_to_le16(inode->i_nlink);
+	ocfs2_set_links_count(fe, inode->i_nlink);
 	fe->i_ctime = cpu_to_le64(inode->i_ctime.tv_sec);
 	fe->i_ctime_nsec = cpu_to_le32(inode->i_ctime.tv_nsec);
 
 	err = ocfs2_journal_dirty(handle, fe_bh);
 	if (err < 0) {
-		le16_add_cpu(&fe->i_links_count, -1);
+		ocfs2_add_links_count(fe, -1);
 		drop_nlink(inode);
 		mlog_errno(err);
 		goto out_commit;
@@ -688,9 +705,9 @@ static int ocfs2_link(struct dentry *old_dentry,
 
 	err = ocfs2_add_entry(handle, dentry, inode,
 			      OCFS2_I(inode)->ip_blkno,
-			      parent_fe_bh, de_bh);
+			      parent_fe_bh, &lookup);
 	if (err) {
-		le16_add_cpu(&fe->i_links_count, -1);
+		ocfs2_add_links_count(fe, -1);
 		drop_nlink(inode);
 		mlog_errno(err);
 		goto out_commit;
@@ -714,10 +731,11 @@ out_unlock_inode:
 out:
 	ocfs2_inode_unlock(dir, 1);
 
-	brelse(de_bh);
 	brelse(fe_bh);
 	brelse(parent_fe_bh);
 
+	ocfs2_free_dir_lookup_result(&lookup);
+
 	mlog_exit(err);
 
 	return err;
@@ -766,10 +784,9 @@ static int ocfs2_unlink(struct inode *dir,
 	struct buffer_head *fe_bh = NULL;
 	struct buffer_head *parent_node_bh = NULL;
 	handle_t *handle = NULL;
-	struct ocfs2_dir_entry *dirent = NULL;
-	struct buffer_head *dirent_bh = NULL;
 	char orphan_name[OCFS2_ORPHAN_NAMELEN + 1];
-	struct buffer_head *orphan_entry_bh = NULL;
+	struct ocfs2_dir_lookup_result lookup = { NULL, };
+	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
 
 	mlog_entry("(0x%p, 0x%p, '%.*s')\n", dir, dentry,
 		   dentry->d_name.len, dentry->d_name.name);
@@ -791,8 +808,8 @@ static int ocfs2_unlink(struct inode *dir,
 	}
 
 	status = ocfs2_find_files_on_disk(dentry->d_name.name,
-					  dentry->d_name.len, &blkno,
-					  dir, &dirent_bh, &dirent);
+					  dentry->d_name.len, &blkno, dir,
+					  &lookup);
 	if (status < 0) {
 		if (status != -ENOENT)
 			mlog_errno(status);
@@ -817,10 +834,7 @@ static int ocfs2_unlink(struct inode *dir,
 	child_locked = 1;
 
 	if (S_ISDIR(inode->i_mode)) {
-	       	if (!ocfs2_empty_dir(inode)) {
-			status = -ENOTEMPTY;
-			goto leave;
-		} else if (inode->i_nlink != 2) {
+		if (inode->i_nlink != 2 || !ocfs2_empty_dir(inode)) {
 			status = -ENOTEMPTY;
 			goto leave;
 		}
@@ -836,8 +850,7 @@ static int ocfs2_unlink(struct inode *dir,
 
 	if (inode_is_unlinkable(inode)) {
 		status = ocfs2_prepare_orphan_dir(osb, &orphan_dir, inode,
-						  orphan_name,
-						  &orphan_entry_bh);
+						  orphan_name, &orphan_insert);
 		if (status < 0) {
 			mlog_errno(status);
 			goto leave;
@@ -863,7 +876,7 @@ static int ocfs2_unlink(struct inode *dir,
 
 	if (inode_is_unlinkable(inode)) {
 		status = ocfs2_orphan_add(osb, handle, inode, fe, orphan_name,
-					  orphan_entry_bh, orphan_dir);
+					  &orphan_insert, orphan_dir);
 		if (status < 0) {
 			mlog_errno(status);
 			goto leave;
@@ -871,7 +884,7 @@ static int ocfs2_unlink(struct inode *dir,
 	}
 
 	/* delete the name from the parent dir */
-	status = ocfs2_delete_entry(handle, dir, dirent, dirent_bh);
+	status = ocfs2_delete_entry(handle, dir, &lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -880,7 +893,7 @@ static int ocfs2_unlink(struct inode *dir,
 	if (S_ISDIR(inode->i_mode))
 		drop_nlink(inode);
 	drop_nlink(inode);
-	fe->i_links_count = cpu_to_le16(inode->i_nlink);
+	ocfs2_set_links_count(fe, inode->i_nlink);
 
 	status = ocfs2_journal_dirty(handle, fe_bh);
 	if (status < 0) {
@@ -916,9 +929,10 @@ leave:
 	}
 
 	brelse(fe_bh);
-	brelse(dirent_bh);
 	brelse(parent_node_bh);
-	brelse(orphan_entry_bh);
+
+	ocfs2_free_dir_lookup_result(&orphan_insert);
+	ocfs2_free_dir_lookup_result(&lookup);
 
 	mlog_exit(status);
 
@@ -1004,8 +1018,8 @@ static int ocfs2_rename(struct inode *old_dir,
 			struct inode *new_dir,
 			struct dentry *new_dentry)
 {
-	int status = 0, rename_lock = 0, parents_locked = 0;
-	int old_child_locked = 0, new_child_locked = 0;
+	int status = 0, rename_lock = 0, parents_locked = 0, target_exists = 0;
+	int old_child_locked = 0, new_child_locked = 0, update_dot_dot = 0;
 	struct inode *old_inode = old_dentry->d_inode;
 	struct inode *new_inode = new_dentry->d_inode;
 	struct inode *orphan_dir = NULL;
@@ -1020,13 +1034,13 @@ static int ocfs2_rename(struct inode *old_dir,
 	handle_t *handle = NULL;
 	struct buffer_head *old_dir_bh = NULL;
 	struct buffer_head *new_dir_bh = NULL;
-	struct ocfs2_dir_entry *old_inode_dot_dot_de = NULL, *old_de = NULL,
-		*new_de = NULL;
-	struct buffer_head *new_de_bh = NULL, *old_de_bh = NULL; // bhs for above
-	struct buffer_head *old_inode_de_bh = NULL; // if old_dentry is a dir,
-						    // this is the 1st dirent bh
 	nlink_t old_dir_nlink = old_dir->i_nlink;
 	struct ocfs2_dinode *old_di;
+	struct ocfs2_dir_lookup_result old_inode_dot_dot_res = { NULL, };
+	struct ocfs2_dir_lookup_result target_lookup_res = { NULL, };
+	struct ocfs2_dir_lookup_result old_entry_lookup = { NULL, };
+	struct ocfs2_dir_lookup_result orphan_insert = { NULL, };
+	struct ocfs2_dir_lookup_result target_insert = { NULL, };
 
 	/* At some point it might be nice to break this function up a
 	 * bit. */
@@ -1108,9 +1122,10 @@ static int ocfs2_rename(struct inode *old_dir,
 	if (S_ISDIR(old_inode->i_mode)) {
 		u64 old_inode_parent;
 
+		update_dot_dot = 1;
 		status = ocfs2_find_files_on_disk("..", 2, &old_inode_parent,
-						  old_inode, &old_inode_de_bh,
-						  &old_inode_dot_dot_de);
+						  old_inode,
+						  &old_inode_dot_dot_res);
 		if (status) {
 			status = -EIO;
 			goto bail;
@@ -1122,7 +1137,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		}
 
 		if (!new_inode && new_dir != old_dir &&
-		    new_dir->i_nlink >= OCFS2_LINK_MAX) {
+		    new_dir->i_nlink >= ocfs2_link_max(osb)) {
 			status = -EMLINK;
 			goto bail;
 		}
@@ -1151,8 +1166,8 @@ static int ocfs2_rename(struct inode *old_dir,
 	 * to delete it */
 	status = ocfs2_find_files_on_disk(new_dentry->d_name.name,
 					  new_dentry->d_name.len,
-					  &newfe_blkno, new_dir, &new_de_bh,
-					  &new_de);
+					  &newfe_blkno, new_dir,
+					  &target_lookup_res);
 	/* The only error we allow here is -ENOENT because the new
 	 * file not existing is perfectly valid. */
 	if ((status < 0) && (status != -ENOENT)) {
@@ -1161,8 +1176,10 @@ static int ocfs2_rename(struct inode *old_dir,
 		mlog_errno(status);
 		goto bail;
 	}
+	if (status == 0)
+		target_exists = 1;
 
-	if (!new_de && new_inode) {
+	if (!target_exists && new_inode) {
 		/*
 		 * Target was unlinked by another node while we were
 		 * waiting to get to ocfs2_rename(). There isn't
@@ -1175,7 +1192,7 @@ static int ocfs2_rename(struct inode *old_dir,
 
 	/* In case we need to overwrite an existing file, we blow it
 	 * away first */
-	if (new_de) {
+	if (target_exists) {
 		/* VFS didn't think there existed an inode here, but
 		 * someone else in the cluster must have raced our
 		 * rename to create one. Today we error cleanly, in
@@ -1216,8 +1233,8 @@ static int ocfs2_rename(struct inode *old_dir,
 
 		newfe = (struct ocfs2_dinode *) newfe_bh->b_data;
 
-		mlog(0, "aha rename over existing... new_de=%p new_blkno=%llu "
-		     "newfebh=%p bhblocknr=%llu\n", new_de,
+		mlog(0, "aha rename over existing... new_blkno=%llu "
+		     "newfebh=%p bhblocknr=%llu\n",
 		     (unsigned long long)newfe_blkno, newfe_bh, newfe_bh ?
 		     (unsigned long long)newfe_bh->b_blocknr : 0ULL);
 
@@ -1225,7 +1242,7 @@ static int ocfs2_rename(struct inode *old_dir,
 			status = ocfs2_prepare_orphan_dir(osb, &orphan_dir,
 							  new_inode,
 							  orphan_name,
-							  &orphan_entry_bh);
+							  &orphan_insert);
 			if (status < 0) {
 				mlog_errno(status);
 				goto bail;
@@ -1243,7 +1260,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		status = ocfs2_prepare_dir_for_insert(osb, new_dir, new_dir_bh,
 						      new_dentry->d_name.name,
 						      new_dentry->d_name.len,
-						      &insert_entry_bh);
+						      &target_insert);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail;
@@ -1258,10 +1275,10 @@ static int ocfs2_rename(struct inode *old_dir,
 		goto bail;
 	}
 
-	if (new_de) {
+	if (target_exists) {
 		if (S_ISDIR(new_inode->i_mode)) {
-			if (!ocfs2_empty_dir(new_inode) ||
-			    new_inode->i_nlink != 2) {
+			if (new_inode->i_nlink != 2 ||
+			    !ocfs2_empty_dir(new_inode)) {
 				status = -ENOTEMPTY;
 				goto bail;
 			}
@@ -1274,10 +1291,10 @@ static int ocfs2_rename(struct inode *old_dir,
 		}
 
 		if (S_ISDIR(new_inode->i_mode) ||
-		    (newfe->i_links_count == cpu_to_le16(1))){
+		    (ocfs2_read_links_count(newfe) == 1)) {
 			status = ocfs2_orphan_add(osb, handle, new_inode,
 						  newfe, orphan_name,
-						  orphan_entry_bh, orphan_dir);
+						  &orphan_insert, orphan_dir);
 			if (status < 0) {
 				mlog_errno(status);
 				goto bail;
@@ -1285,8 +1302,8 @@ static int ocfs2_rename(struct inode *old_dir,
 		}
 
 		/* change the dirent to point to the correct inode */
-		status = ocfs2_update_entry(new_dir, handle, new_de_bh,
-					    new_de, old_inode);
+		status = ocfs2_update_entry(new_dir, handle, &target_lookup_res,
+					    old_inode);
 		if (status < 0) {
 			mlog_errno(status);
 			goto bail;
@@ -1294,9 +1311,9 @@ static int ocfs2_rename(struct inode *old_dir,
 		new_dir->i_version++;
 
 		if (S_ISDIR(new_inode->i_mode))
-			newfe->i_links_count = 0;
+			ocfs2_set_links_count(newfe, 0);
 		else
-			le16_add_cpu(&newfe->i_links_count, -1);
+			ocfs2_add_links_count(newfe, -1);
 
 		status = ocfs2_journal_dirty(handle, newfe_bh);
 		if (status < 0) {
@@ -1307,7 +1324,7 @@ static int ocfs2_rename(struct inode *old_dir,
 		/* if the name was not found in new_dir, add it now */
 		status = ocfs2_add_entry(handle, new_dentry, old_inode,
 					 OCFS2_I(old_inode)->ip_blkno,
-					 new_dir_bh, insert_entry_bh);
+					 new_dir_bh, &target_insert);
 	}
 
 	old_inode->i_ctime = CURRENT_TIME;
@@ -1334,15 +1351,13 @@ static int ocfs2_rename(struct inode *old_dir,
 	 * because the insert might have changed the type of directory
 	 * we're dealing with.
 	 */
-	old_de_bh = ocfs2_find_entry(old_dentry->d_name.name,
-				     old_dentry->d_name.len,
-				     old_dir, &old_de);
-	if (!old_de_bh) {
-		status = -EIO;
+	status = ocfs2_find_entry(old_dentry->d_name.name,
+				  old_dentry->d_name.len, old_dir,
+				  &old_entry_lookup);
+	if (status)
 		goto bail;
-	}
 
-	status = ocfs2_delete_entry(handle, old_dir, old_de, old_de_bh);
+	status = ocfs2_delete_entry(handle, old_dir, &old_entry_lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -1353,9 +1368,10 @@ static int ocfs2_rename(struct inode *old_dir,
 		new_inode->i_ctime = CURRENT_TIME;
 	}
 	old_dir->i_ctime = old_dir->i_mtime = CURRENT_TIME;
-	if (old_inode_de_bh) {
-		status = ocfs2_update_entry(old_inode, handle, old_inode_de_bh,
-					    old_inode_dot_dot_de, new_dir);
+
+	if (update_dot_dot) {
+		status = ocfs2_update_entry(old_inode, handle,
+					    &old_inode_dot_dot_res, new_dir);
 		old_dir->i_nlink--;
 		if (new_inode) {
 			new_inode->i_nlink--;
@@ -1391,14 +1407,13 @@ static int ocfs2_rename(struct inode *old_dir,
 		} else {
 			struct ocfs2_dinode *fe;
 			status = ocfs2_journal_access_di(handle, old_dir,
-							 old_dir_bh,
-							 OCFS2_JOURNAL_ACCESS_WRITE);
+						      old_dir_bh,
+						      OCFS2_JOURNAL_ACCESS_WRITE);
 			fe = (struct ocfs2_dinode *) old_dir_bh->b_data;
-			fe->i_links_count = cpu_to_le16(old_dir->i_nlink);
+			ocfs2_set_links_count(fe, old_dir->i_nlink);
 			status = ocfs2_journal_dirty(handle, old_dir_bh);
 		}
 	}
-
 	ocfs2_dentry_move(old_dentry, new_dentry, old_dir, new_dir);
 	status = 0;
 bail:
@@ -1429,13 +1444,17 @@ bail:
 
 	if (new_inode)
 		iput(new_inode);
+
+	ocfs2_free_dir_lookup_result(&target_lookup_res);
+	ocfs2_free_dir_lookup_result(&old_entry_lookup);
+	ocfs2_free_dir_lookup_result(&old_inode_dot_dot_res);
+	ocfs2_free_dir_lookup_result(&orphan_insert);
+	ocfs2_free_dir_lookup_result(&target_insert);
+
 	brelse(newfe_bh);
 	brelse(old_inode_bh);
 	brelse(old_dir_bh);
 	brelse(new_dir_bh);
-	brelse(new_de_bh);
-	brelse(old_de_bh);
-	brelse(old_inode_de_bh);
 	brelse(orphan_entry_bh);
 	brelse(insert_entry_bh);
 
@@ -1558,7 +1577,6 @@ static int ocfs2_symlink(struct inode *dir,
 	struct inode *inode = NULL;
 	struct super_block *sb;
 	struct buffer_head *new_fe_bh = NULL;
-	struct buffer_head *de_bh = NULL;
 	struct buffer_head *parent_fe_bh = NULL;
 	struct ocfs2_dinode *fe = NULL;
 	struct ocfs2_dinode *dirfe;
@@ -1572,6 +1590,7 @@ static int ocfs2_symlink(struct inode *dir,
 		.enable = 1,
 	};
 	int did_quota = 0, did_quota_inode = 0;
+	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
 	mlog_entry("(0x%p, 0x%p, symname='%s' actual='%.*s')\n", dir,
 		   dentry, symname, dentry->d_name.len, dentry->d_name.name);
@@ -1592,7 +1611,7 @@ static int ocfs2_symlink(struct inode *dir,
 	}
 
 	dirfe = (struct ocfs2_dinode *) parent_fe_bh->b_data;
-	if (!dirfe->i_links_count) {
+	if (!ocfs2_read_links_count(dirfe)) {
 		/* can't make a file in a deleted directory. */
 		status = -ENOENT;
 		goto bail;
@@ -1605,7 +1624,7 @@ static int ocfs2_symlink(struct inode *dir,
 
 	status = ocfs2_prepare_dir_for_insert(osb, dir, parent_fe_bh,
 					      dentry->d_name.name,
-					      dentry->d_name.len, &de_bh);
+					      dentry->d_name.len, &lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -1744,7 +1763,7 @@ static int ocfs2_symlink(struct inode *dir,
 
 	status = ocfs2_add_entry(handle, dentry, inode,
 				 le64_to_cpu(fe->i_blkno), parent_fe_bh,
-				 de_bh);
+				 &lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto bail;
@@ -1772,9 +1791,9 @@ bail:
 
 	brelse(new_fe_bh);
 	brelse(parent_fe_bh);
-	brelse(de_bh);
 	kfree(si.name);
 	kfree(si.value);
+	ocfs2_free_dir_lookup_result(&lookup);
 	if (inode_ac)
 		ocfs2_free_alloc_context(inode_ac);
 	if (data_ac)
@@ -1826,7 +1845,7 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 				    struct inode **ret_orphan_dir,
 				    struct inode *inode,
 				    char *name,
-				    struct buffer_head **de_bh)
+				    struct ocfs2_dir_lookup_result *lookup)
 {
 	struct inode *orphan_dir_inode;
 	struct buffer_head *orphan_dir_bh = NULL;
@@ -1857,7 +1876,7 @@ static int ocfs2_prepare_orphan_dir(struct ocfs2_super *osb,
 
 	status = ocfs2_prepare_dir_for_insert(osb, orphan_dir_inode,
 					      orphan_dir_bh, name,
-					      OCFS2_ORPHAN_NAMELEN, de_bh);
+					      OCFS2_ORPHAN_NAMELEN, lookup);
 	if (status < 0) {
 		ocfs2_inode_unlock(orphan_dir_inode, 1);
 
@@ -1884,7 +1903,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 			    struct inode *inode,
 			    struct ocfs2_dinode *fe,
 			    char *name,
-			    struct buffer_head *de_bh,
+			    struct ocfs2_dir_lookup_result *lookup,
 			    struct inode *orphan_dir_inode)
 {
 	struct buffer_head *orphan_dir_bh = NULL;
@@ -1910,8 +1929,8 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 	 * underneath us... */
 	orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
 	if (S_ISDIR(inode->i_mode))
-		le16_add_cpu(&orphan_fe->i_links_count, 1);
-	orphan_dir_inode->i_nlink = le16_to_cpu(orphan_fe->i_links_count);
+		ocfs2_add_links_count(orphan_fe, 1);
+	orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe);
 
 	status = ocfs2_journal_dirty(handle, orphan_dir_bh);
 	if (status < 0) {
@@ -1922,7 +1941,7 @@ static int ocfs2_orphan_add(struct ocfs2_super *osb,
 	status = __ocfs2_add_entry(handle, orphan_dir_inode, name,
 				   OCFS2_ORPHAN_NAMELEN, inode,
 				   OCFS2_I(inode)->ip_blkno,
-				   orphan_dir_bh, de_bh);
+				   orphan_dir_bh, lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -1955,8 +1974,7 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 	char name[OCFS2_ORPHAN_NAMELEN + 1];
 	struct ocfs2_dinode *orphan_fe;
 	int status = 0;
-	struct buffer_head *target_de_bh = NULL;
-	struct ocfs2_dir_entry *target_de = NULL;
+	struct ocfs2_dir_lookup_result lookup = { NULL, };
 
 	mlog_entry_void();
 
@@ -1971,17 +1989,15 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 	     OCFS2_ORPHAN_NAMELEN);
 
 	/* find it's spot in the orphan directory */
-	target_de_bh = ocfs2_find_entry(name, OCFS2_ORPHAN_NAMELEN,
-					orphan_dir_inode, &target_de);
-	if (!target_de_bh) {
-		status = -ENOENT;
+	status = ocfs2_find_entry(name, OCFS2_ORPHAN_NAMELEN, orphan_dir_inode,
+				  &lookup);
+	if (status) {
 		mlog_errno(status);
 		goto leave;
 	}
 
 	/* remove it from the orphan directory */
-	status = ocfs2_delete_entry(handle, orphan_dir_inode, target_de,
-				    target_de_bh);
+	status = ocfs2_delete_entry(handle, orphan_dir_inode, &lookup);
 	if (status < 0) {
 		mlog_errno(status);
 		goto leave;
@@ -1997,8 +2013,8 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 	/* do the i_nlink dance! :) */
 	orphan_fe = (struct ocfs2_dinode *) orphan_dir_bh->b_data;
 	if (S_ISDIR(inode->i_mode))
-		le16_add_cpu(&orphan_fe->i_links_count, -1);
-	orphan_dir_inode->i_nlink = le16_to_cpu(orphan_fe->i_links_count);
+		ocfs2_add_links_count(orphan_fe, -1);
+	orphan_dir_inode->i_nlink = ocfs2_read_links_count(orphan_fe);
 
 	status = ocfs2_journal_dirty(handle, orphan_dir_bh);
 	if (status < 0) {
@@ -2007,7 +2023,7 @@ int ocfs2_orphan_del(struct ocfs2_super *osb,
 	}
 
 leave:
-	brelse(target_de_bh);
+	ocfs2_free_dir_lookup_result(&lookup);
 
 	mlog_exit(status);
 	return status;
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 946d3c34b90b..1386281950db 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -209,6 +209,7 @@ enum ocfs2_mount_options
 struct ocfs2_journal;
 struct ocfs2_slot_info;
 struct ocfs2_recovery_map;
+struct ocfs2_replay_map;
 struct ocfs2_quota_recovery;
 struct ocfs2_dentry_lock;
 struct ocfs2_super
@@ -264,6 +265,7 @@ struct ocfs2_super
 	atomic_t vol_state;
 	struct mutex recovery_lock;
 	struct ocfs2_recovery_map *recovery_map;
+	struct ocfs2_replay_map *replay_map;
 	struct task_struct *recovery_thread_task;
 	int disable_recovery;
 	wait_queue_head_t checkpoint_event;
@@ -287,11 +289,6 @@ struct ocfs2_super
 
 	u64 la_last_gd;
 
-#ifdef CONFIG_OCFS2_FS_STATS
-	struct dentry *local_alloc_debug;
-	char *local_alloc_debug_buf;
-#endif
-
 	/* Next three fields are for local node slot recovery during
 	 * mount. */
 	int dirty;
@@ -305,9 +302,11 @@ struct ocfs2_super
 	struct ocfs2_cluster_connection *cconn;
 	struct ocfs2_lock_res osb_super_lockres;
 	struct ocfs2_lock_res osb_rename_lockres;
+	struct ocfs2_lock_res osb_nfs_sync_lockres;
 	struct ocfs2_dlm_debug *osb_dlm_debug;
 
 	struct dentry *osb_debug_root;
+	struct dentry *osb_ctxt;
 
 	wait_queue_head_t recovery_event;
 
@@ -344,6 +343,12 @@ struct ocfs2_super
 
 	/* used to protect metaecc calculation check of xattr. */
 	spinlock_t osb_xattr_lock;
+
+	unsigned int			osb_dx_mask;
+	u32				osb_dx_seed[4];
+
+	/* the group we used to allocate inodes. */
+	u64				osb_inode_alloc_group;
 };
 
 #define OCFS2_SB(sb)	    ((struct ocfs2_super *)(sb)->s_fs_info)
@@ -402,6 +407,51 @@ static inline int ocfs2_meta_ecc(struct ocfs2_super *osb)
 	return 0;
 }
 
+static inline int ocfs2_supports_indexed_dirs(struct ocfs2_super *osb)
+{
+	if (osb->s_feature_incompat & OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS)
+		return 1;
+	return 0;
+}
+
+static inline unsigned int ocfs2_link_max(struct ocfs2_super *osb)
+{
+	if (ocfs2_supports_indexed_dirs(osb))
+		return OCFS2_DX_LINK_MAX;
+	return OCFS2_LINK_MAX;
+}
+
+static inline unsigned int ocfs2_read_links_count(struct ocfs2_dinode *di)
+{
+	u32 nlink = le16_to_cpu(di->i_links_count);
+	u32 hi = le16_to_cpu(di->i_links_count_hi);
+
+	if (di->i_dyn_features & cpu_to_le16(OCFS2_INDEXED_DIR_FL))
+		nlink |= (hi << OCFS2_LINKS_HI_SHIFT);
+
+	return nlink;
+}
+
+static inline void ocfs2_set_links_count(struct ocfs2_dinode *di, u32 nlink)
+{
+	u16 lo, hi;
+
+	lo = nlink;
+	hi = nlink >> OCFS2_LINKS_HI_SHIFT;
+
+	di->i_links_count = cpu_to_le16(lo);
+	di->i_links_count_hi = cpu_to_le16(hi);
+}
+
+static inline void ocfs2_add_links_count(struct ocfs2_dinode *di, int n)
+{
+	u32 links = ocfs2_read_links_count(di);
+
+	links += n;
+
+	ocfs2_set_links_count(di, links);
+}
+
 /* set / clear functions because cluster events can make these happen
  * in parallel so we want the transitions to be atomic. this also
  * means that any future flags osb_flags must be protected by spinlock
@@ -482,6 +532,12 @@ static inline int ocfs2_uses_extended_slot_map(struct ocfs2_super *osb)
 #define OCFS2_IS_VALID_DIR_TRAILER(ptr)					\
 	(!strcmp((ptr)->db_signature, OCFS2_DIR_TRAILER_SIGNATURE))
 
+#define OCFS2_IS_VALID_DX_ROOT(ptr)					\
+	(!strcmp((ptr)->dr_signature, OCFS2_DX_ROOT_SIGNATURE))
+
+#define OCFS2_IS_VALID_DX_LEAF(ptr)					\
+	(!strcmp((ptr)->dl_signature, OCFS2_DX_LEAF_SIGNATURE))
+
 static inline unsigned long ino_from_blkno(struct super_block *sb,
 					   u64 blkno)
 {
@@ -532,6 +588,16 @@ static inline u64 ocfs2_clusters_to_bytes(struct super_block *sb,
 	return (u64)clusters << OCFS2_SB(sb)->s_clustersize_bits;
 }
 
+static inline u64 ocfs2_block_to_cluster_start(struct super_block *sb,
+					       u64 blocks)
+{
+	int bits = OCFS2_SB(sb)->s_clustersize_bits - sb->s_blocksize_bits;
+	unsigned int clusters;
+
+	clusters = ocfs2_blocks_to_clusters(sb, blocks);
+	return (u64)clusters << bits;
+}
+
 static inline u64 ocfs2_align_bytes_to_clusters(struct super_block *sb,
 						u64 bytes)
 {
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 2332ef740f4f..7ab6e9e5e77c 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -66,6 +66,8 @@
 #define OCFS2_GROUP_DESC_SIGNATURE      "GROUP01"
 #define OCFS2_XATTR_BLOCK_SIGNATURE	"XATTR01"
 #define OCFS2_DIR_TRAILER_SIGNATURE	"DIRTRL1"
+#define OCFS2_DX_ROOT_SIGNATURE		"DXDIR01"
+#define OCFS2_DX_LEAF_SIGNATURE		"DXLEAF1"
 
 /* Compatibility flags */
 #define OCFS2_HAS_COMPAT_FEATURE(sb,mask)			\
@@ -95,7 +97,8 @@
 					 | OCFS2_FEATURE_INCOMPAT_EXTENDED_SLOT_MAP \
 					 | OCFS2_FEATURE_INCOMPAT_USERSPACE_STACK \
 					 | OCFS2_FEATURE_INCOMPAT_XATTR \
-					 | OCFS2_FEATURE_INCOMPAT_META_ECC)
+					 | OCFS2_FEATURE_INCOMPAT_META_ECC \
+					 | OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS)
 #define OCFS2_FEATURE_RO_COMPAT_SUPP	(OCFS2_FEATURE_RO_COMPAT_UNWRITTEN \
 					 | OCFS2_FEATURE_RO_COMPAT_USRQUOTA \
 					 | OCFS2_FEATURE_RO_COMPAT_GRPQUOTA)
@@ -151,6 +154,9 @@
 /* Support for extended attributes */
 #define OCFS2_FEATURE_INCOMPAT_XATTR		0x0200
 
+/* Support for indexed directores */
+#define OCFS2_FEATURE_INCOMPAT_INDEXED_DIRS	0x0400
+
 /* Metadata checksum and error correction */
 #define OCFS2_FEATURE_INCOMPAT_META_ECC		0x0800
 
@@ -411,8 +417,12 @@ static struct ocfs2_system_inode_info ocfs2_system_inodes[NUM_SYSTEM_INODES] = {
 #define OCFS2_DIR_REC_LEN(name_len)	(((name_len) + OCFS2_DIR_MEMBER_LEN + \
                                           OCFS2_DIR_ROUND) & \
 					 ~OCFS2_DIR_ROUND)
+#define OCFS2_DIR_MIN_REC_LEN	OCFS2_DIR_REC_LEN(1)
 
 #define OCFS2_LINK_MAX		32000
+#define	OCFS2_DX_LINK_MAX	((1U << 31) - 1U)
+#define	OCFS2_LINKS_HI_SHIFT	16
+#define	OCFS2_DX_ENTRIES_MAX	(0xffffffffU)
 
 #define S_SHIFT			12
 static unsigned char ocfs2_type_by_mode[S_IFMT >> S_SHIFT] = {
@@ -628,8 +638,9 @@ struct ocfs2_super_block {
 /*B8*/	__le16 s_xattr_inline_size;	/* extended attribute inline size
 					   for this fs*/
 	__le16 s_reserved0;
-	__le32 s_reserved1;
-/*C0*/  __le64 s_reserved2[16];		/* Fill out superblock */
+	__le32 s_dx_seed[3];		/* seed[0-2] for dx dir hash.
+					 * s_uuid_hash serves as seed[3]. */
+/*C0*/  __le64 s_reserved2[15];		/* Fill out superblock */
 /*140*/
 
 	/*
@@ -679,7 +690,7 @@ struct ocfs2_dinode {
 					   belongs to */
 	__le16 i_suballoc_bit;		/* Bit offset in suballocator
 					   block group */
-/*10*/	__le16 i_reserved0;
+/*10*/	__le16 i_links_count_hi;	/* High 16 bits of links count */
 	__le16 i_xattr_inline_size;
 	__le32 i_clusters;		/* Cluster count */
 	__le32 i_uid;			/* Owner UID */
@@ -705,7 +716,8 @@ struct ocfs2_dinode {
 	__le16 i_dyn_features;
 	__le64 i_xattr_loc;
 /*80*/	struct ocfs2_block_check i_check;	/* Error checking */
-/*88*/	__le64 i_reserved2[6];
+/*88*/	__le64 i_dx_root;		/* Pointer to dir index root block */
+	__le64 i_reserved2[5];
 /*B8*/	union {
 		__le64 i_pad1;		/* Generic way to refer to this
 					   64bit union */
@@ -781,6 +793,90 @@ struct ocfs2_dir_block_trailer {
 /*40*/
 };
 
+ /*
+ * A directory entry in the indexed tree. We don't store the full name here,
+ * but instead provide a pointer to the full dirent in the unindexed tree.
+ *
+ * We also store name_len here so as to reduce the number of leaf blocks we
+ * need to search in case of collisions.
+ */
+struct ocfs2_dx_entry {
+	__le32		dx_major_hash;	/* Used to find logical
+					 * cluster in index */
+	__le32		dx_minor_hash;	/* Lower bits used to find
+					 * block in cluster */
+	__le64		dx_dirent_blk;	/* Physical block in unindexed
+					 * tree holding this dirent. */
+};
+
+struct ocfs2_dx_entry_list {
+	__le32		de_reserved;
+	__le16		de_count;	/* Maximum number of entries
+					 * possible in de_entries */
+	__le16		de_num_used;	/* Current number of
+					 * de_entries entries */
+	struct	ocfs2_dx_entry		de_entries[0];	/* Indexed dir entries
+							 * in a packed array of
+							 * length de_num_used */
+};
+
+#define OCFS2_DX_FLAG_INLINE	0x01
+
+/*
+ * A directory indexing block. Each indexed directory has one of these,
+ * pointed to by ocfs2_dinode.
+ *
+ * This block stores an indexed btree root, and a set of free space
+ * start-of-list pointers.
+ */
+struct ocfs2_dx_root_block {
+	__u8		dr_signature[8];	/* Signature for verification */
+	struct ocfs2_block_check dr_check;	/* Error checking */
+	__le16		dr_suballoc_slot;	/* Slot suballocator this
+						 * block belongs to. */
+	__le16		dr_suballoc_bit;	/* Bit offset in suballocator
+						 * block group */
+	__le32		dr_fs_generation;	/* Must match super block */
+	__le64		dr_blkno;		/* Offset on disk, in blocks */
+	__le64		dr_last_eb_blk;		/* Pointer to last
+						 * extent block */
+	__le32		dr_clusters;		/* Clusters allocated
+						 * to the indexed tree. */
+	__u8		dr_flags;		/* OCFS2_DX_FLAG_* flags */
+	__u8		dr_reserved0;
+	__le16		dr_reserved1;
+	__le64		dr_dir_blkno;		/* Pointer to parent inode */
+	__le32		dr_num_entries;		/* Total number of
+						 * names stored in
+						 * this directory.*/
+	__le32		dr_reserved2;
+	__le64		dr_free_blk;		/* Pointer to head of free
+						 * unindexed block list. */
+	__le64		dr_reserved3[15];
+	union {
+		struct ocfs2_extent_list dr_list; /* Keep this aligned to 128
+						   * bits for maximum space
+						   * efficiency. */
+		struct ocfs2_dx_entry_list dr_entries; /* In-root-block list of
+							* entries. We grow out
+							* to extents if this
+							* gets too big. */
+	};
+};
+
+/*
+ * The header of a leaf block in the indexed tree.
+ */
+struct ocfs2_dx_leaf {
+	__u8		dl_signature[8];/* Signature for verification */
+	struct ocfs2_block_check dl_check;	/* Error checking */
+	__le64		dl_blkno;	/* Offset on disk, in blocks */
+	__le32		dl_fs_generation;/* Must match super block */
+	__le32		dl_reserved0;
+	__le64		dl_reserved1;
+	struct ocfs2_dx_entry_list	dl_list;
+};
+
 /*
  * On disk allocator group structure for OCFS2
  */
@@ -1112,6 +1208,16 @@ static inline int ocfs2_extent_recs_per_inode_with_xattr(
 	return size / sizeof(struct ocfs2_extent_rec);
 }
 
+static inline int ocfs2_extent_recs_per_dx_root(struct super_block *sb)
+{
+	int size;
+
+	size = sb->s_blocksize -
+		offsetof(struct ocfs2_dx_root_block, dr_list.l_recs);
+
+	return size / sizeof(struct ocfs2_extent_rec);
+}
+
 static inline int ocfs2_chain_recs_per_inode(struct super_block *sb)
 {
 	int size;
@@ -1132,6 +1238,26 @@ static inline u16 ocfs2_extent_recs_per_eb(struct super_block *sb)
 	return size / sizeof(struct ocfs2_extent_rec);
 }
 
+static inline int ocfs2_dx_entries_per_leaf(struct super_block *sb)
+{
+	int size;
+
+	size = sb->s_blocksize -
+		offsetof(struct ocfs2_dx_leaf, dl_list.de_entries);
+
+	return size / sizeof(struct ocfs2_dx_entry);
+}
+
+static inline int ocfs2_dx_entries_per_root(struct super_block *sb)
+{
+	int size;
+
+	size = sb->s_blocksize -
+		offsetof(struct ocfs2_dx_root_block, dr_entries.de_entries);
+
+	return size / sizeof(struct ocfs2_dx_entry);
+}
+
 static inline u16 ocfs2_local_alloc_size(struct super_block *sb)
 {
 	u16 size;
diff --git a/fs/ocfs2/ocfs2_lockid.h b/fs/ocfs2/ocfs2_lockid.h
index eb6f50c9ceca..a53ce87481bf 100644
--- a/fs/ocfs2/ocfs2_lockid.h
+++ b/fs/ocfs2/ocfs2_lockid.h
@@ -47,6 +47,7 @@ enum ocfs2_lock_type {
 	OCFS2_LOCK_TYPE_OPEN,
 	OCFS2_LOCK_TYPE_FLOCK,
 	OCFS2_LOCK_TYPE_QINFO,
+	OCFS2_LOCK_TYPE_NFS_SYNC,
 	OCFS2_NUM_LOCK_TYPES
 };
 
@@ -81,6 +82,9 @@ static inline char ocfs2_lock_type_char(enum ocfs2_lock_type type)
 		case OCFS2_LOCK_TYPE_QINFO:
 			c = 'Q';
 			break;
+		case OCFS2_LOCK_TYPE_NFS_SYNC:
+			c = 'Y';
+			break;
 		default:
 			c = '\0';
 	}
diff --git a/fs/ocfs2/suballoc.c b/fs/ocfs2/suballoc.c
index a69628603e18..b4ca5911caaf 100644
--- a/fs/ocfs2/suballoc.c
+++ b/fs/ocfs2/suballoc.c
@@ -48,7 +48,8 @@
 #include "buffer_head_io.h"
 
 #define NOT_ALLOC_NEW_GROUP		0
-#define ALLOC_NEW_GROUP			1
+#define ALLOC_NEW_GROUP			0x1
+#define ALLOC_GROUPS_FROM_GLOBAL	0x2
 
 #define OCFS2_MAX_INODES_TO_STEAL	1024
 
@@ -64,7 +65,9 @@ static int ocfs2_block_group_fill(handle_t *handle,
 static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 				   struct inode *alloc_inode,
 				   struct buffer_head *bh,
-				   u64 max_block);
+				   u64 max_block,
+				   u64 *last_alloc_group,
+				   int flags);
 
 static int ocfs2_cluster_group_search(struct inode *inode,
 				      struct buffer_head *group_bh,
@@ -116,6 +119,7 @@ static inline void ocfs2_block_to_cluster_group(struct inode *inode,
 						u16 *bg_bit_off);
 static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 					     u32 bits_wanted, u64 max_block,
+					     int flags,
 					     struct ocfs2_alloc_context **ac);
 
 void ocfs2_free_ac_resource(struct ocfs2_alloc_context *ac)
@@ -403,7 +407,9 @@ static inline u16 ocfs2_find_smallest_chain(struct ocfs2_chain_list *cl)
 static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 				   struct inode *alloc_inode,
 				   struct buffer_head *bh,
-				   u64 max_block)
+				   u64 max_block,
+				   u64 *last_alloc_group,
+				   int flags)
 {
 	int status, credits;
 	struct ocfs2_dinode *fe = (struct ocfs2_dinode *) bh->b_data;
@@ -423,7 +429,7 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 	cl = &fe->id2.i_chain;
 	status = ocfs2_reserve_clusters_with_limit(osb,
 						   le16_to_cpu(cl->cl_cpg),
-						   max_block, &ac);
+						   max_block, flags, &ac);
 	if (status < 0) {
 		if (status != -ENOSPC)
 			mlog_errno(status);
@@ -440,6 +446,11 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 		goto bail;
 	}
 
+	if (last_alloc_group && *last_alloc_group != 0) {
+		mlog(0, "use old allocation group %llu for block group alloc\n",
+		     (unsigned long long)*last_alloc_group);
+		ac->ac_last_group = *last_alloc_group;
+	}
 	status = ocfs2_claim_clusters(osb,
 				      handle,
 				      ac,
@@ -514,6 +525,11 @@ static int ocfs2_block_group_alloc(struct ocfs2_super *osb,
 	alloc_inode->i_blocks = ocfs2_inode_sector_count(alloc_inode);
 
 	status = 0;
+
+	/* save the new last alloc group so that the caller can cache it. */
+	if (last_alloc_group)
+		*last_alloc_group = ac->ac_last_group;
+
 bail:
 	if (handle)
 		ocfs2_commit_trans(osb, handle);
@@ -531,7 +547,8 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
 				       struct ocfs2_alloc_context *ac,
 				       int type,
 				       u32 slot,
-				       int alloc_new_group)
+				       u64 *last_alloc_group,
+				       int flags)
 {
 	int status;
 	u32 bits_wanted = ac->ac_bits_wanted;
@@ -587,7 +604,7 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
 			goto bail;
 		}
 
-		if (alloc_new_group != ALLOC_NEW_GROUP) {
+		if (!(flags & ALLOC_NEW_GROUP)) {
 			mlog(0, "Alloc File %u Full: wanted=%u, free_bits=%u, "
 			     "and we don't alloc a new group for it.\n",
 			     slot, bits_wanted, free_bits);
@@ -596,7 +613,8 @@ static int ocfs2_reserve_suballoc_bits(struct ocfs2_super *osb,
 		}
 
 		status = ocfs2_block_group_alloc(osb, alloc_inode, bh,
-						 ac->ac_max_block);
+						 ac->ac_max_block,
+						 last_alloc_group, flags);
 		if (status < 0) {
 			if (status != -ENOSPC)
 				mlog_errno(status);
@@ -640,7 +658,7 @@ int ocfs2_reserve_new_metadata_blocks(struct ocfs2_super *osb,
 
 	status = ocfs2_reserve_suballoc_bits(osb, (*ac),
 					     EXTENT_ALLOC_SYSTEM_INODE,
-					     slot, ALLOC_NEW_GROUP);
+					     slot, NULL, ALLOC_NEW_GROUP);
 	if (status < 0) {
 		if (status != -ENOSPC)
 			mlog_errno(status);
@@ -686,7 +704,8 @@ static int ocfs2_steal_inode_from_other_nodes(struct ocfs2_super *osb,
 
 		status = ocfs2_reserve_suballoc_bits(osb, ac,
 						     INODE_ALLOC_SYSTEM_INODE,
-						     slot, NOT_ALLOC_NEW_GROUP);
+						     slot, NULL,
+						     NOT_ALLOC_NEW_GROUP);
 		if (status >= 0) {
 			ocfs2_set_inode_steal_slot(osb, slot);
 			break;
@@ -703,6 +722,7 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
 {
 	int status;
 	s16 slot = ocfs2_get_inode_steal_slot(osb);
+	u64 alloc_group;
 
 	*ac = kzalloc(sizeof(struct ocfs2_alloc_context), GFP_KERNEL);
 	if (!(*ac)) {
@@ -738,12 +758,22 @@ int ocfs2_reserve_new_inode(struct ocfs2_super *osb,
 		goto inode_steal;
 
 	atomic_set(&osb->s_num_inodes_stolen, 0);
+	alloc_group = osb->osb_inode_alloc_group;
 	status = ocfs2_reserve_suballoc_bits(osb, *ac,
 					     INODE_ALLOC_SYSTEM_INODE,
-					     osb->slot_num, ALLOC_NEW_GROUP);
+					     osb->slot_num,
+					     &alloc_group,
+					     ALLOC_NEW_GROUP |
+					     ALLOC_GROUPS_FROM_GLOBAL);
 	if (status >= 0) {
 		status = 0;
 
+		spin_lock(&osb->osb_lock);
+		osb->osb_inode_alloc_group = alloc_group;
+		spin_unlock(&osb->osb_lock);
+		mlog(0, "after reservation, new allocation group is "
+		     "%llu\n", (unsigned long long)alloc_group);
+
 		/*
 		 * Some inodes must be freed by us, so try to allocate
 		 * from our own next time.
@@ -790,7 +820,7 @@ int ocfs2_reserve_cluster_bitmap_bits(struct ocfs2_super *osb,
 
 	status = ocfs2_reserve_suballoc_bits(osb, ac,
 					     GLOBAL_BITMAP_SYSTEM_INODE,
-					     OCFS2_INVALID_SLOT,
+					     OCFS2_INVALID_SLOT, NULL,
 					     ALLOC_NEW_GROUP);
 	if (status < 0 && status != -ENOSPC) {
 		mlog_errno(status);
@@ -806,6 +836,7 @@ bail:
  * things a bit. */
 static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 					     u32 bits_wanted, u64 max_block,
+					     int flags,
 					     struct ocfs2_alloc_context **ac)
 {
 	int status;
@@ -823,7 +854,8 @@ static int ocfs2_reserve_clusters_with_limit(struct ocfs2_super *osb,
 	(*ac)->ac_max_block = max_block;
 
 	status = -ENOSPC;
-	if (ocfs2_alloc_should_use_local(osb, bits_wanted)) {
+	if (!(flags & ALLOC_GROUPS_FROM_GLOBAL) &&
+	    ocfs2_alloc_should_use_local(osb, bits_wanted)) {
 		status = ocfs2_reserve_local_alloc_bits(osb,
 							bits_wanted,
 							*ac);
@@ -861,7 +893,8 @@ int ocfs2_reserve_clusters(struct ocfs2_super *osb,
 			   u32 bits_wanted,
 			   struct ocfs2_alloc_context **ac)
 {
-	return ocfs2_reserve_clusters_with_limit(osb, bits_wanted, 0, ac);
+	return ocfs2_reserve_clusters_with_limit(osb, bits_wanted, 0,
+						 ALLOC_NEW_GROUP, ac);
 }
 
 /*
@@ -1618,8 +1651,41 @@ bail:
 	return status;
 }
 
+static void ocfs2_init_inode_ac_group(struct inode *dir,
+				      struct buffer_head *parent_fe_bh,
+				      struct ocfs2_alloc_context *ac)
+{
+	struct ocfs2_dinode *fe = (struct ocfs2_dinode *)parent_fe_bh->b_data;
+	/*
+	 * Try to allocate inodes from some specific group.
+	 *
+	 * If the parent dir has recorded the last group used in allocation,
+	 * cool, use it. Otherwise if we try to allocate new inode from the
+	 * same slot the parent dir belongs to, use the same chunk.
+	 *
+	 * We are very careful here to avoid the mistake of setting
+	 * ac_last_group to a group descriptor from a different (unlocked) slot.
+	 */
+	if (OCFS2_I(dir)->ip_last_used_group &&
+	    OCFS2_I(dir)->ip_last_used_slot == ac->ac_alloc_slot)
+		ac->ac_last_group = OCFS2_I(dir)->ip_last_used_group;
+	else if (le16_to_cpu(fe->i_suballoc_slot) == ac->ac_alloc_slot)
+		ac->ac_last_group = ocfs2_which_suballoc_group(
+					le64_to_cpu(fe->i_blkno),
+					le16_to_cpu(fe->i_suballoc_bit));
+}
+
+static inline void ocfs2_save_inode_ac_group(struct inode *dir,
+					     struct ocfs2_alloc_context *ac)
+{
+	OCFS2_I(dir)->ip_last_used_group = ac->ac_last_group;
+	OCFS2_I(dir)->ip_last_used_slot = ac->ac_alloc_slot;
+}
+
 int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 			  handle_t *handle,
+			  struct inode *dir,
+			  struct buffer_head *parent_fe_bh,
 			  struct ocfs2_alloc_context *ac,
 			  u16 *suballoc_bit,
 			  u64 *fe_blkno)
@@ -1635,6 +1701,8 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 	BUG_ON(ac->ac_bits_wanted != 1);
 	BUG_ON(ac->ac_which != OCFS2_AC_USE_INODE);
 
+	ocfs2_init_inode_ac_group(dir, parent_fe_bh, ac);
+
 	status = ocfs2_claim_suballoc_bits(osb,
 					   ac,
 					   handle,
@@ -1653,6 +1721,7 @@ int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 
 	*fe_blkno = bg_blkno + (u64) (*suballoc_bit);
 	ac->ac_bits_given++;
+	ocfs2_save_inode_ac_group(dir, ac);
 	status = 0;
 bail:
 	mlog_exit(status);
@@ -2116,3 +2185,162 @@ out:
 
 	return ret;
 }
+
+/*
+ * Read the inode specified by blkno to get suballoc_slot and
+ * suballoc_bit.
+ */
+static int ocfs2_get_suballoc_slot_bit(struct ocfs2_super *osb, u64 blkno,
+				       u16 *suballoc_slot, u16 *suballoc_bit)
+{
+	int status;
+	struct buffer_head *inode_bh = NULL;
+	struct ocfs2_dinode *inode_fe;
+
+	mlog_entry("blkno: %llu\n", blkno);
+
+	/* dirty read disk */
+	status = ocfs2_read_blocks_sync(osb, blkno, 1, &inode_bh);
+	if (status < 0) {
+		mlog(ML_ERROR, "read block %llu failed %d\n", blkno, status);
+		goto bail;
+	}
+
+	inode_fe = (struct ocfs2_dinode *) inode_bh->b_data;
+	if (!OCFS2_IS_VALID_DINODE(inode_fe)) {
+		mlog(ML_ERROR, "invalid inode %llu requested\n", blkno);
+		status = -EINVAL;
+		goto bail;
+	}
+
+	if (le16_to_cpu(inode_fe->i_suballoc_slot) != OCFS2_INVALID_SLOT &&
+	    (u32)le16_to_cpu(inode_fe->i_suballoc_slot) > osb->max_slots - 1) {
+		mlog(ML_ERROR, "inode %llu has invalid suballoc slot %u\n",
+		     blkno, (u32)le16_to_cpu(inode_fe->i_suballoc_slot));
+		status = -EINVAL;
+		goto bail;
+	}
+
+	if (suballoc_slot)
+		*suballoc_slot = le16_to_cpu(inode_fe->i_suballoc_slot);
+	if (suballoc_bit)
+		*suballoc_bit = le16_to_cpu(inode_fe->i_suballoc_bit);
+
+bail:
+	brelse(inode_bh);
+
+	mlog_exit(status);
+	return status;
+}
+
+/*
+ * test whether bit is SET in allocator bitmap or not.  on success, 0
+ * is returned and *res is 1 for SET; 0 otherwise.  when fails, errno
+ * is returned and *res is meaningless.  Call this after you have
+ * cluster locked against suballoc, or you may get a result based on
+ * non-up2date contents
+ */
+static int ocfs2_test_suballoc_bit(struct ocfs2_super *osb,
+				   struct inode *suballoc,
+				   struct buffer_head *alloc_bh, u64 blkno,
+				   u16 bit, int *res)
+{
+	struct ocfs2_dinode *alloc_fe;
+	struct ocfs2_group_desc *group;
+	struct buffer_head *group_bh = NULL;
+	u64 bg_blkno;
+	int status;
+
+	mlog_entry("blkno: %llu bit: %u\n", blkno, (unsigned int)bit);
+
+	alloc_fe = (struct ocfs2_dinode *)alloc_bh->b_data;
+	if ((bit + 1) > ocfs2_bits_per_group(&alloc_fe->id2.i_chain)) {
+		mlog(ML_ERROR, "suballoc bit %u out of range of %u\n",
+		     (unsigned int)bit,
+		     ocfs2_bits_per_group(&alloc_fe->id2.i_chain));
+		status = -EINVAL;
+		goto bail;
+	}
+
+	bg_blkno = ocfs2_which_suballoc_group(blkno, bit);
+	status = ocfs2_read_group_descriptor(suballoc, alloc_fe, bg_blkno,
+					     &group_bh);
+	if (status < 0) {
+		mlog(ML_ERROR, "read group %llu failed %d\n", bg_blkno, status);
+		goto bail;
+	}
+
+	group = (struct ocfs2_group_desc *) group_bh->b_data;
+	*res = ocfs2_test_bit(bit, (unsigned long *)group->bg_bitmap);
+
+bail:
+	brelse(group_bh);
+
+	mlog_exit(status);
+	return status;
+}
+
+/*
+ * Test if the bit representing this inode (blkno) is set in the
+ * suballocator.
+ *
+ * On success, 0 is returned and *res is 1 for SET; 0 otherwise.
+ *
+ * In the event of failure, a negative value is returned and *res is
+ * meaningless.
+ *
+ * Callers must make sure to hold nfs_sync_lock to prevent
+ * ocfs2_delete_inode() on another node from accessing the same
+ * suballocator concurrently.
+ */
+int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res)
+{
+	int status;
+	u16 suballoc_bit = 0, suballoc_slot = 0;
+	struct inode *inode_alloc_inode;
+	struct buffer_head *alloc_bh = NULL;
+
+	mlog_entry("blkno: %llu", blkno);
+
+	status = ocfs2_get_suballoc_slot_bit(osb, blkno, &suballoc_slot,
+					     &suballoc_bit);
+	if (status < 0) {
+		mlog(ML_ERROR, "get alloc slot and bit failed %d\n", status);
+		goto bail;
+	}
+
+	inode_alloc_inode =
+		ocfs2_get_system_file_inode(osb, INODE_ALLOC_SYSTEM_INODE,
+					    suballoc_slot);
+	if (!inode_alloc_inode) {
+		/* the error code could be inaccurate, but we are not able to
+		 * get the correct one. */
+		status = -EINVAL;
+		mlog(ML_ERROR, "unable to get alloc inode in slot %u\n",
+		     (u32)suballoc_slot);
+		goto bail;
+	}
+
+	mutex_lock(&inode_alloc_inode->i_mutex);
+	status = ocfs2_inode_lock(inode_alloc_inode, &alloc_bh, 0);
+	if (status < 0) {
+		mutex_unlock(&inode_alloc_inode->i_mutex);
+		mlog(ML_ERROR, "lock on alloc inode on slot %u failed %d\n",
+		     (u32)suballoc_slot, status);
+		goto bail;
+	}
+
+	status = ocfs2_test_suballoc_bit(osb, inode_alloc_inode, alloc_bh,
+					 blkno, suballoc_bit, res);
+	if (status < 0)
+		mlog(ML_ERROR, "test suballoc bit failed %d\n", status);
+
+	ocfs2_inode_unlock(inode_alloc_inode, 0);
+	mutex_unlock(&inode_alloc_inode->i_mutex);
+
+	iput(inode_alloc_inode);
+	brelse(alloc_bh);
+bail:
+	mlog_exit(status);
+	return status;
+}
diff --git a/fs/ocfs2/suballoc.h b/fs/ocfs2/suballoc.h
index e3c13c77f9e8..8c9a78a43164 100644
--- a/fs/ocfs2/suballoc.h
+++ b/fs/ocfs2/suballoc.h
@@ -88,6 +88,8 @@ int ocfs2_claim_metadata(struct ocfs2_super *osb,
 			 u64 *blkno_start);
 int ocfs2_claim_new_inode(struct ocfs2_super *osb,
 			  handle_t *handle,
+			  struct inode *dir,
+			  struct buffer_head *parent_fe_bh,
 			  struct ocfs2_alloc_context *ac,
 			  u16 *suballoc_bit,
 			  u64 *fe_blkno);
@@ -186,4 +188,6 @@ int ocfs2_lock_allocators(struct inode *inode, struct ocfs2_extent_tree *et,
 			  u32 clusters_to_add, u32 extents_to_split,
 			  struct ocfs2_alloc_context **data_ac,
 			  struct ocfs2_alloc_context **meta_ac);
+
+int ocfs2_test_inode_bit(struct ocfs2_super *osb, u64 blkno, int *res);
 #endif /* _CHAINALLOC_H_ */
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index 7ac83a81ee55..79ff8d9d37e0 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -201,6 +201,170 @@ static const match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
+#ifdef CONFIG_DEBUG_FS
+static int ocfs2_osb_dump(struct ocfs2_super *osb, char *buf, int len)
+{
+	int out = 0;
+	int i;
+	struct ocfs2_cluster_connection *cconn = osb->cconn;
+	struct ocfs2_recovery_map *rm = osb->recovery_map;
+
+	out += snprintf(buf + out, len - out,
+			"%10s => Id: %-s  Uuid: %-s  Gen: 0x%X  Label: %-s\n",
+			"Device", osb->dev_str, osb->uuid_str,
+			osb->fs_generation, osb->vol_label);
+
+	out += snprintf(buf + out, len - out,
+			"%10s => State: %d  Flags: 0x%lX\n", "Volume",
+			atomic_read(&osb->vol_state), osb->osb_flags);
+
+	out += snprintf(buf + out, len - out,
+			"%10s => Block: %lu  Cluster: %d\n", "Sizes",
+			osb->sb->s_blocksize, osb->s_clustersize);
+
+	out += snprintf(buf + out, len - out,
+			"%10s => Compat: 0x%X  Incompat: 0x%X  "
+			"ROcompat: 0x%X\n",
+			"Features", osb->s_feature_compat,
+			osb->s_feature_incompat, osb->s_feature_ro_compat);
+
+	out += snprintf(buf + out, len - out,
+			"%10s => Opts: 0x%lX  AtimeQuanta: %u\n", "Mount",
+			osb->s_mount_opt, osb->s_atime_quantum);
+
+	out += snprintf(buf + out, len - out,
+			"%10s => Stack: %s  Name: %*s  Version: %d.%d\n",
+			"Cluster",
+			(*osb->osb_cluster_stack == '\0' ?
+			 "o2cb" : osb->osb_cluster_stack),
+			cconn->cc_namelen, cconn->cc_name,
+			cconn->cc_version.pv_major, cconn->cc_version.pv_minor);
+
+	spin_lock(&osb->dc_task_lock);
+	out += snprintf(buf + out, len - out,
+			"%10s => Pid: %d  Count: %lu  WakeSeq: %lu  "
+			"WorkSeq: %lu\n", "DownCnvt",
+			task_pid_nr(osb->dc_task), osb->blocked_lock_count,
+			osb->dc_wake_sequence, osb->dc_work_sequence);
+	spin_unlock(&osb->dc_task_lock);
+
+	spin_lock(&osb->osb_lock);
+	out += snprintf(buf + out, len - out, "%10s => Pid: %d  Nodes:",
+			"Recovery",
+			(osb->recovery_thread_task ?
+			 task_pid_nr(osb->recovery_thread_task) : -1));
+	if (rm->rm_used == 0)
+		out += snprintf(buf + out, len - out, " None\n");
+	else {
+		for (i = 0; i < rm->rm_used; i++)
+			out += snprintf(buf + out, len - out, " %d",
+					rm->rm_entries[i]);
+		out += snprintf(buf + out, len - out, "\n");
+	}
+	spin_unlock(&osb->osb_lock);
+
+	out += snprintf(buf + out, len - out,
+			"%10s => Pid: %d  Interval: %lu  Needs: %d\n", "Commit",
+			task_pid_nr(osb->commit_task), osb->osb_commit_interval,
+			atomic_read(&osb->needs_checkpoint));
+
+	out += snprintf(buf + out, len - out,
+			"%10s => State: %d  NumTxns: %d  TxnId: %lu\n",
+			"Journal", osb->journal->j_state,
+			atomic_read(&osb->journal->j_num_trans),
+			osb->journal->j_trans_id);
+
+	out += snprintf(buf + out, len - out,
+			"%10s => GlobalAllocs: %d  LocalAllocs: %d  "
+			"SubAllocs: %d  LAWinMoves: %d  SAExtends: %d\n",
+			"Stats",
+			atomic_read(&osb->alloc_stats.bitmap_data),
+			atomic_read(&osb->alloc_stats.local_data),
+			atomic_read(&osb->alloc_stats.bg_allocs),
+			atomic_read(&osb->alloc_stats.moves),
+			atomic_read(&osb->alloc_stats.bg_extends));
+
+	out += snprintf(buf + out, len - out,
+			"%10s => State: %u  Descriptor: %llu  Size: %u bits  "
+			"Default: %u bits\n",
+			"LocalAlloc", osb->local_alloc_state,
+			(unsigned long long)osb->la_last_gd,
+			osb->local_alloc_bits, osb->local_alloc_default_bits);
+
+	spin_lock(&osb->osb_lock);
+	out += snprintf(buf + out, len - out,
+			"%10s => Slot: %d  NumStolen: %d\n", "Steal",
+			osb->s_inode_steal_slot,
+			atomic_read(&osb->s_num_inodes_stolen));
+	spin_unlock(&osb->osb_lock);
+
+	out += snprintf(buf + out, len - out, "%10s => %3s  %10s\n",
+			"Slots", "Num", "RecoGen");
+
+	for (i = 0; i < osb->max_slots; ++i) {
+		out += snprintf(buf + out, len - out,
+				"%10s  %c %3d  %10d\n",
+				" ",
+				(i == osb->slot_num ? '*' : ' '),
+				i, osb->slot_recovery_generations[i]);
+	}
+
+	return out;
+}
+
+static int ocfs2_osb_debug_open(struct inode *inode, struct file *file)
+{
+	struct ocfs2_super *osb = inode->i_private;
+	char *buf = NULL;
+
+	buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!buf)
+		goto bail;
+
+	i_size_write(inode, ocfs2_osb_dump(osb, buf, PAGE_SIZE));
+
+	file->private_data = buf;
+
+	return 0;
+bail:
+	return -ENOMEM;
+}
+
+static int ocfs2_debug_release(struct inode *inode, struct file *file)
+{
+	kfree(file->private_data);
+	return 0;
+}
+
+static ssize_t ocfs2_debug_read(struct file *file, char __user *buf,
+				size_t nbytes, loff_t *ppos)
+{
+	return simple_read_from_buffer(buf, nbytes, ppos, file->private_data,
+				       i_size_read(file->f_mapping->host));
+}
+#else
+static int ocfs2_osb_debug_open(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+static int ocfs2_debug_release(struct inode *inode, struct file *file)
+{
+	return 0;
+}
+static ssize_t ocfs2_debug_read(struct file *file, char __user *buf,
+				size_t nbytes, loff_t *ppos)
+{
+	return 0;
+}
+#endif	/* CONFIG_DEBUG_FS */
+
+static struct file_operations ocfs2_osb_debug_fops = {
+	.open =		ocfs2_osb_debug_open,
+	.release =	ocfs2_debug_release,
+	.read =		ocfs2_debug_read,
+	.llseek =	generic_file_llseek,
+};
+
 /*
  * write_super and sync_fs ripped right out of ext3.
  */
@@ -926,6 +1090,16 @@ static int ocfs2_fill_super(struct super_block *sb, void *data, int silent)
 		goto read_super_error;
 	}
 
+	osb->osb_ctxt = debugfs_create_file("fs_state", S_IFREG|S_IRUSR,
+					    osb->osb_debug_root,
+					    osb,
+					    &ocfs2_osb_debug_fops);
+	if (!osb->osb_ctxt) {
+		status = -EINVAL;
+		mlog_errno(status);
+		goto read_super_error;
+	}
+
 	status = ocfs2_mount_volume(sb);
 	if (osb->root_inode)
 		inode = igrab(osb->root_inode);
@@ -1620,6 +1794,8 @@ static void ocfs2_dismount_volume(struct super_block *sb, int mnt_err)
 	osb = OCFS2_SB(sb);
 	BUG_ON(!osb);
 
+	debugfs_remove(osb->osb_ctxt);
+
 	ocfs2_disable_quotas(osb);
 
 	ocfs2_shutdown_local_alloc(osb);
@@ -1742,6 +1918,12 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
 	sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits);
 
+	osb->osb_dx_mask = (1 << (cbits - bbits)) - 1;
+
+	for (i = 0; i < 3; i++)
+		osb->osb_dx_seed[i] = le32_to_cpu(di->id2.i_super.s_dx_seed[i]);
+	osb->osb_dx_seed[3] = le32_to_cpu(di->id2.i_super.s_uuid_hash);
+
 	osb->sb = sb;
 	/* Save off for ocfs2_rw_direct */
 	osb->s_sectsize_bits = blksize_bits(sector_size);
@@ -2130,6 +2312,12 @@ static int ocfs2_check_volume(struct ocfs2_super *osb)
 	 * lock, and it's marked as dirty, set the bit in the recover
 	 * map and launch a recovery thread for it. */
 	status = ocfs2_mark_dead_nodes(osb);
+	if (status < 0) {
+		mlog_errno(status);
+		goto finally;
+	}
+
+	status = ocfs2_compute_replay_slots(osb);
 	if (status < 0)
 		mlog_errno(status);
 
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 2563df89fc2a..15631019dc63 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -512,7 +512,7 @@ int ocfs2_calc_xattr_init(struct inode *dir,
 			  struct ocfs2_security_xattr_info *si,
 			  int *want_clusters,
 			  int *xattr_credits,
-			  struct ocfs2_alloc_context **xattr_ac)
+			  int *want_meta)
 {
 	int ret = 0;
 	struct ocfs2_super *osb = OCFS2_SB(dir->i_sb);
@@ -554,11 +554,7 @@ int ocfs2_calc_xattr_init(struct inode *dir,
 	if (dir->i_sb->s_blocksize == OCFS2_MIN_BLOCKSIZE ||
 	    (S_ISDIR(mode) && ocfs2_supports_inline_data(osb)) ||
 	    (s_size + a_size) > OCFS2_XATTR_FREE_IN_IBODY) {
-		ret = ocfs2_reserve_new_metadata_blocks(osb, 1, xattr_ac);
-		if (ret) {
-			mlog_errno(ret);
-			return ret;
-		}
+		*want_meta = *want_meta + 1;
 		*xattr_credits += OCFS2_XATTR_BLOCK_CREATE_CREDITS;
 	}
 
diff --git a/fs/ocfs2/xattr.h b/fs/ocfs2/xattr.h
index 5a1ebc789f7e..1ca7e9a1b7bc 100644
--- a/fs/ocfs2/xattr.h
+++ b/fs/ocfs2/xattr.h
@@ -68,7 +68,7 @@ int ocfs2_calc_security_init(struct inode *,
 			     int *, int *, struct ocfs2_alloc_context **);
 int ocfs2_calc_xattr_init(struct inode *, struct buffer_head *,
 			  int, struct ocfs2_security_xattr_info *,
-			  int *, int *, struct ocfs2_alloc_context **);
+			  int *, int *, int *);
 
 /*
  * xattrs can live inside an inode, as part of an external xattr block,
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index 633e9dc972bb..379ae5fb4411 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -262,14 +262,19 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *s = dentry->d_sb;
 	struct omfs_sb_info *sbi = OMFS_SB(s);
+	u64 id = huge_encode_dev(s->s_bdev->bd_dev);
+
 	buf->f_type = OMFS_MAGIC;
 	buf->f_bsize = sbi->s_blocksize;
 	buf->f_blocks = sbi->s_num_blocks;
 	buf->f_files = sbi->s_num_blocks;
 	buf->f_namelen = OMFS_NAMELEN;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 
 	buf->f_bfree = buf->f_bavail = buf->f_ffree =
 		omfs_count_free(s);
+
 	return 0;
 }
 
@@ -421,7 +426,7 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent)
 
 	sbi->s_uid = current_uid();
 	sbi->s_gid = current_gid();
-	sbi->s_dmask = sbi->s_fmask = current->fs->umask;
+	sbi->s_dmask = sbi->s_fmask = current_umask();
 
 	if (!parse_options((char *) data, sbi))
 		goto end;
diff --git a/fs/open.c b/fs/open.c
index 75b61677daaf..377eb25b6abf 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -29,6 +29,7 @@
 #include <linux/rcupdate.h>
 #include <linux/audit.h>
 #include <linux/falloc.h>
+#include <linux/fs_struct.h>
 
 int vfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
diff --git a/fs/proc/base.c b/fs/proc/base.c
index e0afd326b688..f71559784bfb 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -80,6 +80,7 @@
 #include <linux/oom.h>
 #include <linux/elf.h>
 #include <linux/pid_namespace.h>
+#include <linux/fs_struct.h>
 #include "internal.h"
 
 /* NOTE:
diff --git a/fs/proc/meminfo.c b/fs/proc/meminfo.c
index 43d23948384a..74ea974f5ca6 100644
--- a/fs/proc/meminfo.c
+++ b/fs/proc/meminfo.c
@@ -120,7 +120,7 @@ static int meminfo_proc_show(struct seq_file *m, void *v)
 		K(i.freeram-i.freehigh),
 #endif
 #ifndef CONFIG_MMU
-		K((unsigned long) atomic_read(&mmap_pages_allocated)),
+		K((unsigned long) atomic_long_read(&mmap_pages_allocated)),
 #endif
 		K(i.totalswap),
 		K(i.freeswap),
diff --git a/fs/proc/nommu.c b/fs/proc/nommu.c
index b446d7ad0b0d..7e14d1a04001 100644
--- a/fs/proc/nommu.c
+++ b/fs/proc/nommu.c
@@ -76,7 +76,7 @@ static int nommu_region_show(struct seq_file *m, struct vm_region *region)
 
 /*
  * display a list of all the REGIONs the kernel knows about
- * - nommu kernals have a single flat list
+ * - nommu kernels have a single flat list
  */
 static int nommu_region_list_show(struct seq_file *m, void *_p)
 {
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 343ea1216bc8..863464d5519c 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -2,6 +2,7 @@
 #include <linux/mm.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
+#include <linux/fs_struct.h>
 #include <linux/mount.h>
 #include <linux/ptrace.h>
 #include <linux/seq_file.h>
@@ -49,7 +50,7 @@ void task_mem(struct seq_file *m, struct mm_struct *mm)
 	else
 		bytes += kobjsize(mm);
 	
-	if (current->fs && atomic_read(&current->fs->count) > 1)
+	if (current->fs && current->fs->users > 1)
 		sbytes += kobjsize(current->fs);
 	else
 		bytes += kobjsize(current->fs);
@@ -136,14 +137,14 @@ static int nommu_vma_show(struct seq_file *m, struct vm_area_struct *vma)
 	}
 
 	seq_printf(m,
-		   "%08lx-%08lx %c%c%c%c %08lx %02x:%02x %lu %n",
+		   "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu %n",
 		   vma->vm_start,
 		   vma->vm_end,
 		   flags & VM_READ ? 'r' : '-',
 		   flags & VM_WRITE ? 'w' : '-',
 		   flags & VM_EXEC ? 'x' : '-',
 		   flags & VM_MAYSHARE ? flags & VM_SHARED ? 'S' : 's' : 'p',
-		   vma->vm_pgoff << PAGE_SHIFT,
+		   (unsigned long long) vma->vm_pgoff << PAGE_SHIFT,
 		   MAJOR(dev), MINOR(dev), ino, &len);
 
 	if (file) {
diff --git a/fs/qnx4/inode.c b/fs/qnx4/inode.c
index 2aad1044b84c..fe1f0f31d11c 100644
--- a/fs/qnx4/inode.c
+++ b/fs/qnx4/inode.c
@@ -282,6 +282,7 @@ unsigned long qnx4_block_map( struct inode *inode, long iblock )
 static int qnx4_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	lock_kernel();
 
@@ -291,6 +292,8 @@ static int qnx4_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bfree   = qnx4_count_free_blocks(sb);
 	buf->f_bavail  = buf->f_bfree;
 	buf->f_namelen = QNX4_NAME_MAX;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 
 	unlock_kernel();
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 2ca967a5ef77..607c579e5eca 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -823,7 +823,7 @@ static void add_dquot_ref(struct super_block *sb, int type)
 
 	spin_lock(&inode_lock);
 	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW))
+		if (inode->i_state & (I_FREEING|I_CLEAR|I_WILL_FREE|I_NEW))
 			continue;
 		if (!atomic_read(&inode->i_writecount))
 			continue;
diff --git a/fs/read_write.c b/fs/read_write.c
index 400fe81c973e..9d1e76bb9ee1 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -731,6 +731,62 @@ SYSCALL_DEFINE3(writev, unsigned long, fd, const struct iovec __user *, vec,
 	return ret;
 }
 
+static inline loff_t pos_from_hilo(unsigned long high, unsigned long low)
+{
+#define HALF_LONG_BITS (BITS_PER_LONG / 2)
+	return (((loff_t)high << HALF_LONG_BITS) << HALF_LONG_BITS) | low;
+}
+
+SYSCALL_DEFINE5(preadv, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+	struct file *file;
+	ssize_t ret = -EBADF;
+	int fput_needed;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	file = fget_light(fd, &fput_needed);
+	if (file) {
+		ret = -ESPIPE;
+		if (file->f_mode & FMODE_PREAD)
+			ret = vfs_readv(file, vec, vlen, &pos);
+		fput_light(file, fput_needed);
+	}
+
+	if (ret > 0)
+		add_rchar(current, ret);
+	inc_syscr(current);
+	return ret;
+}
+
+SYSCALL_DEFINE5(pwritev, unsigned long, fd, const struct iovec __user *, vec,
+		unsigned long, vlen, unsigned long, pos_l, unsigned long, pos_h)
+{
+	loff_t pos = pos_from_hilo(pos_h, pos_l);
+	struct file *file;
+	ssize_t ret = -EBADF;
+	int fput_needed;
+
+	if (pos < 0)
+		return -EINVAL;
+
+	file = fget_light(fd, &fput_needed);
+	if (file) {
+		ret = -ESPIPE;
+		if (file->f_mode & FMODE_PWRITE)
+			ret = vfs_writev(file, vec, vlen, &pos);
+		fput_light(file, fput_needed);
+	}
+
+	if (ret > 0)
+		add_wchar(current, ret);
+	inc_syscw(current);
+	return ret;
+}
+
 static ssize_t do_sendfile(int out_fd, int in_fd, loff_t *ppos,
 			   size_t count, loff_t max)
 {
diff --git a/fs/reiserfs/Kconfig b/fs/reiserfs/Kconfig
index 949b8c6addc8..513f431038f9 100644
--- a/fs/reiserfs/Kconfig
+++ b/fs/reiserfs/Kconfig
@@ -1,5 +1,6 @@
 config REISERFS_FS
 	tristate "Reiserfs support"
+	select CRC32
 	help
 	  Stores not just filenames but the files themselves in a balanced
 	  tree.  Uses journalling.
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index 972250c62896..0ae6486d9046 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -27,6 +27,7 @@
 #include <linux/mnt_namespace.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
+#include <linux/crc32.h>
 
 struct file_system_type reiserfs_fs_type;
 
@@ -1904,6 +1905,10 @@ static int reiserfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_bsize = dentry->d_sb->s_blocksize;
 	/* changed to accommodate gcc folks. */
 	buf->f_type = REISERFS_SUPER_MAGIC;
+	buf->f_fsid.val[0] = (u32)crc32_le(0, rs->s_uuid, sizeof(rs->s_uuid)/2);
+	buf->f_fsid.val[1] = (u32)crc32_le(0, rs->s_uuid + sizeof(rs->s_uuid)/2,
+				sizeof(rs->s_uuid)/2);
+
 	return 0;
 }
 
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index d423416d93d1..c303c426fe2b 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -428,7 +428,7 @@ reiserfs_inherit_default_acl(struct reiserfs_transaction_handle *th,
 	} else {
 	      apply_umask:
 		/* no ACL, apply umask */
-		inode->i_mode &= ~current->fs->umask;
+		inode->i_mode &= ~current_umask();
 	}
 
 	return err;
diff --git a/fs/splice.c b/fs/splice.c
index 4ed0ba44a966..dd727d43e5b7 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -59,7 +59,8 @@ static int page_cache_pipe_buf_steal(struct pipe_inode_info *pipe,
 		 */
 		wait_on_page_writeback(page);
 
-		if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+		if (page_has_private(page) &&
+		    !try_to_release_page(page, GFP_KERNEL))
 			goto out_unlock;
 
 		/*
diff --git a/fs/squashfs/super.c b/fs/squashfs/super.c
index 681ec0d83799..ffa6edcd2d0c 100644
--- a/fs/squashfs/super.c
+++ b/fs/squashfs/super.c
@@ -301,6 +301,7 @@ failure:
 static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct squashfs_sb_info *msblk = dentry->d_sb->s_fs_info;
+	u64 id = huge_encode_dev(dentry->d_sb->s_bdev->bd_dev);
 
 	TRACE("Entered squashfs_statfs\n");
 
@@ -311,6 +312,8 @@ static int squashfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = msblk->inodes;
 	buf->f_ffree = 0;
 	buf->f_namelen = SQUASHFS_NAME_LEN;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 
 	return 0;
 }
diff --git a/fs/super.c b/fs/super.c
index 2ba481518ba7..77cb4ec919b9 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -287,6 +287,7 @@ int fsync_super(struct super_block *sb)
 	__fsync_super(sb);
 	return sync_blockdev(sb->s_bdev);
 }
+EXPORT_SYMBOL_GPL(fsync_super);
 
 /**
  *	generic_shutdown_super	-	common helper for ->kill_sb()
diff --git a/fs/sysv/inode.c b/fs/sysv/inode.c
index 3d81bf58dae2..da20b48d350f 100644
--- a/fs/sysv/inode.c
+++ b/fs/sysv/inode.c
@@ -90,6 +90,7 @@ static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
 	struct sysv_sb_info *sbi = SYSV_SB(sb);
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	buf->f_type = sb->s_magic;
 	buf->f_bsize = sb->s_blocksize;
@@ -98,6 +99,8 @@ static int sysv_statfs(struct dentry *dentry, struct kstatfs *buf)
 	buf->f_files = sbi->s_ninodes;
 	buf->f_ffree = sysv_count_free_inodes(sb);
 	buf->f_namelen = SYSV_NAMELEN;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 	return 0;
 }
 
diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig
index e35b54d5059d..830e3f76f442 100644
--- a/fs/ubifs/Kconfig
+++ b/fs/ubifs/Kconfig
@@ -22,7 +22,7 @@ config UBIFS_FS_ADVANCED_COMPR
 	depends on UBIFS_FS
 	help
 	  This option allows to explicitly choose which compressions, if any,
-	  are enabled in UBIFS. Removing compressors means inbility to read
+	  are enabled in UBIFS. Removing compressors means inability to read
 	  existing file systems.
 
 	  If unsure, say 'N'.
@@ -32,7 +32,7 @@ config UBIFS_FS_LZO
 	depends on UBIFS_FS
 	default y
 	help
-	   LZO compressor is generally faster then zlib but compresses worse.
+	   LZO compressor is generally faster than zlib but compresses worse.
 	   Say 'Y' if unsure.
 
 config UBIFS_FS_ZLIB
diff --git a/fs/udf/balloc.c b/fs/udf/balloc.c
index 2bb788a2acb1..e48e9a3af763 100644
--- a/fs/udf/balloc.c
+++ b/fs/udf/balloc.c
@@ -87,12 +87,12 @@ static int read_block_bitmap(struct super_block *sb,
 {
 	struct buffer_head *bh = NULL;
 	int retval = 0;
-	kernel_lb_addr loc;
+	struct kernel_lb_addr loc;
 
 	loc.logicalBlockNum = bitmap->s_extPosition;
 	loc.partitionReferenceNum = UDF_SB(sb)->s_partition;
 
-	bh = udf_tread(sb, udf_get_lb_pblock(sb, loc, block));
+	bh = udf_tread(sb, udf_get_lb_pblock(sb, &loc, block));
 	if (!bh)
 		retval = -EIO;
 
@@ -140,27 +140,29 @@ static inline int load_block_bitmap(struct super_block *sb,
 	return slot;
 }
 
-static bool udf_add_free_space(struct udf_sb_info *sbi,
-				u16 partition, u32 cnt)
+static void udf_add_free_space(struct super_block *sb, u16 partition, u32 cnt)
 {
+	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct logicalVolIntegrityDesc *lvid;
 
-	if (sbi->s_lvid_bh == NULL)
-		return false;
+	if (!sbi->s_lvid_bh)
+		return;
 
 	lvid = (struct logicalVolIntegrityDesc *)sbi->s_lvid_bh->b_data;
 	le32_add_cpu(&lvid->freeSpaceTable[partition], cnt);
-	return true;
+	udf_updated_lvid(sb);
 }
 
 static void udf_bitmap_free_blocks(struct super_block *sb,
 				   struct inode *inode,
 				   struct udf_bitmap *bitmap,
-				   kernel_lb_addr bloc, uint32_t offset,
+				   struct kernel_lb_addr *bloc,
+				   uint32_t offset,
 				   uint32_t count)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct buffer_head *bh = NULL;
+	struct udf_part_map *partmap;
 	unsigned long block;
 	unsigned long block_group;
 	unsigned long bit;
@@ -169,17 +171,17 @@ static void udf_bitmap_free_blocks(struct super_block *sb,
 	unsigned long overflow;
 
 	mutex_lock(&sbi->s_alloc_mutex);
-	if (bloc.logicalBlockNum < 0 ||
-	    (bloc.logicalBlockNum + count) >
-		sbi->s_partmaps[bloc.partitionReferenceNum].s_partition_len) {
+	partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
+	if (bloc->logicalBlockNum < 0 ||
+	    (bloc->logicalBlockNum + count) >
+		partmap->s_partition_len) {
 		udf_debug("%d < %d || %d + %d > %d\n",
-			  bloc.logicalBlockNum, 0, bloc.logicalBlockNum, count,
-			  sbi->s_partmaps[bloc.partitionReferenceNum].
-							s_partition_len);
+			  bloc->logicalBlockNum, 0, bloc->logicalBlockNum,
+			  count, partmap->s_partition_len);
 		goto error_return;
 	}
 
-	block = bloc.logicalBlockNum + offset +
+	block = bloc->logicalBlockNum + offset +
 		(sizeof(struct spaceBitmapDesc) << 3);
 
 	do {
@@ -207,7 +209,7 @@ static void udf_bitmap_free_blocks(struct super_block *sb,
 			} else {
 				if (inode)
 					vfs_dq_free_block(inode, 1);
-				udf_add_free_space(sbi, sbi->s_partition, 1);
+				udf_add_free_space(sb, sbi->s_partition, 1);
 			}
 		}
 		mark_buffer_dirty(bh);
@@ -218,9 +220,6 @@ static void udf_bitmap_free_blocks(struct super_block *sb,
 	} while (overflow);
 
 error_return:
-	sb->s_dirt = 1;
-	if (sbi->s_lvid_bh)
-		mark_buffer_dirty(sbi->s_lvid_bh);
 	mutex_unlock(&sbi->s_alloc_mutex);
 }
 
@@ -277,9 +276,7 @@ static int udf_bitmap_prealloc_blocks(struct super_block *sb,
 	} while (block_count > 0);
 
 out:
-	if (udf_add_free_space(sbi, partition, -alloc_count))
-		mark_buffer_dirty(sbi->s_lvid_bh);
-	sb->s_dirt = 1;
+	udf_add_free_space(sb, partition, -alloc_count);
 	mutex_unlock(&sbi->s_alloc_mutex);
 	return alloc_count;
 }
@@ -409,9 +406,7 @@ got_block:
 
 	mark_buffer_dirty(bh);
 
-	if (udf_add_free_space(sbi, partition, -1))
-		mark_buffer_dirty(sbi->s_lvid_bh);
-	sb->s_dirt = 1;
+	udf_add_free_space(sb, partition, -1);
 	mutex_unlock(&sbi->s_alloc_mutex);
 	*err = 0;
 	return newblock;
@@ -425,26 +420,28 @@ error_return:
 static void udf_table_free_blocks(struct super_block *sb,
 				  struct inode *inode,
 				  struct inode *table,
-				  kernel_lb_addr bloc, uint32_t offset,
+				  struct kernel_lb_addr *bloc,
+				  uint32_t offset,
 				  uint32_t count)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
+	struct udf_part_map *partmap;
 	uint32_t start, end;
 	uint32_t elen;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	struct extent_position oepos, epos;
 	int8_t etype;
 	int i;
 	struct udf_inode_info *iinfo;
 
 	mutex_lock(&sbi->s_alloc_mutex);
-	if (bloc.logicalBlockNum < 0 ||
-	    (bloc.logicalBlockNum + count) >
-		sbi->s_partmaps[bloc.partitionReferenceNum].s_partition_len) {
+	partmap = &sbi->s_partmaps[bloc->partitionReferenceNum];
+	if (bloc->logicalBlockNum < 0 ||
+	    (bloc->logicalBlockNum + count) >
+		partmap->s_partition_len) {
 		udf_debug("%d < %d || %d + %d > %d\n",
 			  bloc.logicalBlockNum, 0, bloc.logicalBlockNum, count,
-			  sbi->s_partmaps[bloc.partitionReferenceNum].
-							s_partition_len);
+			  partmap->s_partition_len);
 		goto error_return;
 	}
 
@@ -453,11 +450,10 @@ static void udf_table_free_blocks(struct super_block *sb,
 	   could occure, but.. oh well */
 	if (inode)
 		vfs_dq_free_block(inode, count);
-	if (udf_add_free_space(sbi, sbi->s_partition, count))
-		mark_buffer_dirty(sbi->s_lvid_bh);
+	udf_add_free_space(sb, sbi->s_partition, count);
 
-	start = bloc.logicalBlockNum + offset;
-	end = bloc.logicalBlockNum + offset + count - 1;
+	start = bloc->logicalBlockNum + offset;
+	end = bloc->logicalBlockNum + offset + count - 1;
 
 	epos.offset = oepos.offset = sizeof(struct unallocSpaceEntry);
 	elen = 0;
@@ -483,7 +479,7 @@ static void udf_table_free_blocks(struct super_block *sb,
 				start += count;
 				count = 0;
 			}
-			udf_write_aext(table, &oepos, eloc, elen, 1);
+			udf_write_aext(table, &oepos, &eloc, elen, 1);
 		} else if (eloc.logicalBlockNum == (end + 1)) {
 			if ((0x3FFFFFFF - elen) <
 					(count << sb->s_blocksize_bits)) {
@@ -502,7 +498,7 @@ static void udf_table_free_blocks(struct super_block *sb,
 				end -= count;
 				count = 0;
 			}
-			udf_write_aext(table, &oepos, eloc, elen, 1);
+			udf_write_aext(table, &oepos, &eloc, elen, 1);
 		}
 
 		if (epos.bh != oepos.bh) {
@@ -532,8 +528,8 @@ static void udf_table_free_blocks(struct super_block *sb,
 		 */
 
 		int adsize;
-		short_ad *sad = NULL;
-		long_ad *lad = NULL;
+		struct short_ad *sad = NULL;
+		struct long_ad *lad = NULL;
 		struct allocExtDesc *aed;
 
 		eloc.logicalBlockNum = start;
@@ -541,9 +537,9 @@ static void udf_table_free_blocks(struct super_block *sb,
 			(count << sb->s_blocksize_bits);
 
 		if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-			adsize = sizeof(short_ad);
+			adsize = sizeof(struct short_ad);
 		else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-			adsize = sizeof(long_ad);
+			adsize = sizeof(struct long_ad);
 		else {
 			brelse(oepos.bh);
 			brelse(epos.bh);
@@ -563,7 +559,7 @@ static void udf_table_free_blocks(struct super_block *sb,
 			elen -= sb->s_blocksize;
 
 			epos.bh = udf_tread(sb,
-					udf_get_lb_pblock(sb, epos.block, 0));
+					udf_get_lb_pblock(sb, &epos.block, 0));
 			if (!epos.bh) {
 				brelse(oepos.bh);
 				goto error_return;
@@ -601,15 +597,15 @@ static void udf_table_free_blocks(struct super_block *sb,
 			if (sbi->s_udfrev >= 0x0200)
 				udf_new_tag(epos.bh->b_data, TAG_IDENT_AED,
 					    3, 1, epos.block.logicalBlockNum,
-					    sizeof(tag));
+					    sizeof(struct tag));
 			else
 				udf_new_tag(epos.bh->b_data, TAG_IDENT_AED,
 					    2, 1, epos.block.logicalBlockNum,
-					    sizeof(tag));
+					    sizeof(struct tag));
 
 			switch (iinfo->i_alloc_type) {
 			case ICBTAG_FLAG_AD_SHORT:
-				sad = (short_ad *)sptr;
+				sad = (struct short_ad *)sptr;
 				sad->extLength = cpu_to_le32(
 					EXT_NEXT_EXTENT_ALLOCDECS |
 					sb->s_blocksize);
@@ -617,7 +613,7 @@ static void udf_table_free_blocks(struct super_block *sb,
 					cpu_to_le32(epos.block.logicalBlockNum);
 				break;
 			case ICBTAG_FLAG_AD_LONG:
-				lad = (long_ad *)sptr;
+				lad = (struct long_ad *)sptr;
 				lad->extLength = cpu_to_le32(
 					EXT_NEXT_EXTENT_ALLOCDECS |
 					sb->s_blocksize);
@@ -635,7 +631,7 @@ static void udf_table_free_blocks(struct super_block *sb,
 
 		/* It's possible that stealing the block emptied the extent */
 		if (elen) {
-			udf_write_aext(table, &epos, eloc, elen, 1);
+			udf_write_aext(table, &epos, &eloc, elen, 1);
 
 			if (!epos.bh) {
 				iinfo->i_lenAlloc += adsize;
@@ -653,7 +649,6 @@ static void udf_table_free_blocks(struct super_block *sb,
 	brelse(oepos.bh);
 
 error_return:
-	sb->s_dirt = 1;
 	mutex_unlock(&sbi->s_alloc_mutex);
 	return;
 }
@@ -666,7 +661,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	int alloc_count = 0;
 	uint32_t elen, adsize;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	struct extent_position epos;
 	int8_t etype = -1;
 	struct udf_inode_info *iinfo;
@@ -677,9 +672,9 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
 
 	iinfo = UDF_I(table);
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		adsize = sizeof(short_ad);
+		adsize = sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 	else
 		return 0;
 
@@ -707,7 +702,7 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
 			alloc_count = block_count;
 			eloc.logicalBlockNum += alloc_count;
 			elen -= (alloc_count << sb->s_blocksize_bits);
-			udf_write_aext(table, &epos, eloc,
+			udf_write_aext(table, &epos, &eloc,
 					(etype << 30) | elen, 1);
 		} else
 			udf_delete_aext(table, epos, eloc,
@@ -718,10 +713,8 @@ static int udf_table_prealloc_blocks(struct super_block *sb,
 
 	brelse(epos.bh);
 
-	if (alloc_count && udf_add_free_space(sbi, partition, -alloc_count)) {
-		mark_buffer_dirty(sbi->s_lvid_bh);
-		sb->s_dirt = 1;
-	}
+	if (alloc_count)
+		udf_add_free_space(sb, partition, -alloc_count);
 	mutex_unlock(&sbi->s_alloc_mutex);
 	return alloc_count;
 }
@@ -735,7 +728,7 @@ static int udf_table_new_block(struct super_block *sb,
 	uint32_t spread = 0xFFFFFFFF, nspread = 0xFFFFFFFF;
 	uint32_t newblock = 0, adsize;
 	uint32_t elen, goal_elen = 0;
-	kernel_lb_addr eloc, uninitialized_var(goal_eloc);
+	struct kernel_lb_addr eloc, uninitialized_var(goal_eloc);
 	struct extent_position epos, goal_epos;
 	int8_t etype;
 	struct udf_inode_info *iinfo = UDF_I(table);
@@ -743,9 +736,9 @@ static int udf_table_new_block(struct super_block *sb,
 	*err = -ENOSPC;
 
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		adsize = sizeof(short_ad);
+		adsize = sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 	else
 		return newblock;
 
@@ -814,46 +807,37 @@ static int udf_table_new_block(struct super_block *sb,
 	}
 
 	if (goal_elen)
-		udf_write_aext(table, &goal_epos, goal_eloc, goal_elen, 1);
+		udf_write_aext(table, &goal_epos, &goal_eloc, goal_elen, 1);
 	else
 		udf_delete_aext(table, goal_epos, goal_eloc, goal_elen);
 	brelse(goal_epos.bh);
 
-	if (udf_add_free_space(sbi, partition, -1))
-		mark_buffer_dirty(sbi->s_lvid_bh);
+	udf_add_free_space(sb, partition, -1);
 
-	sb->s_dirt = 1;
 	mutex_unlock(&sbi->s_alloc_mutex);
 	*err = 0;
 	return newblock;
 }
 
-inline void udf_free_blocks(struct super_block *sb,
-			    struct inode *inode,
-			    kernel_lb_addr bloc, uint32_t offset,
-			    uint32_t count)
+void udf_free_blocks(struct super_block *sb, struct inode *inode,
+		     struct kernel_lb_addr *bloc, uint32_t offset,
+		     uint32_t count)
 {
-	uint16_t partition = bloc.partitionReferenceNum;
+	uint16_t partition = bloc->partitionReferenceNum;
 	struct udf_part_map *map = &UDF_SB(sb)->s_partmaps[partition];
 
 	if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_BITMAP) {
-		return udf_bitmap_free_blocks(sb, inode,
-					      map->s_uspace.s_bitmap,
-					      bloc, offset, count);
+		udf_bitmap_free_blocks(sb, inode, map->s_uspace.s_bitmap,
+				       bloc, offset, count);
 	} else if (map->s_partition_flags & UDF_PART_FLAG_UNALLOC_TABLE) {
-		return udf_table_free_blocks(sb, inode,
-					     map->s_uspace.s_table,
-					     bloc, offset, count);
+		udf_table_free_blocks(sb, inode, map->s_uspace.s_table,
+				      bloc, offset, count);
 	} else if (map->s_partition_flags & UDF_PART_FLAG_FREED_BITMAP) {
-		return udf_bitmap_free_blocks(sb, inode,
-					      map->s_fspace.s_bitmap,
-					      bloc, offset, count);
+		udf_bitmap_free_blocks(sb, inode, map->s_fspace.s_bitmap,
+				       bloc, offset, count);
 	} else if (map->s_partition_flags & UDF_PART_FLAG_FREED_TABLE) {
-		return udf_table_free_blocks(sb, inode,
-					     map->s_fspace.s_table,
-					     bloc, offset, count);
-	} else {
-		return;
+		udf_table_free_blocks(sb, inode, map->s_fspace.s_table,
+				      bloc, offset, count);
 	}
 }
 
diff --git a/fs/udf/dir.c b/fs/udf/dir.c
index 62dc270c69d1..2efd4d5291b6 100644
--- a/fs/udf/dir.c
+++ b/fs/udf/dir.c
@@ -51,7 +51,7 @@ static int do_udf_readdir(struct inode *dir, struct file *filp,
 	uint8_t lfi;
 	loff_t size = udf_ext0_offset(dir) + dir->i_size;
 	struct buffer_head *tmp, *bha[16];
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen;
 	sector_t offset;
 	int i, num, ret = 0;
@@ -80,13 +80,13 @@ static int do_udf_readdir(struct inode *dir, struct file *filp,
 			ret = -ENOENT;
 			goto out;
 		}
-		block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
+		block = udf_get_lb_pblock(dir->i_sb, &eloc, offset);
 		if ((++offset << dir->i_sb->s_blocksize_bits) < elen) {
 			if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-				epos.offset -= sizeof(short_ad);
+				epos.offset -= sizeof(struct short_ad);
 			else if (iinfo->i_alloc_type ==
 					ICBTAG_FLAG_AD_LONG)
-				epos.offset -= sizeof(long_ad);
+				epos.offset -= sizeof(struct long_ad);
 		} else {
 			offset = 0;
 		}
@@ -101,7 +101,7 @@ static int do_udf_readdir(struct inode *dir, struct file *filp,
 			if (i + offset > (elen >> dir->i_sb->s_blocksize_bits))
 				i = (elen >> dir->i_sb->s_blocksize_bits) - offset;
 			for (num = 0; i > 0; i--) {
-				block = udf_get_lb_pblock(dir->i_sb, eloc, offset + i);
+				block = udf_get_lb_pblock(dir->i_sb, &eloc, offset + i);
 				tmp = udf_tgetblk(dir->i_sb, block);
 				if (tmp && !buffer_uptodate(tmp) && !buffer_locked(tmp))
 					bha[num++] = tmp;
@@ -161,9 +161,9 @@ static int do_udf_readdir(struct inode *dir, struct file *filp,
 			memcpy(fname, "..", flen);
 			dt_type = DT_DIR;
 		} else {
-			kernel_lb_addr tloc = lelb_to_cpu(cfi.icb.extLocation);
+			struct kernel_lb_addr tloc = lelb_to_cpu(cfi.icb.extLocation);
 
-			iblock = udf_get_lb_pblock(dir->i_sb, tloc, 0);
+			iblock = udf_get_lb_pblock(dir->i_sb, &tloc, 0);
 			flen = udf_get_filename(dir->i_sb, nameptr, fname, lfi);
 			dt_type = DT_UNKNOWN;
 		}
diff --git a/fs/udf/directory.c b/fs/udf/directory.c
index 2820f8fcf4cc..1d2c570704c8 100644
--- a/fs/udf/directory.c
+++ b/fs/udf/directory.c
@@ -20,7 +20,7 @@
 
 #if 0
 static uint8_t *udf_filead_read(struct inode *dir, uint8_t *tmpad,
-				uint8_t ad_size, kernel_lb_addr fe_loc,
+				uint8_t ad_size, struct kernel_lb_addr fe_loc,
 				int *pos, int *offset, struct buffer_head **bh,
 				int *error)
 {
@@ -75,7 +75,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos,
 					 struct udf_fileident_bh *fibh,
 					 struct fileIdentDesc *cfi,
 					 struct extent_position *epos,
-					 kernel_lb_addr *eloc, uint32_t *elen,
+					 struct kernel_lb_addr *eloc, uint32_t *elen,
 					 sector_t *offset)
 {
 	struct fileIdentDesc *fi;
@@ -111,7 +111,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos,
 		    (EXT_RECORDED_ALLOCATED >> 30))
 			return NULL;
 
-		block = udf_get_lb_pblock(dir->i_sb, *eloc, *offset);
+		block = udf_get_lb_pblock(dir->i_sb, eloc, *offset);
 
 		(*offset)++;
 
@@ -131,7 +131,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos,
 			if (i + *offset > (*elen >> blocksize_bits))
 				i = (*elen >> blocksize_bits)-*offset;
 			for (num = 0; i > 0; i--) {
-				block = udf_get_lb_pblock(dir->i_sb, *eloc,
+				block = udf_get_lb_pblock(dir->i_sb, eloc,
 							  *offset + i);
 				tmp = udf_tgetblk(dir->i_sb, block);
 				if (tmp && !buffer_uptodate(tmp) &&
@@ -169,7 +169,7 @@ struct fileIdentDesc *udf_fileident_read(struct inode *dir, loff_t *nf_pos,
 		    (EXT_RECORDED_ALLOCATED >> 30))
 			return NULL;
 
-		block = udf_get_lb_pblock(dir->i_sb, *eloc, *offset);
+		block = udf_get_lb_pblock(dir->i_sb, eloc, *offset);
 
 		(*offset)++;
 
@@ -249,9 +249,9 @@ struct fileIdentDesc *udf_get_fileident(void *buffer, int bufsize, int *offset)
 }
 
 #if 0
-static extent_ad *udf_get_fileextent(void *buffer, int bufsize, int *offset)
+static struct extent_ad *udf_get_fileextent(void *buffer, int bufsize, int *offset)
 {
-	extent_ad *ext;
+	struct extent_ad *ext;
 	struct fileEntry *fe;
 	uint8_t *ptr;
 
@@ -274,54 +274,54 @@ static extent_ad *udf_get_fileextent(void *buffer, int bufsize, int *offset)
 	if ((*offset > 0) && (*offset < le32_to_cpu(fe->lengthAllocDescs)))
 		ptr += *offset;
 
-	ext = (extent_ad *)ptr;
+	ext = (struct extent_ad *)ptr;
 
-	*offset = *offset + sizeof(extent_ad);
+	*offset = *offset + sizeof(struct extent_ad);
 	return ext;
 }
 #endif
 
-short_ad *udf_get_fileshortad(uint8_t *ptr, int maxoffset, uint32_t *offset,
+struct short_ad *udf_get_fileshortad(uint8_t *ptr, int maxoffset, uint32_t *offset,
 			      int inc)
 {
-	short_ad *sa;
+	struct short_ad *sa;
 
 	if ((!ptr) || (!offset)) {
 		printk(KERN_ERR "udf: udf_get_fileshortad() invalidparms\n");
 		return NULL;
 	}
 
-	if ((*offset + sizeof(short_ad)) > maxoffset)
+	if ((*offset + sizeof(struct short_ad)) > maxoffset)
 		return NULL;
 	else {
-		sa = (short_ad *)ptr;
+		sa = (struct short_ad *)ptr;
 		if (sa->extLength == 0)
 			return NULL;
 	}
 
 	if (inc)
-		*offset += sizeof(short_ad);
+		*offset += sizeof(struct short_ad);
 	return sa;
 }
 
-long_ad *udf_get_filelongad(uint8_t *ptr, int maxoffset, uint32_t *offset, int inc)
+struct long_ad *udf_get_filelongad(uint8_t *ptr, int maxoffset, uint32_t *offset, int inc)
 {
-	long_ad *la;
+	struct long_ad *la;
 
 	if ((!ptr) || (!offset)) {
 		printk(KERN_ERR "udf: udf_get_filelongad() invalidparms\n");
 		return NULL;
 	}
 
-	if ((*offset + sizeof(long_ad)) > maxoffset)
+	if ((*offset + sizeof(struct long_ad)) > maxoffset)
 		return NULL;
 	else {
-		la = (long_ad *)ptr;
+		la = (struct long_ad *)ptr;
 		if (la->extLength == 0)
 			return NULL;
 	}
 
 	if (inc)
-		*offset += sizeof(long_ad);
+		*offset += sizeof(struct long_ad);
 	return la;
 }
diff --git a/fs/udf/ecma_167.h b/fs/udf/ecma_167.h
index a0974df82b31..4792b771aa80 100644
--- a/fs/udf/ecma_167.h
+++ b/fs/udf/ecma_167.h
@@ -38,10 +38,10 @@
 #define _ECMA_167_H 1
 
 /* Character set specification (ECMA 167r3 1/7.2.1) */
-typedef struct {
+struct charspec {
 	uint8_t		charSetType;
 	uint8_t		charSetInfo[63];
-} __attribute__ ((packed)) charspec;
+} __attribute__ ((packed));
 
 /* Character Set Type (ECMA 167r3 1/7.2.1.1) */
 #define CHARSPEC_TYPE_CS0		0x00	/* (1/7.2.2) */
@@ -57,7 +57,7 @@ typedef struct {
 typedef uint8_t		dstring;
 
 /* Timestamp (ECMA 167r3 1/7.3) */
-typedef struct {
+struct timestamp {
 	__le16		typeAndTimezone;
 	__le16		year;
 	uint8_t		month;
@@ -68,7 +68,7 @@ typedef struct {
 	uint8_t		centiseconds;
 	uint8_t		hundredsOfMicroseconds;
 	uint8_t		microseconds;
-} __attribute__ ((packed)) timestamp;
+} __attribute__ ((packed));
 
 /* Type and Time Zone (ECMA 167r3 1/7.3.1) */
 #define TIMESTAMP_TYPE_MASK		0xF000
@@ -78,11 +78,11 @@ typedef struct {
 #define TIMESTAMP_TIMEZONE_MASK		0x0FFF
 
 /* Entity identifier (ECMA 167r3 1/7.4) */
-typedef struct {
+struct regid {
 	uint8_t		flags;
 	uint8_t		ident[23];
 	uint8_t		identSuffix[8];
-} __attribute__ ((packed)) regid;
+} __attribute__ ((packed));
 
 /* Flags (ECMA 167r3 1/7.4.1) */
 #define ENTITYID_FLAGS_DIRTY		0x00
@@ -126,38 +126,38 @@ struct terminatingExtendedAreaDesc {
 
 /* Boot Descriptor (ECMA 167r3 2/9.4) */
 struct bootDesc {
-	uint8_t		structType;
-	uint8_t		stdIdent[VSD_STD_ID_LEN];
-	uint8_t		structVersion;
-	uint8_t		reserved1;
-	regid		archType;
-	regid		bootIdent;
-	__le32		bootExtLocation;
-	__le32		bootExtLength;
-	__le64		loadAddress;
-	__le64		startAddress;
-	timestamp	descCreationDateAndTime;
-	__le16		flags;
-	uint8_t		reserved2[32];
-	uint8_t		bootUse[1906];
+	uint8_t			structType;
+	uint8_t			stdIdent[VSD_STD_ID_LEN];
+	uint8_t			structVersion;
+	uint8_t			reserved1;
+	struct regid		archType;
+	struct regid		bootIdent;
+	__le32			bootExtLocation;
+	__le32			bootExtLength;
+	__le64			loadAddress;
+	__le64			startAddress;
+	struct timestamp	descCreationDateAndTime;
+	__le16			flags;
+	uint8_t			reserved2[32];
+	uint8_t			bootUse[1906];
 } __attribute__ ((packed));
 
 /* Flags (ECMA 167r3 2/9.4.12) */
 #define BOOT_FLAGS_ERASE		0x01
 
 /* Extent Descriptor (ECMA 167r3 3/7.1) */
-typedef struct {
+struct extent_ad {
 	__le32		extLength;
 	__le32		extLocation;
-} __attribute__ ((packed)) extent_ad;
+} __attribute__ ((packed));
 
-typedef struct {
+struct kernel_extent_ad {
 	uint32_t	extLength;
 	uint32_t	extLocation;
-} kernel_extent_ad;
+};
 
 /* Descriptor Tag (ECMA 167r3 3/7.2) */
-typedef struct {
+struct tag {
 	__le16		tagIdent;
 	__le16		descVersion;
 	uint8_t		tagChecksum;
@@ -166,7 +166,7 @@ typedef struct {
 	__le16		descCRC;
 	__le16		descCRCLength;
 	__le32		tagLocation;
-} __attribute__ ((packed)) tag;
+} __attribute__ ((packed));
 
 /* Tag Identifier (ECMA 167r3 3/7.2.1) */
 #define TAG_IDENT_PVD			0x0001
@@ -190,28 +190,28 @@ struct NSRDesc {
 
 /* Primary Volume Descriptor (ECMA 167r3 3/10.1) */
 struct primaryVolDesc {
-	tag		descTag;
-	__le32		volDescSeqNum;
-	__le32		primaryVolDescNum;
-	dstring		volIdent[32];
-	__le16		volSeqNum;
-	__le16		maxVolSeqNum;
-	__le16		interchangeLvl;
-	__le16		maxInterchangeLvl;
-	__le32		charSetList;
-	__le32		maxCharSetList;
-	dstring		volSetIdent[128];
-	charspec	descCharSet;
-	charspec	explanatoryCharSet;
-	extent_ad	volAbstract;
-	extent_ad	volCopyright;
-	regid		appIdent;
-	timestamp	recordingDateAndTime;
-	regid		impIdent;
-	uint8_t		impUse[64];
-	__le32		predecessorVolDescSeqLocation;
-	__le16		flags;
-	uint8_t		reserved[22];
+	struct tag		descTag;
+	__le32			volDescSeqNum;
+	__le32			primaryVolDescNum;
+	dstring			volIdent[32];
+	__le16			volSeqNum;
+	__le16			maxVolSeqNum;
+	__le16			interchangeLvl;
+	__le16			maxInterchangeLvl;
+	__le32			charSetList;
+	__le32			maxCharSetList;
+	dstring			volSetIdent[128];
+	struct charspec		descCharSet;
+	struct charspec		explanatoryCharSet;
+	struct extent_ad	volAbstract;
+	struct extent_ad	volCopyright;
+	struct regid		appIdent;
+	struct timestamp	recordingDateAndTime;
+	struct regid		impIdent;
+	uint8_t			impUse[64];
+	__le32			predecessorVolDescSeqLocation;
+	__le16			flags;
+	uint8_t			reserved[22];
 } __attribute__ ((packed));
 
 /* Flags (ECMA 167r3 3/10.1.21) */
@@ -219,40 +219,40 @@ struct primaryVolDesc {
 
 /* Anchor Volume Descriptor Pointer (ECMA 167r3 3/10.2) */
 struct anchorVolDescPtr {
-	tag		descTag;
-	extent_ad	mainVolDescSeqExt;
-	extent_ad	reserveVolDescSeqExt;
-	uint8_t	 	reserved[480];
+	struct tag		descTag;
+	struct extent_ad	mainVolDescSeqExt;
+	struct extent_ad	reserveVolDescSeqExt;
+	uint8_t	 		reserved[480];
 } __attribute__ ((packed));
 
 /* Volume Descriptor Pointer (ECMA 167r3 3/10.3) */
 struct volDescPtr {
-	tag		descTag;
-	__le32		volDescSeqNum;
-	extent_ad	nextVolDescSeqExt;
-	uint8_t		reserved[484];
+	struct tag		descTag;
+	__le32			volDescSeqNum;
+	struct extent_ad	nextVolDescSeqExt;
+	uint8_t			reserved[484];
 } __attribute__ ((packed));
 
 /* Implementation Use Volume Descriptor (ECMA 167r3 3/10.4) */
 struct impUseVolDesc {
-	tag		descTag;
+	struct tag	descTag;
 	__le32		volDescSeqNum;
-	regid		impIdent;
+	struct regid	impIdent;
 	uint8_t		impUse[460];
 } __attribute__ ((packed));
 
 /* Partition Descriptor (ECMA 167r3 3/10.5) */
 struct partitionDesc {
-	tag descTag;
+	struct tag descTag;
 	__le32 volDescSeqNum;
 	__le16 partitionFlags;
 	__le16 partitionNumber;
-	regid partitionContents;
+	struct regid partitionContents;
 	uint8_t partitionContentsUse[128];
 	__le32 accessType;
 	__le32 partitionStartingLocation;
 	__le32 partitionLength;
-	regid impIdent;
+	struct regid impIdent;
 	uint8_t impUse[128];
 	uint8_t reserved[156];
 } __attribute__ ((packed));
@@ -278,19 +278,19 @@ struct partitionDesc {
 
 /* Logical Volume Descriptor (ECMA 167r3 3/10.6) */
 struct logicalVolDesc {
-	tag		descTag;
-	__le32		volDescSeqNum;
-	charspec	descCharSet;
-	dstring		logicalVolIdent[128];
-	__le32		logicalBlockSize;
-	regid		domainIdent;
-	uint8_t		logicalVolContentsUse[16];
-	__le32		mapTableLength;
-	__le32		numPartitionMaps;
-	regid		impIdent;
-	uint8_t		impUse[128];
-	extent_ad	integritySeqExt;
-	uint8_t		partitionMaps[0];
+	struct tag		descTag;
+	__le32			volDescSeqNum;
+	struct charspec		descCharSet;
+	dstring			logicalVolIdent[128];
+	__le32			logicalBlockSize;
+	struct regid		domainIdent;
+	uint8_t			logicalVolContentsUse[16];
+	__le32			mapTableLength;
+	__le32			numPartitionMaps;
+	struct regid		impIdent;
+	uint8_t			impUse[128];
+	struct extent_ad	integritySeqExt;
+	uint8_t			partitionMaps[0];
 } __attribute__ ((packed));
 
 /* Generic Partition Map (ECMA 167r3 3/10.7.1) */
@@ -322,30 +322,30 @@ struct genericPartitionMap2 {
 
 /* Unallocated Space Descriptor (ECMA 167r3 3/10.8) */
 struct unallocSpaceDesc {
-	tag		descTag;
-	__le32		volDescSeqNum;
-	__le32		numAllocDescs;
-	extent_ad	allocDescs[0];
+	struct tag		descTag;
+	__le32			volDescSeqNum;
+	__le32			numAllocDescs;
+	struct extent_ad	allocDescs[0];
 } __attribute__ ((packed));
 
 /* Terminating Descriptor (ECMA 167r3 3/10.9) */
 struct terminatingDesc {
-	tag		descTag;
+	struct tag	descTag;
 	uint8_t		reserved[496];
 } __attribute__ ((packed));
 
 /* Logical Volume Integrity Descriptor (ECMA 167r3 3/10.10) */
 struct logicalVolIntegrityDesc {
-	tag		descTag;
-	timestamp	recordingDateAndTime;
-	__le32		integrityType;
-	extent_ad	nextIntegrityExt;
-	uint8_t		logicalVolContentsUse[32];
-	__le32		numOfPartitions;
-	__le32		lengthOfImpUse;
-	__le32		freeSpaceTable[0];
-	__le32		sizeTable[0];
-	uint8_t		impUse[0];
+	struct tag		descTag;
+	struct timestamp	recordingDateAndTime;
+	__le32			integrityType;
+	struct extent_ad	nextIntegrityExt;
+	uint8_t			logicalVolContentsUse[32];
+	__le32			numOfPartitions;
+	__le32			lengthOfImpUse;
+	__le32			freeSpaceTable[0];
+	__le32			sizeTable[0];
+	uint8_t			impUse[0];
 } __attribute__ ((packed));
 
 /* Integrity Type (ECMA 167r3 3/10.10.3) */
@@ -353,50 +353,50 @@ struct logicalVolIntegrityDesc {
 #define LVID_INTEGRITY_TYPE_CLOSE	0x00000001
 
 /* Recorded Address (ECMA 167r3 4/7.1) */
-typedef struct {
+struct lb_addr {
 	__le32		logicalBlockNum;
 	__le16	 	partitionReferenceNum;
-} __attribute__ ((packed)) lb_addr;
+} __attribute__ ((packed));
 
 /* ... and its in-core analog */
-typedef struct {
+struct kernel_lb_addr {
 	uint32_t		logicalBlockNum;
 	uint16_t	 	partitionReferenceNum;
-} kernel_lb_addr;
+};
 
 /* Short Allocation Descriptor (ECMA 167r3 4/14.14.1) */
-typedef struct {
+struct short_ad {
         __le32		extLength;
         __le32		extPosition;
-} __attribute__ ((packed)) short_ad;
+} __attribute__ ((packed));
 
 /* Long Allocation Descriptor (ECMA 167r3 4/14.14.2) */
-typedef struct {
+struct long_ad {
 	__le32		extLength;
-	lb_addr		extLocation;
+	struct lb_addr	extLocation;
 	uint8_t		impUse[6];
-} __attribute__ ((packed)) long_ad;
+} __attribute__ ((packed));
 
-typedef struct {
-	uint32_t	extLength;
-	kernel_lb_addr	extLocation;
-	uint8_t		impUse[6];
-} kernel_long_ad;
+struct kernel_long_ad {
+	uint32_t		extLength;
+	struct kernel_lb_addr	extLocation;
+	uint8_t			impUse[6];
+};
 
 /* Extended Allocation Descriptor (ECMA 167r3 4/14.14.3) */
-typedef struct {
+struct ext_ad {
 	__le32		extLength;
 	__le32		recordedLength;
 	__le32		informationLength;
-	lb_addr		extLocation;
-} __attribute__ ((packed)) ext_ad;
+	struct lb_addr	extLocation;
+} __attribute__ ((packed));
 
-typedef struct {
-	uint32_t	extLength;
-	uint32_t	recordedLength;
-	uint32_t	informationLength;
-	kernel_lb_addr	extLocation;
-} kernel_ext_ad;
+struct kernel_ext_ad {
+	uint32_t		extLength;
+	uint32_t		recordedLength;
+	uint32_t		informationLength;
+	struct kernel_lb_addr	extLocation;
+};
 
 /* Descriptor Tag (ECMA 167r3 4/7.2 - See 3/7.2) */
 
@@ -415,44 +415,44 @@ typedef struct {
 
 /* File Set Descriptor (ECMA 167r3 4/14.1) */
 struct fileSetDesc {
-	tag		descTag;
-	timestamp	recordingDateAndTime;
-	__le16		interchangeLvl;
-	__le16		maxInterchangeLvl;
-	__le32		charSetList;
-	__le32		maxCharSetList;
-	__le32		fileSetNum;
-	__le32		fileSetDescNum;
-	charspec	logicalVolIdentCharSet;
-	dstring		logicalVolIdent[128];
-	charspec	fileSetCharSet;
-	dstring		fileSetIdent[32];
-	dstring		copyrightFileIdent[32];
-	dstring		abstractFileIdent[32];
-	long_ad		rootDirectoryICB;
-	regid		domainIdent;
-	long_ad		nextExt;
-	long_ad		streamDirectoryICB;
-	uint8_t		reserved[32];
+	struct tag		descTag;
+	struct timestamp	recordingDateAndTime;
+	__le16			interchangeLvl;
+	__le16			maxInterchangeLvl;
+	__le32			charSetList;
+	__le32			maxCharSetList;
+	__le32			fileSetNum;
+	__le32			fileSetDescNum;
+	struct charspec		logicalVolIdentCharSet;
+	dstring			logicalVolIdent[128];
+	struct charspec		fileSetCharSet;
+	dstring			fileSetIdent[32];
+	dstring			copyrightFileIdent[32];
+	dstring			abstractFileIdent[32];
+	struct long_ad		rootDirectoryICB;
+	struct regid		domainIdent;
+	struct long_ad		nextExt;
+	struct long_ad		streamDirectoryICB;
+	uint8_t			reserved[32];
 } __attribute__ ((packed));
 
 /* Partition Header Descriptor (ECMA 167r3 4/14.3) */
 struct partitionHeaderDesc {
-	short_ad	unallocSpaceTable;
-	short_ad	unallocSpaceBitmap;
-	short_ad	partitionIntegrityTable;
-	short_ad	freedSpaceTable;
-	short_ad	freedSpaceBitmap;
+	struct short_ad	unallocSpaceTable;
+	struct short_ad	unallocSpaceBitmap;
+	struct short_ad	partitionIntegrityTable;
+	struct short_ad	freedSpaceTable;
+	struct short_ad	freedSpaceBitmap;
 	uint8_t		reserved[88];
 } __attribute__ ((packed));
 
 /* File Identifier Descriptor (ECMA 167r3 4/14.4) */
 struct fileIdentDesc {
-	tag		descTag;
+	struct tag	descTag;
 	__le16		fileVersionNum;
 	uint8_t		fileCharacteristics;
 	uint8_t		lengthFileIdent;
-	long_ad		icb;
+	struct long_ad	icb;
 	__le16		lengthOfImpUse;
 	uint8_t		impUse[0];
 	uint8_t		fileIdent[0];
@@ -468,22 +468,22 @@ struct fileIdentDesc {
 
 /* Allocation Ext Descriptor (ECMA 167r3 4/14.5) */
 struct allocExtDesc {
-	tag		descTag;
+	struct tag	descTag;
 	__le32		previousAllocExtLocation;
 	__le32		lengthAllocDescs;
 } __attribute__ ((packed));
 
 /* ICB Tag (ECMA 167r3 4/14.6) */
-typedef struct {
+struct icbtag {
 	__le32		priorRecordedNumDirectEntries;
 	__le16		strategyType;
 	__le16		strategyParameter;
 	__le16		numEntries;
 	uint8_t		reserved;
 	uint8_t		fileType;
-	lb_addr		parentICBLocation;
+	struct lb_addr	parentICBLocation;
 	__le16		flags;
-} __attribute__ ((packed)) icbtag;
+} __attribute__ ((packed));
 
 /* Strategy Type (ECMA 167r3 4/14.6.2) */
 #define ICBTAG_STRATEGY_TYPE_UNDEF	0x0000
@@ -528,41 +528,41 @@ typedef struct {
 
 /* Indirect Entry (ECMA 167r3 4/14.7) */
 struct indirectEntry {
-	tag		descTag;
-	icbtag		icbTag;
-	long_ad		indirectICB;
+	struct tag	descTag;
+	struct icbtag	icbTag;
+	struct long_ad	indirectICB;
 } __attribute__ ((packed));
 
 /* Terminal Entry (ECMA 167r3 4/14.8) */
 struct terminalEntry {
-	tag		descTag;
-	icbtag		icbTag;
+	struct tag	descTag;
+	struct icbtag	icbTag;
 } __attribute__ ((packed));
 
 /* File Entry (ECMA 167r3 4/14.9) */
 struct fileEntry {
-	tag		descTag;
-	icbtag		icbTag;
-	__le32		uid;
-	__le32		gid;
-	__le32		permissions;
-	__le16		fileLinkCount;
-	uint8_t		recordFormat;
-	uint8_t		recordDisplayAttr;
-	__le32		recordLength;
-	__le64		informationLength;
-	__le64		logicalBlocksRecorded;
-	timestamp	accessTime;
-	timestamp	modificationTime;
-	timestamp	attrTime;
-	__le32		checkpoint;
-	long_ad		extendedAttrICB;
-	regid		impIdent;
-	__le64		uniqueID;
-	__le32		lengthExtendedAttr;
-	__le32		lengthAllocDescs;
-	uint8_t		extendedAttr[0];
-	uint8_t		allocDescs[0];
+	struct tag		descTag;
+	struct icbtag		icbTag;
+	__le32			uid;
+	__le32			gid;
+	__le32			permissions;
+	__le16			fileLinkCount;
+	uint8_t			recordFormat;
+	uint8_t			recordDisplayAttr;
+	__le32			recordLength;
+	__le64			informationLength;
+	__le64			logicalBlocksRecorded;
+	struct timestamp	accessTime;
+	struct timestamp	modificationTime;
+	struct timestamp	attrTime;
+	__le32			checkpoint;
+	struct long_ad		extendedAttrICB;
+	struct regid		impIdent;
+	__le64			uniqueID;
+	__le32			lengthExtendedAttr;
+	__le32			lengthAllocDescs;
+	uint8_t			extendedAttr[0];
+	uint8_t			allocDescs[0];
 } __attribute__ ((packed));
 
 /* Permissions (ECMA 167r3 4/14.9.5) */
@@ -604,7 +604,7 @@ struct fileEntry {
 
 /* Extended Attribute Header Descriptor (ECMA 167r3 4/14.10.1) */
 struct extendedAttrHeaderDesc {
-	tag		descTag;
+	struct tag	descTag;
 	__le32		impAttrLocation;
 	__le32		appAttrLocation;
 } __attribute__ ((packed));
@@ -687,7 +687,7 @@ struct impUseExtAttr {
 	uint8_t		reserved[3];
 	__le32		attrLength;
 	__le32		impUseLength;
-	regid		impIdent;
+	struct regid	impIdent;
 	uint8_t		impUse[0];
 } __attribute__ ((packed));
 
@@ -698,7 +698,7 @@ struct appUseExtAttr {
 	uint8_t		reserved[3];
 	__le32		attrLength;
 	__le32		appUseLength;
-	regid		appIdent;
+	struct regid	appIdent;
 	uint8_t		appUse[0];
 } __attribute__ ((packed));
 
@@ -712,15 +712,15 @@ struct appUseExtAttr {
 
 /* Unallocated Space Entry (ECMA 167r3 4/14.11) */
 struct unallocSpaceEntry {
-	tag		descTag;
-	icbtag		icbTag;
+	struct tag	descTag;
+	struct icbtag	icbTag;
 	__le32		lengthAllocDescs;
 	uint8_t		allocDescs[0];
 } __attribute__ ((packed));
 
 /* Space Bitmap Descriptor (ECMA 167r3 4/14.12) */
 struct spaceBitmapDesc {
-	tag		descTag;
+	struct tag	descTag;
 	__le32		numOfBits;
 	__le32		numOfBytes;
 	uint8_t		bitmap[0];
@@ -728,13 +728,13 @@ struct spaceBitmapDesc {
 
 /* Partition Integrity Entry (ECMA 167r3 4/14.13) */
 struct partitionIntegrityEntry {
-	tag		descTag;
-	icbtag		icbTag;
-	timestamp	recordingDateAndTime;
-	uint8_t		integrityType;
-	uint8_t		reserved[175];
-	regid		impIdent;
-	uint8_t		impUse[256];
+	struct tag		descTag;
+	struct icbtag		icbTag;
+	struct timestamp	recordingDateAndTime;
+	uint8_t			integrityType;
+	uint8_t			reserved[175];
+	struct regid		impIdent;
+	uint8_t			impUse[256];
 } __attribute__ ((packed));
 
 /* Short Allocation Descriptor (ECMA 167r3 4/14.14.1) */
@@ -765,32 +765,32 @@ struct pathComponent {
 
 /* File Entry (ECMA 167r3 4/14.17) */
 struct extendedFileEntry {
-	tag		descTag;
-	icbtag		icbTag;
-	__le32		uid;
-	__le32		gid;
-	__le32		permissions;
-	__le16		fileLinkCount;
-	uint8_t		recordFormat;
-	uint8_t		recordDisplayAttr;
-	__le32		recordLength;
-	__le64		informationLength;
-	__le64		objectSize;
-	__le64		logicalBlocksRecorded;
-	timestamp	accessTime;
-	timestamp	modificationTime;
-	timestamp	createTime;
-	timestamp	attrTime;
-	__le32		checkpoint;
-	__le32		reserved;
-	long_ad		extendedAttrICB;
-	long_ad		streamDirectoryICB;
-	regid		impIdent;
-	__le64		uniqueID;
-	__le32		lengthExtendedAttr;
-	__le32		lengthAllocDescs;
-	uint8_t		extendedAttr[0];
-	uint8_t		allocDescs[0];
+	struct tag		descTag;
+	struct icbtag		icbTag;
+	__le32			uid;
+	__le32			gid;
+	__le32			permissions;
+	__le16			fileLinkCount;
+	uint8_t			recordFormat;
+	uint8_t			recordDisplayAttr;
+	__le32			recordLength;
+	__le64			informationLength;
+	__le64			objectSize;
+	__le64			logicalBlocksRecorded;
+	struct timestamp	accessTime;
+	struct timestamp	modificationTime;
+	struct timestamp	createTime;
+	struct timestamp	attrTime;
+	__le32			checkpoint;
+	__le32			reserved;
+	struct long_ad		extendedAttrICB;
+	struct long_ad		streamDirectoryICB;
+	struct regid		impIdent;
+	__le64			uniqueID;
+	__le32			lengthExtendedAttr;
+	__le32			lengthAllocDescs;
+	uint8_t			extendedAttr[0];
+	uint8_t			allocDescs[0];
 } __attribute__ ((packed));
 
 #endif /* _ECMA_167_H */
diff --git a/fs/udf/ialloc.c b/fs/udf/ialloc.c
index 47dbe5613f90..c10fa39f97e2 100644
--- a/fs/udf/ialloc.c
+++ b/fs/udf/ialloc.c
@@ -49,12 +49,11 @@ void udf_free_inode(struct inode *inode)
 			le32_add_cpu(&lvidiu->numDirs, -1);
 		else
 			le32_add_cpu(&lvidiu->numFiles, -1);
-
-		mark_buffer_dirty(sbi->s_lvid_bh);
+		udf_updated_lvid(sb);
 	}
 	mutex_unlock(&sbi->s_alloc_mutex);
 
-	udf_free_blocks(sb, NULL, UDF_I(inode)->i_location, 0, 1);
+	udf_free_blocks(sb, NULL, &UDF_I(inode)->i_location, 0, 1);
 }
 
 struct inode *udf_new_inode(struct inode *dir, int mode, int *err)
@@ -122,7 +121,7 @@ struct inode *udf_new_inode(struct inode *dir, int mode, int *err)
 		if (!(++uniqueID & 0x00000000FFFFFFFFUL))
 			uniqueID += 16;
 		lvhd->uniqueID = cpu_to_le64(uniqueID);
-		mark_buffer_dirty(sbi->s_lvid_bh);
+		udf_updated_lvid(sb);
 	}
 	mutex_unlock(&sbi->s_alloc_mutex);
 	inode->i_mode = mode;
@@ -138,7 +137,7 @@ struct inode *udf_new_inode(struct inode *dir, int mode, int *err)
 	iinfo->i_location.logicalBlockNum = block;
 	iinfo->i_location.partitionReferenceNum =
 				dinfo->i_location.partitionReferenceNum;
-	inode->i_ino = udf_get_lb_pblock(sb, iinfo->i_location, 0);
+	inode->i_ino = udf_get_lb_pblock(sb, &iinfo->i_location, 0);
 	inode->i_blocks = 0;
 	iinfo->i_lenEAttr = 0;
 	iinfo->i_lenAlloc = 0;
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 30ebde490f7f..e7533f785636 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -55,15 +55,15 @@ static int udf_alloc_i_data(struct inode *inode, size_t size);
 static struct buffer_head *inode_getblk(struct inode *, sector_t, int *,
 					sector_t *, int *);
 static int8_t udf_insert_aext(struct inode *, struct extent_position,
-			      kernel_lb_addr, uint32_t);
+			      struct kernel_lb_addr, uint32_t);
 static void udf_split_extents(struct inode *, int *, int, int,
-			      kernel_long_ad[EXTENT_MERGE_SIZE], int *);
+			      struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
 static void udf_prealloc_extents(struct inode *, int, int,
-				 kernel_long_ad[EXTENT_MERGE_SIZE], int *);
+				 struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
 static void udf_merge_extents(struct inode *,
-			      kernel_long_ad[EXTENT_MERGE_SIZE], int *);
+			      struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
 static void udf_update_extents(struct inode *,
-			       kernel_long_ad[EXTENT_MERGE_SIZE], int, int,
+			       struct kernel_long_ad[EXTENT_MERGE_SIZE], int, int,
 			       struct extent_position *);
 static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int);
 
@@ -200,7 +200,7 @@ struct buffer_head *udf_expand_dir_adinicb(struct inode *inode, int *block,
 {
 	int newblock;
 	struct buffer_head *dbh = NULL;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen;
 	uint8_t alloctype;
 	struct extent_position epos;
@@ -281,7 +281,7 @@ struct buffer_head *udf_expand_dir_adinicb(struct inode *inode, int *block,
 	epos.bh = NULL;
 	epos.block = iinfo->i_location;
 	epos.offset = udf_file_entry_alloc_offset(inode);
-	udf_add_aext(inode, &epos, eloc, elen, 0);
+	udf_add_aext(inode, &epos, &eloc, elen, 0);
 	/* UniqueID stuff */
 
 	brelse(epos.bh);
@@ -359,12 +359,12 @@ static struct buffer_head *udf_getblk(struct inode *inode, long block,
 
 /* Extend the file by 'blocks' blocks, return the number of extents added */
 int udf_extend_file(struct inode *inode, struct extent_position *last_pos,
-		    kernel_long_ad *last_ext, sector_t blocks)
+		    struct kernel_long_ad *last_ext, sector_t blocks)
 {
 	sector_t add;
 	int count = 0, fake = !(last_ext->extLength & UDF_EXTENT_LENGTH_MASK);
 	struct super_block *sb = inode->i_sb;
-	kernel_lb_addr prealloc_loc = {};
+	struct kernel_lb_addr prealloc_loc = {};
 	int prealloc_len = 0;
 	struct udf_inode_info *iinfo;
 
@@ -411,11 +411,11 @@ int udf_extend_file(struct inode *inode, struct extent_position *last_pos,
 	}
 
 	if (fake) {
-		udf_add_aext(inode, last_pos, last_ext->extLocation,
+		udf_add_aext(inode, last_pos, &last_ext->extLocation,
 			     last_ext->extLength, 1);
 		count++;
 	} else
-		udf_write_aext(inode, last_pos, last_ext->extLocation,
+		udf_write_aext(inode, last_pos, &last_ext->extLocation,
 				last_ext->extLength, 1);
 
 	/* Managed to do everything necessary? */
@@ -432,7 +432,7 @@ int udf_extend_file(struct inode *inode, struct extent_position *last_pos,
 	/* Create enough extents to cover the whole hole */
 	while (blocks > add) {
 		blocks -= add;
-		if (udf_add_aext(inode, last_pos, last_ext->extLocation,
+		if (udf_add_aext(inode, last_pos, &last_ext->extLocation,
 				 last_ext->extLength, 1) == -1)
 			return -1;
 		count++;
@@ -440,7 +440,7 @@ int udf_extend_file(struct inode *inode, struct extent_position *last_pos,
 	if (blocks) {
 		last_ext->extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
 			(blocks << sb->s_blocksize_bits);
-		if (udf_add_aext(inode, last_pos, last_ext->extLocation,
+		if (udf_add_aext(inode, last_pos, &last_ext->extLocation,
 				 last_ext->extLength, 1) == -1)
 			return -1;
 		count++;
@@ -449,7 +449,7 @@ int udf_extend_file(struct inode *inode, struct extent_position *last_pos,
 out:
 	/* Do we have some preallocated blocks saved? */
 	if (prealloc_len) {
-		if (udf_add_aext(inode, last_pos, prealloc_loc,
+		if (udf_add_aext(inode, last_pos, &prealloc_loc,
 				 prealloc_len, 1) == -1)
 			return -1;
 		last_ext->extLocation = prealloc_loc;
@@ -459,9 +459,9 @@ out:
 
 	/* last_pos should point to the last written extent... */
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		last_pos->offset -= sizeof(short_ad);
+		last_pos->offset -= sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		last_pos->offset -= sizeof(long_ad);
+		last_pos->offset -= sizeof(struct long_ad);
 	else
 		return -1;
 
@@ -473,11 +473,11 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 {
 	static sector_t last_block;
 	struct buffer_head *result = NULL;
-	kernel_long_ad laarr[EXTENT_MERGE_SIZE];
+	struct kernel_long_ad laarr[EXTENT_MERGE_SIZE];
 	struct extent_position prev_epos, cur_epos, next_epos;
 	int count = 0, startnum = 0, endnum = 0;
 	uint32_t elen = 0, tmpelen;
-	kernel_lb_addr eloc, tmpeloc;
+	struct kernel_lb_addr eloc, tmpeloc;
 	int c = 1;
 	loff_t lbcount = 0, b_off = 0;
 	uint32_t newblocknum, newblock;
@@ -550,12 +550,12 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 			elen = EXT_RECORDED_ALLOCATED |
 				((elen + inode->i_sb->s_blocksize - 1) &
 				 ~(inode->i_sb->s_blocksize - 1));
-			etype = udf_write_aext(inode, &cur_epos, eloc, elen, 1);
+			etype = udf_write_aext(inode, &cur_epos, &eloc, elen, 1);
 		}
 		brelse(prev_epos.bh);
 		brelse(cur_epos.bh);
 		brelse(next_epos.bh);
-		newblock = udf_get_lb_pblock(inode->i_sb, eloc, offset);
+		newblock = udf_get_lb_pblock(inode->i_sb, &eloc, offset);
 		*phys = newblock;
 		return NULL;
 	}
@@ -572,7 +572,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 		} else {
 			/* Create a fake extent when there's not one */
 			memset(&laarr[0].extLocation, 0x00,
-				sizeof(kernel_lb_addr));
+				sizeof(struct kernel_lb_addr));
 			laarr[0].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED;
 			/* Will udf_extend_file() create real extent from
 			   a fake one? */
@@ -602,7 +602,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 			laarr[c].extLength = EXT_NOT_RECORDED_NOT_ALLOCATED |
 				inode->i_sb->s_blocksize;
 			memset(&laarr[c].extLocation, 0x00,
-				sizeof(kernel_lb_addr));
+				sizeof(struct kernel_lb_addr));
 			count++;
 			endnum++;
 		}
@@ -699,7 +699,7 @@ static struct buffer_head *inode_getblk(struct inode *inode, sector_t block,
 
 static void udf_split_extents(struct inode *inode, int *c, int offset,
 			      int newblocknum,
-			      kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+			      struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
 			      int *endnum)
 {
 	unsigned long blocksize = inode->i_sb->s_blocksize;
@@ -726,7 +726,7 @@ static void udf_split_extents(struct inode *inode, int *c, int offset,
 		if (offset) {
 			if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) {
 				udf_free_blocks(inode->i_sb, inode,
-						laarr[curr].extLocation,
+						&laarr[curr].extLocation,
 						0, offset);
 				laarr[curr].extLength =
 					EXT_NOT_RECORDED_NOT_ALLOCATED |
@@ -763,7 +763,7 @@ static void udf_split_extents(struct inode *inode, int *c, int offset,
 }
 
 static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
-				 kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+				 struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
 				 int *endnum)
 {
 	int start, length = 0, currlength = 0, i;
@@ -817,7 +817,7 @@ static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
 					 inode->i_sb->s_blocksize_bits);
 			else {
 				memmove(&laarr[c + 2], &laarr[c + 1],
-					sizeof(long_ad) * (*endnum - (c + 1)));
+					sizeof(struct long_ad) * (*endnum - (c + 1)));
 				(*endnum)++;
 				laarr[c + 1].extLocation.logicalBlockNum = next;
 				laarr[c + 1].extLocation.partitionReferenceNum =
@@ -846,7 +846,7 @@ static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
 					if (*endnum > (i + 1))
 						memmove(&laarr[i],
 							&laarr[i + 1],
-							sizeof(long_ad) *
+							sizeof(struct long_ad) *
 							(*endnum - (i + 1)));
 					i--;
 					(*endnum)--;
@@ -859,7 +859,7 @@ static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
 }
 
 static void udf_merge_extents(struct inode *inode,
-			      kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+			      struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
 			      int *endnum)
 {
 	int i;
@@ -867,8 +867,8 @@ static void udf_merge_extents(struct inode *inode,
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
 
 	for (i = 0; i < (*endnum - 1); i++) {
-		kernel_long_ad *li /*l[i]*/ = &laarr[i];
-		kernel_long_ad *lip1 /*l[i plus 1]*/ = &laarr[i + 1];
+		struct kernel_long_ad *li /*l[i]*/ = &laarr[i];
+		struct kernel_long_ad *lip1 /*l[i plus 1]*/ = &laarr[i + 1];
 
 		if (((li->extLength >> 30) == (lip1->extLength >> 30)) &&
 			(((li->extLength >> 30) ==
@@ -902,7 +902,7 @@ static void udf_merge_extents(struct inode *inode,
 					 blocksize - 1) & ~(blocksize - 1));
 				if (*endnum > (i + 2))
 					memmove(&laarr[i + 1], &laarr[i + 2],
-						sizeof(long_ad) *
+						sizeof(struct long_ad) *
 						(*endnum - (i + 2)));
 				i--;
 				(*endnum)--;
@@ -911,7 +911,7 @@ static void udf_merge_extents(struct inode *inode,
 				(EXT_NOT_RECORDED_ALLOCATED >> 30)) &&
 			   ((lip1->extLength >> 30) ==
 				(EXT_NOT_RECORDED_NOT_ALLOCATED >> 30))) {
-			udf_free_blocks(inode->i_sb, inode, li->extLocation, 0,
+			udf_free_blocks(inode->i_sb, inode, &li->extLocation, 0,
 					((li->extLength &
 					  UDF_EXTENT_LENGTH_MASK) +
 					 blocksize - 1) >> blocksize_bits);
@@ -937,7 +937,7 @@ static void udf_merge_extents(struct inode *inode,
 					  blocksize - 1) & ~(blocksize - 1));
 				if (*endnum > (i + 2))
 					memmove(&laarr[i + 1], &laarr[i + 2],
-						sizeof(long_ad) *
+						sizeof(struct long_ad) *
 						(*endnum - (i + 2)));
 				i--;
 				(*endnum)--;
@@ -945,7 +945,7 @@ static void udf_merge_extents(struct inode *inode,
 		} else if ((li->extLength >> 30) ==
 					(EXT_NOT_RECORDED_ALLOCATED >> 30)) {
 			udf_free_blocks(inode->i_sb, inode,
-					li->extLocation, 0,
+					&li->extLocation, 0,
 					((li->extLength &
 						UDF_EXTENT_LENGTH_MASK) +
 					 blocksize - 1) >> blocksize_bits);
@@ -959,12 +959,12 @@ static void udf_merge_extents(struct inode *inode,
 }
 
 static void udf_update_extents(struct inode *inode,
-			       kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+			       struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
 			       int startnum, int endnum,
 			       struct extent_position *epos)
 {
 	int start = 0, i;
-	kernel_lb_addr tmploc;
+	struct kernel_lb_addr tmploc;
 	uint32_t tmplen;
 
 	if (startnum > endnum) {
@@ -983,7 +983,7 @@ static void udf_update_extents(struct inode *inode,
 
 	for (i = start; i < endnum; i++) {
 		udf_next_aext(inode, epos, &tmploc, &tmplen, 0);
-		udf_write_aext(inode, epos, laarr[i].extLocation,
+		udf_write_aext(inode, epos, &laarr[i].extLocation,
 			       laarr[i].extLength, 1);
 	}
 }
@@ -1076,7 +1076,7 @@ static void __udf_read_inode(struct inode *inode)
 	 *      i_nlink = 1
 	 *      i_op = NULL;
 	 */
-	bh = udf_read_ptagged(inode->i_sb, iinfo->i_location, 0, &ident);
+	bh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 0, &ident);
 	if (!bh) {
 		printk(KERN_ERR "udf: udf_read_inode(ino %ld) failed !bh\n",
 		       inode->i_ino);
@@ -1098,24 +1098,24 @@ static void __udf_read_inode(struct inode *inode)
 	if (fe->icbTag.strategyType == cpu_to_le16(4096)) {
 		struct buffer_head *ibh;
 
-		ibh = udf_read_ptagged(inode->i_sb, iinfo->i_location, 1,
+		ibh = udf_read_ptagged(inode->i_sb, &iinfo->i_location, 1,
 					&ident);
 		if (ident == TAG_IDENT_IE && ibh) {
 			struct buffer_head *nbh = NULL;
-			kernel_lb_addr loc;
+			struct kernel_lb_addr loc;
 			struct indirectEntry *ie;
 
 			ie = (struct indirectEntry *)ibh->b_data;
 			loc = lelb_to_cpu(ie->indirectICB.extLocation);
 
 			if (ie->indirectICB.extLength &&
-				(nbh = udf_read_ptagged(inode->i_sb, loc, 0,
+				(nbh = udf_read_ptagged(inode->i_sb, &loc, 0,
 							&ident))) {
 				if (ident == TAG_IDENT_FE ||
 					ident == TAG_IDENT_EFE) {
 					memcpy(&iinfo->i_location,
 						&loc,
-						sizeof(kernel_lb_addr));
+						sizeof(struct kernel_lb_addr));
 					brelse(bh);
 					brelse(ibh);
 					brelse(nbh);
@@ -1222,8 +1222,15 @@ static void udf_fill_inode(struct inode *inode, struct buffer_head *bh)
 	inode->i_size = le64_to_cpu(fe->informationLength);
 	iinfo->i_lenExtents = inode->i_size;
 
-	inode->i_mode = udf_convert_permissions(fe);
-	inode->i_mode &= ~UDF_SB(inode->i_sb)->s_umask;
+	if (fe->icbTag.fileType != ICBTAG_FILE_TYPE_DIRECTORY &&
+			sbi->s_fmode != UDF_INVALID_MODE)
+		inode->i_mode = sbi->s_fmode;
+	else if (fe->icbTag.fileType == ICBTAG_FILE_TYPE_DIRECTORY &&
+			sbi->s_dmode != UDF_INVALID_MODE)
+		inode->i_mode = sbi->s_dmode;
+	else
+		inode->i_mode = udf_convert_permissions(fe);
+	inode->i_mode &= ~sbi->s_umask;
 
 	if (iinfo->i_efe == 0) {
 		inode->i_blocks = le64_to_cpu(fe->logicalBlocksRecorded) <<
@@ -1396,7 +1403,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 
 	bh = udf_tread(inode->i_sb,
 			udf_get_lb_pblock(inode->i_sb,
-					  iinfo->i_location, 0));
+					  &iinfo->i_location, 0));
 	if (!bh) {
 		udf_debug("bread failure\n");
 		return -EIO;
@@ -1416,13 +1423,13 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		       iinfo->i_ext.i_data, inode->i_sb->s_blocksize -
 					sizeof(struct unallocSpaceEntry));
 		crclen = sizeof(struct unallocSpaceEntry) +
-				iinfo->i_lenAlloc - sizeof(tag);
+				iinfo->i_lenAlloc - sizeof(struct tag);
 		use->descTag.tagLocation = cpu_to_le32(
 						iinfo->i_location.
 							logicalBlockNum);
 		use->descTag.descCRCLength = cpu_to_le16(crclen);
 		use->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)use +
-							   sizeof(tag),
+							   sizeof(struct tag),
 							   crclen));
 		use->descTag.tagChecksum = udf_tag_checksum(&use->descTag);
 
@@ -1459,23 +1466,23 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 	fe->informationLength = cpu_to_le64(inode->i_size);
 
 	if (S_ISCHR(inode->i_mode) || S_ISBLK(inode->i_mode)) {
-		regid *eid;
+		struct regid *eid;
 		struct deviceSpec *dsea =
 			(struct deviceSpec *)udf_get_extendedattr(inode, 12, 1);
 		if (!dsea) {
 			dsea = (struct deviceSpec *)
 				udf_add_extendedattr(inode,
 						     sizeof(struct deviceSpec) +
-						     sizeof(regid), 12, 0x3);
+						     sizeof(struct regid), 12, 0x3);
 			dsea->attrType = cpu_to_le32(12);
 			dsea->attrSubtype = 1;
 			dsea->attrLength = cpu_to_le32(
 						sizeof(struct deviceSpec) +
-						sizeof(regid));
-			dsea->impUseLength = cpu_to_le32(sizeof(regid));
+						sizeof(struct regid));
+			dsea->impUseLength = cpu_to_le32(sizeof(struct regid));
 		}
-		eid = (regid *)dsea->impUse;
-		memset(eid, 0, sizeof(regid));
+		eid = (struct regid *)dsea->impUse;
+		memset(eid, 0, sizeof(struct regid));
 		strcpy(eid->ident, UDF_ID_DEVELOPER);
 		eid->identSuffix[0] = UDF_OS_CLASS_UNIX;
 		eid->identSuffix[1] = UDF_OS_ID_LINUX;
@@ -1494,7 +1501,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		udf_time_to_disk_stamp(&fe->accessTime, inode->i_atime);
 		udf_time_to_disk_stamp(&fe->modificationTime, inode->i_mtime);
 		udf_time_to_disk_stamp(&fe->attrTime, inode->i_ctime);
-		memset(&(fe->impIdent), 0, sizeof(regid));
+		memset(&(fe->impIdent), 0, sizeof(struct regid));
 		strcpy(fe->impIdent.ident, UDF_ID_DEVELOPER);
 		fe->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 		fe->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
@@ -1533,7 +1540,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		udf_time_to_disk_stamp(&efe->createTime, iinfo->i_crtime);
 		udf_time_to_disk_stamp(&efe->attrTime, inode->i_ctime);
 
-		memset(&(efe->impIdent), 0, sizeof(regid));
+		memset(&(efe->impIdent), 0, sizeof(struct regid));
 		strcpy(efe->impIdent.ident, UDF_ID_DEVELOPER);
 		efe->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 		efe->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
@@ -1584,9 +1591,9 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 	fe->descTag.tagLocation = cpu_to_le32(
 					iinfo->i_location.logicalBlockNum);
 	crclen += iinfo->i_lenEAttr + iinfo->i_lenAlloc -
-								sizeof(tag);
+								sizeof(struct tag);
 	fe->descTag.descCRCLength = cpu_to_le16(crclen);
-	fe->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)fe + sizeof(tag),
+	fe->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)fe + sizeof(struct tag),
 						  crclen));
 	fe->descTag.tagChecksum = udf_tag_checksum(&fe->descTag);
 
@@ -1606,7 +1613,7 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 	return err;
 }
 
-struct inode *udf_iget(struct super_block *sb, kernel_lb_addr ino)
+struct inode *udf_iget(struct super_block *sb, struct kernel_lb_addr *ino)
 {
 	unsigned long block = udf_get_lb_pblock(sb, ino, 0);
 	struct inode *inode = iget_locked(sb, block);
@@ -1615,7 +1622,7 @@ struct inode *udf_iget(struct super_block *sb, kernel_lb_addr ino)
 		return NULL;
 
 	if (inode->i_state & I_NEW) {
-		memcpy(&UDF_I(inode)->i_location, &ino, sizeof(kernel_lb_addr));
+		memcpy(&UDF_I(inode)->i_location, ino, sizeof(struct kernel_lb_addr));
 		__udf_read_inode(inode);
 		unlock_new_inode(inode);
 	}
@@ -1623,10 +1630,10 @@ struct inode *udf_iget(struct super_block *sb, kernel_lb_addr ino)
 	if (is_bad_inode(inode))
 		goto out_iput;
 
-	if (ino.logicalBlockNum >= UDF_SB(sb)->
-			s_partmaps[ino.partitionReferenceNum].s_partition_len) {
+	if (ino->logicalBlockNum >= UDF_SB(sb)->
+			s_partmaps[ino->partitionReferenceNum].s_partition_len) {
 		udf_debug("block=%d, partition=%d out of range\n",
-			  ino.logicalBlockNum, ino.partitionReferenceNum);
+			  ino->logicalBlockNum, ino->partitionReferenceNum);
 		make_bad_inode(inode);
 		goto out_iput;
 	}
@@ -1639,11 +1646,11 @@ struct inode *udf_iget(struct super_block *sb, kernel_lb_addr ino)
 }
 
 int8_t udf_add_aext(struct inode *inode, struct extent_position *epos,
-		    kernel_lb_addr eloc, uint32_t elen, int inc)
+		    struct kernel_lb_addr *eloc, uint32_t elen, int inc)
 {
 	int adsize;
-	short_ad *sad = NULL;
-	long_ad *lad = NULL;
+	struct short_ad *sad = NULL;
+	struct long_ad *lad = NULL;
 	struct allocExtDesc *aed;
 	int8_t etype;
 	uint8_t *ptr;
@@ -1657,9 +1664,9 @@ int8_t udf_add_aext(struct inode *inode, struct extent_position *epos,
 		ptr = epos->bh->b_data + epos->offset;
 
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		adsize = sizeof(short_ad);
+		adsize = sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 	else
 		return -1;
 
@@ -1667,7 +1674,7 @@ int8_t udf_add_aext(struct inode *inode, struct extent_position *epos,
 		char *sptr, *dptr;
 		struct buffer_head *nbh;
 		int err, loffset;
-		kernel_lb_addr obloc = epos->block;
+		struct kernel_lb_addr obloc = epos->block;
 
 		epos->block.logicalBlockNum = udf_new_block(inode->i_sb, NULL,
 						obloc.partitionReferenceNum,
@@ -1675,7 +1682,7 @@ int8_t udf_add_aext(struct inode *inode, struct extent_position *epos,
 		if (!epos->block.logicalBlockNum)
 			return -1;
 		nbh = udf_tgetblk(inode->i_sb, udf_get_lb_pblock(inode->i_sb,
-								 epos->block,
+								 &epos->block,
 								 0));
 		if (!nbh)
 			return -1;
@@ -1712,20 +1719,20 @@ int8_t udf_add_aext(struct inode *inode, struct extent_position *epos,
 		}
 		if (UDF_SB(inode->i_sb)->s_udfrev >= 0x0200)
 			udf_new_tag(nbh->b_data, TAG_IDENT_AED, 3, 1,
-				    epos->block.logicalBlockNum, sizeof(tag));
+				    epos->block.logicalBlockNum, sizeof(struct tag));
 		else
 			udf_new_tag(nbh->b_data, TAG_IDENT_AED, 2, 1,
-				    epos->block.logicalBlockNum, sizeof(tag));
+				    epos->block.logicalBlockNum, sizeof(struct tag));
 		switch (iinfo->i_alloc_type) {
 		case ICBTAG_FLAG_AD_SHORT:
-			sad = (short_ad *)sptr;
+			sad = (struct short_ad *)sptr;
 			sad->extLength = cpu_to_le32(EXT_NEXT_EXTENT_ALLOCDECS |
 						     inode->i_sb->s_blocksize);
 			sad->extPosition =
 				cpu_to_le32(epos->block.logicalBlockNum);
 			break;
 		case ICBTAG_FLAG_AD_LONG:
-			lad = (long_ad *)sptr;
+			lad = (struct long_ad *)sptr;
 			lad->extLength = cpu_to_le32(EXT_NEXT_EXTENT_ALLOCDECS |
 						     inode->i_sb->s_blocksize);
 			lad->extLocation = cpu_to_lelb(epos->block);
@@ -1769,12 +1776,12 @@ int8_t udf_add_aext(struct inode *inode, struct extent_position *epos,
 }
 
 int8_t udf_write_aext(struct inode *inode, struct extent_position *epos,
-		      kernel_lb_addr eloc, uint32_t elen, int inc)
+		      struct kernel_lb_addr *eloc, uint32_t elen, int inc)
 {
 	int adsize;
 	uint8_t *ptr;
-	short_ad *sad;
-	long_ad *lad;
+	struct short_ad *sad;
+	struct long_ad *lad;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
 	if (!epos->bh)
@@ -1786,17 +1793,17 @@ int8_t udf_write_aext(struct inode *inode, struct extent_position *epos,
 
 	switch (iinfo->i_alloc_type) {
 	case ICBTAG_FLAG_AD_SHORT:
-		sad = (short_ad *)ptr;
+		sad = (struct short_ad *)ptr;
 		sad->extLength = cpu_to_le32(elen);
-		sad->extPosition = cpu_to_le32(eloc.logicalBlockNum);
-		adsize = sizeof(short_ad);
+		sad->extPosition = cpu_to_le32(eloc->logicalBlockNum);
+		adsize = sizeof(struct short_ad);
 		break;
 	case ICBTAG_FLAG_AD_LONG:
-		lad = (long_ad *)ptr;
+		lad = (struct long_ad *)ptr;
 		lad->extLength = cpu_to_le32(elen);
-		lad->extLocation = cpu_to_lelb(eloc);
+		lad->extLocation = cpu_to_lelb(*eloc);
 		memset(lad->impUse, 0x00, sizeof(lad->impUse));
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 		break;
 	default:
 		return -1;
@@ -1823,7 +1830,7 @@ int8_t udf_write_aext(struct inode *inode, struct extent_position *epos,
 }
 
 int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
-		     kernel_lb_addr *eloc, uint32_t *elen, int inc)
+		     struct kernel_lb_addr *eloc, uint32_t *elen, int inc)
 {
 	int8_t etype;
 
@@ -1833,7 +1840,7 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
 		epos->block = *eloc;
 		epos->offset = sizeof(struct allocExtDesc);
 		brelse(epos->bh);
-		block = udf_get_lb_pblock(inode->i_sb, epos->block, 0);
+		block = udf_get_lb_pblock(inode->i_sb, &epos->block, 0);
 		epos->bh = udf_tread(inode->i_sb, block);
 		if (!epos->bh) {
 			udf_debug("reading block %d failed!\n", block);
@@ -1845,13 +1852,13 @@ int8_t udf_next_aext(struct inode *inode, struct extent_position *epos,
 }
 
 int8_t udf_current_aext(struct inode *inode, struct extent_position *epos,
-			kernel_lb_addr *eloc, uint32_t *elen, int inc)
+			struct kernel_lb_addr *eloc, uint32_t *elen, int inc)
 {
 	int alen;
 	int8_t etype;
 	uint8_t *ptr;
-	short_ad *sad;
-	long_ad *lad;
+	struct short_ad *sad;
+	struct long_ad *lad;
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
 	if (!epos->bh) {
@@ -1900,9 +1907,9 @@ int8_t udf_current_aext(struct inode *inode, struct extent_position *epos,
 }
 
 static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos,
-			      kernel_lb_addr neloc, uint32_t nelen)
+			      struct kernel_lb_addr neloc, uint32_t nelen)
 {
-	kernel_lb_addr oeloc;
+	struct kernel_lb_addr oeloc;
 	uint32_t oelen;
 	int8_t etype;
 
@@ -1910,18 +1917,18 @@ static int8_t udf_insert_aext(struct inode *inode, struct extent_position epos,
 		get_bh(epos.bh);
 
 	while ((etype = udf_next_aext(inode, &epos, &oeloc, &oelen, 0)) != -1) {
-		udf_write_aext(inode, &epos, neloc, nelen, 1);
+		udf_write_aext(inode, &epos, &neloc, nelen, 1);
 		neloc = oeloc;
 		nelen = (etype << 30) | oelen;
 	}
-	udf_add_aext(inode, &epos, neloc, nelen, 1);
+	udf_add_aext(inode, &epos, &neloc, nelen, 1);
 	brelse(epos.bh);
 
 	return (nelen >> 30);
 }
 
 int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
-		       kernel_lb_addr eloc, uint32_t elen)
+		       struct kernel_lb_addr eloc, uint32_t elen)
 {
 	struct extent_position oepos;
 	int adsize;
@@ -1936,9 +1943,9 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
 
 	iinfo = UDF_I(inode);
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		adsize = sizeof(short_ad);
+		adsize = sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 	else
 		adsize = 0;
 
@@ -1947,7 +1954,7 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
 		return -1;
 
 	while ((etype = udf_next_aext(inode, &epos, &eloc, &elen, 1)) != -1) {
-		udf_write_aext(inode, &oepos, eloc, (etype << 30) | elen, 1);
+		udf_write_aext(inode, &oepos, &eloc, (etype << 30) | elen, 1);
 		if (oepos.bh != epos.bh) {
 			oepos.block = epos.block;
 			brelse(oepos.bh);
@@ -1956,13 +1963,13 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
 			oepos.offset = epos.offset - adsize;
 		}
 	}
-	memset(&eloc, 0x00, sizeof(kernel_lb_addr));
+	memset(&eloc, 0x00, sizeof(struct kernel_lb_addr));
 	elen = 0;
 
 	if (epos.bh != oepos.bh) {
-		udf_free_blocks(inode->i_sb, inode, epos.block, 0, 1);
-		udf_write_aext(inode, &oepos, eloc, elen, 1);
-		udf_write_aext(inode, &oepos, eloc, elen, 1);
+		udf_free_blocks(inode->i_sb, inode, &epos.block, 0, 1);
+		udf_write_aext(inode, &oepos, &eloc, elen, 1);
+		udf_write_aext(inode, &oepos, &eloc, elen, 1);
 		if (!oepos.bh) {
 			iinfo->i_lenAlloc -= (adsize * 2);
 			mark_inode_dirty(inode);
@@ -1979,7 +1986,7 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
 			mark_buffer_dirty_inode(oepos.bh, inode);
 		}
 	} else {
-		udf_write_aext(inode, &oepos, eloc, elen, 1);
+		udf_write_aext(inode, &oepos, &eloc, elen, 1);
 		if (!oepos.bh) {
 			iinfo->i_lenAlloc -= adsize;
 			mark_inode_dirty(inode);
@@ -2004,7 +2011,7 @@ int8_t udf_delete_aext(struct inode *inode, struct extent_position epos,
 }
 
 int8_t inode_bmap(struct inode *inode, sector_t block,
-		  struct extent_position *pos, kernel_lb_addr *eloc,
+		  struct extent_position *pos, struct kernel_lb_addr *eloc,
 		  uint32_t *elen, sector_t *offset)
 {
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
@@ -2036,7 +2043,7 @@ int8_t inode_bmap(struct inode *inode, sector_t block,
 
 long udf_block_map(struct inode *inode, sector_t block)
 {
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen;
 	sector_t offset;
 	struct extent_position epos = {};
@@ -2046,7 +2053,7 @@ long udf_block_map(struct inode *inode, sector_t block)
 
 	if (inode_bmap(inode, block, &epos, &eloc, &elen, &offset) ==
 						(EXT_RECORDED_ALLOCATED >> 30))
-		ret = udf_get_lb_pblock(inode->i_sb, eloc, offset);
+		ret = udf_get_lb_pblock(inode->i_sb, &eloc, offset);
 	else
 		ret = 0;
 
diff --git a/fs/udf/misc.c b/fs/udf/misc.c
index 84bf0fd4a4f1..9215700c00a4 100644
--- a/fs/udf/misc.c
+++ b/fs/udf/misc.c
@@ -134,10 +134,10 @@ struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size,
 			}
 		}
 		/* rewrite CRC + checksum of eahd */
-		crclen = sizeof(struct extendedAttrHeaderDesc) - sizeof(tag);
+		crclen = sizeof(struct extendedAttrHeaderDesc) - sizeof(struct tag);
 		eahd->descTag.descCRCLength = cpu_to_le16(crclen);
 		eahd->descTag.descCRC = cpu_to_le16(crc_itu_t(0, (char *)eahd +
-						sizeof(tag), crclen));
+						sizeof(struct tag), crclen));
 		eahd->descTag.tagChecksum = udf_tag_checksum(&eahd->descTag);
 		iinfo->i_lenEAttr += size;
 		return (struct genericFormat *)&ea[offset];
@@ -202,7 +202,7 @@ struct genericFormat *udf_get_extendedattr(struct inode *inode, uint32_t type,
 struct buffer_head *udf_read_tagged(struct super_block *sb, uint32_t block,
 				    uint32_t location, uint16_t *ident)
 {
-	tag *tag_p;
+	struct tag *tag_p;
 	struct buffer_head *bh = NULL;
 
 	/* Read the block */
@@ -216,7 +216,7 @@ struct buffer_head *udf_read_tagged(struct super_block *sb, uint32_t block,
 		return NULL;
 	}
 
-	tag_p = (tag *)(bh->b_data);
+	tag_p = (struct tag *)(bh->b_data);
 
 	*ident = le16_to_cpu(tag_p->tagIdent);
 
@@ -241,9 +241,9 @@ struct buffer_head *udf_read_tagged(struct super_block *sb, uint32_t block,
 	}
 
 	/* Verify the descriptor CRC */
-	if (le16_to_cpu(tag_p->descCRCLength) + sizeof(tag) > sb->s_blocksize ||
+	if (le16_to_cpu(tag_p->descCRCLength) + sizeof(struct tag) > sb->s_blocksize ||
 	    le16_to_cpu(tag_p->descCRC) == crc_itu_t(0,
-					bh->b_data + sizeof(tag),
+					bh->b_data + sizeof(struct tag),
 					le16_to_cpu(tag_p->descCRCLength)))
 		return bh;
 
@@ -255,27 +255,28 @@ error_out:
 	return NULL;
 }
 
-struct buffer_head *udf_read_ptagged(struct super_block *sb, kernel_lb_addr loc,
+struct buffer_head *udf_read_ptagged(struct super_block *sb,
+				     struct kernel_lb_addr *loc,
 				     uint32_t offset, uint16_t *ident)
 {
 	return udf_read_tagged(sb, udf_get_lb_pblock(sb, loc, offset),
-			       loc.logicalBlockNum + offset, ident);
+			       loc->logicalBlockNum + offset, ident);
 }
 
 void udf_update_tag(char *data, int length)
 {
-	tag *tptr = (tag *)data;
-	length -= sizeof(tag);
+	struct tag *tptr = (struct tag *)data;
+	length -= sizeof(struct tag);
 
 	tptr->descCRCLength = cpu_to_le16(length);
-	tptr->descCRC = cpu_to_le16(crc_itu_t(0, data + sizeof(tag), length));
+	tptr->descCRC = cpu_to_le16(crc_itu_t(0, data + sizeof(struct tag), length));
 	tptr->tagChecksum = udf_tag_checksum(tptr);
 }
 
 void udf_new_tag(char *data, uint16_t ident, uint16_t version, uint16_t snum,
 		 uint32_t loc, int length)
 {
-	tag *tptr = (tag *)data;
+	struct tag *tptr = (struct tag *)data;
 	tptr->tagIdent = cpu_to_le16(ident);
 	tptr->descVersion = cpu_to_le16(version);
 	tptr->tagSerialNum = cpu_to_le16(snum);
@@ -283,12 +284,12 @@ void udf_new_tag(char *data, uint16_t ident, uint16_t version, uint16_t snum,
 	udf_update_tag(data, length);
 }
 
-u8 udf_tag_checksum(const tag *t)
+u8 udf_tag_checksum(const struct tag *t)
 {
 	u8 *data = (u8 *)t;
 	u8 checksum = 0;
 	int i;
-	for (i = 0; i < sizeof(tag); ++i)
+	for (i = 0; i < sizeof(struct tag); ++i)
 		if (i != 4) /* position of checksum */
 			checksum += data[i];
 	return checksum;
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index f84bfaa8d941..6a29fa34c478 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -47,7 +47,7 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi,
 		 struct fileIdentDesc *sfi, struct udf_fileident_bh *fibh,
 		 uint8_t *impuse, uint8_t *fileident)
 {
-	uint16_t crclen = fibh->eoffset - fibh->soffset - sizeof(tag);
+	uint16_t crclen = fibh->eoffset - fibh->soffset - sizeof(struct tag);
 	uint16_t crc;
 	int offset;
 	uint16_t liu = le16_to_cpu(cfi->lengthOfImpUse);
@@ -99,18 +99,18 @@ int udf_write_fi(struct inode *inode, struct fileIdentDesc *cfi,
 		memset(fibh->ebh->b_data, 0x00, padlen + offset);
 	}
 
-	crc = crc_itu_t(0, (uint8_t *)cfi + sizeof(tag),
-		      sizeof(struct fileIdentDesc) - sizeof(tag));
+	crc = crc_itu_t(0, (uint8_t *)cfi + sizeof(struct tag),
+		      sizeof(struct fileIdentDesc) - sizeof(struct tag));
 
 	if (fibh->sbh == fibh->ebh) {
 		crc = crc_itu_t(crc, (uint8_t *)sfi->impUse,
-			      crclen + sizeof(tag) -
+			      crclen + sizeof(struct tag) -
 			      sizeof(struct fileIdentDesc));
 	} else if (sizeof(struct fileIdentDesc) >= -fibh->soffset) {
 		crc = crc_itu_t(crc, fibh->ebh->b_data +
 					sizeof(struct fileIdentDesc) +
 					fibh->soffset,
-			      crclen + sizeof(tag) -
+			      crclen + sizeof(struct tag) -
 					sizeof(struct fileIdentDesc));
 	} else {
 		crc = crc_itu_t(crc, (uint8_t *)sfi->impUse,
@@ -154,7 +154,7 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir,
 	uint8_t lfi;
 	uint16_t liu;
 	loff_t size;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen;
 	sector_t offset;
 	struct extent_position epos = {};
@@ -171,12 +171,12 @@ static struct fileIdentDesc *udf_find_entry(struct inode *dir,
 		if (inode_bmap(dir, f_pos >> dir->i_sb->s_blocksize_bits, &epos,
 		    &eloc, &elen, &offset) != (EXT_RECORDED_ALLOCATED >> 30))
 			goto out_err;
-		block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
+		block = udf_get_lb_pblock(dir->i_sb, &eloc, offset);
 		if ((++offset << dir->i_sb->s_blocksize_bits) < elen) {
 			if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-				epos.offset -= sizeof(short_ad);
+				epos.offset -= sizeof(struct short_ad);
 			else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-				epos.offset -= sizeof(long_ad);
+				epos.offset -= sizeof(struct long_ad);
 		} else
 			offset = 0;
 
@@ -268,7 +268,7 @@ static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry,
 #ifdef UDF_RECOVERY
 	/* temporary shorthand for specifying files by inode number */
 	if (!strncmp(dentry->d_name.name, ".B=", 3)) {
-		kernel_lb_addr lb = {
+		struct kernel_lb_addr lb = {
 			.logicalBlockNum = 0,
 			.partitionReferenceNum =
 				simple_strtoul(dentry->d_name.name + 3,
@@ -283,11 +283,14 @@ static struct dentry *udf_lookup(struct inode *dir, struct dentry *dentry,
 #endif /* UDF_RECOVERY */
 
 	if (udf_find_entry(dir, &dentry->d_name, &fibh, &cfi)) {
+		struct kernel_lb_addr loc;
+
 		if (fibh.sbh != fibh.ebh)
 			brelse(fibh.ebh);
 		brelse(fibh.sbh);
 
-		inode = udf_iget(dir->i_sb, lelb_to_cpu(cfi.icb.extLocation));
+		loc = lelb_to_cpu(cfi.icb.extLocation);
+		inode = udf_iget(dir->i_sb, &loc);
 		if (!inode) {
 			unlock_kernel();
 			return ERR_PTR(-EACCES);
@@ -313,7 +316,7 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir,
 	uint8_t lfi;
 	uint16_t liu;
 	int block;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen = 0;
 	sector_t offset;
 	struct extent_position epos = {};
@@ -351,16 +354,16 @@ static struct fileIdentDesc *udf_add_entry(struct inode *dir,
 		if (inode_bmap(dir, f_pos >> dir->i_sb->s_blocksize_bits, &epos,
 		    &eloc, &elen, &offset) != (EXT_RECORDED_ALLOCATED >> 30)) {
 			block = udf_get_lb_pblock(dir->i_sb,
-					dinfo->i_location, 0);
+					&dinfo->i_location, 0);
 			fibh->soffset = fibh->eoffset = sb->s_blocksize;
 			goto add;
 		}
-		block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
+		block = udf_get_lb_pblock(dir->i_sb, &eloc, offset);
 		if ((++offset << dir->i_sb->s_blocksize_bits) < elen) {
 			if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-				epos.offset -= sizeof(short_ad);
+				epos.offset -= sizeof(struct short_ad);
 			else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-				epos.offset -= sizeof(long_ad);
+				epos.offset -= sizeof(struct long_ad);
 		} else
 			offset = 0;
 
@@ -409,10 +412,10 @@ add:
 	if (dinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB && elen) {
 		elen = (elen + sb->s_blocksize - 1) & ~(sb->s_blocksize - 1);
 		if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-			epos.offset -= sizeof(short_ad);
+			epos.offset -= sizeof(struct short_ad);
 		else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-			epos.offset -= sizeof(long_ad);
-		udf_write_aext(dir, &epos, eloc, elen, 1);
+			epos.offset -= sizeof(struct long_ad);
+		udf_write_aext(dir, &epos, &eloc, elen, 1);
 	}
 	f_pos += nfidlen;
 
@@ -494,10 +497,10 @@ add:
 	memset(cfi, 0, sizeof(struct fileIdentDesc));
 	if (UDF_SB(sb)->s_udfrev >= 0x0200)
 		udf_new_tag((char *)cfi, TAG_IDENT_FID, 3, 1, block,
-			    sizeof(tag));
+			    sizeof(struct tag));
 	else
 		udf_new_tag((char *)cfi, TAG_IDENT_FID, 2, 1, block,
-			    sizeof(tag));
+			    sizeof(struct tag));
 	cfi->fileVersionNum = cpu_to_le16(1);
 	cfi->lengthFileIdent = namelen;
 	cfi->lengthOfImpUse = cpu_to_le16(0);
@@ -530,7 +533,7 @@ static int udf_delete_entry(struct inode *inode, struct fileIdentDesc *fi,
 	cfi->fileCharacteristics |= FID_FILE_CHAR_DELETED;
 
 	if (UDF_QUERY_FLAG(inode->i_sb, UDF_FLAG_STRICT))
-		memset(&(cfi->icb), 0x00, sizeof(long_ad));
+		memset(&(cfi->icb), 0x00, sizeof(struct long_ad));
 
 	return udf_write_fi(inode, cfi, fi, fibh, NULL, NULL);
 }
@@ -710,7 +713,7 @@ static int empty_dir(struct inode *dir)
 	loff_t f_pos;
 	loff_t size = udf_ext0_offset(dir) + dir->i_size;
 	int block;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen;
 	sector_t offset;
 	struct extent_position epos = {};
@@ -724,12 +727,12 @@ static int empty_dir(struct inode *dir)
 	else if (inode_bmap(dir, f_pos >> dir->i_sb->s_blocksize_bits,
 			      &epos, &eloc, &elen, &offset) ==
 					(EXT_RECORDED_ALLOCATED >> 30)) {
-		block = udf_get_lb_pblock(dir->i_sb, eloc, offset);
+		block = udf_get_lb_pblock(dir->i_sb, &eloc, offset);
 		if ((++offset << dir->i_sb->s_blocksize_bits) < elen) {
 			if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-				epos.offset -= sizeof(short_ad);
+				epos.offset -= sizeof(struct short_ad);
 			else if (dinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-				epos.offset -= sizeof(long_ad);
+				epos.offset -= sizeof(struct long_ad);
 		} else
 			offset = 0;
 
@@ -778,7 +781,7 @@ static int udf_rmdir(struct inode *dir, struct dentry *dentry)
 	struct inode *inode = dentry->d_inode;
 	struct udf_fileident_bh fibh;
 	struct fileIdentDesc *fi, cfi;
-	kernel_lb_addr tloc;
+	struct kernel_lb_addr tloc;
 
 	retval = -ENOENT;
 	lock_kernel();
@@ -788,7 +791,7 @@ static int udf_rmdir(struct inode *dir, struct dentry *dentry)
 
 	retval = -EIO;
 	tloc = lelb_to_cpu(cfi.icb.extLocation);
-	if (udf_get_lb_pblock(dir->i_sb, tloc, 0) != inode->i_ino)
+	if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino)
 		goto end_rmdir;
 	retval = -ENOTEMPTY;
 	if (!empty_dir(inode))
@@ -824,7 +827,7 @@ static int udf_unlink(struct inode *dir, struct dentry *dentry)
 	struct udf_fileident_bh fibh;
 	struct fileIdentDesc *fi;
 	struct fileIdentDesc cfi;
-	kernel_lb_addr tloc;
+	struct kernel_lb_addr tloc;
 
 	retval = -ENOENT;
 	lock_kernel();
@@ -834,7 +837,7 @@ static int udf_unlink(struct inode *dir, struct dentry *dentry)
 
 	retval = -EIO;
 	tloc = lelb_to_cpu(cfi.icb.extLocation);
-	if (udf_get_lb_pblock(dir->i_sb, tloc, 0) != inode->i_ino)
+	if (udf_get_lb_pblock(dir->i_sb, &tloc, 0) != inode->i_ino)
 		goto end_unlink;
 
 	if (!inode->i_nlink) {
@@ -897,7 +900,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 	inode->i_op = &page_symlink_inode_operations;
 
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
-		kernel_lb_addr eloc;
+		struct kernel_lb_addr eloc;
 		uint32_t bsize;
 
 		block = udf_new_block(inode->i_sb, inode,
@@ -913,7 +916,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 				iinfo->i_location.partitionReferenceNum;
 		bsize = inode->i_sb->s_blocksize;
 		iinfo->i_lenExtents = bsize;
-		udf_add_aext(inode, &epos, eloc, bsize, 0);
+		udf_add_aext(inode, &epos, &eloc, bsize, 0);
 		brelse(epos.bh);
 
 		block = udf_get_pblock(inode->i_sb, block,
@@ -1108,7 +1111,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
 	struct fileIdentDesc ocfi, ncfi;
 	struct buffer_head *dir_bh = NULL;
 	int retval = -ENOENT;
-	kernel_lb_addr tloc;
+	struct kernel_lb_addr tloc;
 	struct udf_inode_info *old_iinfo = UDF_I(old_inode);
 
 	lock_kernel();
@@ -1119,7 +1122,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
 		brelse(ofibh.sbh);
 	}
 	tloc = lelb_to_cpu(ocfi.icb.extLocation);
-	if (!ofi || udf_get_lb_pblock(old_dir->i_sb, tloc, 0)
+	if (!ofi || udf_get_lb_pblock(old_dir->i_sb, &tloc, 0)
 	    != old_inode->i_ino)
 		goto end_rename;
 
@@ -1158,7 +1161,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (!dir_fi)
 			goto end_rename;
 		tloc = lelb_to_cpu(dir_fi->icb.extLocation);
-		if (udf_get_lb_pblock(old_inode->i_sb, tloc, 0) !=
+		if (udf_get_lb_pblock(old_inode->i_sb, &tloc, 0) !=
 				old_dir->i_ino)
 			goto end_rename;
 
@@ -1187,7 +1190,7 @@ static int udf_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 */
 	ncfi.fileVersionNum = ocfi.fileVersionNum;
 	ncfi.fileCharacteristics = ocfi.fileCharacteristics;
-	memcpy(&(ncfi.icb), &(ocfi.icb), sizeof(long_ad));
+	memcpy(&(ncfi.icb), &(ocfi.icb), sizeof(struct long_ad));
 	udf_write_fi(new_dir, &ncfi, nfi, &nfibh, NULL, NULL);
 
 	/* The old fid may have moved - find it again */
@@ -1242,6 +1245,7 @@ end_rename:
 
 static struct dentry *udf_get_parent(struct dentry *child)
 {
+	struct kernel_lb_addr tloc;
 	struct inode *inode = NULL;
 	struct qstr dotdot = {.name = "..", .len = 2};
 	struct fileIdentDesc cfi;
@@ -1255,8 +1259,8 @@ static struct dentry *udf_get_parent(struct dentry *child)
 		brelse(fibh.ebh);
 	brelse(fibh.sbh);
 
-	inode = udf_iget(child->d_inode->i_sb,
-			 lelb_to_cpu(cfi.icb.extLocation));
+	tloc = lelb_to_cpu(cfi.icb.extLocation);
+	inode = udf_iget(child->d_inode->i_sb, &tloc);
 	if (!inode)
 		goto out_unlock;
 	unlock_kernel();
@@ -1272,14 +1276,14 @@ static struct dentry *udf_nfs_get_inode(struct super_block *sb, u32 block,
 					u16 partref, __u32 generation)
 {
 	struct inode *inode;
-	kernel_lb_addr loc;
+	struct kernel_lb_addr loc;
 
 	if (block == 0)
 		return ERR_PTR(-ESTALE);
 
 	loc.logicalBlockNum = block;
 	loc.partitionReferenceNum = partref;
-	inode = udf_iget(sb, loc);
+	inode = udf_iget(sb, &loc);
 
 	if (inode == NULL)
 		return ERR_PTR(-ENOMEM);
@@ -1318,7 +1322,7 @@ static int udf_encode_fh(struct dentry *de, __u32 *fh, int *lenp,
 {
 	int len = *lenp;
 	struct inode *inode =  de->d_inode;
-	kernel_lb_addr location = UDF_I(inode)->i_location;
+	struct kernel_lb_addr location = UDF_I(inode)->i_location;
 	struct fid *fid = (struct fid *)fh;
 	int type = FILEID_UDF_WITHOUT_PARENT;
 
diff --git a/fs/udf/osta_udf.h b/fs/udf/osta_udf.h
index 65ff47902bd2..fbff74654df2 100644
--- a/fs/udf/osta_udf.h
+++ b/fs/udf/osta_udf.h
@@ -85,7 +85,7 @@ struct appIdentSuffix {
 /* Logical Volume Integrity Descriptor (UDF 2.50 2.2.6) */
 /* Implementation Use (UDF 2.50 2.2.6.4) */
 struct logicalVolIntegrityDescImpUse {
-	regid		impIdent;
+	struct regid	impIdent;
 	__le32		numFiles;
 	__le32		numDirs;
 	__le16		minUDFReadRev;
@@ -97,12 +97,12 @@ struct logicalVolIntegrityDescImpUse {
 /* Implementation Use Volume Descriptor (UDF 2.50 2.2.7) */
 /* Implementation Use (UDF 2.50 2.2.7.2) */
 struct impUseVolDescImpUse {
-	charspec	LVICharset;
+	struct charspec	LVICharset;
 	dstring		logicalVolIdent[128];
 	dstring		LVInfo1[36];
 	dstring		LVInfo2[36];
 	dstring		LVInfo3[36];
-	regid		impIdent;
+	struct regid	impIdent;
 	uint8_t		impUse[128];
 } __attribute__ ((packed));
 
@@ -110,7 +110,7 @@ struct udfPartitionMap2 {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
 	uint8_t		reserved1[2];
-	regid		partIdent;
+	struct regid	partIdent;
 	__le16		volSeqNum;
 	__le16		partitionNum;
 } __attribute__ ((packed));
@@ -120,7 +120,7 @@ struct virtualPartitionMap {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
 	uint8_t		reserved1[2];
-	regid		partIdent;
+	struct regid	partIdent;
 	__le16		volSeqNum;
 	__le16		partitionNum;
 	uint8_t		reserved2[24];
@@ -131,7 +131,7 @@ struct sparablePartitionMap {
 	uint8_t partitionMapType;
 	uint8_t partitionMapLength;
 	uint8_t reserved1[2];
-	regid partIdent;
+	struct regid partIdent;
 	__le16 volSeqNum;
 	__le16 partitionNum;
 	__le16 packetLength;
@@ -146,7 +146,7 @@ struct metadataPartitionMap {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
 	uint8_t		reserved1[2];
-	regid		partIdent;
+	struct regid	partIdent;
 	__le16		volSeqNum;
 	__le16		partitionNum;
 	__le32		metadataFileLoc;
@@ -161,7 +161,7 @@ struct metadataPartitionMap {
 /* Virtual Allocation Table (UDF 1.5 2.2.10) */
 struct virtualAllocationTable15 {
 	__le32		VirtualSector[0];
-	regid		vatIdent;
+	struct regid	vatIdent;
 	__le32		previousVATICBLoc;
 } __attribute__ ((packed));
 
@@ -192,8 +192,8 @@ struct sparingEntry {
 } __attribute__ ((packed));
 
 struct sparingTable {
-	tag 		descTag;
-	regid		sparingIdent;
+	struct tag	descTag;
+	struct regid	sparingIdent;
 	__le16		reallocationTableLen;
 	__le16		reserved;
 	__le32		sequenceNum;
@@ -206,7 +206,7 @@ struct sparingTable {
 #define ICBTAG_FILE_TYPE_MIRROR		0xFB
 #define ICBTAG_FILE_TYPE_BITMAP		0xFC
 
-/* struct long_ad ICB - ADImpUse (UDF 2.50 2.2.4.3) */
+/* struct struct long_ad ICB - ADImpUse (UDF 2.50 2.2.4.3) */
 struct allocDescImpUse {
 	__le16		flags;
 	uint8_t		impUse[4];
diff --git a/fs/udf/partition.c b/fs/udf/partition.c
index 96dfd207c3d6..4b540ee632d5 100644
--- a/fs/udf/partition.c
+++ b/fs/udf/partition.c
@@ -273,7 +273,7 @@ static uint32_t udf_try_read_meta(struct inode *inode, uint32_t block,
 {
 	struct super_block *sb = inode->i_sb;
 	struct udf_part_map *map;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen;
 	sector_t ext_offset;
 	struct extent_position epos = {};
diff --git a/fs/udf/super.c b/fs/udf/super.c
index e25e7010627b..72348cc855a4 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -81,16 +81,13 @@ static char error_buf[1024];
 /* These are the "meat" - everything else is stuffing */
 static int udf_fill_super(struct super_block *, void *, int);
 static void udf_put_super(struct super_block *);
-static void udf_write_super(struct super_block *);
+static int udf_sync_fs(struct super_block *, int);
 static int udf_remount_fs(struct super_block *, int *, char *);
-static int udf_check_valid(struct super_block *, int, int);
-static int udf_vrs(struct super_block *sb, int silent);
-static void udf_load_logicalvolint(struct super_block *, kernel_extent_ad);
-static void udf_find_anchor(struct super_block *);
-static int udf_find_fileset(struct super_block *, kernel_lb_addr *,
-			    kernel_lb_addr *);
+static void udf_load_logicalvolint(struct super_block *, struct kernel_extent_ad);
+static int udf_find_fileset(struct super_block *, struct kernel_lb_addr *,
+			    struct kernel_lb_addr *);
 static void udf_load_fileset(struct super_block *, struct buffer_head *,
-			     kernel_lb_addr *);
+			     struct kernel_lb_addr *);
 static void udf_open_lvid(struct super_block *);
 static void udf_close_lvid(struct super_block *);
 static unsigned int udf_count_free(struct super_block *);
@@ -181,7 +178,7 @@ static const struct super_operations udf_sb_ops = {
 	.delete_inode	= udf_delete_inode,
 	.clear_inode	= udf_clear_inode,
 	.put_super	= udf_put_super,
-	.write_super	= udf_write_super,
+	.sync_fs	= udf_sync_fs,
 	.statfs		= udf_statfs,
 	.remount_fs	= udf_remount_fs,
 	.show_options	= udf_show_options,
@@ -201,6 +198,8 @@ struct udf_options {
 	mode_t umask;
 	gid_t gid;
 	uid_t uid;
+	mode_t fmode;
+	mode_t dmode;
 	struct nls_table *nls_map;
 };
 
@@ -258,7 +257,7 @@ static int udf_show_options(struct seq_file *seq, struct vfsmount *mnt)
 
 	if (!UDF_QUERY_FLAG(sb, UDF_FLAG_STRICT))
 		seq_puts(seq, ",nostrict");
-	if (sb->s_blocksize != UDF_DEFAULT_BLOCKSIZE)
+	if (UDF_QUERY_FLAG(sb, UDF_FLAG_BLOCKSIZE_SET))
 		seq_printf(seq, ",bs=%lu", sb->s_blocksize);
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UNHIDE))
 		seq_puts(seq, ",unhide");
@@ -282,18 +281,16 @@ static int udf_show_options(struct seq_file *seq, struct vfsmount *mnt)
 		seq_printf(seq, ",gid=%u", sbi->s_gid);
 	if (sbi->s_umask != 0)
 		seq_printf(seq, ",umask=%o", sbi->s_umask);
+	if (sbi->s_fmode != UDF_INVALID_MODE)
+		seq_printf(seq, ",mode=%o", sbi->s_fmode);
+	if (sbi->s_dmode != UDF_INVALID_MODE)
+		seq_printf(seq, ",dmode=%o", sbi->s_dmode);
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_SESSION_SET))
 		seq_printf(seq, ",session=%u", sbi->s_session);
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_LASTBLOCK_SET))
 		seq_printf(seq, ",lastblock=%u", sbi->s_last_block);
-	/*
-	 * s_anchor[2] could be zeroed out in case there is no anchor
-	 * in the specified block, but then the "anchor=N" option
-	 * originally given by the user wasn't effective, so it's OK
-	 * if we don't show it.
-	 */
-	if (sbi->s_anchor[2] != 0)
-		seq_printf(seq, ",anchor=%u", sbi->s_anchor[2]);
+	if (sbi->s_anchor != 0)
+		seq_printf(seq, ",anchor=%u", sbi->s_anchor);
 	/*
 	 * volume, partition, fileset and rootdir seem to be ignored
 	 * currently
@@ -317,6 +314,8 @@ static int udf_show_options(struct seq_file *seq, struct vfsmount *mnt)
  *
  *	gid=		Set the default group.
  *	umask=		Set the default umask.
+ *	mode=		Set the default file permissions.
+ *	dmode=		Set the default directory permissions.
  *	uid=		Set the default user.
  *	bs=		Set the block size.
  *	unhide		Show otherwise hidden files.
@@ -366,7 +365,8 @@ enum {
 	Opt_gid, Opt_uid, Opt_umask, Opt_session, Opt_lastblock,
 	Opt_anchor, Opt_volume, Opt_partition, Opt_fileset,
 	Opt_rootdir, Opt_utf8, Opt_iocharset,
-	Opt_err, Opt_uforget, Opt_uignore, Opt_gforget, Opt_gignore
+	Opt_err, Opt_uforget, Opt_uignore, Opt_gforget, Opt_gignore,
+	Opt_fmode, Opt_dmode
 };
 
 static const match_table_t tokens = {
@@ -395,6 +395,8 @@ static const match_table_t tokens = {
 	{Opt_rootdir,	"rootdir=%u"},
 	{Opt_utf8,	"utf8"},
 	{Opt_iocharset,	"iocharset=%s"},
+	{Opt_fmode,     "mode=%o"},
+	{Opt_dmode,     "dmode=%o"},
 	{Opt_err,	NULL}
 };
 
@@ -405,7 +407,6 @@ static int udf_parse_options(char *options, struct udf_options *uopt,
 	int option;
 
 	uopt->novrs = 0;
-	uopt->blocksize = UDF_DEFAULT_BLOCKSIZE;
 	uopt->partition = 0xFFFF;
 	uopt->session = 0xFFFFFFFF;
 	uopt->lastblock = 0;
@@ -428,10 +429,12 @@ static int udf_parse_options(char *options, struct udf_options *uopt,
 		switch (token) {
 		case Opt_novrs:
 			uopt->novrs = 1;
+			break;
 		case Opt_bs:
 			if (match_int(&args[0], &option))
 				return 0;
 			uopt->blocksize = option;
+			uopt->flags |= (1 << UDF_FLAG_BLOCKSIZE_SET);
 			break;
 		case Opt_unhide:
 			uopt->flags |= (1 << UDF_FLAG_UNHIDE);
@@ -531,6 +534,16 @@ static int udf_parse_options(char *options, struct udf_options *uopt,
 		case Opt_gforget:
 			uopt->flags |= (1 << UDF_FLAG_GID_FORGET);
 			break;
+		case Opt_fmode:
+			if (match_octal(args, &option))
+				return 0;
+			uopt->fmode = option & 0777;
+			break;
+		case Opt_dmode:
+			if (match_octal(args, &option))
+				return 0;
+			uopt->dmode = option & 0777;
+			break;
 		default:
 			printk(KERN_ERR "udf: bad mount option \"%s\" "
 			       "or missing value\n", p);
@@ -540,17 +553,6 @@ static int udf_parse_options(char *options, struct udf_options *uopt,
 	return 1;
 }
 
-static void udf_write_super(struct super_block *sb)
-{
-	lock_kernel();
-
-	if (!(sb->s_flags & MS_RDONLY))
-		udf_open_lvid(sb);
-	sb->s_dirt = 0;
-
-	unlock_kernel();
-}
-
 static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 {
 	struct udf_options uopt;
@@ -560,6 +562,8 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 	uopt.uid   = sbi->s_uid;
 	uopt.gid   = sbi->s_gid;
 	uopt.umask = sbi->s_umask;
+	uopt.fmode = sbi->s_fmode;
+	uopt.dmode = sbi->s_dmode;
 
 	if (!udf_parse_options(options, &uopt, true))
 		return -EINVAL;
@@ -568,6 +572,8 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 	sbi->s_uid   = uopt.uid;
 	sbi->s_gid   = uopt.gid;
 	sbi->s_umask = uopt.umask;
+	sbi->s_fmode = uopt.fmode;
+	sbi->s_dmode = uopt.dmode;
 
 	if (sbi->s_lvid_bh) {
 		int write_rev = le16_to_cpu(udf_sb_lvidiu(sbi)->minUDFWriteRev);
@@ -585,22 +591,19 @@ static int udf_remount_fs(struct super_block *sb, int *flags, char *options)
 	return 0;
 }
 
-static int udf_vrs(struct super_block *sb, int silent)
+/* Check Volume Structure Descriptors (ECMA 167 2/9.1) */
+/* We also check any "CD-ROM Volume Descriptor Set" (ECMA 167 2/8.3.1) */
+static loff_t udf_check_vsd(struct super_block *sb)
 {
 	struct volStructDesc *vsd = NULL;
 	loff_t sector = 32768;
 	int sectorsize;
 	struct buffer_head *bh = NULL;
-	int iso9660 = 0;
 	int nsr02 = 0;
 	int nsr03 = 0;
 	struct udf_sb_info *sbi;
 
-	/* Block size must be a multiple of 512 */
-	if (sb->s_blocksize & 511)
-		return 0;
 	sbi = UDF_SB(sb);
-
 	if (sb->s_blocksize < sizeof(struct volStructDesc))
 		sectorsize = sizeof(struct volStructDesc);
 	else
@@ -627,7 +630,6 @@ static int udf_vrs(struct super_block *sb, int silent)
 			break;
 		} else if (!strncmp(vsd->stdIdent, VSD_STD_ID_CD001,
 				    VSD_STD_ID_LEN)) {
-			iso9660 = sector;
 			switch (vsd->structType) {
 			case 0:
 				udf_debug("ISO9660 Boot Record found\n");
@@ -679,139 +681,9 @@ static int udf_vrs(struct super_block *sb, int silent)
 		return 0;
 }
 
-/*
- * Check whether there is an anchor block in the given block
- */
-static int udf_check_anchor_block(struct super_block *sb, sector_t block)
-{
-	struct buffer_head *bh;
-	uint16_t ident;
-
-	if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
-	    udf_fixed_to_variable(block) >=
-	    sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
-		return 0;
-
-	bh = udf_read_tagged(sb, block, block, &ident);
-	if (!bh)
-		return 0;
-	brelse(bh);
-
-	return ident == TAG_IDENT_AVDP;
-}
-
-/* Search for an anchor volume descriptor pointer */
-static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock)
-{
-	sector_t last[6];
-	int i;
-	struct udf_sb_info *sbi = UDF_SB(sb);
-
-	last[0] = lastblock;
-	last[1] = last[0] - 1;
-	last[2] = last[0] + 1;
-	last[3] = last[0] - 2;
-	last[4] = last[0] - 150;
-	last[5] = last[0] - 152;
-
-	/*  according to spec, anchor is in either:
-	 *     block 256
-	 *     lastblock-256
-	 *     lastblock
-	 *  however, if the disc isn't closed, it could be 512 */
-
-	for (i = 0; i < ARRAY_SIZE(last); i++) {
-		if (last[i] < 0)
-			continue;
-		if (last[i] >= sb->s_bdev->bd_inode->i_size >>
-				sb->s_blocksize_bits)
-			continue;
-
-		if (udf_check_anchor_block(sb, last[i])) {
-			sbi->s_anchor[0] = last[i];
-			sbi->s_anchor[1] = last[i] - 256;
-			return last[i];
-		}
-
-		if (last[i] < 256)
-			continue;
-
-		if (udf_check_anchor_block(sb, last[i] - 256)) {
-			sbi->s_anchor[1] = last[i] - 256;
-			return last[i];
-		}
-	}
-
-	if (udf_check_anchor_block(sb, sbi->s_session + 256)) {
-		sbi->s_anchor[0] = sbi->s_session + 256;
-		return last[0];
-	}
-	if (udf_check_anchor_block(sb, sbi->s_session + 512)) {
-		sbi->s_anchor[0] = sbi->s_session + 512;
-		return last[0];
-	}
-	return 0;
-}
-
-/*
- * Find an anchor volume descriptor. The function expects sbi->s_lastblock to
- * be the last block on the media.
- *
- * Return 1 if not found, 0 if ok
- *
- */
-static void udf_find_anchor(struct super_block *sb)
-{
-	sector_t lastblock;
-	struct buffer_head *bh = NULL;
-	uint16_t ident;
-	int i;
-	struct udf_sb_info *sbi = UDF_SB(sb);
-
-	lastblock = udf_scan_anchors(sb, sbi->s_last_block);
-	if (lastblock)
-		goto check_anchor;
-
-	/* No anchor found? Try VARCONV conversion of block numbers */
-	UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
-	/* Firstly, we try to not convert number of the last block */
-	lastblock = udf_scan_anchors(sb,
-				udf_variable_to_fixed(sbi->s_last_block));
-	if (lastblock)
-		goto check_anchor;
-
-	/* Secondly, we try with converted number of the last block */
-	lastblock = udf_scan_anchors(sb, sbi->s_last_block);
-	if (!lastblock) {
-		/* VARCONV didn't help. Clear it. */
-		UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV);
-	}
-
-check_anchor:
-	/*
-	 * Check located anchors and the anchor block supplied via
-	 * mount options
-	 */
-	for (i = 0; i < ARRAY_SIZE(sbi->s_anchor); i++) {
-		if (!sbi->s_anchor[i])
-			continue;
-		bh = udf_read_tagged(sb, sbi->s_anchor[i],
-					sbi->s_anchor[i], &ident);
-		if (!bh)
-			sbi->s_anchor[i] = 0;
-		else {
-			brelse(bh);
-			if (ident != TAG_IDENT_AVDP)
-				sbi->s_anchor[i] = 0;
-		}
-	}
-
-	sbi->s_last_block = lastblock;
-}
-
 static int udf_find_fileset(struct super_block *sb,
-			    kernel_lb_addr *fileset,
-			    kernel_lb_addr *root)
+			    struct kernel_lb_addr *fileset,
+			    struct kernel_lb_addr *root)
 {
 	struct buffer_head *bh = NULL;
 	long lastblock;
@@ -820,7 +692,7 @@ static int udf_find_fileset(struct super_block *sb,
 
 	if (fileset->logicalBlockNum != 0xFFFFFFFF ||
 	    fileset->partitionReferenceNum != 0xFFFF) {
-		bh = udf_read_ptagged(sb, *fileset, 0, &ident);
+		bh = udf_read_ptagged(sb, fileset, 0, &ident);
 
 		if (!bh) {
 			return 1;
@@ -834,7 +706,7 @@ static int udf_find_fileset(struct super_block *sb,
 	sbi = UDF_SB(sb);
 	if (!bh) {
 		/* Search backwards through the partitions */
-		kernel_lb_addr newfileset;
+		struct kernel_lb_addr newfileset;
 
 /* --> cvg: FIXME - is it reasonable? */
 		return 1;
@@ -850,7 +722,7 @@ static int udf_find_fileset(struct super_block *sb,
 			newfileset.logicalBlockNum = 0;
 
 			do {
-				bh = udf_read_ptagged(sb, newfileset, 0,
+				bh = udf_read_ptagged(sb, &newfileset, 0,
 						      &ident);
 				if (!bh) {
 					newfileset.logicalBlockNum++;
@@ -902,14 +774,23 @@ static int udf_find_fileset(struct super_block *sb,
 static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 {
 	struct primaryVolDesc *pvoldesc;
-	struct ustr instr;
-	struct ustr outstr;
+	struct ustr *instr, *outstr;
 	struct buffer_head *bh;
 	uint16_t ident;
+	int ret = 1;
+
+	instr = kmalloc(sizeof(struct ustr), GFP_NOFS);
+	if (!instr)
+		return 1;
+
+	outstr = kmalloc(sizeof(struct ustr), GFP_NOFS);
+	if (!outstr)
+		goto out1;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
 	if (!bh)
-		return 1;
+		goto out2;
+
 	BUG_ON(ident != TAG_IDENT_PVD);
 
 	pvoldesc = (struct primaryVolDesc *)bh->b_data;
@@ -917,7 +798,7 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 	if (udf_disk_stamp_to_time(&UDF_SB(sb)->s_record_time,
 			      pvoldesc->recordingDateAndTime)) {
 #ifdef UDFFS_DEBUG
-		timestamp *ts = &pvoldesc->recordingDateAndTime;
+		struct timestamp *ts = &pvoldesc->recordingDateAndTime;
 		udf_debug("recording time %04u/%02u/%02u"
 			  " %02u:%02u (%x)\n",
 			  le16_to_cpu(ts->year), ts->month, ts->day, ts->hour,
@@ -925,20 +806,25 @@ static int udf_load_pvoldesc(struct super_block *sb, sector_t block)
 #endif
 	}
 
-	if (!udf_build_ustr(&instr, pvoldesc->volIdent, 32))
-		if (udf_CS0toUTF8(&outstr, &instr)) {
-			strncpy(UDF_SB(sb)->s_volume_ident, outstr.u_name,
-				outstr.u_len > 31 ? 31 : outstr.u_len);
+	if (!udf_build_ustr(instr, pvoldesc->volIdent, 32))
+		if (udf_CS0toUTF8(outstr, instr)) {
+			strncpy(UDF_SB(sb)->s_volume_ident, outstr->u_name,
+				outstr->u_len > 31 ? 31 : outstr->u_len);
 			udf_debug("volIdent[] = '%s'\n",
 					UDF_SB(sb)->s_volume_ident);
 		}
 
-	if (!udf_build_ustr(&instr, pvoldesc->volSetIdent, 128))
-		if (udf_CS0toUTF8(&outstr, &instr))
-			udf_debug("volSetIdent[] = '%s'\n", outstr.u_name);
+	if (!udf_build_ustr(instr, pvoldesc->volSetIdent, 128))
+		if (udf_CS0toUTF8(outstr, instr))
+			udf_debug("volSetIdent[] = '%s'\n", outstr->u_name);
 
 	brelse(bh);
-	return 0;
+	ret = 0;
+out2:
+	kfree(outstr);
+out1:
+	kfree(instr);
+	return ret;
 }
 
 static int udf_load_metadata_files(struct super_block *sb, int partition)
@@ -946,7 +832,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct udf_part_map *map;
 	struct udf_meta_data *mdata;
-	kernel_lb_addr addr;
+	struct kernel_lb_addr addr;
 	int fe_error = 0;
 
 	map = &sbi->s_partmaps[partition];
@@ -959,7 +845,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 	udf_debug("Metadata file location: block = %d part = %d\n",
 			  addr.logicalBlockNum, addr.partitionReferenceNum);
 
-	mdata->s_metadata_fe = udf_iget(sb, addr);
+	mdata->s_metadata_fe = udf_iget(sb, &addr);
 
 	if (mdata->s_metadata_fe == NULL) {
 		udf_warning(sb, __func__, "metadata inode efe not found, "
@@ -981,7 +867,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 	udf_debug("Mirror metadata file location: block = %d part = %d\n",
 			  addr.logicalBlockNum, addr.partitionReferenceNum);
 
-	mdata->s_mirror_fe = udf_iget(sb, addr);
+	mdata->s_mirror_fe = udf_iget(sb, &addr);
 
 	if (mdata->s_mirror_fe == NULL) {
 		if (fe_error) {
@@ -1013,7 +899,7 @@ static int udf_load_metadata_files(struct super_block *sb, int partition)
 		udf_debug("Bitmap file location: block = %d part = %d\n",
 			addr.logicalBlockNum, addr.partitionReferenceNum);
 
-		mdata->s_bitmap_fe = udf_iget(sb, addr);
+		mdata->s_bitmap_fe = udf_iget(sb, &addr);
 
 		if (mdata->s_bitmap_fe == NULL) {
 			if (sb->s_flags & MS_RDONLY)
@@ -1037,7 +923,7 @@ error_exit:
 }
 
 static void udf_load_fileset(struct super_block *sb, struct buffer_head *bh,
-			     kernel_lb_addr *root)
+			     struct kernel_lb_addr *root)
 {
 	struct fileSetDesc *fset;
 
@@ -1119,13 +1005,13 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 
 	phd = (struct partitionHeaderDesc *)p->partitionContentsUse;
 	if (phd->unallocSpaceTable.extLength) {
-		kernel_lb_addr loc = {
+		struct kernel_lb_addr loc = {
 			.logicalBlockNum = le32_to_cpu(
 				phd->unallocSpaceTable.extPosition),
 			.partitionReferenceNum = p_index,
 		};
 
-		map->s_uspace.s_table = udf_iget(sb, loc);
+		map->s_uspace.s_table = udf_iget(sb, &loc);
 		if (!map->s_uspace.s_table) {
 			udf_debug("cannot load unallocSpaceTable (part %d)\n",
 					p_index);
@@ -1154,13 +1040,13 @@ static int udf_fill_partdesc_info(struct super_block *sb,
 		udf_debug("partitionIntegrityTable (part %d)\n", p_index);
 
 	if (phd->freedSpaceTable.extLength) {
-		kernel_lb_addr loc = {
+		struct kernel_lb_addr loc = {
 			.logicalBlockNum = le32_to_cpu(
 				phd->freedSpaceTable.extPosition),
 			.partitionReferenceNum = p_index,
 		};
 
-		map->s_fspace.s_table = udf_iget(sb, loc);
+		map->s_fspace.s_table = udf_iget(sb, &loc);
 		if (!map->s_fspace.s_table) {
 			udf_debug("cannot load freedSpaceTable (part %d)\n",
 				p_index);
@@ -1192,7 +1078,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct udf_part_map *map = &sbi->s_partmaps[p_index];
-	kernel_lb_addr ino;
+	struct kernel_lb_addr ino;
 	struct buffer_head *bh = NULL;
 	struct udf_inode_info *vati;
 	uint32_t pos;
@@ -1201,7 +1087,7 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 	/* VAT file entry is in the last recorded block */
 	ino.partitionReferenceNum = type1_index;
 	ino.logicalBlockNum = sbi->s_last_block - map->s_partition_root;
-	sbi->s_vat_inode = udf_iget(sb, ino);
+	sbi->s_vat_inode = udf_iget(sb, &ino);
 	if (!sbi->s_vat_inode)
 		return 1;
 
@@ -1322,7 +1208,7 @@ out_bh:
 }
 
 static int udf_load_logicalvol(struct super_block *sb, sector_t block,
-			       kernel_lb_addr *fileset)
+			       struct kernel_lb_addr *fileset)
 {
 	struct logicalVolDesc *lvd;
 	int i, j, offset;
@@ -1471,7 +1357,7 @@ static int udf_load_logicalvol(struct super_block *sb, sector_t block,
 	}
 
 	if (fileset) {
-		long_ad *la = (long_ad *)&(lvd->logicalVolContentsUse[0]);
+		struct long_ad *la = (struct long_ad *)&(lvd->logicalVolContentsUse[0]);
 
 		*fileset = lelb_to_cpu(la->extLocation);
 		udf_debug("FileSet found in LogicalVolDesc at block=%d, "
@@ -1490,7 +1376,7 @@ out_bh:
  * udf_load_logicalvolint
  *
  */
-static void udf_load_logicalvolint(struct super_block *sb, kernel_extent_ad loc)
+static void udf_load_logicalvolint(struct super_block *sb, struct kernel_extent_ad loc)
 {
 	struct buffer_head *bh = NULL;
 	uint16_t ident;
@@ -1533,7 +1419,7 @@ static void udf_load_logicalvolint(struct super_block *sb, kernel_extent_ad loc)
  *	Written, tested, and released.
  */
 static noinline int udf_process_sequence(struct super_block *sb, long block,
-				long lastblock, kernel_lb_addr *fileset)
+				long lastblock, struct kernel_lb_addr *fileset)
 {
 	struct buffer_head *bh = NULL;
 	struct udf_vds_record vds[VDS_POS_LENGTH];
@@ -1655,85 +1541,199 @@ static noinline int udf_process_sequence(struct super_block *sb, long block,
 	return 0;
 }
 
+static int udf_load_sequence(struct super_block *sb, struct buffer_head *bh,
+			     struct kernel_lb_addr *fileset)
+{
+	struct anchorVolDescPtr *anchor;
+	long main_s, main_e, reserve_s, reserve_e;
+	struct udf_sb_info *sbi;
+
+	sbi = UDF_SB(sb);
+	anchor = (struct anchorVolDescPtr *)bh->b_data;
+
+	/* Locate the main sequence */
+	main_s = le32_to_cpu(anchor->mainVolDescSeqExt.extLocation);
+	main_e = le32_to_cpu(anchor->mainVolDescSeqExt.extLength);
+	main_e = main_e >> sb->s_blocksize_bits;
+	main_e += main_s;
+
+	/* Locate the reserve sequence */
+	reserve_s = le32_to_cpu(anchor->reserveVolDescSeqExt.extLocation);
+	reserve_e = le32_to_cpu(anchor->reserveVolDescSeqExt.extLength);
+	reserve_e = reserve_e >> sb->s_blocksize_bits;
+	reserve_e += reserve_s;
+
+	/* Process the main & reserve sequences */
+	/* responsible for finding the PartitionDesc(s) */
+	if (!udf_process_sequence(sb, main_s, main_e, fileset))
+		return 1;
+	return !udf_process_sequence(sb, reserve_s, reserve_e, fileset);
+}
+
 /*
- * udf_check_valid()
+ * Check whether there is an anchor block in the given block and
+ * load Volume Descriptor Sequence if so.
  */
-static int udf_check_valid(struct super_block *sb, int novrs, int silent)
+static int udf_check_anchor_block(struct super_block *sb, sector_t block,
+				  struct kernel_lb_addr *fileset)
 {
-	long block;
-	struct udf_sb_info *sbi = UDF_SB(sb);
+	struct buffer_head *bh;
+	uint16_t ident;
+	int ret;
 
-	if (novrs) {
-		udf_debug("Validity check skipped because of novrs option\n");
+	if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
+	    udf_fixed_to_variable(block) >=
+	    sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
+		return 0;
+
+	bh = udf_read_tagged(sb, block, block, &ident);
+	if (!bh)
+		return 0;
+	if (ident != TAG_IDENT_AVDP) {
+		brelse(bh);
 		return 0;
 	}
-	/* Check that it is NSR02 compliant */
-	/* Process any "CD-ROM Volume Descriptor Set" (ECMA 167 2/8.3.1) */
-	block = udf_vrs(sb, silent);
-	if (block == -1)
-		udf_debug("Failed to read byte 32768. Assuming open "
-			  "disc. Skipping validity check\n");
-	if (block && !sbi->s_last_block)
-		sbi->s_last_block = udf_get_last_block(sb);
-	return !block;
+	ret = udf_load_sequence(sb, bh, fileset);
+	brelse(bh);
+	return ret;
 }
 
-static int udf_load_sequence(struct super_block *sb, kernel_lb_addr *fileset)
+/* Search for an anchor volume descriptor pointer */
+static sector_t udf_scan_anchors(struct super_block *sb, sector_t lastblock,
+				 struct kernel_lb_addr *fileset)
 {
-	struct anchorVolDescPtr *anchor;
-	uint16_t ident;
-	struct buffer_head *bh;
-	long main_s, main_e, reserve_s, reserve_e;
+	sector_t last[6];
 	int i;
-	struct udf_sb_info *sbi;
-
-	if (!sb)
-		return 1;
-	sbi = UDF_SB(sb);
+	struct udf_sb_info *sbi = UDF_SB(sb);
+	int last_count = 0;
 
-	for (i = 0; i < ARRAY_SIZE(sbi->s_anchor); i++) {
-		if (!sbi->s_anchor[i])
+	/* First try user provided anchor */
+	if (sbi->s_anchor) {
+		if (udf_check_anchor_block(sb, sbi->s_anchor, fileset))
+			return lastblock;
+	}
+	/*
+	 * according to spec, anchor is in either:
+	 *     block 256
+	 *     lastblock-256
+	 *     lastblock
+	 *  however, if the disc isn't closed, it could be 512.
+	 */
+	if (udf_check_anchor_block(sb, sbi->s_session + 256, fileset))
+		return lastblock;
+	/*
+	 * The trouble is which block is the last one. Drives often misreport
+	 * this so we try various possibilities.
+	 */
+	last[last_count++] = lastblock;
+	if (lastblock >= 1)
+		last[last_count++] = lastblock - 1;
+	last[last_count++] = lastblock + 1;
+	if (lastblock >= 2)
+		last[last_count++] = lastblock - 2;
+	if (lastblock >= 150)
+		last[last_count++] = lastblock - 150;
+	if (lastblock >= 152)
+		last[last_count++] = lastblock - 152;
+
+	for (i = 0; i < last_count; i++) {
+		if (last[i] >= sb->s_bdev->bd_inode->i_size >>
+				sb->s_blocksize_bits)
 			continue;
-
-		bh = udf_read_tagged(sb, sbi->s_anchor[i], sbi->s_anchor[i],
-				     &ident);
-		if (!bh)
+		if (udf_check_anchor_block(sb, last[i], fileset))
+			return last[i];
+		if (last[i] < 256)
 			continue;
+		if (udf_check_anchor_block(sb, last[i] - 256, fileset))
+			return last[i];
+	}
 
-		anchor = (struct anchorVolDescPtr *)bh->b_data;
+	/* Finally try block 512 in case media is open */
+	if (udf_check_anchor_block(sb, sbi->s_session + 512, fileset))
+		return last[0];
+	return 0;
+}
 
-		/* Locate the main sequence */
-		main_s = le32_to_cpu(anchor->mainVolDescSeqExt.extLocation);
-		main_e = le32_to_cpu(anchor->mainVolDescSeqExt.extLength);
-		main_e = main_e >> sb->s_blocksize_bits;
-		main_e += main_s;
+/*
+ * Find an anchor volume descriptor and load Volume Descriptor Sequence from
+ * area specified by it. The function expects sbi->s_lastblock to be the last
+ * block on the media.
+ *
+ * Return 1 if ok, 0 if not found.
+ *
+ */
+static int udf_find_anchor(struct super_block *sb,
+			   struct kernel_lb_addr *fileset)
+{
+	sector_t lastblock;
+	struct udf_sb_info *sbi = UDF_SB(sb);
 
-		/* Locate the reserve sequence */
-		reserve_s = le32_to_cpu(
-				anchor->reserveVolDescSeqExt.extLocation);
-		reserve_e = le32_to_cpu(
-				anchor->reserveVolDescSeqExt.extLength);
-		reserve_e = reserve_e >> sb->s_blocksize_bits;
-		reserve_e += reserve_s;
+	lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset);
+	if (lastblock)
+		goto out;
 
-		brelse(bh);
+	/* No anchor found? Try VARCONV conversion of block numbers */
+	UDF_SET_FLAG(sb, UDF_FLAG_VARCONV);
+	/* Firstly, we try to not convert number of the last block */
+	lastblock = udf_scan_anchors(sb,
+				udf_variable_to_fixed(sbi->s_last_block),
+				fileset);
+	if (lastblock)
+		goto out;
 
-		/* Process the main & reserve sequences */
-		/* responsible for finding the PartitionDesc(s) */
-		if (!(udf_process_sequence(sb, main_s, main_e,
-					   fileset) &&
-		      udf_process_sequence(sb, reserve_s, reserve_e,
-					   fileset)))
-			break;
+	/* Secondly, we try with converted number of the last block */
+	lastblock = udf_scan_anchors(sb, sbi->s_last_block, fileset);
+	if (!lastblock) {
+		/* VARCONV didn't help. Clear it. */
+		UDF_CLEAR_FLAG(sb, UDF_FLAG_VARCONV);
+		return 0;
 	}
+out:
+	sbi->s_last_block = lastblock;
+	return 1;
+}
 
-	if (i == ARRAY_SIZE(sbi->s_anchor)) {
-		udf_debug("No Anchor block found\n");
-		return 1;
+/*
+ * Check Volume Structure Descriptor, find Anchor block and load Volume
+ * Descriptor Sequence
+ */
+static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt,
+			int silent, struct kernel_lb_addr *fileset)
+{
+	struct udf_sb_info *sbi = UDF_SB(sb);
+	loff_t nsr_off;
+
+	if (!sb_set_blocksize(sb, uopt->blocksize)) {
+		if (!silent)
+			printk(KERN_WARNING "UDF-fs: Bad block size\n");
+		return 0;
+	}
+	sbi->s_last_block = uopt->lastblock;
+	if (!uopt->novrs) {
+		/* Check that it is NSR02 compliant */
+		nsr_off = udf_check_vsd(sb);
+		if (!nsr_off) {
+			if (!silent)
+				printk(KERN_WARNING "UDF-fs: No VRS found\n");
+			return 0;
+		}
+		if (nsr_off == -1)
+			udf_debug("Failed to read byte 32768. Assuming open "
+				  "disc. Skipping validity check\n");
+		if (!sbi->s_last_block)
+			sbi->s_last_block = udf_get_last_block(sb);
+	} else {
+		udf_debug("Validity check skipped because of novrs option\n");
 	}
-	udf_debug("Using anchor in block %d\n", sbi->s_anchor[i]);
 
-	return 0;
+	/* Look for anchor block and load Volume Descriptor Sequence */
+	sbi->s_anchor = uopt->anchor;
+	if (!udf_find_anchor(sb, fileset)) {
+		if (!silent)
+			printk(KERN_WARNING "UDF-fs: No anchor found\n");
+		return 0;
+	}
+	return 1;
 }
 
 static void udf_open_lvid(struct super_block *sb)
@@ -1742,9 +1742,9 @@ static void udf_open_lvid(struct super_block *sb)
 	struct buffer_head *bh = sbi->s_lvid_bh;
 	struct logicalVolIntegrityDesc *lvid;
 	struct logicalVolIntegrityDescImpUse *lvidiu;
+
 	if (!bh)
 		return;
-
 	lvid = (struct logicalVolIntegrityDesc *)bh->b_data;
 	lvidiu = udf_sb_lvidiu(sbi);
 
@@ -1752,14 +1752,15 @@ static void udf_open_lvid(struct super_block *sb)
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
 	udf_time_to_disk_stamp(&lvid->recordingDateAndTime,
 				CURRENT_TIME);
-	lvid->integrityType = LVID_INTEGRITY_TYPE_OPEN;
+	lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN);
 
 	lvid->descTag.descCRC = cpu_to_le16(
-		crc_itu_t(0, (char *)lvid + sizeof(tag),
+		crc_itu_t(0, (char *)lvid + sizeof(struct tag),
 			le16_to_cpu(lvid->descTag.descCRCLength)));
 
 	lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag);
 	mark_buffer_dirty(bh);
+	sbi->s_lvid_dirty = 0;
 }
 
 static void udf_close_lvid(struct super_block *sb)
@@ -1773,10 +1774,6 @@ static void udf_close_lvid(struct super_block *sb)
 		return;
 
 	lvid = (struct logicalVolIntegrityDesc *)bh->b_data;
-
-	if (lvid->integrityType != LVID_INTEGRITY_TYPE_OPEN)
-		return;
-
 	lvidiu = udf_sb_lvidiu(sbi);
 	lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
@@ -1790,11 +1787,12 @@ static void udf_close_lvid(struct super_block *sb)
 	lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_CLOSE);
 
 	lvid->descTag.descCRC = cpu_to_le16(
-			crc_itu_t(0, (char *)lvid + sizeof(tag),
+			crc_itu_t(0, (char *)lvid + sizeof(struct tag),
 				le16_to_cpu(lvid->descTag.descCRCLength)));
 
 	lvid->descTag.tagChecksum = udf_tag_checksum(&lvid->descTag);
 	mark_buffer_dirty(bh);
+	sbi->s_lvid_dirty = 0;
 }
 
 static void udf_sb_free_bitmap(struct udf_bitmap *bitmap)
@@ -1846,15 +1844,18 @@ static void udf_free_partition(struct udf_part_map *map)
 static int udf_fill_super(struct super_block *sb, void *options, int silent)
 {
 	int i;
+	int ret;
 	struct inode *inode = NULL;
 	struct udf_options uopt;
-	kernel_lb_addr rootdir, fileset;
+	struct kernel_lb_addr rootdir, fileset;
 	struct udf_sb_info *sbi;
 
 	uopt.flags = (1 << UDF_FLAG_USE_AD_IN_ICB) | (1 << UDF_FLAG_STRICT);
 	uopt.uid = -1;
 	uopt.gid = -1;
 	uopt.umask = 0;
+	uopt.fmode = UDF_INVALID_MODE;
+	uopt.dmode = UDF_INVALID_MODE;
 
 	sbi = kzalloc(sizeof(struct udf_sb_info), GFP_KERNEL);
 	if (!sbi)
@@ -1892,15 +1893,10 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	sbi->s_uid = uopt.uid;
 	sbi->s_gid = uopt.gid;
 	sbi->s_umask = uopt.umask;
+	sbi->s_fmode = uopt.fmode;
+	sbi->s_dmode = uopt.dmode;
 	sbi->s_nls_map = uopt.nls_map;
 
-	/* Set the block size for all transfers */
-	if (!sb_min_blocksize(sb, uopt.blocksize)) {
-		udf_debug("Bad block size (%d)\n", uopt.blocksize);
-		printk(KERN_ERR "udf: bad block size (%d)\n", uopt.blocksize);
-		goto error_out;
-	}
-
 	if (uopt.session == 0xFFFFFFFF)
 		sbi->s_session = udf_get_last_session(sb);
 	else
@@ -1908,18 +1904,6 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 
 	udf_debug("Multi-session=%d\n", sbi->s_session);
 
-	sbi->s_last_block = uopt.lastblock;
-	sbi->s_anchor[0] = sbi->s_anchor[1] = 0;
-	sbi->s_anchor[2] = uopt.anchor;
-
-	if (udf_check_valid(sb, uopt.novrs, silent)) {
-		/* read volume recognition sequences */
-		printk(KERN_WARNING "UDF-fs: No VRS found\n");
-		goto error_out;
-	}
-
-	udf_find_anchor(sb);
-
 	/* Fill in the rest of the superblock */
 	sb->s_op = &udf_sb_ops;
 	sb->s_export_op = &udf_export_ops;
@@ -1928,7 +1912,21 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	sb->s_magic = UDF_SUPER_MAGIC;
 	sb->s_time_gran = 1000;
 
-	if (udf_load_sequence(sb, &fileset)) {
+	if (uopt.flags & (1 << UDF_FLAG_BLOCKSIZE_SET)) {
+		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
+	} else {
+		uopt.blocksize = bdev_hardsect_size(sb->s_bdev);
+		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
+		if (!ret && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
+			if (!silent)
+				printk(KERN_NOTICE
+				       "UDF-fs: Rescanning with blocksize "
+				       "%d\n", UDF_DEFAULT_BLOCKSIZE);
+			uopt.blocksize = UDF_DEFAULT_BLOCKSIZE;
+			ret = udf_load_vrs(sb, &uopt, silent, &fileset);
+		}
+	}
+	if (!ret) {
 		printk(KERN_WARNING "UDF-fs: No partition found (1)\n");
 		goto error_out;
 	}
@@ -1978,7 +1976,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	}
 
 	if (!silent) {
-		timestamp ts;
+		struct timestamp ts;
 		udf_time_to_disk_stamp(&ts, sbi->s_record_time);
 		udf_info("UDF: Mounting volume '%s', "
 			 "timestamp %04u/%02u/%02u %02u:%02u (%x)\n",
@@ -1991,7 +1989,7 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 	/* Assign the root inode */
 	/* assign inodes by physical block number */
 	/* perhaps it's not extensible enough, but for now ... */
-	inode = udf_iget(sb, rootdir);
+	inode = udf_iget(sb, &rootdir);
 	if (!inode) {
 		printk(KERN_ERR "UDF-fs: Error in udf_iget, block=%d, "
 				"partition=%d\n",
@@ -2081,11 +2079,31 @@ static void udf_put_super(struct super_block *sb)
 	sb->s_fs_info = NULL;
 }
 
+static int udf_sync_fs(struct super_block *sb, int wait)
+{
+	struct udf_sb_info *sbi = UDF_SB(sb);
+
+	mutex_lock(&sbi->s_alloc_mutex);
+	if (sbi->s_lvid_dirty) {
+		/*
+		 * Blockdevice will be synced later so we don't have to submit
+		 * the buffer for IO
+		 */
+		mark_buffer_dirty(sbi->s_lvid_bh);
+		sb->s_dirt = 0;
+		sbi->s_lvid_dirty = 0;
+	}
+	mutex_unlock(&sbi->s_alloc_mutex);
+
+	return 0;
+}
+
 static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct super_block *sb = dentry->d_sb;
 	struct udf_sb_info *sbi = UDF_SB(sb);
 	struct logicalVolIntegrityDescImpUse *lvidiu;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	if (sbi->s_lvid_bh != NULL)
 		lvidiu = udf_sb_lvidiu(sbi);
@@ -2101,8 +2119,9 @@ static int udf_statfs(struct dentry *dentry, struct kstatfs *buf)
 					  le32_to_cpu(lvidiu->numDirs)) : 0)
 			+ buf->f_bfree;
 	buf->f_ffree = buf->f_bfree;
-	/* __kernel_fsid_t f_fsid */
 	buf->f_namelen = UDF_NAME_LEN - 2;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 
 	return 0;
 }
@@ -2114,7 +2133,7 @@ static unsigned int udf_count_free_bitmap(struct super_block *sb,
 	unsigned int accum = 0;
 	int index;
 	int block = 0, newblock;
-	kernel_lb_addr loc;
+	struct kernel_lb_addr loc;
 	uint32_t bytes;
 	uint8_t *ptr;
 	uint16_t ident;
@@ -2124,7 +2143,7 @@ static unsigned int udf_count_free_bitmap(struct super_block *sb,
 
 	loc.logicalBlockNum = bitmap->s_extPosition;
 	loc.partitionReferenceNum = UDF_SB(sb)->s_partition;
-	bh = udf_read_ptagged(sb, loc, 0, &ident);
+	bh = udf_read_ptagged(sb, &loc, 0, &ident);
 
 	if (!bh) {
 		printk(KERN_ERR "udf: udf_count_free failed\n");
@@ -2147,7 +2166,7 @@ static unsigned int udf_count_free_bitmap(struct super_block *sb,
 		bytes -= cur_bytes;
 		if (bytes) {
 			brelse(bh);
-			newblock = udf_get_lb_pblock(sb, loc, ++block);
+			newblock = udf_get_lb_pblock(sb, &loc, ++block);
 			bh = udf_tread(sb, newblock);
 			if (!bh) {
 				udf_debug("read failed\n");
@@ -2170,7 +2189,7 @@ static unsigned int udf_count_free_table(struct super_block *sb,
 {
 	unsigned int accum = 0;
 	uint32_t elen;
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	int8_t etype;
 	struct extent_position epos;
 
diff --git a/fs/udf/truncate.c b/fs/udf/truncate.c
index 65e19b4f9424..225527cdc885 100644
--- a/fs/udf/truncate.c
+++ b/fs/udf/truncate.c
@@ -28,10 +28,10 @@
 #include "udf_sb.h"
 
 static void extent_trunc(struct inode *inode, struct extent_position *epos,
-			 kernel_lb_addr eloc, int8_t etype, uint32_t elen,
+			 struct kernel_lb_addr *eloc, int8_t etype, uint32_t elen,
 			 uint32_t nelen)
 {
-	kernel_lb_addr neloc = {};
+	struct kernel_lb_addr neloc = {};
 	int last_block = (elen + inode->i_sb->s_blocksize - 1) >>
 		inode->i_sb->s_blocksize_bits;
 	int first_block = (nelen + inode->i_sb->s_blocksize - 1) >>
@@ -43,12 +43,12 @@ static void extent_trunc(struct inode *inode, struct extent_position *epos,
 					last_block);
 			etype = (EXT_NOT_RECORDED_NOT_ALLOCATED >> 30);
 		} else
-			neloc = eloc;
+			neloc = *eloc;
 		nelen = (etype << 30) | nelen;
 	}
 
 	if (elen != nelen) {
-		udf_write_aext(inode, epos, neloc, nelen, 0);
+		udf_write_aext(inode, epos, &neloc, nelen, 0);
 		if (last_block - first_block > 0) {
 			if (etype == (EXT_RECORDED_ALLOCATED >> 30))
 				mark_inode_dirty(inode);
@@ -68,7 +68,7 @@ static void extent_trunc(struct inode *inode, struct extent_position *epos,
 void udf_truncate_tail_extent(struct inode *inode)
 {
 	struct extent_position epos = {};
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen, nelen;
 	uint64_t lbcount = 0;
 	int8_t etype = -1, netype;
@@ -83,9 +83,9 @@ void udf_truncate_tail_extent(struct inode *inode)
 		return;
 
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		adsize = sizeof(short_ad);
+		adsize = sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 	else
 		BUG();
 
@@ -106,7 +106,7 @@ void udf_truncate_tail_extent(struct inode *inode)
 				       (unsigned)elen);
 			nelen = elen - (lbcount - inode->i_size);
 			epos.offset -= adsize;
-			extent_trunc(inode, &epos, eloc, etype, elen, nelen);
+			extent_trunc(inode, &epos, &eloc, etype, elen, nelen);
 			epos.offset += adsize;
 			if (udf_next_aext(inode, &epos, &eloc, &elen, 1) != -1)
 				printk(KERN_ERR "udf_truncate_tail_extent(): "
@@ -124,7 +124,7 @@ void udf_truncate_tail_extent(struct inode *inode)
 void udf_discard_prealloc(struct inode *inode)
 {
 	struct extent_position epos = { NULL, 0, {0, 0} };
-	kernel_lb_addr eloc;
+	struct kernel_lb_addr eloc;
 	uint32_t elen;
 	uint64_t lbcount = 0;
 	int8_t etype = -1, netype;
@@ -136,9 +136,9 @@ void udf_discard_prealloc(struct inode *inode)
 		return;
 
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		adsize = sizeof(short_ad);
+		adsize = sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 	else
 		adsize = 0;
 
@@ -152,7 +152,7 @@ void udf_discard_prealloc(struct inode *inode)
 	if (etype == (EXT_NOT_RECORDED_ALLOCATED >> 30)) {
 		epos.offset -= adsize;
 		lbcount -= elen;
-		extent_trunc(inode, &epos, eloc, etype, elen, 0);
+		extent_trunc(inode, &epos, &eloc, etype, elen, 0);
 		if (!epos.bh) {
 			iinfo->i_lenAlloc =
 				epos.offset -
@@ -200,7 +200,7 @@ static void udf_update_alloc_ext_desc(struct inode *inode,
 void udf_truncate_extents(struct inode *inode)
 {
 	struct extent_position epos;
-	kernel_lb_addr eloc, neloc = {};
+	struct kernel_lb_addr eloc, neloc = {};
 	uint32_t elen, nelen = 0, indirect_ext_len = 0, lenalloc;
 	int8_t etype;
 	struct super_block *sb = inode->i_sb;
@@ -210,9 +210,9 @@ void udf_truncate_extents(struct inode *inode)
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
 	if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_SHORT)
-		adsize = sizeof(short_ad);
+		adsize = sizeof(struct short_ad);
 	else if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_LONG)
-		adsize = sizeof(long_ad);
+		adsize = sizeof(struct long_ad);
 	else
 		BUG();
 
@@ -221,7 +221,7 @@ void udf_truncate_extents(struct inode *inode)
 		(inode->i_size & (sb->s_blocksize - 1));
 	if (etype != -1) {
 		epos.offset -= adsize;
-		extent_trunc(inode, &epos, eloc, etype, elen, byte_offset);
+		extent_trunc(inode, &epos, &eloc, etype, elen, byte_offset);
 		epos.offset += adsize;
 		if (byte_offset)
 			lenalloc = epos.offset;
@@ -236,12 +236,12 @@ void udf_truncate_extents(struct inode *inode)
 		while ((etype = udf_current_aext(inode, &epos, &eloc,
 						 &elen, 0)) != -1) {
 			if (etype == (EXT_NEXT_EXTENT_ALLOCDECS >> 30)) {
-				udf_write_aext(inode, &epos, neloc, nelen, 0);
+				udf_write_aext(inode, &epos, &neloc, nelen, 0);
 				if (indirect_ext_len) {
 					/* We managed to free all extents in the
 					 * indirect extent - free it too */
 					BUG_ON(!epos.bh);
-					udf_free_blocks(sb, inode, epos.block,
+					udf_free_blocks(sb, inode, &epos.block,
 							0, indirect_ext_len);
 				} else if (!epos.bh) {
 					iinfo->i_lenAlloc = lenalloc;
@@ -253,7 +253,7 @@ void udf_truncate_extents(struct inode *inode)
 				epos.offset = sizeof(struct allocExtDesc);
 				epos.block = eloc;
 				epos.bh = udf_tread(sb,
-						udf_get_lb_pblock(sb, eloc, 0));
+						udf_get_lb_pblock(sb, &eloc, 0));
 				if (elen)
 					indirect_ext_len =
 						(elen + sb->s_blocksize - 1) >>
@@ -261,7 +261,7 @@ void udf_truncate_extents(struct inode *inode)
 				else
 					indirect_ext_len = 1;
 			} else {
-				extent_trunc(inode, &epos, eloc, etype,
+				extent_trunc(inode, &epos, &eloc, etype,
 					     elen, 0);
 				epos.offset += adsize;
 			}
@@ -269,7 +269,7 @@ void udf_truncate_extents(struct inode *inode)
 
 		if (indirect_ext_len) {
 			BUG_ON(!epos.bh);
-			udf_free_blocks(sb, inode, epos.block, 0,
+			udf_free_blocks(sb, inode, &epos.block, 0,
 					indirect_ext_len);
 		} else if (!epos.bh) {
 			iinfo->i_lenAlloc = lenalloc;
@@ -278,7 +278,7 @@ void udf_truncate_extents(struct inode *inode)
 			udf_update_alloc_ext_desc(inode, &epos, lenalloc);
 	} else if (inode->i_size) {
 		if (byte_offset) {
-			kernel_long_ad extent;
+			struct kernel_long_ad extent;
 
 			/*
 			 *  OK, there is not extent covering inode->i_size and
diff --git a/fs/udf/udf_i.h b/fs/udf/udf_i.h
index 4f86b1d98a5d..e58d1de41073 100644
--- a/fs/udf/udf_i.h
+++ b/fs/udf/udf_i.h
@@ -4,7 +4,7 @@
 struct udf_inode_info {
 	struct timespec		i_crtime;
 	/* Physical address of inode */
-	kernel_lb_addr		i_location;
+	struct kernel_lb_addr		i_location;
 	__u64			i_unique;
 	__u32			i_lenEAttr;
 	__u32			i_lenAlloc;
@@ -17,8 +17,8 @@ struct udf_inode_info {
 	unsigned		i_strat4096 : 1;
 	unsigned		reserved : 26;
 	union {
-		short_ad	*i_sad;
-		long_ad		*i_lad;
+		struct short_ad	*i_sad;
+		struct long_ad		*i_lad;
 		__u8		*i_data;
 	} i_ext;
 	struct inode vfs_inode;
diff --git a/fs/udf/udf_sb.h b/fs/udf/udf_sb.h
index 1c1c514a9725..d113b72c2768 100644
--- a/fs/udf/udf_sb.h
+++ b/fs/udf/udf_sb.h
@@ -30,6 +30,7 @@
 #define UDF_FLAG_GID_SET	16
 #define UDF_FLAG_SESSION_SET	17
 #define UDF_FLAG_LASTBLOCK_SET	18
+#define UDF_FLAG_BLOCKSIZE_SET	19
 
 #define UDF_PART_FLAG_UNALLOC_BITMAP	0x0001
 #define UDF_PART_FLAG_UNALLOC_TABLE	0x0002
@@ -48,6 +49,8 @@
 #define UDF_SPARABLE_MAP15		0x1522U
 #define UDF_METADATA_MAP25		0x2511U
 
+#define UDF_INVALID_MODE		((mode_t)-1)
+
 #pragma pack(1) /* XXX(hch): Why?  This file just defines in-core structures */
 
 struct udf_meta_data {
@@ -114,7 +117,7 @@ struct udf_sb_info {
 
 	/* Sector headers */
 	__s32			s_session;
-	__u32			s_anchor[3];
+	__u32			s_anchor;
 	__u32			s_last_block;
 
 	struct buffer_head	*s_lvid_bh;
@@ -123,6 +126,8 @@ struct udf_sb_info {
 	mode_t			s_umask;
 	gid_t			s_gid;
 	uid_t			s_uid;
+	mode_t			s_fmode;
+	mode_t			s_dmode;
 
 	/* Root Info */
 	struct timespec		s_record_time;
@@ -143,6 +148,8 @@ struct udf_sb_info {
 	struct inode		*s_vat_inode;
 
 	struct mutex		s_alloc_mutex;
+	/* Protected by s_alloc_mutex */
+	unsigned int		s_lvid_dirty;
 };
 
 static inline struct udf_sb_info *UDF_SB(struct super_block *sb)
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 8ec865de5f13..cac51b77a5d1 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -62,10 +62,8 @@ static inline size_t udf_ext0_offset(struct inode *inode)
 		return 0;
 }
 
-#define udf_get_lb_pblock(sb,loc,offset) udf_get_pblock((sb), (loc).logicalBlockNum, (loc).partitionReferenceNum, (offset))
-
 /* computes tag checksum */
-u8 udf_tag_checksum(const tag *t);
+u8 udf_tag_checksum(const struct tag *t);
 
 struct dentry;
 struct inode;
@@ -95,7 +93,7 @@ struct udf_vds_record {
 };
 
 struct generic_desc {
-	tag		descTag;
+	struct tag	descTag;
 	__le32		volDescSeqNum;
 };
 
@@ -108,11 +106,22 @@ struct ustr {
 struct extent_position {
 	struct buffer_head *bh;
 	uint32_t offset;
-	kernel_lb_addr block;
+	struct kernel_lb_addr block;
 };
 
 /* super.c */
 extern void udf_warning(struct super_block *, const char *, const char *, ...);
+static inline void udf_updated_lvid(struct super_block *sb)
+{
+	struct buffer_head *bh = UDF_SB(sb)->s_lvid_bh;
+
+	BUG_ON(!bh);
+	WARN_ON_ONCE(((struct logicalVolIntegrityDesc *)
+		     bh->b_data)->integrityType !=
+		     cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN));
+	sb->s_dirt = 1;
+	UDF_SB(sb)->s_lvid_dirty = 1;
+}
 
 /* namei.c */
 extern int udf_write_fi(struct inode *inode, struct fileIdentDesc *,
@@ -124,7 +133,7 @@ extern int udf_ioctl(struct inode *, struct file *, unsigned int,
 		     unsigned long);
 
 /* inode.c */
-extern struct inode *udf_iget(struct super_block *, kernel_lb_addr);
+extern struct inode *udf_iget(struct super_block *, struct kernel_lb_addr *);
 extern int udf_sync_inode(struct inode *);
 extern void udf_expand_file_adinicb(struct inode *, int, int *);
 extern struct buffer_head *udf_expand_dir_adinicb(struct inode *, int *, int *);
@@ -136,19 +145,19 @@ extern void udf_clear_inode(struct inode *);
 extern int udf_write_inode(struct inode *, int);
 extern long udf_block_map(struct inode *, sector_t);
 extern int udf_extend_file(struct inode *, struct extent_position *,
-			   kernel_long_ad *, sector_t);
+			   struct kernel_long_ad *, sector_t);
 extern int8_t inode_bmap(struct inode *, sector_t, struct extent_position *,
-			 kernel_lb_addr *, uint32_t *, sector_t *);
+			 struct kernel_lb_addr *, uint32_t *, sector_t *);
 extern int8_t udf_add_aext(struct inode *, struct extent_position *,
-			   kernel_lb_addr, uint32_t, int);
+			   struct kernel_lb_addr *, uint32_t, int);
 extern int8_t udf_write_aext(struct inode *, struct extent_position *,
-			     kernel_lb_addr, uint32_t, int);
+			     struct kernel_lb_addr *, uint32_t, int);
 extern int8_t udf_delete_aext(struct inode *, struct extent_position,
-			      kernel_lb_addr, uint32_t);
+			      struct kernel_lb_addr, uint32_t);
 extern int8_t udf_next_aext(struct inode *, struct extent_position *,
-			    kernel_lb_addr *, uint32_t *, int);
+			    struct kernel_lb_addr *, uint32_t *, int);
 extern int8_t udf_current_aext(struct inode *, struct extent_position *,
-			       kernel_lb_addr *, uint32_t *, int);
+			       struct kernel_lb_addr *, uint32_t *, int);
 
 /* misc.c */
 extern struct buffer_head *udf_tgetblk(struct super_block *, int);
@@ -160,7 +169,7 @@ extern struct genericFormat *udf_get_extendedattr(struct inode *, uint32_t,
 extern struct buffer_head *udf_read_tagged(struct super_block *, uint32_t,
 					   uint32_t, uint16_t *);
 extern struct buffer_head *udf_read_ptagged(struct super_block *,
-					    kernel_lb_addr, uint32_t,
+					    struct kernel_lb_addr *, uint32_t,
 					    uint16_t *);
 extern void udf_update_tag(char *, int);
 extern void udf_new_tag(char *, uint16_t, uint16_t, uint16_t, uint32_t, int);
@@ -182,6 +191,14 @@ extern uint32_t udf_get_pblock_meta25(struct super_block *, uint32_t, uint16_t,
 					  uint32_t);
 extern int udf_relocate_blocks(struct super_block *, long, long *);
 
+static inline uint32_t
+udf_get_lb_pblock(struct super_block *sb, struct kernel_lb_addr *loc,
+		  uint32_t offset)
+{
+	return udf_get_pblock(sb, loc->logicalBlockNum,
+			loc->partitionReferenceNum, offset);
+}
+
 /* unicode.c */
 extern int udf_get_filename(struct super_block *, uint8_t *, uint8_t *, int);
 extern int udf_put_filename(struct super_block *, const uint8_t *, uint8_t *,
@@ -200,7 +217,7 @@ extern void udf_truncate_extents(struct inode *);
 
 /* balloc.c */
 extern void udf_free_blocks(struct super_block *, struct inode *,
-			    kernel_lb_addr, uint32_t, uint32_t);
+			    struct kernel_lb_addr *, uint32_t, uint32_t);
 extern int udf_prealloc_blocks(struct super_block *, struct inode *, uint16_t,
 			       uint32_t, uint32_t);
 extern int udf_new_block(struct super_block *, struct inode *, uint16_t,
@@ -214,16 +231,16 @@ extern struct fileIdentDesc *udf_fileident_read(struct inode *, loff_t *,
 						struct udf_fileident_bh *,
 						struct fileIdentDesc *,
 						struct extent_position *,
-						kernel_lb_addr *, uint32_t *,
+						struct kernel_lb_addr *, uint32_t *,
 						sector_t *);
 extern struct fileIdentDesc *udf_get_fileident(void *buffer, int bufsize,
 					       int *offset);
-extern long_ad *udf_get_filelongad(uint8_t *, int, uint32_t *, int);
-extern short_ad *udf_get_fileshortad(uint8_t *, int, uint32_t *, int);
+extern struct long_ad *udf_get_filelongad(uint8_t *, int, uint32_t *, int);
+extern struct short_ad *udf_get_fileshortad(uint8_t *, int, uint32_t *, int);
 
 /* udftime.c */
 extern struct timespec *udf_disk_stamp_to_time(struct timespec *dest,
-						timestamp src);
-extern timestamp *udf_time_to_disk_stamp(timestamp *dest, struct timespec src);
+						struct timestamp src);
+extern struct timestamp *udf_time_to_disk_stamp(struct timestamp *dest, struct timespec src);
 
 #endif				/* __UDF_DECL_H */
diff --git a/fs/udf/udfend.h b/fs/udf/udfend.h
index 489f52fb428c..6a9f3a9cc428 100644
--- a/fs/udf/udfend.h
+++ b/fs/udf/udfend.h
@@ -4,9 +4,9 @@
 #include <asm/byteorder.h>
 #include <linux/string.h>
 
-static inline kernel_lb_addr lelb_to_cpu(lb_addr in)
+static inline struct kernel_lb_addr lelb_to_cpu(struct lb_addr in)
 {
-	kernel_lb_addr out;
+	struct kernel_lb_addr out;
 
 	out.logicalBlockNum = le32_to_cpu(in.logicalBlockNum);
 	out.partitionReferenceNum = le16_to_cpu(in.partitionReferenceNum);
@@ -14,9 +14,9 @@ static inline kernel_lb_addr lelb_to_cpu(lb_addr in)
 	return out;
 }
 
-static inline lb_addr cpu_to_lelb(kernel_lb_addr in)
+static inline struct lb_addr cpu_to_lelb(struct kernel_lb_addr in)
 {
-	lb_addr out;
+	struct lb_addr out;
 
 	out.logicalBlockNum = cpu_to_le32(in.logicalBlockNum);
 	out.partitionReferenceNum = cpu_to_le16(in.partitionReferenceNum);
@@ -24,9 +24,9 @@ static inline lb_addr cpu_to_lelb(kernel_lb_addr in)
 	return out;
 }
 
-static inline short_ad lesa_to_cpu(short_ad in)
+static inline struct short_ad lesa_to_cpu(struct short_ad in)
 {
-	short_ad out;
+	struct short_ad out;
 
 	out.extLength = le32_to_cpu(in.extLength);
 	out.extPosition = le32_to_cpu(in.extPosition);
@@ -34,9 +34,9 @@ static inline short_ad lesa_to_cpu(short_ad in)
 	return out;
 }
 
-static inline short_ad cpu_to_lesa(short_ad in)
+static inline struct short_ad cpu_to_lesa(struct short_ad in)
 {
-	short_ad out;
+	struct short_ad out;
 
 	out.extLength = cpu_to_le32(in.extLength);
 	out.extPosition = cpu_to_le32(in.extPosition);
@@ -44,9 +44,9 @@ static inline short_ad cpu_to_lesa(short_ad in)
 	return out;
 }
 
-static inline kernel_long_ad lela_to_cpu(long_ad in)
+static inline struct kernel_long_ad lela_to_cpu(struct long_ad in)
 {
-	kernel_long_ad out;
+	struct kernel_long_ad out;
 
 	out.extLength = le32_to_cpu(in.extLength);
 	out.extLocation = lelb_to_cpu(in.extLocation);
@@ -54,9 +54,9 @@ static inline kernel_long_ad lela_to_cpu(long_ad in)
 	return out;
 }
 
-static inline long_ad cpu_to_lela(kernel_long_ad in)
+static inline struct long_ad cpu_to_lela(struct kernel_long_ad in)
 {
-	long_ad out;
+	struct long_ad out;
 
 	out.extLength = cpu_to_le32(in.extLength);
 	out.extLocation = cpu_to_lelb(in.extLocation);
@@ -64,9 +64,9 @@ static inline long_ad cpu_to_lela(kernel_long_ad in)
 	return out;
 }
 
-static inline kernel_extent_ad leea_to_cpu(extent_ad in)
+static inline struct kernel_extent_ad leea_to_cpu(struct extent_ad in)
 {
-	kernel_extent_ad out;
+	struct kernel_extent_ad out;
 
 	out.extLength = le32_to_cpu(in.extLength);
 	out.extLocation = le32_to_cpu(in.extLocation);
diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c
index 5f811655c9b5..b8c828c4d200 100644
--- a/fs/udf/udftime.c
+++ b/fs/udf/udftime.c
@@ -85,7 +85,8 @@ extern struct timezone sys_tz;
 #define SECS_PER_HOUR	(60 * 60)
 #define SECS_PER_DAY	(SECS_PER_HOUR * 24)
 
-struct timespec *udf_disk_stamp_to_time(struct timespec *dest, timestamp src)
+struct timespec *
+udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src)
 {
 	int yday;
 	u16 typeAndTimezone = le16_to_cpu(src.typeAndTimezone);
@@ -116,7 +117,8 @@ struct timespec *udf_disk_stamp_to_time(struct timespec *dest, timestamp src)
 	return dest;
 }
 
-timestamp *udf_time_to_disk_stamp(timestamp *dest, struct timespec ts)
+struct timestamp *
+udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts)
 {
 	long int days, rem, y;
 	const unsigned short int *ip;
diff --git a/fs/udf/unicode.c b/fs/udf/unicode.c
index 9fdf8c93c58e..cefa8c8913e6 100644
--- a/fs/udf/unicode.c
+++ b/fs/udf/unicode.c
@@ -254,7 +254,7 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o,
 {
 	const uint8_t *ocu;
 	uint8_t cmp_id, ocu_len;
-	int i;
+	int i, len;
 
 
 	ocu_len = ocu_i->u_len;
@@ -279,8 +279,13 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o,
 		if (cmp_id == 16)
 			c = (c << 8) | ocu[i++];
 
-		utf_o->u_len += nls->uni2char(c, &utf_o->u_name[utf_o->u_len],
-					      UDF_NAME_LEN - utf_o->u_len);
+		len = nls->uni2char(c, &utf_o->u_name[utf_o->u_len],
+				    UDF_NAME_LEN - utf_o->u_len);
+		/* Valid character? */
+		if (len >= 0)
+			utf_o->u_len += len;
+		else
+			utf_o->u_name[utf_o->u_len++] = '?';
 	}
 	utf_o->u_cmpID = 8;
 
@@ -290,7 +295,8 @@ static int udf_CS0toNLS(struct nls_table *nls, struct ustr *utf_o,
 static int udf_NLStoCS0(struct nls_table *nls, dstring *ocu, struct ustr *uni,
 			int length)
 {
-	unsigned len, i, max_val;
+	int len;
+	unsigned i, max_val;
 	uint16_t uni_char;
 	int u_len;
 
@@ -302,8 +308,13 @@ try_again:
 	u_len = 0U;
 	for (i = 0U; i < uni->u_len; i++) {
 		len = nls->char2uni(&uni->u_name[i], uni->u_len - i, &uni_char);
-		if (len <= 0)
+		if (!len)
 			continue;
+		/* Invalid character, deal with it */
+		if (len < 0) {
+			len = 1;
+			uni_char = '?';
+		}
 
 		if (uni_char > max_val) {
 			max_val = 0xffffU;
@@ -324,34 +335,43 @@ try_again:
 int udf_get_filename(struct super_block *sb, uint8_t *sname, uint8_t *dname,
 		     int flen)
 {
-	struct ustr filename, unifilename;
-	int len;
+	struct ustr *filename, *unifilename;
+	int len = 0;
 
-	if (udf_build_ustr_exact(&unifilename, sname, flen))
+	filename = kmalloc(sizeof(struct ustr), GFP_NOFS);
+	if (!filename)
 		return 0;
 
+	unifilename = kmalloc(sizeof(struct ustr), GFP_NOFS);
+	if (!unifilename)
+		goto out1;
+
+	if (udf_build_ustr_exact(unifilename, sname, flen))
+		goto out2;
+
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_UTF8)) {
-		if (!udf_CS0toUTF8(&filename, &unifilename)) {
+		if (!udf_CS0toUTF8(filename, unifilename)) {
 			udf_debug("Failed in udf_get_filename: sname = %s\n",
 				  sname);
-			return 0;
+			goto out2;
 		}
 	} else if (UDF_QUERY_FLAG(sb, UDF_FLAG_NLS_MAP)) {
-		if (!udf_CS0toNLS(UDF_SB(sb)->s_nls_map, &filename,
-				  &unifilename)) {
+		if (!udf_CS0toNLS(UDF_SB(sb)->s_nls_map, filename,
+				  unifilename)) {
 			udf_debug("Failed in udf_get_filename: sname = %s\n",
 				  sname);
-			return 0;
+			goto out2;
 		}
 	} else
-		return 0;
-
-	len = udf_translate_to_linux(dname, filename.u_name, filename.u_len,
-				     unifilename.u_name, unifilename.u_len);
-	if (len)
-		return len;
-
-	return 0;
+		goto out2;
+
+	len = udf_translate_to_linux(dname, filename->u_name, filename->u_len,
+				     unifilename->u_name, unifilename->u_len);
+out2:
+	kfree(unifilename);
+out1:
+	kfree(filename);
+	return len;
 }
 
 int udf_put_filename(struct super_block *sb, const uint8_t *sname,
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index e1c1fc5ee239..60359291761f 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -1268,6 +1268,7 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct ufs_super_block_first *usb1;
 	struct ufs_super_block_second *usb2;
 	struct ufs_super_block_third *usb3;
+	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 
 	lock_kernel();
 
@@ -1290,6 +1291,8 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 		? (buf->f_bfree - (((long)buf->f_blocks / 100) * uspi->s_minfree)) : 0;
 	buf->f_files = uspi->s_ncg * uspi->s_ipg;
 	buf->f_namelen = UFS_MAXNAMLEN;
+	buf->f_fsid.val[0] = (u32)id;
+	buf->f_fsid.val[1] = (u32)(id >> 32);
 
 	unlock_kernel();
 
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index c3dc491fff89..60f107e47fe9 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -33,6 +33,7 @@ xfs-$(CONFIG_XFS_QUOTA)		+= $(addprefix quota/, \
 				   xfs_qm_syscalls.o \
 				   xfs_qm_bhv.o \
 				   xfs_qm.o)
+xfs-$(CONFIG_XFS_QUOTA)		+= linux-2.6/xfs_quotaops.o
 
 ifeq ($(CONFIG_XFS_QUOTA),y)
 xfs-$(CONFIG_PROC_FS)		+= quota/xfs_qm_stats.o
diff --git a/fs/xfs/linux-2.6/mutex.h b/fs/xfs/linux-2.6/mutex.h
deleted file mode 100644
index 2a88d56c4dc2..000000000000
--- a/fs/xfs/linux-2.6/mutex.h
+++ /dev/null
@@ -1,25 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_SUPPORT_MUTEX_H__
-#define __XFS_SUPPORT_MUTEX_H__
-
-#include <linux/mutex.h>
-
-typedef struct mutex mutex_t;
-
-#endif /* __XFS_SUPPORT_MUTEX_H__ */
diff --git a/fs/xfs/linux-2.6/xfs_aops.c b/fs/xfs/linux-2.6/xfs_aops.c
index de3a198f771e..c13f67300fe7 100644
--- a/fs/xfs/linux-2.6/xfs_aops.c
+++ b/fs/xfs/linux-2.6/xfs_aops.c
@@ -1623,4 +1623,5 @@ const struct address_space_operations xfs_address_space_operations = {
 	.bmap			= xfs_vm_bmap,
 	.direct_IO		= xfs_vm_direct_IO,
 	.migratepage		= buffer_migrate_page,
+	.is_partially_uptodate  = block_is_partially_uptodate,
 };
diff --git a/fs/xfs/linux-2.6/xfs_ioctl.c b/fs/xfs/linux-2.6/xfs_ioctl.c
index 4bd112313f33..d0b499418a7d 100644
--- a/fs/xfs/linux-2.6/xfs_ioctl.c
+++ b/fs/xfs/linux-2.6/xfs_ioctl.c
@@ -34,6 +34,7 @@
 #include "xfs_dir2_sf.h"
 #include "xfs_dinode.h"
 #include "xfs_inode.h"
+#include "xfs_ioctl.h"
 #include "xfs_btree.h"
 #include "xfs_ialloc.h"
 #include "xfs_rtalloc.h"
@@ -78,92 +79,74 @@ xfs_find_handle(
 	int			hsize;
 	xfs_handle_t		handle;
 	struct inode		*inode;
+	struct file		*file = NULL;
+	struct path		path;
+	int			error;
+	struct xfs_inode	*ip;
 
-	memset((char *)&handle, 0, sizeof(handle));
-
-	switch (cmd) {
-	case XFS_IOC_PATH_TO_FSHANDLE:
-	case XFS_IOC_PATH_TO_HANDLE: {
-		struct path path;
-		int error = user_lpath((const char __user *)hreq->path, &path);
+	if (cmd == XFS_IOC_FD_TO_HANDLE) {
+		file = fget(hreq->fd);
+		if (!file)
+			return -EBADF;
+		inode = file->f_path.dentry->d_inode;
+	} else {
+		error = user_lpath((const char __user *)hreq->path, &path);
 		if (error)
 			return error;
-
-		ASSERT(path.dentry);
-		ASSERT(path.dentry->d_inode);
-		inode = igrab(path.dentry->d_inode);
-		path_put(&path);
-		break;
+		inode = path.dentry->d_inode;
 	}
+	ip = XFS_I(inode);
 
-	case XFS_IOC_FD_TO_HANDLE: {
-		struct file	*file;
-
-		file = fget(hreq->fd);
-		if (!file)
-		    return -EBADF;
+	/*
+	 * We can only generate handles for inodes residing on a XFS filesystem,
+	 * and only for regular files, directories or symbolic links.
+	 */
+	error = -EINVAL;
+	if (inode->i_sb->s_magic != XFS_SB_MAGIC)
+		goto out_put;
 
-		ASSERT(file->f_path.dentry);
-		ASSERT(file->f_path.dentry->d_inode);
-		inode = igrab(file->f_path.dentry->d_inode);
-		fput(file);
-		break;
-	}
+	error = -EBADF;
+	if (!S_ISREG(inode->i_mode) &&
+	    !S_ISDIR(inode->i_mode) &&
+	    !S_ISLNK(inode->i_mode))
+		goto out_put;
 
-	default:
-		ASSERT(0);
-		return -XFS_ERROR(EINVAL);
-	}
 
-	if (inode->i_sb->s_magic != XFS_SB_MAGIC) {
-		/* we're not in XFS anymore, Toto */
-		iput(inode);
-		return -XFS_ERROR(EINVAL);
-	}
+	memcpy(&handle.ha_fsid, ip->i_mount->m_fixedfsid, sizeof(xfs_fsid_t));
 
-	switch (inode->i_mode & S_IFMT) {
-	case S_IFREG:
-	case S_IFDIR:
-	case S_IFLNK:
-		break;
-	default:
-		iput(inode);
-		return -XFS_ERROR(EBADF);
-	}
-
-	/* now we can grab the fsid */
-	memcpy(&handle.ha_fsid, XFS_I(inode)->i_mount->m_fixedfsid,
-			sizeof(xfs_fsid_t));
-	hsize = sizeof(xfs_fsid_t);
-
-	if (cmd != XFS_IOC_PATH_TO_FSHANDLE) {
-		xfs_inode_t	*ip = XFS_I(inode);
+	if (cmd == XFS_IOC_PATH_TO_FSHANDLE) {
+		/*
+		 * This handle only contains an fsid, zero the rest.
+		 */
+		memset(&handle.ha_fid, 0, sizeof(handle.ha_fid));
+		hsize = sizeof(xfs_fsid_t);
+	} else {
 		int		lock_mode;
 
-		/* need to get access to the xfs_inode to read the generation */
 		lock_mode = xfs_ilock_map_shared(ip);
-
-		/* fill in fid section of handle from inode */
 		handle.ha_fid.fid_len = sizeof(xfs_fid_t) -
 					sizeof(handle.ha_fid.fid_len);
 		handle.ha_fid.fid_pad = 0;
 		handle.ha_fid.fid_gen = ip->i_d.di_gen;
 		handle.ha_fid.fid_ino = ip->i_ino;
-
 		xfs_iunlock_map_shared(ip, lock_mode);
 
 		hsize = XFS_HSIZE(handle);
 	}
 
-	/* now copy our handle into the user buffer & write out the size */
+	error = -EFAULT;
 	if (copy_to_user(hreq->ohandle, &handle, hsize) ||
-	    copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32))) {
-		iput(inode);
-		return -XFS_ERROR(EFAULT);
-	}
+	    copy_to_user(hreq->ohandlen, &hsize, sizeof(__s32)))
+		goto out_put;
 
-	iput(inode);
-	return 0;
+	error = 0;
+
+ out_put:
+	if (cmd == XFS_IOC_FD_TO_HANDLE)
+		fput(file);
+	else
+		path_put(&path);
+	return error;
 }
 
 /*
diff --git a/fs/xfs/linux-2.6/xfs_iops.c b/fs/xfs/linux-2.6/xfs_iops.c
index 7aa53fefc67f..6075382336d7 100644
--- a/fs/xfs/linux-2.6/xfs_iops.c
+++ b/fs/xfs/linux-2.6/xfs_iops.c
@@ -211,8 +211,13 @@ xfs_vn_mknod(
 	 * Irix uses Missed'em'V split, but doesn't want to see
 	 * the upper 5 bits of (14bit) major.
 	 */
-	if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
-		return -EINVAL;
+	if (S_ISCHR(mode) || S_ISBLK(mode)) {
+		if (unlikely(!sysv_valid_dev(rdev) || MAJOR(rdev) & ~0x1ff))
+			return -EINVAL;
+		rdev = sysv_encode_dev(rdev);
+	} else {
+		rdev = 0;
+	}
 
 	if (test_default_acl && test_default_acl(dir)) {
 		if (!_ACL_ALLOC(default_acl)) {
@@ -224,28 +229,11 @@ xfs_vn_mknod(
 		}
 	}
 
-	xfs_dentry_to_name(&name, dentry);
-
 	if (IS_POSIXACL(dir) && !default_acl)
-		mode &= ~current->fs->umask;
-
-	switch (mode & S_IFMT) {
-	case S_IFCHR:
-	case S_IFBLK:
-	case S_IFIFO:
-	case S_IFSOCK:
-		rdev = sysv_encode_dev(rdev);
-	case S_IFREG:
-		error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
-		break;
-	case S_IFDIR:
-		error = xfs_mkdir(XFS_I(dir), &name, mode, &ip, NULL);
-		break;
-	default:
-		error = EINVAL;
-		break;
-	}
+		mode &= ~current_umask();
 
+	xfs_dentry_to_name(&name, dentry);
+	error = xfs_create(XFS_I(dir), &name, mode, rdev, &ip, NULL);
 	if (unlikely(error))
 		goto out_free_acl;
 
@@ -416,7 +404,7 @@ xfs_vn_symlink(
 	mode_t		mode;
 
 	mode = S_IFLNK |
-		(irix_symlink_mode ? 0777 & ~current->fs->umask : S_IRWXUGO);
+		(irix_symlink_mode ? 0777 & ~current_umask() : S_IRWXUGO);
 	xfs_dentry_to_name(&name, dentry);
 
 	error = xfs_symlink(XFS_I(dir), &name, symname, mode, &cip, NULL);
@@ -553,9 +541,6 @@ xfs_vn_getattr(
 	stat->uid = ip->i_d.di_uid;
 	stat->gid = ip->i_d.di_gid;
 	stat->ino = ip->i_ino;
-#if XFS_BIG_INUMS
-	stat->ino += mp->m_inoadd;
-#endif
 	stat->atime = inode->i_atime;
 	stat->mtime.tv_sec = ip->i_d.di_mtime.t_sec;
 	stat->mtime.tv_nsec = ip->i_d.di_mtime.t_nsec;
diff --git a/fs/xfs/linux-2.6/xfs_linux.h b/fs/xfs/linux-2.6/xfs_linux.h
index 507492d6dccd..f65a53f8752f 100644
--- a/fs/xfs/linux-2.6/xfs_linux.h
+++ b/fs/xfs/linux-2.6/xfs_linux.h
@@ -38,7 +38,6 @@
 #include <kmem.h>
 #include <mrlock.h>
 #include <sv.h>
-#include <mutex.h>
 #include <time.h>
 
 #include <support/ktrace.h>
@@ -51,6 +50,7 @@
 #include <linux/blkdev.h>
 #include <linux/slab.h>
 #include <linux/module.h>
+#include <linux/mutex.h>
 #include <linux/file.h>
 #include <linux/swap.h>
 #include <linux/errno.h>
@@ -147,17 +147,6 @@
 #define SYNCHRONIZE()	barrier()
 #define __return_address __builtin_return_address(0)
 
-/*
- * IRIX (BSD) quotactl makes use of separate commands for user/group,
- * whereas on Linux the syscall encodes this information into the cmd
- * field (see the QCMD macro in quota.h).  These macros help keep the
- * code portable - they are not visible from the syscall interface.
- */
-#define Q_XSETGQLIM	XQM_CMD(8)	/* set groups disk limits */
-#define Q_XGETGQUOTA	XQM_CMD(9)	/* get groups disk limits */
-#define Q_XSETPQLIM	XQM_CMD(10)	/* set projects disk limits */
-#define Q_XGETPQUOTA	XQM_CMD(11)	/* get projects disk limits */
-
 #define dfltprid	0
 #define MAXPATHLEN	1024
 
diff --git a/fs/xfs/linux-2.6/xfs_quotaops.c b/fs/xfs/linux-2.6/xfs_quotaops.c
new file mode 100644
index 000000000000..94d9a633d3d9
--- /dev/null
+++ b/fs/xfs/linux-2.6/xfs_quotaops.c
@@ -0,0 +1,157 @@
+/*
+ * Copyright (c) 2008, Christoph Hellwig
+ * All Rights Reserved.
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License as
+ * published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
+ */
+#include "xfs.h"
+#include "xfs_dmapi.h"
+#include "xfs_sb.h"
+#include "xfs_inum.h"
+#include "xfs_ag.h"
+#include "xfs_mount.h"
+#include "xfs_quota.h"
+#include "xfs_log.h"
+#include "xfs_trans.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_inode.h"
+#include "quota/xfs_qm.h"
+#include <linux/quota.h>
+
+
+STATIC int
+xfs_quota_type(int type)
+{
+	switch (type) {
+	case USRQUOTA:
+		return XFS_DQ_USER;
+	case GRPQUOTA:
+		return XFS_DQ_GROUP;
+	default:
+		return XFS_DQ_PROJ;
+	}
+}
+
+STATIC int
+xfs_fs_quota_sync(
+	struct super_block	*sb,
+	int			type)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	return -xfs_sync_inodes(mp, SYNC_DELWRI);
+}
+
+STATIC int
+xfs_fs_get_xstate(
+	struct super_block	*sb,
+	struct fs_quota_stat	*fqs)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	return -xfs_qm_scall_getqstat(mp, fqs);
+}
+
+STATIC int
+xfs_fs_set_xstate(
+	struct super_block	*sb,
+	unsigned int		uflags,
+	int			op)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+	unsigned int		flags = 0;
+
+	if (sb->s_flags & MS_RDONLY)
+		return -EROFS;
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (uflags & XFS_QUOTA_UDQ_ACCT)
+		flags |= XFS_UQUOTA_ACCT;
+	if (uflags & XFS_QUOTA_PDQ_ACCT)
+		flags |= XFS_PQUOTA_ACCT;
+	if (uflags & XFS_QUOTA_GDQ_ACCT)
+		flags |= XFS_GQUOTA_ACCT;
+	if (uflags & XFS_QUOTA_UDQ_ENFD)
+		flags |= XFS_UQUOTA_ENFD;
+	if (uflags & (XFS_QUOTA_PDQ_ENFD|XFS_QUOTA_GDQ_ENFD))
+		flags |= XFS_OQUOTA_ENFD;
+
+	switch (op) {
+	case Q_XQUOTAON:
+		return -xfs_qm_scall_quotaon(mp, flags);
+	case Q_XQUOTAOFF:
+		if (!XFS_IS_QUOTA_ON(mp))
+			return -EINVAL;
+		return -xfs_qm_scall_quotaoff(mp, flags);
+	case Q_XQUOTARM:
+		if (XFS_IS_QUOTA_ON(mp))
+			return -EINVAL;
+		return -xfs_qm_scall_trunc_qfiles(mp, flags);
+	}
+
+	return -EINVAL;
+}
+
+STATIC int
+xfs_fs_get_xquota(
+	struct super_block	*sb,
+	int			type,
+	qid_t			id,
+	struct fs_disk_quota	*fdq)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ESRCH;
+
+	return -xfs_qm_scall_getquota(mp, id, xfs_quota_type(type), fdq);
+}
+
+STATIC int
+xfs_fs_set_xquota(
+	struct super_block	*sb,
+	int			type,
+	qid_t			id,
+	struct fs_disk_quota	*fdq)
+{
+	struct xfs_mount	*mp = XFS_M(sb);
+
+	if (sb->s_flags & MS_RDONLY)
+		return -EROFS;
+	if (!XFS_IS_QUOTA_RUNNING(mp))
+		return -ENOSYS;
+	if (!XFS_IS_QUOTA_ON(mp))
+		return -ESRCH;
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return -xfs_qm_scall_setqlim(mp, id, xfs_quota_type(type), fdq);
+}
+
+struct quotactl_ops xfs_quotactl_operations = {
+	.quota_sync		= xfs_fs_quota_sync,
+	.get_xstate		= xfs_fs_get_xstate,
+	.set_xstate		= xfs_fs_set_xstate,
+	.get_xquota		= xfs_fs_get_xquota,
+	.set_xquota		= xfs_fs_set_xquota,
+};
diff --git a/fs/xfs/linux-2.6/xfs_super.c b/fs/xfs/linux-2.6/xfs_super.c
index 32ae5028e96b..bb685269f832 100644
--- a/fs/xfs/linux-2.6/xfs_super.c
+++ b/fs/xfs/linux-2.6/xfs_super.c
@@ -68,7 +68,6 @@
 #include <linux/freezer.h>
 #include <linux/parser.h>
 
-static struct quotactl_ops xfs_quotactl_operations;
 static struct super_operations xfs_super_operations;
 static kmem_zone_t *xfs_ioend_zone;
 mempool_t *xfs_ioend_pool;
@@ -79,7 +78,6 @@ mempool_t *xfs_ioend_pool;
 #define MNTOPT_RTDEV	"rtdev"		/* realtime I/O device */
 #define MNTOPT_BIOSIZE	"biosize"	/* log2 of preferred buffered io size */
 #define MNTOPT_WSYNC	"wsync"		/* safe-mode nfs compatible mount */
-#define MNTOPT_INO64	"ino64"		/* force inodes into 64-bit range */
 #define MNTOPT_NOALIGN	"noalign"	/* turn off stripe alignment */
 #define MNTOPT_SWALLOC	"swalloc"	/* turn on stripe width allocation */
 #define MNTOPT_SUNIT	"sunit"		/* data volume stripe unit */
@@ -180,7 +178,7 @@ xfs_parseargs(
 	int			dswidth = 0;
 	int			iosize = 0;
 	int			dmapi_implies_ikeep = 1;
-	uchar_t			iosizelog = 0;
+	__uint8_t		iosizelog = 0;
 
 	/*
 	 * Copy binary VFS mount flags we are interested in.
@@ -291,16 +289,6 @@ xfs_parseargs(
 			mp->m_flags |= XFS_MOUNT_OSYNCISOSYNC;
 		} else if (!strcmp(this_char, MNTOPT_NORECOVERY)) {
 			mp->m_flags |= XFS_MOUNT_NORECOVERY;
-		} else if (!strcmp(this_char, MNTOPT_INO64)) {
-#if XFS_BIG_INUMS
-			mp->m_flags |= XFS_MOUNT_INO64;
-			mp->m_inoadd = XFS_INO64_OFFSET;
-#else
-			cmn_err(CE_WARN,
-				"XFS: %s option not allowed on this system",
-				this_char);
-			return EINVAL;
-#endif
 		} else if (!strcmp(this_char, MNTOPT_NOALIGN)) {
 			mp->m_flags |= XFS_MOUNT_NOALIGN;
 		} else if (!strcmp(this_char, MNTOPT_SWALLOC)) {
@@ -529,7 +517,6 @@ xfs_showargs(
 		/* the few simple ones we can get from the mount struct */
 		{ XFS_MOUNT_IKEEP,		"," MNTOPT_IKEEP },
 		{ XFS_MOUNT_WSYNC,		"," MNTOPT_WSYNC },
-		{ XFS_MOUNT_INO64,		"," MNTOPT_INO64 },
 		{ XFS_MOUNT_NOALIGN,		"," MNTOPT_NOALIGN },
 		{ XFS_MOUNT_SWALLOC,		"," MNTOPT_SWALLOC },
 		{ XFS_MOUNT_NOUUID,		"," MNTOPT_NOUUID },
@@ -634,7 +621,7 @@ xfs_max_file_offset(
 	return (((__uint64_t)pagefactor) << bitshift) - 1;
 }
 
-int
+STATIC int
 xfs_blkdev_get(
 	xfs_mount_t		*mp,
 	const char		*name,
@@ -651,7 +638,7 @@ xfs_blkdev_get(
 	return -error;
 }
 
-void
+STATIC void
 xfs_blkdev_put(
 	struct block_device	*bdev)
 {
@@ -872,7 +859,7 @@ xfsaild_wakeup(
 	wake_up_process(ailp->xa_task);
 }
 
-int
+STATIC int
 xfsaild(
 	void	*data)
 {
@@ -990,26 +977,57 @@ xfs_fs_write_inode(
 	int			sync)
 {
 	struct xfs_inode	*ip = XFS_I(inode);
+	struct xfs_mount	*mp = ip->i_mount;
 	int			error = 0;
-	int			flags = 0;
 
 	xfs_itrace_entry(ip);
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return XFS_ERROR(EIO);
+
 	if (sync) {
 		error = xfs_wait_on_pages(ip, 0, -1);
 		if (error)
-			goto out_error;
-		flags |= FLUSH_SYNC;
+			goto out;
 	}
-	error = xfs_inode_flush(ip, flags);
 
-out_error:
+	/*
+	 * Bypass inodes which have already been cleaned by
+	 * the inode flush clustering code inside xfs_iflush
+	 */
+	if (xfs_inode_clean(ip))
+		goto out;
+
+	/*
+	 * We make this non-blocking if the inode is contended, return
+	 * EAGAIN to indicate to the caller that they did not succeed.
+	 * This prevents the flush path from blocking on inodes inside
+	 * another operation right now, they get caught later by xfs_sync.
+	 */
+	if (sync) {
+		xfs_ilock(ip, XFS_ILOCK_SHARED);
+		xfs_iflock(ip);
+
+		error = xfs_iflush(ip, XFS_IFLUSH_SYNC);
+	} else {
+		error = EAGAIN;
+		if (!xfs_ilock_nowait(ip, XFS_ILOCK_SHARED))
+			goto out;
+		if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip))
+			goto out_unlock;
+
+		error = xfs_iflush(ip, XFS_IFLUSH_ASYNC_NOBLOCK);
+	}
+
+ out_unlock:
+	xfs_iunlock(ip, XFS_ILOCK_SHARED);
+ out:
 	/*
 	 * if we failed to write out the inode then mark
 	 * it dirty again so we'll try again later.
 	 */
 	if (error)
 		xfs_mark_inode_dirty_sync(ip);
-
 	return -error;
 }
 
@@ -1169,18 +1187,12 @@ xfs_fs_statfs(
 	statp->f_bfree = statp->f_bavail =
 				sbp->sb_fdblocks - XFS_ALLOC_SET_ASIDE(mp);
 	fakeinos = statp->f_bfree << sbp->sb_inopblog;
-#if XFS_BIG_INUMS
-	fakeinos += mp->m_inoadd;
-#endif
 	statp->f_files =
 	    MIN(sbp->sb_icount + fakeinos, (__uint64_t)XFS_MAXINUMBER);
 	if (mp->m_maxicount)
-#if XFS_BIG_INUMS
-		if (!mp->m_inoadd)
-#endif
-			statp->f_files = min_t(typeof(statp->f_files),
-						statp->f_files,
-						mp->m_maxicount);
+		statp->f_files = min_t(typeof(statp->f_files),
+					statp->f_files,
+					mp->m_maxicount);
 	statp->f_ffree = statp->f_files - (sbp->sb_icount - sbp->sb_ifree);
 	spin_unlock(&mp->m_sb_lock);
 
@@ -1302,57 +1314,6 @@ xfs_fs_show_options(
 	return -xfs_showargs(XFS_M(mnt->mnt_sb), m);
 }
 
-STATIC int
-xfs_fs_quotasync(
-	struct super_block	*sb,
-	int			type)
-{
-	return -XFS_QM_QUOTACTL(XFS_M(sb), Q_XQUOTASYNC, 0, NULL);
-}
-
-STATIC int
-xfs_fs_getxstate(
-	struct super_block	*sb,
-	struct fs_quota_stat	*fqs)
-{
-	return -XFS_QM_QUOTACTL(XFS_M(sb), Q_XGETQSTAT, 0, (caddr_t)fqs);
-}
-
-STATIC int
-xfs_fs_setxstate(
-	struct super_block	*sb,
-	unsigned int		flags,
-	int			op)
-{
-	return -XFS_QM_QUOTACTL(XFS_M(sb), op, 0, (caddr_t)&flags);
-}
-
-STATIC int
-xfs_fs_getxquota(
-	struct super_block	*sb,
-	int			type,
-	qid_t			id,
-	struct fs_disk_quota	*fdq)
-{
-	return -XFS_QM_QUOTACTL(XFS_M(sb),
-				 (type == USRQUOTA) ? Q_XGETQUOTA :
-				  ((type == GRPQUOTA) ? Q_XGETGQUOTA :
-				   Q_XGETPQUOTA), id, (caddr_t)fdq);
-}
-
-STATIC int
-xfs_fs_setxquota(
-	struct super_block	*sb,
-	int			type,
-	qid_t			id,
-	struct fs_disk_quota	*fdq)
-{
-	return -XFS_QM_QUOTACTL(XFS_M(sb),
-				 (type == USRQUOTA) ? Q_XSETQLIM :
-				  ((type == GRPQUOTA) ? Q_XSETGQLIM :
-				   Q_XSETPQLIM), id, (caddr_t)fdq);
-}
-
 /*
  * This function fills in xfs_mount_t fields based on mount args.
  * Note: the superblock _has_ now been read in.
@@ -1435,7 +1396,9 @@ xfs_fs_fill_super(
 	sb_min_blocksize(sb, BBSIZE);
 	sb->s_xattr = xfs_xattr_handlers;
 	sb->s_export_op = &xfs_export_operations;
+#ifdef CONFIG_XFS_QUOTA
 	sb->s_qcop = &xfs_quotactl_operations;
+#endif
 	sb->s_op = &xfs_super_operations;
 
 	error = xfs_dmops_get(mp);
@@ -1578,14 +1541,6 @@ static struct super_operations xfs_super_operations = {
 	.show_options		= xfs_fs_show_options,
 };
 
-static struct quotactl_ops xfs_quotactl_operations = {
-	.quota_sync		= xfs_fs_quotasync,
-	.get_xstate		= xfs_fs_getxstate,
-	.set_xstate		= xfs_fs_setxstate,
-	.get_xquota		= xfs_fs_getxquota,
-	.set_xquota		= xfs_fs_setxquota,
-};
-
 static struct file_system_type xfs_fs_type = {
 	.owner			= THIS_MODULE,
 	.name			= "xfs",
diff --git a/fs/xfs/linux-2.6/xfs_super.h b/fs/xfs/linux-2.6/xfs_super.h
index d5d776d4cd67..5a2ea3a21781 100644
--- a/fs/xfs/linux-2.6/xfs_super.h
+++ b/fs/xfs/linux-2.6/xfs_super.h
@@ -93,6 +93,7 @@ extern void xfs_blkdev_issue_flush(struct xfs_buftarg *);
 
 extern const struct export_operations xfs_export_operations;
 extern struct xattr_handler *xfs_xattr_handlers[];
+extern struct quotactl_ops xfs_quotactl_operations;
 
 #define XFS_M(sb)		((struct xfs_mount *)((sb)->s_fs_info))
 
diff --git a/fs/xfs/linux-2.6/xfs_sync.h b/fs/xfs/linux-2.6/xfs_sync.h
index 5f6de1efe1f6..04f058c848ae 100644
--- a/fs/xfs/linux-2.6/xfs_sync.h
+++ b/fs/xfs/linux-2.6/xfs_sync.h
@@ -19,6 +19,7 @@
 #define XFS_SYNC_H 1
 
 struct xfs_mount;
+struct xfs_perag;
 
 typedef struct bhv_vfs_sync_work {
 	struct list_head	w_list;
diff --git a/fs/xfs/linux-2.6/xfs_vnode.h b/fs/xfs/linux-2.6/xfs_vnode.h
index f65983a230d3..ad7fbead4c97 100644
--- a/fs/xfs/linux-2.6/xfs_vnode.h
+++ b/fs/xfs/linux-2.6/xfs_vnode.h
@@ -41,11 +41,6 @@ struct attrlist_cursor_kern;
 #define IO_INVIS	0x00020		/* don't update inode timestamps */
 
 /*
- * Flags for xfs_inode_flush
- */
-#define FLUSH_SYNC		1	/* wait for flush to complete	*/
-
-/*
  * Flush/Invalidate options for vop_toss/flush/flushinval_pages.
  */
 #define FI_NONE			0	/* none */
@@ -55,33 +50,6 @@ struct attrlist_cursor_kern;
 					   the operation completes. */
 
 /*
- * Dealing with bad inodes
- */
-static inline int VN_BAD(struct inode *vp)
-{
-	return is_bad_inode(vp);
-}
-
-/*
- * Extracting atime values in various formats
- */
-static inline void vn_atime_to_bstime(struct inode *vp, xfs_bstime_t *bs_atime)
-{
-	bs_atime->tv_sec = vp->i_atime.tv_sec;
-	bs_atime->tv_nsec = vp->i_atime.tv_nsec;
-}
-
-static inline void vn_atime_to_timespec(struct inode *vp, struct timespec *ts)
-{
-	*ts = vp->i_atime;
-}
-
-static inline void vn_atime_to_time_t(struct inode *vp, time_t *tt)
-{
-	*tt = vp->i_atime.tv_sec;
-}
-
-/*
  * Some useful predicates.
  */
 #define VN_MAPPED(vp)	mapping_mapped(vp->i_mapping)
diff --git a/fs/xfs/quota/xfs_dquot.c b/fs/xfs/quota/xfs_dquot.c
index 6543c0b29753..e4babcc63423 100644
--- a/fs/xfs/quota/xfs_dquot.c
+++ b/fs/xfs/quota/xfs_dquot.c
@@ -804,7 +804,7 @@ xfs_qm_dqlookup(
 	uint			flist_locked;
 	xfs_dquot_t		*d;
 
-	ASSERT(XFS_DQ_IS_HASH_LOCKED(qh));
+	ASSERT(mutex_is_locked(&qh->qh_lock));
 
 	flist_locked = B_FALSE;
 
@@ -877,7 +877,7 @@ xfs_qm_dqlookup(
 			/*
 			 * move the dquot to the front of the hashchain
 			 */
-			ASSERT(XFS_DQ_IS_HASH_LOCKED(qh));
+			ASSERT(mutex_is_locked(&qh->qh_lock));
 			if (dqp->HL_PREVP != &qh->qh_next) {
 				xfs_dqtrace_entry(dqp,
 						  "DQLOOKUP: HASH MOVETOFRONT");
@@ -892,13 +892,13 @@ xfs_qm_dqlookup(
 			}
 			xfs_dqtrace_entry(dqp, "LOOKUP END");
 			*O_dqpp = dqp;
-			ASSERT(XFS_DQ_IS_HASH_LOCKED(qh));
+			ASSERT(mutex_is_locked(&qh->qh_lock));
 			return (0);
 		}
 	}
 
 	*O_dqpp = NULL;
-	ASSERT(XFS_DQ_IS_HASH_LOCKED(qh));
+	ASSERT(mutex_is_locked(&qh->qh_lock));
 	return (1);
 }
 
@@ -956,7 +956,7 @@ xfs_qm_dqget(
 			ASSERT(ip->i_gdquot == NULL);
 	}
 #endif
-	XFS_DQ_HASH_LOCK(h);
+	mutex_lock(&h->qh_lock);
 
 	/*
 	 * Look in the cache (hashtable).
@@ -971,7 +971,7 @@ xfs_qm_dqget(
 		 */
 		ASSERT(*O_dqpp);
 		ASSERT(XFS_DQ_IS_LOCKED(*O_dqpp));
-		XFS_DQ_HASH_UNLOCK(h);
+		mutex_unlock(&h->qh_lock);
 		xfs_dqtrace_entry(*O_dqpp, "DQGET DONE (FROM CACHE)");
 		return (0);	/* success */
 	}
@@ -991,7 +991,7 @@ xfs_qm_dqget(
 	 * we don't keep the lock across a disk read
 	 */
 	version = h->qh_version;
-	XFS_DQ_HASH_UNLOCK(h);
+	mutex_unlock(&h->qh_lock);
 
 	/*
 	 * Allocate the dquot on the kernel heap, and read the ondisk
@@ -1056,7 +1056,7 @@ xfs_qm_dqget(
 	/*
 	 * Hashlock comes after ilock in lock order
 	 */
-	XFS_DQ_HASH_LOCK(h);
+	mutex_lock(&h->qh_lock);
 	if (version != h->qh_version) {
 		xfs_dquot_t *tmpdqp;
 		/*
@@ -1072,7 +1072,7 @@ xfs_qm_dqget(
 			 * and start over.
 			 */
 			xfs_qm_dqput(tmpdqp);
-			XFS_DQ_HASH_UNLOCK(h);
+			mutex_unlock(&h->qh_lock);
 			xfs_qm_dqdestroy(dqp);
 			XQM_STATS_INC(xqmstats.xs_qm_dquot_dups);
 			goto again;
@@ -1083,7 +1083,7 @@ xfs_qm_dqget(
 	 * Put the dquot at the beginning of the hash-chain and mp's list
 	 * LOCK ORDER: hashlock, freelistlock, mplistlock, udqlock, gdqlock ..
 	 */
-	ASSERT(XFS_DQ_IS_HASH_LOCKED(h));
+	ASSERT(mutex_is_locked(&h->qh_lock));
 	dqp->q_hash = h;
 	XQM_HASHLIST_INSERT(h, dqp);
 
@@ -1102,7 +1102,7 @@ xfs_qm_dqget(
 	XQM_MPLIST_INSERT(&(XFS_QI_MPL_LIST(mp)), dqp);
 
 	xfs_qm_mplist_unlock(mp);
-	XFS_DQ_HASH_UNLOCK(h);
+	mutex_unlock(&h->qh_lock);
  dqret:
 	ASSERT((ip == NULL) || xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	xfs_dqtrace_entry(dqp, "DQGET DONE");
@@ -1440,7 +1440,7 @@ xfs_qm_dqpurge(
 	xfs_mount_t	*mp = dqp->q_mount;
 
 	ASSERT(XFS_QM_IS_MPLIST_LOCKED(mp));
-	ASSERT(XFS_DQ_IS_HASH_LOCKED(dqp->q_hash));
+	ASSERT(mutex_is_locked(&dqp->q_hash->qh_lock));
 
 	xfs_dqlock(dqp);
 	/*
@@ -1453,7 +1453,7 @@ xfs_qm_dqpurge(
 	 */
 	if (dqp->q_nrefs != 0) {
 		xfs_dqunlock(dqp);
-		XFS_DQ_HASH_UNLOCK(dqp->q_hash);
+		mutex_unlock(&dqp->q_hash->qh_lock);
 		return (1);
 	}
 
@@ -1517,7 +1517,7 @@ xfs_qm_dqpurge(
 	memset(&dqp->q_core, 0, sizeof(dqp->q_core));
 	xfs_dqfunlock(dqp);
 	xfs_dqunlock(dqp);
-	XFS_DQ_HASH_UNLOCK(thishash);
+	mutex_unlock(&thishash->qh_lock);
 	return (0);
 }
 
diff --git a/fs/xfs/quota/xfs_dquot.h b/fs/xfs/quota/xfs_dquot.h
index d443e93b4331..de0f402ddb4c 100644
--- a/fs/xfs/quota/xfs_dquot.h
+++ b/fs/xfs/quota/xfs_dquot.h
@@ -34,7 +34,7 @@
  */
 typedef struct xfs_dqhash {
 	struct xfs_dquot *qh_next;
-	mutex_t		  qh_lock;
+	struct mutex	  qh_lock;
 	uint		  qh_version;	/* ever increasing version */
 	uint		  qh_nelems;	/* number of dquots on the list */
 } xfs_dqhash_t;
@@ -81,7 +81,7 @@ typedef struct xfs_dquot {
 	xfs_qcnt_t	 q_res_bcount;	/* total regular nblks used+reserved */
 	xfs_qcnt_t	 q_res_icount;	/* total inos allocd+reserved */
 	xfs_qcnt_t	 q_res_rtbcount;/* total realtime blks used+reserved */
-	mutex_t		 q_qlock;	/* quota lock */
+	struct mutex	 q_qlock;	/* quota lock */
 	struct completion q_flush;	/* flush completion queue */
 	atomic_t          q_pincount;	/* dquot pin count */
 	wait_queue_head_t q_pinwait;	/* dquot pinning wait queue */
@@ -109,19 +109,6 @@ enum {
 
 #define XFS_DQHOLD(dqp)		((dqp)->q_nrefs++)
 
-#ifdef DEBUG
-static inline int
-XFS_DQ_IS_LOCKED(xfs_dquot_t *dqp)
-{
-	if (mutex_trylock(&dqp->q_qlock)) {
-		mutex_unlock(&dqp->q_qlock);
-		return 0;
-	}
-	return 1;
-}
-#endif
-
-
 /*
  * Manage the q_flush completion queue embedded in the dquot.  This completion
  * queue synchronizes processes attempting to flush the in-core dquot back to
@@ -142,6 +129,7 @@ static inline void xfs_dqfunlock(xfs_dquot_t *dqp)
 	complete(&dqp->q_flush);
 }
 
+#define XFS_DQ_IS_LOCKED(dqp)	(mutex_is_locked(&((dqp)->q_qlock)))
 #define XFS_DQ_IS_ON_FREELIST(dqp)  ((dqp)->dq_flnext != (dqp))
 #define XFS_DQ_IS_DIRTY(dqp)	((dqp)->dq_flags & XFS_DQ_DIRTY)
 #define XFS_QM_ISUDQ(dqp)	((dqp)->dq_flags & XFS_DQ_USER)
diff --git a/fs/xfs/quota/xfs_qm.c b/fs/xfs/quota/xfs_qm.c
index 7a2beb64314f..5b6695049e00 100644
--- a/fs/xfs/quota/xfs_qm.c
+++ b/fs/xfs/quota/xfs_qm.c
@@ -55,7 +55,7 @@
  * quota functionality, including maintaining the freelist and hash
  * tables of dquots.
  */
-mutex_t		xfs_Gqm_lock;
+struct mutex	xfs_Gqm_lock;
 struct xfs_qm	*xfs_Gqm;
 uint		ndquot;
 
@@ -69,8 +69,6 @@ STATIC void	xfs_qm_list_destroy(xfs_dqlist_t *);
 
 STATIC void	xfs_qm_freelist_init(xfs_frlist_t *);
 STATIC void	xfs_qm_freelist_destroy(xfs_frlist_t *);
-STATIC int	xfs_qm_mplist_nowait(xfs_mount_t *);
-STATIC int	xfs_qm_dqhashlock_nowait(xfs_dquot_t *);
 
 STATIC int	xfs_qm_init_quotainos(xfs_mount_t *);
 STATIC int	xfs_qm_init_quotainfo(xfs_mount_t *);
@@ -82,7 +80,7 @@ static struct shrinker xfs_qm_shaker = {
 };
 
 #ifdef DEBUG
-extern mutex_t	qcheck_lock;
+extern struct mutex	qcheck_lock;
 #endif
 
 #ifdef QUOTADEBUG
@@ -219,7 +217,7 @@ xfs_qm_hold_quotafs_ref(
 	 * the structure could disappear between the entry to this routine and
 	 * a HOLD operation if not locked.
 	 */
-	XFS_QM_LOCK(xfs_Gqm);
+	mutex_lock(&xfs_Gqm_lock);
 
 	if (xfs_Gqm == NULL)
 		xfs_Gqm = xfs_Gqm_init();
@@ -228,8 +226,8 @@ xfs_qm_hold_quotafs_ref(
 	 * debugging and statistical purposes, but ...
 	 * Just take a reference and get out.
 	 */
-	XFS_QM_HOLD(xfs_Gqm);
-	XFS_QM_UNLOCK(xfs_Gqm);
+	xfs_Gqm->qm_nrefs++;
+	mutex_unlock(&xfs_Gqm_lock);
 
 	return 0;
 }
@@ -277,13 +275,12 @@ xfs_qm_rele_quotafs_ref(
 	 * Destroy the entire XQM. If somebody mounts with quotaon, this'll
 	 * be restarted.
 	 */
-	XFS_QM_LOCK(xfs_Gqm);
-	XFS_QM_RELE(xfs_Gqm);
-	if (xfs_Gqm->qm_nrefs == 0) {
+	mutex_lock(&xfs_Gqm_lock);
+	if (--xfs_Gqm->qm_nrefs == 0) {
 		xfs_qm_destroy(xfs_Gqm);
 		xfs_Gqm = NULL;
 	}
-	XFS_QM_UNLOCK(xfs_Gqm);
+	mutex_unlock(&xfs_Gqm_lock);
 }
 
 /*
@@ -577,10 +574,10 @@ xfs_qm_dqpurge_int(
 			continue;
 		}
 
-		if (! xfs_qm_dqhashlock_nowait(dqp)) {
+		if (!mutex_trylock(&dqp->q_hash->qh_lock)) {
 			nrecl = XFS_QI_MPLRECLAIMS(mp);
 			xfs_qm_mplist_unlock(mp);
-			XFS_DQ_HASH_LOCK(dqp->q_hash);
+			mutex_lock(&dqp->q_hash->qh_lock);
 			xfs_qm_mplist_lock(mp);
 
 			/*
@@ -590,7 +587,7 @@ xfs_qm_dqpurge_int(
 			 * this point, but somebody might be taking things off.
 			 */
 			if (nrecl != XFS_QI_MPLRECLAIMS(mp)) {
-				XFS_DQ_HASH_UNLOCK(dqp->q_hash);
+				mutex_unlock(&dqp->q_hash->qh_lock);
 				goto again;
 			}
 		}
@@ -632,7 +629,6 @@ xfs_qm_dqattach_one(
 	xfs_dqid_t	id,
 	uint		type,
 	uint		doalloc,
-	uint		dolock,
 	xfs_dquot_t	*udqhint, /* hint */
 	xfs_dquot_t	**IO_idqpp)
 {
@@ -641,16 +637,16 @@ xfs_qm_dqattach_one(
 
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 	error = 0;
+
 	/*
 	 * See if we already have it in the inode itself. IO_idqpp is
 	 * &i_udquot or &i_gdquot. This made the code look weird, but
 	 * made the logic a lot simpler.
 	 */
-	if ((dqp = *IO_idqpp)) {
-		if (dolock)
-			xfs_dqlock(dqp);
+	dqp = *IO_idqpp;
+	if (dqp) {
 		xfs_dqtrace_entry(dqp, "DQATTACH: found in ip");
-		goto done;
+		return 0;
 	}
 
 	/*
@@ -659,38 +655,38 @@ xfs_qm_dqattach_one(
 	 * lookup by dqid (xfs_qm_dqget) by caching a group dquot inside
 	 * the user dquot.
 	 */
-	ASSERT(!udqhint || type == XFS_DQ_GROUP || type == XFS_DQ_PROJ);
-	if (udqhint && !dolock)
+	if (udqhint) {
+		ASSERT(type == XFS_DQ_GROUP || type == XFS_DQ_PROJ);
 		xfs_dqlock(udqhint);
 
-	/*
-	 * No need to take dqlock to look at the id.
-	 * The ID can't change until it gets reclaimed, and it won't
-	 * be reclaimed as long as we have a ref from inode and we hold
-	 * the ilock.
-	 */
-	if (udqhint &&
-	    (dqp = udqhint->q_gdquot) &&
-	    (be32_to_cpu(dqp->q_core.d_id) == id)) {
-		ASSERT(XFS_DQ_IS_LOCKED(udqhint));
-		xfs_dqlock(dqp);
-		XFS_DQHOLD(dqp);
-		ASSERT(*IO_idqpp == NULL);
-		*IO_idqpp = dqp;
-		if (!dolock) {
+		/*
+		 * No need to take dqlock to look at the id.
+		 *
+		 * The ID can't change until it gets reclaimed, and it won't
+		 * be reclaimed as long as we have a ref from inode and we
+		 * hold the ilock.
+		 */
+		dqp = udqhint->q_gdquot;
+		if (dqp && be32_to_cpu(dqp->q_core.d_id) == id) {
+			xfs_dqlock(dqp);
+			XFS_DQHOLD(dqp);
+			ASSERT(*IO_idqpp == NULL);
+			*IO_idqpp = dqp;
+
 			xfs_dqunlock(dqp);
 			xfs_dqunlock(udqhint);
+			return 0;
 		}
-		goto done;
-	}
-	/*
-	 * We can't hold a dquot lock when we call the dqget code.
-	 * We'll deadlock in no time, because of (not conforming to)
-	 * lock ordering - the inodelock comes before any dquot lock,
-	 * and we may drop and reacquire the ilock in xfs_qm_dqget().
-	 */
-	if (udqhint)
+
+		/*
+		 * We can't hold a dquot lock when we call the dqget code.
+		 * We'll deadlock in no time, because of (not conforming to)
+		 * lock ordering - the inodelock comes before any dquot lock,
+		 * and we may drop and reacquire the ilock in xfs_qm_dqget().
+		 */
 		xfs_dqunlock(udqhint);
+	}
+
 	/*
 	 * Find the dquot from somewhere. This bumps the
 	 * reference count of dquot and returns it locked.
@@ -698,48 +694,19 @@ xfs_qm_dqattach_one(
 	 * disk and we didn't ask it to allocate;
 	 * ESRCH if quotas got turned off suddenly.
 	 */
-	if ((error = xfs_qm_dqget(ip->i_mount, ip, id, type,
-				 doalloc|XFS_QMOPT_DOWARN, &dqp))) {
-		if (udqhint && dolock)
-			xfs_dqlock(udqhint);
-		goto done;
-	}
+	error = xfs_qm_dqget(ip->i_mount, ip, id, type, XFS_QMOPT_DOWARN, &dqp);
+	if (error)
+		return error;
 
 	xfs_dqtrace_entry(dqp, "DQATTACH: found by dqget");
+
 	/*
 	 * dqget may have dropped and re-acquired the ilock, but it guarantees
 	 * that the dquot returned is the one that should go in the inode.
 	 */
 	*IO_idqpp = dqp;
-	ASSERT(dqp);
-	ASSERT(XFS_DQ_IS_LOCKED(dqp));
-	if (! dolock) {
-		xfs_dqunlock(dqp);
-		goto done;
-	}
-	if (! udqhint)
-		goto done;
-
-	ASSERT(udqhint);
-	ASSERT(dolock);
-	ASSERT(XFS_DQ_IS_LOCKED(dqp));
-	if (! xfs_qm_dqlock_nowait(udqhint)) {
-		xfs_dqunlock(dqp);
-		xfs_dqlock(udqhint);
-		xfs_dqlock(dqp);
-	}
-      done:
-#ifdef QUOTADEBUG
-	if (udqhint) {
-		if (dolock)
-			ASSERT(XFS_DQ_IS_LOCKED(udqhint));
-	}
-	if (! error) {
-		if (dolock)
-			ASSERT(XFS_DQ_IS_LOCKED(dqp));
-	}
-#endif
-	return error;
+	xfs_dqunlock(dqp);
+	return 0;
 }
 
 
@@ -754,24 +721,15 @@ xfs_qm_dqattach_one(
 STATIC void
 xfs_qm_dqattach_grouphint(
 	xfs_dquot_t	*udq,
-	xfs_dquot_t	*gdq,
-	uint		locked)
+	xfs_dquot_t	*gdq)
 {
 	xfs_dquot_t	*tmp;
 
-#ifdef QUOTADEBUG
-	if (locked) {
-		ASSERT(XFS_DQ_IS_LOCKED(udq));
-		ASSERT(XFS_DQ_IS_LOCKED(gdq));
-	}
-#endif
-	if (! locked)
-		xfs_dqlock(udq);
+	xfs_dqlock(udq);
 
 	if ((tmp = udq->q_gdquot)) {
 		if (tmp == gdq) {
-			if (! locked)
-				xfs_dqunlock(udq);
+			xfs_dqunlock(udq);
 			return;
 		}
 
@@ -781,8 +739,6 @@ xfs_qm_dqattach_grouphint(
 		 * because the freelist lock comes before dqlocks.
 		 */
 		xfs_dqunlock(udq);
-		if (locked)
-			xfs_dqunlock(gdq);
 		/*
 		 * we took a hard reference once upon a time in dqget,
 		 * so give it back when the udquot no longer points at it
@@ -795,9 +751,7 @@ xfs_qm_dqattach_grouphint(
 
 	} else {
 		ASSERT(XFS_DQ_IS_LOCKED(udq));
-		if (! locked) {
-			xfs_dqlock(gdq);
-		}
+		xfs_dqlock(gdq);
 	}
 
 	ASSERT(XFS_DQ_IS_LOCKED(udq));
@@ -810,10 +764,9 @@ xfs_qm_dqattach_grouphint(
 		XFS_DQHOLD(gdq);
 		udq->q_gdquot = gdq;
 	}
-	if (! locked) {
-		xfs_dqunlock(gdq);
-		xfs_dqunlock(udq);
-	}
+
+	xfs_dqunlock(gdq);
+	xfs_dqunlock(udq);
 }
 
 
@@ -821,8 +774,6 @@ xfs_qm_dqattach_grouphint(
  * Given a locked inode, attach dquot(s) to it, taking U/G/P-QUOTAON
  * into account.
  * If XFS_QMOPT_DQALLOC, the dquot(s) will be allocated if needed.
- * If XFS_QMOPT_DQLOCK, the dquot(s) will be returned locked. This option pretty
- * much made this code a complete mess, but it has been pretty useful.
  * If XFS_QMOPT_ILOCKED, then inode sent is already locked EXCL.
  * Inode may get unlocked and relocked in here, and the caller must deal with
  * the consequences.
@@ -851,7 +802,6 @@ xfs_qm_dqattach(
 	if (XFS_IS_UQUOTA_ON(mp)) {
 		error = xfs_qm_dqattach_one(ip, ip->i_d.di_uid, XFS_DQ_USER,
 						flags & XFS_QMOPT_DQALLOC,
-						flags & XFS_QMOPT_DQLOCK,
 						NULL, &ip->i_udquot);
 		if (error)
 			goto done;
@@ -863,11 +813,9 @@ xfs_qm_dqattach(
 		error = XFS_IS_GQUOTA_ON(mp) ?
 			xfs_qm_dqattach_one(ip, ip->i_d.di_gid, XFS_DQ_GROUP,
 						flags & XFS_QMOPT_DQALLOC,
-						flags & XFS_QMOPT_DQLOCK,
 						ip->i_udquot, &ip->i_gdquot) :
 			xfs_qm_dqattach_one(ip, ip->i_d.di_projid, XFS_DQ_PROJ,
 						flags & XFS_QMOPT_DQALLOC,
-						flags & XFS_QMOPT_DQLOCK,
 						ip->i_udquot, &ip->i_gdquot);
 		/*
 		 * Don't worry about the udquot that we may have
@@ -898,22 +846,13 @@ xfs_qm_dqattach(
 		/*
 		 * Attach i_gdquot to the gdquot hint inside the i_udquot.
 		 */
-		xfs_qm_dqattach_grouphint(ip->i_udquot, ip->i_gdquot,
-					 flags & XFS_QMOPT_DQLOCK);
+		xfs_qm_dqattach_grouphint(ip->i_udquot, ip->i_gdquot);
 	}
 
       done:
 
 #ifdef QUOTADEBUG
 	if (! error) {
-		if (ip->i_udquot) {
-			if (flags & XFS_QMOPT_DQLOCK)
-				ASSERT(XFS_DQ_IS_LOCKED(ip->i_udquot));
-		}
-		if (ip->i_gdquot) {
-			if (flags & XFS_QMOPT_DQLOCK)
-				ASSERT(XFS_DQ_IS_LOCKED(ip->i_gdquot));
-		}
 		if (XFS_IS_UQUOTA_ON(mp))
 			ASSERT(ip->i_udquot);
 		if (XFS_IS_OQUOTA_ON(mp))
@@ -2086,7 +2025,7 @@ xfs_qm_shake_freelist(
 		 * a dqlookup process that holds the hashlock that is
 		 * waiting for the freelist lock.
 		 */
-		if (! xfs_qm_dqhashlock_nowait(dqp)) {
+		if (!mutex_trylock(&dqp->q_hash->qh_lock)) {
 			xfs_dqfunlock(dqp);
 			xfs_dqunlock(dqp);
 			dqp = dqp->dq_flnext;
@@ -2103,7 +2042,7 @@ xfs_qm_shake_freelist(
 			/* XXX put a sentinel so that we can come back here */
 			xfs_dqfunlock(dqp);
 			xfs_dqunlock(dqp);
-			XFS_DQ_HASH_UNLOCK(hash);
+			mutex_unlock(&hash->qh_lock);
 			xfs_qm_freelist_unlock(xfs_Gqm);
 			if (++restarts >= XFS_QM_RECLAIM_MAX_RESTARTS)
 				return nreclaimed;
@@ -2120,7 +2059,7 @@ xfs_qm_shake_freelist(
 		XQM_HASHLIST_REMOVE(hash, dqp);
 		xfs_dqfunlock(dqp);
 		xfs_qm_mplist_unlock(dqp->q_mount);
-		XFS_DQ_HASH_UNLOCK(hash);
+		mutex_unlock(&hash->qh_lock);
 
  off_freelist:
 		XQM_FREELIST_REMOVE(dqp);
@@ -2262,7 +2201,7 @@ xfs_qm_dqreclaim_one(void)
 			continue;
 		}
 
-		if (! xfs_qm_dqhashlock_nowait(dqp))
+		if (!mutex_trylock(&dqp->q_hash->qh_lock))
 			goto mplistunlock;
 
 		ASSERT(dqp->q_nrefs == 0);
@@ -2271,7 +2210,7 @@ xfs_qm_dqreclaim_one(void)
 		XQM_HASHLIST_REMOVE(dqp->q_hash, dqp);
 		XQM_FREELIST_REMOVE(dqp);
 		dqpout = dqp;
-		XFS_DQ_HASH_UNLOCK(dqp->q_hash);
+		mutex_unlock(&dqp->q_hash->qh_lock);
  mplistunlock:
 		xfs_qm_mplist_unlock(dqp->q_mount);
 		xfs_dqfunlock(dqp);
@@ -2774,34 +2713,3 @@ xfs_qm_freelist_append(xfs_frlist_t *ql, xfs_dquot_t *dq)
 {
 	xfs_qm_freelist_insert((xfs_frlist_t *)ql->qh_prev, dq);
 }
-
-STATIC int
-xfs_qm_dqhashlock_nowait(
-	xfs_dquot_t *dqp)
-{
-	int locked;
-
-	locked = mutex_trylock(&((dqp)->q_hash->qh_lock));
-	return locked;
-}
-
-int
-xfs_qm_freelist_lock_nowait(
-	xfs_qm_t *xqm)
-{
-	int locked;
-
-	locked = mutex_trylock(&(xqm->qm_dqfreelist.qh_lock));
-	return locked;
-}
-
-STATIC int
-xfs_qm_mplist_nowait(
-	xfs_mount_t	*mp)
-{
-	int locked;
-
-	ASSERT(mp->m_quotainfo);
-	locked = mutex_trylock(&(XFS_QI_MPLLOCK(mp)));
-	return locked;
-}
diff --git a/fs/xfs/quota/xfs_qm.h b/fs/xfs/quota/xfs_qm.h
index ddf09166387c..a371954cae1b 100644
--- a/fs/xfs/quota/xfs_qm.h
+++ b/fs/xfs/quota/xfs_qm.h
@@ -27,7 +27,7 @@ struct xfs_qm;
 struct xfs_inode;
 
 extern uint		ndquot;
-extern mutex_t		xfs_Gqm_lock;
+extern struct mutex	xfs_Gqm_lock;
 extern struct xfs_qm	*xfs_Gqm;
 extern kmem_zone_t	*qm_dqzone;
 extern kmem_zone_t	*qm_dqtrxzone;
@@ -79,7 +79,7 @@ typedef xfs_dqhash_t	xfs_dqlist_t;
 typedef struct xfs_frlist {
        struct xfs_dquot *qh_next;
        struct xfs_dquot *qh_prev;
-       mutex_t		 qh_lock;
+       struct mutex	 qh_lock;
        uint		 qh_version;
        uint		 qh_nelems;
 } xfs_frlist_t;
@@ -115,7 +115,7 @@ typedef struct xfs_quotainfo {
 	xfs_qwarncnt_t	 qi_bwarnlimit;	 /* limit for blks warnings */
 	xfs_qwarncnt_t	 qi_iwarnlimit;	 /* limit for inodes warnings */
 	xfs_qwarncnt_t	 qi_rtbwarnlimit;/* limit for rt blks warnings */
-	mutex_t		 qi_quotaofflock;/* to serialize quotaoff */
+	struct mutex	 qi_quotaofflock;/* to serialize quotaoff */
 	xfs_filblks_t	 qi_dqchunklen;	 /* # BBs in a chunk of dqs */
 	uint		 qi_dqperchunk;	 /* # ondisk dqs in above chunk */
 	xfs_qcnt_t	 qi_bhardlimit;	 /* default data blk hard limit */
@@ -158,11 +158,6 @@ typedef struct xfs_dquot_acct {
 #define XFS_QM_IWARNLIMIT	5
 #define XFS_QM_RTBWARNLIMIT	5
 
-#define XFS_QM_LOCK(xqm)	(mutex_lock(&xqm##_lock))
-#define XFS_QM_UNLOCK(xqm)	(mutex_unlock(&xqm##_lock))
-#define XFS_QM_HOLD(xqm)	((xqm)->qm_nrefs++)
-#define XFS_QM_RELE(xqm)	((xqm)->qm_nrefs--)
-
 extern void		xfs_qm_destroy_quotainfo(xfs_mount_t *);
 extern void		xfs_qm_mount_quotas(xfs_mount_t *);
 extern int		xfs_qm_quotacheck(xfs_mount_t *);
@@ -178,6 +173,16 @@ extern void		xfs_qm_dqdetach(xfs_inode_t *);
 extern int		xfs_qm_dqpurge_all(xfs_mount_t *, uint);
 extern void		xfs_qm_dqrele_all_inodes(xfs_mount_t *, uint);
 
+/* quota ops */
+extern int		xfs_qm_scall_trunc_qfiles(xfs_mount_t *, uint);
+extern int		xfs_qm_scall_getquota(xfs_mount_t *, xfs_dqid_t, uint,
+					fs_disk_quota_t *);
+extern int		xfs_qm_scall_setqlim(xfs_mount_t *, xfs_dqid_t, uint,
+					fs_disk_quota_t *);
+extern int		xfs_qm_scall_getqstat(xfs_mount_t *, fs_quota_stat_t *);
+extern int		xfs_qm_scall_quotaon(xfs_mount_t *, uint);
+extern int		xfs_qm_scall_quotaoff(xfs_mount_t *, uint);
+
 /* vop stuff */
 extern int		xfs_qm_vop_dqalloc(xfs_mount_t *, xfs_inode_t *,
 					uid_t, gid_t, prid_t, uint,
@@ -194,11 +199,6 @@ extern int		xfs_qm_vop_chown_reserve(xfs_trans_t *, xfs_inode_t *,
 /* list stuff */
 extern void		xfs_qm_freelist_append(xfs_frlist_t *, xfs_dquot_t *);
 extern void		xfs_qm_freelist_unlink(xfs_dquot_t *);
-extern int		xfs_qm_freelist_lock_nowait(xfs_qm_t *);
-
-/* system call interface */
-extern int		xfs_qm_quotactl(struct xfs_mount *, int, int,
-				xfs_caddr_t);
 
 #ifdef DEBUG
 extern int		xfs_qm_internalqcheck(xfs_mount_t *);
diff --git a/fs/xfs/quota/xfs_qm_bhv.c b/fs/xfs/quota/xfs_qm_bhv.c
index bc6c5cca3e12..63037c689a4b 100644
--- a/fs/xfs/quota/xfs_qm_bhv.c
+++ b/fs/xfs/quota/xfs_qm_bhv.c
@@ -235,7 +235,6 @@ struct xfs_qmops xfs_qmcore_xfs = {
 	.xfs_dqvopchownresv	= xfs_qm_vop_chown_reserve,
 	.xfs_dqstatvfs		= xfs_qm_statvfs,
 	.xfs_dqsync		= xfs_qm_sync,
-	.xfs_quotactl		= xfs_qm_quotactl,
 	.xfs_dqtrxops		= &xfs_trans_dquot_ops,
 };
 EXPORT_SYMBOL(xfs_qmcore_xfs);
diff --git a/fs/xfs/quota/xfs_qm_syscalls.c b/fs/xfs/quota/xfs_qm_syscalls.c
index 68139b38aede..c7b66f6506ce 100644
--- a/fs/xfs/quota/xfs_qm_syscalls.c
+++ b/fs/xfs/quota/xfs_qm_syscalls.c
@@ -57,135 +57,16 @@
 # define qdprintk(s, args...)	do { } while (0)
 #endif
 
-STATIC int	xfs_qm_scall_trunc_qfiles(xfs_mount_t *, uint);
-STATIC int	xfs_qm_scall_getquota(xfs_mount_t *, xfs_dqid_t, uint,
-					fs_disk_quota_t *);
-STATIC int	xfs_qm_scall_getqstat(xfs_mount_t *, fs_quota_stat_t *);
-STATIC int	xfs_qm_scall_setqlim(xfs_mount_t *, xfs_dqid_t, uint,
-					fs_disk_quota_t *);
-STATIC int	xfs_qm_scall_quotaon(xfs_mount_t *, uint);
-STATIC int	xfs_qm_scall_quotaoff(xfs_mount_t *, uint, boolean_t);
 STATIC int	xfs_qm_log_quotaoff(xfs_mount_t *, xfs_qoff_logitem_t **, uint);
 STATIC int	xfs_qm_log_quotaoff_end(xfs_mount_t *, xfs_qoff_logitem_t *,
 					uint);
-STATIC uint	xfs_qm_import_flags(uint);
 STATIC uint	xfs_qm_export_flags(uint);
-STATIC uint	xfs_qm_import_qtype_flags(uint);
 STATIC uint	xfs_qm_export_qtype_flags(uint);
 STATIC void	xfs_qm_export_dquot(xfs_mount_t *, xfs_disk_dquot_t *,
 					fs_disk_quota_t *);
 
 
 /*
- * The main distribution switch of all XFS quotactl system calls.
- */
-int
-xfs_qm_quotactl(
-	xfs_mount_t	*mp,
-	int		cmd,
-	int		id,
-	xfs_caddr_t	addr)
-{
-	int		error;
-
-	ASSERT(addr != NULL || cmd == Q_XQUOTASYNC);
-
-	/*
-	 * The following commands are valid even when quotaoff.
-	 */
-	switch (cmd) {
-	case Q_XQUOTARM:
-		/*
-		 * Truncate quota files. quota must be off.
-		 */
-		if (XFS_IS_QUOTA_ON(mp))
-			return XFS_ERROR(EINVAL);
-		if (mp->m_flags & XFS_MOUNT_RDONLY)
-			return XFS_ERROR(EROFS);
-		return (xfs_qm_scall_trunc_qfiles(mp,
-			       xfs_qm_import_qtype_flags(*(uint *)addr)));
-
-	case Q_XGETQSTAT:
-		/*
-		 * Get quota status information.
-		 */
-		return (xfs_qm_scall_getqstat(mp, (fs_quota_stat_t *)addr));
-
-	case Q_XQUOTAON:
-		/*
-		 * QUOTAON - enabling quota enforcement.
-		 * Quota accounting must be turned on at mount time.
-		 */
-		if (mp->m_flags & XFS_MOUNT_RDONLY)
-			return XFS_ERROR(EROFS);
-		return (xfs_qm_scall_quotaon(mp,
-					  xfs_qm_import_flags(*(uint *)addr)));
-
-	case Q_XQUOTAOFF:
-		if (mp->m_flags & XFS_MOUNT_RDONLY)
-			return XFS_ERROR(EROFS);
-		break;
-
-	case Q_XQUOTASYNC:
-		return xfs_sync_inodes(mp, SYNC_DELWRI);
-
-	default:
-		break;
-	}
-
-	if (! XFS_IS_QUOTA_ON(mp))
-		return XFS_ERROR(ESRCH);
-
-	switch (cmd) {
-	case Q_XQUOTAOFF:
-		if (mp->m_flags & XFS_MOUNT_RDONLY)
-			return XFS_ERROR(EROFS);
-		error = xfs_qm_scall_quotaoff(mp,
-					    xfs_qm_import_flags(*(uint *)addr),
-					    B_FALSE);
-		break;
-
-	case Q_XGETQUOTA:
-		error = xfs_qm_scall_getquota(mp, (xfs_dqid_t)id, XFS_DQ_USER,
-					(fs_disk_quota_t *)addr);
-		break;
-	case Q_XGETGQUOTA:
-		error = xfs_qm_scall_getquota(mp, (xfs_dqid_t)id, XFS_DQ_GROUP,
-					(fs_disk_quota_t *)addr);
-		break;
-	case Q_XGETPQUOTA:
-		error = xfs_qm_scall_getquota(mp, (xfs_dqid_t)id, XFS_DQ_PROJ,
-					(fs_disk_quota_t *)addr);
-		break;
-
-	case Q_XSETQLIM:
-		if (mp->m_flags & XFS_MOUNT_RDONLY)
-			return XFS_ERROR(EROFS);
-		error = xfs_qm_scall_setqlim(mp, (xfs_dqid_t)id, XFS_DQ_USER,
-					     (fs_disk_quota_t *)addr);
-		break;
-	case Q_XSETGQLIM:
-		if (mp->m_flags & XFS_MOUNT_RDONLY)
-			return XFS_ERROR(EROFS);
-		error = xfs_qm_scall_setqlim(mp, (xfs_dqid_t)id, XFS_DQ_GROUP,
-					     (fs_disk_quota_t *)addr);
-		break;
-	case Q_XSETPQLIM:
-		if (mp->m_flags & XFS_MOUNT_RDONLY)
-			return XFS_ERROR(EROFS);
-		error = xfs_qm_scall_setqlim(mp, (xfs_dqid_t)id, XFS_DQ_PROJ,
-					     (fs_disk_quota_t *)addr);
-		break;
-
-	default:
-		error = XFS_ERROR(EINVAL);
-		break;
-	}
-
-	return (error);
-}
-
-/*
  * Turn off quota accounting and/or enforcement for all udquots and/or
  * gdquots. Called only at unmount time.
  *
@@ -193,11 +74,10 @@ xfs_qm_quotactl(
  * incore, and modifies the ondisk dquot directly. Therefore, for example,
  * it is an error to call this twice, without purging the cache.
  */
-STATIC int
+int
 xfs_qm_scall_quotaoff(
 	xfs_mount_t		*mp,
-	uint			flags,
-	boolean_t		force)
+	uint			flags)
 {
 	uint			dqtype;
 	int			error;
@@ -205,8 +85,6 @@ xfs_qm_scall_quotaoff(
 	xfs_qoff_logitem_t	*qoffstart;
 	int			nculprits;
 
-	if (!force && !capable(CAP_SYS_ADMIN))
-		return XFS_ERROR(EPERM);
 	/*
 	 * No file system can have quotas enabled on disk but not in core.
 	 * Note that quota utilities (like quotaoff) _expect_
@@ -375,7 +253,7 @@ out_error:
 	return (error);
 }
 
-STATIC int
+int
 xfs_qm_scall_trunc_qfiles(
 	xfs_mount_t	*mp,
 	uint		flags)
@@ -383,8 +261,6 @@ xfs_qm_scall_trunc_qfiles(
 	int		error = 0, error2 = 0;
 	xfs_inode_t	*qip;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return XFS_ERROR(EPERM);
 	if (!xfs_sb_version_hasquota(&mp->m_sb) || flags == 0) {
 		qdprintk("qtrunc flags=%x m_qflags=%x\n", flags, mp->m_qflags);
 		return XFS_ERROR(EINVAL);
@@ -416,7 +292,7 @@ xfs_qm_scall_trunc_qfiles(
  * effect immediately.
  * (Switching on quota accounting must be done at mount time.)
  */
-STATIC int
+int
 xfs_qm_scall_quotaon(
 	xfs_mount_t	*mp,
 	uint		flags)
@@ -426,9 +302,6 @@ xfs_qm_scall_quotaon(
 	uint		accflags;
 	__int64_t	sbflags;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return XFS_ERROR(EPERM);
-
 	flags &= (XFS_ALL_QUOTA_ACCT | XFS_ALL_QUOTA_ENFD);
 	/*
 	 * Switching on quota accounting must be done at mount time.
@@ -517,7 +390,7 @@ xfs_qm_scall_quotaon(
 /*
  * Return quota status information, such as uquota-off, enforcements, etc.
  */
-STATIC int
+int
 xfs_qm_scall_getqstat(
 	xfs_mount_t	*mp,
 	fs_quota_stat_t *out)
@@ -582,7 +455,7 @@ xfs_qm_scall_getqstat(
 /*
  * Adjust quota limits, and start/stop timers accordingly.
  */
-STATIC int
+int
 xfs_qm_scall_setqlim(
 	xfs_mount_t		*mp,
 	xfs_dqid_t		id,
@@ -595,9 +468,6 @@ xfs_qm_scall_setqlim(
 	int			error;
 	xfs_qcnt_t		hard, soft;
 
-	if (!capable(CAP_SYS_ADMIN))
-		return XFS_ERROR(EPERM);
-
 	if ((newlim->d_fieldmask &
 	    (FS_DQ_LIMIT_MASK|FS_DQ_TIMER_MASK|FS_DQ_WARNS_MASK)) == 0)
 		return (0);
@@ -742,7 +612,7 @@ xfs_qm_scall_setqlim(
 	return error;
 }
 
-STATIC int
+int
 xfs_qm_scall_getquota(
 	xfs_mount_t	*mp,
 	xfs_dqid_t	id,
@@ -935,30 +805,6 @@ xfs_qm_export_dquot(
 }
 
 STATIC uint
-xfs_qm_import_qtype_flags(
-	uint		uflags)
-{
-	uint		oflags = 0;
-
-	/*
-	 * Can't be more than one, or none.
-	 */
-	if (((uflags & (XFS_GROUP_QUOTA | XFS_USER_QUOTA)) ==
-			(XFS_GROUP_QUOTA | XFS_USER_QUOTA)) ||
-	    ((uflags & (XFS_GROUP_QUOTA | XFS_PROJ_QUOTA)) ==
-			(XFS_GROUP_QUOTA | XFS_PROJ_QUOTA)) ||
-	    ((uflags & (XFS_USER_QUOTA | XFS_PROJ_QUOTA)) ==
-			(XFS_USER_QUOTA | XFS_PROJ_QUOTA)) ||
-	    ((uflags & (XFS_GROUP_QUOTA|XFS_USER_QUOTA|XFS_PROJ_QUOTA)) == 0))
-		return (0);
-
-	oflags |= (uflags & XFS_USER_QUOTA) ? XFS_DQ_USER : 0;
-	oflags |= (uflags & XFS_PROJ_QUOTA) ? XFS_DQ_PROJ : 0;
-	oflags |= (uflags & XFS_GROUP_QUOTA) ? XFS_DQ_GROUP: 0;
-	return oflags;
-}
-
-STATIC uint
 xfs_qm_export_qtype_flags(
 	uint flags)
 {
@@ -979,26 +825,6 @@ xfs_qm_export_qtype_flags(
 }
 
 STATIC uint
-xfs_qm_import_flags(
-	uint uflags)
-{
-	uint flags = 0;
-
-	if (uflags & XFS_QUOTA_UDQ_ACCT)
-		flags |= XFS_UQUOTA_ACCT;
-	if (uflags & XFS_QUOTA_PDQ_ACCT)
-		flags |= XFS_PQUOTA_ACCT;
-	if (uflags & XFS_QUOTA_GDQ_ACCT)
-		flags |= XFS_GQUOTA_ACCT;
-	if (uflags & XFS_QUOTA_UDQ_ENFD)
-		flags |= XFS_UQUOTA_ENFD;
-	if (uflags & (XFS_QUOTA_PDQ_ENFD|XFS_QUOTA_GDQ_ENFD))
-		flags |= XFS_OQUOTA_ENFD;
-	return (flags);
-}
-
-
-STATIC uint
 xfs_qm_export_flags(
 	uint flags)
 {
@@ -1134,7 +960,7 @@ xfs_dqhash_t *qmtest_udqtab;
 xfs_dqhash_t *qmtest_gdqtab;
 int	      qmtest_hashmask;
 int	      qmtest_nfails;
-mutex_t	      qcheck_lock;
+struct mutex  qcheck_lock;
 
 #define DQTEST_HASHVAL(mp, id) (((__psunsigned_t)(mp) + \
 				 (__psunsigned_t)(id)) & \
diff --git a/fs/xfs/quota/xfs_quota_priv.h b/fs/xfs/quota/xfs_quota_priv.h
index c4fcea600bc2..8286b2842b6b 100644
--- a/fs/xfs/quota/xfs_quota_priv.h
+++ b/fs/xfs/quota/xfs_quota_priv.h
@@ -42,34 +42,24 @@
 #define XFS_QI_QOFFLOCK(mp)	((mp)->m_quotainfo->qi_quotaofflock)
 
 #define XFS_QI_MPL_LIST(mp)	((mp)->m_quotainfo->qi_dqlist)
-#define XFS_QI_MPLLOCK(mp)	((mp)->m_quotainfo->qi_dqlist.qh_lock)
 #define XFS_QI_MPLNEXT(mp)	((mp)->m_quotainfo->qi_dqlist.qh_next)
 #define XFS_QI_MPLNDQUOTS(mp)	((mp)->m_quotainfo->qi_dqlist.qh_nelems)
 
-#define XQMLCK(h)			(mutex_lock(&((h)->qh_lock)))
-#define XQMUNLCK(h)			(mutex_unlock(&((h)->qh_lock)))
-#ifdef DEBUG
-struct xfs_dqhash;
-static inline int XQMISLCKD(struct xfs_dqhash *h)
-{
-	if (mutex_trylock(&h->qh_lock)) {
-		mutex_unlock(&h->qh_lock);
-		return 0;
-	}
-	return 1;
-}
-#endif
-
-#define XFS_DQ_HASH_LOCK(h)		XQMLCK(h)
-#define XFS_DQ_HASH_UNLOCK(h)		XQMUNLCK(h)
-#define XFS_DQ_IS_HASH_LOCKED(h)	XQMISLCKD(h)
-
-#define xfs_qm_mplist_lock(mp)		XQMLCK(&(XFS_QI_MPL_LIST(mp)))
-#define xfs_qm_mplist_unlock(mp)	XQMUNLCK(&(XFS_QI_MPL_LIST(mp)))
-#define XFS_QM_IS_MPLIST_LOCKED(mp)	XQMISLCKD(&(XFS_QI_MPL_LIST(mp)))
-
-#define xfs_qm_freelist_lock(qm)	XQMLCK(&((qm)->qm_dqfreelist))
-#define xfs_qm_freelist_unlock(qm)	XQMUNLCK(&((qm)->qm_dqfreelist))
+#define xfs_qm_mplist_lock(mp) \
+	mutex_lock(&(XFS_QI_MPL_LIST(mp).qh_lock))
+#define xfs_qm_mplist_nowait(mp) \
+	mutex_trylock(&(XFS_QI_MPL_LIST(mp).qh_lock))
+#define xfs_qm_mplist_unlock(mp) \
+	mutex_unlock(&(XFS_QI_MPL_LIST(mp).qh_lock))
+#define XFS_QM_IS_MPLIST_LOCKED(mp) \
+	mutex_is_locked(&(XFS_QI_MPL_LIST(mp).qh_lock))
+
+#define xfs_qm_freelist_lock(qm) \
+	mutex_lock(&((qm)->qm_dqfreelist.qh_lock))
+#define xfs_qm_freelist_lock_nowait(qm) \
+	mutex_trylock(&((qm)->qm_dqfreelist.qh_lock))
+#define xfs_qm_freelist_unlock(qm) \
+	mutex_unlock(&((qm)->qm_dqfreelist.qh_lock))
 
 /*
  * Hash into a bucket in the dquot hash table, based on <mp, id>.
diff --git a/fs/xfs/quota/xfs_trans_dquot.c b/fs/xfs/quota/xfs_trans_dquot.c
index 99611381e740..447173bcf96d 100644
--- a/fs/xfs/quota/xfs_trans_dquot.c
+++ b/fs/xfs/quota/xfs_trans_dquot.c
@@ -624,10 +624,9 @@ xfs_trans_dqresv(
 	xfs_qcnt_t	*resbcountp;
 	xfs_quotainfo_t	*q = mp->m_quotainfo;
 
-	if (! (flags & XFS_QMOPT_DQLOCK)) {
-		xfs_dqlock(dqp);
-	}
-	ASSERT(XFS_DQ_IS_LOCKED(dqp));
+
+	xfs_dqlock(dqp);
+
 	if (flags & XFS_TRANS_DQ_RES_BLKS) {
 		hardlimit = be64_to_cpu(dqp->q_core.d_blk_hardlimit);
 		if (!hardlimit)
@@ -740,10 +739,8 @@ xfs_trans_dqresv(
 	ASSERT(dqp->q_res_icount >= be64_to_cpu(dqp->q_core.d_icount));
 
 error_return:
-	if (! (flags & XFS_QMOPT_DQLOCK)) {
-		xfs_dqunlock(dqp);
-	}
-	return (error);
+	xfs_dqunlock(dqp);
+	return error;
 }
 
 
@@ -753,8 +750,7 @@ error_return:
  * grp/prj quotas is important, because this follows a both-or-nothing
  * approach.
  *
- * flags = XFS_QMOPT_DQLOCK indicate if dquot(s) need to be locked.
- *	   XFS_QMOPT_FORCE_RES evades limit enforcement. Used by chown.
+ * flags = XFS_QMOPT_FORCE_RES evades limit enforcement. Used by chown.
  *	   XFS_QMOPT_ENOSPC returns ENOSPC not EDQUOT.  Used by pquota.
  *	   XFS_TRANS_DQ_RES_BLKS reserves regular disk blocks
  *	   XFS_TRANS_DQ_RES_RTBLKS reserves realtime disk blocks
diff --git a/fs/xfs/support/debug.c b/fs/xfs/support/debug.c
index ae5482965424..3f3610a7ee05 100644
--- a/fs/xfs/support/debug.c
+++ b/fs/xfs/support/debug.c
@@ -24,6 +24,7 @@
 #include "xfs_ag.h"
 #include "xfs_dmapi.h"
 #include "xfs_mount.h"
+#include "xfs_error.h"
 
 static char		message[1024];	/* keep it off the stack */
 static DEFINE_SPINLOCK(xfs_err_lock);
diff --git a/fs/xfs/support/uuid.c b/fs/xfs/support/uuid.c
index 5830c040ea7e..b83f76b6d410 100644
--- a/fs/xfs/support/uuid.c
+++ b/fs/xfs/support/uuid.c
@@ -17,10 +17,6 @@
  */
 #include <xfs.h>
 
-static DEFINE_MUTEX(uuid_monitor);
-static int	uuid_table_size;
-static uuid_t	*uuid_table;
-
 /* IRIX interpretation of an uuid_t */
 typedef struct {
 	__be32	uu_timelow;
@@ -46,12 +42,6 @@ uuid_getnodeuniq(uuid_t *uuid, int fsid [2])
 	fsid[1] = be32_to_cpu(uup->uu_timelow);
 }
 
-void
-uuid_create_nil(uuid_t *uuid)
-{
-	memset(uuid, 0, sizeof(*uuid));
-}
-
 int
 uuid_is_nil(uuid_t *uuid)
 {
@@ -71,64 +61,3 @@ uuid_equal(uuid_t *uuid1, uuid_t *uuid2)
 {
 	return memcmp(uuid1, uuid2, sizeof(uuid_t)) ? 0 : 1;
 }
-
-/*
- * Given a 128-bit uuid, return a 64-bit value by adding the top and bottom
- * 64-bit words.  NOTE: This function can not be changed EVER.  Although
- * brain-dead, some applications depend on this 64-bit value remaining
- * persistent.  Specifically, DMI vendors store the value as a persistent
- * filehandle.
- */
-__uint64_t
-uuid_hash64(uuid_t *uuid)
-{
-	__uint64_t	*sp = (__uint64_t *)uuid;
-
-	return sp[0] + sp[1];
-}
-
-int
-uuid_table_insert(uuid_t *uuid)
-{
-	int	i, hole;
-
-	mutex_lock(&uuid_monitor);
-	for (i = 0, hole = -1; i < uuid_table_size; i++) {
-		if (uuid_is_nil(&uuid_table[i])) {
-			hole = i;
-			continue;
-		}
-		if (uuid_equal(uuid, &uuid_table[i])) {
-			mutex_unlock(&uuid_monitor);
-			return 0;
-		}
-	}
-	if (hole < 0) {
-		uuid_table = kmem_realloc(uuid_table,
-			(uuid_table_size + 1) * sizeof(*uuid_table),
-			uuid_table_size  * sizeof(*uuid_table),
-			KM_SLEEP);
-		hole = uuid_table_size++;
-	}
-	uuid_table[hole] = *uuid;
-	mutex_unlock(&uuid_monitor);
-	return 1;
-}
-
-void
-uuid_table_remove(uuid_t *uuid)
-{
-	int	i;
-
-	mutex_lock(&uuid_monitor);
-	for (i = 0; i < uuid_table_size; i++) {
-		if (uuid_is_nil(&uuid_table[i]))
-			continue;
-		if (!uuid_equal(uuid, &uuid_table[i]))
-			continue;
-		uuid_create_nil(&uuid_table[i]);
-		break;
-	}
-	ASSERT(i < uuid_table_size);
-	mutex_unlock(&uuid_monitor);
-}
diff --git a/fs/xfs/support/uuid.h b/fs/xfs/support/uuid.h
index cff5b607d445..4732d71262cc 100644
--- a/fs/xfs/support/uuid.h
+++ b/fs/xfs/support/uuid.h
@@ -22,12 +22,8 @@ typedef struct {
 	unsigned char	__u_bits[16];
 } uuid_t;
 
-extern void uuid_create_nil(uuid_t *uuid);
 extern int uuid_is_nil(uuid_t *uuid);
 extern int uuid_equal(uuid_t *uuid1, uuid_t *uuid2);
 extern void uuid_getnodeuniq(uuid_t *uuid, int fsid [2]);
-extern __uint64_t uuid_hash64(uuid_t *uuid);
-extern int uuid_table_insert(uuid_t *uuid);
-extern void uuid_table_remove(uuid_t *uuid);
 
 #endif	/* __XFS_SUPPORT_UUID_H__ */
diff --git a/fs/xfs/xfs_ag.h b/fs/xfs/xfs_ag.h
index 143d63ecb20a..c8641f713caa 100644
--- a/fs/xfs/xfs_ag.h
+++ b/fs/xfs/xfs_ag.h
@@ -223,8 +223,8 @@ typedef struct xfs_perag
 		be32_to_cpu((a)->agf_levels[XFS_BTNUM_CNTi]), mp))
 #define	XFS_MIN_FREELIST_PAG(pag,mp)	\
 	(XFS_MIN_FREELIST_RAW(		\
-		(uint_t)(pag)->pagf_levels[XFS_BTNUM_BNOi], \
-		(uint_t)(pag)->pagf_levels[XFS_BTNUM_CNTi], mp))
+		(unsigned int)(pag)->pagf_levels[XFS_BTNUM_BNOi], \
+		(unsigned int)(pag)->pagf_levels[XFS_BTNUM_CNTi], mp))
 
 #define XFS_AGB_TO_FSB(mp,agno,agbno)	\
 	(((xfs_fsblock_t)(agno) << (mp)->m_sb.sb_agblklog) | (agbno))
diff --git a/fs/xfs/xfs_alloc.c b/fs/xfs/xfs_alloc.c
index 028e44e58ea9..2cf944eb796d 100644
--- a/fs/xfs/xfs_alloc.c
+++ b/fs/xfs/xfs_alloc.c
@@ -1872,6 +1872,25 @@ xfs_alloc_compute_maxlevels(
 }
 
 /*
+ * Find the length of the longest extent in an AG.
+ */
+xfs_extlen_t
+xfs_alloc_longest_free_extent(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag)
+{
+	xfs_extlen_t		need, delta = 0;
+
+	need = XFS_MIN_FREELIST_PAG(pag, mp);
+	if (need > pag->pagf_flcount)
+		delta = need - pag->pagf_flcount;
+
+	if (pag->pagf_longest > delta)
+		return pag->pagf_longest - delta;
+	return pag->pagf_flcount > 0 || pag->pagf_longest > 0;
+}
+
+/*
  * Decide whether to use this allocation group for this allocation.
  * If so, fix up the btree freelist's size.
  */
@@ -1923,15 +1942,12 @@ xfs_alloc_fix_freelist(
 	}
 
 	if (!(flags & XFS_ALLOC_FLAG_FREEING)) {
-		need = XFS_MIN_FREELIST_PAG(pag, mp);
-		delta = need > pag->pagf_flcount ? need - pag->pagf_flcount : 0;
 		/*
 		 * If it looks like there isn't a long enough extent, or enough
 		 * total blocks, reject it.
 		 */
-		longest = (pag->pagf_longest > delta) ?
-			(pag->pagf_longest - delta) :
-			(pag->pagf_flcount > 0 || pag->pagf_longest > 0);
+		need = XFS_MIN_FREELIST_PAG(pag, mp);
+		longest = xfs_alloc_longest_free_extent(mp, pag);
 		if ((args->minlen + args->alignment + args->minalignslop - 1) >
 				longest ||
 		    ((int)(pag->pagf_freeblks + pag->pagf_flcount -
diff --git a/fs/xfs/xfs_alloc.h b/fs/xfs/xfs_alloc.h
index 588172796f7b..e704caee10df 100644
--- a/fs/xfs/xfs_alloc.h
+++ b/fs/xfs/xfs_alloc.h
@@ -100,6 +100,12 @@ typedef struct xfs_alloc_arg {
 #define XFS_ALLOC_USERDATA		1	/* allocation is for user data*/
 #define XFS_ALLOC_INITIAL_USER_DATA	2	/* special case start of file */
 
+/*
+ * Find the length of the longest extent in an AG.
+ */
+xfs_extlen_t
+xfs_alloc_longest_free_extent(struct xfs_mount *mp,
+		struct xfs_perag *pag);
 
 #ifdef __KERNEL__
 
diff --git a/fs/xfs/xfs_attr_leaf.c b/fs/xfs/xfs_attr_leaf.c
index 6c323f8a4cd1..afdc8911637d 100644
--- a/fs/xfs/xfs_attr_leaf.c
+++ b/fs/xfs/xfs_attr_leaf.c
@@ -155,7 +155,8 @@ xfs_attr_shortform_bytesfit(xfs_inode_t *dp, int bytes)
 		 * minimum offset only needs to be the space required for 
 		 * the btree root.
 		 */ 
-		if (!dp->i_d.di_forkoff && dp->i_df.if_bytes > mp->m_attroffset)
+		if (!dp->i_d.di_forkoff && dp->i_df.if_bytes >
+		    xfs_default_attroffset(dp))
 			dsize = XFS_BMDR_SPACE_CALC(MINDBTPTRS);
 		break;
 		
@@ -298,6 +299,26 @@ xfs_attr_shortform_add(xfs_da_args_t *args, int forkoff)
 }
 
 /*
+ * After the last attribute is removed revert to original inode format,
+ * making all literal area available to the data fork once more.
+ */
+STATIC void
+xfs_attr_fork_reset(
+	struct xfs_inode	*ip,
+	struct xfs_trans	*tp)
+{
+	xfs_idestroy_fork(ip, XFS_ATTR_FORK);
+	ip->i_d.di_forkoff = 0;
+	ip->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
+
+	ASSERT(ip->i_d.di_anextents == 0);
+	ASSERT(ip->i_afp == NULL);
+
+	ip->i_df.if_ext_max = XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t);
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+}
+
+/*
  * Remove an attribute from the shortform attribute list structure.
  */
 int
@@ -344,22 +365,10 @@ xfs_attr_shortform_remove(xfs_da_args_t *args)
 	 */
 	totsize -= size;
 	if (totsize == sizeof(xfs_attr_sf_hdr_t) &&
-				!(args->op_flags & XFS_DA_OP_ADDNAME) &&
-				(mp->m_flags & XFS_MOUNT_ATTR2) &&
-				(dp->i_d.di_format != XFS_DINODE_FMT_BTREE)) {
-		/*
-		 * Last attribute now removed, revert to original
-		 * inode format making all literal area available
-		 * to the data fork once more.
-		 */
-		xfs_idestroy_fork(dp, XFS_ATTR_FORK);
-		dp->i_d.di_forkoff = 0;
-		dp->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
-		ASSERT(dp->i_d.di_anextents == 0);
-		ASSERT(dp->i_afp == NULL);
-		dp->i_df.if_ext_max =
-			XFS_IFORK_DSIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
-		xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
+	    (mp->m_flags & XFS_MOUNT_ATTR2) &&
+	    (dp->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
+	    !(args->op_flags & XFS_DA_OP_ADDNAME)) {
+		xfs_attr_fork_reset(dp, args->trans);
 	} else {
 		xfs_idata_realloc(dp, -size, XFS_ATTR_FORK);
 		dp->i_d.di_forkoff = xfs_attr_shortform_bytesfit(dp, totsize);
@@ -786,20 +795,7 @@ xfs_attr_leaf_to_shortform(xfs_dabuf_t *bp, xfs_da_args_t *args, int forkoff)
 	if (forkoff == -1) {
 		ASSERT(dp->i_mount->m_flags & XFS_MOUNT_ATTR2);
 		ASSERT(dp->i_d.di_format != XFS_DINODE_FMT_BTREE);
-
-		/*
-		 * Last attribute was removed, revert to original
-		 * inode format making all literal area available
-		 * to the data fork once more.
-		 */
-		xfs_idestroy_fork(dp, XFS_ATTR_FORK);
-		dp->i_d.di_forkoff = 0;
-		dp->i_d.di_aformat = XFS_DINODE_FMT_EXTENTS;
-		ASSERT(dp->i_d.di_anextents == 0);
-		ASSERT(dp->i_afp == NULL);
-		dp->i_df.if_ext_max =
-			XFS_IFORK_DSIZE(dp) / (uint)sizeof(xfs_bmbt_rec_t);
-		xfs_trans_log_inode(args->trans, dp, XFS_ILOG_CORE);
+		xfs_attr_fork_reset(dp, args->trans);
 		goto out;
 	}
 
diff --git a/fs/xfs/xfs_bmap.c b/fs/xfs/xfs_bmap.c
index c852cd65aaea..3a6ed426327a 100644
--- a/fs/xfs/xfs_bmap.c
+++ b/fs/xfs/xfs_bmap.c
@@ -2479,7 +2479,7 @@ xfs_bmap_adjacent(
 	fb_agno = nullfb ? NULLAGNUMBER : XFS_FSB_TO_AGNO(mp, ap->firstblock);
 	/*
 	 * If allocating at eof, and there's a previous real block,
-	 * try to use it's last block as our starting point.
+	 * try to use its last block as our starting point.
 	 */
 	if (ap->eof && ap->prevp->br_startoff != NULLFILEOFF &&
 	    !isnullstartblock(ap->prevp->br_startblock) &&
@@ -2712,9 +2712,6 @@ xfs_bmap_btalloc(
 	xfs_agnumber_t	startag;
 	xfs_alloc_arg_t	args;
 	xfs_extlen_t	blen;
-	xfs_extlen_t	delta;
-	xfs_extlen_t	longest;
-	xfs_extlen_t	need;
 	xfs_extlen_t	nextminlen = 0;
 	xfs_perag_t	*pag;
 	int		nullfb;		/* true if ap->firstblock isn't set */
@@ -2796,13 +2793,8 @@ xfs_bmap_btalloc(
 			 * See xfs_alloc_fix_freelist...
 			 */
 			if (pag->pagf_init) {
-				need = XFS_MIN_FREELIST_PAG(pag, mp);
-				delta = need > pag->pagf_flcount ?
-					need - pag->pagf_flcount : 0;
-				longest = (pag->pagf_longest > delta) ?
-					(pag->pagf_longest - delta) :
-					(pag->pagf_flcount > 0 ||
-					 pag->pagf_longest > 0);
+				xfs_extlen_t	longest;
+				longest = xfs_alloc_longest_free_extent(mp, pag);
 				if (blen < longest)
 					blen = longest;
 			} else
@@ -3577,6 +3569,27 @@ xfs_bmap_extents_to_btree(
 }
 
 /*
+ * Calculate the default attribute fork offset for newly created inodes.
+ */
+uint
+xfs_default_attroffset(
+	struct xfs_inode	*ip)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	uint			offset;
+
+	if (mp->m_sb.sb_inodesize == 256) {
+		offset = XFS_LITINO(mp) -
+				XFS_BMDR_SPACE_CALC(MINABTPTRS);
+	} else {
+		offset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
+	}
+
+	ASSERT(offset < XFS_LITINO(mp));
+	return offset;
+}
+
+/*
  * Helper routine to reset inode di_forkoff field when switching
  * attribute fork from local to extent format - we reset it where
  * possible to make space available for inline data fork extents.
@@ -3588,15 +3601,18 @@ xfs_bmap_forkoff_reset(
 	int		whichfork)
 {
 	if (whichfork == XFS_ATTR_FORK &&
-	    (ip->i_d.di_format != XFS_DINODE_FMT_DEV) &&
-	    (ip->i_d.di_format != XFS_DINODE_FMT_UUID) &&
-	    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
-	    ((mp->m_attroffset >> 3) > ip->i_d.di_forkoff)) {
-		ip->i_d.di_forkoff = mp->m_attroffset >> 3;
-		ip->i_df.if_ext_max = XFS_IFORK_DSIZE(ip) /
-					(uint)sizeof(xfs_bmbt_rec_t);
-		ip->i_afp->if_ext_max = XFS_IFORK_ASIZE(ip) /
-					(uint)sizeof(xfs_bmbt_rec_t);
+	    ip->i_d.di_format != XFS_DINODE_FMT_DEV &&
+	    ip->i_d.di_format != XFS_DINODE_FMT_UUID &&
+	    ip->i_d.di_format != XFS_DINODE_FMT_BTREE) {
+		uint	dfl_forkoff = xfs_default_attroffset(ip) >> 3;
+
+		if (dfl_forkoff > ip->i_d.di_forkoff) {
+			ip->i_d.di_forkoff = dfl_forkoff;
+			ip->i_df.if_ext_max =
+				XFS_IFORK_DSIZE(ip) / sizeof(xfs_bmbt_rec_t);
+			ip->i_afp->if_ext_max =
+				XFS_IFORK_ASIZE(ip) / sizeof(xfs_bmbt_rec_t);
+		}
 	}
 }
 
@@ -4065,7 +4081,7 @@ xfs_bmap_add_attrfork(
 	case XFS_DINODE_FMT_BTREE:
 		ip->i_d.di_forkoff = xfs_attr_shortform_bytesfit(ip, size);
 		if (!ip->i_d.di_forkoff)
-			ip->i_d.di_forkoff = mp->m_attroffset >> 3;
+			ip->i_d.di_forkoff = xfs_default_attroffset(ip) >> 3;
 		else if (mp->m_flags & XFS_MOUNT_ATTR2)
 			version = 2;
 		break;
@@ -4212,12 +4228,12 @@ xfs_bmap_compute_maxlevels(
 	 * (a signed 16-bit number, xfs_aextnum_t).
 	 *
 	 * Note that we can no longer assume that if we are in ATTR1 that
-	 * the fork offset of all the inodes will be (m_attroffset >> 3)
-	 * because we could have mounted with ATTR2 and then mounted back
-	 * with ATTR1, keeping the di_forkoff's fixed but probably at
-	 * various positions. Therefore, for both ATTR1 and ATTR2
-	 * we have to assume the worst case scenario of a minimum size
-	 * available.
+	 * the fork offset of all the inodes will be
+	 * (xfs_default_attroffset(ip) >> 3) because we could have mounted
+	 * with ATTR2 and then mounted back with ATTR1, keeping the
+	 * di_forkoff's fixed but probably at various positions. Therefore,
+	 * for both ATTR1 and ATTR2 we have to assume the worst case scenario
+	 * of a minimum size available.
 	 */
 	if (whichfork == XFS_DATA_FORK) {
 		maxleafents = MAXEXTNUM;
@@ -4804,7 +4820,7 @@ xfs_bmapi(
 	xfs_extlen_t	minlen;		/* min allocation size */
 	xfs_mount_t	*mp;		/* xfs mount structure */
 	int		n;		/* current extent index */
-	int		nallocs;	/* number of extents alloc\'d */
+	int		nallocs;	/* number of extents alloc'd */
 	xfs_extnum_t	nextents;	/* number of extents in file */
 	xfs_fileoff_t	obno;		/* old block number (offset) */
 	xfs_bmbt_irec_t	prev;		/* previous file extent record */
@@ -6204,7 +6220,7 @@ xfs_bmap_get_bp(
 	return(bp);
 }
 
-void
+STATIC void
 xfs_check_block(
 	struct xfs_btree_block	*block,
 	xfs_mount_t		*mp,
@@ -6494,7 +6510,7 @@ xfs_bmap_count_tree(
 	block = XFS_BUF_TO_BLOCK(bp);
 
 	if (--level) {
-		/* Not at node above leafs, count this level of nodes */
+		/* Not at node above leaves, count this level of nodes */
 		nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
 		while (nextbno != NULLFSBLOCK) {
 			if ((error = xfs_btree_read_bufl(mp, tp, nextbno,
diff --git a/fs/xfs/xfs_bmap.h b/fs/xfs/xfs_bmap.h
index be2979d88d32..1b8ff9256bd0 100644
--- a/fs/xfs/xfs_bmap.h
+++ b/fs/xfs/xfs_bmap.h
@@ -125,7 +125,7 @@ typedef struct xfs_bmalloca {
 	struct xfs_bmbt_irec	*gotp;	/* extent after, or delayed */
 	xfs_extlen_t		alen;	/* i/o length asked/allocated */
 	xfs_extlen_t		total;	/* total blocks needed for xaction */
-	xfs_extlen_t		minlen;	/* mininum allocation size (blocks) */
+	xfs_extlen_t		minlen;	/* minimum allocation size (blocks) */
 	xfs_extlen_t		minleft; /* amount must be left after alloc */
 	char			eof;	/* set if allocating past last extent */
 	char			wasdel;	/* replacing a delayed allocation */
@@ -338,6 +338,10 @@ xfs_check_nostate_extents(
 	xfs_extnum_t		idx,
 	xfs_extnum_t		num);
 
+uint
+xfs_default_attroffset(
+	struct xfs_inode	*ip);
+
 #ifdef __KERNEL__
 
 /*
diff --git a/fs/xfs/xfs_btree.c b/fs/xfs/xfs_btree.c
index e73c332eb23f..e9df99574829 100644
--- a/fs/xfs/xfs_btree.c
+++ b/fs/xfs/xfs_btree.c
@@ -1883,7 +1883,7 @@ xfs_btree_lshift(
 
 	/*
 	 * We add one entry to the left side and remove one for the right side.
-	 * Accout for it here, the changes will be updated on disk and logged
+	 * Account for it here, the changes will be updated on disk and logged
 	 * later.
 	 */
 	lrecs++;
@@ -3535,7 +3535,7 @@ xfs_btree_delrec(
 	XFS_BTREE_STATS_INC(cur, join);
 
 	/*
-	 * Fix up the the number of records and right block pointer in the
+	 * Fix up the number of records and right block pointer in the
 	 * surviving block, and log it.
 	 */
 	xfs_btree_set_numrecs(left, lrecs + rrecs);
diff --git a/fs/xfs/xfs_btree.h b/fs/xfs/xfs_btree.h
index 789fffdf8b2f..4f852b735b96 100644
--- a/fs/xfs/xfs_btree.h
+++ b/fs/xfs/xfs_btree.h
@@ -41,7 +41,7 @@ extern kmem_zone_t	*xfs_btree_cur_zone;
 /*
  * Generic btree header.
  *
- * This is a comination of the actual format used on disk for short and long
+ * This is a combination of the actual format used on disk for short and long
  * format btrees.  The first three fields are shared by both format, but
  * the pointers are different and should be used with care.
  *
diff --git a/fs/xfs/xfs_da_btree.c b/fs/xfs/xfs_da_btree.c
index c45f74ff1a5b..9ff6e57a5075 100644
--- a/fs/xfs/xfs_da_btree.c
+++ b/fs/xfs/xfs_da_btree.c
@@ -1503,7 +1503,7 @@ xfs_da_path_shift(xfs_da_state_t *state, xfs_da_state_path_t *path,
  * This is implemented with some source-level loop unrolling.
  */
 xfs_dahash_t
-xfs_da_hashname(const uchar_t *name, int namelen)
+xfs_da_hashname(const __uint8_t *name, int namelen)
 {
 	xfs_dahash_t hash;
 
diff --git a/fs/xfs/xfs_da_btree.h b/fs/xfs/xfs_da_btree.h
index 70b710c1792d..8c536167bf75 100644
--- a/fs/xfs/xfs_da_btree.h
+++ b/fs/xfs/xfs_da_btree.h
@@ -91,9 +91,9 @@ enum xfs_dacmp {
  * Structure to ease passing around component names.
  */
 typedef struct xfs_da_args {
-	const uchar_t	*name;		/* string (maybe not NULL terminated) */
+	const __uint8_t	*name;		/* string (maybe not NULL terminated) */
 	int		namelen;	/* length of string (maybe no NULL) */
-	uchar_t		*value;		/* set of bytes (maybe contain NULLs) */
+	__uint8_t	*value;		/* set of bytes (maybe contain NULLs) */
 	int		valuelen;	/* length of value */
 	int		flags;		/* argument flags (eg: ATTR_NOCREATE) */
 	xfs_dahash_t	hashval;	/* hash value of name */
@@ -185,7 +185,7 @@ typedef struct xfs_da_state {
 	unsigned char		inleaf;		/* insert into 1->lf, 0->splf */
 	unsigned char		extravalid;	/* T/F: extrablk is in use */
 	unsigned char		extraafter;	/* T/F: extrablk is after new */
-	xfs_da_state_blk_t	extrablk;	/* for double-splits on leafs */
+	xfs_da_state_blk_t	extrablk;	/* for double-splits on leaves */
 						/* for dirv2 extrablk is data */
 } xfs_da_state_t;
 
@@ -251,7 +251,7 @@ xfs_daddr_t	xfs_da_reada_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 					  xfs_dabuf_t *dead_buf);
 
-uint xfs_da_hashname(const uchar_t *name_string, int name_length);
+uint xfs_da_hashname(const __uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
 				const char *name, int len);
 
@@ -268,5 +268,6 @@ xfs_daddr_t xfs_da_blkno(xfs_dabuf_t *dabuf);
 
 extern struct kmem_zone *xfs_da_state_zone;
 extern struct kmem_zone *xfs_dabuf_zone;
+extern const struct xfs_nameops xfs_default_nameops;
 
 #endif	/* __XFS_DA_BTREE_H__ */
diff --git a/fs/xfs/xfs_dfrag.c b/fs/xfs/xfs_dfrag.c
index f8278cfcc1d3..e6d839bddbf0 100644
--- a/fs/xfs/xfs_dfrag.c
+++ b/fs/xfs/xfs_dfrag.c
@@ -79,6 +79,12 @@ xfs_swapext(
 		goto out_put_target_file;
 	}
 
+	if (IS_SWAPFILE(file->f_path.dentry->d_inode) ||
+	    IS_SWAPFILE(target_file->f_path.dentry->d_inode)) {
+		error = XFS_ERROR(EINVAL);
+		goto out_put_target_file;
+	}
+
 	ip = XFS_I(file->f_path.dentry->d_inode);
 	tip = XFS_I(target_file->f_path.dentry->d_inode);
 
@@ -118,19 +124,17 @@ xfs_swap_extents(
 	xfs_bstat_t	*sbp = &sxp->sx_stat;
 	xfs_ifork_t	*tempifp, *ifp, *tifp;
 	int		ilf_fields, tilf_fields;
-	static uint	lock_flags = XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL;
 	int		error = 0;
 	int		aforkblks = 0;
 	int		taforkblks = 0;
 	__uint64_t	tmp;
-	char		locked = 0;
 
 	mp = ip->i_mount;
 
 	tempifp = kmem_alloc(sizeof(xfs_ifork_t), KM_MAYFAIL);
 	if (!tempifp) {
 		error = XFS_ERROR(ENOMEM);
-		goto error0;
+		goto out;
 	}
 
 	sbp = &sxp->sx_stat;
@@ -143,25 +147,24 @@ xfs_swap_extents(
 	 */
 	xfs_lock_two_inodes(ip, tip, XFS_IOLOCK_EXCL);
 	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
-	locked = 1;
 
 	/* Verify that both files have the same format */
 	if ((ip->i_d.di_mode & S_IFMT) != (tip->i_d.di_mode & S_IFMT)) {
 		error = XFS_ERROR(EINVAL);
-		goto error0;
+		goto out_unlock;
 	}
 
 	/* Verify both files are either real-time or non-realtime */
 	if (XFS_IS_REALTIME_INODE(ip) != XFS_IS_REALTIME_INODE(tip)) {
 		error = XFS_ERROR(EINVAL);
-		goto error0;
+		goto out_unlock;
 	}
 
 	/* Should never get a local format */
 	if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL ||
 	    tip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
 		error = XFS_ERROR(EINVAL);
-		goto error0;
+		goto out_unlock;
 	}
 
 	if (VN_CACHED(VFS_I(tip)) != 0) {
@@ -169,13 +172,13 @@ xfs_swap_extents(
 		error = xfs_flushinval_pages(tip, 0, -1,
 				FI_REMAPF_LOCKED);
 		if (error)
-			goto error0;
+			goto out_unlock;
 	}
 
 	/* Verify O_DIRECT for ftmp */
 	if (VN_CACHED(VFS_I(tip)) != 0) {
 		error = XFS_ERROR(EINVAL);
-		goto error0;
+		goto out_unlock;
 	}
 
 	/* Verify all data are being swapped */
@@ -183,7 +186,7 @@ xfs_swap_extents(
 	    sxp->sx_length != ip->i_d.di_size ||
 	    sxp->sx_length != tip->i_d.di_size) {
 		error = XFS_ERROR(EFAULT);
-		goto error0;
+		goto out_unlock;
 	}
 
 	/*
@@ -193,7 +196,7 @@ xfs_swap_extents(
 	 */
 	if ( XFS_IFORK_Q(ip) != XFS_IFORK_Q(tip) ) {
 		error = XFS_ERROR(EINVAL);
-		goto error0;
+		goto out_unlock;
 	}
 
 	/*
@@ -208,7 +211,7 @@ xfs_swap_extents(
 	    (sbp->bs_mtime.tv_sec != ip->i_d.di_mtime.t_sec) ||
 	    (sbp->bs_mtime.tv_nsec != ip->i_d.di_mtime.t_nsec)) {
 		error = XFS_ERROR(EBUSY);
-		goto error0;
+		goto out_unlock;
 	}
 
 	/* We need to fail if the file is memory mapped.  Once we have tossed
@@ -219,7 +222,7 @@ xfs_swap_extents(
 	 */
 	if (VN_MAPPED(VFS_I(ip))) {
 		error = XFS_ERROR(EBUSY);
-		goto error0;
+		goto out_unlock;
 	}
 
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
@@ -242,8 +245,7 @@ xfs_swap_extents(
 		xfs_iunlock(ip,  XFS_IOLOCK_EXCL);
 		xfs_iunlock(tip, XFS_IOLOCK_EXCL);
 		xfs_trans_cancel(tp, 0);
-		locked = 0;
-		goto error0;
+		goto out;
 	}
 	xfs_lock_two_inodes(ip, tip, XFS_ILOCK_EXCL);
 
@@ -253,19 +255,15 @@ xfs_swap_extents(
 	if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
 	     (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
 		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &aforkblks);
-		if (error) {
-			xfs_trans_cancel(tp, 0);
-			goto error0;
-		}
+		if (error)
+			goto out_trans_cancel;
 	}
 	if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
 	     (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
 		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
 			&taforkblks);
-		if (error) {
-			xfs_trans_cancel(tp, 0);
-			goto error0;
-		}
+		if (error)
+			goto out_trans_cancel;
 	}
 
 	/*
@@ -332,10 +330,10 @@ xfs_swap_extents(
 
 
 	IHOLD(ip);
-	xfs_trans_ijoin(tp, ip, lock_flags);
+	xfs_trans_ijoin(tp, ip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 
 	IHOLD(tip);
-	xfs_trans_ijoin(tp, tip, lock_flags);
+	xfs_trans_ijoin(tp, tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
 
 	xfs_trans_log_inode(tp, ip,  ilf_fields);
 	xfs_trans_log_inode(tp, tip, tilf_fields);
@@ -344,19 +342,19 @@ xfs_swap_extents(
 	 * If this is a synchronous mount, make sure that the
 	 * transaction goes to disk before returning to the user.
 	 */
-	if (mp->m_flags & XFS_MOUNT_WSYNC) {
+	if (mp->m_flags & XFS_MOUNT_WSYNC)
 		xfs_trans_set_sync(tp);
-	}
 
 	error = xfs_trans_commit(tp, XFS_TRANS_SWAPEXT);
-	locked = 0;
 
- error0:
-	if (locked) {
-		xfs_iunlock(ip,  lock_flags);
-		xfs_iunlock(tip, lock_flags);
-	}
-	if (tempifp != NULL)
-		kmem_free(tempifp);
+out_unlock:
+	xfs_iunlock(ip,  XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+	xfs_iunlock(tip, XFS_ILOCK_EXCL | XFS_IOLOCK_EXCL);
+out:
+	kmem_free(tempifp);
 	return error;
+
+out_trans_cancel:
+	xfs_trans_cancel(tp, 0);
+	goto out_unlock;
 }
diff --git a/fs/xfs/xfs_dinode.h b/fs/xfs/xfs_dinode.h
index 162e8726df5e..e5b153b2e6a3 100644
--- a/fs/xfs/xfs_dinode.h
+++ b/fs/xfs/xfs_dinode.h
@@ -103,7 +103,9 @@ typedef enum xfs_dinode_fmt {
 /*
  * Inode size for given fs.
  */
-#define	XFS_LITINO(mp)	((mp)->m_litino)
+#define XFS_LITINO(mp) \
+	((int)(((mp)->m_sb.sb_inodesize) - sizeof(struct xfs_dinode)))
+
 #define	XFS_BROOT_SIZE_ADJ	\
 	(XFS_BTREE_LBLOCK_LEN - sizeof(xfs_bmdr_block_t))
 
diff --git a/fs/xfs/xfs_dir2.c b/fs/xfs/xfs_dir2.c
index 1afb12278b8d..c657bec6d951 100644
--- a/fs/xfs/xfs_dir2.c
+++ b/fs/xfs/xfs_dir2.c
@@ -46,8 +46,6 @@
 
 struct xfs_name xfs_name_dotdot = {"..", 2};
 
-extern const struct xfs_nameops xfs_default_nameops;
-
 /*
  * ASCII case-insensitive (ie. A-Z) support for directories that was
  * used in IRIX.
diff --git a/fs/xfs/xfs_dir2_block.c b/fs/xfs/xfs_dir2_block.c
index e1f0a06aaf04..ab52e9e1c1ee 100644
--- a/fs/xfs/xfs_dir2_block.c
+++ b/fs/xfs/xfs_dir2_block.c
@@ -448,7 +448,6 @@ xfs_dir2_block_getdents(
 	xfs_mount_t		*mp;		/* filesystem mount point */
 	char			*ptr;		/* current data entry */
 	int			wantoff;	/* starting block offset */
-	xfs_ino_t		ino;
 	xfs_off_t		cook;
 
 	mp = dp->i_mount;
@@ -509,16 +508,12 @@ xfs_dir2_block_getdents(
 
 		cook = xfs_dir2_db_off_to_dataptr(mp, mp->m_dirdatablk,
 					    (char *)dep - (char *)block);
-		ino = be64_to_cpu(dep->inumber);
-#if XFS_BIG_INUMS
-		ino += mp->m_inoadd;
-#endif
 
 		/*
 		 * If it didn't fit, set the final offset to here & return.
 		 */
 		if (filldir(dirent, dep->name, dep->namelen, cook & 0x7fffffff,
-			    ino, DT_UNKNOWN)) {
+			    be64_to_cpu(dep->inumber), DT_UNKNOWN)) {
 			*offset = cook & 0x7fffffff;
 			xfs_da_brelse(NULL, bp);
 			return 0;
diff --git a/fs/xfs/xfs_dir2_data.h b/fs/xfs/xfs_dir2_data.h
index b816e0252739..efbc290c7fec 100644
--- a/fs/xfs/xfs_dir2_data.h
+++ b/fs/xfs/xfs_dir2_data.h
@@ -38,7 +38,7 @@ struct xfs_trans;
 
 /*
  * Directory address space divided into sections,
- * spaces separated by 32gb.
+ * spaces separated by 32GB.
  */
 #define	XFS_DIR2_SPACE_SIZE	(1ULL << (32 + XFS_DIR2_DATA_ALIGN_LOG))
 #define	XFS_DIR2_DATA_SPACE	0
diff --git a/fs/xfs/xfs_dir2_leaf.c b/fs/xfs/xfs_dir2_leaf.c
index ef805a374eec..fa913e459442 100644
--- a/fs/xfs/xfs_dir2_leaf.c
+++ b/fs/xfs/xfs_dir2_leaf.c
@@ -549,7 +549,7 @@ xfs_dir2_leaf_addname(
  * Check the internal consistency of a leaf1 block.
  * Pop an assert if something is wrong.
  */
-void
+STATIC void
 xfs_dir2_leaf_check(
 	xfs_inode_t		*dp,		/* incore directory inode */
 	xfs_dabuf_t		*bp)		/* leaf's buffer */
@@ -780,7 +780,6 @@ xfs_dir2_leaf_getdents(
 	int			ra_index;	/* *map index for read-ahead */
 	int			ra_offset;	/* map entry offset for ra */
 	int			ra_want;	/* readahead count wanted */
-	xfs_ino_t		ino;
 
 	/*
 	 * If the offset is at or past the largest allowed value,
@@ -1076,24 +1075,12 @@ xfs_dir2_leaf_getdents(
 			continue;
 		}
 
-		/*
-		 * Copy the entry into the putargs, and try formatting it.
-		 */
 		dep = (xfs_dir2_data_entry_t *)ptr;
-
 		length = xfs_dir2_data_entsize(dep->namelen);
 
-		ino = be64_to_cpu(dep->inumber);
-#if XFS_BIG_INUMS
-		ino += mp->m_inoadd;
-#endif
-
-		/*
-		 * Won't fit.  Return to caller.
-		 */
 		if (filldir(dirent, dep->name, dep->namelen,
 			    xfs_dir2_byte_to_dataptr(mp, curoff) & 0x7fffffff,
-			    ino, DT_UNKNOWN))
+			    be64_to_cpu(dep->inumber), DT_UNKNOWN))
 			break;
 
 		/*
diff --git a/fs/xfs/xfs_dir2_node.c b/fs/xfs/xfs_dir2_node.c
index fa6c3a5ddbc6..5a81ccd1045b 100644
--- a/fs/xfs/xfs_dir2_node.c
+++ b/fs/xfs/xfs_dir2_node.c
@@ -1104,7 +1104,7 @@ xfs_dir2_leafn_remove(
 	}
 	xfs_dir2_leafn_check(dp, bp);
 	/*
-	 * Return indication of whether this leaf block is emtpy enough
+	 * Return indication of whether this leaf block is empty enough
 	 * to justify trying to join it with a neighbor.
 	 */
 	*rval =
diff --git a/fs/xfs/xfs_dir2_sf.c b/fs/xfs/xfs_dir2_sf.c
index a8a8a6efad5b..e89734e84646 100644
--- a/fs/xfs/xfs_dir2_sf.c
+++ b/fs/xfs/xfs_dir2_sf.c
@@ -748,11 +748,7 @@ xfs_dir2_sf_getdents(
 	 * Put . entry unless we're starting past it.
 	 */
 	if (*offset <= dot_offset) {
-		ino = dp->i_ino;
-#if XFS_BIG_INUMS
-		ino += mp->m_inoadd;
-#endif
-		if (filldir(dirent, ".", 1, dot_offset & 0x7fffffff, ino, DT_DIR)) {
+		if (filldir(dirent, ".", 1, dot_offset & 0x7fffffff, dp->i_ino, DT_DIR)) {
 			*offset = dot_offset & 0x7fffffff;
 			return 0;
 		}
@@ -763,9 +759,6 @@ xfs_dir2_sf_getdents(
 	 */
 	if (*offset <= dotdot_offset) {
 		ino = xfs_dir2_sf_get_inumber(sfp, &sfp->hdr.parent);
-#if XFS_BIG_INUMS
-		ino += mp->m_inoadd;
-#endif
 		if (filldir(dirent, "..", 2, dotdot_offset & 0x7fffffff, ino, DT_DIR)) {
 			*offset = dotdot_offset & 0x7fffffff;
 			return 0;
@@ -786,10 +779,6 @@ xfs_dir2_sf_getdents(
 		}
 
 		ino = xfs_dir2_sf_get_inumber(sfp, xfs_dir2_sf_inumberp(sfep));
-#if XFS_BIG_INUMS
-		ino += mp->m_inoadd;
-#endif
-
 		if (filldir(dirent, sfep->name, sfep->namelen,
 			    off & 0x7fffffff, ino, DT_UNKNOWN)) {
 			*offset = off & 0x7fffffff;
diff --git a/fs/xfs/xfs_extfree_item.h b/fs/xfs/xfs_extfree_item.h
index 2f049f63e85f..0d22c56fdf64 100644
--- a/fs/xfs/xfs_extfree_item.h
+++ b/fs/xfs/xfs_extfree_item.h
@@ -33,12 +33,10 @@ typedef struct xfs_extent {
  * conversion routine.
  */
 
-#ifndef HAVE_FORMAT32
 typedef struct xfs_extent_32 {
 	__uint64_t	ext_start;
 	__uint32_t	ext_len;
 } __attribute__((packed)) xfs_extent_32_t;
-#endif
 
 typedef struct xfs_extent_64 {
 	__uint64_t	ext_start;
@@ -59,7 +57,6 @@ typedef struct xfs_efi_log_format {
 	xfs_extent_t		efi_extents[1];	/* array of extents to free */
 } xfs_efi_log_format_t;
 
-#ifndef HAVE_FORMAT32
 typedef struct xfs_efi_log_format_32 {
 	__uint16_t		efi_type;	/* efi log item type */
 	__uint16_t		efi_size;	/* size of this item */
@@ -67,7 +64,6 @@ typedef struct xfs_efi_log_format_32 {
 	__uint64_t		efi_id;		/* efi identifier */
 	xfs_extent_32_t		efi_extents[1];	/* array of extents to free */
 } __attribute__((packed)) xfs_efi_log_format_32_t;
-#endif
 
 typedef struct xfs_efi_log_format_64 {
 	__uint16_t		efi_type;	/* efi log item type */
@@ -90,7 +86,6 @@ typedef struct xfs_efd_log_format {
 	xfs_extent_t		efd_extents[1];	/* array of extents freed */
 } xfs_efd_log_format_t;
 
-#ifndef HAVE_FORMAT32
 typedef struct xfs_efd_log_format_32 {
 	__uint16_t		efd_type;	/* efd log item type */
 	__uint16_t		efd_size;	/* size of this item */
@@ -98,7 +93,6 @@ typedef struct xfs_efd_log_format_32 {
 	__uint64_t		efd_efi_id;	/* id of corresponding efi */
 	xfs_extent_32_t		efd_extents[1];	/* array of extents freed */
 } __attribute__((packed)) xfs_efd_log_format_32_t;
-#endif
 
 typedef struct xfs_efd_log_format_64 {
 	__uint16_t		efd_type;	/* efd log item type */
diff --git a/fs/xfs/xfs_filestream.c b/fs/xfs/xfs_filestream.c
index f3bb75da384e..6c87c8f304ef 100644
--- a/fs/xfs/xfs_filestream.c
+++ b/fs/xfs/xfs_filestream.c
@@ -140,7 +140,7 @@ _xfs_filestream_pick_ag(
 	xfs_extlen_t	minlen)
 {
 	int		err, trylock, nscan;
-	xfs_extlen_t	delta, longest, need, free, minfree, maxfree = 0;
+	xfs_extlen_t	longest, free, minfree, maxfree = 0;
 	xfs_agnumber_t	ag, max_ag = NULLAGNUMBER;
 	struct xfs_perag *pag;
 
@@ -186,12 +186,7 @@ _xfs_filestream_pick_ag(
 			goto next_ag;
 		}
 
-		need = XFS_MIN_FREELIST_PAG(pag, mp);
-		delta = need > pag->pagf_flcount ? need - pag->pagf_flcount : 0;
-		longest = (pag->pagf_longest > delta) ?
-		          (pag->pagf_longest - delta) :
-		          (pag->pagf_flcount > 0 || pag->pagf_longest > 0);
-
+		longest = xfs_alloc_longest_free_extent(mp, pag);
 		if (((minlen && longest >= minlen) ||
 		     (!minlen && pag->pagf_freeblks >= minfree)) &&
 		    (!pag->pagf_metadata || !(flags & XFS_PICK_USERDATA) ||
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 680d0e0ec932..8379e3bca26c 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -576,7 +576,7 @@ out:
 	if (fdblks_delta) {
 		/*
 		 * If we are putting blocks back here, m_resblks_avail is
-		 * already at it's max so this will put it in the free pool.
+		 * already at its max so this will put it in the free pool.
 		 *
 		 * If we need space, we'll either succeed in getting it
 		 * from the free block count or we'll get an enospc. If
diff --git a/fs/xfs/xfs_ialloc.c b/fs/xfs/xfs_ialloc.c
index ab016e5ae7be..3120a3a5e20f 100644
--- a/fs/xfs/xfs_ialloc.c
+++ b/fs/xfs/xfs_ialloc.c
@@ -230,7 +230,7 @@ xfs_ialloc_ag_alloc(
 		args.minalignslop = xfs_ialloc_cluster_alignment(&args) - 1;
 
 		/* Allow space for the inode btree to split. */
-		args.minleft = XFS_IN_MAXLEVELS(args.mp) - 1;
+		args.minleft = args.mp->m_in_maxlevels - 1;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 	} else
@@ -270,7 +270,7 @@ xfs_ialloc_ag_alloc(
 		/*
 		 * Allow space for the inode btree to split.
 		 */
-		args.minleft = XFS_IN_MAXLEVELS(args.mp) - 1;
+		args.minleft = args.mp->m_in_maxlevels - 1;
 		if ((error = xfs_alloc_vextent(&args)))
 			return error;
 	}
@@ -349,7 +349,7 @@ xfs_ialloc_ag_alloc(
 		 * Initialize all inodes in this buffer and then log them.
 		 *
 		 * XXX: It would be much better if we had just one transaction to
-		 *      log a whole cluster of inodes instead of all the indivdual
+		 *      log a whole cluster of inodes instead of all the individual
 		 *      transactions causing a lot of log traffic.
 		 */
 		xfs_biozero(fbuf, 0, ninodes << args.mp->m_sb.sb_inodelog);
@@ -943,7 +943,7 @@ nextag:
 	ASSERT((XFS_AGINO_TO_OFFSET(mp, rec.ir_startino) %
 				   XFS_INODES_PER_CHUNK) == 0);
 	ino = XFS_AGINO_TO_INO(mp, agno, rec.ir_startino + offset);
-	XFS_INOBT_CLR_FREE(&rec, offset);
+	rec.ir_free &= ~XFS_INOBT_MASK(offset);
 	rec.ir_freecount--;
 	if ((error = xfs_inobt_update(cur, rec.ir_startino, rec.ir_freecount,
 			rec.ir_free)))
@@ -1105,11 +1105,11 @@ xfs_difree(
 	 */
 	off = agino - rec.ir_startino;
 	ASSERT(off >= 0 && off < XFS_INODES_PER_CHUNK);
-	ASSERT(!XFS_INOBT_IS_FREE(&rec, off));
+	ASSERT(!(rec.ir_free & XFS_INOBT_MASK(off)));
 	/*
 	 * Mark the inode free & increment the count.
 	 */
-	XFS_INOBT_SET_FREE(&rec, off);
+	rec.ir_free |= XFS_INOBT_MASK(off);
 	rec.ir_freecount++;
 
 	/*
diff --git a/fs/xfs/xfs_ialloc_btree.c b/fs/xfs/xfs_ialloc_btree.c
index 99f2408e8d8e..c282a9af5393 100644
--- a/fs/xfs/xfs_ialloc_btree.c
+++ b/fs/xfs/xfs_ialloc_btree.c
@@ -164,7 +164,7 @@ xfs_inobt_init_rec_from_cur(
 }
 
 /*
- * intial value of ptr for lookup
+ * initial value of ptr for lookup
  */
 STATIC void
 xfs_inobt_init_ptr_from_cur(
diff --git a/fs/xfs/xfs_ialloc_btree.h b/fs/xfs/xfs_ialloc_btree.h
index 5580e255ff06..f782ad0c4769 100644
--- a/fs/xfs/xfs_ialloc_btree.h
+++ b/fs/xfs/xfs_ialloc_btree.h
@@ -32,14 +32,14 @@ struct xfs_mount;
 #define	XFS_IBT_MAGIC	0x49414254	/* 'IABT' */
 
 typedef	__uint64_t	xfs_inofree_t;
-#define	XFS_INODES_PER_CHUNK	(NBBY * sizeof(xfs_inofree_t))
+#define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
 #define	XFS_INODES_PER_CHUNK_LOG	(XFS_NBBYLOG + 3)
-#define	XFS_INOBT_ALL_FREE	((xfs_inofree_t)-1)
+#define	XFS_INOBT_ALL_FREE		((xfs_inofree_t)-1)
+#define	XFS_INOBT_MASK(i)		((xfs_inofree_t)1 << (i))
 
 static inline xfs_inofree_t xfs_inobt_maskn(int i, int n)
 {
-	return (((n) >= XFS_INODES_PER_CHUNK ? \
-		(xfs_inofree_t)0 : ((xfs_inofree_t)1 << (n))) - 1) << (i);
+	return ((n >= XFS_INODES_PER_CHUNK ? 0 : XFS_INOBT_MASK(n)) - 1) << i;
 }
 
 /*
@@ -69,20 +69,6 @@ typedef struct xfs_inobt_key {
 typedef __be32 xfs_inobt_ptr_t;
 
 /*
- * Bit manipulations for ir_free.
- */
-#define	XFS_INOBT_MASK(i)		((xfs_inofree_t)1 << (i))
-#define	XFS_INOBT_IS_FREE(rp,i)		\
-		(((rp)->ir_free & XFS_INOBT_MASK(i)) != 0)
-#define	XFS_INOBT_SET_FREE(rp,i)	((rp)->ir_free |= XFS_INOBT_MASK(i))
-#define	XFS_INOBT_CLR_FREE(rp,i)	((rp)->ir_free &= ~XFS_INOBT_MASK(i))
-
-/*
- * Maximum number of inode btree levels.
- */
-#define	XFS_IN_MAXLEVELS(mp)		((mp)->m_in_maxlevels)
-
-/*
  * block numbers in the AG.
  */
 #define	XFS_IBT_BLOCK(mp)		((xfs_agblock_t)(XFS_CNT_BLOCK(mp) + 1))
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 1f175fa34b22..f879c1bc4b96 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -122,7 +122,7 @@ typedef struct xfs_ictimestamp {
 
 /*
  * NOTE:  This structure must be kept identical to struct xfs_dinode
- * 	  in xfs_dinode.h except for the endianess annotations.
+ * 	  in xfs_dinode.h except for the endianness annotations.
  */
 typedef struct xfs_icdinode {
 	__uint16_t	di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
diff --git a/fs/xfs/xfs_inode_item.h b/fs/xfs/xfs_inode_item.h
index 9957d0602d54..a52ac125f055 100644
--- a/fs/xfs/xfs_inode_item.h
+++ b/fs/xfs/xfs_inode_item.h
@@ -40,7 +40,6 @@ typedef struct xfs_inode_log_format {
 	__int32_t		ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_t;
 
-#ifndef HAVE_FORMAT32
 typedef struct xfs_inode_log_format_32 {
 	__uint16_t		ilf_type;	/* inode log item type */
 	__uint16_t		ilf_size;	/* size of this item */
@@ -56,7 +55,6 @@ typedef struct xfs_inode_log_format_32 {
 	__int32_t		ilf_len;	/* len of inode buffer */
 	__int32_t		ilf_boffset;	/* off of inode in buffer */
 } __attribute__((packed)) xfs_inode_log_format_32_t;
-#endif
 
 typedef struct xfs_inode_log_format_64 {
 	__uint16_t		ilf_type;	/* inode log item type */
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index ee1a0c134cc2..a1cc1322fc0f 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -63,7 +63,7 @@ typedef enum {
  */
 
 typedef struct xfs_iomap {
-	xfs_daddr_t		iomap_bn;	/* first 512b blk of mapping */
+	xfs_daddr_t		iomap_bn;	/* first 512B blk of mapping */
 	xfs_buftarg_t		*iomap_target;
 	xfs_off_t		iomap_offset;	/* offset of mapping, bytes */
 	xfs_off_t		iomap_bsize;	/* size of mapping, bytes */
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index cf98a805ec90..aeb2d2221c7d 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -83,7 +83,12 @@ xfs_bulkstat_one_iget(
 	buf->bs_uid = dic->di_uid;
 	buf->bs_gid = dic->di_gid;
 	buf->bs_size = dic->di_size;
-	vn_atime_to_bstime(VFS_I(ip), &buf->bs_atime);
+	/*
+	 * We are reading the atime from the Linux inode because the
+	 * dinode might not be uptodate.
+	 */
+	buf->bs_atime.tv_sec = VFS_I(ip)->i_atime.tv_sec;
+	buf->bs_atime.tv_nsec = VFS_I(ip)->i_atime.tv_nsec;
 	buf->bs_mtime.tv_sec = dic->di_mtime.t_sec;
 	buf->bs_mtime.tv_nsec = dic->di_mtime.t_nsec;
 	buf->bs_ctime.tv_sec = dic->di_ctime.t_sec;
@@ -579,7 +584,7 @@ xfs_bulkstat(
 				 * first inode of the cluster.
 				 *
 				 * Careful with clustidx.   There can be
-				 * multple clusters per chunk, a single
+				 * multiple clusters per chunk, a single
 				 * cluster per chunk or a cluster that has
 				 * inodes represented from several different
 				 * chunks (if blocksize is large).
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index f4726f702a9e..f76c6d7cea21 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -574,7 +574,7 @@ xfs_log_mount(
 	error = xfs_trans_ail_init(mp);
 	if (error) {
 		cmn_err(CE_WARN, "XFS: AIL initialisation failed: error %d", error);
-		goto error;
+		goto out_free_log;
 	}
 	mp->m_log->l_ailp = mp->m_ail;
 
@@ -594,20 +594,22 @@ xfs_log_mount(
 			mp->m_flags |= XFS_MOUNT_RDONLY;
 		if (error) {
 			cmn_err(CE_WARN, "XFS: log mount/recovery failed: error %d", error);
-			goto error;
+			goto out_destroy_ail;
 		}
 	}
 
 	/* Normal transactions can now occur */
 	mp->m_log->l_flags &= ~XLOG_ACTIVE_RECOVERY;
 
-	/* End mounting message in xfs_log_mount_finish */
 	return 0;
-error:
-	xfs_log_unmount_dealloc(mp);
+
+out_destroy_ail:
+	xfs_trans_ail_destroy(mp);
+out_free_log:
+	xlog_dealloc_log(mp->m_log);
 out:
 	return error;
-}	/* xfs_log_mount */
+}
 
 /*
  * Finish the recovery of the file system.  This is separate from
@@ -633,19 +635,6 @@ xfs_log_mount_finish(xfs_mount_t *mp)
 }
 
 /*
- * Unmount processing for the log.
- */
-int
-xfs_log_unmount(xfs_mount_t *mp)
-{
-	int		error;
-
-	error = xfs_log_unmount_write(mp);
-	xfs_log_unmount_dealloc(mp);
-	return error;
-}
-
-/*
  * Final log writes as part of unmount.
  *
  * Mark the filesystem clean as unmount happens.  Note that during relocation
@@ -795,7 +784,7 @@ xfs_log_unmount_write(xfs_mount_t *mp)
  * and deallocate the log as the aild references the log.
  */
 void
-xfs_log_unmount_dealloc(xfs_mount_t *mp)
+xfs_log_unmount(xfs_mount_t *mp)
 {
 	xfs_trans_ail_destroy(mp);
 	xlog_dealloc_log(mp->m_log);
@@ -1109,7 +1098,7 @@ xlog_bdstrat_cb(struct xfs_buf *bp)
 /*
  * Return size of each in-core log record buffer.
  *
- * All machines get 8 x 32KB buffers by default, unless tuned otherwise.
+ * All machines get 8 x 32kB buffers by default, unless tuned otherwise.
  *
  * If the filesystem blocksize is too large, we may need to choose a
  * larger size since the directory code currently logs entire blocks.
@@ -1139,8 +1128,8 @@ xlog_get_iclog_buffer_size(xfs_mount_t	*mp,
 		}
 
 		if (xfs_sb_version_haslogv2(&mp->m_sb)) {
-			/* # headers = size / 32K
-			 * one header holds cycles from 32K of data
+			/* # headers = size / 32k
+			 * one header holds cycles from 32k of data
 			 */
 
 			xhdrs = mp->m_logbsize / XLOG_HEADER_CYCLE_SIZE;
@@ -1156,7 +1145,7 @@ xlog_get_iclog_buffer_size(xfs_mount_t	*mp,
 		goto done;
 	}
 
-	/* All machines use 32KB buffers by default. */
+	/* All machines use 32kB buffers by default. */
 	log->l_iclog_size = XLOG_BIG_RECORD_BSIZE;
 	log->l_iclog_size_log = XLOG_BIG_RECORD_BSHIFT;
 
@@ -1164,32 +1153,8 @@ xlog_get_iclog_buffer_size(xfs_mount_t	*mp,
 	log->l_iclog_hsize = BBSIZE;
 	log->l_iclog_heads = 1;
 
-	/*
-	 * For 16KB, we use 3 32KB buffers.  For 32KB block sizes, we use
-	 * 4 32KB buffers.  For 64KB block sizes, we use 8 32KB buffers.
-	 */
-	if (mp->m_sb.sb_blocksize >= 16*1024) {
-		log->l_iclog_size = XLOG_BIG_RECORD_BSIZE;
-		log->l_iclog_size_log = XLOG_BIG_RECORD_BSHIFT;
-		if (mp->m_logbufs <= 0) {
-			switch (mp->m_sb.sb_blocksize) {
-			    case 16*1024:			/* 16 KB */
-				log->l_iclog_bufs = 3;
-				break;
-			    case 32*1024:			/* 32 KB */
-				log->l_iclog_bufs = 4;
-				break;
-			    case 64*1024:			/* 64 KB */
-				log->l_iclog_bufs = 8;
-				break;
-			    default:
-				xlog_panic("XFS: Invalid blocksize");
-				break;
-			}
-		}
-	}
-
-done:	/* are we being asked to make the sizes selected above visible? */
+done:
+	/* are we being asked to make the sizes selected above visible? */
 	if (mp->m_logbufs == 0)
 		mp->m_logbufs = log->l_iclog_bufs;
 	if (mp->m_logbsize == 0)
@@ -3214,7 +3179,7 @@ xlog_state_want_sync(xlog_t *log, xlog_in_core_t *iclog)
  */
 
 /*
- * Free a used ticket when it's refcount falls to zero.
+ * Free a used ticket when its refcount falls to zero.
  */
 void
 xfs_log_ticket_put(
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index 8a3e84e900a3..d0c9baa50b1a 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -170,9 +170,8 @@ int	  xfs_log_write(struct xfs_mount *mp,
 			int		 nentries,
 			xfs_log_ticket_t ticket,
 			xfs_lsn_t	 *start_lsn);
-int	  xfs_log_unmount(struct xfs_mount *mp);
 int	  xfs_log_unmount_write(struct xfs_mount *mp);
-void      xfs_log_unmount_dealloc(struct xfs_mount *mp);
+void      xfs_log_unmount(struct xfs_mount *mp);
 int	  xfs_log_force_umount(struct xfs_mount *mp, int logerror);
 int	  xfs_log_need_covered(struct xfs_mount *mp);
 
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 654167be0efb..bcad5f4c1fd1 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -359,7 +359,7 @@ typedef struct xlog_in_core {
 	int			ic_size;
 	int			ic_offset;
 	int			ic_bwritecnt;
-	ushort_t		ic_state;
+	unsigned short		ic_state;
 	char			*ic_datap;	/* pointer to iclog data */
 #ifdef XFS_LOG_TRACE
 	struct ktrace		*ic_trace;
@@ -455,7 +455,6 @@ extern void	 xlog_recover_process_iunlinks(xlog_t *log);
 
 extern struct xfs_buf *xlog_get_bp(xlog_t *, int);
 extern void	 xlog_put_bp(struct xfs_buf *);
-extern int	 xlog_bread(xlog_t *, xfs_daddr_t, int, struct xfs_buf *);
 
 extern kmem_zone_t	*xfs_log_ticket_zone;
 
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 61af610d79b3..7ba450116d4f 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -94,12 +94,30 @@ xlog_put_bp(
 	xfs_buf_free(bp);
 }
 
+STATIC xfs_caddr_t
+xlog_align(
+	xlog_t		*log,
+	xfs_daddr_t	blk_no,
+	int		nbblks,
+	xfs_buf_t	*bp)
+{
+	xfs_caddr_t	ptr;
+
+	if (!log->l_sectbb_log)
+		return XFS_BUF_PTR(bp);
+
+	ptr = XFS_BUF_PTR(bp) + BBTOB((int)blk_no & log->l_sectbb_mask);
+	ASSERT(XFS_BUF_SIZE(bp) >=
+		BBTOB(nbblks + (blk_no & log->l_sectbb_mask)));
+	return ptr;
+}
+
 
 /*
  * nbblks should be uint, but oh well.  Just want to catch that 32-bit length.
  */
-int
-xlog_bread(
+STATIC int
+xlog_bread_noalign(
 	xlog_t		*log,
 	xfs_daddr_t	blk_no,
 	int		nbblks,
@@ -137,6 +155,24 @@ xlog_bread(
 	return error;
 }
 
+STATIC int
+xlog_bread(
+	xlog_t		*log,
+	xfs_daddr_t	blk_no,
+	int		nbblks,
+	xfs_buf_t	*bp,
+	xfs_caddr_t	*offset)
+{
+	int		error;
+
+	error = xlog_bread_noalign(log, blk_no, nbblks, bp);
+	if (error)
+		return error;
+
+	*offset = xlog_align(log, blk_no, nbblks, bp);
+	return 0;
+}
+
 /*
  * Write out the buffer at the given block for the given number of blocks.
  * The buffer is kept locked across the write and is returned locked.
@@ -180,24 +216,6 @@ xlog_bwrite(
 	return error;
 }
 
-STATIC xfs_caddr_t
-xlog_align(
-	xlog_t		*log,
-	xfs_daddr_t	blk_no,
-	int		nbblks,
-	xfs_buf_t	*bp)
-{
-	xfs_caddr_t	ptr;
-
-	if (!log->l_sectbb_log)
-		return XFS_BUF_PTR(bp);
-
-	ptr = XFS_BUF_PTR(bp) + BBTOB((int)blk_no & log->l_sectbb_mask);
-	ASSERT(XFS_BUF_SIZE(bp) >=
-		BBTOB(nbblks + (blk_no & log->l_sectbb_mask)));
-	return ptr;
-}
-
 #ifdef DEBUG
 /*
  * dump debug superblock and log record information
@@ -211,11 +229,11 @@ xlog_header_check_dump(
 
 	cmn_err(CE_DEBUG, "%s:  SB : uuid = ", __func__);
 	for (b = 0; b < 16; b++)
-		cmn_err(CE_DEBUG, "%02x", ((uchar_t *)&mp->m_sb.sb_uuid)[b]);
+		cmn_err(CE_DEBUG, "%02x", ((__uint8_t *)&mp->m_sb.sb_uuid)[b]);
 	cmn_err(CE_DEBUG, ", fmt = %d\n", XLOG_FMT);
 	cmn_err(CE_DEBUG, "    log : uuid = ");
 	for (b = 0; b < 16; b++)
-		cmn_err(CE_DEBUG, "%02x",((uchar_t *)&head->h_fs_uuid)[b]);
+		cmn_err(CE_DEBUG, "%02x", ((__uint8_t *)&head->h_fs_uuid)[b]);
 	cmn_err(CE_DEBUG, ", fmt = %d\n", be32_to_cpu(head->h_fmt));
 }
 #else
@@ -321,9 +339,9 @@ xlog_find_cycle_start(
 
 	mid_blk = BLK_AVG(first_blk, *last_blk);
 	while (mid_blk != first_blk && mid_blk != *last_blk) {
-		if ((error = xlog_bread(log, mid_blk, 1, bp)))
+		error = xlog_bread(log, mid_blk, 1, bp, &offset);
+		if (error)
 			return error;
-		offset = xlog_align(log, mid_blk, 1, bp);
 		mid_cycle = xlog_get_cycle(offset);
 		if (mid_cycle == cycle) {
 			*last_blk = mid_blk;
@@ -379,10 +397,10 @@ xlog_find_verify_cycle(
 
 		bcount = min(bufblks, (start_blk + nbblks - i));
 
-		if ((error = xlog_bread(log, i, bcount, bp)))
+		error = xlog_bread(log, i, bcount, bp, &buf);
+		if (error)
 			goto out;
 
-		buf = xlog_align(log, i, bcount, bp);
 		for (j = 0; j < bcount; j++) {
 			cycle = xlog_get_cycle(buf);
 			if (cycle == stop_on_cycle_no) {
@@ -436,9 +454,9 @@ xlog_find_verify_log_record(
 			return ENOMEM;
 		smallmem = 1;
 	} else {
-		if ((error = xlog_bread(log, start_blk, num_blks, bp)))
+		error = xlog_bread(log, start_blk, num_blks, bp, &offset);
+		if (error)
 			goto out;
-		offset = xlog_align(log, start_blk, num_blks, bp);
 		offset += ((num_blks - 1) << BBSHIFT);
 	}
 
@@ -453,9 +471,9 @@ xlog_find_verify_log_record(
 		}
 
 		if (smallmem) {
-			if ((error = xlog_bread(log, i, 1, bp)))
+			error = xlog_bread(log, i, 1, bp, &offset);
+			if (error)
 				goto out;
-			offset = xlog_align(log, i, 1, bp);
 		}
 
 		head = (xlog_rec_header_t *)offset;
@@ -559,15 +577,18 @@ xlog_find_head(
 	bp = xlog_get_bp(log, 1);
 	if (!bp)
 		return ENOMEM;
-	if ((error = xlog_bread(log, 0, 1, bp)))
+
+	error = xlog_bread(log, 0, 1, bp, &offset);
+	if (error)
 		goto bp_err;
-	offset = xlog_align(log, 0, 1, bp);
+
 	first_half_cycle = xlog_get_cycle(offset);
 
 	last_blk = head_blk = log_bbnum - 1;	/* get cycle # of last block */
-	if ((error = xlog_bread(log, last_blk, 1, bp)))
+	error = xlog_bread(log, last_blk, 1, bp, &offset);
+	if (error)
 		goto bp_err;
-	offset = xlog_align(log, last_blk, 1, bp);
+
 	last_half_cycle = xlog_get_cycle(offset);
 	ASSERT(last_half_cycle != 0);
 
@@ -817,9 +838,10 @@ xlog_find_tail(
 	if (!bp)
 		return ENOMEM;
 	if (*head_blk == 0) {				/* special case */
-		if ((error = xlog_bread(log, 0, 1, bp)))
+		error = xlog_bread(log, 0, 1, bp, &offset);
+		if (error)
 			goto bread_err;
-		offset = xlog_align(log, 0, 1, bp);
+
 		if (xlog_get_cycle(offset) == 0) {
 			*tail_blk = 0;
 			/* leave all other log inited values alone */
@@ -832,9 +854,10 @@ xlog_find_tail(
 	 */
 	ASSERT(*head_blk < INT_MAX);
 	for (i = (int)(*head_blk) - 1; i >= 0; i--) {
-		if ((error = xlog_bread(log, i, 1, bp)))
+		error = xlog_bread(log, i, 1, bp, &offset);
+		if (error)
 			goto bread_err;
-		offset = xlog_align(log, i, 1, bp);
+
 		if (XLOG_HEADER_MAGIC_NUM == be32_to_cpu(*(__be32 *)offset)) {
 			found = 1;
 			break;
@@ -848,9 +871,10 @@ xlog_find_tail(
 	 */
 	if (!found) {
 		for (i = log->l_logBBsize - 1; i >= (int)(*head_blk); i--) {
-			if ((error = xlog_bread(log, i, 1, bp)))
+			error = xlog_bread(log, i, 1, bp, &offset);
+			if (error)
 				goto bread_err;
-			offset = xlog_align(log, i, 1, bp);
+
 			if (XLOG_HEADER_MAGIC_NUM ==
 			    be32_to_cpu(*(__be32 *)offset)) {
 				found = 2;
@@ -922,10 +946,10 @@ xlog_find_tail(
 	if (*head_blk == after_umount_blk &&
 	    be32_to_cpu(rhead->h_num_logops) == 1) {
 		umount_data_blk = (i + hblks) % log->l_logBBsize;
-		if ((error = xlog_bread(log, umount_data_blk, 1, bp))) {
+		error = xlog_bread(log, umount_data_blk, 1, bp, &offset);
+		if (error)
 			goto bread_err;
-		}
-		offset = xlog_align(log, umount_data_blk, 1, bp);
+
 		op_head = (xlog_op_header_t *)offset;
 		if (op_head->oh_flags & XLOG_UNMOUNT_TRANS) {
 			/*
@@ -1017,9 +1041,10 @@ xlog_find_zeroed(
 	bp = xlog_get_bp(log, 1);
 	if (!bp)
 		return ENOMEM;
-	if ((error = xlog_bread(log, 0, 1, bp)))
+	error = xlog_bread(log, 0, 1, bp, &offset);
+	if (error)
 		goto bp_err;
-	offset = xlog_align(log, 0, 1, bp);
+
 	first_cycle = xlog_get_cycle(offset);
 	if (first_cycle == 0) {		/* completely zeroed log */
 		*blk_no = 0;
@@ -1028,9 +1053,10 @@ xlog_find_zeroed(
 	}
 
 	/* check partially zeroed log */
-	if ((error = xlog_bread(log, log_bbnum-1, 1, bp)))
+	error = xlog_bread(log, log_bbnum-1, 1, bp, &offset);
+	if (error)
 		goto bp_err;
-	offset = xlog_align(log, log_bbnum-1, 1, bp);
+
 	last_cycle = xlog_get_cycle(offset);
 	if (last_cycle != 0) {		/* log completely written to */
 		xlog_put_bp(bp);
@@ -1152,10 +1178,10 @@ xlog_write_log_records(
 	 */
 	balign = XLOG_SECTOR_ROUNDDOWN_BLKNO(log, start_block);
 	if (balign != start_block) {
-		if ((error = xlog_bread(log, start_block, 1, bp))) {
-			xlog_put_bp(bp);
-			return error;
-		}
+		error = xlog_bread_noalign(log, start_block, 1, bp);
+		if (error)
+			goto out_put_bp;
+
 		j = start_block - balign;
 	}
 
@@ -1175,10 +1201,14 @@ xlog_write_log_records(
 			balign = BBTOB(ealign - start_block);
 			error = XFS_BUF_SET_PTR(bp, offset + balign,
 						BBTOB(sectbb));
-			if (!error)
-				error = xlog_bread(log, ealign, sectbb, bp);
-			if (!error)
-				error = XFS_BUF_SET_PTR(bp, offset, bufblks);
+			if (error)
+				break;
+
+			error = xlog_bread_noalign(log, ealign, sectbb, bp);
+			if (error)
+				break;
+
+			error = XFS_BUF_SET_PTR(bp, offset, bufblks);
 			if (error)
 				break;
 		}
@@ -1195,6 +1225,8 @@ xlog_write_log_records(
 		start_block += endcount;
 		j = 0;
 	}
+
+ out_put_bp:
 	xlog_put_bp(bp);
 	return error;
 }
@@ -2511,16 +2543,10 @@ xlog_recover_do_inode_trans(
 	}
 
 write_inode_buffer:
-	if (ITEM_TYPE(item) == XFS_LI_INODE) {
-		ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
-		bp->b_mount = mp;
-		XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
-		xfs_bdwrite(mp, bp);
-	} else {
-		XFS_BUF_STALE(bp);
-		error = xfs_bwrite(mp, bp);
-	}
-
+	ASSERT(bp->b_mount == NULL || bp->b_mount == mp);
+	bp->b_mount = mp;
+	XFS_BUF_SET_IODONE_FUNC(bp, xlog_recover_iodone);
+	xfs_bdwrite(mp, bp);
 error:
 	if (need_free)
 		kmem_free(in_f);
@@ -2769,51 +2795,48 @@ xlog_recover_do_trans(
 	int			error = 0;
 	xlog_recover_item_t	*item, *first_item;
 
-	if ((error = xlog_recover_reorder_trans(trans)))
+	error = xlog_recover_reorder_trans(trans);
+	if (error)
 		return error;
+
 	first_item = item = trans->r_itemq;
 	do {
-		/*
-		 * we don't need to worry about the block number being
-		 * truncated in > 1 TB buffers because in user-land,
-		 * we're now n32 or 64-bit so xfs_daddr_t is 64-bits so
-		 * the blknos will get through the user-mode buffer
-		 * cache properly.  The only bad case is o32 kernels
-		 * where xfs_daddr_t is 32-bits but mount will warn us
-		 * off a > 1 TB filesystem before we get here.
-		 */
-		if ((ITEM_TYPE(item) == XFS_LI_BUF)) {
-			if  ((error = xlog_recover_do_buffer_trans(log, item,
-								 pass)))
-				break;
-		} else if ((ITEM_TYPE(item) == XFS_LI_INODE)) {
-			if ((error = xlog_recover_do_inode_trans(log, item,
-								pass)))
-				break;
-		} else if (ITEM_TYPE(item) == XFS_LI_EFI) {
-			if ((error = xlog_recover_do_efi_trans(log, item, trans->r_lsn,
-						  pass)))
-				break;
-		} else if (ITEM_TYPE(item) == XFS_LI_EFD) {
+		switch (ITEM_TYPE(item)) {
+		case XFS_LI_BUF:
+			error = xlog_recover_do_buffer_trans(log, item, pass);
+			break;
+		case XFS_LI_INODE:
+			error = xlog_recover_do_inode_trans(log, item, pass);
+			break;
+		case XFS_LI_EFI:
+			error = xlog_recover_do_efi_trans(log, item,
+							  trans->r_lsn, pass);
+			break;
+		case XFS_LI_EFD:
 			xlog_recover_do_efd_trans(log, item, pass);
-		} else if (ITEM_TYPE(item) == XFS_LI_DQUOT) {
-			if ((error = xlog_recover_do_dquot_trans(log, item,
-								   pass)))
-					break;
-		} else if ((ITEM_TYPE(item) == XFS_LI_QUOTAOFF)) {
-			if ((error = xlog_recover_do_quotaoff_trans(log, item,
-								   pass)))
-					break;
-		} else {
-			xlog_warn("XFS: xlog_recover_do_trans");
+			error = 0;
+			break;
+		case XFS_LI_DQUOT:
+			error = xlog_recover_do_dquot_trans(log, item, pass);
+			break;
+		case XFS_LI_QUOTAOFF:
+			error = xlog_recover_do_quotaoff_trans(log, item,
+							       pass);
+			break;
+		default:
+			xlog_warn(
+	"XFS: invalid item type (%d) xlog_recover_do_trans", ITEM_TYPE(item));
 			ASSERT(0);
 			error = XFS_ERROR(EIO);
 			break;
 		}
+
+		if (error)
+			return error;
 		item = item->ri_next;
 	} while (first_item != item);
 
-	return error;
+	return 0;
 }
 
 /*
@@ -3490,9 +3513,11 @@ xlog_do_recovery_pass(
 		hbp = xlog_get_bp(log, 1);
 		if (!hbp)
 			return ENOMEM;
-		if ((error = xlog_bread(log, tail_blk, 1, hbp)))
+
+		error = xlog_bread(log, tail_blk, 1, hbp, &offset);
+		if (error)
 			goto bread_err1;
-		offset = xlog_align(log, tail_blk, 1, hbp);
+
 		rhead = (xlog_rec_header_t *)offset;
 		error = xlog_valid_rec_header(log, rhead, tail_blk);
 		if (error)
@@ -3526,9 +3551,10 @@ xlog_do_recovery_pass(
 	memset(rhash, 0, sizeof(rhash));
 	if (tail_blk <= head_blk) {
 		for (blk_no = tail_blk; blk_no < head_blk; ) {
-			if ((error = xlog_bread(log, blk_no, hblks, hbp)))
+			error = xlog_bread(log, blk_no, hblks, hbp, &offset);
+			if (error)
 				goto bread_err2;
-			offset = xlog_align(log, blk_no, hblks, hbp);
+
 			rhead = (xlog_rec_header_t *)offset;
 			error = xlog_valid_rec_header(log, rhead, blk_no);
 			if (error)
@@ -3536,10 +3562,11 @@ xlog_do_recovery_pass(
 
 			/* blocks in data section */
 			bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
-			error = xlog_bread(log, blk_no + hblks, bblks, dbp);
+			error = xlog_bread(log, blk_no + hblks, bblks, dbp,
+					   &offset);
 			if (error)
 				goto bread_err2;
-			offset = xlog_align(log, blk_no + hblks, bblks, dbp);
+
 			xlog_unpack_data(rhead, offset, log);
 			if ((error = xlog_recover_process_data(log,
 						rhash, rhead, offset, pass)))
@@ -3562,10 +3589,10 @@ xlog_do_recovery_pass(
 			wrapped_hblks = 0;
 			if (blk_no + hblks <= log->l_logBBsize) {
 				/* Read header in one read */
-				error = xlog_bread(log, blk_no, hblks, hbp);
+				error = xlog_bread(log, blk_no, hblks, hbp,
+						   &offset);
 				if (error)
 					goto bread_err2;
-				offset = xlog_align(log, blk_no, hblks, hbp);
 			} else {
 				/* This LR is split across physical log end */
 				if (blk_no != log->l_logBBsize) {
@@ -3573,12 +3600,13 @@ xlog_do_recovery_pass(
 					ASSERT(blk_no <= INT_MAX);
 					split_hblks = log->l_logBBsize - (int)blk_no;
 					ASSERT(split_hblks > 0);
-					if ((error = xlog_bread(log, blk_no,
-							split_hblks, hbp)))
+					error = xlog_bread(log, blk_no,
+							   split_hblks, hbp,
+							   &offset);
+					if (error)
 						goto bread_err2;
-					offset = xlog_align(log, blk_no,
-							split_hblks, hbp);
 				}
+
 				/*
 				 * Note: this black magic still works with
 				 * large sector sizes (non-512) only because:
@@ -3596,14 +3624,19 @@ xlog_do_recovery_pass(
 				error = XFS_BUF_SET_PTR(hbp,
 						bufaddr + BBTOB(split_hblks),
 						BBTOB(hblks - split_hblks));
-				if (!error)
-					error = xlog_bread(log, 0,
-							wrapped_hblks, hbp);
-				if (!error)
-					error = XFS_BUF_SET_PTR(hbp, bufaddr,
+				if (error)
+					goto bread_err2;
+
+				error = xlog_bread_noalign(log, 0,
+							   wrapped_hblks, hbp);
+				if (error)
+					goto bread_err2;
+
+				error = XFS_BUF_SET_PTR(hbp, bufaddr,
 							BBTOB(hblks));
 				if (error)
 					goto bread_err2;
+
 				if (!offset)
 					offset = xlog_align(log, 0,
 							wrapped_hblks, hbp);
@@ -3619,10 +3652,10 @@ xlog_do_recovery_pass(
 
 			/* Read in data for log record */
 			if (blk_no + bblks <= log->l_logBBsize) {
-				error = xlog_bread(log, blk_no, bblks, dbp);
+				error = xlog_bread(log, blk_no, bblks, dbp,
+						   &offset);
 				if (error)
 					goto bread_err2;
-				offset = xlog_align(log, blk_no, bblks, dbp);
 			} else {
 				/* This log record is split across the
 				 * physical end of log */
@@ -3636,12 +3669,13 @@ xlog_do_recovery_pass(
 					split_bblks =
 						log->l_logBBsize - (int)blk_no;
 					ASSERT(split_bblks > 0);
-					if ((error = xlog_bread(log, blk_no,
-							split_bblks, dbp)))
+					error = xlog_bread(log, blk_no,
+							split_bblks, dbp,
+							&offset);
+					if (error)
 						goto bread_err2;
-					offset = xlog_align(log, blk_no,
-							split_bblks, dbp);
 				}
+
 				/*
 				 * Note: this black magic still works with
 				 * large sector sizes (non-512) only because:
@@ -3658,15 +3692,19 @@ xlog_do_recovery_pass(
 				error = XFS_BUF_SET_PTR(dbp,
 						bufaddr + BBTOB(split_bblks),
 						BBTOB(bblks - split_bblks));
-				if (!error)
-					error = xlog_bread(log, wrapped_hblks,
-							bblks - split_bblks,
-							dbp);
-				if (!error)
-					error = XFS_BUF_SET_PTR(dbp, bufaddr,
-							h_size);
 				if (error)
 					goto bread_err2;
+
+				error = xlog_bread_noalign(log, wrapped_hblks,
+						bblks - split_bblks,
+						dbp);
+				if (error)
+					goto bread_err2;
+
+				error = XFS_BUF_SET_PTR(dbp, bufaddr, h_size);
+				if (error)
+					goto bread_err2;
+
 				if (!offset)
 					offset = xlog_align(log, wrapped_hblks,
 						bblks - split_bblks, dbp);
@@ -3683,17 +3721,21 @@ xlog_do_recovery_pass(
 
 		/* read first part of physical log */
 		while (blk_no < head_blk) {
-			if ((error = xlog_bread(log, blk_no, hblks, hbp)))
+			error = xlog_bread(log, blk_no, hblks, hbp, &offset);
+			if (error)
 				goto bread_err2;
-			offset = xlog_align(log, blk_no, hblks, hbp);
+
 			rhead = (xlog_rec_header_t *)offset;
 			error = xlog_valid_rec_header(log, rhead, blk_no);
 			if (error)
 				goto bread_err2;
+
 			bblks = (int)BTOBB(be32_to_cpu(rhead->h_len));
-			if ((error = xlog_bread(log, blk_no+hblks, bblks, dbp)))
+			error = xlog_bread(log, blk_no+hblks, bblks, dbp,
+					   &offset);
+			if (error)
 				goto bread_err2;
-			offset = xlog_align(log, blk_no+hblks, bblks, dbp);
+
 			xlog_unpack_data(rhead, offset, log);
 			if ((error = xlog_recover_process_data(log, rhash,
 							rhead, offset, pass)))
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 35300250e86d..b101990df027 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -45,7 +45,6 @@
 #include "xfs_fsops.h"
 #include "xfs_utils.h"
 
-STATIC int	xfs_uuid_mount(xfs_mount_t *);
 STATIC void	xfs_unmountfs_wait(xfs_mount_t *);
 
 
@@ -121,6 +120,84 @@ static const struct {
     { sizeof(xfs_sb_t),			 0 }
 };
 
+static DEFINE_MUTEX(xfs_uuid_table_mutex);
+static int xfs_uuid_table_size;
+static uuid_t *xfs_uuid_table;
+
+/*
+ * See if the UUID is unique among mounted XFS filesystems.
+ * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
+ */
+STATIC int
+xfs_uuid_mount(
+	struct xfs_mount	*mp)
+{
+	uuid_t			*uuid = &mp->m_sb.sb_uuid;
+	int			hole, i;
+
+	if (mp->m_flags & XFS_MOUNT_NOUUID)
+		return 0;
+
+	if (uuid_is_nil(uuid)) {
+		cmn_err(CE_WARN,
+			"XFS: Filesystem %s has nil UUID - can't mount",
+			mp->m_fsname);
+		return XFS_ERROR(EINVAL);
+	}
+
+	mutex_lock(&xfs_uuid_table_mutex);
+	for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) {
+		if (uuid_is_nil(&xfs_uuid_table[i])) {
+			hole = i;
+			continue;
+		}
+		if (uuid_equal(uuid, &xfs_uuid_table[i]))
+			goto out_duplicate;
+	}
+
+	if (hole < 0) {
+		xfs_uuid_table = kmem_realloc(xfs_uuid_table,
+			(xfs_uuid_table_size + 1) * sizeof(*xfs_uuid_table),
+			xfs_uuid_table_size  * sizeof(*xfs_uuid_table),
+			KM_SLEEP);
+		hole = xfs_uuid_table_size++;
+	}
+	xfs_uuid_table[hole] = *uuid;
+	mutex_unlock(&xfs_uuid_table_mutex);
+
+	return 0;
+
+ out_duplicate:
+	mutex_unlock(&xfs_uuid_table_mutex);
+	cmn_err(CE_WARN, "XFS: Filesystem %s has duplicate UUID - can't mount",
+			 mp->m_fsname);
+	return XFS_ERROR(EINVAL);
+}
+
+STATIC void
+xfs_uuid_unmount(
+	struct xfs_mount	*mp)
+{
+	uuid_t			*uuid = &mp->m_sb.sb_uuid;
+	int			i;
+
+	if (mp->m_flags & XFS_MOUNT_NOUUID)
+		return;
+
+	mutex_lock(&xfs_uuid_table_mutex);
+	for (i = 0; i < xfs_uuid_table_size; i++) {
+		if (uuid_is_nil(&xfs_uuid_table[i]))
+			continue;
+		if (!uuid_equal(uuid, &xfs_uuid_table[i]))
+			continue;
+		memset(&xfs_uuid_table[i], 0, sizeof(uuid_t));
+		break;
+	}
+	ASSERT(i < xfs_uuid_table_size);
+	mutex_unlock(&xfs_uuid_table_mutex);
+}
+
+
 /*
  * Free up the resources associated with a mount structure.  Assume that
  * the structure was initially zeroed, so we can tell which fields got
@@ -256,6 +333,22 @@ xfs_mount_validate_sb(
 		return XFS_ERROR(ENOSYS);
 	}
 
+	/*
+	 * Currently only very few inode sizes are supported.
+	 */
+	switch (sbp->sb_inodesize) {
+	case 256:
+	case 512:
+	case 1024:
+	case 2048:
+		break;
+	default:
+		xfs_fs_mount_cmn_err(flags,
+			"inode size of %d bytes not supported",
+			sbp->sb_inodesize);
+		return XFS_ERROR(ENOSYS);
+	}
+
 	if (xfs_sb_validate_fsb_count(sbp, sbp->sb_dblocks) ||
 	    xfs_sb_validate_fsb_count(sbp, sbp->sb_rblocks)) {
 		xfs_fs_mount_cmn_err(flags,
@@ -574,32 +667,10 @@ xfs_mount_common(xfs_mount_t *mp, xfs_sb_t *sbp)
 	mp->m_sectbb_log = sbp->sb_sectlog - BBSHIFT;
 	mp->m_agno_log = xfs_highbit32(sbp->sb_agcount - 1) + 1;
 	mp->m_agino_log = sbp->sb_inopblog + sbp->sb_agblklog;
-	mp->m_litino = sbp->sb_inodesize - sizeof(struct xfs_dinode);
 	mp->m_blockmask = sbp->sb_blocksize - 1;
 	mp->m_blockwsize = sbp->sb_blocksize >> XFS_WORDLOG;
 	mp->m_blockwmask = mp->m_blockwsize - 1;
 
-	/*
-	 * Setup for attributes, in case they get created.
-	 * This value is for inodes getting attributes for the first time,
-	 * the per-inode value is for old attribute values.
-	 */
-	ASSERT(sbp->sb_inodesize >= 256 && sbp->sb_inodesize <= 2048);
-	switch (sbp->sb_inodesize) {
-	case 256:
-		mp->m_attroffset = XFS_LITINO(mp) -
-				   XFS_BMDR_SPACE_CALC(MINABTPTRS);
-		break;
-	case 512:
-	case 1024:
-	case 2048:
-		mp->m_attroffset = XFS_BMDR_SPACE_CALC(6 * MINABTPTRS);
-		break;
-	default:
-		ASSERT(0);
-	}
-	ASSERT(mp->m_attroffset < XFS_LITINO(mp));
-
 	mp->m_alloc_mxr[0] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 1);
 	mp->m_alloc_mxr[1] = xfs_allocbt_maxrecs(mp, sbp->sb_blocksize, 0);
 	mp->m_alloc_mnr[0] = mp->m_alloc_mxr[0] / 2;
@@ -645,7 +716,7 @@ xfs_initialize_perag_data(xfs_mount_t *mp, xfs_agnumber_t agcount)
 	for (index = 0; index < agcount; index++) {
 		/*
 		 * read the agf, then the agi. This gets us
-		 * all the inforamtion we need and populates the
+		 * all the information we need and populates the
 		 * per-ag structures for us.
 		 */
 		error = xfs_alloc_pagf_init(mp, NULL, index, 0);
@@ -886,8 +957,6 @@ xfs_check_sizes(xfs_mount_t *mp)
 }
 
 /*
- * xfs_mountfs
- *
  * This function does the following on an initial mount of a file system:
  *	- reads the superblock from disk and init the mount struct
  *	- if we're a 32-bit kernel, do a size check on the superblock
@@ -905,7 +974,6 @@ xfs_mountfs(
 	xfs_inode_t	*rip;
 	__uint64_t	resblks;
 	uint		quotamount, quotaflags;
-	int		uuid_mounted = 0;
 	int		error = 0;
 
 	xfs_mount_common(mp, sbp);
@@ -960,7 +1028,7 @@ xfs_mountfs(
 	 */
 	error = xfs_update_alignment(mp);
 	if (error)
-		goto error1;
+		goto out;
 
 	xfs_alloc_compute_maxlevels(mp);
 	xfs_bmap_compute_maxlevels(mp, XFS_DATA_FORK);
@@ -971,19 +1039,9 @@ xfs_mountfs(
 
 	mp->m_maxioffset = xfs_max_file_offset(sbp->sb_blocklog);
 
-	/*
-	 * XFS uses the uuid from the superblock as the unique
-	 * identifier for fsid.  We can not use the uuid from the volume
-	 * since a single partition filesystem is identical to a single
-	 * partition volume/filesystem.
-	 */
-	if ((mp->m_flags & XFS_MOUNT_NOUUID) == 0) {
-		if (xfs_uuid_mount(mp)) {
-			error = XFS_ERROR(EINVAL);
-			goto error1;
-		}
-		uuid_mounted=1;
-	}
+	error = xfs_uuid_mount(mp);
+	if (error)
+		goto out;
 
 	/*
 	 * Set the minimum read and write sizes
@@ -1007,7 +1065,7 @@ xfs_mountfs(
 	 */
 	error = xfs_check_sizes(mp);
 	if (error)
-		goto error1;
+		goto out_remove_uuid;
 
 	/*
 	 * Initialize realtime fields in the mount structure
@@ -1015,7 +1073,7 @@ xfs_mountfs(
 	error = xfs_rtmount_init(mp);
 	if (error) {
 		cmn_err(CE_WARN, "XFS: RT mount failed");
-		goto error1;
+		goto out_remove_uuid;
 	}
 
 	/*
@@ -1045,26 +1103,26 @@ xfs_mountfs(
 	mp->m_perag = kmem_zalloc(sbp->sb_agcount * sizeof(xfs_perag_t),
 				  KM_MAYFAIL);
 	if (!mp->m_perag)
-		goto error1;
+		goto out_remove_uuid;
 
 	mp->m_maxagi = xfs_initialize_perag(mp, sbp->sb_agcount);
 
+	if (!sbp->sb_logblocks) {
+		cmn_err(CE_WARN, "XFS: no log defined");
+		XFS_ERROR_REPORT("xfs_mountfs", XFS_ERRLEVEL_LOW, mp);
+		error = XFS_ERROR(EFSCORRUPTED);
+		goto out_free_perag;
+	}
+
 	/*
 	 * log's mount-time initialization. Perform 1st part recovery if needed
 	 */
-	if (likely(sbp->sb_logblocks > 0)) {	/* check for volume case */
-		error = xfs_log_mount(mp, mp->m_logdev_targp,
-				      XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
-				      XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
-		if (error) {
-			cmn_err(CE_WARN, "XFS: log mount failed");
-			goto error2;
-		}
-	} else {	/* No log has been defined */
-		cmn_err(CE_WARN, "XFS: no log defined");
-		XFS_ERROR_REPORT("xfs_mountfs_int(1)", XFS_ERRLEVEL_LOW, mp);
-		error = XFS_ERROR(EFSCORRUPTED);
-		goto error2;
+	error = xfs_log_mount(mp, mp->m_logdev_targp,
+			      XFS_FSB_TO_DADDR(mp, sbp->sb_logstart),
+			      XFS_FSB_TO_BB(mp, sbp->sb_logblocks));
+	if (error) {
+		cmn_err(CE_WARN, "XFS: log mount failed");
+		goto out_free_perag;
 	}
 
 	/*
@@ -1086,15 +1144,14 @@ xfs_mountfs(
 	 * If we are currently making the filesystem, the initialisation will
 	 * fail as the perag data is in an undefined state.
 	 */
-
 	if (xfs_sb_version_haslazysbcount(&mp->m_sb) &&
 	    !XFS_LAST_UNMOUNT_WAS_CLEAN(mp) &&
 	     !mp->m_sb.sb_inprogress) {
 		error = xfs_initialize_perag_data(mp, sbp->sb_agcount);
-		if (error) {
-			goto error2;
-		}
+		if (error)
+			goto out_free_perag;
 	}
+
 	/*
 	 * Get and sanity-check the root inode.
 	 * Save the pointer to it in the mount structure.
@@ -1102,7 +1159,7 @@ xfs_mountfs(
 	error = xfs_iget(mp, NULL, sbp->sb_rootino, 0, XFS_ILOCK_EXCL, &rip, 0);
 	if (error) {
 		cmn_err(CE_WARN, "XFS: failed to read root inode");
-		goto error3;
+		goto out_log_dealloc;
 	}
 
 	ASSERT(rip != NULL);
@@ -1116,7 +1173,7 @@ xfs_mountfs(
 		XFS_ERROR_REPORT("xfs_mountfs_int(2)", XFS_ERRLEVEL_LOW,
 				 mp);
 		error = XFS_ERROR(EFSCORRUPTED);
-		goto error4;
+		goto out_rele_rip;
 	}
 	mp->m_rootip = rip;	/* save it */
 
@@ -1131,7 +1188,7 @@ xfs_mountfs(
 		 * Free up the root inode.
 		 */
 		cmn_err(CE_WARN, "XFS: failed to read RT inodes");
-		goto error4;
+		goto out_rele_rip;
 	}
 
 	/*
@@ -1143,7 +1200,7 @@ xfs_mountfs(
 		error = xfs_mount_log_sb(mp, mp->m_update_flags);
 		if (error) {
 			cmn_err(CE_WARN, "XFS: failed to write sb changes");
-			goto error4;
+			goto out_rtunmount;
 		}
 	}
 
@@ -1152,7 +1209,7 @@ xfs_mountfs(
 	 */
 	error = XFS_QM_INIT(mp, &quotamount, &quotaflags);
 	if (error)
-		goto error4;
+		goto out_rtunmount;
 
 	/*
 	 * Finish recovering the file system.  This part needed to be
@@ -1162,7 +1219,7 @@ xfs_mountfs(
 	error = xfs_log_mount_finish(mp);
 	if (error) {
 		cmn_err(CE_WARN, "XFS: log mount finish failed");
-		goto error4;
+		goto out_rtunmount;
 	}
 
 	/*
@@ -1170,7 +1227,7 @@ xfs_mountfs(
 	 */
 	error = XFS_QM_MOUNT(mp, quotamount, quotaflags);
 	if (error)
-		goto error4;
+		goto out_rtunmount;
 
 	/*
 	 * Now we are mounted, reserve a small amount of unused space for
@@ -1194,18 +1251,17 @@ xfs_mountfs(
 
 	return 0;
 
- error4:
-	/*
-	 * Free up the root inode.
-	 */
+ out_rtunmount:
+	xfs_rtunmount_inodes(mp);
+ out_rele_rip:
 	IRELE(rip);
- error3:
-	xfs_log_unmount_dealloc(mp);
- error2:
+ out_log_dealloc:
+	xfs_log_unmount(mp);
+ out_free_perag:
 	xfs_free_perag(mp);
- error1:
-	if (uuid_mounted)
-		uuid_table_remove(&mp->m_sb.sb_uuid);
+ out_remove_uuid:
+	xfs_uuid_unmount(mp);
+ out:
 	return error;
 }
 
@@ -1226,15 +1282,12 @@ xfs_unmountfs(
 	 */
 	XFS_QM_UNMOUNT(mp);
 
-	if (mp->m_rbmip)
-		IRELE(mp->m_rbmip);
-	if (mp->m_rsumip)
-		IRELE(mp->m_rsumip);
+	xfs_rtunmount_inodes(mp);
 	IRELE(mp->m_rootip);
 
 	/*
 	 * We can potentially deadlock here if we have an inode cluster
-	 * that has been freed has it's buffer still pinned in memory because
+	 * that has been freed has its buffer still pinned in memory because
 	 * the transaction is still sitting in a iclog. The stale inodes
 	 * on that buffer will have their flush locks held until the
 	 * transaction hits the disk and the callbacks run. the inode
@@ -1266,7 +1319,7 @@ xfs_unmountfs(
 	 * Unreserve any blocks we have so that when we unmount we don't account
 	 * the reserved free space as used. This is really only necessary for
 	 * lazy superblock counting because it trusts the incore superblock
-	 * counters to be aboslutely correct on clean unmount.
+	 * counters to be absolutely correct on clean unmount.
 	 *
 	 * We don't bother correcting this elsewhere for lazy superblock
 	 * counting because on mount of an unclean filesystem we reconstruct the
@@ -1288,10 +1341,9 @@ xfs_unmountfs(
 				"Freespace may not be correct on next mount.");
 	xfs_unmountfs_writesb(mp);
 	xfs_unmountfs_wait(mp); 		/* wait for async bufs */
-	xfs_log_unmount(mp);			/* Done! No more fs ops. */
-
-	if ((mp->m_flags & XFS_MOUNT_NOUUID) == 0)
-		uuid_table_remove(&mp->m_sb.sb_uuid);
+	xfs_log_unmount_write(mp);
+	xfs_log_unmount(mp);
+	xfs_uuid_unmount(mp);
 
 #if defined(DEBUG)
 	xfs_errortag_clearall(mp, 0);
@@ -1793,29 +1845,6 @@ xfs_freesb(
 }
 
 /*
- * See if the UUID is unique among mounted XFS filesystems.
- * Mount fails if UUID is nil or a FS with the same UUID is already mounted.
- */
-STATIC int
-xfs_uuid_mount(
-	xfs_mount_t	*mp)
-{
-	if (uuid_is_nil(&mp->m_sb.sb_uuid)) {
-		cmn_err(CE_WARN,
-			"XFS: Filesystem %s has nil UUID - can't mount",
-			mp->m_fsname);
-		return -1;
-	}
-	if (!uuid_table_insert(&mp->m_sb.sb_uuid)) {
-		cmn_err(CE_WARN,
-			"XFS: Filesystem %s has duplicate UUID - can't mount",
-			mp->m_fsname);
-		return -1;
-	}
-	return 0;
-}
-
-/*
  * Used to log changes to the superblock unit and width fields which could
  * be altered by the mount options, as well as any potential sb_features2
  * fixup. Only the first superblock is updated.
@@ -1868,7 +1897,7 @@ xfs_mount_log_sb(
  * we disable the per-cpu counter and go through the slow path.
  *
  * The slow path is the current xfs_mod_incore_sb() function.  This means that
- * when we disable a per-cpu counter, we need to drain it's resources back to
+ * when we disable a per-cpu counter, we need to drain its resources back to
  * the global superblock. We do this after disabling the counter to prevent
  * more threads from queueing up on the counter.
  *
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index f5e9937f9bdb..7af44adffc8f 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -136,7 +136,6 @@ typedef int	(*xfs_dqvopchownresv_t)(struct xfs_trans *, struct xfs_inode *,
 			struct xfs_dquot *, struct xfs_dquot *, uint);
 typedef void	(*xfs_dqstatvfs_t)(struct xfs_inode *, struct kstatfs *);
 typedef int	(*xfs_dqsync_t)(struct xfs_mount *, int flags);
-typedef int	(*xfs_quotactl_t)(struct xfs_mount *, int, int, xfs_caddr_t);
 
 typedef struct xfs_qmops {
 	xfs_qminit_t		xfs_qminit;
@@ -154,7 +153,6 @@ typedef struct xfs_qmops {
 	xfs_dqvopchownresv_t	xfs_dqvopchownresv;
 	xfs_dqstatvfs_t		xfs_dqstatvfs;
 	xfs_dqsync_t		xfs_dqsync;
-	xfs_quotactl_t		xfs_quotactl;
 	struct xfs_dqtrxops	*xfs_dqtrxops;
 } xfs_qmops_t;
 
@@ -188,8 +186,6 @@ typedef struct xfs_qmops {
 	(*(ip)->i_mount->m_qm_ops->xfs_dqstatvfs)(ip, statp)
 #define XFS_QM_DQSYNC(mp, flags) \
 	(*(mp)->m_qm_ops->xfs_dqsync)(mp, flags)
-#define XFS_QM_QUOTACTL(mp, cmd, id, addr) \
-	(*(mp)->m_qm_ops->xfs_quotactl)(mp, cmd, id, addr)
 
 #ifdef HAVE_PERCPU_SB
 
@@ -273,19 +269,17 @@ typedef struct xfs_mount {
 	uint			m_inobt_mnr[2];	/* min inobt btree records */
 	uint			m_ag_maxlevels;	/* XFS_AG_MAXLEVELS */
 	uint			m_bm_maxlevels[2]; /* XFS_BM_MAXLEVELS */
-	uint			m_in_maxlevels;	/* XFS_IN_MAXLEVELS */
+	uint			m_in_maxlevels;	/* max inobt btree levels. */
 	struct xfs_perag	*m_perag;	/* per-ag accounting info */
 	struct rw_semaphore	m_peraglock;	/* lock for m_perag (pointer) */
 	struct mutex		m_growlock;	/* growfs mutex */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_dmevmask;	/* DMI events for this FS */
 	__uint64_t		m_flags;	/* global mount flags */
-	uint			m_attroffset;	/* inode attribute offset */
 	uint			m_dir_node_ents; /* #entries in a dir danode */
 	uint			m_attr_node_ents; /* #entries in attr danode */
 	int			m_ialloc_inos;	/* inodes in inode allocation */
 	int			m_ialloc_blks;	/* blocks in inode allocation */
-	int			m_litino;	/* size of inode union area */
 	int			m_inoalign_mask;/* mask sb_inoalignmt if used */
 	uint			m_qflags;	/* quota status flags */
 	xfs_trans_reservations_t m_reservations;/* precomputed res values */
@@ -293,9 +287,6 @@ typedef struct xfs_mount {
 	__uint64_t		m_maxioffset;	/* maximum inode offset */
 	__uint64_t		m_resblks;	/* total reserved blocks */
 	__uint64_t		m_resblks_avail;/* available reserved blocks */
-#if XFS_BIG_INUMS
-	xfs_ino_t		m_inoadd;	/* add value for ino64_offset */
-#endif
 	int			m_dalign;	/* stripe unit */
 	int			m_swidth;	/* stripe width */
 	int			m_sinoalign;	/* stripe unit inode alignment */
@@ -337,7 +328,6 @@ typedef struct xfs_mount {
 #define XFS_MOUNT_WSYNC		(1ULL << 0)	/* for nfs - all metadata ops
 						   must be synchronous except
 						   for space allocations */
-#define XFS_MOUNT_INO64		(1ULL << 1)
 #define XFS_MOUNT_DMAPI		(1ULL << 2)	/* dmapi is enabled */
 #define XFS_MOUNT_WAS_CLEAN	(1ULL << 3)
 #define XFS_MOUNT_FS_SHUTDOWN	(1ULL << 4)	/* atomic stop of all filesystem
@@ -389,8 +379,8 @@ typedef struct xfs_mount {
  * Synchronous read and write sizes.  This should be
  * better for NFSv2 wsync filesystems.
  */
-#define	XFS_WSYNC_READIO_LOG	15	/* 32K */
-#define	XFS_WSYNC_WRITEIO_LOG	14	/* 16K */
+#define	XFS_WSYNC_READIO_LOG	15	/* 32k */
+#define	XFS_WSYNC_WRITEIO_LOG	14	/* 16k */
 
 /*
  * Allow large block sizes to be reported to userspace programs if the
@@ -500,9 +490,6 @@ typedef struct xfs_mod_sb {
 	int64_t		msb_delta;	/* Change to make to specified field */
 } xfs_mod_sb_t;
 
-#define	XFS_MOUNT_ILOCK(mp)	mutex_lock(&((mp)->m_ilock))
-#define	XFS_MOUNT_IUNLOCK(mp)	mutex_unlock(&((mp)->m_ilock))
-
 extern int	xfs_log_sbcount(xfs_mount_t *, uint);
 extern int	xfs_mountfs(xfs_mount_t *mp);
 extern void	xfs_mountfs_check_barriers(xfs_mount_t *mp);
diff --git a/fs/xfs/xfs_qmops.c b/fs/xfs/xfs_qmops.c
index 27f80581520a..e101790ea8e7 100644
--- a/fs/xfs/xfs_qmops.c
+++ b/fs/xfs/xfs_qmops.c
@@ -126,7 +126,6 @@ static struct xfs_qmops xfs_qmcore_stub = {
 	.xfs_dqvopchownresv	= (xfs_dqvopchownresv_t) fs_noerr,
 	.xfs_dqstatvfs		= (xfs_dqstatvfs_t) fs_noval,
 	.xfs_dqsync		= (xfs_dqsync_t) fs_noerr,
-	.xfs_quotactl		= (xfs_quotactl_t) fs_nosys,
 };
 
 int
diff --git a/fs/xfs/xfs_quota.h b/fs/xfs/xfs_quota.h
index 48965ecaa155..f5d1202dde25 100644
--- a/fs/xfs/xfs_quota.h
+++ b/fs/xfs/xfs_quota.h
@@ -18,6 +18,8 @@
 #ifndef __XFS_QUOTA_H__
 #define __XFS_QUOTA_H__
 
+struct xfs_trans;
+
 /*
  * The ondisk form of a dquot structure.
  */
@@ -185,7 +187,6 @@ typedef struct xfs_qoff_logformat {
  * to a single function. None of these XFS_QMOPT_* flags are meant to have
  * persistent values (ie. their values can and will change between versions)
  */
-#define XFS_QMOPT_DQLOCK	0x0000001 /* dqlock */
 #define XFS_QMOPT_DQALLOC	0x0000002 /* alloc dquot ondisk if needed */
 #define XFS_QMOPT_UQUOTA	0x0000004 /* user dquot requested */
 #define XFS_QMOPT_PQUOTA	0x0000008 /* project dquot requested */
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index c5bb86f3ec05..385f6dceba5d 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -2288,6 +2288,16 @@ xfs_rtmount_inodes(
 	return 0;
 }
 
+void
+xfs_rtunmount_inodes(
+	struct xfs_mount	*mp)
+{
+	if (mp->m_rbmip)
+		IRELE(mp->m_rbmip);
+	if (mp->m_rsumip)
+		IRELE(mp->m_rsumip);
+}
+
 /*
  * Pick an extent for allocation at the start of a new realtime file.
  * Use the sequence number stored in the atime field of the bitmap inode.
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index 8d8dcd215716..b2d67adb6a08 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -23,8 +23,8 @@ struct xfs_trans;
 
 /* Min and max rt extent sizes, specified in bytes */
 #define	XFS_MAX_RTEXTSIZE	(1024 * 1024 * 1024)	/* 1GB */
-#define	XFS_DFL_RTEXTSIZE	(64 * 1024)	        /* 64KB */
-#define	XFS_MIN_RTEXTSIZE	(4 * 1024)		/* 4KB */
+#define	XFS_DFL_RTEXTSIZE	(64 * 1024)	        /* 64kB */
+#define	XFS_MIN_RTEXTSIZE	(4 * 1024)		/* 4kB */
 
 /*
  * Constants for bit manipulations.
@@ -108,6 +108,9 @@ xfs_rtfree_extent(
 int					/* error */
 xfs_rtmount_init(
 	struct xfs_mount	*mp);	/* file system mount structure */
+void
+xfs_rtunmount_inodes(
+	struct xfs_mount	*mp);
 
 /*
  * Get the bitmap and summary inodes into the mount structure
@@ -146,6 +149,7 @@ xfs_growfs_rt(
 # define xfs_growfs_rt(mp,in)                           (ENOSYS)
 # define xfs_rtmount_init(m)    (((mp)->m_sb.sb_rblocks == 0)? 0 : (ENOSYS))
 # define xfs_rtmount_inodes(m)  (((mp)->m_sb.sb_rblocks == 0)? 0 : (ENOSYS))
+# define xfs_rtunmount_inodes(m)
 #endif	/* CONFIG_XFS_RT */
 
 #endif	/* __KERNEL__ */
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index d6fe4a88d79f..775249a54f6f 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -292,7 +292,7 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
  * In a write transaction we can allocate a maximum of 2
  * extents.  This gives:
  *    the inode getting the new extents: inode size
- *    the inode\'s bmap btree: max depth * block size
+ *    the inode's bmap btree: max depth * block size
  *    the agfs of the ags from which the extents are allocated: 2 * sector
  *    the superblock free block counter: sector size
  *    the allocation btrees: 2 exts * 2 trees * (2 * max depth - 1) * block size
@@ -321,7 +321,7 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
 /*
  * In truncating a file we free up to two extents at once.  We can modify:
  *    the inode being truncated: inode size
- *    the inode\'s bmap btree: (max depth + 1) * block size
+ *    the inode's bmap btree: (max depth + 1) * block size
  * And the bmap_finish transaction can free the blocks and bmap blocks:
  *    the agf for each of the ags: 4 * sector size
  *    the agfl for each of the ags: 4 * sector size
@@ -343,7 +343,7 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
 	  (128 * (9 + XFS_ALLOCFREE_LOG_COUNT(mp, 4))) + \
 	  (128 * 5) + \
 	  XFS_ALLOCFREE_LOG_RES(mp, 1) + \
-	   (128 * (2 + XFS_IALLOC_BLOCKS(mp) + XFS_IN_MAXLEVELS(mp) + \
+	   (128 * (2 + XFS_IALLOC_BLOCKS(mp) + (mp)->m_in_maxlevels + \
 	    XFS_ALLOCFREE_LOG_COUNT(mp, 1))))))
 
 #define	XFS_ITRUNCATE_LOG_RES(mp)   ((mp)->m_reservations.tr_itruncate)
@@ -431,8 +431,8 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
  *    the new inode: inode size
  *    the inode btree entry: 1 block
  *    the directory btree: (max depth + v2) * dir block size
- *    the directory inode\'s bmap btree: (max depth + v2) * block size
- *    the blocks for the symlink: 1 KB
+ *    the directory inode's bmap btree: (max depth + v2) * block size
+ *    the blocks for the symlink: 1 kB
  * Or in the first xact we allocate some inodes giving:
  *    the agi and agf of the ag getting the new inodes: 2 * sectorsize
  *    the inode blocks allocated: XFS_IALLOC_BLOCKS * blocksize
@@ -449,9 +449,9 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
 	  (128 * (4 + XFS_DIROP_LOG_COUNT(mp)))), \
 	 (2 * (mp)->m_sb.sb_sectsize + \
 	  XFS_FSB_TO_B((mp), XFS_IALLOC_BLOCKS((mp))) + \
-	  XFS_FSB_TO_B((mp), XFS_IN_MAXLEVELS(mp)) + \
+	  XFS_FSB_TO_B((mp), (mp)->m_in_maxlevels) + \
 	  XFS_ALLOCFREE_LOG_RES(mp, 1) + \
-	  (128 * (2 + XFS_IALLOC_BLOCKS(mp) + XFS_IN_MAXLEVELS(mp) + \
+	  (128 * (2 + XFS_IALLOC_BLOCKS(mp) + (mp)->m_in_maxlevels + \
 	   XFS_ALLOCFREE_LOG_COUNT(mp, 1))))))
 
 #define	XFS_SYMLINK_LOG_RES(mp)	((mp)->m_reservations.tr_symlink)
@@ -463,7 +463,7 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
  *    the inode btree entry: block size
  *    the superblock for the nlink flag: sector size
  *    the directory btree: (max depth + v2) * dir block size
- *    the directory inode\'s bmap btree: (max depth + v2) * block size
+ *    the directory inode's bmap btree: (max depth + v2) * block size
  * Or in the first xact we allocate some inodes giving:
  *    the agi and agf of the ag getting the new inodes: 2 * sectorsize
  *    the superblock for the nlink flag: sector size
@@ -481,9 +481,9 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
 	  (128 * (3 + XFS_DIROP_LOG_COUNT(mp)))), \
 	 (3 * (mp)->m_sb.sb_sectsize + \
 	  XFS_FSB_TO_B((mp), XFS_IALLOC_BLOCKS((mp))) + \
-	  XFS_FSB_TO_B((mp), XFS_IN_MAXLEVELS(mp)) + \
+	  XFS_FSB_TO_B((mp), (mp)->m_in_maxlevels) + \
 	  XFS_ALLOCFREE_LOG_RES(mp, 1) + \
-	  (128 * (2 + XFS_IALLOC_BLOCKS(mp) + XFS_IN_MAXLEVELS(mp) + \
+	  (128 * (2 + XFS_IALLOC_BLOCKS(mp) + (mp)->m_in_maxlevels + \
 	   XFS_ALLOCFREE_LOG_COUNT(mp, 1))))))
 
 #define	XFS_CREATE_LOG_RES(mp)	((mp)->m_reservations.tr_create)
@@ -513,7 +513,7 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
 	 MAX((__uint16_t)XFS_FSB_TO_B((mp), 1), XFS_INODE_CLUSTER_SIZE(mp)) + \
 	 (128 * 5) + \
 	  XFS_ALLOCFREE_LOG_RES(mp, 1) + \
-	  (128 * (2 + XFS_IALLOC_BLOCKS(mp) + XFS_IN_MAXLEVELS(mp) + \
+	  (128 * (2 + XFS_IALLOC_BLOCKS(mp) + (mp)->m_in_maxlevels + \
 	   XFS_ALLOCFREE_LOG_COUNT(mp, 1))))
 
 
@@ -637,7 +637,7 @@ xfs_lic_desc_to_chunk(xfs_log_item_desc_t *dp)
 /*
  * Removing the attribute fork of a file
  *    the inode being truncated: inode size
- *    the inode\'s bmap btree: max depth * block size
+ *    the inode's bmap btree: max depth * block size
  * And the bmap_finish transaction can free the blocks and bmap blocks:
  *    the agf for each of the ags: 4 * sector size
  *    the agfl for each of the ags: 4 * sector size
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index 2d47f10f8bed..f31271c30de9 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -79,7 +79,7 @@ xfs_trans_ail_tail(
  * the push is run asynchronously in a separate thread, so we return the tail
  * of the log right now instead of the tail after the push. This means we will
  * either continue right away, or we will sleep waiting on the async thread to
- * do it's work.
+ * do its work.
  *
  * We do this unlocked - we only need to know whether there is anything in the
  * AIL at the time we are called. We don't need to access the contents of
@@ -160,7 +160,7 @@ xfs_trans_ail_cursor_next(
 /*
  * Now that the traversal is complete, we need to remove the cursor
  * from the list of traversing cursors. Avoid removing the embedded
- * push cursor, but use the fact it is alway present to make the
+ * push cursor, but use the fact it is always present to make the
  * list deletion simple.
  */
 void
diff --git a/fs/xfs/xfs_trans_item.c b/fs/xfs/xfs_trans_item.c
index e110bf57d7f4..eb3fc57f9eef 100644
--- a/fs/xfs/xfs_trans_item.c
+++ b/fs/xfs/xfs_trans_item.c
@@ -22,7 +22,7 @@
 #include "xfs_inum.h"
 #include "xfs_trans.h"
 #include "xfs_trans_priv.h"
-/* XXX: from here down needed until struct xfs_trans has it's own ailp */
+/* XXX: from here down needed until struct xfs_trans has its own ailp */
 #include "xfs_bit.h"
 #include "xfs_buf_item.h"
 #include "xfs_sb.h"
diff --git a/fs/xfs/xfs_trans_space.h b/fs/xfs/xfs_trans_space.h
index 4ea2e5074bdd..7d2c920dfb9c 100644
--- a/fs/xfs/xfs_trans_space.h
+++ b/fs/xfs/xfs_trans_space.h
@@ -47,7 +47,7 @@
 #define	XFS_DIRREMOVE_SPACE_RES(mp)	\
 	XFS_DAREMOVE_SPACE_RES(mp, XFS_DATA_FORK)
 #define	XFS_IALLOC_SPACE_RES(mp)	\
-	(XFS_IALLOC_BLOCKS(mp) + XFS_IN_MAXLEVELS(mp)-1)
+	(XFS_IALLOC_BLOCKS(mp) + (mp)->m_in_maxlevels - 1)
 
 /*
  * Space reservation values for various transactions.
diff --git a/fs/xfs/xfs_types.h b/fs/xfs/xfs_types.h
index b2f724502f1b..d725428c9df6 100644
--- a/fs/xfs/xfs_types.h
+++ b/fs/xfs/xfs_types.h
@@ -21,14 +21,6 @@
 #ifdef __KERNEL__
 
 /*
- * POSIX Extensions
- */
-typedef unsigned char		uchar_t;
-typedef unsigned short		ushort_t;
-typedef unsigned int		uint_t;
-typedef unsigned long		ulong_t;
-
-/*
  * Additional type declarations for XFS
  */
 typedef signed char		__int8_t;
diff --git a/fs/xfs/xfs_utils.c b/fs/xfs/xfs_utils.c
index fcc2285d03ed..79b9e5ea5359 100644
--- a/fs/xfs/xfs_utils.c
+++ b/fs/xfs/xfs_utils.c
@@ -374,7 +374,7 @@ xfs_truncate_file(
 
 	/*
 	 * Follow the normal truncate locking protocol.  Since we
-	 * hold the inode in the transaction, we know that it's number
+	 * hold the inode in the transaction, we know that its number
 	 * of references will stay constant.
 	 */
 	xfs_ilock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_vnodeops.c b/fs/xfs/xfs_vnodeops.c
index 0e55c5d7db5f..7394c7af5de5 100644
--- a/fs/xfs/xfs_vnodeops.c
+++ b/fs/xfs/xfs_vnodeops.c
@@ -1136,7 +1136,7 @@ xfs_inactive(
 	 * If the inode is already free, then there can be nothing
 	 * to clean up here.
 	 */
-	if (ip->i_d.di_mode == 0 || VN_BAD(VFS_I(ip))) {
+	if (ip->i_d.di_mode == 0 || is_bad_inode(VFS_I(ip))) {
 		ASSERT(ip->i_df.if_real_bytes == 0);
 		ASSERT(ip->i_df.if_broot_bytes == 0);
 		return VN_INACTIVE_CACHE;
@@ -1387,23 +1387,28 @@ xfs_create(
 	xfs_inode_t		**ipp,
 	cred_t			*credp)
 {
-	xfs_mount_t		*mp = dp->i_mount;
-	xfs_inode_t		*ip;
-	xfs_trans_t		*tp;
+	int			is_dir = S_ISDIR(mode);
+	struct xfs_mount	*mp = dp->i_mount;
+	struct xfs_inode	*ip = NULL;
+	struct xfs_trans	*tp = NULL;
 	int			error;
 	xfs_bmap_free_t		free_list;
 	xfs_fsblock_t		first_block;
 	boolean_t		unlock_dp_on_error = B_FALSE;
-	int			dm_event_sent = 0;
 	uint			cancel_flags;
 	int			committed;
 	xfs_prid_t		prid;
-	struct xfs_dquot	*udqp, *gdqp;
+	struct xfs_dquot	*udqp = NULL;
+	struct xfs_dquot	*gdqp = NULL;
 	uint			resblks;
+	uint			log_res;
+	uint			log_count;
 
-	ASSERT(!*ipp);
 	xfs_itrace_entry(dp);
 
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return XFS_ERROR(EIO);
+
 	if (DM_EVENT_ENABLED(dp, DM_EVENT_CREATE)) {
 		error = XFS_SEND_NAMESP(mp, DM_EVENT_CREATE,
 				dp, DM_RIGHT_NULL, NULL,
@@ -1412,84 +1417,97 @@ xfs_create(
 
 		if (error)
 			return error;
-		dm_event_sent = 1;
 	}
 
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
-
-	/* Return through std_return after this point. */
-
-	udqp = gdqp = NULL;
 	if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
 		prid = dp->i_d.di_projid;
 	else
-		prid = (xfs_prid_t)dfltprid;
+		prid = dfltprid;
 
 	/*
 	 * Make sure that we have allocated dquot(s) on disk.
 	 */
 	error = XFS_QM_DQVOPALLOC(mp, dp,
 			current_fsuid(), current_fsgid(), prid,
-			XFS_QMOPT_QUOTALL|XFS_QMOPT_INHERIT, &udqp, &gdqp);
+			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp);
 	if (error)
 		goto std_return;
 
-	ip = NULL;
+	if (is_dir) {
+		rdev = 0;
+		resblks = XFS_MKDIR_SPACE_RES(mp, name->len);
+		log_res = XFS_MKDIR_LOG_RES(mp);
+		log_count = XFS_MKDIR_LOG_COUNT;
+		tp = xfs_trans_alloc(mp, XFS_TRANS_MKDIR);
+	} else {
+		resblks = XFS_CREATE_SPACE_RES(mp, name->len);
+		log_res = XFS_CREATE_LOG_RES(mp);
+		log_count = XFS_CREATE_LOG_COUNT;
+		tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE);
+	}
 
-	tp = xfs_trans_alloc(mp, XFS_TRANS_CREATE);
 	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-	resblks = XFS_CREATE_SPACE_RES(mp, name->len);
+
 	/*
 	 * Initially assume that the file does not exist and
 	 * reserve the resources for that case.  If that is not
 	 * the case we'll drop the one we have and get a more
 	 * appropriate transaction later.
 	 */
-	error = xfs_trans_reserve(tp, resblks, XFS_CREATE_LOG_RES(mp), 0,
-			XFS_TRANS_PERM_LOG_RES, XFS_CREATE_LOG_COUNT);
+	error = xfs_trans_reserve(tp, resblks, log_res, 0,
+			XFS_TRANS_PERM_LOG_RES, log_count);
 	if (error == ENOSPC) {
 		resblks = 0;
-		error = xfs_trans_reserve(tp, 0, XFS_CREATE_LOG_RES(mp), 0,
-				XFS_TRANS_PERM_LOG_RES, XFS_CREATE_LOG_COUNT);
+		error = xfs_trans_reserve(tp, 0, log_res, 0,
+				XFS_TRANS_PERM_LOG_RES, log_count);
 	}
 	if (error) {
 		cancel_flags = 0;
-		goto error_return;
+		goto out_trans_cancel;
 	}
 
 	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
 	unlock_dp_on_error = B_TRUE;
 
-	xfs_bmap_init(&free_list, &first_block);
+	/*
+	 * Check for directory link count overflow.
+	 */
+	if (is_dir && dp->i_d.di_nlink >= XFS_MAXLINK) {
+		error = XFS_ERROR(EMLINK);
+		goto out_trans_cancel;
+	}
 
-	ASSERT(ip == NULL);
+	xfs_bmap_init(&free_list, &first_block);
 
 	/*
 	 * Reserve disk quota and the inode.
 	 */
 	error = XFS_TRANS_RESERVE_QUOTA(mp, tp, udqp, gdqp, resblks, 1, 0);
 	if (error)
-		goto error_return;
+		goto out_trans_cancel;
 
 	error = xfs_dir_canenter(tp, dp, name, resblks);
 	if (error)
-		goto error_return;
-	error = xfs_dir_ialloc(&tp, dp, mode, 1,
-			rdev, credp, prid, resblks > 0,
-			&ip, &committed);
+		goto out_trans_cancel;
+
+	/*
+	 * A newly created regular or special file just has one directory
+	 * entry pointing to them, but a directory also the "." entry
+	 * pointing to itself.
+	 */
+	error = xfs_dir_ialloc(&tp, dp, mode, is_dir ? 2 : 1, rdev, credp,
+			       prid, resblks > 0, &ip, &committed);
 	if (error) {
 		if (error == ENOSPC)
-			goto error_return;
-		goto abort_return;
+			goto out_trans_cancel;
+		goto out_trans_abort;
 	}
-	xfs_itrace_ref(ip);
 
 	/*
 	 * At this point, we've gotten a newly allocated inode.
 	 * It is locked (and joined to the transaction).
 	 */
-
+	xfs_itrace_ref(ip);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
 
 	/*
@@ -1508,19 +1526,28 @@ xfs_create(
 					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
 	if (error) {
 		ASSERT(error != ENOSPC);
-		goto abort_return;
+		goto out_trans_abort;
 	}
 	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
 	xfs_trans_log_inode(tp, dp, XFS_ILOG_CORE);
 
+	if (is_dir) {
+		error = xfs_dir_init(tp, ip, dp);
+		if (error)
+			goto out_bmap_cancel;
+
+		error = xfs_bumplink(tp, dp);
+		if (error)
+			goto out_bmap_cancel;
+	}
+
 	/*
 	 * If this is a synchronous mount, make sure that the
 	 * create transaction goes to disk before returning to
 	 * the user.
 	 */
-	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
+	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC))
 		xfs_trans_set_sync(tp);
-	}
 
 	/*
 	 * Attach the dquot(s) to the inodes and modify them incore.
@@ -1537,16 +1564,13 @@ xfs_create(
 	IHOLD(ip);
 
 	error = xfs_bmap_finish(&tp, &free_list, &committed);
-	if (error) {
-		xfs_bmap_cancel(&free_list);
-		goto abort_rele;
-	}
+	if (error)
+		goto out_abort_rele;
 
 	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
 	if (error) {
 		IRELE(ip);
-		tp = NULL;
-		goto error_return;
+		goto out_dqrele;
 	}
 
 	XFS_QM_DQRELE(mp, udqp);
@@ -1555,26 +1579,22 @@ xfs_create(
 	*ipp = ip;
 
 	/* Fallthrough to std_return with error = 0  */
-
-std_return:
-	if ((*ipp || (error != 0 && dm_event_sent != 0)) &&
-	    DM_EVENT_ENABLED(dp, DM_EVENT_POSTCREATE)) {
-		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTCREATE,
-			dp, DM_RIGHT_NULL,
-			*ipp ? ip : NULL,
-			DM_RIGHT_NULL, name->name, NULL,
-			mode, error, 0);
+ std_return:
+	if (DM_EVENT_ENABLED(dp, DM_EVENT_POSTCREATE)) {
+		XFS_SEND_NAMESP(mp, DM_EVENT_POSTCREATE, dp, DM_RIGHT_NULL,
+				ip, DM_RIGHT_NULL, name->name, NULL, mode,
+				error, 0);
 	}
+
 	return error;
 
- abort_return:
+ out_bmap_cancel:
+	xfs_bmap_cancel(&free_list);
+ out_trans_abort:
 	cancel_flags |= XFS_TRANS_ABORT;
-	/* FALLTHROUGH */
-
- error_return:
-	if (tp != NULL)
-		xfs_trans_cancel(tp, cancel_flags);
-
+ out_trans_cancel:
+	xfs_trans_cancel(tp, cancel_flags);
+ out_dqrele:
 	XFS_QM_DQRELE(mp, udqp);
 	XFS_QM_DQRELE(mp, gdqp);
 
@@ -1583,20 +1603,18 @@ std_return:
 
 	goto std_return;
 
- abort_rele:
+ out_abort_rele:
 	/*
 	 * Wait until after the current transaction is aborted to
 	 * release the inode.  This prevents recursive transactions
 	 * and deadlocks from xfs_inactive.
 	 */
+	xfs_bmap_cancel(&free_list);
 	cancel_flags |= XFS_TRANS_ABORT;
 	xfs_trans_cancel(tp, cancel_flags);
 	IRELE(ip);
-
-	XFS_QM_DQRELE(mp, udqp);
-	XFS_QM_DQRELE(mp, gdqp);
-
-	goto std_return;
+	unlock_dp_on_error = B_FALSE;
+	goto out_dqrele;
 }
 
 #ifdef DEBUG
@@ -2004,8 +2022,10 @@ xfs_link(
 	/* Return through std_return after this point. */
 
 	error = XFS_QM_DQATTACH(mp, sip, 0);
-	if (!error && sip != tdp)
-		error = XFS_QM_DQATTACH(mp, tdp, 0);
+	if (error)
+		goto std_return;
+
+	error = XFS_QM_DQATTACH(mp, tdp, 0);
 	if (error)
 		goto std_return;
 
@@ -2110,209 +2130,6 @@ std_return:
 	goto std_return;
 }
 
-
-int
-xfs_mkdir(
-	xfs_inode_t             *dp,
-	struct xfs_name		*dir_name,
-	mode_t			mode,
-	xfs_inode_t		**ipp,
-	cred_t			*credp)
-{
-	xfs_mount_t		*mp = dp->i_mount;
-	xfs_inode_t		*cdp;	/* inode of created dir */
-	xfs_trans_t		*tp;
-	int			cancel_flags;
-	int			error;
-	int			committed;
-	xfs_bmap_free_t         free_list;
-	xfs_fsblock_t           first_block;
-	boolean_t		unlock_dp_on_error = B_FALSE;
-	boolean_t		created = B_FALSE;
-	int			dm_event_sent = 0;
-	xfs_prid_t		prid;
-	struct xfs_dquot	*udqp, *gdqp;
-	uint			resblks;
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
-
-	tp = NULL;
-
-	if (DM_EVENT_ENABLED(dp, DM_EVENT_CREATE)) {
-		error = XFS_SEND_NAMESP(mp, DM_EVENT_CREATE,
-					dp, DM_RIGHT_NULL, NULL,
-					DM_RIGHT_NULL, dir_name->name, NULL,
-					mode, 0, 0);
-		if (error)
-			return error;
-		dm_event_sent = 1;
-	}
-
-	/* Return through std_return after this point. */
-
-	xfs_itrace_entry(dp);
-
-	mp = dp->i_mount;
-	udqp = gdqp = NULL;
-	if (dp->i_d.di_flags & XFS_DIFLAG_PROJINHERIT)
-		prid = dp->i_d.di_projid;
-	else
-		prid = (xfs_prid_t)dfltprid;
-
-	/*
-	 * Make sure that we have allocated dquot(s) on disk.
-	 */
-	error = XFS_QM_DQVOPALLOC(mp, dp,
-			current_fsuid(), current_fsgid(), prid,
-			XFS_QMOPT_QUOTALL | XFS_QMOPT_INHERIT, &udqp, &gdqp);
-	if (error)
-		goto std_return;
-
-	tp = xfs_trans_alloc(mp, XFS_TRANS_MKDIR);
-	cancel_flags = XFS_TRANS_RELEASE_LOG_RES;
-	resblks = XFS_MKDIR_SPACE_RES(mp, dir_name->len);
-	error = xfs_trans_reserve(tp, resblks, XFS_MKDIR_LOG_RES(mp), 0,
-				  XFS_TRANS_PERM_LOG_RES, XFS_MKDIR_LOG_COUNT);
-	if (error == ENOSPC) {
-		resblks = 0;
-		error = xfs_trans_reserve(tp, 0, XFS_MKDIR_LOG_RES(mp), 0,
-					  XFS_TRANS_PERM_LOG_RES,
-					  XFS_MKDIR_LOG_COUNT);
-	}
-	if (error) {
-		cancel_flags = 0;
-		goto error_return;
-	}
-
-	xfs_ilock(dp, XFS_ILOCK_EXCL | XFS_ILOCK_PARENT);
-	unlock_dp_on_error = B_TRUE;
-
-	/*
-	 * Check for directory link count overflow.
-	 */
-	if (dp->i_d.di_nlink >= XFS_MAXLINK) {
-		error = XFS_ERROR(EMLINK);
-		goto error_return;
-	}
-
-	/*
-	 * Reserve disk quota and the inode.
-	 */
-	error = XFS_TRANS_RESERVE_QUOTA(mp, tp, udqp, gdqp, resblks, 1, 0);
-	if (error)
-		goto error_return;
-
-	error = xfs_dir_canenter(tp, dp, dir_name, resblks);
-	if (error)
-		goto error_return;
-	/*
-	 * create the directory inode.
-	 */
-	error = xfs_dir_ialloc(&tp, dp, mode, 2,
-			0, credp, prid, resblks > 0,
-		&cdp, NULL);
-	if (error) {
-		if (error == ENOSPC)
-			goto error_return;
-		goto abort_return;
-	}
-	xfs_itrace_ref(cdp);
-
-	/*
-	 * Now we add the directory inode to the transaction.
-	 * We waited until now since xfs_dir_ialloc might start
-	 * a new transaction.  Had we joined the transaction
-	 * earlier, the locks might have gotten released. An error
-	 * from here on will result in the transaction cancel
-	 * unlocking dp so don't do it explicitly in the error path.
-	 */
-	IHOLD(dp);
-	xfs_trans_ijoin(tp, dp, XFS_ILOCK_EXCL);
-	unlock_dp_on_error = B_FALSE;
-
-	xfs_bmap_init(&free_list, &first_block);
-
-	error = xfs_dir_createname(tp, dp, dir_name, cdp->i_ino,
-					&first_block, &free_list, resblks ?
-					resblks - XFS_IALLOC_SPACE_RES(mp) : 0);
-	if (error) {
-		ASSERT(error != ENOSPC);
-		goto error1;
-	}
-	xfs_ichgtime(dp, XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
-
-	error = xfs_dir_init(tp, cdp, dp);
-	if (error)
-		goto error2;
-
-	error = xfs_bumplink(tp, dp);
-	if (error)
-		goto error2;
-
-	created = B_TRUE;
-
-	*ipp = cdp;
-	IHOLD(cdp);
-
-	/*
-	 * Attach the dquots to the new inode and modify the icount incore.
-	 */
-	XFS_QM_DQVOPCREATE(mp, tp, cdp, udqp, gdqp);
-
-	/*
-	 * If this is a synchronous mount, make sure that the
-	 * mkdir transaction goes to disk before returning to
-	 * the user.
-	 */
-	if (mp->m_flags & (XFS_MOUNT_WSYNC|XFS_MOUNT_DIRSYNC)) {
-		xfs_trans_set_sync(tp);
-	}
-
-	error = xfs_bmap_finish(&tp, &free_list, &committed);
-	if (error) {
-		IRELE(cdp);
-		goto error2;
-	}
-
-	error = xfs_trans_commit(tp, XFS_TRANS_RELEASE_LOG_RES);
-	XFS_QM_DQRELE(mp, udqp);
-	XFS_QM_DQRELE(mp, gdqp);
-	if (error) {
-		IRELE(cdp);
-	}
-
-	/* Fall through to std_return with error = 0 or errno from
-	 * xfs_trans_commit. */
-
-std_return:
-	if ((created || (error != 0 && dm_event_sent != 0)) &&
-	    DM_EVENT_ENABLED(dp, DM_EVENT_POSTCREATE)) {
-		(void) XFS_SEND_NAMESP(mp, DM_EVENT_POSTCREATE,
-					dp, DM_RIGHT_NULL,
-					created ? cdp : NULL,
-					DM_RIGHT_NULL,
-					dir_name->name, NULL,
-					mode, error, 0);
-	}
-	return error;
-
- error2:
- error1:
-	xfs_bmap_cancel(&free_list);
- abort_return:
-	cancel_flags |= XFS_TRANS_ABORT;
- error_return:
-	xfs_trans_cancel(tp, cancel_flags);
-	XFS_QM_DQRELE(mp, udqp);
-	XFS_QM_DQRELE(mp, gdqp);
-
-	if (unlock_dp_on_error)
-		xfs_iunlock(dp, XFS_ILOCK_EXCL);
-
-	goto std_return;
-}
-
 int
 xfs_symlink(
 	xfs_inode_t		*dp,
@@ -2587,51 +2404,6 @@ std_return:
 }
 
 int
-xfs_inode_flush(
-	xfs_inode_t	*ip,
-	int		flags)
-{
-	xfs_mount_t	*mp = ip->i_mount;
-	int		error = 0;
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return XFS_ERROR(EIO);
-
-	/*
-	 * Bypass inodes which have already been cleaned by
-	 * the inode flush clustering code inside xfs_iflush
-	 */
-	if (xfs_inode_clean(ip))
-		return 0;
-
-	/*
-	 * We make this non-blocking if the inode is contended,
-	 * return EAGAIN to indicate to the caller that they
-	 * did not succeed. This prevents the flush path from
-	 * blocking on inodes inside another operation right
-	 * now, they get caught later by xfs_sync.
-	 */
-	if (flags & FLUSH_SYNC) {
-		xfs_ilock(ip, XFS_ILOCK_SHARED);
-		xfs_iflock(ip);
-	} else if (xfs_ilock_nowait(ip, XFS_ILOCK_SHARED)) {
-		if (xfs_ipincount(ip) || !xfs_iflock_nowait(ip)) {
-			xfs_iunlock(ip, XFS_ILOCK_SHARED);
-			return EAGAIN;
-		}
-	} else {
-		return EAGAIN;
-	}
-
-	error = xfs_iflush(ip, (flags & FLUSH_SYNC) ? XFS_IFLUSH_SYNC
-						    : XFS_IFLUSH_ASYNC_NOBLOCK);
-	xfs_iunlock(ip, XFS_ILOCK_SHARED);
-
-	return error;
-}
-
-
-int
 xfs_set_dmattrs(
 	xfs_inode_t     *ip,
 	u_int		evmask,
@@ -2676,7 +2448,7 @@ xfs_reclaim(
 	ASSERT(!VN_MAPPED(VFS_I(ip)));
 
 	/* bad inode, get out here ASAP */
-	if (VN_BAD(VFS_I(ip))) {
+	if (is_bad_inode(VFS_I(ip))) {
 		xfs_ireclaim(ip);
 		return 0;
 	}
@@ -3090,7 +2862,7 @@ xfs_free_file_space(
 
 	/*
 	 * Need to zero the stuff we're not freeing, on disk.
-	 * If its a realtime file & can't use unwritten extents then we
+	 * If it's a realtime file & can't use unwritten extents then we
 	 * actually need to zero the extent edges.  Otherwise xfs_bunmapi
 	 * will take care of it for us.
 	 */
diff --git a/fs/xfs/xfs_vnodeops.h b/fs/xfs/xfs_vnodeops.h
index 76df328c61b4..04373c6c61ff 100644
--- a/fs/xfs/xfs_vnodeops.h
+++ b/fs/xfs/xfs_vnodeops.h
@@ -31,14 +31,11 @@ int xfs_remove(struct xfs_inode *dp, struct xfs_name *name,
 		struct xfs_inode *ip);
 int xfs_link(struct xfs_inode *tdp, struct xfs_inode *sip,
 		struct xfs_name *target_name);
-int xfs_mkdir(struct xfs_inode *dp, struct xfs_name *dir_name,
-		mode_t mode, struct xfs_inode **ipp, cred_t *credp);
 int xfs_readdir(struct xfs_inode	*dp, void *dirent, size_t bufsize,
 		       xfs_off_t *offset, filldir_t filldir);
 int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
 		const char *target_path, mode_t mode, struct xfs_inode **ipp,
 		cred_t *credp);
-int xfs_inode_flush(struct xfs_inode *ip, int flags);
 int xfs_set_dmattrs(struct xfs_inode *ip, u_int evmask, u_int16_t state);
 int xfs_reclaim(struct xfs_inode *ip);
 int xfs_change_file_space(struct xfs_inode *ip, int cmd,
diff --git a/include/asm-generic/gpio.h b/include/asm-generic/gpio.h
index 81797ec9ab29..d6c379dc64fa 100644
--- a/include/asm-generic/gpio.h
+++ b/include/asm-generic/gpio.h
@@ -55,6 +55,10 @@ struct module;
  *	handled is (base + ngpio - 1).
  * @can_sleep: flag must be set iff get()/set() methods sleep, as they
  *	must while accessing GPIO expander chips over I2C or SPI
+ * @names: if set, must be an array of strings to use as alternative
+ *      names for the GPIOs in this chip. Any entry in the array
+ *      may be NULL if there is no alias for the GPIO, however the
+ *      array must be @ngpio entries long.
  *
  * A gpio_chip can help platforms abstract various sources of GPIOs so
  * they can all be accessed through a common programing interface.
@@ -92,6 +96,7 @@ struct gpio_chip {
 						struct gpio_chip *chip);
 	int			base;
 	u16			ngpio;
+	char			**names;
 	unsigned		can_sleep:1;
 	unsigned		exported:1;
 };
diff --git a/include/asm-m32r/spinlock.h b/include/asm-m32r/spinlock.h
index f5cfba81ee10..dded923883b2 100644
--- a/include/asm-m32r/spinlock.h
+++ b/include/asm-m32r/spinlock.h
@@ -316,6 +316,9 @@ static inline int __raw_write_trylock(raw_rwlock_t *lock)
 	return 0;
 }
 
+#define __raw_read_lock_flags(lock, flags) __raw_read_lock(lock)
+#define __raw_write_lock_flags(lock, flags) __raw_write_lock(lock)
+
 #define _raw_spin_relax(lock)	cpu_relax()
 #define _raw_read_relax(lock)	cpu_relax()
 #define _raw_write_relax(lock)	cpu_relax()
diff --git a/include/drm/drm_crtc_helper.h b/include/drm/drm_crtc_helper.h
index c7d4b2e606a5..ec073d8288d9 100644
--- a/include/drm/drm_crtc_helper.h
+++ b/include/drm/drm_crtc_helper.h
@@ -33,7 +33,6 @@
 #ifndef __DRM_CRTC_HELPER_H__
 #define __DRM_CRTC_HELPER_H__
 
-#include <linux/i2c.h>
 #include <linux/spinlock.h>
 #include <linux/types.h>
 #include <linux/idr.h>
@@ -92,7 +91,7 @@ struct drm_connector_helper_funcs {
 extern int drm_helper_probe_single_connector_modes(struct drm_connector *connector, uint32_t maxX, uint32_t maxY);
 extern void drm_helper_disable_unused_functions(struct drm_device *dev);
 extern int drm_helper_hotplug_stage_two(struct drm_device *dev);
-extern bool drm_helper_initial_config(struct drm_device *dev, bool can_grow);
+extern bool drm_helper_initial_config(struct drm_device *dev);
 extern int drm_crtc_helper_set_config(struct drm_mode_set *set);
 extern bool drm_crtc_helper_set_mode(struct drm_crtc *crtc,
 				     struct drm_display_mode *mode,
diff --git a/include/drm/drm_os_linux.h b/include/drm/drm_os_linux.h
index 013551d03c03..26641e95e0a4 100644
--- a/include/drm/drm_os_linux.h
+++ b/include/drm/drm_os_linux.h
@@ -7,12 +7,12 @@
 #include <linux/delay.h>
 
 #ifndef readq
-static u64 readq(void __iomem *reg)
+static inline u64 readq(void __iomem *reg)
 {
 	return ((u64) readl(reg)) | (((u64) readl(reg + 4UL)) << 32);
 }
 
-static void writeq(u64 val, void __iomem *reg)
+static inline void writeq(u64 val, void __iomem *reg)
 {
 	writel(val & 0xffffffff, reg);
 	writel(val >> 32, reg + 0x4UL);
diff --git a/include/linux/Kbuild b/include/linux/Kbuild
index a67b6227d272..ca9b9b9bd331 100644
--- a/include/linux/Kbuild
+++ b/include/linux/Kbuild
@@ -67,6 +67,7 @@ header-y += falloc.h
 header-y += fd.h
 header-y += fdreg.h
 header-y += fib_rules.h
+header-y += fiemap.h
 header-y += firewire-cdev.h
 header-y += firewire-constants.h
 header-y += fuse.h
diff --git a/include/linux/async_tx.h b/include/linux/async_tx.h
index 45f6297821bd..5fc2ef8d97fa 100644
--- a/include/linux/async_tx.h
+++ b/include/linux/async_tx.h
@@ -21,6 +21,15 @@
 #include <linux/spinlock.h>
 #include <linux/interrupt.h>
 
+/* on architectures without dma-mapping capabilities we need to ensure
+ * that the asynchronous path compiles away
+ */
+#ifdef CONFIG_HAS_DMA
+#define __async_inline
+#else
+#define __async_inline __always_inline
+#endif
+
 /**
  * dma_chan_ref - object used to manage dma channels received from the
  *   dmaengine core.
diff --git a/include/linux/binfmts.h b/include/linux/binfmts.h
index 77b4a9e46004..6638b8148de7 100644
--- a/include/linux/binfmts.h
+++ b/include/linux/binfmts.h
@@ -35,8 +35,7 @@ struct linux_binprm{
 #endif
 	struct mm_struct *mm;
 	unsigned long p; /* current top of mem */
-	unsigned int sh_bang:1,
-		misc_bang:1,
+	unsigned int
 		cred_prepared:1,/* true if creds already prepared (multiple
 				 * preps happen for interpreters) */
 		cap_effective:1;/* true if has elevated effective capabilities,
diff --git a/include/linux/buffer_head.h b/include/linux/buffer_head.h
index 3d7bcde2e332..7b73bb8f1970 100644
--- a/include/linux/buffer_head.h
+++ b/include/linux/buffer_head.h
@@ -332,22 +332,10 @@ extern int __set_page_dirty_buffers(struct page *page);
 
 static inline void buffer_init(void) {}
 static inline int try_to_free_buffers(struct page *page) { return 1; }
-static inline int sync_blockdev(struct block_device *bdev) { return 0; }
 static inline int inode_has_buffers(struct inode *inode) { return 0; }
 static inline void invalidate_inode_buffers(struct inode *inode) {}
 static inline int remove_inode_buffers(struct inode *inode) { return 1; }
 static inline int sync_mapping_buffers(struct address_space *mapping) { return 0; }
-static inline void invalidate_bdev(struct block_device *bdev) {}
-
-static inline struct super_block *freeze_bdev(struct block_device *sb)
-{
-	return NULL;
-}
-
-static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
-{
-	return 0;
-}
 
 #endif /* CONFIG_BLOCK */
 #endif /* _LINUX_BUFFER_HEAD_H */
diff --git a/include/linux/cgroup.h b/include/linux/cgroup.h
index 499900d0cee7..665fa70e4094 100644
--- a/include/linux/cgroup.h
+++ b/include/linux/cgroup.h
@@ -15,6 +15,7 @@
 #include <linux/cgroupstats.h>
 #include <linux/prio_heap.h>
 #include <linux/rwsem.h>
+#include <linux/idr.h>
 
 #ifdef CONFIG_CGROUPS
 
@@ -22,6 +23,7 @@ struct cgroupfs_root;
 struct cgroup_subsys;
 struct inode;
 struct cgroup;
+struct css_id;
 
 extern int cgroup_init_early(void);
 extern int cgroup_init(void);
@@ -47,18 +49,24 @@ enum cgroup_subsys_id {
 
 /* Per-subsystem/per-cgroup state maintained by the system. */
 struct cgroup_subsys_state {
-	/* The cgroup that this subsystem is attached to. Useful
+	/*
+	 * The cgroup that this subsystem is attached to. Useful
 	 * for subsystems that want to know about the cgroup
-	 * hierarchy structure */
+	 * hierarchy structure
+	 */
 	struct cgroup *cgroup;
 
-	/* State maintained by the cgroup system to allow subsystems
+	/*
+	 * State maintained by the cgroup system to allow subsystems
 	 * to be "busy". Should be accessed via css_get(),
-	 * css_tryget() and and css_put(). */
+	 * css_tryget() and and css_put().
+	 */
 
 	atomic_t refcnt;
 
 	unsigned long flags;
+	/* ID for this css, if possible */
+	struct css_id *id;
 };
 
 /* bits in struct cgroup_subsys_state flags field */
@@ -120,19 +128,26 @@ static inline void css_put(struct cgroup_subsys_state *css)
 enum {
 	/* Control Group is dead */
 	CGRP_REMOVED,
-	/* Control Group has previously had a child cgroup or a task,
-	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set) */
+	/*
+	 * Control Group has previously had a child cgroup or a task,
+	 * but no longer (only if CGRP_NOTIFY_ON_RELEASE is set)
+	 */
 	CGRP_RELEASABLE,
 	/* Control Group requires release notifications to userspace */
 	CGRP_NOTIFY_ON_RELEASE,
+	/*
+	 * A thread in rmdir() is wating for this cgroup.
+	 */
+	CGRP_WAIT_ON_RMDIR,
 };
 
 struct cgroup {
 	unsigned long flags;		/* "unsigned long" so bitops work */
 
-	/* count users of this cgroup. >0 means busy, but doesn't
-	 * necessarily indicate the number of tasks in the
-	 * cgroup */
+	/*
+	 * count users of this cgroup. >0 means busy, but doesn't
+	 * necessarily indicate the number of tasks in the cgroup
+	 */
 	atomic_t count;
 
 	/*
@@ -142,7 +157,7 @@ struct cgroup {
 	struct list_head sibling;	/* my parent's children */
 	struct list_head children;	/* my children */
 
-	struct cgroup *parent;	/* my parent */
+	struct cgroup *parent;		/* my parent */
 	struct dentry *dentry;	  	/* cgroup fs entry, RCU protected */
 
 	/* Private pointers for each registered subsystem */
@@ -177,11 +192,12 @@ struct cgroup {
 	struct rcu_head rcu_head;
 };
 
-/* A css_set is a structure holding pointers to a set of
+/*
+ * A css_set is a structure holding pointers to a set of
  * cgroup_subsys_state objects. This saves space in the task struct
  * object and speeds up fork()/exit(), since a single inc/dec and a
- * list_add()/del() can bump the reference count on the entire
- * cgroup set for a task.
+ * list_add()/del() can bump the reference count on the entire cgroup
+ * set for a task.
  */
 
 struct css_set {
@@ -226,13 +242,8 @@ struct cgroup_map_cb {
 	void *state;
 };
 
-/* struct cftype:
- *
- * The files in the cgroup filesystem mostly have a very simple read/write
- * handling, some common function will take care of it. Nevertheless some cases
- * (read tasks) are special and therefore I define this structure for every
- * kind of file.
- *
+/*
+ * struct cftype: handler definitions for cgroup control files
  *
  * When reading/writing to a file:
  *	- the cgroup to use is file->f_dentry->d_parent->d_fsdata
@@ -241,10 +252,17 @@ struct cgroup_map_cb {
 
 #define MAX_CFTYPE_NAME 64
 struct cftype {
-	/* By convention, the name should begin with the name of the
-	 * subsystem, followed by a period */
+	/*
+	 * By convention, the name should begin with the name of the
+	 * subsystem, followed by a period
+	 */
 	char name[MAX_CFTYPE_NAME];
 	int private;
+	/*
+	 * If not 0, file mode is set to this value, otherwise it will
+	 * be figured out automatically
+	 */
+	mode_t mode;
 
 	/*
 	 * If non-zero, defines the maximum length of string that can
@@ -319,15 +337,20 @@ struct cgroup_scanner {
 	void (*process_task)(struct task_struct *p,
 			struct cgroup_scanner *scan);
 	struct ptr_heap *heap;
+	void *data;
 };
 
-/* Add a new file to the given cgroup directory. Should only be
- * called by subsystems from within a populate() method */
+/*
+ * Add a new file to the given cgroup directory. Should only be
+ * called by subsystems from within a populate() method
+ */
 int cgroup_add_file(struct cgroup *cgrp, struct cgroup_subsys *subsys,
 		       const struct cftype *cft);
 
-/* Add a set of new files to the given cgroup directory. Should
- * only be called by subsystems from within a populate() method */
+/*
+ * Add a set of new files to the given cgroup directory. Should
+ * only be called by subsystems from within a populate() method
+ */
 int cgroup_add_files(struct cgroup *cgrp,
 			struct cgroup_subsys *subsys,
 			const struct cftype cft[],
@@ -339,15 +362,18 @@ int cgroup_path(const struct cgroup *cgrp, char *buf, int buflen);
 
 int cgroup_task_count(const struct cgroup *cgrp);
 
-/* Return true if the cgroup is a descendant of the current cgroup */
-int cgroup_is_descendant(const struct cgroup *cgrp);
+/* Return true if cgrp is a descendant of the task's cgroup */
+int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task);
 
-/* Control Group subsystem type. See Documentation/cgroups.txt for details */
+/*
+ * Control Group subsystem type.
+ * See Documentation/cgroups/cgroups.txt for details
+ */
 
 struct cgroup_subsys {
 	struct cgroup_subsys_state *(*create)(struct cgroup_subsys *ss,
 						  struct cgroup *cgrp);
-	void (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
+	int (*pre_destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
 	void (*destroy)(struct cgroup_subsys *ss, struct cgroup *cgrp);
 	int (*can_attach)(struct cgroup_subsys *ss,
 			  struct cgroup *cgrp, struct task_struct *tsk);
@@ -364,6 +390,11 @@ struct cgroup_subsys {
 	int active;
 	int disabled;
 	int early_init;
+	/*
+	 * True if this subsys uses ID. ID is not available before cgroup_init()
+	 * (not available in early_init time.)
+	 */
+	bool use_id;
 #define MAX_CGROUP_TYPE_NAMELEN 32
 	const char *name;
 
@@ -386,6 +417,9 @@ struct cgroup_subsys {
 	 */
 	struct cgroupfs_root *root;
 	struct list_head sibling;
+	/* used when use_id == true */
+	struct idr idr;
+	spinlock_t id_lock;
 };
 
 #define SUBSYS(_x) extern struct cgroup_subsys _x ## _subsys;
@@ -419,7 +453,8 @@ struct cgroup_iter {
 	struct list_head *task;
 };
 
-/* To iterate across the tasks in a cgroup:
+/*
+ * To iterate across the tasks in a cgroup:
  *
  * 1) call cgroup_iter_start to intialize an iterator
  *
@@ -428,9 +463,10 @@ struct cgroup_iter {
  *
  * 3) call cgroup_iter_end() to destroy the iterator.
  *
- * Or, call cgroup_scan_tasks() to iterate through every task in a cpuset.
- *    - cgroup_scan_tasks() holds the css_set_lock when calling the test_task()
- *      callback, but not while calling the process_task() callback.
+ * Or, call cgroup_scan_tasks() to iterate through every task in a
+ * cgroup - cgroup_scan_tasks() holds the css_set_lock when calling
+ * the test_task() callback, but not while calling the process_task()
+ * callback.
  */
 void cgroup_iter_start(struct cgroup *cgrp, struct cgroup_iter *it);
 struct task_struct *cgroup_iter_next(struct cgroup *cgrp,
@@ -439,6 +475,44 @@ void cgroup_iter_end(struct cgroup *cgrp, struct cgroup_iter *it);
 int cgroup_scan_tasks(struct cgroup_scanner *scan);
 int cgroup_attach_task(struct cgroup *, struct task_struct *);
 
+/*
+ * CSS ID is ID for cgroup_subsys_state structs under subsys. This only works
+ * if cgroup_subsys.use_id == true. It can be used for looking up and scanning.
+ * CSS ID is assigned at cgroup allocation (create) automatically
+ * and removed when subsys calls free_css_id() function. This is because
+ * the lifetime of cgroup_subsys_state is subsys's matter.
+ *
+ * Looking up and scanning function should be called under rcu_read_lock().
+ * Taking cgroup_mutex()/hierarchy_mutex() is not necessary for following calls.
+ * But the css returned by this routine can be "not populated yet" or "being
+ * destroyed". The caller should check css and cgroup's status.
+ */
+
+/*
+ * Typically Called at ->destroy(), or somewhere the subsys frees
+ * cgroup_subsys_state.
+ */
+void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css);
+
+/* Find a cgroup_subsys_state which has given ID */
+
+struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id);
+
+/*
+ * Get a cgroup whose id is greater than or equal to id under tree of root.
+ * Returning a cgroup_subsys_state or NULL.
+ */
+struct cgroup_subsys_state *css_get_next(struct cgroup_subsys *ss, int id,
+		struct cgroup_subsys_state *root, int *foundid);
+
+/* Returns true if root is ancestor of cg */
+bool css_is_ancestor(struct cgroup_subsys_state *cg,
+		     const struct cgroup_subsys_state *root);
+
+/* Get id and depth of css */
+unsigned short css_id(struct cgroup_subsys_state *css);
+unsigned short css_depth(struct cgroup_subsys_state *css);
+
 #else /* !CONFIG_CGROUPS */
 
 static inline int cgroup_init_early(void) { return 0; }
diff --git a/include/linux/compat.h b/include/linux/compat.h
index b880864672de..f2ded21f9a3c 100644
--- a/include/linux/compat.h
+++ b/include/linux/compat.h
@@ -191,6 +191,12 @@ asmlinkage ssize_t compat_sys_readv(unsigned long fd,
 		const struct compat_iovec __user *vec, unsigned long vlen);
 asmlinkage ssize_t compat_sys_writev(unsigned long fd,
 		const struct compat_iovec __user *vec, unsigned long vlen);
+asmlinkage ssize_t compat_sys_preadv(unsigned long fd,
+		const struct compat_iovec __user *vec,
+		unsigned long vlen, u32 pos_low, u32 pos_high);
+asmlinkage ssize_t compat_sys_pwritev(unsigned long fd,
+		const struct compat_iovec __user *vec,
+		unsigned long vlen, u32 pos_low, u32 pos_high);
 
 int compat_do_execve(char * filename, compat_uptr_t __user *argv,
 	        compat_uptr_t __user *envp, struct pt_regs * regs);
diff --git a/include/linux/cpu.h b/include/linux/cpu.h
index c2747ac2ae43..2643d848df90 100644
--- a/include/linux/cpu.h
+++ b/include/linux/cpu.h
@@ -23,7 +23,6 @@
 #include <linux/node.h>
 #include <linux/compiler.h>
 #include <linux/cpumask.h>
-#include <linux/mutex.h>
 
 struct cpu {
 	int node_id;		/* The node which contains the CPU */
@@ -103,16 +102,6 @@ extern struct sysdev_class cpu_sysdev_class;
 #ifdef CONFIG_HOTPLUG_CPU
 /* Stop CPUs going up and down. */
 
-static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex)
-{
-	mutex_lock(cpu_hp_mutex);
-}
-
-static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
-{
-	mutex_unlock(cpu_hp_mutex);
-}
-
 extern void get_online_cpus(void);
 extern void put_online_cpus(void);
 #define hotcpu_notifier(fn, pri) {				\
@@ -126,11 +115,6 @@ int cpu_down(unsigned int cpu);
 
 #else		/* CONFIG_HOTPLUG_CPU */
 
-static inline void cpuhotplug_mutex_lock(struct mutex *cpu_hp_mutex)
-{ }
-static inline void cpuhotplug_mutex_unlock(struct mutex *cpu_hp_mutex)
-{ }
-
 #define get_online_cpus()	do { } while (0)
 #define put_online_cpus()	do { } while (0)
 #define hotcpu_notifier(fn, pri)	do { (void)(fn); } while (0)
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 2e0d79678deb..05ea1dd7d681 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -12,6 +12,7 @@
 #include <linux/cpumask.h>
 #include <linux/nodemask.h>
 #include <linux/cgroup.h>
+#include <linux/mm.h>
 
 #ifdef CONFIG_CPUSETS
 
@@ -29,19 +30,29 @@ void cpuset_init_current_mems_allowed(void);
 void cpuset_update_task_memory_state(void);
 int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask);
 
-extern int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask);
-extern int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask);
+extern int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask);
+extern int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask);
 
-static int inline cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 {
 	return number_of_cpusets <= 1 ||
-		__cpuset_zone_allowed_softwall(z, gfp_mask);
+		__cpuset_node_allowed_softwall(node, gfp_mask);
 }
 
-static int inline cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 {
 	return number_of_cpusets <= 1 ||
-		__cpuset_zone_allowed_hardwall(z, gfp_mask);
+		__cpuset_node_allowed_hardwall(node, gfp_mask);
+}
+
+static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+{
+	return cpuset_node_allowed_softwall(zone_to_nid(z), gfp_mask);
+}
+
+static inline int cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+{
+	return cpuset_node_allowed_hardwall(zone_to_nid(z), gfp_mask);
 }
 
 extern int cpuset_mems_allowed_intersects(const struct task_struct *tsk1,
@@ -112,6 +123,16 @@ static inline int cpuset_nodemask_valid_mems_allowed(nodemask_t *nodemask)
 	return 1;
 }
 
+static inline int cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
+{
+	return 1;
+}
+
+static inline int cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
+{
+	return 1;
+}
+
 static inline int cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
 {
 	return 1;
diff --git a/include/linux/device-mapper.h b/include/linux/device-mapper.h
index 8209e08969f9..66ec05a57955 100644
--- a/include/linux/device-mapper.h
+++ b/include/linux/device-mapper.h
@@ -139,6 +139,9 @@ struct target_type {
 	dm_ioctl_fn ioctl;
 	dm_merge_fn merge;
 	dm_busy_fn busy;
+
+	/* For internal device-mapper use. */
+	struct list_head list;
 };
 
 struct io_restrictions {
diff --git a/include/linux/dm-dirty-log.h b/include/linux/dm-dirty-log.h
index 600c5fb2daad..5e8b11d88f6f 100644
--- a/include/linux/dm-dirty-log.h
+++ b/include/linux/dm-dirty-log.h
@@ -28,6 +28,9 @@ struct dm_dirty_log_type {
 	const char *name;
 	struct module *module;
 
+	/* For internal device-mapper use */
+	struct list_head list;
+
 	int (*ctr)(struct dm_dirty_log *log, struct dm_target *ti,
 		   unsigned argc, char **argv);
 	void (*dtr)(struct dm_dirty_log *log);
@@ -113,6 +116,16 @@ struct dm_dirty_log_type {
 	 */
 	int (*status)(struct dm_dirty_log *log, status_type_t status_type,
 		      char *result, unsigned maxlen);
+
+	/*
+	 * is_remote_recovering is necessary for cluster mirroring. It provides
+	 * a way to detect recovery on another node, so we aren't writing
+	 * concurrently.  This function is likely to block (when a cluster log
+	 * is used).
+	 *
+	 * Returns: 0, 1
+	 */
+	int (*is_remote_recovering)(struct dm_dirty_log *log, region_t region);
 };
 
 int dm_dirty_log_type_register(struct dm_dirty_log_type *type);
diff --git a/include/linux/dma_remapping.h b/include/linux/dma_remapping.h
index af1dab41674b..1a455f1f86d7 100644
--- a/include/linux/dma_remapping.h
+++ b/include/linux/dma_remapping.h
@@ -11,6 +11,7 @@
 
 #define DMA_PTE_READ (1)
 #define DMA_PTE_WRITE (2)
+#define DMA_PTE_SNP (1 << 11)
 
 struct intel_iommu;
 struct dmar_domain;
diff --git a/include/linux/dmaengine.h b/include/linux/dmaengine.h
index 1956c8d46d32..2e2aa3df170c 100644
--- a/include/linux/dmaengine.h
+++ b/include/linux/dmaengine.h
@@ -23,9 +23,6 @@
 
 #include <linux/device.h>
 #include <linux/uio.h>
-#include <linux/kref.h>
-#include <linux/completion.h>
-#include <linux/rcupdate.h>
 #include <linux/dma-mapping.h>
 
 /**
@@ -205,6 +202,7 @@ struct dma_async_tx_descriptor {
 /**
  * struct dma_device - info on the entity supplying DMA services
  * @chancnt: how many DMA channels are supported
+ * @privatecnt: how many DMA channels are requested by dma_request_channel
  * @channels: the list of struct dma_chan
  * @global_node: list_head for global dma_device_list
  * @cap_mask: one or more dma_capability flags
@@ -227,6 +225,7 @@ struct dma_async_tx_descriptor {
 struct dma_device {
 
 	unsigned int chancnt;
+	unsigned int privatecnt;
 	struct list_head channels;
 	struct list_head global_node;
 	dma_cap_mask_t  cap_mask;
@@ -291,6 +290,24 @@ static inline void net_dmaengine_put(void)
 }
 #endif
 
+#ifdef CONFIG_ASYNC_TX_DMA
+#define async_dmaengine_get()	dmaengine_get()
+#define async_dmaengine_put()	dmaengine_put()
+#define async_dma_find_channel(type) dma_find_channel(type)
+#else
+static inline void async_dmaengine_get(void)
+{
+}
+static inline void async_dmaengine_put(void)
+{
+}
+static inline struct dma_chan *
+async_dma_find_channel(enum dma_transaction_type type)
+{
+	return NULL;
+}
+#endif
+
 dma_cookie_t dma_async_memcpy_buf_to_buf(struct dma_chan *chan,
 	void *dest, void *src, size_t len);
 dma_cookie_t dma_async_memcpy_buf_to_pg(struct dma_chan *chan,
@@ -337,6 +354,13 @@ __dma_cap_set(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
 	set_bit(tx_type, dstp->bits);
 }
 
+#define dma_cap_clear(tx, mask) __dma_cap_clear((tx), &(mask))
+static inline void
+__dma_cap_clear(enum dma_transaction_type tx_type, dma_cap_mask_t *dstp)
+{
+	clear_bit(tx_type, dstp->bits);
+}
+
 #define dma_cap_zero(mask) __dma_cap_zero(&(mask))
 static inline void __dma_cap_zero(dma_cap_mask_t *dstp)
 {
diff --git a/include/linux/dw_dmac.h b/include/linux/dw_dmac.h
index d797dde247f7..c8aad713a046 100644
--- a/include/linux/dw_dmac.h
+++ b/include/linux/dw_dmac.h
@@ -74,4 +74,23 @@ struct dw_dma_slave {
 #define DWC_CFGL_HS_DST_POL	(1 << 18)	/* dst handshake active low */
 #define DWC_CFGL_HS_SRC_POL	(1 << 19)	/* src handshake active low */
 
+/* DMA API extensions */
+struct dw_cyclic_desc {
+	struct dw_desc	**desc;
+	unsigned long	periods;
+	void		(*period_callback)(void *param);
+	void		*period_callback_param;
+};
+
+struct dw_cyclic_desc *dw_dma_cyclic_prep(struct dma_chan *chan,
+		dma_addr_t buf_addr, size_t buf_len, size_t period_len,
+		enum dma_data_direction direction);
+void dw_dma_cyclic_free(struct dma_chan *chan);
+int dw_dma_cyclic_start(struct dma_chan *chan);
+void dw_dma_cyclic_stop(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_src_addr(struct dma_chan *chan);
+
+dma_addr_t dw_dma_get_dst_addr(struct dma_chan *chan);
+
 #endif /* DW_DMAC_H */
diff --git a/include/linux/ext3_fs.h b/include/linux/ext3_fs.h
index dd495b8c3091..634a5e5aba3e 100644
--- a/include/linux/ext3_fs.h
+++ b/include/linux/ext3_fs.h
@@ -208,6 +208,7 @@ static inline __u32 ext3_mask_flags(umode_t mode, __u32 flags)
 #define EXT3_STATE_JDATA		0x00000001 /* journaled data exists */
 #define EXT3_STATE_NEW			0x00000002 /* inode is newly created */
 #define EXT3_STATE_XATTR		0x00000004 /* has in-inode xattrs */
+#define EXT3_STATE_FLUSH_ON_CLOSE	0x00000008
 
 /* Used to pass group descriptor data when online resize is done */
 struct ext3_new_group_input {
@@ -893,9 +894,8 @@ extern int ext3_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		       u64 start, u64 len);
 
 /* ioctl.c */
-extern int ext3_ioctl (struct inode *, struct file *, unsigned int,
-		       unsigned long);
-extern long ext3_compat_ioctl (struct file *, unsigned int, unsigned long);
+extern long ext3_ioctl(struct file *, unsigned int, unsigned long);
+extern long ext3_compat_ioctl(struct file *, unsigned int, unsigned long);
 
 /* namei.c */
 extern int ext3_orphan_add(handle_t *, struct inode *);
diff --git a/include/linux/fs.h b/include/linux/fs.h
index 61211ad823fe..a09e17c8f5fd 100644
--- a/include/linux/fs.h
+++ b/include/linux/fs.h
@@ -1741,6 +1741,8 @@ extern void drop_collected_mounts(struct vfsmount *);
 
 extern int vfs_statfs(struct dentry *, struct kstatfs *);
 
+extern int current_umask(void);
+
 /* /sys/fs */
 extern struct kobject *fs_kobj;
 
@@ -1885,6 +1887,18 @@ extern int fsync_super(struct super_block *);
 extern int fsync_no_super(struct block_device *);
 #else
 static inline void bd_forget(struct inode *inode) {}
+static inline int sync_blockdev(struct block_device *bdev) { return 0; }
+static inline void invalidate_bdev(struct block_device *bdev) {}
+
+static inline struct super_block *freeze_bdev(struct block_device *sb)
+{
+	return NULL;
+}
+
+static inline int thaw_bdev(struct block_device *bdev, struct super_block *sb)
+{
+	return 0;
+}
 #endif
 extern const struct file_operations def_blk_fops;
 extern const struct file_operations def_chr_fops;
diff --git a/include/linux/fs_struct.h b/include/linux/fs_struct.h
index 18b467dbe278..78a05bfcd8eb 100644
--- a/include/linux/fs_struct.h
+++ b/include/linux/fs_struct.h
@@ -4,12 +4,10 @@
 #include <linux/path.h>
 
 struct fs_struct {
-	atomic_t count;	/* This usage count is used by check_unsafe_exec() for
-			 * security checking purposes - therefore it may not be
-			 * incremented, except by clone(CLONE_FS).
-			 */
+	int users;
 	rwlock_t lock;
 	int umask;
+	int in_exec;
 	struct path root, pwd;
 };
 
@@ -19,6 +17,8 @@ extern void exit_fs(struct task_struct *);
 extern void set_fs_root(struct fs_struct *, struct path *);
 extern void set_fs_pwd(struct fs_struct *, struct path *);
 extern struct fs_struct *copy_fs_struct(struct fs_struct *);
-extern void put_fs_struct(struct fs_struct *);
+extern void free_fs_struct(struct fs_struct *);
+extern void daemonize_fs_struct(void);
+extern int unshare_fs_struct(void);
 
 #endif /* _LINUX_FS_STRUCT_H */
diff --git a/include/linux/fscache-cache.h b/include/linux/fscache-cache.h
new file mode 100644
index 000000000000..84d3532dd3ea
--- /dev/null
+++ b/include/linux/fscache-cache.h
@@ -0,0 +1,505 @@
+/* General filesystem caching backing cache interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ *	Documentation/filesystems/caching/backend-api.txt
+ *
+ * for a description of the cache backend interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_CACHE_H
+#define _LINUX_FSCACHE_CACHE_H
+
+#include <linux/fscache.h>
+#include <linux/sched.h>
+#include <linux/slow-work.h>
+
+#define NR_MAXCACHES BITS_PER_LONG
+
+struct fscache_cache;
+struct fscache_cache_ops;
+struct fscache_object;
+struct fscache_operation;
+
+/*
+ * cache tag definition
+ */
+struct fscache_cache_tag {
+	struct list_head	link;
+	struct fscache_cache	*cache;		/* cache referred to by this tag */
+	unsigned long		flags;
+#define FSCACHE_TAG_RESERVED	0		/* T if tag is reserved for a cache */
+	atomic_t		usage;
+	char			name[0];	/* tag name */
+};
+
+/*
+ * cache definition
+ */
+struct fscache_cache {
+	const struct fscache_cache_ops *ops;
+	struct fscache_cache_tag *tag;		/* tag representing this cache */
+	struct kobject		*kobj;		/* system representation of this cache */
+	struct list_head	link;		/* link in list of caches */
+	size_t			max_index_size;	/* maximum size of index data */
+	char			identifier[36];	/* cache label */
+
+	/* node management */
+	struct work_struct	op_gc;		/* operation garbage collector */
+	struct list_head	object_list;	/* list of data/index objects */
+	struct list_head	op_gc_list;	/* list of ops to be deleted */
+	spinlock_t		object_list_lock;
+	spinlock_t		op_gc_list_lock;
+	atomic_t		object_count;	/* no. of live objects in this cache */
+	struct fscache_object	*fsdef;		/* object for the fsdef index */
+	unsigned long		flags;
+#define FSCACHE_IOERROR		0	/* cache stopped on I/O error */
+#define FSCACHE_CACHE_WITHDRAWN	1	/* cache has been withdrawn */
+};
+
+extern wait_queue_head_t fscache_cache_cleared_wq;
+
+/*
+ * operation to be applied to a cache object
+ * - retrieval initiation operations are done in the context of the process
+ *   that issued them, and not in an async thread pool
+ */
+typedef void (*fscache_operation_release_t)(struct fscache_operation *op);
+typedef void (*fscache_operation_processor_t)(struct fscache_operation *op);
+
+struct fscache_operation {
+	union {
+		struct work_struct fast_work;	/* record for fast ops */
+		struct slow_work slow_work;	/* record for (very) slow ops */
+	};
+	struct list_head	pend_link;	/* link in object->pending_ops */
+	struct fscache_object	*object;	/* object to be operated upon */
+
+	unsigned long		flags;
+#define FSCACHE_OP_TYPE		0x000f	/* operation type */
+#define FSCACHE_OP_FAST		0x0001	/* - fast op, processor may not sleep for disk */
+#define FSCACHE_OP_SLOW		0x0002	/* - (very) slow op, processor may sleep for disk */
+#define FSCACHE_OP_MYTHREAD	0x0003	/* - processing is done be issuing thread, not pool */
+#define FSCACHE_OP_WAITING	4	/* cleared when op is woken */
+#define FSCACHE_OP_EXCLUSIVE	5	/* exclusive op, other ops must wait */
+#define FSCACHE_OP_DEAD		6	/* op is now dead */
+
+	atomic_t		usage;
+	unsigned		debug_id;	/* debugging ID */
+
+	/* operation processor callback
+	 * - can be NULL if FSCACHE_OP_WAITING is going to be used to perform
+	 *   the op in a non-pool thread */
+	fscache_operation_processor_t processor;
+
+	/* operation releaser */
+	fscache_operation_release_t release;
+};
+
+extern atomic_t fscache_op_debug_id;
+extern const struct slow_work_ops fscache_op_slow_work_ops;
+
+extern void fscache_enqueue_operation(struct fscache_operation *);
+extern void fscache_put_operation(struct fscache_operation *);
+
+/**
+ * fscache_operation_init - Do basic initialisation of an operation
+ * @op: The operation to initialise
+ * @release: The release function to assign
+ *
+ * Do basic initialisation of an operation.  The caller must still set flags,
+ * object, either fast_work or slow_work if necessary, and processor if needed.
+ */
+static inline void fscache_operation_init(struct fscache_operation *op,
+					  fscache_operation_release_t release)
+{
+	atomic_set(&op->usage, 1);
+	op->debug_id = atomic_inc_return(&fscache_op_debug_id);
+	op->release = release;
+	INIT_LIST_HEAD(&op->pend_link);
+}
+
+/**
+ * fscache_operation_init_slow - Do additional initialisation of a slow op
+ * @op: The operation to initialise
+ * @processor: The processor function to assign
+ *
+ * Do additional initialisation of an operation as required for slow work.
+ */
+static inline
+void fscache_operation_init_slow(struct fscache_operation *op,
+				 fscache_operation_processor_t processor)
+{
+	op->processor = processor;
+	slow_work_init(&op->slow_work, &fscache_op_slow_work_ops);
+}
+
+/*
+ * data read operation
+ */
+struct fscache_retrieval {
+	struct fscache_operation op;
+	struct address_space	*mapping;	/* netfs pages */
+	fscache_rw_complete_t	end_io_func;	/* function to call on I/O completion */
+	void			*context;	/* netfs read context (pinned) */
+	struct list_head	to_do;		/* list of things to be done by the backend */
+	unsigned long		start_time;	/* time at which retrieval started */
+};
+
+typedef int (*fscache_page_retrieval_func_t)(struct fscache_retrieval *op,
+					     struct page *page,
+					     gfp_t gfp);
+
+typedef int (*fscache_pages_retrieval_func_t)(struct fscache_retrieval *op,
+					      struct list_head *pages,
+					      unsigned *nr_pages,
+					      gfp_t gfp);
+
+/**
+ * fscache_get_retrieval - Get an extra reference on a retrieval operation
+ * @op: The retrieval operation to get a reference on
+ *
+ * Get an extra reference on a retrieval operation.
+ */
+static inline
+struct fscache_retrieval *fscache_get_retrieval(struct fscache_retrieval *op)
+{
+	atomic_inc(&op->op.usage);
+	return op;
+}
+
+/**
+ * fscache_enqueue_retrieval - Enqueue a retrieval operation for processing
+ * @op: The retrieval operation affected
+ *
+ * Enqueue a retrieval operation for processing by the FS-Cache thread pool.
+ */
+static inline void fscache_enqueue_retrieval(struct fscache_retrieval *op)
+{
+	fscache_enqueue_operation(&op->op);
+}
+
+/**
+ * fscache_put_retrieval - Drop a reference to a retrieval operation
+ * @op: The retrieval operation affected
+ *
+ * Drop a reference to a retrieval operation.
+ */
+static inline void fscache_put_retrieval(struct fscache_retrieval *op)
+{
+	fscache_put_operation(&op->op);
+}
+
+/*
+ * cached page storage work item
+ * - used to do three things:
+ *   - batch writes to the cache
+ *   - do cache writes asynchronously
+ *   - defer writes until cache object lookup completion
+ */
+struct fscache_storage {
+	struct fscache_operation op;
+	pgoff_t			store_limit;	/* don't write more than this */
+};
+
+/*
+ * cache operations
+ */
+struct fscache_cache_ops {
+	/* name of cache provider */
+	const char *name;
+
+	/* allocate an object record for a cookie */
+	struct fscache_object *(*alloc_object)(struct fscache_cache *cache,
+					       struct fscache_cookie *cookie);
+
+	/* look up the object for a cookie */
+	void (*lookup_object)(struct fscache_object *object);
+
+	/* finished looking up */
+	void (*lookup_complete)(struct fscache_object *object);
+
+	/* increment the usage count on this object (may fail if unmounting) */
+	struct fscache_object *(*grab_object)(struct fscache_object *object);
+
+	/* pin an object in the cache */
+	int (*pin_object)(struct fscache_object *object);
+
+	/* unpin an object in the cache */
+	void (*unpin_object)(struct fscache_object *object);
+
+	/* store the updated auxilliary data on an object */
+	void (*update_object)(struct fscache_object *object);
+
+	/* discard the resources pinned by an object and effect retirement if
+	 * necessary */
+	void (*drop_object)(struct fscache_object *object);
+
+	/* dispose of a reference to an object */
+	void (*put_object)(struct fscache_object *object);
+
+	/* sync a cache */
+	void (*sync_cache)(struct fscache_cache *cache);
+
+	/* notification that the attributes of a non-index object (such as
+	 * i_size) have changed */
+	int (*attr_changed)(struct fscache_object *object);
+
+	/* reserve space for an object's data and associated metadata */
+	int (*reserve_space)(struct fscache_object *object, loff_t i_size);
+
+	/* request a backing block for a page be read or allocated in the
+	 * cache */
+	fscache_page_retrieval_func_t read_or_alloc_page;
+
+	/* request backing blocks for a list of pages be read or allocated in
+	 * the cache */
+	fscache_pages_retrieval_func_t read_or_alloc_pages;
+
+	/* request a backing block for a page be allocated in the cache so that
+	 * it can be written directly */
+	fscache_page_retrieval_func_t allocate_page;
+
+	/* request backing blocks for pages be allocated in the cache so that
+	 * they can be written directly */
+	fscache_pages_retrieval_func_t allocate_pages;
+
+	/* write a page to its backing block in the cache */
+	int (*write_page)(struct fscache_storage *op, struct page *page);
+
+	/* detach backing block from a page (optional)
+	 * - must release the cookie lock before returning
+	 * - may sleep
+	 */
+	void (*uncache_page)(struct fscache_object *object,
+			     struct page *page);
+
+	/* dissociate a cache from all the pages it was backing */
+	void (*dissociate_pages)(struct fscache_cache *cache);
+};
+
+/*
+ * data file or index object cookie
+ * - a file will only appear in one cache
+ * - a request to cache a file may or may not be honoured, subject to
+ *   constraints such as disk space
+ * - indices are created on disk just-in-time
+ */
+struct fscache_cookie {
+	atomic_t			usage;		/* number of users of this cookie */
+	atomic_t			n_children;	/* number of children of this cookie */
+	spinlock_t			lock;
+	struct hlist_head		backing_objects; /* object(s) backing this file/index */
+	const struct fscache_cookie_def	*def;		/* definition */
+	struct fscache_cookie		*parent;	/* parent of this entry */
+	void				*netfs_data;	/* back pointer to netfs */
+	struct radix_tree_root		stores;		/* pages to be stored on this cookie */
+#define FSCACHE_COOKIE_PENDING_TAG	0		/* pages tag: pending write to cache */
+
+	unsigned long			flags;
+#define FSCACHE_COOKIE_LOOKING_UP	0	/* T if non-index cookie being looked up still */
+#define FSCACHE_COOKIE_CREATING		1	/* T if non-index object being created still */
+#define FSCACHE_COOKIE_NO_DATA_YET	2	/* T if new object with no cached data yet */
+#define FSCACHE_COOKIE_PENDING_FILL	3	/* T if pending initial fill on object */
+#define FSCACHE_COOKIE_FILLING		4	/* T if filling object incrementally */
+#define FSCACHE_COOKIE_UNAVAILABLE	5	/* T if cookie is unavailable (error, etc) */
+};
+
+extern struct fscache_cookie fscache_fsdef_index;
+
+/*
+ * on-disk cache file or index handle
+ */
+struct fscache_object {
+	enum fscache_object_state {
+		FSCACHE_OBJECT_INIT,		/* object in initial unbound state */
+		FSCACHE_OBJECT_LOOKING_UP,	/* looking up object */
+		FSCACHE_OBJECT_CREATING,	/* creating object */
+
+		/* active states */
+		FSCACHE_OBJECT_AVAILABLE,	/* cleaning up object after creation */
+		FSCACHE_OBJECT_ACTIVE,		/* object is usable */
+		FSCACHE_OBJECT_UPDATING,	/* object is updating */
+
+		/* terminal states */
+		FSCACHE_OBJECT_DYING,		/* object waiting for accessors to finish */
+		FSCACHE_OBJECT_LC_DYING,	/* object cleaning up after lookup/create */
+		FSCACHE_OBJECT_ABORT_INIT,	/* abort the init state */
+		FSCACHE_OBJECT_RELEASING,	/* releasing object */
+		FSCACHE_OBJECT_RECYCLING,	/* retiring object */
+		FSCACHE_OBJECT_WITHDRAWING,	/* withdrawing object */
+		FSCACHE_OBJECT_DEAD,		/* object is now dead */
+	} state;
+
+	int			debug_id;	/* debugging ID */
+	int			n_children;	/* number of child objects */
+	int			n_ops;		/* number of ops outstanding on object */
+	int			n_obj_ops;	/* number of object ops outstanding on object */
+	int			n_in_progress;	/* number of ops in progress */
+	int			n_exclusive;	/* number of exclusive ops queued */
+	spinlock_t		lock;		/* state and operations lock */
+
+	unsigned long		lookup_jif;	/* time at which lookup started */
+	unsigned long		event_mask;	/* events this object is interested in */
+	unsigned long		events;		/* events to be processed by this object
+						 * (order is important - using fls) */
+#define FSCACHE_OBJECT_EV_REQUEUE	0	/* T if object should be requeued */
+#define FSCACHE_OBJECT_EV_UPDATE	1	/* T if object should be updated */
+#define FSCACHE_OBJECT_EV_CLEARED	2	/* T if accessors all gone */
+#define FSCACHE_OBJECT_EV_ERROR		3	/* T if fatal error occurred during processing */
+#define FSCACHE_OBJECT_EV_RELEASE	4	/* T if netfs requested object release */
+#define FSCACHE_OBJECT_EV_RETIRE	5	/* T if netfs requested object retirement */
+#define FSCACHE_OBJECT_EV_WITHDRAW	6	/* T if cache requested object withdrawal */
+
+	unsigned long		flags;
+#define FSCACHE_OBJECT_LOCK		0	/* T if object is busy being processed */
+#define FSCACHE_OBJECT_PENDING_WRITE	1	/* T if object has pending write */
+#define FSCACHE_OBJECT_WAITING		2	/* T if object is waiting on its parent */
+
+	struct list_head	cache_link;	/* link in cache->object_list */
+	struct hlist_node	cookie_link;	/* link in cookie->backing_objects */
+	struct fscache_cache	*cache;		/* cache that supplied this object */
+	struct fscache_cookie	*cookie;	/* netfs's file/index object */
+	struct fscache_object	*parent;	/* parent object */
+	struct slow_work	work;		/* attention scheduling record */
+	struct list_head	dependents;	/* FIFO of dependent objects */
+	struct list_head	dep_link;	/* link in parent's dependents list */
+	struct list_head	pending_ops;	/* unstarted operations on this object */
+	pgoff_t			store_limit;	/* current storage limit */
+};
+
+extern const char *fscache_object_states[];
+
+#define fscache_object_is_active(obj)			      \
+	(!test_bit(FSCACHE_IOERROR, &(obj)->cache->flags) &&  \
+	 (obj)->state >= FSCACHE_OBJECT_AVAILABLE &&	      \
+	 (obj)->state < FSCACHE_OBJECT_DYING)
+
+extern const struct slow_work_ops fscache_object_slow_work_ops;
+
+/**
+ * fscache_object_init - Initialise a cache object description
+ * @object: Object description
+ *
+ * Initialise a cache object description to its basic values.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_object_init(struct fscache_object *object,
+			 struct fscache_cookie *cookie,
+			 struct fscache_cache *cache)
+{
+	atomic_inc(&cache->object_count);
+
+	object->state = FSCACHE_OBJECT_INIT;
+	spin_lock_init(&object->lock);
+	INIT_LIST_HEAD(&object->cache_link);
+	INIT_HLIST_NODE(&object->cookie_link);
+	vslow_work_init(&object->work, &fscache_object_slow_work_ops);
+	INIT_LIST_HEAD(&object->dependents);
+	INIT_LIST_HEAD(&object->dep_link);
+	INIT_LIST_HEAD(&object->pending_ops);
+	object->n_children = 0;
+	object->n_ops = object->n_in_progress = object->n_exclusive = 0;
+	object->events = object->event_mask = 0;
+	object->flags = 0;
+	object->store_limit = 0;
+	object->cache = cache;
+	object->cookie = cookie;
+	object->parent = NULL;
+}
+
+extern void fscache_object_lookup_negative(struct fscache_object *object);
+extern void fscache_obtained_object(struct fscache_object *object);
+
+/**
+ * fscache_object_destroyed - Note destruction of an object in a cache
+ * @cache: The cache from which the object came
+ *
+ * Note the destruction and deallocation of an object record in a cache.
+ */
+static inline void fscache_object_destroyed(struct fscache_cache *cache)
+{
+	if (atomic_dec_and_test(&cache->object_count))
+		wake_up_all(&fscache_cache_cleared_wq);
+}
+
+/**
+ * fscache_object_lookup_error - Note an object encountered an error
+ * @object: The object on which the error was encountered
+ *
+ * Note that an object encountered a fatal error (usually an I/O error) and
+ * that it should be withdrawn as soon as possible.
+ */
+static inline void fscache_object_lookup_error(struct fscache_object *object)
+{
+	set_bit(FSCACHE_OBJECT_EV_ERROR, &object->events);
+}
+
+/**
+ * fscache_set_store_limit - Set the maximum size to be stored in an object
+ * @object: The object to set the maximum on
+ * @i_size: The limit to set in bytes
+ *
+ * Set the maximum size an object is permitted to reach, implying the highest
+ * byte that may be written.  Intended to be called by the attr_changed() op.
+ *
+ * See Documentation/filesystems/caching/backend-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_set_store_limit(struct fscache_object *object, loff_t i_size)
+{
+	object->store_limit = i_size >> PAGE_SHIFT;
+	if (i_size & ~PAGE_MASK)
+		object->store_limit++;
+}
+
+/**
+ * fscache_end_io - End a retrieval operation on a page
+ * @op: The FS-Cache operation covering the retrieval
+ * @page: The page that was to be fetched
+ * @error: The error code (0 if successful)
+ *
+ * Note the end of an operation to retrieve a page, as covered by a particular
+ * operation record.
+ */
+static inline void fscache_end_io(struct fscache_retrieval *op,
+				  struct page *page, int error)
+{
+	op->end_io_func(page, op->context, error);
+}
+
+/*
+ * out-of-line cache backend functions
+ */
+extern void fscache_init_cache(struct fscache_cache *cache,
+			       const struct fscache_cache_ops *ops,
+			       const char *idfmt,
+			       ...) __attribute__ ((format (printf, 3, 4)));
+
+extern int fscache_add_cache(struct fscache_cache *cache,
+			     struct fscache_object *fsdef,
+			     const char *tagname);
+extern void fscache_withdraw_cache(struct fscache_cache *cache);
+
+extern void fscache_io_error(struct fscache_cache *cache);
+
+extern void fscache_mark_pages_cached(struct fscache_retrieval *op,
+				      struct pagevec *pagevec);
+
+extern enum fscache_checkaux fscache_check_aux(struct fscache_object *object,
+					       const void *data,
+					       uint16_t datalen);
+
+#endif /* _LINUX_FSCACHE_CACHE_H */
diff --git a/include/linux/fscache.h b/include/linux/fscache.h
new file mode 100644
index 000000000000..6d8ee466e0a0
--- /dev/null
+++ b/include/linux/fscache.h
@@ -0,0 +1,618 @@
+/* General filesystem caching interface
+ *
+ * Copyright (C) 2004-2007 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ * NOTE!!! See:
+ *
+ *	Documentation/filesystems/caching/netfs-api.txt
+ *
+ * for a description of the network filesystem interface declared here.
+ */
+
+#ifndef _LINUX_FSCACHE_H
+#define _LINUX_FSCACHE_H
+
+#include <linux/fs.h>
+#include <linux/list.h>
+#include <linux/pagemap.h>
+#include <linux/pagevec.h>
+
+#if defined(CONFIG_FSCACHE) || defined(CONFIG_FSCACHE_MODULE)
+#define fscache_available() (1)
+#define fscache_cookie_valid(cookie) (cookie)
+#else
+#define fscache_available() (0)
+#define fscache_cookie_valid(cookie) (0)
+#endif
+
+
+/*
+ * overload PG_private_2 to give us PG_fscache - this is used to indicate that
+ * a page is currently backed by a local disk cache
+ */
+#define PageFsCache(page)		PagePrivate2((page))
+#define SetPageFsCache(page)		SetPagePrivate2((page))
+#define ClearPageFsCache(page)		ClearPagePrivate2((page))
+#define TestSetPageFsCache(page)	TestSetPagePrivate2((page))
+#define TestClearPageFsCache(page)	TestClearPagePrivate2((page))
+
+/* pattern used to fill dead space in an index entry */
+#define FSCACHE_INDEX_DEADFILL_PATTERN 0x79
+
+struct pagevec;
+struct fscache_cache_tag;
+struct fscache_cookie;
+struct fscache_netfs;
+
+typedef void (*fscache_rw_complete_t)(struct page *page,
+				      void *context,
+				      int error);
+
+/* result of index entry consultation */
+enum fscache_checkaux {
+	FSCACHE_CHECKAUX_OKAY,		/* entry okay as is */
+	FSCACHE_CHECKAUX_NEEDS_UPDATE,	/* entry requires update */
+	FSCACHE_CHECKAUX_OBSOLETE,	/* entry requires deletion */
+};
+
+/*
+ * fscache cookie definition
+ */
+struct fscache_cookie_def {
+	/* name of cookie type */
+	char name[16];
+
+	/* cookie type */
+	uint8_t type;
+#define FSCACHE_COOKIE_TYPE_INDEX	0
+#define FSCACHE_COOKIE_TYPE_DATAFILE	1
+
+	/* select the cache into which to insert an entry in this index
+	 * - optional
+	 * - should return a cache identifier or NULL to cause the cache to be
+	 *   inherited from the parent if possible or the first cache picked
+	 *   for a non-index file if not
+	 */
+	struct fscache_cache_tag *(*select_cache)(
+		const void *parent_netfs_data,
+		const void *cookie_netfs_data);
+
+	/* get an index key
+	 * - should store the key data in the buffer
+	 * - should return the amount of amount stored
+	 * - not permitted to return an error
+	 * - the netfs data from the cookie being used as the source is
+	 *   presented
+	 */
+	uint16_t (*get_key)(const void *cookie_netfs_data,
+			    void *buffer,
+			    uint16_t bufmax);
+
+	/* get certain file attributes from the netfs data
+	 * - this function can be absent for an index
+	 * - not permitted to return an error
+	 * - the netfs data from the cookie being used as the source is
+	 *   presented
+	 */
+	void (*get_attr)(const void *cookie_netfs_data, uint64_t *size);
+
+	/* get the auxilliary data from netfs data
+	 * - this function can be absent if the index carries no state data
+	 * - should store the auxilliary data in the buffer
+	 * - should return the amount of amount stored
+	 * - not permitted to return an error
+	 * - the netfs data from the cookie being used as the source is
+	 *   presented
+	 */
+	uint16_t (*get_aux)(const void *cookie_netfs_data,
+			    void *buffer,
+			    uint16_t bufmax);
+
+	/* consult the netfs about the state of an object
+	 * - this function can be absent if the index carries no state data
+	 * - the netfs data from the cookie being used as the target is
+	 *   presented, as is the auxilliary data
+	 */
+	enum fscache_checkaux (*check_aux)(void *cookie_netfs_data,
+					   const void *data,
+					   uint16_t datalen);
+
+	/* get an extra reference on a read context
+	 * - this function can be absent if the completion function doesn't
+	 *   require a context
+	 */
+	void (*get_context)(void *cookie_netfs_data, void *context);
+
+	/* release an extra reference on a read context
+	 * - this function can be absent if the completion function doesn't
+	 *   require a context
+	 */
+	void (*put_context)(void *cookie_netfs_data, void *context);
+
+	/* indicate pages that now have cache metadata retained
+	 * - this function should mark the specified pages as now being cached
+	 * - the pages will have been marked with PG_fscache before this is
+	 *   called, so this is optional
+	 */
+	void (*mark_pages_cached)(void *cookie_netfs_data,
+				  struct address_space *mapping,
+				  struct pagevec *cached_pvec);
+
+	/* indicate the cookie is no longer cached
+	 * - this function is called when the backing store currently caching
+	 *   a cookie is removed
+	 * - the netfs should use this to clean up any markers indicating
+	 *   cached pages
+	 * - this is mandatory for any object that may have data
+	 */
+	void (*now_uncached)(void *cookie_netfs_data);
+};
+
+/*
+ * fscache cached network filesystem type
+ * - name, version and ops must be filled in before registration
+ * - all other fields will be set during registration
+ */
+struct fscache_netfs {
+	uint32_t			version;	/* indexing version */
+	const char			*name;		/* filesystem name */
+	struct fscache_cookie		*primary_index;
+	struct list_head		link;		/* internal link */
+};
+
+/*
+ * slow-path functions for when there is actually caching available, and the
+ * netfs does actually have a valid token
+ * - these are not to be called directly
+ * - these are undefined symbols when FS-Cache is not configured and the
+ *   optimiser takes care of not using them
+ */
+extern int __fscache_register_netfs(struct fscache_netfs *);
+extern void __fscache_unregister_netfs(struct fscache_netfs *);
+extern struct fscache_cache_tag *__fscache_lookup_cache_tag(const char *);
+extern void __fscache_release_cache_tag(struct fscache_cache_tag *);
+
+extern struct fscache_cookie *__fscache_acquire_cookie(
+	struct fscache_cookie *,
+	const struct fscache_cookie_def *,
+	void *);
+extern void __fscache_relinquish_cookie(struct fscache_cookie *, int);
+extern void __fscache_update_cookie(struct fscache_cookie *);
+extern int __fscache_attr_changed(struct fscache_cookie *);
+extern int __fscache_read_or_alloc_page(struct fscache_cookie *,
+					struct page *,
+					fscache_rw_complete_t,
+					void *,
+					gfp_t);
+extern int __fscache_read_or_alloc_pages(struct fscache_cookie *,
+					 struct address_space *,
+					 struct list_head *,
+					 unsigned *,
+					 fscache_rw_complete_t,
+					 void *,
+					 gfp_t);
+extern int __fscache_alloc_page(struct fscache_cookie *, struct page *, gfp_t);
+extern int __fscache_write_page(struct fscache_cookie *, struct page *, gfp_t);
+extern void __fscache_uncache_page(struct fscache_cookie *, struct page *);
+extern bool __fscache_check_page_write(struct fscache_cookie *, struct page *);
+extern void __fscache_wait_on_page_write(struct fscache_cookie *, struct page *);
+
+/**
+ * fscache_register_netfs - Register a filesystem as desiring caching services
+ * @netfs: The description of the filesystem
+ *
+ * Register a filesystem as desiring caching services if they're available.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_register_netfs(struct fscache_netfs *netfs)
+{
+	if (fscache_available())
+		return __fscache_register_netfs(netfs);
+	else
+		return 0;
+}
+
+/**
+ * fscache_unregister_netfs - Indicate that a filesystem no longer desires
+ * caching services
+ * @netfs: The description of the filesystem
+ *
+ * Indicate that a filesystem no longer desires caching services for the
+ * moment.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unregister_netfs(struct fscache_netfs *netfs)
+{
+	if (fscache_available())
+		__fscache_unregister_netfs(netfs);
+}
+
+/**
+ * fscache_lookup_cache_tag - Look up a cache tag
+ * @name: The name of the tag to search for
+ *
+ * Acquire a specific cache referral tag that can be used to select a specific
+ * cache in which to cache an index.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cache_tag *fscache_lookup_cache_tag(const char *name)
+{
+	if (fscache_available())
+		return __fscache_lookup_cache_tag(name);
+	else
+		return NULL;
+}
+
+/**
+ * fscache_release_cache_tag - Release a cache tag
+ * @tag: The tag to release
+ *
+ * Release a reference to a cache referral tag previously looked up.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_release_cache_tag(struct fscache_cache_tag *tag)
+{
+	if (fscache_available())
+		__fscache_release_cache_tag(tag);
+}
+
+/**
+ * fscache_acquire_cookie - Acquire a cookie to represent a cache object
+ * @parent: The cookie that's to be the parent of this one
+ * @def: A description of the cache object, including callback operations
+ * @netfs_data: An arbitrary piece of data to be kept in the cookie to
+ * represent the cache object to the netfs
+ *
+ * This function is used to inform FS-Cache about part of an index hierarchy
+ * that can be used to locate files.  This is done by requesting a cookie for
+ * each index in the path to the file.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+struct fscache_cookie *fscache_acquire_cookie(
+	struct fscache_cookie *parent,
+	const struct fscache_cookie_def *def,
+	void *netfs_data)
+{
+	if (fscache_cookie_valid(parent))
+		return __fscache_acquire_cookie(parent, def, netfs_data);
+	else
+		return NULL;
+}
+
+/**
+ * fscache_relinquish_cookie - Return the cookie to the cache, maybe discarding
+ * it
+ * @cookie: The cookie being returned
+ * @retire: True if the cache object the cookie represents is to be discarded
+ *
+ * This function returns a cookie to the cache, forcibly discarding the
+ * associated cache object if retire is set to true.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_relinquish_cookie(struct fscache_cookie *cookie, int retire)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_relinquish_cookie(cookie, retire);
+}
+
+/**
+ * fscache_update_cookie - Request that a cache object be updated
+ * @cookie: The cookie representing the cache object
+ *
+ * Request an update of the index data for the cache object associated with the
+ * cookie.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_update_cookie(struct fscache_cookie *cookie)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_update_cookie(cookie);
+}
+
+/**
+ * fscache_pin_cookie - Pin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be pinned in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_pin_cookie(struct fscache_cookie *cookie)
+{
+	return -ENOBUFS;
+}
+
+/**
+ * fscache_pin_cookie - Unpin a data-storage cache object in its cache
+ * @cookie: The cookie representing the cache object
+ *
+ * Permit data-storage cache objects to be unpinned from the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_unpin_cookie(struct fscache_cookie *cookie)
+{
+}
+
+/**
+ * fscache_attr_changed - Notify cache that an object's attributes changed
+ * @cookie: The cookie representing the cache object
+ *
+ * Send a notification to the cache indicating that an object's attributes have
+ * changed.  This includes the data size.  These attributes will be obtained
+ * through the get_attr() cookie definition op.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_attr_changed(struct fscache_cookie *cookie)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_attr_changed(cookie);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_reserve_space - Reserve data space for a cached object
+ * @cookie: The cookie representing the cache object
+ * @i_size: The amount of space to be reserved
+ *
+ * Reserve an amount of space in the cache for the cache object attached to a
+ * cookie so that a write to that object within the space can always be
+ * honoured.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_reserve_space(struct fscache_cookie *cookie, loff_t size)
+{
+	return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_page - Read a page from the cache or allocate a block
+ * in which to store it
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to fill if possible
+ * @end_io_func: The callback to invoke when and if the page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a page from the cache, or if that's not possible make a potential
+ * one-block reservation in the cache into which the page may be stored once
+ * fetched from the server.
+ *
+ * If the page is not backed by the cache object, or if it there's some reason
+ * it can't be, -ENOBUFS will be returned and nothing more will be done for
+ * that page.
+ *
+ * Else, if that page is backed by the cache, a read will be initiated directly
+ * to the netfs's page and 0 will be returned by this function.  The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure.  Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if the page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_page(struct fscache_cookie *cookie,
+			       struct page *page,
+			       fscache_rw_complete_t end_io_func,
+			       void *context,
+			       gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_read_or_alloc_page(cookie, page, end_io_func,
+						    context, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_read_or_alloc_pages - Read pages from the cache and/or allocate
+ * blocks in which to store them
+ * @cookie: The cookie representing the cache object
+ * @mapping: The netfs inode mapping to which the pages will be attached
+ * @pages: A list of potential netfs pages to be filled
+ * @end_io_func: The callback to invoke when and if each page is filled
+ * @context: An arbitrary piece of data to pass on to end_io_func()
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Read a set of pages from the cache, or if that's not possible, attempt to
+ * make a potential one-block reservation for each page in the cache into which
+ * that page may be stored once fetched from the server.
+ *
+ * If some pages are not backed by the cache object, or if it there's some
+ * reason they can't be, -ENOBUFS will be returned and nothing more will be
+ * done for that pages.
+ *
+ * Else, if some of the pages are backed by the cache, a read will be initiated
+ * directly to the netfs's page and 0 will be returned by this function.  The
+ * end_io_func() callback will be invoked when the operation terminates on a
+ * completion or failure.  Note that the callback may be invoked before the
+ * return.
+ *
+ * Else, if a page is unbacked, -ENODATA is returned and a block may have
+ * been allocated in the cache.
+ *
+ * Because the function may want to return all of -ENOBUFS, -ENODATA and 0 in
+ * regard to different pages, the return values are prioritised in that order.
+ * Any pages submitted for reading are removed from the pages list.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_read_or_alloc_pages(struct fscache_cookie *cookie,
+				struct address_space *mapping,
+				struct list_head *pages,
+				unsigned *nr_pages,
+				fscache_rw_complete_t end_io_func,
+				void *context,
+				gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_read_or_alloc_pages(cookie, mapping, pages,
+						     nr_pages, end_io_func,
+						     context, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_alloc_page - Allocate a block in which to store a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to allocate a page for
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request Allocation a block in the cache in which to store a netfs page
+ * without retrieving any contents from the cache.
+ *
+ * If the page is not backed by a file then -ENOBUFS will be returned and
+ * nothing more will be done, and no reservation will be made.
+ *
+ * Else, a block will be allocated if one wasn't already, and 0 will be
+ * returned
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_alloc_page(struct fscache_cookie *cookie,
+		       struct page *page,
+		       gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_alloc_page(cookie, page, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_write_page - Request storage of a page in the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page to store
+ * @gfp: The conditions under which memory allocation should be made
+ *
+ * Request the contents of the netfs page be written into the cache.  This
+ * request may be ignored if no cache block is currently allocated, in which
+ * case it will return -ENOBUFS.
+ *
+ * If a cache block was already allocated, a write will be initiated and 0 will
+ * be returned.  The PG_fscache_write page bit is set immediately and will then
+ * be cleared at the completion of the write to indicate the success or failure
+ * of the operation.  Note that the completion may happen before the return.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+int fscache_write_page(struct fscache_cookie *cookie,
+		       struct page *page,
+		       gfp_t gfp)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_write_page(cookie, page, gfp);
+	else
+		return -ENOBUFS;
+}
+
+/**
+ * fscache_uncache_page - Indicate that caching is no longer required on a page
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that was being cached.
+ *
+ * Tell the cache that we no longer want a page to be cached and that it should
+ * remove any knowledge of the netfs page it may have.
+ *
+ * Note that this cannot cancel any outstanding I/O operations between this
+ * page and the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_uncache_page(struct fscache_cookie *cookie,
+			  struct page *page)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_uncache_page(cookie, page);
+}
+
+/**
+ * fscache_check_page_write - Ask if a page is being writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache if a page is being written to the cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+bool fscache_check_page_write(struct fscache_cookie *cookie,
+			      struct page *page)
+{
+	if (fscache_cookie_valid(cookie))
+		return __fscache_check_page_write(cookie, page);
+	return false;
+}
+
+/**
+ * fscache_wait_on_page_write - Wait for a page to complete writing to the cache
+ * @cookie: The cookie representing the cache object
+ * @page: The netfs page that is being cached.
+ *
+ * Ask the cache to wake us up when a page is no longer being written to the
+ * cache.
+ *
+ * See Documentation/filesystems/caching/netfs-api.txt for a complete
+ * description.
+ */
+static inline
+void fscache_wait_on_page_write(struct fscache_cookie *cookie,
+				struct page *page)
+{
+	if (fscache_cookie_valid(cookie))
+		__fscache_wait_on_page_write(cookie, page);
+}
+
+#endif /* _LINUX_FSCACHE_H */
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index dd20cd78faa8..0bbc15f54536 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -4,6 +4,7 @@
 #include <linux/mmzone.h>
 #include <linux/stddef.h>
 #include <linux/linkage.h>
+#include <linux/topology.h>
 
 struct vm_area_struct;
 
diff --git a/include/linux/hdreg.h b/include/linux/hdreg.h
index ed21bd3dbd25..29ee2873f4a8 100644
--- a/include/linux/hdreg.h
+++ b/include/linux/hdreg.h
@@ -1,68 +1,6 @@
 #ifndef _LINUX_HDREG_H
 #define _LINUX_HDREG_H
 
-#ifdef __KERNEL__
-#include <linux/ata.h>
-
-/*
- * This file contains some defines for the AT-hd-controller.
- * Various sources.
- */
-
-/* ide.c has its own port definitions in "ide.h" */
-
-#define HD_IRQ		14
-
-/* Hd controller regs. Ref: IBM AT Bios-listing */
-#define HD_DATA		0x1f0		/* _CTL when writing */
-#define HD_ERROR	0x1f1		/* see err-bits */
-#define HD_NSECTOR	0x1f2		/* nr of sectors to read/write */
-#define HD_SECTOR	0x1f3		/* starting sector */
-#define HD_LCYL		0x1f4		/* starting cylinder */
-#define HD_HCYL		0x1f5		/* high byte of starting cyl */
-#define HD_CURRENT	0x1f6		/* 101dhhhh , d=drive, hhhh=head */
-#define HD_STATUS	0x1f7		/* see status-bits */
-#define HD_FEATURE	HD_ERROR	/* same io address, read=error, write=feature */
-#define HD_PRECOMP	HD_FEATURE	/* obsolete use of this port - predates IDE */
-#define HD_COMMAND	HD_STATUS	/* same io address, read=status, write=cmd */
-
-#define HD_CMD		0x3f6		/* used for resets */
-#define HD_ALTSTATUS	0x3f6		/* same as HD_STATUS but doesn't clear irq */
-
-/* remainder is shared between hd.c, ide.c, ide-cd.c, and the hdparm utility */
-
-/* Bits of HD_STATUS */
-#define ERR_STAT		0x01
-#define INDEX_STAT		0x02
-#define ECC_STAT		0x04	/* Corrected error */
-#define DRQ_STAT		0x08
-#define SEEK_STAT		0x10
-#define SRV_STAT		0x10
-#define WRERR_STAT		0x20
-#define READY_STAT		0x40
-#define BUSY_STAT		0x80
-
-/* Bits for HD_ERROR */
-#define MARK_ERR		0x01	/* Bad address mark */
-#define ILI_ERR			0x01	/* Illegal Length Indication (ATAPI) */
-#define TRK0_ERR		0x02	/* couldn't find track 0 */
-#define EOM_ERR			0x02	/* End Of Media (ATAPI) */
-#define ABRT_ERR		0x04	/* Command aborted */
-#define MCR_ERR			0x08	/* media change request */
-#define ID_ERR			0x10	/* ID field not found */
-#define MC_ERR			0x20	/* media changed */
-#define ECC_ERR			0x40	/* Uncorrectable ECC error */
-#define BBD_ERR			0x80	/* pre-EIDE meaning:  block marked bad */
-#define ICRC_ERR		0x80	/* new meaning:  CRC error during transfer */
-#define LFS_ERR			0xf0	/* Last Failed Sense (ATAPI) */
-
-/* Bits of HD_NSECTOR */
-#define CD			0x01
-#define IO			0x02
-#define REL			0x04
-#define TAG_MASK		0xf8
-#endif /* __KERNEL__ */
-
 #include <linux/types.h>
 
 /*
@@ -191,6 +129,7 @@ typedef struct hd_drive_hob_hdr {
 #define TASKFILE_INVALID		0x7fff
 #endif
 
+#ifndef __KERNEL__
 /* ATA/ATAPI Commands pre T13 Spec */
 #define WIN_NOP				0x00
 /*
@@ -379,6 +318,7 @@ typedef struct hd_drive_hob_hdr {
 #define SECURITY_ERASE_UNIT		0xBD
 #define SECURITY_FREEZE_LOCK		0xBE
 #define SECURITY_DISABLE_PASSWORD	0xBF
+#endif /* __KERNEL__ */
 
 struct hd_geometry {
       unsigned char heads;
@@ -448,6 +388,7 @@ enum {
 
 #define __NEW_HD_DRIVE_ID
 
+#ifndef __KERNEL__
 /*
  * Structure returned by HDIO_GET_IDENTITY, as per ANSI NCITS ATA6 rev.1b spec.
  *
@@ -699,6 +640,7 @@ struct hd_driveid {
 					 *  7:0 Signature
 					 */
 };
+#endif /* __KERNEL__ */
 
 /*
  * IDE "nice" flags. These are used on a per drive basis to determine
diff --git a/include/linux/hid.h b/include/linux/hid.h
index fa8ee9cef7be..a72876e43589 100644
--- a/include/linux/hid.h
+++ b/include/linux/hid.h
@@ -270,6 +270,7 @@ struct hid_item {
 
 #define HID_QUIRK_INVERT			0x00000001
 #define HID_QUIRK_NOTOUCH			0x00000002
+#define HID_QUIRK_IGNORE			0x00000004
 #define HID_QUIRK_NOGET				0x00000008
 #define HID_QUIRK_BADPAD			0x00000020
 #define HID_QUIRK_MULTI_INPUT			0x00000040
@@ -603,12 +604,17 @@ struct hid_ll_driver {
 	int (*open)(struct hid_device *hdev);
 	void (*close)(struct hid_device *hdev);
 
+	int (*power)(struct hid_device *hdev, int level);
+
 	int (*hidinput_input_event) (struct input_dev *idev, unsigned int type,
 			unsigned int code, int value);
 
 	int (*parse)(struct hid_device *hdev);
 };
 
+#define	PM_HINT_FULLON	1<<5
+#define PM_HINT_NORMAL	1<<1
+
 /* Applications from HID Usage Tables 4/8/99 Version 1.1 */
 /* We ignore a few input applications that are not widely used */
 #define IS_INPUT_APPLICATION(a) (((a >= 0x00010000) && (a <= 0x00010008)) || (a == 0x00010080) || (a == 0x000c0001) || (a == 0x000d0002))
@@ -641,6 +647,7 @@ int hidinput_find_field(struct hid_device *hid, unsigned int type, unsigned int
 void hid_output_report(struct hid_report *report, __u8 *data);
 struct hid_device *hid_allocate_device(void);
 int hid_parse_report(struct hid_device *hid, __u8 *start, unsigned size);
+int hid_check_keys_pressed(struct hid_device *hid);
 int hid_connect(struct hid_device *hid, unsigned int connect_mask);
 
 /**
@@ -791,21 +798,5 @@ dbg_hid(const char *fmt, ...)
 		__FILE__ , ## arg)
 #endif /* HID_FF */
 
-#ifdef __KERNEL__
-#ifdef CONFIG_HID_COMPAT
-#define HID_COMPAT_LOAD_DRIVER(name)	\
-/* prototype to avoid sparse warning */	\
-extern void hid_compat_##name(void);	\
-void hid_compat_##name(void) { }	\
-EXPORT_SYMBOL(hid_compat_##name)
-#else
-#define HID_COMPAT_LOAD_DRIVER(name)
-#endif /* HID_COMPAT */
-#define HID_COMPAT_CALL_DRIVER(name)	do {	\
-	extern void hid_compat_##name(void);	\
-	hid_compat_##name();			\
-} while (0)
-#endif /* __KERNEL__ */
-
 #endif
 
diff --git a/include/linux/highmem.h b/include/linux/highmem.h
index 7ff5c55f9b55..1fcb7126a01f 100644
--- a/include/linux/highmem.h
+++ b/include/linux/highmem.h
@@ -19,8 +19,21 @@ static inline void flush_kernel_dcache_page(struct page *page)
 }
 #endif
 
-#ifdef CONFIG_HIGHMEM
+#include <asm/kmap_types.h>
+
+#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
+
+void debug_kmap_atomic(enum km_type type);
+
+#else
 
+static inline void debug_kmap_atomic(enum km_type type)
+{
+}
+
+#endif
+
+#ifdef CONFIG_HIGHMEM
 #include <asm/highmem.h>
 
 /* declarations for linux/mm/highmem.c */
@@ -44,8 +57,6 @@ static inline void *kmap(struct page *page)
 
 #define kunmap(page) do { (void) (page); } while (0)
 
-#include <asm/kmap_types.h>
-
 static inline void *kmap_atomic(struct page *page, enum km_type idx)
 {
 	pagefault_disable();
@@ -187,16 +198,4 @@ static inline void copy_highpage(struct page *to, struct page *from)
 	kunmap_atomic(vto, KM_USER1);
 }
 
-#if defined(CONFIG_DEBUG_HIGHMEM) && defined(CONFIG_TRACE_IRQFLAGS_SUPPORT)
-
-void debug_kmap_atomic(enum km_type type);
-
-#else
-
-static inline void debug_kmap_atomic(enum km_type type)
-{
-}
-
-#endif
-
 #endif /* _LINUX_HIGHMEM_H */
diff --git a/include/linux/i2c/at24.h b/include/linux/i2c/at24.h
index f6edd522a929..8ace93024d60 100644
--- a/include/linux/i2c/at24.h
+++ b/include/linux/i2c/at24.h
@@ -2,6 +2,7 @@
 #define _LINUX_AT24_H
 
 #include <linux/types.h>
+#include <linux/memory.h>
 
 /*
  * As seen through Linux I2C, differences between the most common types of I2C
@@ -23,6 +24,9 @@ struct at24_platform_data {
 #define AT24_FLAG_READONLY	0x40	/* sysfs-entry will be read-only */
 #define AT24_FLAG_IRUGO		0x20	/* sysfs-entry will be world-readable */
 #define AT24_FLAG_TAKE8ADDR	0x10	/* take always 8 addresses (24c00) */
+
+	void		(*setup)(struct memory_accessor *, void *context);
+	void		*context;
 };
 
 #endif /* _LINUX_AT24_H */
diff --git a/include/linux/i2c/twl4030.h b/include/linux/i2c/twl4030.h
index 8137f660a5cc..0dc80ef24975 100644
--- a/include/linux/i2c/twl4030.h
+++ b/include/linux/i2c/twl4030.h
@@ -218,6 +218,53 @@ int twl4030_i2c_read(u8 mod_no, u8 *value, u8 reg, unsigned num_bytes);
 
 /*----------------------------------------------------------------------*/
 
+/* Power bus message definitions */
+
+#define DEV_GRP_NULL		0x0
+#define DEV_GRP_P1		0x1
+#define DEV_GRP_P2		0x2
+#define DEV_GRP_P3		0x4
+
+#define RES_GRP_RES		0x0
+#define RES_GRP_PP		0x1
+#define RES_GRP_RC		0x2
+#define RES_GRP_PP_RC		0x3
+#define RES_GRP_PR		0x4
+#define RES_GRP_PP_PR		0x5
+#define RES_GRP_RC_PR		0x6
+#define RES_GRP_ALL		0x7
+
+#define RES_TYPE2_R0		0x0
+
+#define RES_TYPE_ALL		0x7
+
+#define RES_STATE_WRST		0xF
+#define RES_STATE_ACTIVE	0xE
+#define RES_STATE_SLEEP		0x8
+#define RES_STATE_OFF		0x0
+
+/*
+ * Power Bus Message Format ... these can be sent individually by Linux,
+ * but are usually part of downloaded scripts that are run when various
+ * power events are triggered.
+ *
+ *  Broadcast Message (16 Bits):
+ *    DEV_GRP[15:13] MT[12]  RES_GRP[11:9]  RES_TYPE2[8:7] RES_TYPE[6:4]
+ *    RES_STATE[3:0]
+ *
+ *  Singular Message (16 Bits):
+ *    DEV_GRP[15:13] MT[12]  RES_ID[11:4]  RES_STATE[3:0]
+ */
+
+#define MSG_BROADCAST(devgrp, grp, type, type2, state) \
+	( (devgrp) << 13 | 1 << 12 | (grp) << 9 | (type2) << 7 \
+	| (type) << 4 | (state))
+
+#define MSG_SINGULAR(devgrp, id, state) \
+	((devgrp) << 13 | 0 << 12 | (id) << 4 | (state))
+
+/*----------------------------------------------------------------------*/
+
 struct twl4030_bci_platform_data {
 	int *battery_tmp_tbl;
 	unsigned int tblsize;
diff --git a/include/linux/idr.h b/include/linux/idr.h
index dd846df8cd32..e968db71e33a 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -106,6 +106,7 @@ int idr_get_new(struct idr *idp, void *ptr, int *id);
 int idr_get_new_above(struct idr *idp, void *ptr, int starting_id, int *id);
 int idr_for_each(struct idr *idp,
 		 int (*fn)(int id, void *p, void *data), void *data);
+void *idr_get_next(struct idr *idp, int *nextid);
 void *idr_replace(struct idr *idp, void *ptr, int id);
 void idr_remove(struct idr *idp, int id);
 void idr_remove_all(struct idr *idp);
diff --git a/include/linux/intel-iommu.h b/include/linux/intel-iommu.h
index 1d6c71d96ede..77214ead1a36 100644
--- a/include/linux/intel-iommu.h
+++ b/include/linux/intel-iommu.h
@@ -123,7 +123,7 @@ static inline void dmar_writeq(void __iomem *addr, u64 val)
 #define ecap_eim_support(e)	((e >> 4) & 0x1)
 #define ecap_ir_support(e)	((e >> 3) & 0x1)
 #define ecap_max_handle_mask(e) ((e >> 20) & 0xf)
-
+#define ecap_sc_support(e)	((e >> 7) & 0x1) /* Snooping Control */
 
 /* IOTLB_REG */
 #define DMA_TLB_FLUSH_GRANU_OFFSET  60
diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index 8a7bfb1b6ca0..3af4ffd591b9 100644
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -21,6 +21,7 @@
 
 #define IOMMU_READ	(1)
 #define IOMMU_WRITE	(2)
+#define IOMMU_CACHE	(4) /* DMA cache coherency */
 
 struct device;
 
@@ -28,6 +29,8 @@ struct iommu_domain {
 	void *priv;
 };
 
+#define IOMMU_CAP_CACHE_COHERENCY	0x1
+
 struct iommu_ops {
 	int (*domain_init)(struct iommu_domain *domain);
 	void (*domain_destroy)(struct iommu_domain *domain);
@@ -39,6 +42,8 @@ struct iommu_ops {
 		      size_t size);
 	phys_addr_t (*iova_to_phys)(struct iommu_domain *domain,
 				    unsigned long iova);
+	int (*domain_has_cap)(struct iommu_domain *domain,
+			      unsigned long cap);
 };
 
 #ifdef CONFIG_IOMMU_API
@@ -57,6 +62,8 @@ extern void iommu_unmap_range(struct iommu_domain *domain, unsigned long iova,
 			      size_t size);
 extern phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
 				      unsigned long iova);
+extern int iommu_domain_has_cap(struct iommu_domain *domain,
+				unsigned long cap);
 
 #else /* CONFIG_IOMMU_API */
 
@@ -107,6 +114,12 @@ static inline phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain,
 	return 0;
 }
 
+static inline int domain_has_cap(struct iommu_domain *domain,
+				 unsigned long cap)
+{
+	return 0;
+}
+
 #endif /* CONFIG_IOMMU_API */
 
 #endif /* __LINUX_IOMMU_H */
diff --git a/include/linux/jbd.h b/include/linux/jbd.h
index 64246dce5663..53ae4399da2d 100644
--- a/include/linux/jbd.h
+++ b/include/linux/jbd.h
@@ -35,7 +35,7 @@
 #define journal_oom_retry 1
 
 /*
- * Define JBD_PARANIOD_IOFAIL to cause a kernel BUG() if ext3 finds
+ * Define JBD_PARANOID_IOFAIL to cause a kernel BUG() if ext3 finds
  * certain classes of error which can occur due to failed IOs.  Under
  * normal use we want ext3 to continue after such errors, because
  * hardware _can_ fail, but for debugging purposes when running tests on
@@ -552,6 +552,11 @@ struct transaction_s
 	 */
 	int t_handle_count;
 
+	/*
+	 * This transaction is being forced and some process is
+	 * waiting for it to finish.
+	 */
+	int t_synchronous_commit:1;
 };
 
 /**
diff --git a/include/linux/kallsyms.h b/include/linux/kallsyms.h
index f3fe34391d8e..792274269f2b 100644
--- a/include/linux/kallsyms.h
+++ b/include/linux/kallsyms.h
@@ -13,10 +13,17 @@
 #define KSYM_SYMBOL_LEN (sizeof("%s+%#lx/%#lx [%s]") + (KSYM_NAME_LEN - 1) + \
 			 2*(BITS_PER_LONG*3/10) + (MODULE_NAME_LEN - 1) + 1)
 
+struct module;
+
 #ifdef CONFIG_KALLSYMS
 /* Lookup the address for a symbol. Returns 0 if not found. */
 unsigned long kallsyms_lookup_name(const char *name);
 
+/* Call a function on each kallsyms symbol in the core kernel */
+int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
+				      unsigned long),
+			    void *data);
+
 extern int kallsyms_lookup_size_offset(unsigned long addr,
 				  unsigned long *symbolsize,
 				  unsigned long *offset);
@@ -43,6 +50,14 @@ static inline unsigned long kallsyms_lookup_name(const char *name)
 	return 0;
 }
 
+static inline int kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+						    struct module *,
+						    unsigned long),
+					  void *data)
+{
+	return 0;
+}
+
 static inline int kallsyms_lookup_size_offset(unsigned long addr,
 					      unsigned long *symbolsize,
 					      unsigned long *offset)
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index e81f2637fdef..d9e75ec7def5 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -255,6 +255,7 @@ extern bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 	}					\
 })
 
+void log_buf_kexec_setup(void);
 #else
 static inline int vprintk(const char *s, va_list args)
 	__attribute__ ((format (printf, 1, 0)));
@@ -270,6 +271,9 @@ static inline bool printk_timed_ratelimit(unsigned long *caller_jiffies, \
 /* No effect, but we still get type checking even in the !PRINTK case: */
 #define printk_once(x...) printk(x)
 
+static inline void log_buf_kexec_setup(void)
+{
+}
 #endif
 
 extern int printk_needs_cpu(int cpu);
diff --git a/include/linux/kmod.h b/include/linux/kmod.h
index 92213a9194e1..d5fa565086d1 100644
--- a/include/linux/kmod.h
+++ b/include/linux/kmod.h
@@ -29,10 +29,15 @@
 #ifdef CONFIG_MODULES
 /* modprobe exit status on success, -ve on error.  Return value
  * usually useless though. */
-extern int request_module(const char * name, ...) __attribute__ ((format (printf, 1, 2)));
-#define try_then_request_module(x, mod...) ((x) ?: (request_module(mod), (x)))
+extern int __request_module(bool wait, const char *name, ...) \
+	__attribute__((format(printf, 2, 3)));
+#define request_module(mod...) __request_module(true, mod)
+#define request_module_nowait(mod...) __request_module(false, mod)
+#define try_then_request_module(x, mod...) \
+	((x) ?: (__request_module(false, mod), (x)))
 #else
-static inline int request_module(const char * name, ...) { return -ENOSYS; }
+static inline int request_module(const char *name, ...) { return -ENOSYS; }
+static inline int request_module_nowait(const char *name, ...) { return -ENOSYS; }
 #define try_then_request_module(x, mod...) (x)
 #endif
 
diff --git a/include/linux/libata.h b/include/linux/libata.h
index 76262d83656b..b450a2628855 100644
--- a/include/linux/libata.h
+++ b/include/linux/libata.h
@@ -379,7 +379,7 @@ enum {
 	ATA_HORKAGE_BRIDGE_OK	= (1 << 10),	/* no bridge limits */
 	ATA_HORKAGE_ATAPI_MOD16_DMA = (1 << 11), /* use ATAPI DMA for commands
 						    not multiple of 16 bytes */
-	ATA_HORKAGE_FIRMWARE_WARN = (1 << 12),	/* firwmare update warning */
+	ATA_HORKAGE_FIRMWARE_WARN = (1 << 12),	/* firmware update warning */
 	ATA_HORKAGE_1_5_GBPS	= (1 << 13),	/* force 1.5 Gbps */
 
 	 /* DMA mask for user DMA control: User visible values; DO NOT
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index 5a58ea3e91e9..da5a5a1f4cd2 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -364,6 +364,23 @@ do {								\
 
 #endif /* CONFIG_LOCK_STAT */
 
+#ifdef CONFIG_LOCKDEP
+
+/*
+ * On lockdep we dont want the hand-coded irq-enable of
+ * _raw_*_lock_flags() code, because lockdep assumes
+ * that interrupts are not re-enabled during lock-acquire:
+ */
+#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \
+	LOCK_CONTENDED((_lock), (try), (lock))
+
+#else /* CONFIG_LOCKDEP */
+
+#define LOCK_CONTENDED_FLAGS(_lock, try, lock, lockfl, flags) \
+	lockfl((_lock), (flags))
+
+#endif /* CONFIG_LOCKDEP */
+
 #ifdef CONFIG_GENERIC_HARDIRQS
 extern void early_init_irq_lock_class(void);
 #else
diff --git a/include/linux/memcontrol.h b/include/linux/memcontrol.h
index 326f45c86530..18146c980b68 100644
--- a/include/linux/memcontrol.h
+++ b/include/linux/memcontrol.h
@@ -88,9 +88,6 @@ extern void mem_cgroup_end_migration(struct mem_cgroup *mem,
 /*
  * For memory reclaim.
  */
-extern int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem);
-extern long mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem);
-
 extern int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem);
 extern void mem_cgroup_note_reclaim_priority(struct mem_cgroup *mem,
 							int priority);
@@ -104,6 +101,8 @@ struct zone_reclaim_stat *mem_cgroup_get_reclaim_stat(struct mem_cgroup *memcg,
 						      struct zone *zone);
 struct zone_reclaim_stat*
 mem_cgroup_get_reclaim_stat_from_page(struct page *page);
+extern void mem_cgroup_print_oom_info(struct mem_cgroup *memcg,
+					struct task_struct *p);
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 extern int do_swap_account;
@@ -209,16 +208,6 @@ static inline void mem_cgroup_end_migration(struct mem_cgroup *mem,
 {
 }
 
-static inline int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
-{
-	return 0;
-}
-
-static inline int mem_cgroup_reclaim_imbalance(struct mem_cgroup *mem)
-{
-	return 0;
-}
-
 static inline int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
 {
 	return 0;
@@ -270,6 +259,11 @@ mem_cgroup_get_reclaim_stat_from_page(struct page *page)
 	return NULL;
 }
 
+static inline void
+mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
+{
+}
+
 #endif /* CONFIG_CGROUP_MEM_CONT */
 
 #endif /* _LINUX_MEMCONTROL_H */
diff --git a/include/linux/memory.h b/include/linux/memory.h
index 86a6c0f0518d..37fa19b34ef5 100644
--- a/include/linux/memory.h
+++ b/include/linux/memory.h
@@ -100,6 +100,17 @@ enum mem_add_context { BOOT, HOTPLUG };
 #endif
 
 /*
+ * 'struct memory_accessor' is a generic interface to provide
+ * in-kernel access to persistent memory such as i2c or SPI EEPROMs
+ */
+struct memory_accessor {
+	ssize_t (*read)(struct memory_accessor *, char *buf, off_t offset,
+			size_t count);
+	ssize_t (*write)(struct memory_accessor *, const char *buf,
+			 off_t offset, size_t count);
+};
+
+/*
  * Kernel text modification mutex, used for code patching. Users of this lock
  * can sleep.
  */
diff --git a/include/linux/mm.h b/include/linux/mm.h
index aeabe953ba4f..bff1f0d475c7 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -1079,7 +1079,7 @@ static inline void setup_per_cpu_pageset(void) {}
 #endif
 
 /* nommu.c */
-extern atomic_t mmap_pages_allocated;
+extern atomic_long_t mmap_pages_allocated;
 
 /* prio_tree.c */
 void vma_prio_tree_add(struct vm_area_struct *, struct vm_area_struct *old);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index ddadb4defe00..0e80e26ecf21 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -95,6 +95,9 @@ struct page {
 	void *virtual;			/* Kernel virtual address (NULL if
 					   not kmapped, ie. highmem) */
 #endif /* WANT_PAGE_VIRTUAL */
+#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
+	unsigned long debug_flags;	/* Use atomic bitops on this */
+#endif
 };
 
 /*
@@ -175,9 +178,6 @@ struct vm_area_struct {
 #ifdef CONFIG_NUMA
 	struct mempolicy *vm_policy;	/* NUMA policy for the VMA */
 #endif
-#ifdef CONFIG_WANT_PAGE_DEBUG_FLAGS
-	unsigned long debug_flags;	/* Use atomic bitops on this */
-#endif
 };
 
 struct core_thread {
diff --git a/include/linux/mmc/host.h b/include/linux/mmc/host.h
index 4e457256bd33..3e7615e9087e 100644
--- a/include/linux/mmc/host.h
+++ b/include/linux/mmc/host.h
@@ -192,5 +192,10 @@ static inline void mmc_signal_sdio_irq(struct mmc_host *host)
 	wake_up_process(host->sdio_irq_thread);
 }
 
+struct regulator;
+
+int mmc_regulator_get_ocrmask(struct regulator *supply);
+int mmc_regulator_set_ocr(struct regulator *supply, unsigned short vdd_bit);
+
 #endif
 
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 26ef24076b76..186ec6ab334d 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -764,12 +764,6 @@ extern int numa_zonelist_order_handler(struct ctl_table *, int,
 extern char numa_zonelist_order[];
 #define NUMA_ZONELIST_ORDER_LEN 16	/* string buffer size */
 
-#include <linux/topology.h>
-/* Returns the number of the current Node. */
-#ifndef numa_node_id
-#define numa_node_id()		(cpu_to_node(raw_smp_processor_id()))
-#endif
-
 #ifndef CONFIG_NEED_MULTIPLE_NODES
 
 extern struct pglist_data contig_page_data;
diff --git a/include/linux/mnt_namespace.h b/include/linux/mnt_namespace.h
index 830bbcd449d6..3a059298cc19 100644
--- a/include/linux/mnt_namespace.h
+++ b/include/linux/mnt_namespace.h
@@ -22,6 +22,8 @@ struct proc_mounts {
 	int event;
 };
 
+struct fs_struct;
+
 extern struct mnt_namespace *copy_mnt_ns(unsigned long, struct mnt_namespace *,
 		struct fs_struct *);
 extern void __put_mnt_ns(struct mnt_namespace *ns);
diff --git a/include/linux/module.h b/include/linux/module.h
index 22d9878e868c..627ac082e2a6 100644
--- a/include/linux/module.h
+++ b/include/linux/module.h
@@ -248,6 +248,10 @@ struct module
 	const unsigned long *crcs;
 	unsigned int num_syms;
 
+	/* Kernel parameters. */
+	struct kernel_param *kp;
+	unsigned int num_kp;
+
 	/* GPL-only exported symbols. */
 	unsigned int num_gpl_syms;
 	const struct kernel_symbol *gpl_syms;
@@ -355,6 +359,8 @@ struct module
 #define MODULE_ARCH_INIT {}
 #endif
 
+extern struct mutex module_mutex;
+
 /* FIXME: It'd be nice to isolate modules during init, too, so they
    aren't used before they (may) fail.  But presently too much code
    (IDE & SCSI) require entry into the module during init.*/
@@ -363,10 +369,10 @@ static inline int module_is_live(struct module *mod)
 	return mod->state != MODULE_STATE_GOING;
 }
 
-/* Is this address in a module? (second is with no locks, for oops) */
-struct module *module_text_address(unsigned long addr);
 struct module *__module_text_address(unsigned long addr);
-int is_module_address(unsigned long addr);
+struct module *__module_address(unsigned long addr);
+bool is_module_address(unsigned long addr);
+bool is_module_text_address(unsigned long addr);
 
 static inline int within_module_core(unsigned long addr, struct module *mod)
 {
@@ -380,6 +386,31 @@ static inline int within_module_init(unsigned long addr, struct module *mod)
 	       addr < (unsigned long)mod->module_init + mod->init_size;
 }
 
+/* Search for module by name: must hold module_mutex. */
+struct module *find_module(const char *name);
+
+struct symsearch {
+	const struct kernel_symbol *start, *stop;
+	const unsigned long *crcs;
+	enum {
+		NOT_GPL_ONLY,
+		GPL_ONLY,
+		WILL_BE_GPL_ONLY,
+	} licence;
+	bool unused;
+};
+
+/* Search for an exported symbol by name. */
+const struct kernel_symbol *find_symbol(const char *name,
+					struct module **owner,
+					const unsigned long **crc,
+					bool gplok,
+					bool warn);
+
+/* Walk the exported symbol table */
+bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
+			    unsigned int symnum, void *data), void *data);
+
 /* Returns 0 and fills in value, defined and namebuf, or -ERANGE if
    symnum out of range. */
 int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
@@ -388,6 +419,10 @@ int module_get_kallsym(unsigned int symnum, unsigned long *value, char *type,
 /* Look for this name: can be of form module:name. */
 unsigned long module_kallsyms_lookup_name(const char *name);
 
+int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+					     struct module *, unsigned long),
+				   void *data);
+
 extern void __module_put_and_exit(struct module *mod, long code)
 	__attribute__((noreturn));
 #define module_put_and_exit(code) __module_put_and_exit(THIS_MODULE, code);
@@ -449,6 +484,7 @@ static inline void __module_get(struct module *module)
 #define symbol_put_addr(p) do { } while(0)
 
 #endif /* CONFIG_MODULE_UNLOAD */
+int use_module(struct module *a, struct module *b);
 
 /* This is a #define so the string doesn't get put in every .o file */
 #define module_name(mod)			\
@@ -495,21 +531,24 @@ search_module_extables(unsigned long addr)
 	return NULL;
 }
 
-/* Is this address in a module? */
-static inline struct module *module_text_address(unsigned long addr)
+static inline struct module *__module_address(unsigned long addr)
 {
 	return NULL;
 }
 
-/* Is this address in a module? (don't take a lock, we're oopsing) */
 static inline struct module *__module_text_address(unsigned long addr)
 {
 	return NULL;
 }
 
-static inline int is_module_address(unsigned long addr)
+static inline bool is_module_address(unsigned long addr)
 {
-	return 0;
+	return false;
+}
+
+static inline bool is_module_text_address(unsigned long addr)
+{
+	return false;
 }
 
 /* Get/put a kernel symbol (calls should be symmetric) */
@@ -564,6 +603,14 @@ static inline unsigned long module_kallsyms_lookup_name(const char *name)
 	return 0;
 }
 
+static inline int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+							   struct module *,
+							   unsigned long),
+						 void *data)
+{
+	return 0;
+}
+
 static inline int register_module_notifier(struct notifier_block * nb)
 {
 	/* no events will happen anyway, so this can always succeed */
diff --git a/include/linux/moduleparam.h b/include/linux/moduleparam.h
index e4af3399ef48..a4f0b931846c 100644
--- a/include/linux/moduleparam.h
+++ b/include/linux/moduleparam.h
@@ -138,6 +138,16 @@ extern int parse_args(const char *name,
 		      unsigned num,
 		      int (*unknown)(char *param, char *val));
 
+/* Called by module remove. */
+#ifdef CONFIG_SYSFS
+extern void destroy_params(const struct kernel_param *params, unsigned num);
+#else
+static inline void destroy_params(const struct kernel_param *params,
+				  unsigned num)
+{
+}
+#endif /* !CONFIG_SYSFS */
+
 /* All the helper functions */
 /* The macros to do compile-time type checking stolen from Jakub
    Jelinek, who IIRC came up with this idea for the 2.4 module init code. */
diff --git a/include/linux/mpage.h b/include/linux/mpage.h
index 5c42821da2d1..068a0c9946af 100644
--- a/include/linux/mpage.h
+++ b/include/linux/mpage.h
@@ -11,21 +11,11 @@
  */
 #ifdef CONFIG_BLOCK
 
-struct mpage_data {
-	struct bio *bio;
-	sector_t last_block_in_bio;
-	get_block_t *get_block;
-	unsigned use_writepage;
-};
-
 struct writeback_control;
 
-struct bio *mpage_bio_submit(int rw, struct bio *bio);
 int mpage_readpages(struct address_space *mapping, struct list_head *pages,
 				unsigned nr_pages, get_block_t get_block);
 int mpage_readpage(struct page *page, get_block_t get_block);
-int __mpage_writepage(struct page *page, struct writeback_control *wbc,
-		      void *data);
 int mpage_writepages(struct address_space *mapping,
 		struct writeback_control *wbc, get_block_t get_block);
 int mpage_writepage(struct page *page, get_block_t *get_block,
diff --git a/include/linux/nfs_fs.h b/include/linux/nfs_fs.h
index bde2557c2a9c..fdffb413b192 100644
--- a/include/linux/nfs_fs.h
+++ b/include/linux/nfs_fs.h
@@ -185,6 +185,9 @@ struct nfs_inode {
 	fmode_t			 delegation_state;
 	struct rw_semaphore	rwsem;
 #endif /* CONFIG_NFS_V4*/
+#ifdef CONFIG_NFS_FSCACHE
+	struct fscache_cookie	*fscache;
+#endif
 	struct inode		vfs_inode;
 };
 
@@ -207,6 +210,8 @@ struct nfs_inode {
 #define NFS_INO_ACL_LRU_SET	(2)		/* Inode is on the LRU list */
 #define NFS_INO_MOUNTPOINT	(3)		/* inode is remote mountpoint */
 #define NFS_INO_FLUSHING	(4)		/* inode is flushing out data */
+#define NFS_INO_FSCACHE		(5)		/* inode can be cached by FS-Cache */
+#define NFS_INO_FSCACHE_LOCK	(6)		/* FS-Cache cookie management lock */
 
 static inline struct nfs_inode *NFS_I(const struct inode *inode)
 {
@@ -260,6 +265,11 @@ static inline int NFS_STALE(const struct inode *inode)
 	return test_bit(NFS_INO_STALE, &NFS_I(inode)->flags);
 }
 
+static inline int NFS_FSCACHE(const struct inode *inode)
+{
+	return test_bit(NFS_INO_FSCACHE, &NFS_I(inode)->flags);
+}
+
 static inline __u64 NFS_FILEID(const struct inode *inode)
 {
 	return NFS_I(inode)->fileid;
@@ -506,6 +516,8 @@ extern int  nfs_readpages(struct file *, struct address_space *,
 		struct list_head *, unsigned);
 extern int  nfs_readpage_result(struct rpc_task *, struct nfs_read_data *);
 extern void nfs_readdata_release(void *data);
+extern int  nfs_readpage_async(struct nfs_open_context *, struct inode *,
+			       struct page *);
 
 /*
  * Allocate nfs_read_data structures
@@ -583,6 +595,7 @@ extern void * nfs_root_data(void);
 #define NFSDBG_CALLBACK		0x0100
 #define NFSDBG_CLIENT		0x0200
 #define NFSDBG_MOUNT		0x0400
+#define NFSDBG_FSCACHE		0x0800
 #define NFSDBG_ALL		0xFFFF
 
 #ifdef __KERNEL__
diff --git a/include/linux/nfs_fs_sb.h b/include/linux/nfs_fs_sb.h
index 29b1e40dce99..6ad75948cbf7 100644
--- a/include/linux/nfs_fs_sb.h
+++ b/include/linux/nfs_fs_sb.h
@@ -64,6 +64,10 @@ struct nfs_client {
 	char			cl_ipaddr[48];
 	unsigned char		cl_id_uniquifier;
 #endif
+
+#ifdef CONFIG_NFS_FSCACHE
+	struct fscache_cookie	*fscache;	/* client index cache cookie */
+#endif
 };
 
 /*
@@ -96,12 +100,19 @@ struct nfs_server {
 	unsigned int		acdirmin;
 	unsigned int		acdirmax;
 	unsigned int		namelen;
+	unsigned int		options;	/* extra options enabled by mount */
+#define NFS_OPTION_FSCACHE	0x00000001	/* - local caching enabled */
 
 	struct nfs_fsid		fsid;
 	__u64			maxfilesize;	/* maximum file size */
 	unsigned long		mount_time;	/* when this fs was mounted */
 	dev_t			s_dev;		/* superblock dev numbers */
 
+#ifdef CONFIG_NFS_FSCACHE
+	struct nfs_fscache_key	*fscache_key;	/* unique key for superblock */
+	struct fscache_cookie	*fscache;	/* superblock cookie */
+#endif
+
 #ifdef CONFIG_NFS_V4
 	u32			attr_bitmask[2];/* V4 bitmask representing the set
 						   of attributes supported on this
diff --git a/include/linux/nfs_iostat.h b/include/linux/nfs_iostat.h
index 1cb9a3fed2b3..68b10f5f8907 100644
--- a/include/linux/nfs_iostat.h
+++ b/include/linux/nfs_iostat.h
@@ -116,4 +116,16 @@ enum nfs_stat_eventcounters {
 	__NFSIOS_COUNTSMAX,
 };
 
+/*
+ * NFS local caching servicing counters
+ */
+enum nfs_stat_fscachecounters {
+	NFSIOS_FSCACHE_PAGES_READ_OK,
+	NFSIOS_FSCACHE_PAGES_READ_FAIL,
+	NFSIOS_FSCACHE_PAGES_WRITTEN_OK,
+	NFSIOS_FSCACHE_PAGES_WRITTEN_FAIL,
+	NFSIOS_FSCACHE_PAGES_UNCACHED,
+	__NFSIOS_FSCACHEMAX,
+};
+
 #endif	/* _LINUX_NFS_IOSTAT */
diff --git a/include/linux/nsproxy.h b/include/linux/nsproxy.h
index afad7dec1b36..7b370c7cfeff 100644
--- a/include/linux/nsproxy.h
+++ b/include/linux/nsproxy.h
@@ -8,6 +8,7 @@ struct mnt_namespace;
 struct uts_namespace;
 struct ipc_namespace;
 struct pid_namespace;
+struct fs_struct;
 
 /*
  * A structure to contain pointers to all per-process
diff --git a/include/linux/page-flags.h b/include/linux/page-flags.h
index 61df1779b2a5..62214c7d2d93 100644
--- a/include/linux/page-flags.h
+++ b/include/linux/page-flags.h
@@ -82,6 +82,7 @@ enum pageflags {
 	PG_arch_1,
 	PG_reserved,
 	PG_private,		/* If pagecache, has fs-private data */
+	PG_private_2,		/* If pagecache, has fs aux data */
 	PG_writeback,		/* Page is under writeback */
 #ifdef CONFIG_PAGEFLAGS_EXTENDED
 	PG_head,		/* A head page */
@@ -108,6 +109,12 @@ enum pageflags {
 	/* Filesystems */
 	PG_checked = PG_owner_priv_1,
 
+	/* Two page bits are conscripted by FS-Cache to maintain local caching
+	 * state.  These bits are set on pages belonging to the netfs's inodes
+	 * when those inodes are being locally cached.
+	 */
+	PG_fscache = PG_private_2,	/* page backed by cache */
+
 	/* XEN */
 	PG_pinned = PG_owner_priv_1,
 	PG_savepinned = PG_dirty,
@@ -182,7 +189,7 @@ static inline int TestClearPage##uname(struct page *page) { return 0; }
 
 struct page;	/* forward declaration */
 
-TESTPAGEFLAG(Locked, locked)
+TESTPAGEFLAG(Locked, locked) TESTSETFLAG(Locked, locked)
 PAGEFLAG(Error, error)
 PAGEFLAG(Referenced, referenced) TESTCLEARFLAG(Referenced, referenced)
 PAGEFLAG(Dirty, dirty) TESTSCFLAG(Dirty, dirty) __CLEARPAGEFLAG(Dirty, dirty)
@@ -194,8 +201,6 @@ PAGEFLAG(Checked, checked)		/* Used by some filesystems */
 PAGEFLAG(Pinned, pinned) TESTSCFLAG(Pinned, pinned)	/* Xen */
 PAGEFLAG(SavePinned, savepinned);			/* Xen */
 PAGEFLAG(Reserved, reserved) __CLEARPAGEFLAG(Reserved, reserved)
-PAGEFLAG(Private, private) __CLEARPAGEFLAG(Private, private)
-	__SETPAGEFLAG(Private, private)
 PAGEFLAG(SwapBacked, swapbacked) __CLEARPAGEFLAG(SwapBacked, swapbacked)
 
 __PAGEFLAG(SlobPage, slob_page)
@@ -205,6 +210,16 @@ __PAGEFLAG(SlubFrozen, slub_frozen)
 __PAGEFLAG(SlubDebug, slub_debug)
 
 /*
+ * Private page markings that may be used by the filesystem that owns the page
+ * for its own purposes.
+ * - PG_private and PG_private_2 cause releasepage() and co to be invoked
+ */
+PAGEFLAG(Private, private) __SETPAGEFLAG(Private, private)
+	__CLEARPAGEFLAG(Private, private)
+PAGEFLAG(Private2, private_2) TESTSCFLAG(Private2, private_2)
+PAGEFLAG(OwnerPriv1, owner_priv_1) TESTCLEARFLAG(OwnerPriv1, owner_priv_1)
+
+/*
  * Only test-and-set exist for PG_writeback.  The unconditional operators are
  * risky: they bypass page accounting.
  */
@@ -384,9 +399,10 @@ static inline void __ClearPageTail(struct page *page)
  * these flags set.  It they are, there is a problem.
  */
 #define PAGE_FLAGS_CHECK_AT_FREE \
-	(1 << PG_lru   | 1 << PG_private   | 1 << PG_locked | \
-	 1 << PG_buddy | 1 << PG_writeback | 1 << PG_reserved | \
-	 1 << PG_slab  | 1 << PG_swapcache | 1 << PG_active | \
+	(1 << PG_lru	 | 1 << PG_locked    | \
+	 1 << PG_private | 1 << PG_private_2 | \
+	 1 << PG_buddy	 | 1 << PG_writeback | 1 << PG_reserved | \
+	 1 << PG_slab	 | 1 << PG_swapcache | 1 << PG_active | \
 	 __PG_UNEVICTABLE | __PG_MLOCKED)
 
 /*
@@ -397,4 +413,16 @@ static inline void __ClearPageTail(struct page *page)
 #define PAGE_FLAGS_CHECK_AT_PREP	((1 << NR_PAGEFLAGS) - 1)
 
 #endif /* !__GENERATING_BOUNDS_H */
+
+/**
+ * page_has_private - Determine if page has private stuff
+ * @page: The page to be checked
+ *
+ * Determine if a page has private stuff, indicating that release routines
+ * should be invoked upon it.
+ */
+#define page_has_private(page)			\
+	((page)->flags & ((1 << PG_private) |	\
+			  (1 << PG_private_2)))
+
 #endif	/* PAGE_FLAGS_H */
diff --git a/include/linux/page_cgroup.h b/include/linux/page_cgroup.h
index 602cc1fdee90..7339c7bf7331 100644
--- a/include/linux/page_cgroup.h
+++ b/include/linux/page_cgroup.h
@@ -91,24 +91,23 @@ static inline void page_cgroup_init(void)
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
 #include <linux/swap.h>
-extern struct mem_cgroup *
-swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem);
-extern struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent);
+extern unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id);
+extern unsigned short lookup_swap_cgroup(swp_entry_t ent);
 extern int swap_cgroup_swapon(int type, unsigned long max_pages);
 extern void swap_cgroup_swapoff(int type);
 #else
 #include <linux/swap.h>
 
 static inline
-struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 {
-	return NULL;
+	return 0;
 }
 
 static inline
-struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+unsigned short lookup_swap_cgroup(swp_entry_t ent)
 {
-	return NULL;
+	return 0;
 }
 
 static inline int
diff --git a/include/linux/pagemap.h b/include/linux/pagemap.h
index 01ca0856caff..34da5230faab 100644
--- a/include/linux/pagemap.h
+++ b/include/linux/pagemap.h
@@ -18,9 +18,14 @@
  * Bits in mapping->flags.  The lower __GFP_BITS_SHIFT bits are the page
  * allocation mode flags.
  */
-#define	AS_EIO		(__GFP_BITS_SHIFT + 0)	/* IO error on async write */
-#define AS_ENOSPC	(__GFP_BITS_SHIFT + 1)	/* ENOSPC on async write */
-#define AS_MM_ALL_LOCKS	(__GFP_BITS_SHIFT + 2)	/* under mm_take_all_locks() */
+enum mapping_flags {
+	AS_EIO		= __GFP_BITS_SHIFT + 0,	/* IO error on async write */
+	AS_ENOSPC	= __GFP_BITS_SHIFT + 1,	/* ENOSPC on async write */
+	AS_MM_ALL_LOCKS	= __GFP_BITS_SHIFT + 2,	/* under mm_take_all_locks() */
+#ifdef CONFIG_UNEVICTABLE_LRU
+	AS_UNEVICTABLE	= __GFP_BITS_SHIFT + 3,	/* e.g., ramdisk, SHM_LOCK */
+#endif
+};
 
 static inline void mapping_set_error(struct address_space *mapping, int error)
 {
@@ -33,7 +38,6 @@ static inline void mapping_set_error(struct address_space *mapping, int error)
 }
 
 #ifdef CONFIG_UNEVICTABLE_LRU
-#define AS_UNEVICTABLE	(__GFP_BITS_SHIFT + 2)	/* e.g., ramdisk, SHM_LOCK */
 
 static inline void mapping_set_unevictable(struct address_space *mapping)
 {
@@ -380,6 +384,11 @@ static inline void wait_on_page_writeback(struct page *page)
 extern void end_page_writeback(struct page *page);
 
 /*
+ * Add an arbitrary waiter to a page's wait queue
+ */
+extern void add_page_wait_queue(struct page *page, wait_queue_t *waiter);
+
+/*
  * Fault a userspace page into pagetables.  Return non-zero on a fault.
  *
  * This assumes that two userspace pages are always sufficient.  That's
diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h
index cb14fd260837..170f8b1f22db 100644
--- a/include/linux/pci_ids.h
+++ b/include/linux/pci_ids.h
@@ -526,6 +526,7 @@
 #define PCI_DEVICE_ID_AMD_OPUS_7443	0x7443
 #define PCI_DEVICE_ID_AMD_VIPER_7443	0x7443
 #define PCI_DEVICE_ID_AMD_OPUS_7445	0x7445
+#define PCI_DEVICE_ID_AMD_8111_PCI	0x7460
 #define PCI_DEVICE_ID_AMD_8111_LPC	0x7468
 #define PCI_DEVICE_ID_AMD_8111_IDE	0x7469
 #define PCI_DEVICE_ID_AMD_8111_SMBUS2	0x746a
diff --git a/include/linux/ptrace.h b/include/linux/ptrace.h
index 98b93ca4db06..67c15653fc23 100644
--- a/include/linux/ptrace.h
+++ b/include/linux/ptrace.h
@@ -94,6 +94,7 @@ extern void ptrace_notify(int exit_code);
 extern void __ptrace_link(struct task_struct *child,
 			  struct task_struct *new_parent);
 extern void __ptrace_unlink(struct task_struct *child);
+extern void exit_ptrace(struct task_struct *tracer);
 extern void ptrace_fork(struct task_struct *task, unsigned long clone_flags);
 #define PTRACE_MODE_READ   1
 #define PTRACE_MODE_ATTACH 2
diff --git a/include/linux/pwm.h b/include/linux/pwm.h
index 3945f803d514..7c775751392c 100644
--- a/include/linux/pwm.h
+++ b/include/linux/pwm.h
@@ -28,4 +28,4 @@ int pwm_enable(struct pwm_device *pwm);
  */
 void pwm_disable(struct pwm_device *pwm);
 
-#endif /* __ASM_ARCH_PWM_H */
+#endif /* __LINUX_PWM_H */
diff --git a/include/linux/raid/md.h b/include/linux/raid/md.h
deleted file mode 100644
index 82bea14cae1a..000000000000
--- a/include/linux/raid/md.h
+++ /dev/null
@@ -1,81 +0,0 @@
-/*
-   md.h : Multiple Devices driver for Linux
-          Copyright (C) 1996-98 Ingo Molnar, Gadi Oxman
-          Copyright (C) 1994-96 Marc ZYNGIER
-	  <zyngier@ufr-info-p7.ibp.fr> or
-	  <maz@gloups.fdn.fr>
-	  
-   This program is free software; you can redistribute it and/or modify
-   it under the terms of the GNU General Public License as published by
-   the Free Software Foundation; either version 2, or (at your option)
-   any later version.
-   
-   You should have received a copy of the GNU General Public License
-   (for example /usr/src/linux/COPYING); if not, write to the Free
-   Software Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.  
-*/
-
-#ifndef _MD_H
-#define _MD_H
-
-#include <linux/blkdev.h>
-#include <linux/seq_file.h>
-
-/*
- * 'md_p.h' holds the 'physical' layout of RAID devices
- * 'md_u.h' holds the user <=> kernel API
- *
- * 'md_k.h' holds kernel internal definitions
- */
-
-#include <linux/raid/md_p.h>
-#include <linux/raid/md_u.h>
-#include <linux/raid/md_k.h>
-
-#ifdef CONFIG_MD
-
-/*
- * Different major versions are not compatible.
- * Different minor versions are only downward compatible.
- * Different patchlevel versions are downward and upward compatible.
- */
-#define MD_MAJOR_VERSION                0
-#define MD_MINOR_VERSION                90
-/*
- * MD_PATCHLEVEL_VERSION indicates kernel functionality.
- * >=1 means different superblock formats are selectable using SET_ARRAY_INFO
- *     and major_version/minor_version accordingly
- * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT
- *     in the super status byte
- * >=3 means that bitmap superblock version 4 is supported, which uses
- *     little-ending representation rather than host-endian
- */
-#define MD_PATCHLEVEL_VERSION           3
-
-extern int mdp_major;
-
-extern int register_md_personality(struct mdk_personality *p);
-extern int unregister_md_personality(struct mdk_personality *p);
-extern mdk_thread_t * md_register_thread(void (*run) (mddev_t *mddev),
-				mddev_t *mddev, const char *name);
-extern void md_unregister_thread(mdk_thread_t *thread);
-extern void md_wakeup_thread(mdk_thread_t *thread);
-extern void md_check_recovery(mddev_t *mddev);
-extern void md_write_start(mddev_t *mddev, struct bio *bi);
-extern void md_write_end(mddev_t *mddev);
-extern void md_done_sync(mddev_t *mddev, int blocks, int ok);
-extern void md_error(mddev_t *mddev, mdk_rdev_t *rdev);
-
-extern void md_super_write(mddev_t *mddev, mdk_rdev_t *rdev,
-			   sector_t sector, int size, struct page *page);
-extern void md_super_wait(mddev_t *mddev);
-extern int sync_page_io(struct block_device *bdev, sector_t sector, int size,
-			struct page *page, int rw);
-extern void md_do_sync(mddev_t *mddev);
-extern void md_new_event(mddev_t *mddev);
-extern int md_allow_write(mddev_t *mddev);
-extern void md_wait_for_blocked_rdev(mdk_rdev_t *rdev, mddev_t *mddev);
-
-#endif /* CONFIG_MD */
-#endif 
-
diff --git a/include/linux/raid/md_u.h b/include/linux/raid/md_u.h
index 7192035fc4b0..fb1abb3367e9 100644
--- a/include/linux/raid/md_u.h
+++ b/include/linux/raid/md_u.h
@@ -15,6 +15,24 @@
 #ifndef _MD_U_H
 #define _MD_U_H
 
+/*
+ * Different major versions are not compatible.
+ * Different minor versions are only downward compatible.
+ * Different patchlevel versions are downward and upward compatible.
+ */
+#define MD_MAJOR_VERSION                0
+#define MD_MINOR_VERSION                90
+/*
+ * MD_PATCHLEVEL_VERSION indicates kernel functionality.
+ * >=1 means different superblock formats are selectable using SET_ARRAY_INFO
+ *     and major_version/minor_version accordingly
+ * >=2 means that Internal bitmaps are supported by setting MD_SB_BITMAP_PRESENT
+ *     in the super status byte
+ * >=3 means that bitmap superblock version 4 is supported, which uses
+ *     little-ending representation rather than host-endian
+ */
+#define MD_PATCHLEVEL_VERSION           3
+
 /* ioctls */
 
 /* status */
@@ -46,6 +64,12 @@
 #define STOP_ARRAY_RO		_IO (MD_MAJOR, 0x33)
 #define RESTART_ARRAY_RW	_IO (MD_MAJOR, 0x34)
 
+/* 63 partitions with the alternate major number (mdp) */
+#define MdpMinorShift 6
+#ifdef __KERNEL__
+extern int mdp_major;
+#endif
+
 typedef struct mdu_version_s {
 	int major;
 	int minor;
@@ -85,6 +109,17 @@ typedef struct mdu_array_info_s {
 
 } mdu_array_info_t;
 
+/* non-obvious values for 'level' */
+#define	LEVEL_MULTIPATH		(-4)
+#define	LEVEL_LINEAR		(-1)
+#define	LEVEL_FAULTY		(-5)
+
+/* we need a value for 'no level specified' and 0
+ * means 'raid0', so we need something else.  This is
+ * for internal use only
+ */
+#define	LEVEL_NONE		(-1000000)
+
 typedef struct mdu_disk_info_s {
 	/*
 	 * configuration/status of one particular disk
diff --git a/drivers/md/raid6.h b/include/linux/raid/pq.h
index 98dcde88470e..d92480f8285c 100644
--- a/drivers/md/raid6.h
+++ b/include/linux/raid/pq.h
@@ -5,7 +5,7 @@
  *   This program is free software; you can redistribute it and/or modify
  *   it under the terms of the GNU General Public License as published by
  *   the Free Software Foundation, Inc., 53 Temple Place Ste 330,
- *   Bostom MA 02111-1307, USA; either version 2 of the License, or
+ *   Boston MA 02111-1307, USA; either version 2 of the License, or
  *   (at your option) any later version; incorporated herein by reference.
  *
  * ----------------------------------------------------------------------- */
@@ -17,14 +17,7 @@
 
 /* Set to 1 to use kernel-wide empty_zero_page */
 #define RAID6_USE_EMPTY_ZERO_PAGE 0
-
-#include <linux/raid/md.h>
-#include <linux/raid/raid5.h>
-
-typedef raid5_conf_t raid6_conf_t; /* Same configuration */
-
-/* Additional compute_parity mode -- updates the parity w/o LOCKING */
-#define UPDATE_PARITY	4
+#include <linux/blkdev.h>
 
 /* We need a pre-zeroed page... if we don't want to use the kernel-provided
    one define it here */
@@ -68,6 +61,10 @@ extern const char raid6_empty_zero_page[PAGE_SIZE];
 #define enable_kernel_altivec()
 #define disable_kernel_altivec()
 
+#define EXPORT_SYMBOL(sym)
+#define MODULE_LICENSE(licence)
+#define subsys_initcall(x)
+#define module_exit(x)
 #endif /* __KERNEL__ */
 
 /* Routine choices */
@@ -98,9 +95,11 @@ extern const u8 raid6_gfinv[256]      __attribute__((aligned(256)));
 extern const u8 raid6_gfexi[256]      __attribute__((aligned(256)));
 
 /* Recovery routines */
-void raid6_2data_recov(int disks, size_t bytes, int faila, int failb, void **ptrs);
+void raid6_2data_recov(int disks, size_t bytes, int faila, int failb,
+		       void **ptrs);
 void raid6_datap_recov(int disks, size_t bytes, int faila, void **ptrs);
-void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, void **ptrs);
+void raid6_dual_recov(int disks, size_t bytes, int faila, int failb,
+		      void **ptrs);
 
 /* Some definitions to allow code to be compiled for testing in userspace */
 #ifndef __KERNEL__
@@ -108,8 +107,11 @@ void raid6_dual_recov(int disks, size_t bytes, int faila, int failb, void **ptrs
 # define jiffies	raid6_jiffies()
 # define printk 	printf
 # define GFP_KERNEL	0
-# define __get_free_pages(x,y)	((unsigned long)mmap(NULL, PAGE_SIZE << (y), PROT_READ|PROT_WRITE, MAP_PRIVATE|MAP_ANONYMOUS, 0, 0))
-# define free_pages(x,y)	munmap((void *)(x), (y)*PAGE_SIZE)
+# define __get_free_pages(x, y)	((unsigned long)mmap(NULL, PAGE_SIZE << (y), \
+						     PROT_READ|PROT_WRITE,   \
+						     MAP_PRIVATE|MAP_ANONYMOUS,\
+						     0, 0))
+# define free_pages(x, y)	munmap((void *)(x), (y)*PAGE_SIZE)
 
 static inline void cpu_relax(void)
 {
diff --git a/include/linux/raid/xor.h b/include/linux/raid/xor.h
index 3e120587eada..5a210959e3f8 100644
--- a/include/linux/raid/xor.h
+++ b/include/linux/raid/xor.h
@@ -1,8 +1,6 @@
 #ifndef _XOR_H
 #define _XOR_H
 
-#include <linux/raid/md.h>
-
 #define MAX_XOR_BLOCKS 4
 
 extern void xor_blocks(unsigned int count, unsigned int bytes,
diff --git a/include/linux/regulator/bq24022.h b/include/linux/regulator/bq24022.h
index e84b0a9feda5..a6d014005d49 100644
--- a/include/linux/regulator/bq24022.h
+++ b/include/linux/regulator/bq24022.h
@@ -10,6 +10,8 @@
  *
  */
 
+struct regulator_init_data;
+
 /**
  * bq24022_mach_info - platform data for bq24022
  * @gpio_nce: GPIO line connected to the nCE pin, used to enable / disable charging
@@ -18,4 +20,5 @@
 struct bq24022_mach_info {
 	int gpio_nce;
 	int gpio_iset2;
+	struct regulator_init_data *init_data;
 };
diff --git a/include/linux/regulator/consumer.h b/include/linux/regulator/consumer.h
index 801bf77ff4e2..277f4b964df5 100644
--- a/include/linux/regulator/consumer.h
+++ b/include/linux/regulator/consumer.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
  *
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -88,6 +88,7 @@
  * FAIL           Regulator output has failed.
  * OVER_TEMP      Regulator over temp.
  * FORCE_DISABLE  Regulator shut down by software.
+ * VOLTAGE_CHANGE Regulator voltage changed.
  *
  * NOTE: These events can be OR'ed together when passed into handler.
  */
@@ -98,6 +99,7 @@
 #define REGULATOR_EVENT_FAIL			0x08
 #define REGULATOR_EVENT_OVER_TEMP		0x10
 #define REGULATOR_EVENT_FORCE_DISABLE		0x20
+#define REGULATOR_EVENT_VOLTAGE_CHANGE		0x40
 
 struct regulator;
 
@@ -140,6 +142,8 @@ int regulator_bulk_disable(int num_consumers,
 void regulator_bulk_free(int num_consumers,
 			 struct regulator_bulk_data *consumers);
 
+int regulator_count_voltages(struct regulator *regulator);
+int regulator_list_voltage(struct regulator *regulator, unsigned selector);
 int regulator_set_voltage(struct regulator *regulator, int min_uV, int max_uV);
 int regulator_get_voltage(struct regulator *regulator);
 int regulator_set_current_limit(struct regulator *regulator,
diff --git a/include/linux/regulator/driver.h b/include/linux/regulator/driver.h
index 2dae05705f13..4848d8dacd90 100644
--- a/include/linux/regulator/driver.h
+++ b/include/linux/regulator/driver.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
  *
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -21,25 +21,38 @@
 struct regulator_dev;
 struct regulator_init_data;
 
+enum regulator_status {
+	REGULATOR_STATUS_OFF,
+	REGULATOR_STATUS_ON,
+	REGULATOR_STATUS_ERROR,
+	/* fast/normal/idle/standby are flavors of "on" */
+	REGULATOR_STATUS_FAST,
+	REGULATOR_STATUS_NORMAL,
+	REGULATOR_STATUS_IDLE,
+	REGULATOR_STATUS_STANDBY,
+};
+
 /**
  * struct regulator_ops - regulator operations.
  *
- * This struct describes regulator operations which can be implemented by
- * regulator chip drivers.
- *
- * @enable: Enable the regulator.
- * @disable: Disable the regulator.
+ * @enable: Configure the regulator as enabled.
+ * @disable: Configure the regulator as disabled.
  * @is_enabled: Return 1 if the regulator is enabled, 0 otherwise.
  *
  * @set_voltage: Set the voltage for the regulator within the range specified.
  *               The driver should select the voltage closest to min_uV.
  * @get_voltage: Return the currently configured voltage for the regulator.
+ * @list_voltage: Return one of the supported voltages, in microvolts; zero
+ *	if the selector indicates a voltage that is unusable on this system;
+ *	or negative errno.  Selectors range from zero to one less than
+ *	regulator_desc.n_voltages.  Voltages may be reported in any order.
  *
  * @set_current_limit: Configure a limit for a current-limited regulator.
- * @get_current_limit: Get the limit for a current-limited regulator.
+ * @get_current_limit: Get the configured limit for a current-limited regulator.
  *
- * @set_mode: Set the operating mode for the regulator.
- * @get_mode: Get the current operating mode for the regulator.
+ * @get_mode: Get the configured operating mode for the regulator.
+ * @get_status: Return actual (not as-configured) status of regulator, as a
+ *	REGULATOR_STATUS value (or negative errno)
  * @get_optimum_mode: Get the most efficient operating mode for the regulator
  *                    when running with the specified parameters.
  *
@@ -51,9 +64,15 @@ struct regulator_init_data;
  *                       suspended.
  * @set_suspend_mode: Set the operating mode for the regulator when the
  *                    system is suspended.
+ *
+ * This struct describes regulator operations which can be implemented by
+ * regulator chip drivers.
  */
 struct regulator_ops {
 
+	/* enumerate supported voltages */
+	int (*list_voltage) (struct regulator_dev *, unsigned selector);
+
 	/* get/set regulator voltage */
 	int (*set_voltage) (struct regulator_dev *, int min_uV, int max_uV);
 	int (*get_voltage) (struct regulator_dev *);
@@ -72,6 +91,13 @@ struct regulator_ops {
 	int (*set_mode) (struct regulator_dev *, unsigned int mode);
 	unsigned int (*get_mode) (struct regulator_dev *);
 
+	/* report regulator status ... most other accessors report
+	 * control inputs, this reports results of combining inputs
+	 * from Linux (and other sources) with the actual load.
+	 * returns REGULATOR_STATUS_* or negative errno.
+	 */
+	int (*get_status)(struct regulator_dev *);
+
 	/* get most efficient regulator operating mode for load */
 	unsigned int (*get_optimum_mode) (struct regulator_dev *, int input_uV,
 					  int output_uV, int load_uA);
@@ -106,6 +132,7 @@ enum regulator_type {
  *
  * @name: Identifying name for the regulator.
  * @id: Numerical identifier for the regulator.
+ * @n_voltages: Number of selectors available for ops.list_voltage().
  * @ops: Regulator operations table.
  * @irq: Interrupt number for the regulator.
  * @type: Indicates if the regulator is a voltage or current regulator.
@@ -114,14 +141,48 @@ enum regulator_type {
 struct regulator_desc {
 	const char *name;
 	int id;
+	unsigned n_voltages;
 	struct regulator_ops *ops;
 	int irq;
 	enum regulator_type type;
 	struct module *owner;
 };
 
+/*
+ * struct regulator_dev
+ *
+ * Voltage / Current regulator class device. One for each
+ * regulator.
+ *
+ * This should *not* be used directly by anything except the regulator
+ * core and notification injection (which should take the mutex and do
+ * no other direct access).
+ */
+struct regulator_dev {
+	struct regulator_desc *desc;
+	int use_count;
+
+	/* lists we belong to */
+	struct list_head list; /* list of all regulators */
+	struct list_head slist; /* list of supplied regulators */
+
+	/* lists we own */
+	struct list_head consumer_list; /* consumers we supply */
+	struct list_head supply_list; /* regulators we supply */
+
+	struct blocking_notifier_head notifier;
+	struct mutex mutex; /* consumer lock */
+	struct module *owner;
+	struct device dev;
+	struct regulation_constraints *constraints;
+	struct regulator_dev *supply;	/* for tree */
+
+	void *reg_data;		/* regulator_dev data */
+};
+
 struct regulator_dev *regulator_register(struct regulator_desc *regulator_desc,
-	struct device *dev, void *driver_data);
+	struct device *dev, struct regulator_init_data *init_data,
+	void *driver_data);
 void regulator_unregister(struct regulator_dev *rdev);
 
 int regulator_notifier_call_chain(struct regulator_dev *rdev,
diff --git a/include/linux/regulator/fixed.h b/include/linux/regulator/fixed.h
index 1387a5d2190e..91b4da31f1b5 100644
--- a/include/linux/regulator/fixed.h
+++ b/include/linux/regulator/fixed.h
@@ -14,9 +14,12 @@
 #ifndef __REGULATOR_FIXED_H
 #define __REGULATOR_FIXED_H
 
+struct regulator_init_data;
+
 struct fixed_voltage_config {
 	const char *supply_name;
 	int microvolts;
+	struct regulator_init_data *init_data;
 };
 
 #endif
diff --git a/include/linux/regulator/machine.h b/include/linux/regulator/machine.h
index 3794773b23d2..bac64fa390f2 100644
--- a/include/linux/regulator/machine.h
+++ b/include/linux/regulator/machine.h
@@ -3,7 +3,7 @@
  *
  * Copyright (C) 2007, 2008 Wolfson Microelectronics PLC.
  *
- * Author: Liam Girdwood <lg@opensource.wolfsonmicro.com>
+ * Author: Liam Girdwood <lrg@slimlogic.co.uk>
  *
  * This program is free software; you can redistribute it and/or modify
  * it under the terms of the GNU General Public License version 2 as
@@ -73,7 +73,9 @@ struct regulator_state {
  *
  * @always_on: Set if the regulator should never be disabled.
  * @boot_on: Set if the regulator is enabled when the system is initially
- *           started.
+ *           started.  If the regulator is not enabled by the hardware or
+ *           bootloader then it will be enabled when the constraints are
+ *           applied.
  * @apply_uV: Apply the voltage constraint when initialising.
  *
  * @input_uV: Input voltage for regulator when supplied by another regulator.
@@ -83,6 +85,7 @@ struct regulator_state {
  * @state_standby: State for regulator when system is suspended in standby
  *                 mode.
  * @initial_state: Suspend state to set by default.
+ * @initial_mode: Mode to set at startup.
  */
 struct regulation_constraints {
 
@@ -111,6 +114,9 @@ struct regulation_constraints {
 	struct regulator_state state_standby;
 	suspend_state_t initial_state; /* suspend state to set at init */
 
+	/* mode to set on startup */
+	unsigned int initial_mode;
+
 	/* constriant flags */
 	unsigned always_on:1;	/* regulator never off when system is on */
 	unsigned boot_on:1;	/* bootloader/firmware enabled regulator */
@@ -160,4 +166,6 @@ struct regulator_init_data {
 
 int regulator_suspend_prepare(suspend_state_t state);
 
+void regulator_has_full_constraints(void);
+
 #endif
diff --git a/include/linux/rtc-v3020.h b/include/linux/rtc-v3020.h
index bf74e63c98fe..8ba646e610d9 100644
--- a/include/linux/rtc-v3020.h
+++ b/include/linux/rtc-v3020.h
@@ -14,6 +14,12 @@
  * is used depends on the board. */
 struct v3020_platform_data {
 	int leftshift; /* (1<<(leftshift)) & readl() */
+
+	int use_gpio:1;
+	unsigned int gpio_cs;
+	unsigned int gpio_wr;
+	unsigned int gpio_rd;
+	unsigned int gpio_io;
 };
 
 #define V3020_STATUS_0	0x00
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 5a50fdef5be5..b94f3541f67b 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -68,7 +68,7 @@ struct sched_param {
 #include <linux/smp.h>
 #include <linux/sem.h>
 #include <linux/signal.h>
-#include <linux/fs_struct.h>
+#include <linux/path.h>
 #include <linux/compiler.h>
 #include <linux/completion.h>
 #include <linux/pid.h>
@@ -97,6 +97,7 @@ struct futex_pi_state;
 struct robust_list_head;
 struct bio;
 struct bts_tracer;
+struct fs_struct;
 
 /*
  * List of flags we want to share for kernel threads,
@@ -549,25 +550,8 @@ struct signal_struct {
 
 	struct list_head cpu_timers[3];
 
-	/* job control IDs */
-
-	/*
-	 * pgrp and session fields are deprecated.
-	 * use the task_session_Xnr and task_pgrp_Xnr routines below
-	 */
-
-	union {
-		pid_t pgrp __deprecated;
-		pid_t __pgrp;
-	};
-
 	struct pid *tty_old_pgrp;
 
-	union {
-		pid_t session __deprecated;
-		pid_t __session;
-	};
-
 	/* boolean value for session group leader */
 	int leader;
 
@@ -1473,16 +1457,6 @@ static inline int rt_task(struct task_struct *p)
 	return rt_prio(p->prio);
 }
 
-static inline void set_task_session(struct task_struct *tsk, pid_t session)
-{
-	tsk->signal->__session = session;
-}
-
-static inline void set_task_pgrp(struct task_struct *tsk, pid_t pgrp)
-{
-	tsk->signal->__pgrp = pgrp;
-}
-
 static inline struct pid *task_pid(struct task_struct *task)
 {
 	return task->pids[PIDTYPE_PID].pid;
@@ -1493,6 +1467,11 @@ static inline struct pid *task_tgid(struct task_struct *task)
 	return task->group_leader->pids[PIDTYPE_PID].pid;
 }
 
+/*
+ * Without tasklist or rcu lock it is not safe to dereference
+ * the result of task_pgrp/task_session even if task == current,
+ * we can race with another thread doing sys_setsid/sys_setpgid.
+ */
 static inline struct pid *task_pgrp(struct task_struct *task)
 {
 	return task->group_leader->pids[PIDTYPE_PGID].pid;
@@ -1518,17 +1497,23 @@ struct pid_namespace;
  *
  * see also pid_nr() etc in include/linux/pid.h
  */
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
+			struct pid_namespace *ns);
 
 static inline pid_t task_pid_nr(struct task_struct *tsk)
 {
 	return tsk->pid;
 }
 
-pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
+static inline pid_t task_pid_nr_ns(struct task_struct *tsk,
+					struct pid_namespace *ns)
+{
+	return __task_pid_nr_ns(tsk, PIDTYPE_PID, ns);
+}
 
 static inline pid_t task_pid_vnr(struct task_struct *tsk)
 {
-	return pid_vnr(task_pid(tsk));
+	return __task_pid_nr_ns(tsk, PIDTYPE_PID, NULL);
 }
 
 
@@ -1545,31 +1530,34 @@ static inline pid_t task_tgid_vnr(struct task_struct *tsk)
 }
 
 
-static inline pid_t task_pgrp_nr(struct task_struct *tsk)
+static inline pid_t task_pgrp_nr_ns(struct task_struct *tsk,
+					struct pid_namespace *ns)
 {
-	return tsk->signal->__pgrp;
+	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, ns);
 }
 
-pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
 static inline pid_t task_pgrp_vnr(struct task_struct *tsk)
 {
-	return pid_vnr(task_pgrp(tsk));
+	return __task_pid_nr_ns(tsk, PIDTYPE_PGID, NULL);
 }
 
 
-static inline pid_t task_session_nr(struct task_struct *tsk)
+static inline pid_t task_session_nr_ns(struct task_struct *tsk,
+					struct pid_namespace *ns)
 {
-	return tsk->signal->__session;
+	return __task_pid_nr_ns(tsk, PIDTYPE_SID, ns);
 }
 
-pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns);
-
 static inline pid_t task_session_vnr(struct task_struct *tsk)
 {
-	return pid_vnr(task_session(tsk));
+	return __task_pid_nr_ns(tsk, PIDTYPE_SID, NULL);
 }
 
+/* obsolete, do not use */
+static inline pid_t task_pgrp_nr(struct task_struct *tsk)
+{
+	return task_pgrp_nr_ns(tsk, &init_pid_ns);
+}
 
 /**
  * pid_alive - check that a task structure is not stale
@@ -1979,7 +1967,8 @@ extern void mm_release(struct task_struct *, struct mm_struct *);
 /* Allocate a new mm structure and copy contents from tsk->mm */
 extern struct mm_struct *dup_mm(struct task_struct *tsk);
 
-extern int  copy_thread(int, unsigned long, unsigned long, unsigned long, struct task_struct *, struct pt_regs *);
+extern int copy_thread(unsigned long, unsigned long, unsigned long,
+			struct task_struct *, struct pt_regs *);
 extern void flush_thread(void);
 extern void exit_thread(void);
 
@@ -2064,6 +2053,11 @@ static inline int thread_group_empty(struct task_struct *p)
 #define delay_group_leader(p) \
 		(thread_group_leader(p) && !thread_group_empty(p))
 
+static inline int task_detached(struct task_struct *p)
+{
+	return p->exit_signal == -1;
+}
+
 /*
  * Protects ->fs, ->files, ->mm, ->group_info, ->comm, keyring
  * subscriptions and synchronises with wait4().  Also used in procfs.  Also
diff --git a/include/linux/slow-work.h b/include/linux/slow-work.h
new file mode 100644
index 000000000000..85958277f83d
--- /dev/null
+++ b/include/linux/slow-work.h
@@ -0,0 +1,95 @@
+/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/slow-work.txt
+ */
+
+#ifndef _LINUX_SLOW_WORK_H
+#define _LINUX_SLOW_WORK_H
+
+#ifdef CONFIG_SLOW_WORK
+
+#include <linux/sysctl.h>
+
+struct slow_work;
+
+/*
+ * The operations used to support slow work items
+ */
+struct slow_work_ops {
+	/* get a ref on a work item
+	 * - return 0 if successful, -ve if not
+	 */
+	int (*get_ref)(struct slow_work *work);
+
+	/* discard a ref to a work item */
+	void (*put_ref)(struct slow_work *work);
+
+	/* execute a work item */
+	void (*execute)(struct slow_work *work);
+};
+
+/*
+ * A slow work item
+ * - A reference is held on the parent object by the thread pool when it is
+ *   queued
+ */
+struct slow_work {
+	unsigned long		flags;
+#define SLOW_WORK_PENDING	0	/* item pending (further) execution */
+#define SLOW_WORK_EXECUTING	1	/* item currently executing */
+#define SLOW_WORK_ENQ_DEFERRED	2	/* item enqueue deferred */
+#define SLOW_WORK_VERY_SLOW	3	/* item is very slow */
+	const struct slow_work_ops *ops; /* operations table for this item */
+	struct list_head	link;	/* link in queue */
+};
+
+/**
+ * slow_work_init - Initialise a slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a slow work item.
+ */
+static inline void slow_work_init(struct slow_work *work,
+				  const struct slow_work_ops *ops)
+{
+	work->flags = 0;
+	work->ops = ops;
+	INIT_LIST_HEAD(&work->link);
+}
+
+/**
+ * slow_work_init - Initialise a very slow work item
+ * @work: The work item to initialise
+ * @ops: The operations to use to handle the slow work item
+ *
+ * Initialise a very slow work item.  This item will be restricted such that
+ * only a certain number of the pool threads will be able to execute items of
+ * this type.
+ */
+static inline void vslow_work_init(struct slow_work *work,
+				   const struct slow_work_ops *ops)
+{
+	work->flags = 1 << SLOW_WORK_VERY_SLOW;
+	work->ops = ops;
+	INIT_LIST_HEAD(&work->link);
+}
+
+extern int slow_work_enqueue(struct slow_work *work);
+extern int slow_work_register_user(void);
+extern void slow_work_unregister_user(void);
+
+#ifdef CONFIG_SYSCTL
+extern ctl_table slow_work_sysctls[];
+#endif
+
+#endif /* CONFIG_SLOW_WORK */
+#endif /* _LINUX_SLOW_WORK_H */
diff --git a/include/linux/smp.h b/include/linux/smp.h
index bbacb7baa446..a69db820eed6 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -38,7 +38,7 @@ int smp_call_function_single(int cpuid, void (*func) (void *info), void *info,
 /*
  * main cross-CPU interfaces, handles INIT, TLB flush, STOP, etc.
  * (defined in asm header):
- */ 
+ */
 
 /*
  * stops all CPUs but the current one:
@@ -82,7 +82,8 @@ smp_call_function_mask(cpumask_t mask, void(*func)(void *info), void *info,
 	return 0;
 }
 
-void __smp_call_function_single(int cpuid, struct call_single_data *data);
+void __smp_call_function_single(int cpuid, struct call_single_data *data,
+				int wait);
 
 /*
  * Generic and arch helpers
@@ -121,6 +122,8 @@ extern unsigned int setup_max_cpus;
 
 #else /* !SMP */
 
+static inline void smp_send_stop(void) { }
+
 /*
  *	These macros fold the SMP functionality into a single CPU system
  */
diff --git a/include/linux/spi/eeprom.h b/include/linux/spi/eeprom.h
index 1085212c446e..306e7b1c69ed 100644
--- a/include/linux/spi/eeprom.h
+++ b/include/linux/spi/eeprom.h
@@ -1,6 +1,8 @@
 #ifndef __LINUX_SPI_EEPROM_H
 #define __LINUX_SPI_EEPROM_H
 
+#include <linux/memory.h>
+
 /*
  * Put one of these structures in platform_data for SPI EEPROMS handled
  * by the "at25" driver.  On SPI, most EEPROMS understand the same core
@@ -17,6 +19,10 @@ struct spi_eeprom {
 #define	EE_ADDR2	0x0002			/* 16 bit addrs */
 #define	EE_ADDR3	0x0004			/* 24 bit addrs */
 #define	EE_READONLY	0x0008			/* disallow writes */
+
+	/* for exporting this chip's data to other kernel code */
+	void (*setup)(struct memory_accessor *mem, void *context);
+	void *context;
 };
 
 #endif /* __LINUX_SPI_EEPROM_H */
diff --git a/include/linux/spi/spi_gpio.h b/include/linux/spi/spi_gpio.h
index 0f01a0f1f40c..ca6782ee4b9f 100644
--- a/include/linux/spi/spi_gpio.h
+++ b/include/linux/spi/spi_gpio.h
@@ -25,10 +25,16 @@
  *	...
  *	};
  *
+ * If chipselect is not used (there's only one device on the bus), assign
+ * SPI_GPIO_NO_CHIPSELECT to the controller_data:
+ *		.controller_data = (void *) SPI_GPIO_NO_CHIPSELECT;
+ *
  * If the bitbanged bus is later switched to a "native" controller,
  * that platform_device and controller_data should be removed.
  */
 
+#define SPI_GPIO_NO_CHIPSELECT		((unsigned long)-1l)
+
 /**
  * struct spi_gpio_platform_data - parameter for bitbanged SPI master
  * @sck: number of the GPIO used for clock output
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index a0c66a2e00ad..252b245cfcf4 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -153,9 +153,11 @@ do {								\
  extern int _raw_spin_trylock(spinlock_t *lock);
  extern void _raw_spin_unlock(spinlock_t *lock);
  extern void _raw_read_lock(rwlock_t *lock);
+#define _raw_read_lock_flags(lock, flags) _raw_read_lock(lock)
  extern int _raw_read_trylock(rwlock_t *lock);
  extern void _raw_read_unlock(rwlock_t *lock);
  extern void _raw_write_lock(rwlock_t *lock);
+#define _raw_write_lock_flags(lock, flags) _raw_write_lock(lock)
  extern int _raw_write_trylock(rwlock_t *lock);
  extern void _raw_write_unlock(rwlock_t *lock);
 #else
@@ -165,9 +167,13 @@ do {								\
 # define _raw_spin_trylock(lock)	__raw_spin_trylock(&(lock)->raw_lock)
 # define _raw_spin_unlock(lock)		__raw_spin_unlock(&(lock)->raw_lock)
 # define _raw_read_lock(rwlock)		__raw_read_lock(&(rwlock)->raw_lock)
+# define _raw_read_lock_flags(lock, flags) \
+		__raw_read_lock_flags(&(lock)->raw_lock, *(flags))
 # define _raw_read_trylock(rwlock)	__raw_read_trylock(&(rwlock)->raw_lock)
 # define _raw_read_unlock(rwlock)	__raw_read_unlock(&(rwlock)->raw_lock)
 # define _raw_write_lock(rwlock)	__raw_write_lock(&(rwlock)->raw_lock)
+# define _raw_write_lock_flags(lock, flags) \
+		__raw_write_lock_flags(&(lock)->raw_lock, *(flags))
 # define _raw_write_trylock(rwlock)	__raw_write_trylock(&(rwlock)->raw_lock)
 # define _raw_write_unlock(rwlock)	__raw_write_unlock(&(rwlock)->raw_lock)
 #endif
diff --git a/include/linux/string.h b/include/linux/string.h
index 3c877d686375..489019ef1694 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -122,5 +122,14 @@ int bprintf(u32 *bin_buf, size_t size, const char *fmt, ...) __printf(3, 4);
 extern ssize_t memory_read_from_buffer(void *to, size_t count, loff_t *ppos,
 			const void *from, size_t available);
 
+/**
+ * strstarts - does @str start with @prefix?
+ * @str: string to examine
+ * @prefix: prefix to look for.
+ */
+static inline bool strstarts(const char *str, const char *prefix)
+{
+	return strncmp(str, prefix, strlen(prefix)) == 0;
+}
 #endif
 #endif /* _LINUX_STRING_H_ */
diff --git a/include/linux/synclink.h b/include/linux/synclink.h
index 99b8bdb17b2b..0ff2779c44d0 100644
--- a/include/linux/synclink.h
+++ b/include/linux/synclink.h
@@ -125,6 +125,7 @@
 #define MGSL_MODE_MONOSYNC	3
 #define MGSL_MODE_BISYNC	4
 #define MGSL_MODE_RAW		6
+#define MGSL_MODE_BASE_CLOCK    7
 
 #define MGSL_BUS_TYPE_ISA	1
 #define MGSL_BUS_TYPE_EISA	2
diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h
index 0cff9bb80b02..6470f74074af 100644
--- a/include/linux/syscalls.h
+++ b/include/linux/syscalls.h
@@ -517,6 +517,10 @@ asmlinkage long sys_pread64(unsigned int fd, char __user *buf,
 			    size_t count, loff_t pos);
 asmlinkage long sys_pwrite64(unsigned int fd, const char __user *buf,
 			     size_t count, loff_t pos);
+asmlinkage long sys_preadv(unsigned long fd, const struct iovec __user *vec,
+			   unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
+asmlinkage long sys_pwritev(unsigned long fd, const struct iovec __user *vec,
+			    unsigned long vlen, unsigned long pos_l, unsigned long pos_h);
 asmlinkage long sys_getcwd(char __user *buf, unsigned long size);
 asmlinkage long sys_mkdir(const char __user *pathname, int mode);
 asmlinkage long sys_chdir(const char __user *filename);
diff --git a/include/linux/timeriomem-rng.h b/include/linux/timeriomem-rng.h
index dd253177f65f..3e08a1c86830 100644
--- a/include/linux/timeriomem-rng.h
+++ b/include/linux/timeriomem-rng.h
@@ -14,7 +14,7 @@ struct timeriomem_rng_data {
 	struct completion	completion;
 	unsigned int		present:1;
 
-	u32 __iomem		*address;
+	void __iomem		*address;
 
 	/* measures in usecs */
 	unsigned int		period;
diff --git a/include/linux/topology.h b/include/linux/topology.h
index a16b9e06f2e5..7402c1a27c4f 100644
--- a/include/linux/topology.h
+++ b/include/linux/topology.h
@@ -38,11 +38,7 @@
 #endif
 
 #ifndef nr_cpus_node
-#define nr_cpus_node(node)				\
-	({						\
-		node_to_cpumask_ptr(__tmp__, node);	\
-		cpus_weight(*__tmp__);			\
-	})
+#define nr_cpus_node(node) cpumask_weight(cpumask_of_node(node))
 #endif
 
 #define for_each_node_with_cpus(node)			\
@@ -200,4 +196,9 @@ int arch_update_cpu_topology(void);
 #define topology_core_cpumask(cpu)		cpumask_of(cpu)
 #endif
 
+/* Returns the number of the current Node. */
+#ifndef numa_node_id
+#define numa_node_id()		(cpu_to_node(raw_smp_processor_id()))
+#endif
+
 #endif /* _LINUX_TOPOLOGY_H */
diff --git a/include/linux/tracehook.h b/include/linux/tracehook.h
index 6186a789d6c7..c7aa154f4bfc 100644
--- a/include/linux/tracehook.h
+++ b/include/linux/tracehook.h
@@ -388,17 +388,14 @@ static inline void tracehook_signal_handler(int sig, siginfo_t *info,
  * tracehook_consider_ignored_signal - suppress short-circuit of ignored signal
  * @task:		task receiving the signal
  * @sig:		signal number being sent
- * @handler:		%SIG_IGN or %SIG_DFL
  *
  * Return zero iff tracing doesn't care to examine this ignored signal,
  * so it can short-circuit normal delivery and never even get queued.
- * Either @handler is %SIG_DFL and @sig's default is ignore, or it's %SIG_IGN.
  *
  * Called with @task->sighand->siglock held.
  */
 static inline int tracehook_consider_ignored_signal(struct task_struct *task,
-						    int sig,
-						    void __user *handler)
+						    int sig)
 {
 	return (task_ptrace(task) & PT_PTRACED) != 0;
 }
@@ -407,19 +404,17 @@ static inline int tracehook_consider_ignored_signal(struct task_struct *task,
  * tracehook_consider_fatal_signal - suppress special handling of fatal signal
  * @task:		task receiving the signal
  * @sig:		signal number being sent
- * @handler:		%SIG_DFL or %SIG_IGN
  *
  * Return nonzero to prevent special handling of this termination signal.
- * Normally @handler is %SIG_DFL.  It can be %SIG_IGN if @sig is ignored,
- * in which case force_sig() is about to reset it to %SIG_DFL.
+ * Normally handler for signal is %SIG_DFL.  It can be %SIG_IGN if @sig is
+ * ignored, in which case force_sig() is about to reset it to %SIG_DFL.
  * When this returns zero, this signal might cause a quick termination
  * that does not give the debugger a chance to intercept the signal.
  *
  * Called with or without @task->sighand->siglock held.
  */
 static inline int tracehook_consider_fatal_signal(struct task_struct *task,
-						  int sig,
-						  void __user *handler)
+						  int sig)
 {
 	return (task_ptrace(task) & PT_PTRACED) != 0;
 }
@@ -507,7 +502,7 @@ static inline int tracehook_notify_jctl(int notify, int why)
 static inline int tracehook_notify_death(struct task_struct *task,
 					 void **death_cookie, int group_dead)
 {
-	if (task->exit_signal == -1)
+	if (task_detached(task))
 		return task->ptrace ? SIGCHLD : DEATH_REAP;
 
 	/*
diff --git a/include/linux/usb/wusb.h b/include/linux/usb/wusb.h
index 5f401b644ed5..429c631d2aad 100644
--- a/include/linux/usb/wusb.h
+++ b/include/linux/usb/wusb.h
@@ -80,8 +80,7 @@ struct wusb_ckhdid {
 	u8 data[16];
 } __attribute__((packed));
 
-const static
-struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } };
+static const struct wusb_ckhdid wusb_ckhdid_zero = { .data = { 0 } };
 
 #define WUSB_CKHDID_STRSIZE (3 * sizeof(struct wusb_ckhdid) + 1)
 
diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 3cd51e579ab1..13e1adf55c4c 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -41,6 +41,11 @@ struct delayed_work {
 	struct timer_list timer;
 };
 
+static inline struct delayed_work *to_delayed_work(struct work_struct *work)
+{
+	return container_of(work, struct delayed_work, work);
+}
+
 struct execute_work {
 	struct work_struct work;
 };
diff --git a/include/net/tcp.h b/include/net/tcp.h
index e54c76d75495..1b94b9bfe2dc 100644
--- a/include/net/tcp.h
+++ b/include/net/tcp.h
@@ -616,21 +616,6 @@ static inline int tcp_skb_mss(const struct sk_buff *skb)
 	return skb_shinfo(skb)->gso_size;
 }
 
-static inline void tcp_dec_pcount_approx_int(__u32 *count, const int decr)
-{
-	if (*count) {
-		*count -= decr;
-		if ((int)*count < 0)
-			*count = 0;
-	}
-}
-
-static inline void tcp_dec_pcount_approx(__u32 *count,
-					 const struct sk_buff *skb)
-{
-	tcp_dec_pcount_approx_int(count, tcp_skb_pcount(skb));
-}
-
 /* Events passed to congestion control interface */
 enum tcp_ca_event {
 	CA_EVENT_TX_START,	/* first transmit when no packets in flight */
diff --git a/init/Kconfig b/init/Kconfig
index 9d8cf2d2f840..09c79537ae09 100644
--- a/init/Kconfig
+++ b/init/Kconfig
@@ -531,7 +531,7 @@ config CGROUP_DEVICE
 
 config CPUSETS
 	bool "Cpuset support"
-	depends on SMP && CGROUPS
+	depends on CGROUPS
 	help
 	  This option will let you create and manage CPUSETs which
 	  allow dynamically partitioning a system into sets of CPUs and
@@ -565,7 +565,7 @@ config CGROUP_MEM_RES_CTLR
 	select MM_OWNER
 	help
 	  Provides a memory resource controller that manages both anonymous
-	  memory and page cache. (See Documentation/controllers/memory.txt)
+	  memory and page cache. (See Documentation/cgroups/memory.txt)
 
 	  Note that setting this option increases fixed memory overhead
 	  associated with each page of memory in the system. By this,
@@ -597,6 +597,8 @@ config CGROUP_MEM_RES_CTLR_SWAP
 	  is disabled by boot option, this will be automatically disabled and
 	  there will be no overhead from this. Even when you set this config=y,
 	  if boot option "noswapaccount" is set, swap will not be accounted.
+	  Now, memory usage of swap_cgroup is 2 bytes per entry. If swap page
+	  size is 4096bytes, 512k per 1Gbytes of swap.
 
 endif # CGROUPS
 
@@ -687,7 +689,7 @@ config PID_NS
 	depends on NAMESPACES && EXPERIMENTAL
 	help
 	  Support process id namespaces.  This allows having multiple
-	  process with the same pid as long as they are in different
+	  processes with the same pid as long as they are in different
 	  pid namespaces.  This is a building block of containers.
 
 	  Unless you want to work with an experimental feature
@@ -952,7 +954,7 @@ config COMPAT_BRK
 	  Randomizing heap placement makes heap exploits harder, but it
 	  also breaks ancient binaries (including anything libc5 based).
 	  This option changes the bootup default to heap randomization
-	  disabled, and can be overriden runtime by setting
+	  disabled, and can be overridden at runtime by setting
 	  /proc/sys/kernel/randomize_va_space to 2.
 
 	  On non-ancient distros (post-2000 ones) N is usually a safe choice.
@@ -1012,6 +1014,18 @@ config MARKERS
 
 source "arch/Kconfig"
 
+config SLOW_WORK
+	default n
+	bool "Enable slow work thread pool"
+	help
+	  The slow work thread pool provides a number of dynamically allocated
+	  threads that can be used by the kernel to perform operations that
+	  take a relatively long time.
+
+	  An example of this would be CacheFiles doing a path lookup followed
+	  by a series of mkdirs and a create call, all of which have to touch
+	  disk.
+
 endmenu		# General setup
 
 config HAVE_GENERIC_DMA_COHERENT
@@ -1110,7 +1124,7 @@ config INIT_ALL_POSSIBLE
 	  cpu_possible_map, some of them chose to initialize cpu_possible_map
 	  with all 1s, and others with all 0s.  When they were centralised,
 	  it was better to provide this option than to break all the archs
-	  and have several arch maintainers persuing me down dark alleys.
+	  and have several arch maintainers pursuing me down dark alleys.
 
 config STOP_MACHINE
 	bool
diff --git a/init/do_mounts.c b/init/do_mounts.c
index 8d4ff5afc1d8..dd7ee5f203f3 100644
--- a/init/do_mounts.c
+++ b/init/do_mounts.c
@@ -14,6 +14,7 @@
 #include <linux/fs.h>
 #include <linux/initrd.h>
 #include <linux/async.h>
+#include <linux/fs_struct.h>
 
 #include <linux/nfs_fs.h>
 #include <linux/nfs_fs_sb.h>
diff --git a/init/do_mounts.h b/init/do_mounts.h
index 9aa968d54329..f5b978a9bb92 100644
--- a/init/do_mounts.h
+++ b/init/do_mounts.h
@@ -1,4 +1,5 @@
 #include <linux/kernel.h>
+#include <linux/blkdev.h>
 #include <linux/init.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
diff --git a/init/do_mounts_md.c b/init/do_mounts_md.c
index 9bdddbcb3d6a..69aebbf8fd2d 100644
--- a/init/do_mounts_md.c
+++ b/init/do_mounts_md.c
@@ -1,5 +1,6 @@
 #include <linux/delay.h>
-#include <linux/raid/md.h>
+#include <linux/raid/md_u.h>
+#include <linux/raid/md_p.h>
 
 #include "do_mounts.h"
 
@@ -112,8 +113,6 @@ static int __init md_setup(char *str)
 	return 1;
 }
 
-#define MdpMinorShift 6
-
 static void __init md_setup_drive(void)
 {
 	int minor, i, ent, partitioned;
diff --git a/init/initramfs.c b/init/initramfs.c
index 619c1baf7701..80cd713f6cc5 100644
--- a/init/initramfs.c
+++ b/init/initramfs.c
@@ -571,11 +571,11 @@ static int __init populate_rootfs(void)
 	if (initrd_start) {
 #ifdef CONFIG_BLK_DEV_RAM
 		int fd;
-		printk(KERN_INFO "checking if image is initramfs...");
+		printk(KERN_INFO "checking if image is initramfs...\n");
 		err = unpack_to_rootfs((char *)initrd_start,
 			initrd_end - initrd_start);
 		if (!err) {
-			printk(" it is\n");
+			printk(KERN_INFO "rootfs image is initramfs; unpacking...\n");
 			free_initrd();
 			return 0;
 		} else {
@@ -583,7 +583,8 @@ static int __init populate_rootfs(void)
 			unpack_to_rootfs(__initramfs_start,
 				 __initramfs_end - __initramfs_start);
 		}
-		printk("it isn't (%s); looks like an initrd\n", err);
+		printk(KERN_INFO "rootfs image is not initramfs (%s)"
+				"; looks like an initrd\n", err);
 		fd = sys_open("/initrd.image", O_WRONLY|O_CREAT, 0700);
 		if (fd >= 0) {
 			sys_write(fd, (char *)initrd_start,
diff --git a/ipc/ipc_sysctl.c b/ipc/ipc_sysctl.c
index 4a7a12c95abe..40eab7314aeb 100644
--- a/ipc/ipc_sysctl.c
+++ b/ipc/ipc_sysctl.c
@@ -26,7 +26,7 @@ static void *get_ipc(ctl_table *table)
 	return which;
 }
 
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
 static int proc_ipc_dointvec(ctl_table *table, int write, struct file *filp,
 	void __user *buffer, size_t *lenp, loff_t *ppos)
 {
diff --git a/ipc/mqueue.c b/ipc/mqueue.c
index a8ddadbc7459..916785363f0f 100644
--- a/ipc/mqueue.c
+++ b/ipc/mqueue.c
@@ -602,7 +602,7 @@ static struct file *do_create(struct dentry *dir, struct dentry *dentry,
 		dentry->d_fsdata = attr;
 	}
 
-	mode &= ~current->fs->umask;
+	mode &= ~current_umask();
 	ret = mnt_want_write(mqueue_mnt);
 	if (ret)
 		goto out;
diff --git a/ipc/shm.c b/ipc/shm.c
index f239d87e0d37..faa46da99ebe 100644
--- a/ipc/shm.c
+++ b/ipc/shm.c
@@ -555,12 +555,14 @@ static void shm_get_stat(struct ipc_namespace *ns, unsigned long *rss,
 	in_use = shm_ids(ns).in_use;
 
 	for (total = 0, next_id = 0; total < in_use; next_id++) {
+		struct kern_ipc_perm *ipc;
 		struct shmid_kernel *shp;
 		struct inode *inode;
 
-		shp = idr_find(&shm_ids(ns).ipcs_idr, next_id);
-		if (shp == NULL)
+		ipc = idr_find(&shm_ids(ns).ipcs_idr, next_id);
+		if (ipc == NULL)
 			continue;
+		shp = container_of(ipc, struct shmid_kernel, shm_perm);
 
 		inode = shp->shm_file->f_path.dentry->d_inode;
 
diff --git a/kernel/Makefile b/kernel/Makefile
index e4791b3ba55d..bab1dffe37e9 100644
--- a/kernel/Makefile
+++ b/kernel/Makefile
@@ -93,6 +93,7 @@ obj-$(CONFIG_HAVE_GENERIC_DMA_COHERENT) += dma-coherent.o
 obj-$(CONFIG_FUNCTION_TRACER) += trace/
 obj-$(CONFIG_TRACING) += trace/
 obj-$(CONFIG_SMP) += sched_cpupri.o
+obj-$(CONFIG_SLOW_WORK) += slow-work.o
 
 ifneq ($(CONFIG_SCHED_OMIT_FRAME_POINTER),y)
 # According to Alan Modra <alan@linuxcare.com.au>, the -fno-omit-frame-pointer is
diff --git a/kernel/auditsc.c b/kernel/auditsc.c
index 8cbddff6c283..2bfc64786765 100644
--- a/kernel/auditsc.c
+++ b/kernel/auditsc.c
@@ -66,6 +66,7 @@
 #include <linux/syscalls.h>
 #include <linux/inotify.h>
 #include <linux/capability.h>
+#include <linux/fs_struct.h>
 
 #include "audit.h"
 
diff --git a/kernel/cgroup.c b/kernel/cgroup.c
index c500ca7239b2..382109b5baeb 100644
--- a/kernel/cgroup.c
+++ b/kernel/cgroup.c
@@ -94,7 +94,6 @@ struct cgroupfs_root {
 	char release_agent_path[PATH_MAX];
 };
 
-
 /*
  * The "rootnode" hierarchy is the "dummy hierarchy", reserved for the
  * subsystems that are otherwise unattached - it never has more than a
@@ -102,6 +101,39 @@ struct cgroupfs_root {
  */
 static struct cgroupfs_root rootnode;
 
+/*
+ * CSS ID -- ID per subsys's Cgroup Subsys State(CSS). used only when
+ * cgroup_subsys->use_id != 0.
+ */
+#define CSS_ID_MAX	(65535)
+struct css_id {
+	/*
+	 * The css to which this ID points. This pointer is set to valid value
+	 * after cgroup is populated. If cgroup is removed, this will be NULL.
+	 * This pointer is expected to be RCU-safe because destroy()
+	 * is called after synchronize_rcu(). But for safe use, css_is_removed()
+	 * css_tryget() should be used for avoiding race.
+	 */
+	struct cgroup_subsys_state *css;
+	/*
+	 * ID of this css.
+	 */
+	unsigned short id;
+	/*
+	 * Depth in hierarchy which this ID belongs to.
+	 */
+	unsigned short depth;
+	/*
+	 * ID is freed by RCU. (and lookup routine is RCU safe.)
+	 */
+	struct rcu_head rcu_head;
+	/*
+	 * Hierarchy of CSS ID belongs to.
+	 */
+	unsigned short stack[0]; /* Array of Length (depth+1) */
+};
+
+
 /* The list of hierarchy roots */
 
 static LIST_HEAD(roots);
@@ -185,6 +217,8 @@ struct cg_cgroup_link {
 static struct css_set init_css_set;
 static struct cg_cgroup_link init_css_set_link;
 
+static int cgroup_subsys_init_idr(struct cgroup_subsys *ss);
+
 /* css_set_lock protects the list of css_set objects, and the
  * chain of tasks off each css_set.  Nests outside task->alloc_lock
  * due to cgroup_iter_start() */
@@ -567,6 +601,9 @@ static struct backing_dev_info cgroup_backing_dev_info = {
 	.capabilities	= BDI_CAP_NO_ACCT_AND_WRITEBACK,
 };
 
+static int alloc_css_id(struct cgroup_subsys *ss,
+			struct cgroup *parent, struct cgroup *child);
+
 static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
 {
 	struct inode *inode = new_inode(sb);
@@ -585,13 +622,18 @@ static struct inode *cgroup_new_inode(mode_t mode, struct super_block *sb)
  * Call subsys's pre_destroy handler.
  * This is called before css refcnt check.
  */
-static void cgroup_call_pre_destroy(struct cgroup *cgrp)
+static int cgroup_call_pre_destroy(struct cgroup *cgrp)
 {
 	struct cgroup_subsys *ss;
+	int ret = 0;
+
 	for_each_subsys(cgrp->root, ss)
-		if (ss->pre_destroy)
-			ss->pre_destroy(ss, cgrp);
-	return;
+		if (ss->pre_destroy) {
+			ret = ss->pre_destroy(ss, cgrp);
+			if (ret)
+				break;
+		}
+	return ret;
 }
 
 static void free_cgroup_rcu(struct rcu_head *obj)
@@ -685,6 +727,22 @@ static void cgroup_d_remove_dir(struct dentry *dentry)
 	remove_dir(dentry);
 }
 
+/*
+ * A queue for waiters to do rmdir() cgroup. A tasks will sleep when
+ * cgroup->count == 0 && list_empty(&cgroup->children) && subsys has some
+ * reference to css->refcnt. In general, this refcnt is expected to goes down
+ * to zero, soon.
+ *
+ * CGRP_WAIT_ON_RMDIR flag is modified under cgroup's inode->i_mutex;
+ */
+DECLARE_WAIT_QUEUE_HEAD(cgroup_rmdir_waitq);
+
+static void cgroup_wakeup_rmdir_waiters(const struct cgroup *cgrp)
+{
+	if (unlikely(test_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags)))
+		wake_up_all(&cgroup_rmdir_waitq);
+}
+
 static int rebind_subsystems(struct cgroupfs_root *root,
 			      unsigned long final_bits)
 {
@@ -857,16 +915,16 @@ static int cgroup_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	ret = rebind_subsystems(root, opts.subsys_bits);
+	if (ret)
+		goto out_unlock;
 
 	/* (re)populate subsystem files */
-	if (!ret)
-		cgroup_populate_dir(cgrp);
+	cgroup_populate_dir(cgrp);
 
 	if (opts.release_agent)
 		strcpy(root->release_agent_path, opts.release_agent);
  out_unlock:
-	if (opts.release_agent)
-		kfree(opts.release_agent);
+	kfree(opts.release_agent);
 	mutex_unlock(&cgroup_mutex);
 	mutex_unlock(&cgrp->dentry->d_inode->i_mutex);
 	return ret;
@@ -969,15 +1027,13 @@ static int cgroup_get_sb(struct file_system_type *fs_type,
 	/* First find the desired set of subsystems */
 	ret = parse_cgroupfs_options(data, &opts);
 	if (ret) {
-		if (opts.release_agent)
-			kfree(opts.release_agent);
+		kfree(opts.release_agent);
 		return ret;
 	}
 
 	root = kzalloc(sizeof(*root), GFP_KERNEL);
 	if (!root) {
-		if (opts.release_agent)
-			kfree(opts.release_agent);
+		kfree(opts.release_agent);
 		return -ENOMEM;
 	}
 
@@ -1280,6 +1336,12 @@ int cgroup_attach_task(struct cgroup *cgrp, struct task_struct *tsk)
 	set_bit(CGRP_RELEASABLE, &oldcgrp->flags);
 	synchronize_rcu();
 	put_css_set(cg);
+
+	/*
+	 * wake up rmdir() waiter. the rmdir should fail since the cgroup
+	 * is no longer empty.
+	 */
+	cgroup_wakeup_rmdir_waiters(cgrp);
 	return 0;
 }
 
@@ -1625,7 +1687,7 @@ static struct inode_operations cgroup_dir_inode_operations = {
 	.rename = cgroup_rename,
 };
 
-static int cgroup_create_file(struct dentry *dentry, int mode,
+static int cgroup_create_file(struct dentry *dentry, mode_t mode,
 				struct super_block *sb)
 {
 	static const struct dentry_operations cgroup_dops = {
@@ -1671,7 +1733,7 @@ static int cgroup_create_file(struct dentry *dentry, int mode,
  * @mode: mode to set on new directory.
  */
 static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
-				int mode)
+				mode_t mode)
 {
 	struct dentry *parent;
 	int error = 0;
@@ -1689,6 +1751,33 @@ static int cgroup_create_dir(struct cgroup *cgrp, struct dentry *dentry,
 	return error;
 }
 
+/**
+ * cgroup_file_mode - deduce file mode of a control file
+ * @cft: the control file in question
+ *
+ * returns cft->mode if ->mode is not 0
+ * returns S_IRUGO|S_IWUSR if it has both a read and a write handler
+ * returns S_IRUGO if it has only a read handler
+ * returns S_IWUSR if it has only a write hander
+ */
+static mode_t cgroup_file_mode(const struct cftype *cft)
+{
+	mode_t mode = 0;
+
+	if (cft->mode)
+		return cft->mode;
+
+	if (cft->read || cft->read_u64 || cft->read_s64 ||
+	    cft->read_map || cft->read_seq_string)
+		mode |= S_IRUGO;
+
+	if (cft->write || cft->write_u64 || cft->write_s64 ||
+	    cft->write_string || cft->trigger)
+		mode |= S_IWUSR;
+
+	return mode;
+}
+
 int cgroup_add_file(struct cgroup *cgrp,
 		       struct cgroup_subsys *subsys,
 		       const struct cftype *cft)
@@ -1696,6 +1785,7 @@ int cgroup_add_file(struct cgroup *cgrp,
 	struct dentry *dir = cgrp->dentry;
 	struct dentry *dentry;
 	int error;
+	mode_t mode;
 
 	char name[MAX_CGROUP_TYPE_NAMELEN + MAX_CFTYPE_NAME + 2] = { 0 };
 	if (subsys && !test_bit(ROOT_NOPREFIX, &cgrp->root->flags)) {
@@ -1706,7 +1796,8 @@ int cgroup_add_file(struct cgroup *cgrp,
 	BUG_ON(!mutex_is_locked(&dir->d_inode->i_mutex));
 	dentry = lookup_one_len(name, dir, strlen(name));
 	if (!IS_ERR(dentry)) {
-		error = cgroup_create_file(dentry, 0644 | S_IFREG,
+		mode = cgroup_file_mode(cft);
+		error = cgroup_create_file(dentry, mode | S_IFREG,
 						cgrp->root->sb);
 		if (!error)
 			dentry->d_fsdata = (void *)cft;
@@ -2288,6 +2379,7 @@ static struct cftype files[] = {
 		.write_u64 = cgroup_tasks_write,
 		.release = cgroup_tasks_release,
 		.private = FILE_TASKLIST,
+		.mode = S_IRUGO | S_IWUSR,
 	},
 
 	{
@@ -2327,6 +2419,17 @@ static int cgroup_populate_dir(struct cgroup *cgrp)
 		if (ss->populate && (err = ss->populate(ss, cgrp)) < 0)
 			return err;
 	}
+	/* This cgroup is ready now */
+	for_each_subsys(cgrp->root, ss) {
+		struct cgroup_subsys_state *css = cgrp->subsys[ss->subsys_id];
+		/*
+		 * Update id->css pointer and make this css visible from
+		 * CSS ID functions. This pointer will be dereferened
+		 * from RCU-read-side without locks.
+		 */
+		if (css->id)
+			rcu_assign_pointer(css->id->css, css);
+	}
 
 	return 0;
 }
@@ -2338,6 +2441,7 @@ static void init_cgroup_css(struct cgroup_subsys_state *css,
 	css->cgroup = cgrp;
 	atomic_set(&css->refcnt, 1);
 	css->flags = 0;
+	css->id = NULL;
 	if (cgrp == dummytop)
 		set_bit(CSS_ROOT, &css->flags);
 	BUG_ON(cgrp->subsys[ss->subsys_id]);
@@ -2376,7 +2480,7 @@ static void cgroup_unlock_hierarchy(struct cgroupfs_root *root)
  * Must be called with the mutex on the parent inode held
  */
 static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
-			     int mode)
+			     mode_t mode)
 {
 	struct cgroup *cgrp;
 	struct cgroupfs_root *root = parent->root;
@@ -2413,6 +2517,10 @@ static long cgroup_create(struct cgroup *parent, struct dentry *dentry,
 			goto err_destroy;
 		}
 		init_cgroup_css(css, ss, cgrp);
+		if (ss->use_id)
+			if (alloc_css_id(ss, parent, cgrp))
+				goto err_destroy;
+		/* At error, ->destroy() callback has to free assigned ID. */
 	}
 
 	cgroup_lock_hierarchy(root);
@@ -2555,9 +2663,11 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	struct cgroup *cgrp = dentry->d_fsdata;
 	struct dentry *d;
 	struct cgroup *parent;
+	DEFINE_WAIT(wait);
+	int ret;
 
 	/* the vfs holds both inode->i_mutex already */
-
+again:
 	mutex_lock(&cgroup_mutex);
 	if (atomic_read(&cgrp->count) != 0) {
 		mutex_unlock(&cgroup_mutex);
@@ -2573,17 +2683,39 @@ static int cgroup_rmdir(struct inode *unused_dir, struct dentry *dentry)
 	 * Call pre_destroy handlers of subsys. Notify subsystems
 	 * that rmdir() request comes.
 	 */
-	cgroup_call_pre_destroy(cgrp);
+	ret = cgroup_call_pre_destroy(cgrp);
+	if (ret)
+		return ret;
 
 	mutex_lock(&cgroup_mutex);
 	parent = cgrp->parent;
-
-	if (atomic_read(&cgrp->count)
-	    || !list_empty(&cgrp->children)
-	    || !cgroup_clear_css_refs(cgrp)) {
+	if (atomic_read(&cgrp->count) || !list_empty(&cgrp->children)) {
 		mutex_unlock(&cgroup_mutex);
 		return -EBUSY;
 	}
+	/*
+	 * css_put/get is provided for subsys to grab refcnt to css. In typical
+	 * case, subsystem has no reference after pre_destroy(). But, under
+	 * hierarchy management, some *temporal* refcnt can be hold.
+	 * To avoid returning -EBUSY to a user, waitqueue is used. If subsys
+	 * is really busy, it should return -EBUSY at pre_destroy(). wake_up
+	 * is called when css_put() is called and refcnt goes down to 0.
+	 */
+	set_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+	prepare_to_wait(&cgroup_rmdir_waitq, &wait, TASK_INTERRUPTIBLE);
+
+	if (!cgroup_clear_css_refs(cgrp)) {
+		mutex_unlock(&cgroup_mutex);
+		schedule();
+		finish_wait(&cgroup_rmdir_waitq, &wait);
+		clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
+		if (signal_pending(current))
+			return -EINTR;
+		goto again;
+	}
+	/* NO css_tryget() can success after here. */
+	finish_wait(&cgroup_rmdir_waitq, &wait);
+	clear_bit(CGRP_WAIT_ON_RMDIR, &cgrp->flags);
 
 	spin_lock(&release_list_lock);
 	set_bit(CGRP_REMOVED, &cgrp->flags);
@@ -2708,6 +2840,8 @@ int __init cgroup_init(void)
 		struct cgroup_subsys *ss = subsys[i];
 		if (!ss->early_init)
 			cgroup_init_subsys(ss);
+		if (ss->use_id)
+			cgroup_subsys_init_idr(ss);
 	}
 
 	/* Add init_css_set to the hash table */
@@ -3084,18 +3218,19 @@ int cgroup_clone(struct task_struct *tsk, struct cgroup_subsys *subsys,
 }
 
 /**
- * cgroup_is_descendant - see if @cgrp is a descendant of current task's cgrp
+ * cgroup_is_descendant - see if @cgrp is a descendant of @task's cgrp
  * @cgrp: the cgroup in question
+ * @task: the task in question
  *
- * See if @cgrp is a descendant of the current task's cgroup in
- * the appropriate hierarchy.
+ * See if @cgrp is a descendant of @task's cgroup in the appropriate
+ * hierarchy.
  *
  * If we are sending in dummytop, then presumably we are creating
  * the top cgroup in the subsystem.
  *
  * Called only by the ns (nsproxy) cgroup.
  */
-int cgroup_is_descendant(const struct cgroup *cgrp)
+int cgroup_is_descendant(const struct cgroup *cgrp, struct task_struct *task)
 {
 	int ret;
 	struct cgroup *target;
@@ -3105,7 +3240,7 @@ int cgroup_is_descendant(const struct cgroup *cgrp)
 		return 1;
 
 	get_first_subsys(cgrp, NULL, &subsys_id);
-	target = task_cgroup(current, subsys_id);
+	target = task_cgroup(task, subsys_id);
 	while (cgrp != target && cgrp!= cgrp->top_cgroup)
 		cgrp = cgrp->parent;
 	ret = (cgrp == target);
@@ -3138,10 +3273,12 @@ void __css_put(struct cgroup_subsys_state *css)
 {
 	struct cgroup *cgrp = css->cgroup;
 	rcu_read_lock();
-	if ((atomic_dec_return(&css->refcnt) == 1) &&
-	    notify_on_release(cgrp)) {
-		set_bit(CGRP_RELEASABLE, &cgrp->flags);
-		check_for_release(cgrp);
+	if (atomic_dec_return(&css->refcnt) == 1) {
+		if (notify_on_release(cgrp)) {
+			set_bit(CGRP_RELEASABLE, &cgrp->flags);
+			check_for_release(cgrp);
+		}
+		cgroup_wakeup_rmdir_waiters(cgrp);
 	}
 	rcu_read_unlock();
 }
@@ -3241,3 +3378,232 @@ static int __init cgroup_disable(char *str)
 	return 1;
 }
 __setup("cgroup_disable=", cgroup_disable);
+
+/*
+ * Functons for CSS ID.
+ */
+
+/*
+ *To get ID other than 0, this should be called when !cgroup_is_removed().
+ */
+unsigned short css_id(struct cgroup_subsys_state *css)
+{
+	struct css_id *cssid = rcu_dereference(css->id);
+
+	if (cssid)
+		return cssid->id;
+	return 0;
+}
+
+unsigned short css_depth(struct cgroup_subsys_state *css)
+{
+	struct css_id *cssid = rcu_dereference(css->id);
+
+	if (cssid)
+		return cssid->depth;
+	return 0;
+}
+
+bool css_is_ancestor(struct cgroup_subsys_state *child,
+		    const struct cgroup_subsys_state *root)
+{
+	struct css_id *child_id = rcu_dereference(child->id);
+	struct css_id *root_id = rcu_dereference(root->id);
+
+	if (!child_id || !root_id || (child_id->depth < root_id->depth))
+		return false;
+	return child_id->stack[root_id->depth] == root_id->id;
+}
+
+static void __free_css_id_cb(struct rcu_head *head)
+{
+	struct css_id *id;
+
+	id = container_of(head, struct css_id, rcu_head);
+	kfree(id);
+}
+
+void free_css_id(struct cgroup_subsys *ss, struct cgroup_subsys_state *css)
+{
+	struct css_id *id = css->id;
+	/* When this is called before css_id initialization, id can be NULL */
+	if (!id)
+		return;
+
+	BUG_ON(!ss->use_id);
+
+	rcu_assign_pointer(id->css, NULL);
+	rcu_assign_pointer(css->id, NULL);
+	spin_lock(&ss->id_lock);
+	idr_remove(&ss->idr, id->id);
+	spin_unlock(&ss->id_lock);
+	call_rcu(&id->rcu_head, __free_css_id_cb);
+}
+
+/*
+ * This is called by init or create(). Then, calls to this function are
+ * always serialized (By cgroup_mutex() at create()).
+ */
+
+static struct css_id *get_new_cssid(struct cgroup_subsys *ss, int depth)
+{
+	struct css_id *newid;
+	int myid, error, size;
+
+	BUG_ON(!ss->use_id);
+
+	size = sizeof(*newid) + sizeof(unsigned short) * (depth + 1);
+	newid = kzalloc(size, GFP_KERNEL);
+	if (!newid)
+		return ERR_PTR(-ENOMEM);
+	/* get id */
+	if (unlikely(!idr_pre_get(&ss->idr, GFP_KERNEL))) {
+		error = -ENOMEM;
+		goto err_out;
+	}
+	spin_lock(&ss->id_lock);
+	/* Don't use 0. allocates an ID of 1-65535 */
+	error = idr_get_new_above(&ss->idr, newid, 1, &myid);
+	spin_unlock(&ss->id_lock);
+
+	/* Returns error when there are no free spaces for new ID.*/
+	if (error) {
+		error = -ENOSPC;
+		goto err_out;
+	}
+	if (myid > CSS_ID_MAX)
+		goto remove_idr;
+
+	newid->id = myid;
+	newid->depth = depth;
+	return newid;
+remove_idr:
+	error = -ENOSPC;
+	spin_lock(&ss->id_lock);
+	idr_remove(&ss->idr, myid);
+	spin_unlock(&ss->id_lock);
+err_out:
+	kfree(newid);
+	return ERR_PTR(error);
+
+}
+
+static int __init cgroup_subsys_init_idr(struct cgroup_subsys *ss)
+{
+	struct css_id *newid;
+	struct cgroup_subsys_state *rootcss;
+
+	spin_lock_init(&ss->id_lock);
+	idr_init(&ss->idr);
+
+	rootcss = init_css_set.subsys[ss->subsys_id];
+	newid = get_new_cssid(ss, 0);
+	if (IS_ERR(newid))
+		return PTR_ERR(newid);
+
+	newid->stack[0] = newid->id;
+	newid->css = rootcss;
+	rootcss->id = newid;
+	return 0;
+}
+
+static int alloc_css_id(struct cgroup_subsys *ss, struct cgroup *parent,
+			struct cgroup *child)
+{
+	int subsys_id, i, depth = 0;
+	struct cgroup_subsys_state *parent_css, *child_css;
+	struct css_id *child_id, *parent_id = NULL;
+
+	subsys_id = ss->subsys_id;
+	parent_css = parent->subsys[subsys_id];
+	child_css = child->subsys[subsys_id];
+	depth = css_depth(parent_css) + 1;
+	parent_id = parent_css->id;
+
+	child_id = get_new_cssid(ss, depth);
+	if (IS_ERR(child_id))
+		return PTR_ERR(child_id);
+
+	for (i = 0; i < depth; i++)
+		child_id->stack[i] = parent_id->stack[i];
+	child_id->stack[depth] = child_id->id;
+	/*
+	 * child_id->css pointer will be set after this cgroup is available
+	 * see cgroup_populate_dir()
+	 */
+	rcu_assign_pointer(child_css->id, child_id);
+
+	return 0;
+}
+
+/**
+ * css_lookup - lookup css by id
+ * @ss: cgroup subsys to be looked into.
+ * @id: the id
+ *
+ * Returns pointer to cgroup_subsys_state if there is valid one with id.
+ * NULL if not. Should be called under rcu_read_lock()
+ */
+struct cgroup_subsys_state *css_lookup(struct cgroup_subsys *ss, int id)
+{
+	struct css_id *cssid = NULL;
+
+	BUG_ON(!ss->use_id);
+	cssid = idr_find(&ss->idr, id);
+
+	if (unlikely(!cssid))
+		return NULL;
+
+	return rcu_dereference(cssid->css);
+}
+
+/**
+ * css_get_next - lookup next cgroup under specified hierarchy.
+ * @ss: pointer to subsystem
+ * @id: current position of iteration.
+ * @root: pointer to css. search tree under this.
+ * @foundid: position of found object.
+ *
+ * Search next css under the specified hierarchy of rootid. Calling under
+ * rcu_read_lock() is necessary. Returns NULL if it reaches the end.
+ */
+struct cgroup_subsys_state *
+css_get_next(struct cgroup_subsys *ss, int id,
+	     struct cgroup_subsys_state *root, int *foundid)
+{
+	struct cgroup_subsys_state *ret = NULL;
+	struct css_id *tmp;
+	int tmpid;
+	int rootid = css_id(root);
+	int depth = css_depth(root);
+
+	if (!rootid)
+		return NULL;
+
+	BUG_ON(!ss->use_id);
+	/* fill start point for scan */
+	tmpid = id;
+	while (1) {
+		/*
+		 * scan next entry from bitmap(tree), tmpid is updated after
+		 * idr_get_next().
+		 */
+		spin_lock(&ss->id_lock);
+		tmp = idr_get_next(&ss->idr, &tmpid);
+		spin_unlock(&ss->id_lock);
+
+		if (!tmp)
+			break;
+		if (tmp->depth >= depth && tmp->stack[depth] == rootid) {
+			ret = rcu_dereference(tmp->css);
+			if (ret) {
+				*foundid = tmpid;
+				break;
+			}
+		}
+		/* continue to scan from next id */
+		tmpid = tmpid + 1;
+	}
+	return ret;
+}
+
diff --git a/kernel/cgroup_debug.c b/kernel/cgroup_debug.c
index daca6209202d..0c92d797baa6 100644
--- a/kernel/cgroup_debug.c
+++ b/kernel/cgroup_debug.c
@@ -40,9 +40,7 @@ static u64 taskcount_read(struct cgroup *cont, struct cftype *cft)
 {
 	u64 count;
 
-	cgroup_lock();
 	count = cgroup_task_count(cont);
-	cgroup_unlock();
 	return count;
 }
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index f76db9dcaa05..026faccca869 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -128,10 +128,6 @@ static inline struct cpuset *task_cs(struct task_struct *task)
 	return container_of(task_subsys_state(task, cpuset_subsys_id),
 			    struct cpuset, css);
 }
-struct cpuset_hotplug_scanner {
-	struct cgroup_scanner scan;
-	struct cgroup *to;
-};
 
 /* bits in struct cpuset flags field */
 typedef enum {
@@ -521,6 +517,7 @@ static int validate_change(const struct cpuset *cur, const struct cpuset *trial)
 	return 0;
 }
 
+#ifdef CONFIG_SMP
 /*
  * Helper routine for generate_sched_domains().
  * Do cpusets a, b have overlapping cpus_allowed masks?
@@ -815,6 +812,18 @@ static void do_rebuild_sched_domains(struct work_struct *unused)
 
 	put_online_cpus();
 }
+#else /* !CONFIG_SMP */
+static void do_rebuild_sched_domains(struct work_struct *unused)
+{
+}
+
+static int generate_sched_domains(struct cpumask **domains,
+			struct sched_domain_attr **attributes)
+{
+	*domains = NULL;
+	return 1;
+}
+#endif /* CONFIG_SMP */
 
 static DECLARE_WORK(rebuild_sched_domains_work, do_rebuild_sched_domains);
 
@@ -1026,101 +1035,70 @@ static void cpuset_migrate_mm(struct mm_struct *mm, const nodemask_t *from,
 	mutex_unlock(&callback_mutex);
 }
 
+/*
+ * Rebind task's vmas to cpuset's new mems_allowed, and migrate pages to new
+ * nodes if memory_migrate flag is set. Called with cgroup_mutex held.
+ */
+static void cpuset_change_nodemask(struct task_struct *p,
+				   struct cgroup_scanner *scan)
+{
+	struct mm_struct *mm;
+	struct cpuset *cs;
+	int migrate;
+	const nodemask_t *oldmem = scan->data;
+
+	mm = get_task_mm(p);
+	if (!mm)
+		return;
+
+	cs = cgroup_cs(scan->cg);
+	migrate = is_memory_migrate(cs);
+
+	mpol_rebind_mm(mm, &cs->mems_allowed);
+	if (migrate)
+		cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
+	mmput(mm);
+}
+
 static void *cpuset_being_rebound;
 
 /**
  * update_tasks_nodemask - Update the nodemasks of tasks in the cpuset.
  * @cs: the cpuset in which each task's mems_allowed mask needs to be changed
  * @oldmem: old mems_allowed of cpuset cs
+ * @heap: if NULL, defer allocating heap memory to cgroup_scan_tasks()
  *
  * Called with cgroup_mutex held
- * Return 0 if successful, -errno if not.
+ * No return value. It's guaranteed that cgroup_scan_tasks() always returns 0
+ * if @heap != NULL.
  */
-static int update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem)
+static void update_tasks_nodemask(struct cpuset *cs, const nodemask_t *oldmem,
+				 struct ptr_heap *heap)
 {
-	struct task_struct *p;
-	struct mm_struct **mmarray;
-	int i, n, ntasks;
-	int migrate;
-	int fudge;
-	struct cgroup_iter it;
-	int retval;
+	struct cgroup_scanner scan;
 
 	cpuset_being_rebound = cs;		/* causes mpol_dup() rebind */
 
-	fudge = 10;				/* spare mmarray[] slots */
-	fudge += cpumask_weight(cs->cpus_allowed);/* imagine 1 fork-bomb/cpu */
-	retval = -ENOMEM;
-
-	/*
-	 * Allocate mmarray[] to hold mm reference for each task
-	 * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
-	 * tasklist_lock.  We could use GFP_ATOMIC, but with a
-	 * few more lines of code, we can retry until we get a big
-	 * enough mmarray[] w/o using GFP_ATOMIC.
-	 */
-	while (1) {
-		ntasks = cgroup_task_count(cs->css.cgroup);  /* guess */
-		ntasks += fudge;
-		mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
-		if (!mmarray)
-			goto done;
-		read_lock(&tasklist_lock);		/* block fork */
-		if (cgroup_task_count(cs->css.cgroup) <= ntasks)
-			break;				/* got enough */
-		read_unlock(&tasklist_lock);		/* try again */
-		kfree(mmarray);
-	}
-
-	n = 0;
-
-	/* Load up mmarray[] with mm reference for each task in cpuset. */
-	cgroup_iter_start(cs->css.cgroup, &it);
-	while ((p = cgroup_iter_next(cs->css.cgroup, &it))) {
-		struct mm_struct *mm;
-
-		if (n >= ntasks) {
-			printk(KERN_WARNING
-				"Cpuset mempolicy rebind incomplete.\n");
-			break;
-		}
-		mm = get_task_mm(p);
-		if (!mm)
-			continue;
-		mmarray[n++] = mm;
-	}
-	cgroup_iter_end(cs->css.cgroup, &it);
-	read_unlock(&tasklist_lock);
+	scan.cg = cs->css.cgroup;
+	scan.test_task = NULL;
+	scan.process_task = cpuset_change_nodemask;
+	scan.heap = heap;
+	scan.data = (nodemask_t *)oldmem;
 
 	/*
-	 * Now that we've dropped the tasklist spinlock, we can
-	 * rebind the vma mempolicies of each mm in mmarray[] to their
-	 * new cpuset, and release that mm.  The mpol_rebind_mm()
-	 * call takes mmap_sem, which we couldn't take while holding
-	 * tasklist_lock.  Forks can happen again now - the mpol_dup()
-	 * cpuset_being_rebound check will catch such forks, and rebind
-	 * their vma mempolicies too.  Because we still hold the global
-	 * cgroup_mutex, we know that no other rebind effort will
-	 * be contending for the global variable cpuset_being_rebound.
+	 * The mpol_rebind_mm() call takes mmap_sem, which we couldn't
+	 * take while holding tasklist_lock.  Forks can happen - the
+	 * mpol_dup() cpuset_being_rebound check will catch such forks,
+	 * and rebind their vma mempolicies too.  Because we still hold
+	 * the global cgroup_mutex, we know that no other rebind effort
+	 * will be contending for the global variable cpuset_being_rebound.
 	 * It's ok if we rebind the same mm twice; mpol_rebind_mm()
 	 * is idempotent.  Also migrate pages in each mm to new nodes.
 	 */
-	migrate = is_memory_migrate(cs);
-	for (i = 0; i < n; i++) {
-		struct mm_struct *mm = mmarray[i];
-
-		mpol_rebind_mm(mm, &cs->mems_allowed);
-		if (migrate)
-			cpuset_migrate_mm(mm, oldmem, &cs->mems_allowed);
-		mmput(mm);
-	}
+	cgroup_scan_tasks(&scan);
 
 	/* We're done rebinding vmas to this cpuset's new mems_allowed. */
-	kfree(mmarray);
 	cpuset_being_rebound = NULL;
-	retval = 0;
-done:
-	return retval;
 }
 
 /*
@@ -1141,6 +1119,7 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 {
 	nodemask_t oldmem;
 	int retval;
+	struct ptr_heap heap;
 
 	/*
 	 * top_cpuset.mems_allowed tracks node_stats[N_HIGH_MEMORY];
@@ -1175,12 +1154,18 @@ static int update_nodemask(struct cpuset *cs, struct cpuset *trialcs,
 	if (retval < 0)
 		goto done;
 
+	retval = heap_init(&heap, PAGE_SIZE, GFP_KERNEL, NULL);
+	if (retval < 0)
+		goto done;
+
 	mutex_lock(&callback_mutex);
 	cs->mems_allowed = trialcs->mems_allowed;
 	cs->mems_generation = cpuset_mems_generation++;
 	mutex_unlock(&callback_mutex);
 
-	retval = update_tasks_nodemask(cs, &oldmem);
+	update_tasks_nodemask(cs, &oldmem, &heap);
+
+	heap_free(&heap);
 done:
 	return retval;
 }
@@ -1192,8 +1177,10 @@ int current_cpuset_is_being_rebound(void)
 
 static int update_relax_domain_level(struct cpuset *cs, s64 val)
 {
+#ifdef CONFIG_SMP
 	if (val < -1 || val >= SD_LV_MAX)
 		return -EINVAL;
+#endif
 
 	if (val != cs->relax_domain_level) {
 		cs->relax_domain_level = val;
@@ -1355,19 +1342,22 @@ static int cpuset_can_attach(struct cgroup_subsys *ss,
 			     struct cgroup *cont, struct task_struct *tsk)
 {
 	struct cpuset *cs = cgroup_cs(cont);
-	int ret = 0;
 
 	if (cpumask_empty(cs->cpus_allowed) || nodes_empty(cs->mems_allowed))
 		return -ENOSPC;
 
-	if (tsk->flags & PF_THREAD_BOUND) {
-		mutex_lock(&callback_mutex);
-		if (!cpumask_equal(&tsk->cpus_allowed, cs->cpus_allowed))
-			ret = -EINVAL;
-		mutex_unlock(&callback_mutex);
-	}
+	/*
+	 * Kthreads bound to specific cpus cannot be moved to a new cpuset; we
+	 * cannot change their cpu affinity and isolating such threads by their
+	 * set of allowed nodes is unnecessary.  Thus, cpusets are not
+	 * applicable for such threads.  This prevents checking for success of
+	 * set_cpus_allowed_ptr() on all attached tasks before cpus_allowed may
+	 * be changed.
+	 */
+	if (tsk->flags & PF_THREAD_BOUND)
+		return -EINVAL;
 
-	return ret < 0 ? ret : security_task_setscheduler(tsk, 0, NULL);
+	return security_task_setscheduler(tsk, 0, NULL);
 }
 
 static void cpuset_attach(struct cgroup_subsys *ss,
@@ -1706,6 +1696,7 @@ static struct cftype files[] = {
 		.read_u64 = cpuset_read_u64,
 		.write_u64 = cpuset_write_u64,
 		.private = FILE_MEMORY_PRESSURE,
+		.mode = S_IRUGO,
 	},
 
 	{
@@ -1913,10 +1904,9 @@ int __init cpuset_init(void)
 static void cpuset_do_move_task(struct task_struct *tsk,
 				struct cgroup_scanner *scan)
 {
-	struct cpuset_hotplug_scanner *chsp;
+	struct cgroup *new_cgroup = scan->data;
 
-	chsp = container_of(scan, struct cpuset_hotplug_scanner, scan);
-	cgroup_attach_task(chsp->to, tsk);
+	cgroup_attach_task(new_cgroup, tsk);
 }
 
 /**
@@ -1932,15 +1922,15 @@ static void cpuset_do_move_task(struct task_struct *tsk,
  */
 static void move_member_tasks_to_cpuset(struct cpuset *from, struct cpuset *to)
 {
-	struct cpuset_hotplug_scanner scan;
+	struct cgroup_scanner scan;
 
-	scan.scan.cg = from->css.cgroup;
-	scan.scan.test_task = NULL; /* select all tasks in cgroup */
-	scan.scan.process_task = cpuset_do_move_task;
-	scan.scan.heap = NULL;
-	scan.to = to->css.cgroup;
+	scan.cg = from->css.cgroup;
+	scan.test_task = NULL; /* select all tasks in cgroup */
+	scan.process_task = cpuset_do_move_task;
+	scan.heap = NULL;
+	scan.data = to->css.cgroup;
 
-	if (cgroup_scan_tasks(&scan.scan))
+	if (cgroup_scan_tasks(&scan))
 		printk(KERN_ERR "move_member_tasks_to_cpuset: "
 				"cgroup_scan_tasks failed\n");
 }
@@ -2033,7 +2023,7 @@ static void scan_for_empty_cpusets(struct cpuset *root)
 			remove_tasks_in_empty_cpuset(cp);
 		else {
 			update_tasks_cpumask(cp, NULL);
-			update_tasks_nodemask(cp, &oldmems);
+			update_tasks_nodemask(cp, &oldmems, NULL);
 		}
 	}
 }
@@ -2069,7 +2059,9 @@ static int cpuset_track_online_cpus(struct notifier_block *unused_nb,
 	}
 
 	cgroup_lock();
+	mutex_lock(&callback_mutex);
 	cpumask_copy(top_cpuset.cpus_allowed, cpu_online_mask);
+	mutex_unlock(&callback_mutex);
 	scan_for_empty_cpusets(&top_cpuset);
 	ndoms = generate_sched_domains(&doms, &attr);
 	cgroup_unlock();
@@ -2092,11 +2084,12 @@ static int cpuset_track_online_nodes(struct notifier_block *self,
 	cgroup_lock();
 	switch (action) {
 	case MEM_ONLINE:
-		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-		break;
 	case MEM_OFFLINE:
+		mutex_lock(&callback_mutex);
 		top_cpuset.mems_allowed = node_states[N_HIGH_MEMORY];
-		scan_for_empty_cpusets(&top_cpuset);
+		mutex_unlock(&callback_mutex);
+		if (action == MEM_OFFLINE)
+			scan_for_empty_cpusets(&top_cpuset);
 		break;
 	default:
 		break;
@@ -2206,26 +2199,24 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs)
 }
 
 /**
- * cpuset_zone_allowed_softwall - Can we allocate on zone z's memory node?
- * @z: is this zone on an allowed node?
+ * cpuset_node_allowed_softwall - Can we allocate on a memory node?
+ * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
- * If we're in interrupt, yes, we can always allocate.  If
- * __GFP_THISNODE is set, yes, we can always allocate.  If zone
- * z's node is in our tasks mems_allowed, yes.  If it's not a
- * __GFP_HARDWALL request and this zone's nodes is in the nearest
- * hardwalled cpuset ancestor to this tasks cpuset, yes.
- * If the task has been OOM killed and has access to memory reserves
- * as specified by the TIF_MEMDIE flag, yes.
+ * If we're in interrupt, yes, we can always allocate.  If __GFP_THISNODE is
+ * set, yes, we can always allocate.  If node is in our task's mems_allowed,
+ * yes.  If it's not a __GFP_HARDWALL request and this node is in the nearest
+ * hardwalled cpuset ancestor to this task's cpuset, yes.  If the task has been
+ * OOM killed and has access to memory reserves as specified by the TIF_MEMDIE
+ * flag, yes.
  * Otherwise, no.
  *
- * If __GFP_HARDWALL is set, cpuset_zone_allowed_softwall()
- * reduces to cpuset_zone_allowed_hardwall().  Otherwise,
- * cpuset_zone_allowed_softwall() might sleep, and might allow a zone
- * from an enclosing cpuset.
+ * If __GFP_HARDWALL is set, cpuset_node_allowed_softwall() reduces to
+ * cpuset_node_allowed_hardwall().  Otherwise, cpuset_node_allowed_softwall()
+ * might sleep, and might allow a node from an enclosing cpuset.
  *
- * cpuset_zone_allowed_hardwall() only handles the simpler case of
- * hardwall cpusets, and never sleeps.
+ * cpuset_node_allowed_hardwall() only handles the simpler case of hardwall
+ * cpusets, and never sleeps.
  *
  * The __GFP_THISNODE placement logic is really handled elsewhere,
  * by forcibly using a zonelist starting at a specified node, and by
@@ -2264,20 +2255,17 @@ static const struct cpuset *nearest_hardwall_ancestor(const struct cpuset *cs)
  *	GFP_USER     - only nodes in current tasks mems allowed ok.
  *
  * Rule:
- *    Don't call cpuset_zone_allowed_softwall if you can't sleep, unless you
+ *    Don't call cpuset_node_allowed_softwall if you can't sleep, unless you
  *    pass in the __GFP_HARDWALL flag set in gfp_flag, which disables
  *    the code that might scan up ancestor cpusets and sleep.
  */
-
-int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
+int __cpuset_node_allowed_softwall(int node, gfp_t gfp_mask)
 {
-	int node;			/* node that zone z is on */
 	const struct cpuset *cs;	/* current cpuset ancestors */
 	int allowed;			/* is allocation in zone z allowed? */
 
 	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
 		return 1;
-	node = zone_to_nid(z);
 	might_sleep_if(!(gfp_mask & __GFP_HARDWALL));
 	if (node_isset(node, current->mems_allowed))
 		return 1;
@@ -2306,15 +2294,15 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
 }
 
 /*
- * cpuset_zone_allowed_hardwall - Can we allocate on zone z's memory node?
- * @z: is this zone on an allowed node?
+ * cpuset_node_allowed_hardwall - Can we allocate on a memory node?
+ * @node: is this an allowed node?
  * @gfp_mask: memory allocation flags
  *
- * If we're in interrupt, yes, we can always allocate.
- * If __GFP_THISNODE is set, yes, we can always allocate.  If zone
- * z's node is in our tasks mems_allowed, yes.   If the task has been
- * OOM killed and has access to memory reserves as specified by the
- * TIF_MEMDIE flag, yes.  Otherwise, no.
+ * If we're in interrupt, yes, we can always allocate.  If __GFP_THISNODE is
+ * set, yes, we can always allocate.  If node is in our task's mems_allowed,
+ * yes.  If the task has been OOM killed and has access to memory reserves as
+ * specified by the TIF_MEMDIE flag, yes.
+ * Otherwise, no.
  *
  * The __GFP_THISNODE placement logic is really handled elsewhere,
  * by forcibly using a zonelist starting at a specified node, and by
@@ -2322,20 +2310,16 @@ int __cpuset_zone_allowed_softwall(struct zone *z, gfp_t gfp_mask)
  * any node on the zonelist except the first.  By the time any such
  * calls get to this routine, we should just shut up and say 'yes'.
  *
- * Unlike the cpuset_zone_allowed_softwall() variant, above,
- * this variant requires that the zone be in the current tasks
+ * Unlike the cpuset_node_allowed_softwall() variant, above,
+ * this variant requires that the node be in the current task's
  * mems_allowed or that we're in interrupt.  It does not scan up the
  * cpuset hierarchy for the nearest enclosing mem_exclusive cpuset.
  * It never sleeps.
  */
-
-int __cpuset_zone_allowed_hardwall(struct zone *z, gfp_t gfp_mask)
+int __cpuset_node_allowed_hardwall(int node, gfp_t gfp_mask)
 {
-	int node;			/* node that zone z is on */
-
 	if (in_interrupt() || (gfp_mask & __GFP_THISNODE))
 		return 1;
-	node = zone_to_nid(z);
 	if (node_isset(node, current->mems_allowed))
 		return 1;
 	/*
diff --git a/kernel/exec_domain.c b/kernel/exec_domain.c
index 667c841c2952..c35452cadded 100644
--- a/kernel/exec_domain.c
+++ b/kernel/exec_domain.c
@@ -18,6 +18,7 @@
 #include <linux/syscalls.h>
 #include <linux/sysctl.h>
 #include <linux/types.h>
+#include <linux/fs_struct.h>
 
 
 static void default_handler(int, struct pt_regs *);
@@ -145,28 +146,6 @@ __set_personality(u_long personality)
 		return 0;
 	}
 
-	if (atomic_read(&current->fs->count) != 1) {
-		struct fs_struct *fsp, *ofsp;
-
-		fsp = copy_fs_struct(current->fs);
-		if (fsp == NULL) {
-			module_put(ep->module);
-			return -ENOMEM;
-		}
-
-		task_lock(current);
-		ofsp = current->fs;
-		current->fs = fsp;
-		task_unlock(current);
-
-		put_fs_struct(ofsp);
-	}
-
-	/*
-	 * At that point we are guaranteed to be the sole owner of
-	 * current->fs.
-	 */
-
 	current->personality = personality;
 	oep = current_thread_info()->exec_domain;
 	current_thread_info()->exec_domain = ep;
diff --git a/kernel/exit.c b/kernel/exit.c
index 167e1e3ad7c6..6686ed1e4aa3 100644
--- a/kernel/exit.c
+++ b/kernel/exit.c
@@ -46,6 +46,7 @@
 #include <linux/blkdev.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/tracehook.h>
+#include <linux/fs_struct.h>
 #include <linux/init_task.h>
 #include <trace/sched.h>
 
@@ -61,11 +62,6 @@ DEFINE_TRACE(sched_process_wait);
 
 static void exit_mm(struct task_struct * tsk);
 
-static inline int task_detached(struct task_struct *p)
-{
-	return p->exit_signal == -1;
-}
-
 static void __unhash_process(struct task_struct *p)
 {
 	nr_threads--;
@@ -362,16 +358,12 @@ static void reparent_to_kthreadd(void)
 void __set_special_pids(struct pid *pid)
 {
 	struct task_struct *curr = current->group_leader;
-	pid_t nr = pid_nr(pid);
 
-	if (task_session(curr) != pid) {
+	if (task_session(curr) != pid)
 		change_pid(curr, PIDTYPE_SID, pid);
-		set_task_session(curr, nr);
-	}
-	if (task_pgrp(curr) != pid) {
+
+	if (task_pgrp(curr) != pid)
 		change_pid(curr, PIDTYPE_PGID, pid);
-		set_task_pgrp(curr, nr);
-	}
 }
 
 static void set_special_pids(struct pid *pid)
@@ -429,7 +421,6 @@ EXPORT_SYMBOL(disallow_signal);
 void daemonize(const char *name, ...)
 {
 	va_list args;
-	struct fs_struct *fs;
 	sigset_t blocked;
 
 	va_start(args, name);
@@ -462,11 +453,7 @@ void daemonize(const char *name, ...)
 
 	/* Become as one with the init task */
 
-	exit_fs(current);	/* current->fs->count--; */
-	fs = init_task.fs;
-	current->fs = fs;
-	atomic_inc(&fs->count);
-
+	daemonize_fs_struct();
 	exit_files(current);
 	current->files = init_task.files;
 	atomic_inc(&current->files->count);
@@ -565,30 +552,6 @@ void exit_files(struct task_struct *tsk)
 	}
 }
 
-void put_fs_struct(struct fs_struct *fs)
-{
-	/* No need to hold fs->lock if we are killing it */
-	if (atomic_dec_and_test(&fs->count)) {
-		path_put(&fs->root);
-		path_put(&fs->pwd);
-		kmem_cache_free(fs_cachep, fs);
-	}
-}
-
-void exit_fs(struct task_struct *tsk)
-{
-	struct fs_struct * fs = tsk->fs;
-
-	if (fs) {
-		task_lock(tsk);
-		tsk->fs = NULL;
-		task_unlock(tsk);
-		put_fs_struct(fs);
-	}
-}
-
-EXPORT_SYMBOL_GPL(exit_fs);
-
 #ifdef CONFIG_MM_OWNER
 /*
  * Task p is exiting and it owned mm, lets find a new owner for it
@@ -732,119 +695,6 @@ static void exit_mm(struct task_struct * tsk)
 }
 
 /*
- * Return nonzero if @parent's children should reap themselves.
- *
- * Called with write_lock_irq(&tasklist_lock) held.
- */
-static int ignoring_children(struct task_struct *parent)
-{
-	int ret;
-	struct sighand_struct *psig = parent->sighand;
-	unsigned long flags;
-	spin_lock_irqsave(&psig->siglock, flags);
-	ret = (psig->action[SIGCHLD-1].sa.sa_handler == SIG_IGN ||
-	       (psig->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT));
-	spin_unlock_irqrestore(&psig->siglock, flags);
-	return ret;
-}
-
-/*
- * Detach all tasks we were using ptrace on.
- * Any that need to be release_task'd are put on the @dead list.
- *
- * Called with write_lock(&tasklist_lock) held.
- */
-static void ptrace_exit(struct task_struct *parent, struct list_head *dead)
-{
-	struct task_struct *p, *n;
-	int ign = -1;
-
-	list_for_each_entry_safe(p, n, &parent->ptraced, ptrace_entry) {
-		__ptrace_unlink(p);
-
-		if (p->exit_state != EXIT_ZOMBIE)
-			continue;
-
-		/*
-		 * If it's a zombie, our attachedness prevented normal
-		 * parent notification or self-reaping.  Do notification
-		 * now if it would have happened earlier.  If it should
-		 * reap itself, add it to the @dead list.  We can't call
-		 * release_task() here because we already hold tasklist_lock.
-		 *
-		 * If it's our own child, there is no notification to do.
-		 * But if our normal children self-reap, then this child
-		 * was prevented by ptrace and we must reap it now.
-		 */
-		if (!task_detached(p) && thread_group_empty(p)) {
-			if (!same_thread_group(p->real_parent, parent))
-				do_notify_parent(p, p->exit_signal);
-			else {
-				if (ign < 0)
-					ign = ignoring_children(parent);
-				if (ign)
-					p->exit_signal = -1;
-			}
-		}
-
-		if (task_detached(p)) {
-			/*
-			 * Mark it as in the process of being reaped.
-			 */
-			p->exit_state = EXIT_DEAD;
-			list_add(&p->ptrace_entry, dead);
-		}
-	}
-}
-
-/*
- * Finish up exit-time ptrace cleanup.
- *
- * Called without locks.
- */
-static void ptrace_exit_finish(struct task_struct *parent,
-			       struct list_head *dead)
-{
-	struct task_struct *p, *n;
-
-	BUG_ON(!list_empty(&parent->ptraced));
-
-	list_for_each_entry_safe(p, n, dead, ptrace_entry) {
-		list_del_init(&p->ptrace_entry);
-		release_task(p);
-	}
-}
-
-static void reparent_thread(struct task_struct *p, struct task_struct *father)
-{
-	if (p->pdeath_signal)
-		/* We already hold the tasklist_lock here.  */
-		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
-
-	list_move_tail(&p->sibling, &p->real_parent->children);
-
-	/* If this is a threaded reparent there is no need to
-	 * notify anyone anything has happened.
-	 */
-	if (same_thread_group(p->real_parent, father))
-		return;
-
-	/* We don't want people slaying init.  */
-	if (!task_detached(p))
-		p->exit_signal = SIGCHLD;
-
-	/* If we'd notified the old parent about this child's death,
-	 * also notify the new parent.
-	 */
-	if (!ptrace_reparented(p) &&
-	    p->exit_state == EXIT_ZOMBIE &&
-	    !task_detached(p) && thread_group_empty(p))
-		do_notify_parent(p, p->exit_signal);
-
-	kill_orphaned_pgrp(p, father);
-}
-
-/*
  * When we die, we re-parent all our children.
  * Try to give them to another thread in our thread
  * group, and if no such member exists, give it to
@@ -883,17 +733,51 @@ static struct task_struct *find_new_reaper(struct task_struct *father)
 	return pid_ns->child_reaper;
 }
 
+/*
+* Any that need to be release_task'd are put on the @dead list.
+ */
+static void reparent_thread(struct task_struct *father, struct task_struct *p,
+				struct list_head *dead)
+{
+	if (p->pdeath_signal)
+		group_send_sig_info(p->pdeath_signal, SEND_SIG_NOINFO, p);
+
+	list_move_tail(&p->sibling, &p->real_parent->children);
+
+	if (task_detached(p))
+		return;
+	/*
+	 * If this is a threaded reparent there is no need to
+	 * notify anyone anything has happened.
+	 */
+	if (same_thread_group(p->real_parent, father))
+		return;
+
+	/* We don't want people slaying init.  */
+	p->exit_signal = SIGCHLD;
+
+	/* If it has exited notify the new parent about this child's death. */
+	if (!p->ptrace &&
+	    p->exit_state == EXIT_ZOMBIE && thread_group_empty(p)) {
+		do_notify_parent(p, p->exit_signal);
+		if (task_detached(p)) {
+			p->exit_state = EXIT_DEAD;
+			list_move_tail(&p->sibling, dead);
+		}
+	}
+
+	kill_orphaned_pgrp(p, father);
+}
+
 static void forget_original_parent(struct task_struct *father)
 {
 	struct task_struct *p, *n, *reaper;
-	LIST_HEAD(ptrace_dead);
+	LIST_HEAD(dead_children);
+
+	exit_ptrace(father);
 
 	write_lock_irq(&tasklist_lock);
 	reaper = find_new_reaper(father);
-	/*
-	 * First clean up ptrace if we were using it.
-	 */
-	ptrace_exit(father, &ptrace_dead);
 
 	list_for_each_entry_safe(p, n, &father->children, sibling) {
 		p->real_parent = reaper;
@@ -901,13 +785,16 @@ static void forget_original_parent(struct task_struct *father)
 			BUG_ON(p->ptrace);
 			p->parent = p->real_parent;
 		}
-		reparent_thread(p, father);
+		reparent_thread(father, p, &dead_children);
 	}
-
 	write_unlock_irq(&tasklist_lock);
+
 	BUG_ON(!list_empty(&father->children));
 
-	ptrace_exit_finish(father, &ptrace_dead);
+	list_for_each_entry_safe(p, n, &dead_children, sibling) {
+		list_del_init(&p->sibling);
+		release_task(p);
+	}
 }
 
 /*
@@ -1417,6 +1304,18 @@ static int wait_task_zombie(struct task_struct *p, int options,
 	return retval;
 }
 
+static int *task_stopped_code(struct task_struct *p, bool ptrace)
+{
+	if (ptrace) {
+		if (task_is_stopped_or_traced(p))
+			return &p->exit_code;
+	} else {
+		if (p->signal->flags & SIGNAL_STOP_STOPPED)
+			return &p->signal->group_exit_code;
+	}
+	return NULL;
+}
+
 /*
  * Handle sys_wait4 work for one task in state TASK_STOPPED.  We hold
  * read_lock(&tasklist_lock) on entry.  If we return zero, we still hold
@@ -1427,7 +1326,7 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
 			     int options, struct siginfo __user *infop,
 			     int __user *stat_addr, struct rusage __user *ru)
 {
-	int retval, exit_code, why;
+	int retval, exit_code, *p_code, why;
 	uid_t uid = 0; /* unneeded, required by compiler */
 	pid_t pid;
 
@@ -1437,22 +1336,16 @@ static int wait_task_stopped(int ptrace, struct task_struct *p,
 	exit_code = 0;
 	spin_lock_irq(&p->sighand->siglock);
 
-	if (unlikely(!task_is_stopped_or_traced(p)))
-		goto unlock_sig;
-
-	if (!ptrace && p->signal->group_stop_count > 0)
-		/*
-		 * A group stop is in progress and this is the group leader.
-		 * We won't report until all threads have stopped.
-		 */
+	p_code = task_stopped_code(p, ptrace);
+	if (unlikely(!p_code))
 		goto unlock_sig;
 
-	exit_code = p->exit_code;
+	exit_code = *p_code;
 	if (!exit_code)
 		goto unlock_sig;
 
 	if (!unlikely(options & WNOWAIT))
-		p->exit_code = 0;
+		*p_code = 0;
 
 	/* don't need the RCU readlock here as we're holding a spinlock */
 	uid = __task_cred(p)->uid;
@@ -1608,7 +1501,7 @@ static int wait_consider_task(struct task_struct *parent, int ptrace,
 	 */
 	*notask_error = 0;
 
-	if (task_is_stopped_or_traced(p))
+	if (task_stopped_code(p, ptrace))
 		return wait_task_stopped(ptrace, p, options,
 					 infop, stat_addr, ru);
 
@@ -1812,7 +1705,7 @@ SYSCALL_DEFINE4(wait4, pid_t, upid, int __user *, stat_addr,
 		pid = find_get_pid(-upid);
 	} else if (upid == 0) {
 		type = PIDTYPE_PGID;
-		pid = get_pid(task_pgrp(current));
+		pid = get_task_pid(current, PIDTYPE_PGID);
 	} else /* upid > 0 */ {
 		type = PIDTYPE_PID;
 		pid = find_get_pid(upid);
diff --git a/kernel/extable.c b/kernel/extable.c
index b54a6017b6b5..7f8f263f8524 100644
--- a/kernel/extable.c
+++ b/kernel/extable.c
@@ -52,6 +52,14 @@ const struct exception_table_entry *search_exception_tables(unsigned long addr)
 	return e;
 }
 
+static inline int init_kernel_text(unsigned long addr)
+{
+	if (addr >= (unsigned long)_sinittext &&
+	    addr <= (unsigned long)_einittext)
+		return 1;
+	return 0;
+}
+
 int core_kernel_text(unsigned long addr)
 {
 	if (addr >= (unsigned long)_stext &&
@@ -59,8 +67,7 @@ int core_kernel_text(unsigned long addr)
 		return 1;
 
 	if (system_state == SYSTEM_BOOTING &&
-	    addr >= (unsigned long)_sinittext &&
-	    addr <= (unsigned long)_einittext)
+	    init_kernel_text(addr))
 		return 1;
 	return 0;
 }
@@ -69,14 +76,26 @@ int __kernel_text_address(unsigned long addr)
 {
 	if (core_kernel_text(addr))
 		return 1;
-	return __module_text_address(addr) != NULL;
+	if (is_module_text_address(addr))
+		return 1;
+	/*
+	 * There might be init symbols in saved stacktraces.
+	 * Give those symbols a chance to be printed in
+	 * backtraces (such as lockdep traces).
+	 *
+	 * Since we are after the module-symbols check, there's
+	 * no danger of address overlap:
+	 */
+	if (init_kernel_text(addr))
+		return 1;
+	return 0;
 }
 
 int kernel_text_address(unsigned long addr)
 {
 	if (core_kernel_text(addr))
 		return 1;
-	return module_text_address(addr) != NULL;
+	return is_module_text_address(addr);
 }
 
 /*
@@ -92,5 +111,5 @@ int func_ptr_is_kernel_text(void *ptr)
 	addr = (unsigned long) dereference_function_descriptor(ptr);
 	if (core_kernel_text(addr))
 		return 1;
-	return module_text_address(addr) != NULL;
+	return is_module_text_address(addr);
 }
diff --git a/kernel/fork.c b/kernel/fork.c
index 47c15840a381..660c2b8765bc 100644
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -60,6 +60,7 @@
 #include <linux/tty.h>
 #include <linux/proc_fs.h>
 #include <linux/blkdev.h>
+#include <linux/fs_struct.h>
 #include <trace/sched.h>
 #include <linux/magic.h>
 
@@ -681,38 +682,21 @@ fail_nomem:
 	return retval;
 }
 
-static struct fs_struct *__copy_fs_struct(struct fs_struct *old)
-{
-	struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL);
-	/* We don't need to lock fs - think why ;-) */
-	if (fs) {
-		atomic_set(&fs->count, 1);
-		rwlock_init(&fs->lock);
-		fs->umask = old->umask;
-		read_lock(&old->lock);
-		fs->root = old->root;
-		path_get(&old->root);
-		fs->pwd = old->pwd;
-		path_get(&old->pwd);
-		read_unlock(&old->lock);
-	}
-	return fs;
-}
-
-struct fs_struct *copy_fs_struct(struct fs_struct *old)
-{
-	return __copy_fs_struct(old);
-}
-
-EXPORT_SYMBOL_GPL(copy_fs_struct);
-
 static int copy_fs(unsigned long clone_flags, struct task_struct *tsk)
 {
+	struct fs_struct *fs = current->fs;
 	if (clone_flags & CLONE_FS) {
-		atomic_inc(&current->fs->count);
+		/* tsk->fs is already what we want */
+		write_lock(&fs->lock);
+		if (fs->in_exec) {
+			write_unlock(&fs->lock);
+			return -EAGAIN;
+		}
+		fs->users++;
+		write_unlock(&fs->lock);
 		return 0;
 	}
-	tsk->fs = __copy_fs_struct(current->fs);
+	tsk->fs = copy_fs_struct(fs);
 	if (!tsk->fs)
 		return -ENOMEM;
 	return 0;
@@ -841,6 +825,8 @@ static int copy_signal(unsigned long clone_flags, struct task_struct *tsk)
 	atomic_set(&sig->live, 1);
 	init_waitqueue_head(&sig->wait_chldexit);
 	sig->flags = 0;
+	if (clone_flags & CLONE_NEWPID)
+		sig->flags |= SIGNAL_UNKILLABLE;
 	sig->group_exit_code = 0;
 	sig->group_exit_task = NULL;
 	sig->group_stop_count = 0;
@@ -1125,7 +1111,7 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 		goto bad_fork_cleanup_mm;
 	if ((retval = copy_io(clone_flags, p)))
 		goto bad_fork_cleanup_namespaces;
-	retval = copy_thread(0, clone_flags, stack_start, stack_size, p, regs);
+	retval = copy_thread(clone_flags, stack_start, stack_size, p, regs);
 	if (retval)
 		goto bad_fork_cleanup_io;
 
@@ -1263,8 +1249,6 @@ static struct task_struct *copy_process(unsigned long clone_flags,
 			p->signal->leader_pid = pid;
 			tty_kref_put(p->signal->tty);
 			p->signal->tty = tty_kref_get(current->signal->tty);
-			set_task_pgrp(p, task_pgrp_nr(current));
-			set_task_session(p, task_session_nr(current));
 			attach_pid(p, PIDTYPE_PGID, task_pgrp(current));
 			attach_pid(p, PIDTYPE_SID, task_session(current));
 			list_add_tail_rcu(&p->tasks, &init_task.tasks);
@@ -1488,6 +1472,7 @@ void __init proc_caches_init(void)
 	mm_cachep = kmem_cache_create("mm_struct",
 			sizeof(struct mm_struct), ARCH_MIN_MMSTRUCT_ALIGN,
 			SLAB_HWCACHE_ALIGN|SLAB_PANIC, NULL);
+	vm_area_cachep = KMEM_CACHE(vm_area_struct, SLAB_PANIC);
 	mmap_init();
 }
 
@@ -1543,12 +1528,16 @@ static int unshare_fs(unsigned long unshare_flags, struct fs_struct **new_fsp)
 {
 	struct fs_struct *fs = current->fs;
 
-	if ((unshare_flags & CLONE_FS) &&
-	    (fs && atomic_read(&fs->count) > 1)) {
-		*new_fsp = __copy_fs_struct(current->fs);
-		if (!*new_fsp)
-			return -ENOMEM;
-	}
+	if (!(unshare_flags & CLONE_FS) || !fs)
+		return 0;
+
+	/* don't need lock here; in the worst case we'll do useless copy */
+	if (fs->users == 1)
+		return 0;
+
+	*new_fsp = copy_fs_struct(fs);
+	if (!*new_fsp)
+		return -ENOMEM;
 
 	return 0;
 }
@@ -1664,8 +1653,13 @@ SYSCALL_DEFINE1(unshare, unsigned long, unshare_flags)
 
 		if (new_fs) {
 			fs = current->fs;
+			write_lock(&fs->lock);
 			current->fs = new_fs;
-			new_fs = fs;
+			if (--fs->users)
+				new_fs = NULL;
+			else
+				new_fs = fs;
+			write_unlock(&fs->lock);
 		}
 
 		if (new_mm) {
@@ -1704,7 +1698,7 @@ bad_unshare_cleanup_sigh:
 
 bad_unshare_cleanup_fs:
 	if (new_fs)
-		put_fs_struct(new_fs);
+		free_fs_struct(new_fs);
 
 bad_unshare_cleanup_thread:
 bad_unshare_out:
diff --git a/kernel/kallsyms.c b/kernel/kallsyms.c
index 7b8b0f21a5b1..374faf9bfdc7 100644
--- a/kernel/kallsyms.c
+++ b/kernel/kallsyms.c
@@ -161,6 +161,25 @@ unsigned long kallsyms_lookup_name(const char *name)
 	return module_kallsyms_lookup_name(name);
 }
 
+int kallsyms_on_each_symbol(int (*fn)(void *, const char *, struct module *,
+				      unsigned long),
+			    void *data)
+{
+	char namebuf[KSYM_NAME_LEN];
+	unsigned long i;
+	unsigned int off;
+	int ret;
+
+	for (i = 0, off = 0; i < kallsyms_num_syms; i++) {
+		off = kallsyms_expand_symbol(off, namebuf);
+		ret = fn(data, namebuf, NULL, kallsyms_addresses[i]);
+		if (ret != 0)
+			return ret;
+	}
+	return module_kallsyms_on_each_symbol(fn, data);
+}
+EXPORT_SYMBOL_GPL(kallsyms_on_each_symbol);
+
 static unsigned long get_symbol_pos(unsigned long addr,
 				    unsigned long *symbolsize,
 				    unsigned long *offset)
diff --git a/kernel/kexec.c b/kernel/kexec.c
index 93eed85fe017..5a758c6e4950 100644
--- a/kernel/kexec.c
+++ b/kernel/kexec.c
@@ -42,7 +42,7 @@
 note_buf_t* crash_notes;
 
 /* vmcoreinfo stuff */
-unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
+static unsigned char vmcoreinfo_data[VMCOREINFO_BYTES];
 u32 vmcoreinfo_note[VMCOREINFO_NOTE_SIZE/4];
 size_t vmcoreinfo_size;
 size_t vmcoreinfo_max_size = sizeof(vmcoreinfo_data);
@@ -1409,6 +1409,7 @@ static int __init crash_save_vmcoreinfo_init(void)
 	VMCOREINFO_OFFSET(list_head, prev);
 	VMCOREINFO_OFFSET(vm_struct, addr);
 	VMCOREINFO_LENGTH(zone.free_area, MAX_ORDER);
+	log_buf_kexec_setup();
 	VMCOREINFO_LENGTH(free_area.free_list, MIGRATE_TYPES);
 	VMCOREINFO_NUMBER(NR_FREE_PAGES);
 	VMCOREINFO_NUMBER(PG_lru);
diff --git a/kernel/kmod.c b/kernel/kmod.c
index f0c8f545180d..b750675251e5 100644
--- a/kernel/kmod.c
+++ b/kernel/kmod.c
@@ -50,7 +50,8 @@ static struct workqueue_struct *khelper_wq;
 char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
 
 /**
- * request_module - try to load a kernel module
+ * __request_module - try to load a kernel module
+ * @wait: wait (or not) for the operation to complete
  * @fmt: printf style format string for the name of the module
  * @...: arguments as specified in the format string
  *
@@ -63,7 +64,7 @@ char modprobe_path[KMOD_PATH_LEN] = "/sbin/modprobe";
  * If module auto-loading support is disabled then this function
  * becomes a no-operation.
  */
-int request_module(const char *fmt, ...)
+int __request_module(bool wait, const char *fmt, ...)
 {
 	va_list args;
 	char module_name[MODULE_NAME_LEN];
@@ -108,11 +109,12 @@ int request_module(const char *fmt, ...)
 		return -ENOMEM;
 	}
 
-	ret = call_usermodehelper(modprobe_path, argv, envp, 1);
+	ret = call_usermodehelper(modprobe_path, argv, envp,
+			wait ? UMH_WAIT_PROC : UMH_WAIT_EXEC);
 	atomic_dec(&kmod_concurrent);
 	return ret;
 }
-EXPORT_SYMBOL(request_module);
+EXPORT_SYMBOL(__request_module);
 #endif /* CONFIG_MODULES */
 
 struct subprocess_info {
diff --git a/kernel/module.c b/kernel/module.c
index 41f50605eed0..c268a771595c 100644
--- a/kernel/module.c
+++ b/kernel/module.c
@@ -68,7 +68,8 @@
 
 /* List of modules, protected by module_mutex or preempt_disable
  * (delete uses stop_machine/add uses RCU list operations). */
-static DEFINE_MUTEX(module_mutex);
+DEFINE_MUTEX(module_mutex);
+EXPORT_SYMBOL_GPL(module_mutex);
 static LIST_HEAD(modules);
 
 /* Waiting for a module to finish initializing? */
@@ -76,7 +77,7 @@ static DECLARE_WAIT_QUEUE_HEAD(module_wq);
 
 static BLOCKING_NOTIFIER_HEAD(module_notify_list);
 
-/* Bounds of module allocation, for speeding __module_text_address */
+/* Bounds of module allocation, for speeding __module_address */
 static unsigned long module_addr_min = -1UL, module_addr_max = 0;
 
 int register_module_notifier(struct notifier_block * nb)
@@ -186,17 +187,6 @@ extern const unsigned long __start___kcrctab_unused_gpl[];
 #define symversion(base, idx) ((base != NULL) ? ((base) + (idx)) : NULL)
 #endif
 
-struct symsearch {
-	const struct kernel_symbol *start, *stop;
-	const unsigned long *crcs;
-	enum {
-		NOT_GPL_ONLY,
-		GPL_ONLY,
-		WILL_BE_GPL_ONLY,
-	} licence;
-	bool unused;
-};
-
 static bool each_symbol_in_section(const struct symsearch *arr,
 				   unsigned int arrsize,
 				   struct module *owner,
@@ -217,10 +207,8 @@ static bool each_symbol_in_section(const struct symsearch *arr,
 }
 
 /* Returns true as soon as fn returns true, otherwise false. */
-static bool each_symbol(bool (*fn)(const struct symsearch *arr,
-				   struct module *owner,
-				   unsigned int symnum, void *data),
-			void *data)
+bool each_symbol(bool (*fn)(const struct symsearch *arr, struct module *owner,
+			    unsigned int symnum, void *data), void *data)
 {
 	struct module *mod;
 	const struct symsearch arr[] = {
@@ -273,6 +261,7 @@ static bool each_symbol(bool (*fn)(const struct symsearch *arr,
 	}
 	return false;
 }
+EXPORT_SYMBOL_GPL(each_symbol);
 
 struct find_symbol_arg {
 	/* Input */
@@ -283,7 +272,7 @@ struct find_symbol_arg {
 	/* Output */
 	struct module *owner;
 	const unsigned long *crc;
-	unsigned long value;
+	const struct kernel_symbol *sym;
 };
 
 static bool find_symbol_in_section(const struct symsearch *syms,
@@ -324,17 +313,17 @@ static bool find_symbol_in_section(const struct symsearch *syms,
 
 	fsa->owner = owner;
 	fsa->crc = symversion(syms->crcs, symnum);
-	fsa->value = syms->start[symnum].value;
+	fsa->sym = &syms->start[symnum];
 	return true;
 }
 
-/* Find a symbol, return value, (optional) crc and (optional) module
- * which owns it */
-static unsigned long find_symbol(const char *name,
-				 struct module **owner,
-				 const unsigned long **crc,
-				 bool gplok,
-				 bool warn)
+/* Find a symbol and return it, along with, (optional) crc and
+ * (optional) module which owns it */
+const struct kernel_symbol *find_symbol(const char *name,
+					struct module **owner,
+					const unsigned long **crc,
+					bool gplok,
+					bool warn)
 {
 	struct find_symbol_arg fsa;
 
@@ -347,15 +336,16 @@ static unsigned long find_symbol(const char *name,
 			*owner = fsa.owner;
 		if (crc)
 			*crc = fsa.crc;
-		return fsa.value;
+		return fsa.sym;
 	}
 
 	DEBUGP("Failed to find symbol %s\n", name);
-	return -ENOENT;
+	return NULL;
 }
+EXPORT_SYMBOL_GPL(find_symbol);
 
 /* Search for module by name: must hold module_mutex. */
-static struct module *find_module(const char *name)
+struct module *find_module(const char *name)
 {
 	struct module *mod;
 
@@ -365,6 +355,7 @@ static struct module *find_module(const char *name)
 	}
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(find_module);
 
 #ifdef CONFIG_SMP
 
@@ -641,7 +632,7 @@ static int already_uses(struct module *a, struct module *b)
 }
 
 /* Module a uses b */
-static int use_module(struct module *a, struct module *b)
+int use_module(struct module *a, struct module *b)
 {
 	struct module_use *use;
 	int no_warn, err;
@@ -674,6 +665,7 @@ static int use_module(struct module *a, struct module *b)
 	no_warn = sysfs_create_link(b->holders_dir, &a->mkobj.kobj, a->name);
 	return 1;
 }
+EXPORT_SYMBOL_GPL(use_module);
 
 /* Clear the unload stuff of the module. */
 static void module_unload_free(struct module *mod)
@@ -894,7 +886,7 @@ void __symbol_put(const char *symbol)
 	struct module *owner;
 
 	preempt_disable();
-	if (IS_ERR_VALUE(find_symbol(symbol, &owner, NULL, true, false)))
+	if (!find_symbol(symbol, &owner, NULL, true, false))
 		BUG();
 	module_put(owner);
 	preempt_enable();
@@ -908,8 +900,10 @@ void symbol_put_addr(void *addr)
 	if (core_kernel_text((unsigned long)addr))
 		return;
 
-	if (!(modaddr = module_text_address((unsigned long)addr)))
-		BUG();
+	/* module_text_address is safe here: we're supposed to have reference
+	 * to module from symbol_get, so it can't go away. */
+	modaddr = __module_text_address((unsigned long)addr);
+	BUG_ON(!modaddr);
 	module_put(modaddr);
 }
 EXPORT_SYMBOL_GPL(symbol_put_addr);
@@ -949,10 +943,11 @@ static inline void module_unload_free(struct module *mod)
 {
 }
 
-static inline int use_module(struct module *a, struct module *b)
+int use_module(struct module *a, struct module *b)
 {
 	return strong_try_module_get(b) == 0;
 }
+EXPORT_SYMBOL_GPL(use_module);
 
 static inline void module_unload_init(struct module *mod)
 {
@@ -995,12 +990,12 @@ static struct module_attribute *modinfo_attrs[] = {
 
 static const char vermagic[] = VERMAGIC_STRING;
 
-static int try_to_force_load(struct module *mod, const char *symname)
+static int try_to_force_load(struct module *mod, const char *reason)
 {
 #ifdef CONFIG_MODULE_FORCE_LOAD
 	if (!test_taint(TAINT_FORCED_MODULE))
-		printk("%s: no version for \"%s\" found: kernel tainted.\n",
-		       mod->name, symname);
+		printk(KERN_WARNING "%s: %s: kernel tainted.\n",
+		       mod->name, reason);
 	add_taint_module(mod, TAINT_FORCED_MODULE);
 	return 0;
 #else
@@ -1057,9 +1052,9 @@ static inline int check_modstruct_version(Elf_Shdr *sechdrs,
 {
 	const unsigned long *crc;
 
-	if (IS_ERR_VALUE(find_symbol("struct_module", NULL, &crc, true, false)))
+	if (!find_symbol("module_layout", NULL, &crc, true, false))
 		BUG();
-	return check_version(sechdrs, versindex, "struct_module", mod, crc);
+	return check_version(sechdrs, versindex, "module_layout", mod, crc);
 }
 
 /* First part is kernel version, which we ignore if module has crcs. */
@@ -1098,25 +1093,25 @@ static inline int same_magic(const char *amagic, const char *bmagic,
 
 /* Resolve a symbol for this module.  I.e. if we find one, record usage.
    Must be holding module_mutex. */
-static unsigned long resolve_symbol(Elf_Shdr *sechdrs,
-				    unsigned int versindex,
-				    const char *name,
-				    struct module *mod)
+static const struct kernel_symbol *resolve_symbol(Elf_Shdr *sechdrs,
+						  unsigned int versindex,
+						  const char *name,
+						  struct module *mod)
 {
 	struct module *owner;
-	unsigned long ret;
+	const struct kernel_symbol *sym;
 	const unsigned long *crc;
 
-	ret = find_symbol(name, &owner, &crc,
+	sym = find_symbol(name, &owner, &crc,
 			  !(mod->taints & (1 << TAINT_PROPRIETARY_MODULE)), true);
-	if (!IS_ERR_VALUE(ret)) {
-		/* use_module can fail due to OOM,
-		   or module initialization or unloading */
+	/* use_module can fail due to OOM,
+	   or module initialization or unloading */
+	if (sym) {
 		if (!check_version(sechdrs, versindex, name, mod, crc) ||
 		    !use_module(mod, owner))
-			ret = -EINVAL;
+			sym = NULL;
 	}
-	return ret;
+	return sym;
 }
 
 /*
@@ -1491,6 +1486,9 @@ static void free_module(struct module *mod)
 	/* Module unload stuff */
 	module_unload_free(mod);
 
+	/* Free any allocated parameters. */
+	destroy_params(mod->kp, mod->num_kp);
+
 	/* release any pointers to mcount in this module */
 	ftrace_release(mod->module_core, mod->core_size);
 
@@ -1513,17 +1511,15 @@ static void free_module(struct module *mod)
 void *__symbol_get(const char *symbol)
 {
 	struct module *owner;
-	unsigned long value;
+	const struct kernel_symbol *sym;
 
 	preempt_disable();
-	value = find_symbol(symbol, &owner, NULL, true, true);
-	if (IS_ERR_VALUE(value))
-		value = 0;
-	else if (strong_try_module_get(owner))
-		value = 0;
+	sym = find_symbol(symbol, &owner, NULL, true, true);
+	if (sym && strong_try_module_get(owner))
+		sym = NULL;
 	preempt_enable();
 
-	return (void *)value;
+	return sym ? (void *)sym->value : NULL;
 }
 EXPORT_SYMBOL_GPL(__symbol_get);
 
@@ -1551,8 +1547,7 @@ static int verify_export_symbols(struct module *mod)
 
 	for (i = 0; i < ARRAY_SIZE(arr); i++) {
 		for (s = arr[i].sym; s < arr[i].sym + arr[i].num; s++) {
-			if (!IS_ERR_VALUE(find_symbol(s->name, &owner,
-						      NULL, true, false))) {
+			if (find_symbol(s->name, &owner, NULL, true, false)) {
 				printk(KERN_ERR
 				       "%s: exports duplicate symbol %s"
 				       " (owned by %s)\n",
@@ -1576,6 +1571,7 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 	unsigned long secbase;
 	unsigned int i, n = sechdrs[symindex].sh_size / sizeof(Elf_Sym);
 	int ret = 0;
+	const struct kernel_symbol *ksym;
 
 	for (i = 1; i < n; i++) {
 		switch (sym[i].st_shndx) {
@@ -1595,13 +1591,14 @@ static int simplify_symbols(Elf_Shdr *sechdrs,
 			break;
 
 		case SHN_UNDEF:
-			sym[i].st_value
-			  = resolve_symbol(sechdrs, versindex,
-					   strtab + sym[i].st_name, mod);
-
+			ksym = resolve_symbol(sechdrs, versindex,
+					      strtab + sym[i].st_name, mod);
 			/* Ok if resolved.  */
-			if (!IS_ERR_VALUE(sym[i].st_value))
+			if (ksym) {
+				sym[i].st_value = ksym->value;
 				break;
+			}
+
 			/* Ok if weak.  */
 			if (ELF_ST_BIND(sym[i].st_info) == STB_WEAK)
 				break;
@@ -1676,8 +1673,7 @@ static void layout_sections(struct module *mod,
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || strncmp(secstrings + s->sh_name,
-				       ".init", 5) == 0)
+			    || strstarts(secstrings + s->sh_name, ".init"))
 				continue;
 			s->sh_entsize = get_offset(mod, &mod->core_size, s, i);
 			DEBUGP("\t%s\n", secstrings + s->sh_name);
@@ -1694,8 +1690,7 @@ static void layout_sections(struct module *mod,
 			if ((s->sh_flags & masks[m][0]) != masks[m][0]
 			    || (s->sh_flags & masks[m][1])
 			    || s->sh_entsize != ~0UL
-			    || strncmp(secstrings + s->sh_name,
-				       ".init", 5) != 0)
+			    || !strstarts(secstrings + s->sh_name, ".init"))
 				continue;
 			s->sh_entsize = (get_offset(mod, &mod->init_size, s, i)
 					 | INIT_OFFSET_MASK);
@@ -1828,8 +1823,7 @@ static char elf_type(const Elf_Sym *sym,
 		else
 			return 'b';
 	}
-	if (strncmp(secstrings + sechdrs[sym->st_shndx].sh_name,
-		    ".debug", strlen(".debug")) == 0)
+	if (strstarts(secstrings + sechdrs[sym->st_shndx].sh_name, ".debug"))
 		return 'n';
 	return '?';
 }
@@ -1898,8 +1892,7 @@ static noinline struct module *load_module(void __user *umod,
 	unsigned int symindex = 0;
 	unsigned int strindex = 0;
 	unsigned int modindex, versindex, infoindex, pcpuindex;
-	unsigned int num_kp, num_mcount;
-	struct kernel_param *kp;
+	unsigned int num_mcount;
 	struct module *mod;
 	long err = 0;
 	void *percpu = NULL, *ptr = NULL; /* Stops spurious gcc warning */
@@ -1916,12 +1909,6 @@ static noinline struct module *load_module(void __user *umod,
 	if (len > 64 * 1024 * 1024 || (hdr = vmalloc(len)) == NULL)
 		return ERR_PTR(-ENOMEM);
 
-	/* Create stop_machine threads since the error path relies on
-	 * a non-failing stop_machine call. */
-	err = stop_machine_create();
-	if (err)
-		goto free_hdr;
-
 	if (copy_from_user(hdr, umod, len) != 0) {
 		err = -EFAULT;
 		goto free_hdr;
@@ -1962,9 +1949,12 @@ static noinline struct module *load_module(void __user *umod,
 		}
 #ifndef CONFIG_MODULE_UNLOAD
 		/* Don't load .exit sections */
-		if (strncmp(secstrings+sechdrs[i].sh_name, ".exit", 5) == 0)
+		if (strstarts(secstrings+sechdrs[i].sh_name, ".exit"))
 			sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC;
 #endif
+		/* Don't keep __versions around; it's just for loading. */
+		if (strcmp(secstrings + sechdrs[i].sh_name, "__versions") == 0)
+			sechdrs[i].sh_flags &= ~(unsigned long)SHF_ALLOC;
 	}
 
 	modindex = find_sec(hdr, sechdrs, secstrings,
@@ -2006,7 +1996,7 @@ static noinline struct module *load_module(void __user *umod,
 	modmagic = get_modinfo(sechdrs, infoindex, "vermagic");
 	/* This is allowed: modprobe --force will invalidate it. */
 	if (!modmagic) {
-		err = try_to_force_load(mod, "magic");
+		err = try_to_force_load(mod, "bad vermagic");
 		if (err)
 			goto free_hdr;
 	} else if (!same_magic(modmagic, vermagic, versindex)) {
@@ -2144,8 +2134,8 @@ static noinline struct module *load_module(void __user *umod,
 
 	/* Now we've got everything in the final locations, we can
 	 * find optional sections. */
-	kp = section_objs(hdr, sechdrs, secstrings, "__param", sizeof(*kp),
-			  &num_kp);
+	mod->kp = section_objs(hdr, sechdrs, secstrings, "__param",
+			       sizeof(*mod->kp), &mod->num_kp);
 	mod->syms = section_objs(hdr, sechdrs, secstrings, "__ksymtab",
 				 sizeof(*mod->syms), &mod->num_syms);
 	mod->crcs = section_addr(hdr, sechdrs, secstrings, "__kcrctab");
@@ -2195,8 +2185,8 @@ static noinline struct module *load_module(void __user *umod,
 	    || (mod->num_unused_gpl_syms && !mod->unused_gpl_crcs)
 #endif
 		) {
-		printk(KERN_WARNING "%s: No versions for exported symbols.\n", mod->name);
-		err = try_to_force_load(mod, "nocrc");
+		err = try_to_force_load(mod,
+					"no versions for exported symbols");
 		if (err)
 			goto cleanup;
 	}
@@ -2291,11 +2281,11 @@ static noinline struct module *load_module(void __user *umod,
 	 */
 	list_add_rcu(&mod->list, &modules);
 
-	err = parse_args(mod->name, mod->args, kp, num_kp, NULL);
+	err = parse_args(mod->name, mod->args, mod->kp, mod->num_kp, NULL);
 	if (err < 0)
 		goto unlink;
 
-	err = mod_sysfs_setup(mod, kp, num_kp);
+	err = mod_sysfs_setup(mod, mod->kp, mod->num_kp);
 	if (err < 0)
 		goto unlink;
 	add_sect_attrs(mod, hdr->e_shnum, secstrings, sechdrs);
@@ -2304,12 +2294,13 @@ static noinline struct module *load_module(void __user *umod,
 	/* Get rid of temporary copy */
 	vfree(hdr);
 
-	stop_machine_destroy();
 	/* Done! */
 	return mod;
 
  unlink:
-	stop_machine(__unlink_module, mod, NULL);
+	/* Unlink carefully: kallsyms could be walking list. */
+	list_del_rcu(&mod->list);
+	synchronize_sched();
 	module_arch_cleanup(mod);
  cleanup:
 	kobject_del(&mod->mkobj.kobj);
@@ -2317,8 +2308,8 @@ static noinline struct module *load_module(void __user *umod,
 	ftrace_release(mod->module_core, mod->core_size);
  free_unload:
 	module_unload_free(mod);
- free_init:
 #if defined(CONFIG_MODULE_UNLOAD) && defined(CONFIG_SMP)
+ free_init:
 	percpu_modfree(mod->refptr);
 #endif
 	module_free(mod, mod->module_init);
@@ -2332,7 +2323,6 @@ static noinline struct module *load_module(void __user *umod,
 	kfree(args);
  free_hdr:
 	vfree(hdr);
-	stop_machine_destroy();
 	return ERR_PTR(err);
 
  truncated:
@@ -2609,6 +2599,25 @@ unsigned long module_kallsyms_lookup_name(const char *name)
 	preempt_enable();
 	return ret;
 }
+
+int module_kallsyms_on_each_symbol(int (*fn)(void *, const char *,
+					     struct module *, unsigned long),
+				   void *data)
+{
+	struct module *mod;
+	unsigned int i;
+	int ret;
+
+	list_for_each_entry(mod, &modules, list) {
+		for (i = 0; i < mod->num_symtab; i++) {
+			ret = fn(data, mod->strtab + mod->symtab[i].st_name,
+				 mod, mod->symtab[i].st_value);
+			if (ret != 0)
+				return ret;
+		}
+	}
+	return 0;
+}
 #endif /* CONFIG_KALLSYMS */
 
 static char *module_flags(struct module *mod, char *buf)
@@ -2744,29 +2753,31 @@ const struct exception_table_entry *search_module_extables(unsigned long addr)
 }
 
 /*
- * Is this a valid module address?
+ * is_module_address - is this address inside a module?
+ * @addr: the address to check.
+ *
+ * See is_module_text_address() if you simply want to see if the address
+ * is code (not data).
  */
-int is_module_address(unsigned long addr)
+bool is_module_address(unsigned long addr)
 {
-	struct module *mod;
+	bool ret;
 
 	preempt_disable();
-
-	list_for_each_entry_rcu(mod, &modules, list) {
-		if (within_module_core(addr, mod)) {
-			preempt_enable();
-			return 1;
-		}
-	}
-
+	ret = __module_address(addr) != NULL;
 	preempt_enable();
 
-	return 0;
+	return ret;
 }
 
-
-/* Is this a valid kernel address? */
-struct module *__module_text_address(unsigned long addr)
+/*
+ * __module_address - get the module which contains an address.
+ * @addr: the address.
+ *
+ * Must be called with preempt disabled or module mutex held so that
+ * module doesn't get freed during this.
+ */
+struct module *__module_address(unsigned long addr)
 {
 	struct module *mod;
 
@@ -2774,22 +2785,51 @@ struct module *__module_text_address(unsigned long addr)
 		return NULL;
 
 	list_for_each_entry_rcu(mod, &modules, list)
-		if (within(addr, mod->module_init, mod->init_text_size)
-		    || within(addr, mod->module_core, mod->core_text_size))
+		if (within_module_core(addr, mod)
+		    || within_module_init(addr, mod))
 			return mod;
 	return NULL;
 }
+EXPORT_SYMBOL_GPL(__module_address);
 
-struct module *module_text_address(unsigned long addr)
+/*
+ * is_module_text_address - is this address inside module code?
+ * @addr: the address to check.
+ *
+ * See is_module_address() if you simply want to see if the address is
+ * anywhere in a module.  See kernel_text_address() for testing if an
+ * address corresponds to kernel or module code.
+ */
+bool is_module_text_address(unsigned long addr)
 {
-	struct module *mod;
+	bool ret;
 
 	preempt_disable();
-	mod = __module_text_address(addr);
+	ret = __module_text_address(addr) != NULL;
 	preempt_enable();
 
+	return ret;
+}
+
+/*
+ * __module_text_address - get the module whose code contains an address.
+ * @addr: the address.
+ *
+ * Must be called with preempt disabled or module mutex held so that
+ * module doesn't get freed during this.
+ */
+struct module *__module_text_address(unsigned long addr)
+{
+	struct module *mod = __module_address(addr);
+	if (mod) {
+		/* Make sure it's within the text section. */
+		if (!within(addr, mod->module_init, mod->init_text_size)
+		    && !within(addr, mod->module_core, mod->core_text_size))
+			mod = NULL;
+	}
 	return mod;
 }
+EXPORT_SYMBOL_GPL(__module_text_address);
 
 /* Don't grab lock, we're oopsing. */
 void print_modules(void)
@@ -2809,9 +2849,17 @@ void print_modules(void)
 }
 
 #ifdef CONFIG_MODVERSIONS
-/* Generate the signature for struct module here, too, for modversions. */
-void struct_module(struct module *mod) { return; }
-EXPORT_SYMBOL(struct_module);
+/* Generate the signature for all relevant module structures here.
+ * If these change, we don't want to try to parse the module. */
+void module_layout(struct module *mod,
+		   struct modversion_info *ver,
+		   struct kernel_param *kp,
+		   struct kernel_symbol *ks,
+		   struct marker *marker,
+		   struct tracepoint *tp)
+{
+}
+EXPORT_SYMBOL(module_layout);
 #endif
 
 #ifdef CONFIG_MARKERS
diff --git a/kernel/ns_cgroup.c b/kernel/ns_cgroup.c
index 78bc3fdac0d2..5aa854f9e5ae 100644
--- a/kernel/ns_cgroup.c
+++ b/kernel/ns_cgroup.c
@@ -34,7 +34,7 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 
 /*
  * Rules:
- *   1. you can only enter a cgroup which is a child of your current
+ *   1. you can only enter a cgroup which is a descendant of your current
  *     cgroup
  *   2. you can only place another process into a cgroup if
  *     a. you have CAP_SYS_ADMIN
@@ -45,21 +45,15 @@ int ns_cgroup_clone(struct task_struct *task, struct pid *pid)
 static int ns_can_attach(struct cgroup_subsys *ss,
 		struct cgroup *new_cgroup, struct task_struct *task)
 {
-	struct cgroup *orig;
-
 	if (current != task) {
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		if (!cgroup_is_descendant(new_cgroup))
+		if (!cgroup_is_descendant(new_cgroup, current))
 			return -EPERM;
 	}
 
-	if (atomic_read(&new_cgroup->count) != 0)
-		return -EPERM;
-
-	orig = task_cgroup(task, ns_subsys_id);
-	if (orig && orig != new_cgroup->parent)
+	if (!cgroup_is_descendant(new_cgroup, task))
 		return -EPERM;
 
 	return 0;
@@ -77,7 +71,7 @@ static struct cgroup_subsys_state *ns_create(struct cgroup_subsys *ss,
 
 	if (!capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
-	if (!cgroup_is_descendant(cgroup))
+	if (!cgroup_is_descendant(cgroup, current))
 		return ERR_PTR(-EPERM);
 
 	ns_cgroup = kzalloc(sizeof(*ns_cgroup), GFP_KERNEL);
diff --git a/kernel/panic.c b/kernel/panic.c
index 32fe4eff1b89..3fd8c5bf8b39 100644
--- a/kernel/panic.c
+++ b/kernel/panic.c
@@ -8,19 +8,19 @@
  * This function is used through-out the kernel (including mm and fs)
  * to indicate a major problem.
  */
+#include <linux/debug_locks.h>
+#include <linux/interrupt.h>
+#include <linux/kallsyms.h>
+#include <linux/notifier.h>
 #include <linux/module.h>
-#include <linux/sched.h>
-#include <linux/delay.h>
+#include <linux/random.h>
 #include <linux/reboot.h>
-#include <linux/notifier.h>
-#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/kexec.h>
+#include <linux/sched.h>
 #include <linux/sysrq.h>
-#include <linux/interrupt.h>
+#include <linux/init.h>
 #include <linux/nmi.h>
-#include <linux/kexec.h>
-#include <linux/debug_locks.h>
-#include <linux/random.h>
-#include <linux/kallsyms.h>
 #include <linux/dmi.h>
 
 int panic_on_oops;
@@ -52,19 +52,15 @@ EXPORT_SYMBOL(panic_blink);
  *
  *	This function never returns.
  */
-
 NORET_TYPE void panic(const char * fmt, ...)
 {
-	long i;
 	static char buf[1024];
 	va_list args;
-#if defined(CONFIG_S390)
-	unsigned long caller = (unsigned long) __builtin_return_address(0);
-#endif
+	long i;
 
 	/*
-	 * It's possible to come here directly from a panic-assertion and not
-	 * have preempt disabled. Some functions called from here want
+	 * It's possible to come here directly from a panic-assertion and
+	 * not have preempt disabled. Some functions called from here want
 	 * preempt to be disabled. No point enabling it later though...
 	 */
 	preempt_disable();
@@ -77,7 +73,6 @@ NORET_TYPE void panic(const char * fmt, ...)
 #ifdef CONFIG_DEBUG_BUGVERBOSE
 	dump_stack();
 #endif
-	bust_spinlocks(0);
 
 	/*
 	 * If we have crashed and we have a crash kernel loaded let it handle
@@ -86,14 +81,12 @@ NORET_TYPE void panic(const char * fmt, ...)
 	 */
 	crash_kexec(NULL);
 
-#ifdef CONFIG_SMP
 	/*
 	 * Note smp_send_stop is the usual smp shutdown function, which
 	 * unfortunately means it may not be hardened to work in a panic
 	 * situation.
 	 */
 	smp_send_stop();
-#endif
 
 	atomic_notifier_call_chain(&panic_notifier_list, 0, buf);
 
@@ -102,19 +95,21 @@ NORET_TYPE void panic(const char * fmt, ...)
 
 	if (panic_timeout > 0) {
 		/*
-	 	 * Delay timeout seconds before rebooting the machine. 
-		 * We can't use the "normal" timers since we just panicked..
-	 	 */
-		printk(KERN_EMERG "Rebooting in %d seconds..",panic_timeout);
+		 * Delay timeout seconds before rebooting the machine.
+		 * We can't use the "normal" timers since we just panicked.
+		 */
+		printk(KERN_EMERG "Rebooting in %d seconds..", panic_timeout);
+
 		for (i = 0; i < panic_timeout*1000; ) {
 			touch_nmi_watchdog();
 			i += panic_blink(i);
 			mdelay(1);
 			i++;
 		}
-		/*	This will not be a clean reboot, with everything
-		 *	shutting down.  But if there is a chance of
-		 *	rebooting the system it will be rebooted.
+		/*
+		 * This will not be a clean reboot, with everything
+		 * shutting down.  But if there is a chance of
+		 * rebooting the system it will be rebooted.
 		 */
 		emergency_restart();
 	}
@@ -127,38 +122,44 @@ NORET_TYPE void panic(const char * fmt, ...)
 	}
 #endif
 #if defined(CONFIG_S390)
-	disabled_wait(caller);
+	{
+		unsigned long caller;
+
+		caller = (unsigned long)__builtin_return_address(0);
+		disabled_wait(caller);
+	}
 #endif
 	local_irq_enable();
-	for (i = 0;;) {
+	for (i = 0; ; ) {
 		touch_softlockup_watchdog();
 		i += panic_blink(i);
 		mdelay(1);
 		i++;
 	}
+	bust_spinlocks(0);
 }
 
 EXPORT_SYMBOL(panic);
 
 
 struct tnt {
-	u8 bit;
-	char true;
-	char false;
+	u8	bit;
+	char	true;
+	char	false;
 };
 
 static const struct tnt tnts[] = {
-	{ TAINT_PROPRIETARY_MODULE, 'P', 'G' },
-	{ TAINT_FORCED_MODULE, 'F', ' ' },
-	{ TAINT_UNSAFE_SMP, 'S', ' ' },
-	{ TAINT_FORCED_RMMOD, 'R', ' ' },
-	{ TAINT_MACHINE_CHECK, 'M', ' ' },
-	{ TAINT_BAD_PAGE, 'B', ' ' },
-	{ TAINT_USER, 'U', ' ' },
-	{ TAINT_DIE, 'D', ' ' },
-	{ TAINT_OVERRIDDEN_ACPI_TABLE, 'A', ' ' },
-	{ TAINT_WARN, 'W', ' ' },
-	{ TAINT_CRAP, 'C', ' ' },
+	{ TAINT_PROPRIETARY_MODULE,	'P', 'G' },
+	{ TAINT_FORCED_MODULE,		'F', ' ' },
+	{ TAINT_UNSAFE_SMP,		'S', ' ' },
+	{ TAINT_FORCED_RMMOD,		'R', ' ' },
+	{ TAINT_MACHINE_CHECK,		'M', ' ' },
+	{ TAINT_BAD_PAGE,		'B', ' ' },
+	{ TAINT_USER,			'U', ' ' },
+	{ TAINT_DIE,			'D', ' ' },
+	{ TAINT_OVERRIDDEN_ACPI_TABLE,	'A', ' ' },
+	{ TAINT_WARN,			'W', ' ' },
+	{ TAINT_CRAP,			'C', ' ' },
 };
 
 /**
@@ -195,7 +196,8 @@ const char *print_tainted(void)
 		*s = 0;
 	} else
 		snprintf(buf, sizeof(buf), "Not tainted");
-	return(buf);
+
+	return buf;
 }
 
 int test_taint(unsigned flag)
@@ -211,7 +213,8 @@ unsigned long get_taint(void)
 
 void add_taint(unsigned flag)
 {
-	debug_locks = 0; /* can't trust the integrity of the kernel anymore */
+	/* can't trust the integrity of the kernel anymore: */
+	debug_locks = 0;
 	set_bit(flag, &tainted_mask);
 }
 EXPORT_SYMBOL(add_taint);
@@ -266,8 +269,8 @@ static void do_oops_enter_exit(void)
 }
 
 /*
- * Return true if the calling CPU is allowed to print oops-related info.  This
- * is a bit racy..
+ * Return true if the calling CPU is allowed to print oops-related info.
+ * This is a bit racy..
  */
 int oops_may_print(void)
 {
@@ -276,20 +279,22 @@ int oops_may_print(void)
 
 /*
  * Called when the architecture enters its oops handler, before it prints
- * anything.  If this is the first CPU to oops, and it's oopsing the first time
- * then let it proceed.
+ * anything.  If this is the first CPU to oops, and it's oopsing the first
+ * time then let it proceed.
  *
- * This is all enabled by the pause_on_oops kernel boot option.  We do all this
- * to ensure that oopses don't scroll off the screen.  It has the side-effect
- * of preventing later-oopsing CPUs from mucking up the display, too.
+ * This is all enabled by the pause_on_oops kernel boot option.  We do all
+ * this to ensure that oopses don't scroll off the screen.  It has the
+ * side-effect of preventing later-oopsing CPUs from mucking up the display,
+ * too.
  *
- * It turns out that the CPU which is allowed to print ends up pausing for the
- * right duration, whereas all the other CPUs pause for twice as long: once in
- * oops_enter(), once in oops_exit().
+ * It turns out that the CPU which is allowed to print ends up pausing for
+ * the right duration, whereas all the other CPUs pause for twice as long:
+ * once in oops_enter(), once in oops_exit().
  */
 void oops_enter(void)
 {
-	debug_locks_off(); /* can't trust the integrity of the kernel anymore */
+	/* can't trust the integrity of the kernel anymore: */
+	debug_locks_off();
 	do_oops_enter_exit();
 }
 
diff --git a/kernel/params.c b/kernel/params.c
index a1e3025b19a9..de273ec85bd2 100644
--- a/kernel/params.c
+++ b/kernel/params.c
@@ -24,6 +24,9 @@
 #include <linux/err.h>
 #include <linux/slab.h>
 
+/* We abuse the high bits of "perm" to record whether we kmalloc'ed. */
+#define KPARAM_KMALLOCED	0x80000000
+
 #if 0
 #define DEBUGP printk
 #else
@@ -217,7 +220,19 @@ int param_set_charp(const char *val, struct kernel_param *kp)
 		return -ENOSPC;
 	}
 
-	*(char **)kp->arg = (char *)val;
+	if (kp->perm & KPARAM_KMALLOCED)
+		kfree(*(char **)kp->arg);
+
+	/* This is a hack.  We can't need to strdup in early boot, and we
+	 * don't need to; this mangled commandline is preserved. */
+	if (slab_is_available()) {
+		kp->perm |= KPARAM_KMALLOCED;
+		*(char **)kp->arg = kstrdup(val, GFP_KERNEL);
+		if (!kp->arg)
+			return -ENOMEM;
+	} else
+		*(const char **)kp->arg = val;
+
 	return 0;
 }
 
@@ -571,6 +586,15 @@ void module_param_sysfs_remove(struct module *mod)
 }
 #endif
 
+void destroy_params(const struct kernel_param *params, unsigned num)
+{
+	unsigned int i;
+
+	for (i = 0; i < num; i++)
+		if (params[i].perm & KPARAM_KMALLOCED)
+			kfree(*(char **)params[i].arg);
+}
+
 static void __init kernel_add_sysfs_param(const char *name,
 					  struct kernel_param *kparam,
 					  unsigned int name_skip)
diff --git a/kernel/pid.c b/kernel/pid.c
index 1b3586fe753a..b2e5f78fd281 100644
--- a/kernel/pid.c
+++ b/kernel/pid.c
@@ -403,6 +403,8 @@ struct pid *get_task_pid(struct task_struct *task, enum pid_type type)
 {
 	struct pid *pid;
 	rcu_read_lock();
+	if (type != PIDTYPE_PID)
+		task = task->group_leader;
 	pid = get_pid(task->pids[type].pid);
 	rcu_read_unlock();
 	return pid;
@@ -450,11 +452,24 @@ pid_t pid_vnr(struct pid *pid)
 }
 EXPORT_SYMBOL_GPL(pid_vnr);
 
-pid_t task_pid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
+pid_t __task_pid_nr_ns(struct task_struct *task, enum pid_type type,
+			struct pid_namespace *ns)
 {
-	return pid_nr_ns(task_pid(tsk), ns);
+	pid_t nr = 0;
+
+	rcu_read_lock();
+	if (!ns)
+		ns = current->nsproxy->pid_ns;
+	if (likely(pid_alive(task))) {
+		if (type != PIDTYPE_PID)
+			task = task->group_leader;
+		nr = pid_nr_ns(task->pids[type].pid, ns);
+	}
+	rcu_read_unlock();
+
+	return nr;
 }
-EXPORT_SYMBOL(task_pid_nr_ns);
+EXPORT_SYMBOL(__task_pid_nr_ns);
 
 pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 {
@@ -462,18 +477,6 @@ pid_t task_tgid_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
 }
 EXPORT_SYMBOL(task_tgid_nr_ns);
 
-pid_t task_pgrp_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_pgrp(tsk), ns);
-}
-EXPORT_SYMBOL(task_pgrp_nr_ns);
-
-pid_t task_session_nr_ns(struct task_struct *tsk, struct pid_namespace *ns)
-{
-	return pid_nr_ns(task_session(tsk), ns);
-}
-EXPORT_SYMBOL(task_session_nr_ns);
-
 struct pid_namespace *task_active_pid_ns(struct task_struct *tsk)
 {
 	return ns_of_pid(task_pid(tsk));
diff --git a/kernel/pid_namespace.c b/kernel/pid_namespace.c
index fab8ea86fac3..2d1001b4858d 100644
--- a/kernel/pid_namespace.c
+++ b/kernel/pid_namespace.c
@@ -152,6 +152,7 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 {
 	int nr;
 	int rc;
+	struct task_struct *task;
 
 	/*
 	 * The last thread in the cgroup-init thread group is terminating.
@@ -169,7 +170,19 @@ void zap_pid_ns_processes(struct pid_namespace *pid_ns)
 	read_lock(&tasklist_lock);
 	nr = next_pidmap(pid_ns, 1);
 	while (nr > 0) {
-		kill_proc_info(SIGKILL, SEND_SIG_PRIV, nr);
+		rcu_read_lock();
+
+		/*
+		 * Use force_sig() since it clears SIGNAL_UNKILLABLE ensuring
+		 * any nested-container's init processes don't ignore the
+		 * signal
+		 */
+		task = pid_task(find_vpid(nr), PIDTYPE_PID);
+		if (task)
+			force_sig(SIGKILL, task);
+
+		rcu_read_unlock();
+
 		nr = next_pidmap(pid_ns, nr);
 	}
 	read_unlock(&tasklist_lock);
diff --git a/kernel/power/disk.c b/kernel/power/disk.c
index f3db382c2b2d..5f21ab2bbcdf 100644
--- a/kernel/power/disk.c
+++ b/kernel/power/disk.c
@@ -289,7 +289,7 @@ static int create_image(int platform_mode)
  *	hibernation_snapshot - quiesce devices and create the hibernation
  *	snapshot image.
  *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform frimware for the power transition.
+ *			 prepare the platform firmware for the power transition.
  *
  *	Must be called with pm_mutex held
  */
@@ -412,7 +412,7 @@ static int resume_target_kernel(bool platform_mode)
  *	hibernation_restore - quiesce devices and restore the hibernation
  *	snapshot image.  If successful, control returns in hibernation_snaphot()
  *	@platform_mode - if set, use the platform driver, if available, to
- *			 prepare the platform frimware for the transition.
+ *			 prepare the platform firmware for the transition.
  *
  *	Must be called with pm_mutex held
  */
diff --git a/kernel/printk.c b/kernel/printk.c
index e3602d0755b0..5052b5497c67 100644
--- a/kernel/printk.c
+++ b/kernel/printk.c
@@ -32,6 +32,7 @@
 #include <linux/security.h>
 #include <linux/bootmem.h>
 #include <linux/syscalls.h>
+#include <linux/kexec.h>
 
 #include <asm/uaccess.h>
 
@@ -135,6 +136,24 @@ static char *log_buf = __log_buf;
 static int log_buf_len = __LOG_BUF_LEN;
 static unsigned logged_chars; /* Number of chars produced since last read+clear operation */
 
+#ifdef CONFIG_KEXEC
+/*
+ * This appends the listed symbols to /proc/vmcoreinfo
+ *
+ * /proc/vmcoreinfo is used by various utiilties, like crash and makedumpfile to
+ * obtain access to symbols that are otherwise very difficult to locate.  These
+ * symbols are specifically used so that utilities can access and extract the
+ * dmesg log from a vmcore file after a crash.
+ */
+void log_buf_kexec_setup(void)
+{
+	VMCOREINFO_SYMBOL(log_buf);
+	VMCOREINFO_SYMBOL(log_end);
+	VMCOREINFO_SYMBOL(log_buf_len);
+	VMCOREINFO_SYMBOL(logged_chars);
+}
+#endif
+
 static int __init log_buf_len_setup(char *str)
 {
 	unsigned size = memparse(str, &str);
@@ -1292,8 +1311,11 @@ EXPORT_SYMBOL(printk_ratelimit);
 bool printk_timed_ratelimit(unsigned long *caller_jiffies,
 			unsigned int interval_msecs)
 {
-	if (*caller_jiffies == 0 || time_after(jiffies, *caller_jiffies)) {
-		*caller_jiffies = jiffies + msecs_to_jiffies(interval_msecs);
+	if (*caller_jiffies == 0
+			|| !time_in_range(jiffies, *caller_jiffies,
+					*caller_jiffies
+					+ msecs_to_jiffies(interval_msecs))) {
+		*caller_jiffies = jiffies;
 		return true;
 	}
 	return false;
diff --git a/kernel/ptrace.c b/kernel/ptrace.c
index c9cf48b21f05..aaad0ec34194 100644
--- a/kernel/ptrace.c
+++ b/kernel/ptrace.c
@@ -60,11 +60,15 @@ static void ptrace_untrace(struct task_struct *child)
 {
 	spin_lock(&child->sighand->siglock);
 	if (task_is_traced(child)) {
-		if (child->signal->flags & SIGNAL_STOP_STOPPED) {
+		/*
+		 * If the group stop is completed or in progress,
+		 * this thread was already counted as stopped.
+		 */
+		if (child->signal->flags & SIGNAL_STOP_STOPPED ||
+		    child->signal->group_stop_count)
 			__set_task_state(child, TASK_STOPPED);
-		} else {
+		else
 			signal_wake_up(child, 1);
-		}
 	}
 	spin_unlock(&child->sighand->siglock);
 }
@@ -235,18 +239,58 @@ out:
 	return retval;
 }
 
-static inline void __ptrace_detach(struct task_struct *child, unsigned int data)
+/*
+ * Called with irqs disabled, returns true if childs should reap themselves.
+ */
+static int ignoring_children(struct sighand_struct *sigh)
 {
-	child->exit_code = data;
-	/* .. re-parent .. */
-	__ptrace_unlink(child);
-	/* .. and wake it up. */
-	if (child->exit_state != EXIT_ZOMBIE)
-		wake_up_process(child);
+	int ret;
+	spin_lock(&sigh->siglock);
+	ret = (sigh->action[SIGCHLD-1].sa.sa_handler == SIG_IGN) ||
+	      (sigh->action[SIGCHLD-1].sa.sa_flags & SA_NOCLDWAIT);
+	spin_unlock(&sigh->siglock);
+	return ret;
+}
+
+/*
+ * Called with tasklist_lock held for writing.
+ * Unlink a traced task, and clean it up if it was a traced zombie.
+ * Return true if it needs to be reaped with release_task().
+ * (We can't call release_task() here because we already hold tasklist_lock.)
+ *
+ * If it's a zombie, our attachedness prevented normal parent notification
+ * or self-reaping.  Do notification now if it would have happened earlier.
+ * If it should reap itself, return true.
+ *
+ * If it's our own child, there is no notification to do.
+ * But if our normal children self-reap, then this child
+ * was prevented by ptrace and we must reap it now.
+ */
+static bool __ptrace_detach(struct task_struct *tracer, struct task_struct *p)
+{
+	__ptrace_unlink(p);
+
+	if (p->exit_state == EXIT_ZOMBIE) {
+		if (!task_detached(p) && thread_group_empty(p)) {
+			if (!same_thread_group(p->real_parent, tracer))
+				do_notify_parent(p, p->exit_signal);
+			else if (ignoring_children(tracer->sighand))
+				p->exit_signal = -1;
+		}
+		if (task_detached(p)) {
+			/* Mark it as in the process of being reaped. */
+			p->exit_state = EXIT_DEAD;
+			return true;
+		}
+	}
+
+	return false;
 }
 
 int ptrace_detach(struct task_struct *child, unsigned int data)
 {
+	bool dead = false;
+
 	if (!valid_signal(data))
 		return -EIO;
 
@@ -255,14 +299,45 @@ int ptrace_detach(struct task_struct *child, unsigned int data)
 	clear_tsk_thread_flag(child, TIF_SYSCALL_TRACE);
 
 	write_lock_irq(&tasklist_lock);
-	/* protect against de_thread()->release_task() */
-	if (child->ptrace)
-		__ptrace_detach(child, data);
+	/*
+	 * This child can be already killed. Make sure de_thread() or
+	 * our sub-thread doing do_wait() didn't do release_task() yet.
+	 */
+	if (child->ptrace) {
+		child->exit_code = data;
+		dead = __ptrace_detach(current, child);
+	}
 	write_unlock_irq(&tasklist_lock);
 
+	if (unlikely(dead))
+		release_task(child);
+
 	return 0;
 }
 
+/*
+ * Detach all tasks we were using ptrace on.
+ */
+void exit_ptrace(struct task_struct *tracer)
+{
+	struct task_struct *p, *n;
+	LIST_HEAD(ptrace_dead);
+
+	write_lock_irq(&tasklist_lock);
+	list_for_each_entry_safe(p, n, &tracer->ptraced, ptrace_entry) {
+		if (__ptrace_detach(tracer, p))
+			list_add(&p->ptrace_entry, &ptrace_dead);
+	}
+	write_unlock_irq(&tasklist_lock);
+
+	BUG_ON(!list_empty(&tracer->ptraced));
+
+	list_for_each_entry_safe(p, n, &ptrace_dead, ptrace_entry) {
+		list_del_init(&p->ptrace_entry);
+		release_task(p);
+	}
+}
+
 int ptrace_readdata(struct task_struct *tsk, unsigned long src, char __user *dst, int len)
 {
 	int copied = 0;
@@ -612,8 +687,6 @@ SYSCALL_DEFINE4(ptrace, long, request, long, pid, long, addr, long, data)
 		goto out_put_task_struct;
 
 	ret = arch_ptrace(child, request, addr, data);
-	if (ret < 0)
-		goto out_put_task_struct;
 
  out_put_task_struct:
 	put_task_struct(child);
diff --git a/kernel/rcupdate.c b/kernel/rcupdate.c
index cae8a059cf47..2c7b8457d0d2 100644
--- a/kernel/rcupdate.c
+++ b/kernel/rcupdate.c
@@ -122,6 +122,8 @@ static void rcu_barrier_func(void *type)
 	}
 }
 
+static inline void wait_migrated_callbacks(void);
+
 /*
  * Orchestrate the specified type of RCU barrier, waiting for all
  * RCU callbacks of the specified type to complete.
@@ -147,6 +149,7 @@ static void _rcu_barrier(enum rcu_barrier type)
 		complete(&rcu_barrier_completion);
 	wait_for_completion(&rcu_barrier_completion);
 	mutex_unlock(&rcu_barrier_mutex);
+	wait_migrated_callbacks();
 }
 
 /**
@@ -176,9 +179,50 @@ void rcu_barrier_sched(void)
 }
 EXPORT_SYMBOL_GPL(rcu_barrier_sched);
 
+static atomic_t rcu_migrate_type_count = ATOMIC_INIT(0);
+static struct rcu_head rcu_migrate_head[3];
+static DECLARE_WAIT_QUEUE_HEAD(rcu_migrate_wq);
+
+static void rcu_migrate_callback(struct rcu_head *notused)
+{
+	if (atomic_dec_and_test(&rcu_migrate_type_count))
+		wake_up(&rcu_migrate_wq);
+}
+
+static inline void wait_migrated_callbacks(void)
+{
+	wait_event(rcu_migrate_wq, !atomic_read(&rcu_migrate_type_count));
+}
+
+static int __cpuinit rcu_barrier_cpu_hotplug(struct notifier_block *self,
+		unsigned long action, void *hcpu)
+{
+	if (action == CPU_DYING) {
+		/*
+		 * preempt_disable() in on_each_cpu() prevents stop_machine(),
+		 * so when "on_each_cpu(rcu_barrier_func, (void *)type, 1);"
+		 * returns, all online cpus have queued rcu_barrier_func(),
+		 * and the dead cpu(if it exist) queues rcu_migrate_callback()s.
+		 *
+		 * These callbacks ensure _rcu_barrier() waits for all
+		 * RCU callbacks of the specified type to complete.
+		 */
+		atomic_set(&rcu_migrate_type_count, 3);
+		call_rcu_bh(rcu_migrate_head, rcu_migrate_callback);
+		call_rcu_sched(rcu_migrate_head + 1, rcu_migrate_callback);
+		call_rcu(rcu_migrate_head + 2, rcu_migrate_callback);
+	} else if (action == CPU_POST_DEAD) {
+		/* rcu_migrate_head is protected by cpu_add_remove_lock */
+		wait_migrated_callbacks();
+	}
+
+	return NOTIFY_OK;
+}
+
 void __init rcu_init(void)
 {
 	__rcu_init();
+	hotcpu_notifier(rcu_barrier_cpu_hotplug, 0);
 }
 
 void rcu_scheduler_starting(void)
diff --git a/kernel/relay.c b/kernel/relay.c
index 824b91ac10f1..bc188549788f 100644
--- a/kernel/relay.c
+++ b/kernel/relay.c
@@ -795,13 +795,15 @@ void relay_subbufs_consumed(struct rchan *chan,
 	if (!chan)
 		return;
 
-	if (cpu >= NR_CPUS || !chan->buf[cpu])
+	if (cpu >= NR_CPUS || !chan->buf[cpu] ||
+					subbufs_consumed > chan->n_subbufs)
 		return;
 
 	buf = chan->buf[cpu];
-	buf->subbufs_consumed += subbufs_consumed;
-	if (buf->subbufs_consumed > buf->subbufs_produced)
+	if (subbufs_consumed > buf->subbufs_produced - buf->subbufs_consumed)
 		buf->subbufs_consumed = buf->subbufs_produced;
+	else
+		buf->subbufs_consumed += subbufs_consumed;
 }
 EXPORT_SYMBOL_GPL(relay_subbufs_consumed);
 
diff --git a/kernel/sched.c b/kernel/sched.c
index f01cb63d1356..bec249885e17 100644
--- a/kernel/sched.c
+++ b/kernel/sched.c
@@ -1110,7 +1110,7 @@ static void hrtick_start(struct rq *rq, u64 delay)
 	if (rq == this_rq()) {
 		hrtimer_restart(timer);
 	} else if (!rq->hrtick_csd_pending) {
-		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd);
+		__smp_call_function_single(cpu_of(rq), &rq->hrtick_csd, 0);
 		rq->hrtick_csd_pending = 1;
 	}
 }
@@ -3818,19 +3818,23 @@ find_busiest_queue(struct sched_group *group, enum cpu_idle_type idle,
  */
 #define MAX_PINNED_INTERVAL	512
 
+/* Working cpumask for load_balance and load_balance_newidle. */
+static DEFINE_PER_CPU(cpumask_var_t, load_balance_tmpmask);
+
 /*
  * Check this_cpu to ensure it is balanced within domain. Attempt to move
  * tasks if there is an imbalance.
  */
 static int load_balance(int this_cpu, struct rq *this_rq,
 			struct sched_domain *sd, enum cpu_idle_type idle,
-			int *balance, struct cpumask *cpus)
+			int *balance)
 {
 	int ld_moved, all_pinned = 0, active_balance = 0, sd_idle = 0;
 	struct sched_group *group;
 	unsigned long imbalance;
 	struct rq *busiest;
 	unsigned long flags;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -3985,8 +3989,7 @@ out:
  * this_rq is locked.
  */
 static int
-load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
-			struct cpumask *cpus)
+load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd)
 {
 	struct sched_group *group;
 	struct rq *busiest = NULL;
@@ -3994,6 +3997,7 @@ load_balance_newidle(int this_cpu, struct rq *this_rq, struct sched_domain *sd,
 	int ld_moved = 0;
 	int sd_idle = 0;
 	int all_pinned = 0;
+	struct cpumask *cpus = __get_cpu_var(load_balance_tmpmask);
 
 	cpumask_setall(cpus);
 
@@ -4134,10 +4138,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 	struct sched_domain *sd;
 	int pulled_task = 0;
 	unsigned long next_balance = jiffies + HZ;
-	cpumask_var_t tmpmask;
-
-	if (!alloc_cpumask_var(&tmpmask, GFP_ATOMIC))
-		return;
 
 	for_each_domain(this_cpu, sd) {
 		unsigned long interval;
@@ -4148,7 +4148,7 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		if (sd->flags & SD_BALANCE_NEWIDLE)
 			/* If we've pulled tasks over stop searching: */
 			pulled_task = load_balance_newidle(this_cpu, this_rq,
-							   sd, tmpmask);
+							   sd);
 
 		interval = msecs_to_jiffies(sd->balance_interval);
 		if (time_after(next_balance, sd->last_balance + interval))
@@ -4163,7 +4163,6 @@ static void idle_balance(int this_cpu, struct rq *this_rq)
 		 */
 		this_rq->next_balance = next_balance;
 	}
-	free_cpumask_var(tmpmask);
 }
 
 /*
@@ -4313,11 +4312,6 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 	unsigned long next_balance = jiffies + 60*HZ;
 	int update_next_balance = 0;
 	int need_serialize;
-	cpumask_var_t tmp;
-
-	/* Fails alloc?  Rebalancing probably not a priority right now. */
-	if (!alloc_cpumask_var(&tmp, GFP_ATOMIC))
-		return;
 
 	for_each_domain(cpu, sd) {
 		if (!(sd->flags & SD_LOAD_BALANCE))
@@ -4342,7 +4336,7 @@ static void rebalance_domains(int cpu, enum cpu_idle_type idle)
 		}
 
 		if (time_after_eq(jiffies, sd->last_balance + interval)) {
-			if (load_balance(cpu, rq, sd, idle, &balance, tmp)) {
+			if (load_balance(cpu, rq, sd, idle, &balance)) {
 				/*
 				 * We've pulled tasks over so either we're no
 				 * longer idle, or one of our SMT siblings is
@@ -4376,8 +4370,6 @@ out:
 	 */
 	if (likely(update_next_balance))
 		rq->next_balance = next_balance;
-
-	free_cpumask_var(tmp);
 }
 
 /*
@@ -7728,7 +7720,7 @@ cpu_to_core_group(int cpu, const struct cpumask *cpu_map,
 {
 	int group;
 
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 	if (sg)
 		*sg = &per_cpu(sched_group_core, group).sg;
@@ -7757,7 +7749,7 @@ cpu_to_phys_group(int cpu, const struct cpumask *cpu_map,
 	cpumask_and(mask, cpu_coregroup_mask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #elif defined(CONFIG_SCHED_SMT)
-	cpumask_and(mask, &per_cpu(cpu_sibling_map, cpu), cpu_map);
+	cpumask_and(mask, topology_thread_cpumask(cpu), cpu_map);
 	group = cpumask_first(mask);
 #else
 	group = cpu;
@@ -8100,7 +8092,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 		SD_INIT(sd, SIBLING);
 		set_domain_attribute(sd, attr);
 		cpumask_and(sched_domain_span(sd),
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		sd->parent = p;
 		p->child = sd;
 		cpu_to_cpu_group(i, cpu_map, &sd->groups, tmpmask);
@@ -8111,7 +8103,7 @@ static int __build_sched_domains(const struct cpumask *cpu_map,
 	/* Set up CPU (sibling) groups */
 	for_each_cpu(i, cpu_map) {
 		cpumask_and(this_sibling_map,
-			    &per_cpu(cpu_sibling_map, i), cpu_map);
+			    topology_thread_cpumask(i), cpu_map);
 		if (i != cpumask_first(this_sibling_map))
 			continue;
 
@@ -8787,6 +8779,9 @@ void __init sched_init(void)
 #ifdef CONFIG_USER_SCHED
 	alloc_size *= 2;
 #endif
+#ifdef CONFIG_CPUMASK_OFFSTACK
+	alloc_size += num_possible_cpus() * cpumask_size();
+#endif
 	/*
 	 * As sched_init() is called before page_alloc is setup,
 	 * we use alloc_bootmem().
@@ -8824,6 +8819,12 @@ void __init sched_init(void)
 		ptr += nr_cpu_ids * sizeof(void **);
 #endif /* CONFIG_USER_SCHED */
 #endif /* CONFIG_RT_GROUP_SCHED */
+#ifdef CONFIG_CPUMASK_OFFSTACK
+		for_each_possible_cpu(i) {
+			per_cpu(load_balance_tmpmask, i) = (void *)ptr;
+			ptr += cpumask_size();
+		}
+#endif /* CONFIG_CPUMASK_OFFSTACK */
 	}
 
 #ifdef CONFIG_SMP
diff --git a/kernel/signal.c b/kernel/signal.c
index 1c8814481a11..d8034737db4c 100644
--- a/kernel/signal.c
+++ b/kernel/signal.c
@@ -55,10 +55,22 @@ static int sig_handler_ignored(void __user *handler, int sig)
 		(handler == SIG_DFL && sig_kernel_ignore(sig));
 }
 
-static int sig_ignored(struct task_struct *t, int sig)
+static int sig_task_ignored(struct task_struct *t, int sig,
+		int from_ancestor_ns)
 {
 	void __user *handler;
 
+	handler = sig_handler(t, sig);
+
+	if (unlikely(t->signal->flags & SIGNAL_UNKILLABLE) &&
+			handler == SIG_DFL && !from_ancestor_ns)
+		return 1;
+
+	return sig_handler_ignored(handler, sig);
+}
+
+static int sig_ignored(struct task_struct *t, int sig, int from_ancestor_ns)
+{
 	/*
 	 * Blocked signals are never ignored, since the
 	 * signal handler may change by the time it is
@@ -67,14 +79,13 @@ static int sig_ignored(struct task_struct *t, int sig)
 	if (sigismember(&t->blocked, sig) || sigismember(&t->real_blocked, sig))
 		return 0;
 
-	handler = sig_handler(t, sig);
-	if (!sig_handler_ignored(handler, sig))
+	if (!sig_task_ignored(t, sig, from_ancestor_ns))
 		return 0;
 
 	/*
 	 * Tracers may want to know about even ignored signals.
 	 */
-	return !tracehook_consider_ignored_signal(t, sig, handler);
+	return !tracehook_consider_ignored_signal(t, sig);
 }
 
 /*
@@ -318,7 +329,7 @@ int unhandled_signal(struct task_struct *tsk, int sig)
 		return 1;
 	if (handler != SIG_IGN && handler != SIG_DFL)
 		return 0;
-	return !tracehook_consider_fatal_signal(tsk, sig, handler);
+	return !tracehook_consider_fatal_signal(tsk, sig);
 }
 
 
@@ -624,7 +635,7 @@ static int check_kill_permission(int sig, struct siginfo *info,
  * Returns true if the signal should be actually delivered, otherwise
  * it should be dropped.
  */
-static int prepare_signal(int sig, struct task_struct *p)
+static int prepare_signal(int sig, struct task_struct *p, int from_ancestor_ns)
 {
 	struct signal_struct *signal = p->signal;
 	struct task_struct *t;
@@ -708,7 +719,7 @@ static int prepare_signal(int sig, struct task_struct *p)
 		}
 	}
 
-	return !sig_ignored(p, sig);
+	return !sig_ignored(p, sig, from_ancestor_ns);
 }
 
 /*
@@ -777,7 +788,7 @@ static void complete_signal(int sig, struct task_struct *p, int group)
 	    !(signal->flags & (SIGNAL_UNKILLABLE | SIGNAL_GROUP_EXIT)) &&
 	    !sigismember(&t->real_blocked, sig) &&
 	    (sig == SIGKILL ||
-	     !tracehook_consider_fatal_signal(t, sig, SIG_DFL))) {
+	     !tracehook_consider_fatal_signal(t, sig))) {
 		/*
 		 * This signal will be fatal to the whole group.
 		 */
@@ -813,8 +824,8 @@ static inline int legacy_queue(struct sigpending *signals, int sig)
 	return (sig < SIGRTMIN) && sigismember(&signals->signal, sig);
 }
 
-static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
-			int group)
+static int __send_signal(int sig, struct siginfo *info, struct task_struct *t,
+			int group, int from_ancestor_ns)
 {
 	struct sigpending *pending;
 	struct sigqueue *q;
@@ -822,7 +833,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 	trace_sched_signal_send(sig, t);
 
 	assert_spin_locked(&t->sighand->siglock);
-	if (!prepare_signal(sig, t))
+
+	if (!prepare_signal(sig, t, from_ancestor_ns))
 		return 0;
 
 	pending = group ? &t->signal->shared_pending : &t->pending;
@@ -871,6 +883,8 @@ static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
 			break;
 		default:
 			copy_siginfo(&q->info, info);
+			if (from_ancestor_ns)
+				q->info.si_pid = 0;
 			break;
 		}
 	} else if (!is_si_special(info)) {
@@ -889,6 +903,20 @@ out_set:
 	return 0;
 }
 
+static int send_signal(int sig, struct siginfo *info, struct task_struct *t,
+			int group)
+{
+	int from_ancestor_ns = 0;
+
+#ifdef CONFIG_PID_NS
+	if (!is_si_special(info) && SI_FROMUSER(info) &&
+			task_pid_nr_ns(current, task_active_pid_ns(t)) <= 0)
+		from_ancestor_ns = 1;
+#endif
+
+	return __send_signal(sig, info, t, group, from_ancestor_ns);
+}
+
 int print_fatal_signals;
 
 static void print_fatal_signal(struct pt_regs *regs, int signr)
@@ -1133,7 +1161,7 @@ int kill_pid_info_as_uid(int sig, struct siginfo *info, struct pid *pid,
 	if (sig && p->sighand) {
 		unsigned long flags;
 		spin_lock_irqsave(&p->sighand->siglock, flags);
-		ret = __group_send_sig_info(sig, info, p);
+		ret = __send_signal(sig, info, p, 1, 0);
 		spin_unlock_irqrestore(&p->sighand->siglock, flags);
 	}
 out_unlock:
@@ -1320,7 +1348,7 @@ int send_sigqueue(struct sigqueue *q, struct task_struct *t, int group)
 		goto ret;
 
 	ret = 1; /* the signal is ignored */
-	if (!prepare_signal(sig, t))
+	if (!prepare_signal(sig, t, 0))
 		goto out;
 
 	ret = 0;
@@ -1844,9 +1872,16 @@ relock:
 
 		/*
 		 * Global init gets no signals it doesn't want.
+		 * Container-init gets no signals it doesn't want from same
+		 * container.
+		 *
+		 * Note that if global/container-init sees a sig_kernel_only()
+		 * signal here, the signal must have been generated internally
+		 * or must have come from an ancestor namespace. In either
+		 * case, the signal cannot be dropped.
 		 */
 		if (unlikely(signal->flags & SIGNAL_UNKILLABLE) &&
-		    !signal_group_exit(signal))
+				!sig_kernel_only(signr))
 			continue;
 
 		if (sig_kernel_stop(signr)) {
diff --git a/kernel/slow-work.c b/kernel/slow-work.c
new file mode 100644
index 000000000000..cf2bc01186ef
--- /dev/null
+++ b/kernel/slow-work.c
@@ -0,0 +1,640 @@
+/* Worker thread pool for slow items, such as filesystem lookups or mkdirs
+ *
+ * Copyright (C) 2008 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ *
+ * See Documentation/slow-work.txt
+ */
+
+#include <linux/module.h>
+#include <linux/slow-work.h>
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/wait.h>
+
+#define SLOW_WORK_CULL_TIMEOUT (5 * HZ)	/* cull threads 5s after running out of
+					 * things to do */
+#define SLOW_WORK_OOM_TIMEOUT (5 * HZ)	/* can't start new threads for 5s after
+					 * OOM */
+
+static void slow_work_cull_timeout(unsigned long);
+static void slow_work_oom_timeout(unsigned long);
+
+#ifdef CONFIG_SYSCTL
+static int slow_work_min_threads_sysctl(struct ctl_table *, int, struct file *,
+					void __user *, size_t *, loff_t *);
+
+static int slow_work_max_threads_sysctl(struct ctl_table *, int , struct file *,
+					void __user *, size_t *, loff_t *);
+#endif
+
+/*
+ * The pool of threads has at least min threads in it as long as someone is
+ * using the facility, and may have as many as max.
+ *
+ * A portion of the pool may be processing very slow operations.
+ */
+static unsigned slow_work_min_threads = 2;
+static unsigned slow_work_max_threads = 4;
+static unsigned vslow_work_proportion = 50; /* % of threads that may process
+					     * very slow work */
+
+#ifdef CONFIG_SYSCTL
+static const int slow_work_min_min_threads = 2;
+static int slow_work_max_max_threads = 255;
+static const int slow_work_min_vslow = 1;
+static const int slow_work_max_vslow = 99;
+
+ctl_table slow_work_sysctls[] = {
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "min-threads",
+		.data		= &slow_work_min_threads,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= slow_work_min_threads_sysctl,
+		.extra1		= (void *) &slow_work_min_min_threads,
+		.extra2		= &slow_work_max_threads,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "max-threads",
+		.data		= &slow_work_max_threads,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= slow_work_max_threads_sysctl,
+		.extra1		= &slow_work_min_threads,
+		.extra2		= (void *) &slow_work_max_max_threads,
+	},
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "vslow-percentage",
+		.data		= &vslow_work_proportion,
+		.maxlen		= sizeof(unsigned),
+		.mode		= 0644,
+		.proc_handler	= &proc_dointvec_minmax,
+		.extra1		= (void *) &slow_work_min_vslow,
+		.extra2		= (void *) &slow_work_max_vslow,
+	},
+	{ .ctl_name = 0 }
+};
+#endif
+
+/*
+ * The active state of the thread pool
+ */
+static atomic_t slow_work_thread_count;
+static atomic_t vslow_work_executing_count;
+
+static bool slow_work_may_not_start_new_thread;
+static bool slow_work_cull; /* cull a thread due to lack of activity */
+static DEFINE_TIMER(slow_work_cull_timer, slow_work_cull_timeout, 0, 0);
+static DEFINE_TIMER(slow_work_oom_timer, slow_work_oom_timeout, 0, 0);
+static struct slow_work slow_work_new_thread; /* new thread starter */
+
+/*
+ * The queues of work items and the lock governing access to them.  These are
+ * shared between all the CPUs.  It doesn't make sense to have per-CPU queues
+ * as the number of threads bears no relation to the number of CPUs.
+ *
+ * There are two queues of work items: one for slow work items, and one for
+ * very slow work items.
+ */
+static LIST_HEAD(slow_work_queue);
+static LIST_HEAD(vslow_work_queue);
+static DEFINE_SPINLOCK(slow_work_queue_lock);
+
+/*
+ * The thread controls.  A variable used to signal to the threads that they
+ * should exit when the queue is empty, a waitqueue used by the threads to wait
+ * for signals, and a completion set by the last thread to exit.
+ */
+static bool slow_work_threads_should_exit;
+static DECLARE_WAIT_QUEUE_HEAD(slow_work_thread_wq);
+static DECLARE_COMPLETION(slow_work_last_thread_exited);
+
+/*
+ * The number of users of the thread pool and its lock.  Whilst this is zero we
+ * have no threads hanging around, and when this reaches zero, we wait for all
+ * active or queued work items to complete and kill all the threads we do have.
+ */
+static int slow_work_user_count;
+static DEFINE_MUTEX(slow_work_user_lock);
+
+/*
+ * Calculate the maximum number of active threads in the pool that are
+ * permitted to process very slow work items.
+ *
+ * The answer is rounded up to at least 1, but may not equal or exceed the
+ * maximum number of the threads in the pool.  This means we always have at
+ * least one thread that can process slow work items, and we always have at
+ * least one thread that won't get tied up doing so.
+ */
+static unsigned slow_work_calc_vsmax(void)
+{
+	unsigned vsmax;
+
+	vsmax = atomic_read(&slow_work_thread_count) * vslow_work_proportion;
+	vsmax /= 100;
+	vsmax = max(vsmax, 1U);
+	return min(vsmax, slow_work_max_threads - 1);
+}
+
+/*
+ * Attempt to execute stuff queued on a slow thread.  Return true if we managed
+ * it, false if there was nothing to do.
+ */
+static bool slow_work_execute(void)
+{
+	struct slow_work *work = NULL;
+	unsigned vsmax;
+	bool very_slow;
+
+	vsmax = slow_work_calc_vsmax();
+
+	/* see if we can schedule a new thread to be started if we're not
+	 * keeping up with the work */
+	if (!waitqueue_active(&slow_work_thread_wq) &&
+	    (!list_empty(&slow_work_queue) || !list_empty(&vslow_work_queue)) &&
+	    atomic_read(&slow_work_thread_count) < slow_work_max_threads &&
+	    !slow_work_may_not_start_new_thread)
+		slow_work_enqueue(&slow_work_new_thread);
+
+	/* find something to execute */
+	spin_lock_irq(&slow_work_queue_lock);
+	if (!list_empty(&vslow_work_queue) &&
+	    atomic_read(&vslow_work_executing_count) < vsmax) {
+		work = list_entry(vslow_work_queue.next,
+				  struct slow_work, link);
+		if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags))
+			BUG();
+		list_del_init(&work->link);
+		atomic_inc(&vslow_work_executing_count);
+		very_slow = true;
+	} else if (!list_empty(&slow_work_queue)) {
+		work = list_entry(slow_work_queue.next,
+				  struct slow_work, link);
+		if (test_and_set_bit_lock(SLOW_WORK_EXECUTING, &work->flags))
+			BUG();
+		list_del_init(&work->link);
+		very_slow = false;
+	} else {
+		very_slow = false; /* avoid the compiler warning */
+	}
+	spin_unlock_irq(&slow_work_queue_lock);
+
+	if (!work)
+		return false;
+
+	if (!test_and_clear_bit(SLOW_WORK_PENDING, &work->flags))
+		BUG();
+
+	work->ops->execute(work);
+
+	if (very_slow)
+		atomic_dec(&vslow_work_executing_count);
+	clear_bit_unlock(SLOW_WORK_EXECUTING, &work->flags);
+
+	/* if someone tried to enqueue the item whilst we were executing it,
+	 * then it'll be left unenqueued to avoid multiple threads trying to
+	 * execute it simultaneously
+	 *
+	 * there is, however, a race between us testing the pending flag and
+	 * getting the spinlock, and between the enqueuer setting the pending
+	 * flag and getting the spinlock, so we use a deferral bit to tell us
+	 * if the enqueuer got there first
+	 */
+	if (test_bit(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irq(&slow_work_queue_lock);
+
+		if (!test_bit(SLOW_WORK_EXECUTING, &work->flags) &&
+		    test_and_clear_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags))
+			goto auto_requeue;
+
+		spin_unlock_irq(&slow_work_queue_lock);
+	}
+
+	work->ops->put_ref(work);
+	return true;
+
+auto_requeue:
+	/* we must complete the enqueue operation
+	 * - we transfer our ref on the item back to the appropriate queue
+	 * - don't wake another thread up as we're awake already
+	 */
+	if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
+		list_add_tail(&work->link, &vslow_work_queue);
+	else
+		list_add_tail(&work->link, &slow_work_queue);
+	spin_unlock_irq(&slow_work_queue_lock);
+	return true;
+}
+
+/**
+ * slow_work_enqueue - Schedule a slow work item for processing
+ * @work: The work item to queue
+ *
+ * Schedule a slow work item for processing.  If the item is already undergoing
+ * execution, this guarantees not to re-enter the execution routine until the
+ * first execution finishes.
+ *
+ * The item is pinned by this function as it retains a reference to it, managed
+ * through the item operations.  The item is unpinned once it has been
+ * executed.
+ *
+ * An item may hog the thread that is running it for a relatively large amount
+ * of time, sufficient, for example, to perform several lookup, mkdir, create
+ * and setxattr operations.  It may sleep on I/O and may sleep to obtain locks.
+ *
+ * Conversely, if a number of items are awaiting processing, it may take some
+ * time before any given item is given attention.  The number of threads in the
+ * pool may be increased to deal with demand, but only up to a limit.
+ *
+ * If SLOW_WORK_VERY_SLOW is set on the work item, then it will be placed in
+ * the very slow queue, from which only a portion of the threads will be
+ * allowed to pick items to execute.  This ensures that very slow items won't
+ * overly block ones that are just ordinarily slow.
+ *
+ * Returns 0 if successful, -EAGAIN if not.
+ */
+int slow_work_enqueue(struct slow_work *work)
+{
+	unsigned long flags;
+
+	BUG_ON(slow_work_user_count <= 0);
+	BUG_ON(!work);
+	BUG_ON(!work->ops);
+	BUG_ON(!work->ops->get_ref);
+
+	/* when honouring an enqueue request, we only promise that we will run
+	 * the work function in the future; we do not promise to run it once
+	 * per enqueue request
+	 *
+	 * we use the PENDING bit to merge together repeat requests without
+	 * having to disable IRQs and take the spinlock, whilst still
+	 * maintaining our promise
+	 */
+	if (!test_and_set_bit_lock(SLOW_WORK_PENDING, &work->flags)) {
+		spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+		/* we promise that we will not attempt to execute the work
+		 * function in more than one thread simultaneously
+		 *
+		 * this, however, leaves us with a problem if we're asked to
+		 * enqueue the work whilst someone is executing the work
+		 * function as simply queueing the work immediately means that
+		 * another thread may try executing it whilst it is already
+		 * under execution
+		 *
+		 * to deal with this, we set the ENQ_DEFERRED bit instead of
+		 * enqueueing, and the thread currently executing the work
+		 * function will enqueue the work item when the work function
+		 * returns and it has cleared the EXECUTING bit
+		 */
+		if (test_bit(SLOW_WORK_EXECUTING, &work->flags)) {
+			set_bit(SLOW_WORK_ENQ_DEFERRED, &work->flags);
+		} else {
+			if (work->ops->get_ref(work) < 0)
+				goto cant_get_ref;
+			if (test_bit(SLOW_WORK_VERY_SLOW, &work->flags))
+				list_add_tail(&work->link, &vslow_work_queue);
+			else
+				list_add_tail(&work->link, &slow_work_queue);
+			wake_up(&slow_work_thread_wq);
+		}
+
+		spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	}
+	return 0;
+
+cant_get_ref:
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return -EAGAIN;
+}
+EXPORT_SYMBOL(slow_work_enqueue);
+
+/*
+ * Worker thread culling algorithm
+ */
+static bool slow_work_cull_thread(void)
+{
+	unsigned long flags;
+	bool do_cull = false;
+
+	spin_lock_irqsave(&slow_work_queue_lock, flags);
+
+	if (slow_work_cull) {
+		slow_work_cull = false;
+
+		if (list_empty(&slow_work_queue) &&
+		    list_empty(&vslow_work_queue) &&
+		    atomic_read(&slow_work_thread_count) >
+		    slow_work_min_threads) {
+			mod_timer(&slow_work_cull_timer,
+				  jiffies + SLOW_WORK_CULL_TIMEOUT);
+			do_cull = true;
+		}
+	}
+
+	spin_unlock_irqrestore(&slow_work_queue_lock, flags);
+	return do_cull;
+}
+
+/*
+ * Determine if there is slow work available for dispatch
+ */
+static inline bool slow_work_available(int vsmax)
+{
+	return !list_empty(&slow_work_queue) ||
+		(!list_empty(&vslow_work_queue) &&
+		 atomic_read(&vslow_work_executing_count) < vsmax);
+}
+
+/*
+ * Worker thread dispatcher
+ */
+static int slow_work_thread(void *_data)
+{
+	int vsmax;
+
+	DEFINE_WAIT(wait);
+
+	set_freezable();
+	set_user_nice(current, -5);
+
+	for (;;) {
+		vsmax = vslow_work_proportion;
+		vsmax *= atomic_read(&slow_work_thread_count);
+		vsmax /= 100;
+
+		prepare_to_wait(&slow_work_thread_wq, &wait,
+				TASK_INTERRUPTIBLE);
+		if (!freezing(current) &&
+		    !slow_work_threads_should_exit &&
+		    !slow_work_available(vsmax) &&
+		    !slow_work_cull)
+			schedule();
+		finish_wait(&slow_work_thread_wq, &wait);
+
+		try_to_freeze();
+
+		vsmax = vslow_work_proportion;
+		vsmax *= atomic_read(&slow_work_thread_count);
+		vsmax /= 100;
+
+		if (slow_work_available(vsmax) && slow_work_execute()) {
+			cond_resched();
+			if (list_empty(&slow_work_queue) &&
+			    list_empty(&vslow_work_queue) &&
+			    atomic_read(&slow_work_thread_count) >
+			    slow_work_min_threads)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+			continue;
+		}
+
+		if (slow_work_threads_should_exit)
+			break;
+
+		if (slow_work_cull && slow_work_cull_thread())
+			break;
+	}
+
+	if (atomic_dec_and_test(&slow_work_thread_count))
+		complete_and_exit(&slow_work_last_thread_exited, 0);
+	return 0;
+}
+
+/*
+ * Handle thread cull timer expiration
+ */
+static void slow_work_cull_timeout(unsigned long data)
+{
+	slow_work_cull = true;
+	wake_up(&slow_work_thread_wq);
+}
+
+/*
+ * Get a reference on slow work thread starter
+ */
+static int slow_work_new_thread_get_ref(struct slow_work *work)
+{
+	return 0;
+}
+
+/*
+ * Drop a reference on slow work thread starter
+ */
+static void slow_work_new_thread_put_ref(struct slow_work *work)
+{
+}
+
+/*
+ * Start a new slow work thread
+ */
+static void slow_work_new_thread_execute(struct slow_work *work)
+{
+	struct task_struct *p;
+
+	if (slow_work_threads_should_exit)
+		return;
+
+	if (atomic_read(&slow_work_thread_count) >= slow_work_max_threads)
+		return;
+
+	if (!mutex_trylock(&slow_work_user_lock))
+		return;
+
+	slow_work_may_not_start_new_thread = true;
+	atomic_inc(&slow_work_thread_count);
+	p = kthread_run(slow_work_thread, NULL, "kslowd");
+	if (IS_ERR(p)) {
+		printk(KERN_DEBUG "Slow work thread pool: OOM\n");
+		if (atomic_dec_and_test(&slow_work_thread_count))
+			BUG(); /* we're running on a slow work thread... */
+		mod_timer(&slow_work_oom_timer,
+			  jiffies + SLOW_WORK_OOM_TIMEOUT);
+	} else {
+		/* ratelimit the starting of new threads */
+		mod_timer(&slow_work_oom_timer, jiffies + 1);
+	}
+
+	mutex_unlock(&slow_work_user_lock);
+}
+
+static const struct slow_work_ops slow_work_new_thread_ops = {
+	.get_ref	= slow_work_new_thread_get_ref,
+	.put_ref	= slow_work_new_thread_put_ref,
+	.execute	= slow_work_new_thread_execute,
+};
+
+/*
+ * post-OOM new thread start suppression expiration
+ */
+static void slow_work_oom_timeout(unsigned long data)
+{
+	slow_work_may_not_start_new_thread = false;
+}
+
+#ifdef CONFIG_SYSCTL
+/*
+ * Handle adjustment of the minimum number of threads
+ */
+static int slow_work_min_threads_sysctl(struct ctl_table *table, int write,
+					struct file *filp, void __user *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int n;
+
+	if (ret == 0) {
+		mutex_lock(&slow_work_user_lock);
+		if (slow_work_user_count > 0) {
+			/* see if we need to start or stop threads */
+			n = atomic_read(&slow_work_thread_count) -
+				slow_work_min_threads;
+
+			if (n < 0 && !slow_work_may_not_start_new_thread)
+				slow_work_enqueue(&slow_work_new_thread);
+			else if (n > 0)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+		}
+		mutex_unlock(&slow_work_user_lock);
+	}
+
+	return ret;
+}
+
+/*
+ * Handle adjustment of the maximum number of threads
+ */
+static int slow_work_max_threads_sysctl(struct ctl_table *table, int write,
+					struct file *filp, void __user *buffer,
+					size_t *lenp, loff_t *ppos)
+{
+	int ret = proc_dointvec_minmax(table, write, filp, buffer, lenp, ppos);
+	int n;
+
+	if (ret == 0) {
+		mutex_lock(&slow_work_user_lock);
+		if (slow_work_user_count > 0) {
+			/* see if we need to stop threads */
+			n = slow_work_max_threads -
+				atomic_read(&slow_work_thread_count);
+
+			if (n < 0)
+				mod_timer(&slow_work_cull_timer,
+					  jiffies + SLOW_WORK_CULL_TIMEOUT);
+		}
+		mutex_unlock(&slow_work_user_lock);
+	}
+
+	return ret;
+}
+#endif /* CONFIG_SYSCTL */
+
+/**
+ * slow_work_register_user - Register a user of the facility
+ *
+ * Register a user of the facility, starting up the initial threads if there
+ * aren't any other users at this point.  This will return 0 if successful, or
+ * an error if not.
+ */
+int slow_work_register_user(void)
+{
+	struct task_struct *p;
+	int loop;
+
+	mutex_lock(&slow_work_user_lock);
+
+	if (slow_work_user_count == 0) {
+		printk(KERN_NOTICE "Slow work thread pool: Starting up\n");
+		init_completion(&slow_work_last_thread_exited);
+
+		slow_work_threads_should_exit = false;
+		slow_work_init(&slow_work_new_thread,
+			       &slow_work_new_thread_ops);
+		slow_work_may_not_start_new_thread = false;
+		slow_work_cull = false;
+
+		/* start the minimum number of threads */
+		for (loop = 0; loop < slow_work_min_threads; loop++) {
+			atomic_inc(&slow_work_thread_count);
+			p = kthread_run(slow_work_thread, NULL, "kslowd");
+			if (IS_ERR(p))
+				goto error;
+		}
+		printk(KERN_NOTICE "Slow work thread pool: Ready\n");
+	}
+
+	slow_work_user_count++;
+	mutex_unlock(&slow_work_user_lock);
+	return 0;
+
+error:
+	if (atomic_dec_and_test(&slow_work_thread_count))
+		complete(&slow_work_last_thread_exited);
+	if (loop > 0) {
+		printk(KERN_ERR "Slow work thread pool:"
+		       " Aborting startup on ENOMEM\n");
+		slow_work_threads_should_exit = true;
+		wake_up_all(&slow_work_thread_wq);
+		wait_for_completion(&slow_work_last_thread_exited);
+		printk(KERN_ERR "Slow work thread pool: Aborted\n");
+	}
+	mutex_unlock(&slow_work_user_lock);
+	return PTR_ERR(p);
+}
+EXPORT_SYMBOL(slow_work_register_user);
+
+/**
+ * slow_work_unregister_user - Unregister a user of the facility
+ *
+ * Unregister a user of the facility, killing all the threads if this was the
+ * last one.
+ */
+void slow_work_unregister_user(void)
+{
+	mutex_lock(&slow_work_user_lock);
+
+	BUG_ON(slow_work_user_count <= 0);
+
+	slow_work_user_count--;
+	if (slow_work_user_count == 0) {
+		printk(KERN_NOTICE "Slow work thread pool: Shutting down\n");
+		slow_work_threads_should_exit = true;
+		wake_up_all(&slow_work_thread_wq);
+		wait_for_completion(&slow_work_last_thread_exited);
+		printk(KERN_NOTICE "Slow work thread pool:"
+		       " Shut down complete\n");
+	}
+
+	del_timer_sync(&slow_work_cull_timer);
+
+	mutex_unlock(&slow_work_user_lock);
+}
+EXPORT_SYMBOL(slow_work_unregister_user);
+
+/*
+ * Initialise the slow work facility
+ */
+static int __init init_slow_work(void)
+{
+	unsigned nr_cpus = num_possible_cpus();
+
+	if (slow_work_max_threads < nr_cpus)
+		slow_work_max_threads = nr_cpus;
+#ifdef CONFIG_SYSCTL
+	if (slow_work_max_max_threads < nr_cpus * 2)
+		slow_work_max_max_threads = nr_cpus * 2;
+#endif
+	return 0;
+}
+
+subsys_initcall(init_slow_work);
diff --git a/kernel/smp.c b/kernel/smp.c
index bbedbb7efe32..858baac568ee 100644
--- a/kernel/smp.c
+++ b/kernel/smp.c
@@ -2,40 +2,82 @@
  * Generic helpers for smp ipi calls
  *
  * (C) Jens Axboe <jens.axboe@oracle.com> 2008
- *
  */
-#include <linux/init.h>
-#include <linux/module.h>
-#include <linux/percpu.h>
 #include <linux/rcupdate.h>
 #include <linux/rculist.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
 #include <linux/smp.h>
+#include <linux/cpu.h>
 
 static DEFINE_PER_CPU(struct call_single_queue, call_single_queue);
-static LIST_HEAD(call_function_queue);
-__cacheline_aligned_in_smp DEFINE_SPINLOCK(call_function_lock);
+
+static struct {
+	struct list_head	queue;
+	spinlock_t		lock;
+} call_function __cacheline_aligned_in_smp =
+	{
+		.queue		= LIST_HEAD_INIT(call_function.queue),
+		.lock		= __SPIN_LOCK_UNLOCKED(call_function.lock),
+	};
 
 enum {
-	CSD_FLAG_WAIT		= 0x01,
-	CSD_FLAG_ALLOC		= 0x02,
-	CSD_FLAG_LOCK		= 0x04,
+	CSD_FLAG_LOCK		= 0x01,
 };
 
 struct call_function_data {
-	struct call_single_data csd;
-	spinlock_t lock;
-	unsigned int refs;
-	struct rcu_head rcu_head;
-	unsigned long cpumask_bits[];
+	struct call_single_data	csd;
+	spinlock_t		lock;
+	unsigned int		refs;
+	cpumask_var_t		cpumask;
 };
 
 struct call_single_queue {
-	struct list_head list;
-	spinlock_t lock;
+	struct list_head	list;
+	spinlock_t		lock;
+};
+
+static DEFINE_PER_CPU(struct call_function_data, cfd_data) = {
+	.lock			= __SPIN_LOCK_UNLOCKED(cfd_data.lock),
+};
+
+static int
+hotplug_cfd(struct notifier_block *nfb, unsigned long action, void *hcpu)
+{
+	long cpu = (long)hcpu;
+	struct call_function_data *cfd = &per_cpu(cfd_data, cpu);
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		if (!alloc_cpumask_var_node(&cfd->cpumask, GFP_KERNEL,
+				cpu_to_node(cpu)))
+			return NOTIFY_BAD;
+		break;
+
+#ifdef CONFIG_CPU_HOTPLUG
+	case CPU_UP_CANCELED:
+	case CPU_UP_CANCELED_FROZEN:
+
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		free_cpumask_var(cfd->cpumask);
+		break;
+#endif
+	};
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block __cpuinitdata hotplug_cfd_notifier = {
+	.notifier_call		= hotplug_cfd,
 };
 
 static int __cpuinit init_call_single_data(void)
 {
+	void *cpu = (void *)(long)smp_processor_id();
 	int i;
 
 	for_each_possible_cpu(i) {
@@ -44,29 +86,63 @@ static int __cpuinit init_call_single_data(void)
 		spin_lock_init(&q->lock);
 		INIT_LIST_HEAD(&q->list);
 	}
+
+	hotplug_cfd(&hotplug_cfd_notifier, CPU_UP_PREPARE, cpu);
+	register_cpu_notifier(&hotplug_cfd_notifier);
+
 	return 0;
 }
 early_initcall(init_call_single_data);
 
-static void csd_flag_wait(struct call_single_data *data)
+/*
+ * csd_lock/csd_unlock used to serialize access to per-cpu csd resources
+ *
+ * For non-synchronous ipi calls the csd can still be in use by the
+ * previous function call. For multi-cpu calls its even more interesting
+ * as we'll have to ensure no other cpu is observing our csd.
+ */
+static void csd_lock_wait(struct call_single_data *data)
 {
-	/* Wait for response */
-	do {
-		if (!(data->flags & CSD_FLAG_WAIT))
-			break;
+	while (data->flags & CSD_FLAG_LOCK)
 		cpu_relax();
-	} while (1);
+}
+
+static void csd_lock(struct call_single_data *data)
+{
+	csd_lock_wait(data);
+	data->flags = CSD_FLAG_LOCK;
+
+	/*
+	 * prevent CPU from reordering the above assignment
+	 * to ->flags with any subsequent assignments to other
+	 * fields of the specified call_single_data structure:
+	 */
+	smp_mb();
+}
+
+static void csd_unlock(struct call_single_data *data)
+{
+	WARN_ON(!(data->flags & CSD_FLAG_LOCK));
+
+	/*
+	 * ensure we're all done before releasing data:
+	 */
+	smp_mb();
+
+	data->flags &= ~CSD_FLAG_LOCK;
 }
 
 /*
- * Insert a previously allocated call_single_data element for execution
- * on the given CPU. data must already have ->func, ->info, and ->flags set.
+ * Insert a previously allocated call_single_data element
+ * for execution on the given CPU. data must already have
+ * ->func, ->info, and ->flags set.
  */
-static void generic_exec_single(int cpu, struct call_single_data *data)
+static
+void generic_exec_single(int cpu, struct call_single_data *data, int wait)
 {
 	struct call_single_queue *dst = &per_cpu(call_single_queue, cpu);
-	int wait = data->flags & CSD_FLAG_WAIT, ipi;
 	unsigned long flags;
+	int ipi;
 
 	spin_lock_irqsave(&dst->lock, flags);
 	ipi = list_empty(&dst->list);
@@ -74,24 +150,21 @@ static void generic_exec_single(int cpu, struct call_single_data *data)
 	spin_unlock_irqrestore(&dst->lock, flags);
 
 	/*
-	 * Make the list addition visible before sending the ipi.
+	 * The list addition should be visible before sending the IPI
+	 * handler locks the list to pull the entry off it because of
+	 * normal cache coherency rules implied by spinlocks.
+	 *
+	 * If IPIs can go out of order to the cache coherency protocol
+	 * in an architecture, sufficient synchronisation should be added
+	 * to arch code to make it appear to obey cache coherency WRT
+	 * locking and barrier primitives. Generic code isn't really
+	 * equipped to do the right thing...
 	 */
-	smp_mb();
-
 	if (ipi)
 		arch_send_call_function_single_ipi(cpu);
 
 	if (wait)
-		csd_flag_wait(data);
-}
-
-static void rcu_free_call_data(struct rcu_head *head)
-{
-	struct call_function_data *data;
-
-	data = container_of(head, struct call_function_data, rcu_head);
-
-	kfree(data);
+		csd_lock_wait(data);
 }
 
 /*
@@ -104,99 +177,83 @@ void generic_smp_call_function_interrupt(void)
 	int cpu = get_cpu();
 
 	/*
-	 * It's ok to use list_for_each_rcu() here even though we may delete
-	 * 'pos', since list_del_rcu() doesn't clear ->next
+	 * Ensure entry is visible on call_function_queue after we have
+	 * entered the IPI. See comment in smp_call_function_many.
+	 * If we don't have this, then we may miss an entry on the list
+	 * and never get another IPI to process it.
+	 */
+	smp_mb();
+
+	/*
+	 * It's ok to use list_for_each_rcu() here even though we may
+	 * delete 'pos', since list_del_rcu() doesn't clear ->next
 	 */
-	rcu_read_lock();
-	list_for_each_entry_rcu(data, &call_function_queue, csd.list) {
+	list_for_each_entry_rcu(data, &call_function.queue, csd.list) {
 		int refs;
 
-		if (!cpumask_test_cpu(cpu, to_cpumask(data->cpumask_bits)))
+		spin_lock(&data->lock);
+		if (!cpumask_test_cpu(cpu, data->cpumask)) {
+			spin_unlock(&data->lock);
 			continue;
+		}
+		cpumask_clear_cpu(cpu, data->cpumask);
+		spin_unlock(&data->lock);
 
 		data->csd.func(data->csd.info);
 
 		spin_lock(&data->lock);
-		cpumask_clear_cpu(cpu, to_cpumask(data->cpumask_bits));
 		WARN_ON(data->refs == 0);
-		data->refs--;
-		refs = data->refs;
+		refs = --data->refs;
+		if (!refs) {
+			spin_lock(&call_function.lock);
+			list_del_rcu(&data->csd.list);
+			spin_unlock(&call_function.lock);
+		}
 		spin_unlock(&data->lock);
 
 		if (refs)
 			continue;
 
-		spin_lock(&call_function_lock);
-		list_del_rcu(&data->csd.list);
-		spin_unlock(&call_function_lock);
-
-		if (data->csd.flags & CSD_FLAG_WAIT) {
-			/*
-			 * serialize stores to data with the flag clear
-			 * and wakeup
-			 */
-			smp_wmb();
-			data->csd.flags &= ~CSD_FLAG_WAIT;
-		}
-		if (data->csd.flags & CSD_FLAG_ALLOC)
-			call_rcu(&data->rcu_head, rcu_free_call_data);
+		csd_unlock(&data->csd);
 	}
-	rcu_read_unlock();
 
 	put_cpu();
 }
 
 /*
- * Invoked by arch to handle an IPI for call function single. Must be called
- * from the arch with interrupts disabled.
+ * Invoked by arch to handle an IPI for call function single. Must be
+ * called from the arch with interrupts disabled.
  */
 void generic_smp_call_function_single_interrupt(void)
 {
 	struct call_single_queue *q = &__get_cpu_var(call_single_queue);
+	unsigned int data_flags;
 	LIST_HEAD(list);
 
-	/*
-	 * Need to see other stores to list head for checking whether
-	 * list is empty without holding q->lock
-	 */
-	smp_read_barrier_depends();
-	while (!list_empty(&q->list)) {
-		unsigned int data_flags;
-
-		spin_lock(&q->lock);
-		list_replace_init(&q->list, &list);
-		spin_unlock(&q->lock);
-
-		while (!list_empty(&list)) {
-			struct call_single_data *data;
-
-			data = list_entry(list.next, struct call_single_data,
-						list);
-			list_del(&data->list);
-
-			/*
-			 * 'data' can be invalid after this call if
-			 * flags == 0 (when called through
-			 * generic_exec_single(), so save them away before
-			 * making the call.
-			 */
-			data_flags = data->flags;
-
-			data->func(data->info);
-
-			if (data_flags & CSD_FLAG_WAIT) {
-				smp_wmb();
-				data->flags &= ~CSD_FLAG_WAIT;
-			} else if (data_flags & CSD_FLAG_LOCK) {
-				smp_wmb();
-				data->flags &= ~CSD_FLAG_LOCK;
-			} else if (data_flags & CSD_FLAG_ALLOC)
-				kfree(data);
-		}
+	spin_lock(&q->lock);
+	list_replace_init(&q->list, &list);
+	spin_unlock(&q->lock);
+
+	while (!list_empty(&list)) {
+		struct call_single_data *data;
+
+		data = list_entry(list.next, struct call_single_data, list);
+		list_del(&data->list);
+
+		/*
+		 * 'data' can be invalid after this call if flags == 0
+		 * (when called through generic_exec_single()),
+		 * so save them away before making the call:
+		 */
+		data_flags = data->flags;
+
+		data->func(data->info);
+
 		/*
-		 * See comment on outer loop
+		 * Unlocked CSDs are valid through generic_exec_single():
 		 */
-		smp_read_barrier_depends();
+		if (data_flags & CSD_FLAG_LOCK)
+			csd_unlock(data);
 	}
 }
 
@@ -215,65 +272,45 @@ static DEFINE_PER_CPU(struct call_single_data, csd_data);
 int smp_call_function_single(int cpu, void (*func) (void *info), void *info,
 			     int wait)
 {
-	struct call_single_data d;
+	struct call_single_data d = {
+		.flags = 0,
+	};
 	unsigned long flags;
-	/* prevent preemption and reschedule on another processor,
-	   as well as CPU removal */
-	int me = get_cpu();
+	int this_cpu;
 	int err = 0;
 
+	/*
+	 * prevent preemption and reschedule on another processor,
+	 * as well as CPU removal
+	 */
+	this_cpu = get_cpu();
+
 	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
+	WARN_ON_ONCE(irqs_disabled() && !oops_in_progress);
 
-	if (cpu == me) {
+	if (cpu == this_cpu) {
 		local_irq_save(flags);
 		func(info);
 		local_irq_restore(flags);
-	} else if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
-		struct call_single_data *data;
+	} else {
+		if ((unsigned)cpu < nr_cpu_ids && cpu_online(cpu)) {
+			struct call_single_data *data = &d;
+
+			if (!wait)
+				data = &__get_cpu_var(csd_data);
 
-		if (!wait) {
-			/*
-			 * We are calling a function on a single CPU
-			 * and we are not going to wait for it to finish.
-			 * We first try to allocate the data, but if we
-			 * fail, we fall back to use a per cpu data to pass
-			 * the information to that CPU. Since all callers
-			 * of this code will use the same data, we must
-			 * synchronize the callers to prevent a new caller
-			 * from corrupting the data before the callee
-			 * can access it.
-			 *
-			 * The CSD_FLAG_LOCK is used to let us know when
-			 * the IPI handler is done with the data.
-			 * The first caller will set it, and the callee
-			 * will clear it. The next caller must wait for
-			 * it to clear before we set it again. This
-			 * will make sure the callee is done with the
-			 * data before a new caller will use it.
-			 */
-			data = kmalloc(sizeof(*data), GFP_ATOMIC);
-			if (data)
-				data->flags = CSD_FLAG_ALLOC;
-			else {
-				data = &per_cpu(csd_data, me);
-				while (data->flags & CSD_FLAG_LOCK)
-					cpu_relax();
-				data->flags = CSD_FLAG_LOCK;
-			}
+			csd_lock(data);
+
+			data->func = func;
+			data->info = info;
+			generic_exec_single(cpu, data, wait);
 		} else {
-			data = &d;
-			data->flags = CSD_FLAG_WAIT;
+			err = -ENXIO;	/* CPU not online */
 		}
-
-		data->func = func;
-		data->info = info;
-		generic_exec_single(cpu, data);
-	} else {
-		err = -ENXIO;	/* CPU not online */
 	}
 
 	put_cpu();
+
 	return err;
 }
 EXPORT_SYMBOL(smp_call_function_single);
@@ -283,23 +320,26 @@ EXPORT_SYMBOL(smp_call_function_single);
  * @cpu: The CPU to run on.
  * @data: Pre-allocated and setup data structure
  *
- * Like smp_call_function_single(), but allow caller to pass in a pre-allocated
- * data structure. Useful for embedding @data inside other structures, for
- * instance.
- *
+ * Like smp_call_function_single(), but allow caller to pass in a
+ * pre-allocated data structure. Useful for embedding @data inside
+ * other structures, for instance.
  */
-void __smp_call_function_single(int cpu, struct call_single_data *data)
+void __smp_call_function_single(int cpu, struct call_single_data *data,
+				int wait)
 {
+	csd_lock(data);
+
 	/* Can deadlock when called with interrupts disabled */
-	WARN_ON((data->flags & CSD_FLAG_WAIT) && irqs_disabled());
+	WARN_ON_ONCE(wait && irqs_disabled() && !oops_in_progress);
 
-	generic_exec_single(cpu, data);
+	generic_exec_single(cpu, data, wait);
 }
 
-/* FIXME: Shim for archs using old arch_send_call_function_ipi API. */
+/* Deprecated: shim for archs using old arch_send_call_function_ipi API. */
+
 #ifndef arch_send_call_function_ipi_mask
-#define arch_send_call_function_ipi_mask(maskp) \
-	arch_send_call_function_ipi(*(maskp))
+# define arch_send_call_function_ipi_mask(maskp) \
+	 arch_send_call_function_ipi(*(maskp))
 #endif
 
 /**
@@ -307,7 +347,8 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
  * @mask: The set of cpus to run on (only runs on online subset).
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
  *
  * If @wait is true, then returns once @func has returned. Note that @wait
  * will be implicitly turned on in case of allocation failures, since
@@ -318,27 +359,27 @@ void __smp_call_function_single(int cpu, struct call_single_data *data)
  * must be disabled when calling this function.
  */
 void smp_call_function_many(const struct cpumask *mask,
-			    void (*func)(void *), void *info,
-			    bool wait)
+			    void (*func)(void *), void *info, bool wait)
 {
 	struct call_function_data *data;
 	unsigned long flags;
-	int cpu, next_cpu;
+	int cpu, next_cpu, this_cpu = smp_processor_id();
 
 	/* Can deadlock when called with interrupts disabled */
-	WARN_ON(irqs_disabled());
+	WARN_ON_ONCE(irqs_disabled() && !oops_in_progress);
 
-	/* So, what's a CPU they want?  Ignoring this one. */
+	/* So, what's a CPU they want? Ignoring this one. */
 	cpu = cpumask_first_and(mask, cpu_online_mask);
-	if (cpu == smp_processor_id())
+	if (cpu == this_cpu)
 		cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
+
 	/* No online cpus?  We're done. */
 	if (cpu >= nr_cpu_ids)
 		return;
 
 	/* Do we have another CPU which isn't us? */
 	next_cpu = cpumask_next_and(cpu, mask, cpu_online_mask);
-	if (next_cpu == smp_processor_id())
+	if (next_cpu == this_cpu)
 		next_cpu = cpumask_next_and(next_cpu, mask, cpu_online_mask);
 
 	/* Fastpath: do that cpu by itself. */
@@ -347,43 +388,40 @@ void smp_call_function_many(const struct cpumask *mask,
 		return;
 	}
 
-	data = kmalloc(sizeof(*data) + cpumask_size(), GFP_ATOMIC);
-	if (unlikely(!data)) {
-		/* Slow path. */
-		for_each_online_cpu(cpu) {
-			if (cpu == smp_processor_id())
-				continue;
-			if (cpumask_test_cpu(cpu, mask))
-				smp_call_function_single(cpu, func, info, wait);
-		}
-		return;
-	}
+	data = &__get_cpu_var(cfd_data);
+	csd_lock(&data->csd);
 
-	spin_lock_init(&data->lock);
-	data->csd.flags = CSD_FLAG_ALLOC;
-	if (wait)
-		data->csd.flags |= CSD_FLAG_WAIT;
+	spin_lock_irqsave(&data->lock, flags);
 	data->csd.func = func;
 	data->csd.info = info;
-	cpumask_and(to_cpumask(data->cpumask_bits), mask, cpu_online_mask);
-	cpumask_clear_cpu(smp_processor_id(), to_cpumask(data->cpumask_bits));
-	data->refs = cpumask_weight(to_cpumask(data->cpumask_bits));
+	cpumask_and(data->cpumask, mask, cpu_online_mask);
+	cpumask_clear_cpu(this_cpu, data->cpumask);
+	data->refs = cpumask_weight(data->cpumask);
 
-	spin_lock_irqsave(&call_function_lock, flags);
-	list_add_tail_rcu(&data->csd.list, &call_function_queue);
-	spin_unlock_irqrestore(&call_function_lock, flags);
+	spin_lock(&call_function.lock);
+	/*
+	 * Place entry at the _HEAD_ of the list, so that any cpu still
+	 * observing the entry in generic_smp_call_function_interrupt()
+	 * will not miss any other list entries:
+	 */
+	list_add_rcu(&data->csd.list, &call_function.queue);
+	spin_unlock(&call_function.lock);
+
+	spin_unlock_irqrestore(&data->lock, flags);
 
 	/*
 	 * Make the list addition visible before sending the ipi.
+	 * (IPIs must obey or appear to obey normal Linux cache
+	 * coherency rules -- see comment in generic_exec_single).
 	 */
 	smp_mb();
 
 	/* Send a message to all CPUs in the map */
-	arch_send_call_function_ipi_mask(to_cpumask(data->cpumask_bits));
+	arch_send_call_function_ipi_mask(data->cpumask);
 
-	/* optionally wait for the CPUs to complete */
+	/* Optionally wait for the CPUs to complete */
 	if (wait)
-		csd_flag_wait(&data->csd);
+		csd_lock_wait(&data->csd);
 }
 EXPORT_SYMBOL(smp_call_function_many);
 
@@ -391,7 +429,8 @@ EXPORT_SYMBOL(smp_call_function_many);
  * smp_call_function(): Run a function on all other CPUs.
  * @func: The function to run. This must be fast and non-blocking.
  * @info: An arbitrary pointer to pass to the function.
- * @wait: If true, wait (atomically) until function has completed on other CPUs.
+ * @wait: If true, wait (atomically) until function has completed
+ *        on other CPUs.
  *
  * Returns 0.
  *
@@ -407,26 +446,27 @@ int smp_call_function(void (*func)(void *), void *info, int wait)
 	preempt_disable();
 	smp_call_function_many(cpu_online_mask, func, info, wait);
 	preempt_enable();
+
 	return 0;
 }
 EXPORT_SYMBOL(smp_call_function);
 
 void ipi_call_lock(void)
 {
-	spin_lock(&call_function_lock);
+	spin_lock(&call_function.lock);
 }
 
 void ipi_call_unlock(void)
 {
-	spin_unlock(&call_function_lock);
+	spin_unlock(&call_function.lock);
 }
 
 void ipi_call_lock_irq(void)
 {
-	spin_lock_irq(&call_function_lock);
+	spin_lock_irq(&call_function.lock);
 }
 
 void ipi_call_unlock_irq(void)
 {
-	spin_unlock_irq(&call_function_lock);
+	spin_unlock_irq(&call_function.lock);
 }
diff --git a/kernel/softirq.c b/kernel/softirq.c
index 65ff3e3961b4..d105a82543d0 100644
--- a/kernel/softirq.c
+++ b/kernel/softirq.c
@@ -518,7 +518,7 @@ static int __try_remote_softirq(struct call_single_data *cp, int cpu, int softir
 		cp->flags = 0;
 		cp->priv = softirq;
 
-		__smp_call_function_single(cpu, cp);
+		__smp_call_function_single(cpu, cp, 0);
 		return 0;
 	}
 	return 1;
diff --git a/kernel/spinlock.c b/kernel/spinlock.c
index 29ab20749dd3..7932653c4ebd 100644
--- a/kernel/spinlock.c
+++ b/kernel/spinlock.c
@@ -121,7 +121,8 @@ unsigned long __lockfunc _read_lock_irqsave(rwlock_t *lock)
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire_read(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_read_trylock, _raw_read_lock);
+	LOCK_CONTENDED_FLAGS(lock, _raw_read_trylock, _raw_read_lock,
+			     _raw_read_lock_flags, &flags);
 	return flags;
 }
 EXPORT_SYMBOL(_read_lock_irqsave);
@@ -151,7 +152,8 @@ unsigned long __lockfunc _write_lock_irqsave(rwlock_t *lock)
 	local_irq_save(flags);
 	preempt_disable();
 	rwlock_acquire(&lock->dep_map, 0, 0, _RET_IP_);
-	LOCK_CONTENDED(lock, _raw_write_trylock, _raw_write_lock);
+	LOCK_CONTENDED_FLAGS(lock, _raw_write_trylock, _raw_write_lock,
+			     _raw_write_lock_flags, &flags);
 	return flags;
 }
 EXPORT_SYMBOL(_write_lock_irqsave);
@@ -299,16 +301,8 @@ unsigned long __lockfunc _spin_lock_irqsave_nested(spinlock_t *lock, int subclas
 	local_irq_save(flags);
 	preempt_disable();
 	spin_acquire(&lock->dep_map, subclass, 0, _RET_IP_);
-	/*
-	 * On lockdep we dont want the hand-coded irq-enable of
-	 * _raw_spin_lock_flags() code, because lockdep assumes
-	 * that interrupts are not re-enabled during lock-acquire:
-	 */
-#ifdef CONFIG_LOCKDEP
-	LOCK_CONTENDED(lock, _raw_spin_trylock, _raw_spin_lock);
-#else
-	_raw_spin_lock_flags(lock, &flags);
-#endif
+	LOCK_CONTENDED_FLAGS(lock, _raw_spin_trylock, _raw_spin_lock,
+				_raw_spin_lock_flags, &flags);
 	return flags;
 }
 EXPORT_SYMBOL(_spin_lock_irqsave_nested);
diff --git a/kernel/sys.c b/kernel/sys.c
index 37f458e6882a..51dbb55604e8 100644
--- a/kernel/sys.c
+++ b/kernel/sys.c
@@ -34,6 +34,7 @@
 #include <linux/seccomp.h>
 #include <linux/cpu.h>
 #include <linux/ptrace.h>
+#include <linux/fs_struct.h>
 
 #include <linux/compat.h>
 #include <linux/syscalls.h>
@@ -1013,10 +1014,8 @@ SYSCALL_DEFINE2(setpgid, pid_t, pid, pid_t, pgid)
 	if (err)
 		goto out;
 
-	if (task_pgrp(p) != pgrp) {
+	if (task_pgrp(p) != pgrp)
 		change_pid(p, PIDTYPE_PGID, pgrp);
-		set_task_pgrp(p, pid_nr(pgrp));
-	}
 
 	err = 0;
 out:
diff --git a/kernel/sysctl.c b/kernel/sysctl.c
index 2e490a389dd2..82350f8f04f6 100644
--- a/kernel/sysctl.c
+++ b/kernel/sysctl.c
@@ -48,6 +48,7 @@
 #include <linux/acpi.h>
 #include <linux/reboot.h>
 #include <linux/ftrace.h>
+#include <linux/slow-work.h>
 
 #include <asm/uaccess.h>
 #include <asm/processor.h>
@@ -95,12 +96,9 @@ static int sixty = 60;
 static int neg_one = -1;
 #endif
 
-#if defined(CONFIG_MMU) && defined(CONFIG_FILE_LOCKING)
-static int two = 2;
-#endif
-
 static int zero;
 static int one = 1;
+static int two = 2;
 static unsigned long one_ul = 1;
 static int one_hundred = 100;
 
@@ -900,6 +898,14 @@ static struct ctl_table kern_table[] = {
 		.proc_handler	= &scan_unevictable_handler,
 	},
 #endif
+#ifdef CONFIG_SLOW_WORK
+	{
+		.ctl_name	= CTL_UNNUMBERED,
+		.procname	= "slow-work",
+		.mode		= 0555,
+		.child		= slow_work_sysctls,
+	},
+#endif
 /*
  * NOTE: do not add new entries to this table unless you have read
  * Documentation/sysctl/ctl_unnumbered.txt
@@ -1373,10 +1379,7 @@ static struct ctl_table fs_table[] = {
 		.data		= &lease_break_time,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec_minmax,
-		.strategy	= &sysctl_intvec,
-		.extra1		= &zero,
-		.extra2		= &two,
+		.proc_handler	= &proc_dointvec,
 	},
 #endif
 #ifdef CONFIG_AIO
@@ -1417,7 +1420,10 @@ static struct ctl_table fs_table[] = {
 		.data		= &suid_dumpable,
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
-		.proc_handler	= &proc_dointvec,
+		.proc_handler	= &proc_dointvec_minmax,
+		.strategy	= &sysctl_intvec,
+		.extra1		= &zero,
+		.extra2		= &two,
 	},
 #if defined(CONFIG_BINFMT_MISC) || defined(CONFIG_BINFMT_MISC_MODULE)
 	{
diff --git a/kernel/trace/Kconfig b/kernel/trace/Kconfig
index 8a4d72931042..2246141bda4d 100644
--- a/kernel/trace/Kconfig
+++ b/kernel/trace/Kconfig
@@ -99,11 +99,10 @@ config FUNCTION_GRAPH_TRACER
 	help
 	  Enable the kernel to trace a function at both its return
 	  and its entry.
-	  It's first purpose is to trace the duration of functions and
-	  draw a call graph for each thread with some informations like
-	  the return value.
-	  This is done by setting the current return address on the current
-	  task structure into a stack of calls.
+	  Its first purpose is to trace the duration of functions and
+	  draw a call graph for each thread with some information like
+	  the return value. This is done by setting the current return 
+	  address on the current task structure into a stack of calls.
 
 config IRQSOFF_TRACER
 	bool "Interrupts-off Latency Tracer"
diff --git a/kernel/utsname_sysctl.c b/kernel/utsname_sysctl.c
index 3b34b3545936..92359cc747a7 100644
--- a/kernel/utsname_sysctl.c
+++ b/kernel/utsname_sysctl.c
@@ -37,7 +37,7 @@ static void put_uts(ctl_table *table, int write, void *which)
 		up_write(&uts_sem);
 }
 
-#ifdef CONFIG_PROC_FS
+#ifdef CONFIG_PROC_SYSCTL
 /*
  *	Special case of dostring for the UTS structure. This has locks
  *	to observe. Should this be in kernel/sys.c ????
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 3003ecad08f4..b6b966ce1451 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -49,8 +49,6 @@ struct cpu_workqueue_struct {
 
 	struct workqueue_struct *wq;
 	struct task_struct *thread;
-
-	int run_depth;		/* Detect run_workqueue() recursion depth */
 } ____cacheline_aligned;
 
 /*
@@ -269,13 +267,6 @@ DEFINE_TRACE(workqueue_execution);
 static void run_workqueue(struct cpu_workqueue_struct *cwq)
 {
 	spin_lock_irq(&cwq->lock);
-	cwq->run_depth++;
-	if (cwq->run_depth > 3) {
-		/* morton gets to eat his hat */
-		printk("%s: recursion depth exceeded: %d\n",
-			__func__, cwq->run_depth);
-		dump_stack();
-	}
 	while (!list_empty(&cwq->worklist)) {
 		struct work_struct *work = list_entry(cwq->worklist.next,
 						struct work_struct, entry);
@@ -318,7 +309,6 @@ static void run_workqueue(struct cpu_workqueue_struct *cwq)
 		spin_lock_irq(&cwq->lock);
 		cwq->current_work = NULL;
 	}
-	cwq->run_depth--;
 	spin_unlock_irq(&cwq->lock);
 }
 
@@ -375,29 +365,20 @@ static void insert_wq_barrier(struct cpu_workqueue_struct *cwq,
 
 static int flush_cpu_workqueue(struct cpu_workqueue_struct *cwq)
 {
-	int active;
+	int active = 0;
+	struct wq_barrier barr;
 
-	if (cwq->thread == current) {
-		/*
-		 * Probably keventd trying to flush its own queue. So simply run
-		 * it by hand rather than deadlocking.
-		 */
-		run_workqueue(cwq);
-		active = 1;
-	} else {
-		struct wq_barrier barr;
+	WARN_ON(cwq->thread == current);
 
-		active = 0;
-		spin_lock_irq(&cwq->lock);
-		if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
-			insert_wq_barrier(cwq, &barr, &cwq->worklist);
-			active = 1;
-		}
-		spin_unlock_irq(&cwq->lock);
-
-		if (active)
-			wait_for_completion(&barr.done);
+	spin_lock_irq(&cwq->lock);
+	if (!list_empty(&cwq->worklist) || cwq->current_work != NULL) {
+		insert_wq_barrier(cwq, &barr, &cwq->worklist);
+		active = 1;
 	}
+	spin_unlock_irq(&cwq->lock);
+
+	if (active)
+		wait_for_completion(&barr.done);
 
 	return active;
 }
diff --git a/lib/cpumask.c b/lib/cpumask.c
index 3389e2440da0..1f71b97de0f9 100644
--- a/lib/cpumask.c
+++ b/lib/cpumask.c
@@ -109,10 +109,10 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node)
 #endif
 	/* FIXME: Bandaid to save us from old primitives which go to NR_CPUS. */
 	if (*mask) {
+		unsigned char *ptr = (unsigned char *)cpumask_bits(*mask);
 		unsigned int tail;
 		tail = BITS_TO_LONGS(NR_CPUS - nr_cpumask_bits) * sizeof(long);
-		memset(cpumask_bits(*mask) + cpumask_size() - tail,
-		       0, tail);
+		memset(ptr + cpumask_size() - tail, 0, tail);
 	}
 
 	return *mask != NULL;
diff --git a/lib/debugobjects.c b/lib/debugobjects.c
index 5d99be1fd988..2755a3bd16a1 100644
--- a/lib/debugobjects.c
+++ b/lib/debugobjects.c
@@ -30,7 +30,7 @@ struct debug_bucket {
 
 static struct debug_bucket	obj_hash[ODEBUG_HASH_SIZE];
 
-static struct debug_obj		obj_static_pool[ODEBUG_POOL_SIZE];
+static struct debug_obj		obj_static_pool[ODEBUG_POOL_SIZE] __initdata;
 
 static DEFINE_SPINLOCK(pool_lock);
 
@@ -50,12 +50,23 @@ static int			debug_objects_enabled __read_mostly
 
 static struct debug_obj_descr	*descr_test  __read_mostly;
 
+static void free_obj_work(struct work_struct *work);
+static DECLARE_WORK(debug_obj_work, free_obj_work);
+
 static int __init enable_object_debug(char *str)
 {
 	debug_objects_enabled = 1;
 	return 0;
 }
+
+static int __init disable_object_debug(char *str)
+{
+	debug_objects_enabled = 0;
+	return 0;
+}
+
 early_param("debug_objects", enable_object_debug);
+early_param("no_debug_objects", disable_object_debug);
 
 static const char *obj_states[ODEBUG_STATE_MAX] = {
 	[ODEBUG_STATE_NONE]		= "none",
@@ -146,25 +157,51 @@ alloc_object(void *addr, struct debug_bucket *b, struct debug_obj_descr *descr)
 }
 
 /*
- * Put the object back into the pool or give it back to kmem_cache:
+ * workqueue function to free objects.
  */
-static void free_object(struct debug_obj *obj)
+static void free_obj_work(struct work_struct *work)
 {
-	unsigned long idx = (unsigned long)(obj - obj_static_pool);
+	struct debug_obj *obj;
 	unsigned long flags;
 
-	if (obj_pool_free < ODEBUG_POOL_SIZE || idx < ODEBUG_POOL_SIZE) {
-		spin_lock_irqsave(&pool_lock, flags);
-		hlist_add_head(&obj->node, &obj_pool);
-		obj_pool_free++;
-		obj_pool_used--;
-		spin_unlock_irqrestore(&pool_lock, flags);
-	} else {
-		spin_lock_irqsave(&pool_lock, flags);
-		obj_pool_used--;
+	spin_lock_irqsave(&pool_lock, flags);
+	while (obj_pool_free > ODEBUG_POOL_SIZE) {
+		obj = hlist_entry(obj_pool.first, typeof(*obj), node);
+		hlist_del(&obj->node);
+		obj_pool_free--;
+		/*
+		 * We release pool_lock across kmem_cache_free() to
+		 * avoid contention on pool_lock.
+		 */
 		spin_unlock_irqrestore(&pool_lock, flags);
 		kmem_cache_free(obj_cache, obj);
+		spin_lock_irqsave(&pool_lock, flags);
 	}
+	spin_unlock_irqrestore(&pool_lock, flags);
+}
+
+/*
+ * Put the object back into the pool and schedule work to free objects
+ * if necessary.
+ */
+static void free_object(struct debug_obj *obj)
+{
+	unsigned long flags;
+	int sched = 0;
+
+	spin_lock_irqsave(&pool_lock, flags);
+	/*
+	 * schedule work when the pool is filled and the cache is
+	 * initialized:
+	 */
+	if (obj_pool_free > ODEBUG_POOL_SIZE && obj_cache)
+		sched = !work_pending(&debug_obj_work);
+	hlist_add_head(&obj->node, &obj_pool);
+	obj_pool_free++;
+	obj_pool_used--;
+	spin_unlock_irqrestore(&pool_lock, flags);
+	if (sched)
+		schedule_work(&debug_obj_work);
 }
 
 /*
@@ -876,6 +913,63 @@ void __init debug_objects_early_init(void)
 }
 
 /*
+ * Convert the statically allocated objects to dynamic ones:
+ */
+static int debug_objects_replace_static_objects(void)
+{
+	struct debug_bucket *db = obj_hash;
+	struct hlist_node *node, *tmp;
+	struct debug_obj *obj, *new;
+	HLIST_HEAD(objects);
+	int i, cnt = 0;
+
+	for (i = 0; i < ODEBUG_POOL_SIZE; i++) {
+		obj = kmem_cache_zalloc(obj_cache, GFP_KERNEL);
+		if (!obj)
+			goto free;
+		hlist_add_head(&obj->node, &objects);
+	}
+
+	/*
+	 * When debug_objects_mem_init() is called we know that only
+	 * one CPU is up, so disabling interrupts is enough
+	 * protection. This avoids the lockdep hell of lock ordering.
+	 */
+	local_irq_disable();
+
+	/* Remove the statically allocated objects from the pool */
+	hlist_for_each_entry_safe(obj, node, tmp, &obj_pool, node)
+		hlist_del(&obj->node);
+	/* Move the allocated objects to the pool */
+	hlist_move_list(&objects, &obj_pool);
+
+	/* Replace the active object references */
+	for (i = 0; i < ODEBUG_HASH_SIZE; i++, db++) {
+		hlist_move_list(&db->list, &objects);
+
+		hlist_for_each_entry(obj, node, &objects, node) {
+			new = hlist_entry(obj_pool.first, typeof(*obj), node);
+			hlist_del(&new->node);
+			/* copy object data */
+			*new = *obj;
+			hlist_add_head(&new->node, &db->list);
+			cnt++;
+		}
+	}
+
+	printk(KERN_DEBUG "ODEBUG: %d of %d active objects replaced\n", cnt,
+	       obj_pool_used);
+	local_irq_enable();
+	return 0;
+free:
+	hlist_for_each_entry_safe(obj, node, tmp, &objects, node) {
+		hlist_del(&obj->node);
+		kmem_cache_free(obj_cache, obj);
+	}
+	return -ENOMEM;
+}
+
+/*
  * Called after the kmem_caches are functional to setup a dedicated
  * cache pool, which has the SLAB_DEBUG_OBJECTS flag set. This flag
  * prevents that the debug code is called on kmem_cache_free() for the
@@ -890,8 +984,11 @@ void __init debug_objects_mem_init(void)
 				      sizeof (struct debug_obj), 0,
 				      SLAB_DEBUG_OBJECTS, NULL);
 
-	if (!obj_cache)
+	if (!obj_cache || debug_objects_replace_static_objects()) {
 		debug_objects_enabled = 0;
-	else
+		if (obj_cache)
+			kmem_cache_destroy(obj_cache);
+		printk(KERN_WARNING "ODEBUG: out of memory.\n");
+	} else
 		debug_objects_selftest();
 }
diff --git a/lib/idr.c b/lib/idr.c
index dab4bca86f5d..80ca9aca038b 100644
--- a/lib/idr.c
+++ b/lib/idr.c
@@ -579,6 +579,52 @@ int idr_for_each(struct idr *idp,
 EXPORT_SYMBOL(idr_for_each);
 
 /**
+ * idr_get_next - lookup next object of id to given id.
+ * @idp: idr handle
+ * @id:  pointer to lookup key
+ *
+ * Returns pointer to registered object with id, which is next number to
+ * given id.
+ */
+
+void *idr_get_next(struct idr *idp, int *nextidp)
+{
+	struct idr_layer *p, *pa[MAX_LEVEL];
+	struct idr_layer **paa = &pa[0];
+	int id = *nextidp;
+	int n, max;
+
+	/* find first ent */
+	n = idp->layers * IDR_BITS;
+	max = 1 << n;
+	p = rcu_dereference(idp->top);
+	if (!p)
+		return NULL;
+
+	while (id < max) {
+		while (n > 0 && p) {
+			n -= IDR_BITS;
+			*paa++ = p;
+			p = rcu_dereference(p->ary[(id >> n) & IDR_MASK]);
+		}
+
+		if (p) {
+			*nextidp = id;
+			return p;
+		}
+
+		id += 1 << n;
+		while (n < fls(id)) {
+			n += IDR_BITS;
+			p = *--paa;
+		}
+	}
+	return NULL;
+}
+
+
+
+/**
  * idr_replace - replace pointer for given id
  * @idp: idr handle
  * @ptr: pointer you want associated with the id
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index dc1674377009..be3001f912e4 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -398,7 +398,7 @@ static noinline char* put_dec(char *buf, unsigned long long num)
 
 enum format_type {
 	FORMAT_TYPE_NONE, /* Just a string part */
-	FORMAT_TYPE_WITDH,
+	FORMAT_TYPE_WIDTH,
 	FORMAT_TYPE_PRECISION,
 	FORMAT_TYPE_CHAR,
 	FORMAT_TYPE_STR,
@@ -770,7 +770,7 @@ static int format_decode(const char *fmt, struct printf_spec *spec)
 	const char *start = fmt;
 
 	/* we finished early by reading the field width */
-	if (spec->type == FORMAT_TYPE_WITDH) {
+	if (spec->type == FORMAT_TYPE_WIDTH) {
 		if (spec->field_width < 0) {
 			spec->field_width = -spec->field_width;
 			spec->flags |= LEFT;
@@ -828,7 +828,7 @@ static int format_decode(const char *fmt, struct printf_spec *spec)
 		spec->field_width = skip_atoi(&fmt);
 	else if (*fmt == '*') {
 		/* it's the next argument */
-		spec->type = FORMAT_TYPE_WITDH;
+		spec->type = FORMAT_TYPE_WIDTH;
 		return ++fmt - start;
 	}
 
@@ -843,7 +843,7 @@ precision:
 				spec->precision = 0;
 		} else if (*fmt == '*') {
 			/* it's the next argument */
-			spec->type = FORMAT_TYPE_WITDH;
+			spec->type = FORMAT_TYPE_PRECISION;
 			return ++fmt - start;
 		}
 	}
@@ -1002,7 +1002,7 @@ int vsnprintf(char *buf, size_t size, const char *fmt, va_list args)
 			break;
 		}
 
-		case FORMAT_TYPE_WITDH:
+		case FORMAT_TYPE_WIDTH:
 			spec.field_width = va_arg(args, int);
 			break;
 
@@ -1306,7 +1306,7 @@ do {									\
 		case FORMAT_TYPE_NONE:
 			break;
 
-		case FORMAT_TYPE_WITDH:
+		case FORMAT_TYPE_WIDTH:
 		case FORMAT_TYPE_PRECISION:
 			save_arg(int);
 			break;
@@ -1472,7 +1472,7 @@ int bstr_printf(char *buf, size_t size, const char *fmt, const u32 *bin_buf)
 			break;
 		}
 
-		case FORMAT_TYPE_WITDH:
+		case FORMAT_TYPE_WIDTH:
 			spec.field_width = get_arg(int);
 			break;
 
diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug
index c8d62d49a44e..bb01e298f260 100644
--- a/mm/Kconfig.debug
+++ b/mm/Kconfig.debug
@@ -1,3 +1,12 @@
+config DEBUG_PAGEALLOC
+	bool "Debug page memory allocations"
+	depends on DEBUG_KERNEL && ARCH_SUPPORTS_DEBUG_PAGEALLOC
+	depends on !HIBERNATION || !PPC && !SPARC
+	---help---
+	  Unmap pages from the kernel linear mapping after free_pages().
+	  This results in a large slowdown, but helps to find certain types
+	  of memory corruptions.
+
 config WANT_PAGE_DEBUG_FLAGS
 	bool
 
diff --git a/mm/filemap.c b/mm/filemap.c
index 126d3973b3d1..fc11974f2bee 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -565,6 +565,24 @@ void wait_on_page_bit(struct page *page, int bit_nr)
 EXPORT_SYMBOL(wait_on_page_bit);
 
 /**
+ * add_page_wait_queue - Add an arbitrary waiter to a page's wait queue
+ * @page - Page defining the wait queue of interest
+ * @waiter - Waiter to add to the queue
+ *
+ * Add an arbitrary @waiter to the wait queue for the nominated @page.
+ */
+void add_page_wait_queue(struct page *page, wait_queue_t *waiter)
+{
+	wait_queue_head_t *q = page_waitqueue(page);
+	unsigned long flags;
+
+	spin_lock_irqsave(&q->lock, flags);
+	__add_wait_queue(q, waiter);
+	spin_unlock_irqrestore(&q->lock, flags);
+}
+EXPORT_SYMBOL_GPL(add_page_wait_queue);
+
+/**
  * unlock_page - unlock a locked page
  * @page: the page
  *
@@ -2463,6 +2481,9 @@ EXPORT_SYMBOL(generic_file_aio_write);
  * (presumably at page->private).  If the release was successful, return `1'.
  * Otherwise return zero.
  *
+ * This may also be called if PG_fscache is set on a page, indicating that the
+ * page is known to the local caching routines.
+ *
  * The @gfp_mask argument specifies whether I/O may be performed to release
  * this page (__GFP_IO), and whether the call may block (__GFP_WAIT & __GFP_FS).
  *
diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c
index 0c04615651b7..427dfe3ce78c 100644
--- a/mm/filemap_xip.c
+++ b/mm/filemap_xip.c
@@ -89,8 +89,8 @@ do_xip_mapping_read(struct address_space *mapping,
 			}
 		}
 		nr = nr - offset;
-		if (nr > len)
-			nr = len;
+		if (nr > len - copied)
+			nr = len - copied;
 
 		error = mapping->a_ops->get_xip_mem(mapping, index, 0,
 							&xip_mem, &xip_pfn);
diff --git a/mm/memcontrol.c b/mm/memcontrol.c
index 8e4be9cb2a6a..2fc6d6c48238 100644
--- a/mm/memcontrol.c
+++ b/mm/memcontrol.c
@@ -27,6 +27,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bit_spinlock.h>
 #include <linux/rcupdate.h>
+#include <linux/limits.h>
 #include <linux/mutex.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -95,6 +96,15 @@ static s64 mem_cgroup_read_stat(struct mem_cgroup_stat *stat,
 	return ret;
 }
 
+static s64 mem_cgroup_local_usage(struct mem_cgroup_stat *stat)
+{
+	s64 ret;
+
+	ret = mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_CACHE);
+	ret += mem_cgroup_read_stat(stat, MEM_CGROUP_STAT_RSS);
+	return ret;
+}
+
 /*
  * per-zone information in memory controller.
  */
@@ -154,9 +164,9 @@ struct mem_cgroup {
 
 	/*
 	 * While reclaiming in a hiearchy, we cache the last child we
-	 * reclaimed from. Protected by hierarchy_mutex
+	 * reclaimed from.
 	 */
-	struct mem_cgroup *last_scanned_child;
+	int last_scanned_child;
 	/*
 	 * Should the accounting and control be hierarchical, per subtree?
 	 */
@@ -247,7 +257,7 @@ page_cgroup_zoneinfo(struct page_cgroup *pc)
 	return mem_cgroup_zoneinfo(mem, nid, zid);
 }
 
-static unsigned long mem_cgroup_get_all_zonestat(struct mem_cgroup *mem,
+static unsigned long mem_cgroup_get_local_zonestat(struct mem_cgroup *mem,
 					enum lru_list idx)
 {
 	int nid, zid;
@@ -286,6 +296,9 @@ struct mem_cgroup *mem_cgroup_from_task(struct task_struct *p)
 static struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm)
 {
 	struct mem_cgroup *mem = NULL;
+
+	if (!mm)
+		return NULL;
 	/*
 	 * Because we have no locks, mm->owner's may be being moved to other
 	 * cgroup. We use css_tryget() here even if this looks
@@ -308,6 +321,42 @@ static bool mem_cgroup_is_obsolete(struct mem_cgroup *mem)
 	return css_is_removed(&mem->css);
 }
 
+
+/*
+ * Call callback function against all cgroup under hierarchy tree.
+ */
+static int mem_cgroup_walk_tree(struct mem_cgroup *root, void *data,
+			  int (*func)(struct mem_cgroup *, void *))
+{
+	int found, ret, nextid;
+	struct cgroup_subsys_state *css;
+	struct mem_cgroup *mem;
+
+	if (!root->use_hierarchy)
+		return (*func)(root, data);
+
+	nextid = 1;
+	do {
+		ret = 0;
+		mem = NULL;
+
+		rcu_read_lock();
+		css = css_get_next(&mem_cgroup_subsys, nextid, &root->css,
+				   &found);
+		if (css && css_tryget(css))
+			mem = container_of(css, struct mem_cgroup, css);
+		rcu_read_unlock();
+
+		if (mem) {
+			ret = (*func)(mem, data);
+			css_put(&mem->css);
+		}
+		nextid = found + 1;
+	} while (!ret && css);
+
+	return ret;
+}
+
 /*
  * Following LRU functions are allowed to be used without PCG_LOCK.
  * Operations are called by routine of global LRU independently from memcg.
@@ -441,31 +490,24 @@ void mem_cgroup_move_lists(struct page *page,
 int task_in_mem_cgroup(struct task_struct *task, const struct mem_cgroup *mem)
 {
 	int ret;
+	struct mem_cgroup *curr = NULL;
 
 	task_lock(task);
-	ret = task->mm && mm_match_cgroup(task->mm, mem);
+	rcu_read_lock();
+	curr = try_get_mem_cgroup_from_mm(task->mm);
+	rcu_read_unlock();
 	task_unlock(task);
+	if (!curr)
+		return 0;
+	if (curr->use_hierarchy)
+		ret = css_is_ancestor(&curr->css, &mem->css);
+	else
+		ret = (curr == mem);
+	css_put(&curr->css);
 	return ret;
 }
 
 /*
- * Calculate mapped_ratio under memory controller. This will be used in
- * vmscan.c for deteremining we have to reclaim mapped pages.
- */
-int mem_cgroup_calc_mapped_ratio(struct mem_cgroup *mem)
-{
-	long total, rss;
-
-	/*
-	 * usage is recorded in bytes. But, here, we assume the number of
-	 * physical pages can be represented by "long" on any arch.
-	 */
-	total = (long) (mem->res.usage >> PAGE_SHIFT) + 1L;
-	rss = (long)mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
-	return (int)((rss * 100L) / total);
-}
-
-/*
  * prev_priority control...this will be used in memory reclaim path.
  */
 int mem_cgroup_get_reclaim_priority(struct mem_cgroup *mem)
@@ -501,8 +543,8 @@ static int calc_inactive_ratio(struct mem_cgroup *memcg, unsigned long *present_
 	unsigned long gb;
 	unsigned long inactive_ratio;
 
-	inactive = mem_cgroup_get_all_zonestat(memcg, LRU_INACTIVE_ANON);
-	active = mem_cgroup_get_all_zonestat(memcg, LRU_ACTIVE_ANON);
+	inactive = mem_cgroup_get_local_zonestat(memcg, LRU_INACTIVE_ANON);
+	active = mem_cgroup_get_local_zonestat(memcg, LRU_ACTIVE_ANON);
 
 	gb = (inactive + active) >> (30 - PAGE_SHIFT);
 	if (gb)
@@ -629,172 +671,202 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
 #define mem_cgroup_from_res_counter(counter, member)	\
 	container_of(counter, struct mem_cgroup, member)
 
-/*
- * This routine finds the DFS walk successor. This routine should be
- * called with hierarchy_mutex held
- */
-static struct mem_cgroup *
-__mem_cgroup_get_next_node(struct mem_cgroup *curr, struct mem_cgroup *root_mem)
+static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
 {
-	struct cgroup *cgroup, *curr_cgroup, *root_cgroup;
-
-	curr_cgroup = curr->css.cgroup;
-	root_cgroup = root_mem->css.cgroup;
+	if (do_swap_account) {
+		if (res_counter_check_under_limit(&mem->res) &&
+			res_counter_check_under_limit(&mem->memsw))
+			return true;
+	} else
+		if (res_counter_check_under_limit(&mem->res))
+			return true;
+	return false;
+}
 
-	if (!list_empty(&curr_cgroup->children)) {
-		/*
-		 * Walk down to children
-		 */
-		cgroup = list_entry(curr_cgroup->children.next,
-						struct cgroup, sibling);
-		curr = mem_cgroup_from_cont(cgroup);
-		goto done;
-	}
+static unsigned int get_swappiness(struct mem_cgroup *memcg)
+{
+	struct cgroup *cgrp = memcg->css.cgroup;
+	unsigned int swappiness;
 
-visit_parent:
-	if (curr_cgroup == root_cgroup) {
-		/* caller handles NULL case */
-		curr = NULL;
-		goto done;
-	}
+	/* root ? */
+	if (cgrp->parent == NULL)
+		return vm_swappiness;
 
-	/*
-	 * Goto next sibling
-	 */
-	if (curr_cgroup->sibling.next != &curr_cgroup->parent->children) {
-		cgroup = list_entry(curr_cgroup->sibling.next, struct cgroup,
-						sibling);
-		curr = mem_cgroup_from_cont(cgroup);
-		goto done;
-	}
+	spin_lock(&memcg->reclaim_param_lock);
+	swappiness = memcg->swappiness;
+	spin_unlock(&memcg->reclaim_param_lock);
 
-	/*
-	 * Go up to next parent and next parent's sibling if need be
-	 */
-	curr_cgroup = curr_cgroup->parent;
-	goto visit_parent;
+	return swappiness;
+}
 
-done:
-	return curr;
+static int mem_cgroup_count_children_cb(struct mem_cgroup *mem, void *data)
+{
+	int *val = data;
+	(*val)++;
+	return 0;
 }
 
-/*
- * Visit the first child (need not be the first child as per the ordering
- * of the cgroup list, since we track last_scanned_child) of @mem and use
- * that to reclaim free pages from.
+/**
+ * mem_cgroup_print_mem_info: Called from OOM with tasklist_lock held in read mode.
+ * @memcg: The memory cgroup that went over limit
+ * @p: Task that is going to be killed
+ *
+ * NOTE: @memcg and @p's mem_cgroup can be different when hierarchy is
+ * enabled
  */
-static struct mem_cgroup *
-mem_cgroup_get_next_node(struct mem_cgroup *root_mem)
+void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p)
 {
-	struct cgroup *cgroup;
-	struct mem_cgroup *orig, *next;
-	bool obsolete;
-
+	struct cgroup *task_cgrp;
+	struct cgroup *mem_cgrp;
 	/*
-	 * Scan all children under the mem_cgroup mem
+	 * Need a buffer in BSS, can't rely on allocations. The code relies
+	 * on the assumption that OOM is serialized for memory controller.
+	 * If this assumption is broken, revisit this code.
 	 */
-	mutex_lock(&mem_cgroup_subsys.hierarchy_mutex);
+	static char memcg_name[PATH_MAX];
+	int ret;
+
+	if (!memcg)
+		return;
 
-	orig = root_mem->last_scanned_child;
-	obsolete = mem_cgroup_is_obsolete(orig);
 
-	if (list_empty(&root_mem->css.cgroup->children)) {
+	rcu_read_lock();
+
+	mem_cgrp = memcg->css.cgroup;
+	task_cgrp = task_cgroup(p, mem_cgroup_subsys_id);
+
+	ret = cgroup_path(task_cgrp, memcg_name, PATH_MAX);
+	if (ret < 0) {
 		/*
-		 * root_mem might have children before and last_scanned_child
-		 * may point to one of them. We put it later.
+		 * Unfortunately, we are unable to convert to a useful name
+		 * But we'll still print out the usage information
 		 */
-		if (orig)
-			VM_BUG_ON(!obsolete);
-		next = NULL;
+		rcu_read_unlock();
 		goto done;
 	}
+	rcu_read_unlock();
 
-	if (!orig || obsolete) {
-		cgroup = list_first_entry(&root_mem->css.cgroup->children,
-				struct cgroup, sibling);
-		next = mem_cgroup_from_cont(cgroup);
-	} else
-		next = __mem_cgroup_get_next_node(orig, root_mem);
+	printk(KERN_INFO "Task in %s killed", memcg_name);
 
+	rcu_read_lock();
+	ret = cgroup_path(mem_cgrp, memcg_name, PATH_MAX);
+	if (ret < 0) {
+		rcu_read_unlock();
+		goto done;
+	}
+	rcu_read_unlock();
+
+	/*
+	 * Continues from above, so we don't need an KERN_ level
+	 */
+	printk(KERN_CONT " as a result of limit of %s\n", memcg_name);
 done:
-	if (next)
-		mem_cgroup_get(next);
-	root_mem->last_scanned_child = next;
-	if (orig)
-		mem_cgroup_put(orig);
-	mutex_unlock(&mem_cgroup_subsys.hierarchy_mutex);
-	return (next) ? next : root_mem;
+
+	printk(KERN_INFO "memory: usage %llukB, limit %llukB, failcnt %llu\n",
+		res_counter_read_u64(&memcg->res, RES_USAGE) >> 10,
+		res_counter_read_u64(&memcg->res, RES_LIMIT) >> 10,
+		res_counter_read_u64(&memcg->res, RES_FAILCNT));
+	printk(KERN_INFO "memory+swap: usage %llukB, limit %llukB, "
+		"failcnt %llu\n",
+		res_counter_read_u64(&memcg->memsw, RES_USAGE) >> 10,
+		res_counter_read_u64(&memcg->memsw, RES_LIMIT) >> 10,
+		res_counter_read_u64(&memcg->memsw, RES_FAILCNT));
 }
 
-static bool mem_cgroup_check_under_limit(struct mem_cgroup *mem)
+/*
+ * This function returns the number of memcg under hierarchy tree. Returns
+ * 1(self count) if no children.
+ */
+static int mem_cgroup_count_children(struct mem_cgroup *mem)
 {
-	if (do_swap_account) {
-		if (res_counter_check_under_limit(&mem->res) &&
-			res_counter_check_under_limit(&mem->memsw))
-			return true;
-	} else
-		if (res_counter_check_under_limit(&mem->res))
-			return true;
-	return false;
+	int num = 0;
+ 	mem_cgroup_walk_tree(mem, &num, mem_cgroup_count_children_cb);
+	return num;
 }
 
-static unsigned int get_swappiness(struct mem_cgroup *memcg)
+/*
+ * Visit the first child (need not be the first child as per the ordering
+ * of the cgroup list, since we track last_scanned_child) of @mem and use
+ * that to reclaim free pages from.
+ */
+static struct mem_cgroup *
+mem_cgroup_select_victim(struct mem_cgroup *root_mem)
 {
-	struct cgroup *cgrp = memcg->css.cgroup;
-	unsigned int swappiness;
+	struct mem_cgroup *ret = NULL;
+	struct cgroup_subsys_state *css;
+	int nextid, found;
 
-	/* root ? */
-	if (cgrp->parent == NULL)
-		return vm_swappiness;
+	if (!root_mem->use_hierarchy) {
+		css_get(&root_mem->css);
+		ret = root_mem;
+	}
 
-	spin_lock(&memcg->reclaim_param_lock);
-	swappiness = memcg->swappiness;
-	spin_unlock(&memcg->reclaim_param_lock);
+	while (!ret) {
+		rcu_read_lock();
+		nextid = root_mem->last_scanned_child + 1;
+		css = css_get_next(&mem_cgroup_subsys, nextid, &root_mem->css,
+				   &found);
+		if (css && css_tryget(css))
+			ret = container_of(css, struct mem_cgroup, css);
+
+		rcu_read_unlock();
+		/* Updates scanning parameter */
+		spin_lock(&root_mem->reclaim_param_lock);
+		if (!css) {
+			/* this means start scan from ID:1 */
+			root_mem->last_scanned_child = 0;
+		} else
+			root_mem->last_scanned_child = found;
+		spin_unlock(&root_mem->reclaim_param_lock);
+	}
 
-	return swappiness;
+	return ret;
 }
 
 /*
- * Dance down the hierarchy if needed to reclaim memory. We remember the
- * last child we reclaimed from, so that we don't end up penalizing
- * one child extensively based on its position in the children list.
+ * Scan the hierarchy if needed to reclaim memory. We remember the last child
+ * we reclaimed from, so that we don't end up penalizing one child extensively
+ * based on its position in the children list.
  *
  * root_mem is the original ancestor that we've been reclaim from.
+ *
+ * We give up and return to the caller when we visit root_mem twice.
+ * (other groups can be removed while we're walking....)
+ *
+ * If shrink==true, for avoiding to free too much, this returns immedieately.
  */
 static int mem_cgroup_hierarchical_reclaim(struct mem_cgroup *root_mem,
-						gfp_t gfp_mask, bool noswap)
-{
-	struct mem_cgroup *next_mem;
-	int ret = 0;
-
-	/*
-	 * Reclaim unconditionally and don't check for return value.
-	 * We need to reclaim in the current group and down the tree.
-	 * One might think about checking for children before reclaiming,
-	 * but there might be left over accounting, even after children
-	 * have left.
-	 */
-	ret += try_to_free_mem_cgroup_pages(root_mem, gfp_mask, noswap,
-					   get_swappiness(root_mem));
-	if (mem_cgroup_check_under_limit(root_mem))
-		return 1;	/* indicate reclaim has succeeded */
-	if (!root_mem->use_hierarchy)
-		return ret;
-
-	next_mem = mem_cgroup_get_next_node(root_mem);
-
-	while (next_mem != root_mem) {
-		if (mem_cgroup_is_obsolete(next_mem)) {
-			next_mem = mem_cgroup_get_next_node(root_mem);
+				   gfp_t gfp_mask, bool noswap, bool shrink)
+{
+	struct mem_cgroup *victim;
+	int ret, total = 0;
+	int loop = 0;
+
+	while (loop < 2) {
+		victim = mem_cgroup_select_victim(root_mem);
+		if (victim == root_mem)
+			loop++;
+		if (!mem_cgroup_local_usage(&victim->stat)) {
+			/* this cgroup's local usage == 0 */
+			css_put(&victim->css);
 			continue;
 		}
-		ret += try_to_free_mem_cgroup_pages(next_mem, gfp_mask, noswap,
-						   get_swappiness(next_mem));
+		/* we use swappiness of local cgroup */
+		ret = try_to_free_mem_cgroup_pages(victim, gfp_mask, noswap,
+						   get_swappiness(victim));
+		css_put(&victim->css);
+		/*
+		 * At shrinking usage, we can't check we should stop here or
+		 * reclaim more. It's depends on callers. last_scanned_child
+		 * will work enough for keeping fairness under tree.
+		 */
+		if (shrink)
+			return ret;
+		total += ret;
 		if (mem_cgroup_check_under_limit(root_mem))
-			return 1;	/* indicate reclaim has succeeded */
-		next_mem = mem_cgroup_get_next_node(root_mem);
+			return 1 + total;
 	}
-	return ret;
+	return total;
 }
 
 bool mem_cgroup_oom_called(struct task_struct *task)
@@ -813,6 +885,19 @@ bool mem_cgroup_oom_called(struct task_struct *task)
 	rcu_read_unlock();
 	return ret;
 }
+
+static int record_last_oom_cb(struct mem_cgroup *mem, void *data)
+{
+	mem->last_oom_jiffies = jiffies;
+	return 0;
+}
+
+static void record_last_oom(struct mem_cgroup *mem)
+{
+	mem_cgroup_walk_tree(mem, NULL, record_last_oom_cb);
+}
+
+
 /*
  * Unlike exported interface, "oom" parameter is added. if oom==true,
  * oom-killer can be invoked.
@@ -875,7 +960,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 			goto nomem;
 
 		ret = mem_cgroup_hierarchical_reclaim(mem_over_limit, gfp_mask,
-							noswap);
+							noswap, false);
 		if (ret)
 			continue;
 
@@ -895,7 +980,7 @@ static int __mem_cgroup_try_charge(struct mm_struct *mm,
 				mutex_lock(&memcg_tasklist);
 				mem_cgroup_out_of_memory(mem_over_limit, gfp_mask);
 				mutex_unlock(&memcg_tasklist);
-				mem_over_limit->last_oom_jiffies = jiffies;
+				record_last_oom(mem_over_limit);
 			}
 			goto nomem;
 		}
@@ -906,20 +991,55 @@ nomem:
 	return -ENOMEM;
 }
 
+
+/*
+ * A helper function to get mem_cgroup from ID. must be called under
+ * rcu_read_lock(). The caller must check css_is_removed() or some if
+ * it's concern. (dropping refcnt from swap can be called against removed
+ * memcg.)
+ */
+static struct mem_cgroup *mem_cgroup_lookup(unsigned short id)
+{
+	struct cgroup_subsys_state *css;
+
+	/* ID 0 is unused ID */
+	if (!id)
+		return NULL;
+	css = css_lookup(&mem_cgroup_subsys, id);
+	if (!css)
+		return NULL;
+	return container_of(css, struct mem_cgroup, css);
+}
+
 static struct mem_cgroup *try_get_mem_cgroup_from_swapcache(struct page *page)
 {
 	struct mem_cgroup *mem;
+	struct page_cgroup *pc;
+	unsigned short id;
 	swp_entry_t ent;
 
+	VM_BUG_ON(!PageLocked(page));
+
 	if (!PageSwapCache(page))
 		return NULL;
 
-	ent.val = page_private(page);
-	mem = lookup_swap_cgroup(ent);
-	if (!mem)
-		return NULL;
-	if (!css_tryget(&mem->css))
-		return NULL;
+	pc = lookup_page_cgroup(page);
+	/*
+	 * Used bit of swapcache is solid under page lock.
+	 */
+	if (PageCgroupUsed(pc)) {
+		mem = pc->mem_cgroup;
+		if (mem && !css_tryget(&mem->css))
+			mem = NULL;
+	} else {
+		ent.val = page_private(page);
+		id = lookup_swap_cgroup(ent);
+		rcu_read_lock();
+		mem = mem_cgroup_lookup(id);
+		if (mem && !css_tryget(&mem->css))
+			mem = NULL;
+		rcu_read_unlock();
+	}
 	return mem;
 }
 
@@ -1118,6 +1238,10 @@ int mem_cgroup_newpage_charge(struct page *page,
 				MEM_CGROUP_CHARGE_TYPE_MAPPED, NULL);
 }
 
+static void
+__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
+					enum charge_type ctype);
+
 int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 				gfp_t gfp_mask)
 {
@@ -1154,16 +1278,6 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		unlock_page_cgroup(pc);
 	}
 
-	if (do_swap_account && PageSwapCache(page)) {
-		mem = try_get_mem_cgroup_from_swapcache(page);
-		if (mem)
-			mm = NULL;
-		  else
-			mem = NULL;
-		/* SwapCache may be still linked to LRU now. */
-		mem_cgroup_lru_del_before_commit_swapcache(page);
-	}
-
 	if (unlikely(!mm && !mem))
 		mm = &init_mm;
 
@@ -1171,22 +1285,16 @@ int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm,
 		return mem_cgroup_charge_common(page, mm, gfp_mask,
 				MEM_CGROUP_CHARGE_TYPE_CACHE, NULL);
 
-	ret = mem_cgroup_charge_common(page, mm, gfp_mask,
-				MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
-	if (mem)
-		css_put(&mem->css);
-	if (PageSwapCache(page))
-		mem_cgroup_lru_add_after_commit_swapcache(page);
+	/* shmem */
+	if (PageSwapCache(page)) {
+		ret = mem_cgroup_try_charge_swapin(mm, page, gfp_mask, &mem);
+		if (!ret)
+			__mem_cgroup_commit_charge_swapin(page, mem,
+					MEM_CGROUP_CHARGE_TYPE_SHMEM);
+	} else
+		ret = mem_cgroup_charge_common(page, mm, gfp_mask,
+					MEM_CGROUP_CHARGE_TYPE_SHMEM, mem);
 
-	if (do_swap_account && !ret && PageSwapCache(page)) {
-		swp_entry_t ent = {.val = page_private(page)};
-		/* avoid double counting */
-		mem = swap_cgroup_record(ent, NULL);
-		if (mem) {
-			res_counter_uncharge(&mem->memsw, PAGE_SIZE);
-			mem_cgroup_put(mem);
-		}
-	}
 	return ret;
 }
 
@@ -1229,7 +1337,9 @@ charge_cur_mm:
 	return __mem_cgroup_try_charge(mm, mask, ptr, true);
 }
 
-void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+static void
+__mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr,
+					enum charge_type ctype)
 {
 	struct page_cgroup *pc;
 
@@ -1239,7 +1349,7 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
 		return;
 	pc = lookup_page_cgroup(page);
 	mem_cgroup_lru_del_before_commit_swapcache(page);
-	__mem_cgroup_commit_charge(ptr, pc, MEM_CGROUP_CHARGE_TYPE_MAPPED);
+	__mem_cgroup_commit_charge(ptr, pc, ctype);
 	mem_cgroup_lru_add_after_commit_swapcache(page);
 	/*
 	 * Now swap is on-memory. This means this page may be
@@ -1250,18 +1360,32 @@ void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
 	 */
 	if (do_swap_account && PageSwapCache(page)) {
 		swp_entry_t ent = {.val = page_private(page)};
+		unsigned short id;
 		struct mem_cgroup *memcg;
-		memcg = swap_cgroup_record(ent, NULL);
+
+		id = swap_cgroup_record(ent, 0);
+		rcu_read_lock();
+		memcg = mem_cgroup_lookup(id);
 		if (memcg) {
+			/*
+			 * This recorded memcg can be obsolete one. So, avoid
+			 * calling css_tryget
+			 */
 			res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 			mem_cgroup_put(memcg);
 		}
-
+		rcu_read_unlock();
 	}
 	/* add this page(page_cgroup) to the LRU we want. */
 
 }
 
+void mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr)
+{
+	__mem_cgroup_commit_charge_swapin(page, ptr,
+					MEM_CGROUP_CHARGE_TYPE_MAPPED);
+}
+
 void mem_cgroup_cancel_charge_swapin(struct mem_cgroup *mem)
 {
 	if (mem_cgroup_disabled())
@@ -1324,8 +1448,8 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype)
 	res_counter_uncharge(&mem->res, PAGE_SIZE);
 	if (do_swap_account && (ctype != MEM_CGROUP_CHARGE_TYPE_SWAPOUT))
 		res_counter_uncharge(&mem->memsw, PAGE_SIZE);
-
 	mem_cgroup_charge_statistics(mem, pc, false);
+
 	ClearPageCgroupUsed(pc);
 	/*
 	 * pc->mem_cgroup is not cleared here. It will be accessed when it's
@@ -1377,7 +1501,7 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 					MEM_CGROUP_CHARGE_TYPE_SWAPOUT);
 	/* record memcg information */
 	if (do_swap_account && memcg) {
-		swap_cgroup_record(ent, memcg);
+		swap_cgroup_record(ent, css_id(&memcg->css));
 		mem_cgroup_get(memcg);
 	}
 	if (memcg)
@@ -1392,15 +1516,23 @@ void mem_cgroup_uncharge_swapcache(struct page *page, swp_entry_t ent)
 void mem_cgroup_uncharge_swap(swp_entry_t ent)
 {
 	struct mem_cgroup *memcg;
+	unsigned short id;
 
 	if (!do_swap_account)
 		return;
 
-	memcg = swap_cgroup_record(ent, NULL);
+	id = swap_cgroup_record(ent, 0);
+	rcu_read_lock();
+	memcg = mem_cgroup_lookup(id);
 	if (memcg) {
+		/*
+		 * We uncharge this because swap is freed.
+		 * This memcg can be obsolete one. We avoid calling css_tryget
+		 */
 		res_counter_uncharge(&memcg->memsw, PAGE_SIZE);
 		mem_cgroup_put(memcg);
 	}
+	rcu_read_unlock();
 }
 #endif
 
@@ -1508,7 +1640,8 @@ int mem_cgroup_shrink_usage(struct page *page,
 		return 0;
 
 	do {
-		progress = mem_cgroup_hierarchical_reclaim(mem, gfp_mask, true);
+		progress = mem_cgroup_hierarchical_reclaim(mem,
+					gfp_mask, true, false);
 		progress += mem_cgroup_check_under_limit(mem);
 	} while (!progress && --retry);
 
@@ -1523,11 +1656,21 @@ static DEFINE_MUTEX(set_limit_mutex);
 static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
-
-	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	int retry_count;
 	int progress;
 	u64 memswlimit;
 	int ret = 0;
+	int children = mem_cgroup_count_children(memcg);
+	u64 curusage, oldusage;
+
+	/*
+	 * For keeping hierarchical_reclaim simple, how long we should retry
+	 * is depends on callers. We set our retry-count to be function
+	 * of # of children which we should visit in this loop.
+	 */
+	retry_count = MEM_CGROUP_RECLAIM_RETRIES * children;
+
+	oldusage = res_counter_read_u64(&memcg->res, RES_USAGE);
 
 	while (retry_count) {
 		if (signal_pending(current)) {
@@ -1553,8 +1696,13 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 			break;
 
 		progress = mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL,
-							   false);
-  		if (!progress)			retry_count--;
+						   false, true);
+		curusage = res_counter_read_u64(&memcg->res, RES_USAGE);
+		/* Usage is reduced ? */
+  		if (curusage >= oldusage)
+			retry_count--;
+		else
+			oldusage = curusage;
 	}
 
 	return ret;
@@ -1563,13 +1711,16 @@ static int mem_cgroup_resize_limit(struct mem_cgroup *memcg,
 int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 				unsigned long long val)
 {
-	int retry_count = MEM_CGROUP_RECLAIM_RETRIES;
+	int retry_count;
 	u64 memlimit, oldusage, curusage;
-	int ret;
+	int children = mem_cgroup_count_children(memcg);
+	int ret = -EBUSY;
 
 	if (!do_swap_account)
 		return -EINVAL;
-
+	/* see mem_cgroup_resize_res_limit */
+ 	retry_count = children * MEM_CGROUP_RECLAIM_RETRIES;
+	oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
 	while (retry_count) {
 		if (signal_pending(current)) {
 			ret = -EINTR;
@@ -1593,11 +1744,13 @@ int mem_cgroup_resize_memsw_limit(struct mem_cgroup *memcg,
 		if (!ret)
 			break;
 
-		oldusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
-		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true);
+		mem_cgroup_hierarchical_reclaim(memcg, GFP_KERNEL, true, true);
 		curusage = res_counter_read_u64(&memcg->memsw, RES_USAGE);
+		/* Usage is reduced ? */
 		if (curusage >= oldusage)
 			retry_count--;
+		else
+			oldusage = curusage;
 	}
 	return ret;
 }
@@ -1893,54 +2046,90 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event)
 	return 0;
 }
 
-static const struct mem_cgroup_stat_desc {
-	const char *msg;
-	u64 unit;
-} mem_cgroup_stat_desc[] = {
-	[MEM_CGROUP_STAT_CACHE] = { "cache", PAGE_SIZE, },
-	[MEM_CGROUP_STAT_RSS] = { "rss", PAGE_SIZE, },
-	[MEM_CGROUP_STAT_PGPGIN_COUNT] = {"pgpgin", 1, },
-	[MEM_CGROUP_STAT_PGPGOUT_COUNT] = {"pgpgout", 1, },
+
+/* For read statistics */
+enum {
+	MCS_CACHE,
+	MCS_RSS,
+	MCS_PGPGIN,
+	MCS_PGPGOUT,
+	MCS_INACTIVE_ANON,
+	MCS_ACTIVE_ANON,
+	MCS_INACTIVE_FILE,
+	MCS_ACTIVE_FILE,
+	MCS_UNEVICTABLE,
+	NR_MCS_STAT,
+};
+
+struct mcs_total_stat {
+	s64 stat[NR_MCS_STAT];
+};
+
+struct {
+	char *local_name;
+	char *total_name;
+} memcg_stat_strings[NR_MCS_STAT] = {
+	{"cache", "total_cache"},
+	{"rss", "total_rss"},
+	{"pgpgin", "total_pgpgin"},
+	{"pgpgout", "total_pgpgout"},
+	{"inactive_anon", "total_inactive_anon"},
+	{"active_anon", "total_active_anon"},
+	{"inactive_file", "total_inactive_file"},
+	{"active_file", "total_active_file"},
+	{"unevictable", "total_unevictable"}
 };
 
+
+static int mem_cgroup_get_local_stat(struct mem_cgroup *mem, void *data)
+{
+	struct mcs_total_stat *s = data;
+	s64 val;
+
+	/* per cpu stat */
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_CACHE);
+	s->stat[MCS_CACHE] += val * PAGE_SIZE;
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_RSS);
+	s->stat[MCS_RSS] += val * PAGE_SIZE;
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGIN_COUNT);
+	s->stat[MCS_PGPGIN] += val;
+	val = mem_cgroup_read_stat(&mem->stat, MEM_CGROUP_STAT_PGPGOUT_COUNT);
+	s->stat[MCS_PGPGOUT] += val;
+
+	/* per zone stat */
+	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_ANON);
+	s->stat[MCS_INACTIVE_ANON] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_ANON);
+	s->stat[MCS_ACTIVE_ANON] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_INACTIVE_FILE);
+	s->stat[MCS_INACTIVE_FILE] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_ACTIVE_FILE);
+	s->stat[MCS_ACTIVE_FILE] += val * PAGE_SIZE;
+	val = mem_cgroup_get_local_zonestat(mem, LRU_UNEVICTABLE);
+	s->stat[MCS_UNEVICTABLE] += val * PAGE_SIZE;
+	return 0;
+}
+
+static void
+mem_cgroup_get_total_stat(struct mem_cgroup *mem, struct mcs_total_stat *s)
+{
+	mem_cgroup_walk_tree(mem, s, mem_cgroup_get_local_stat);
+}
+
 static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 				 struct cgroup_map_cb *cb)
 {
 	struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont);
-	struct mem_cgroup_stat *stat = &mem_cont->stat;
+	struct mcs_total_stat mystat;
 	int i;
 
-	for (i = 0; i < ARRAY_SIZE(stat->cpustat[0].count); i++) {
-		s64 val;
+	memset(&mystat, 0, sizeof(mystat));
+	mem_cgroup_get_local_stat(mem_cont, &mystat);
 
-		val = mem_cgroup_read_stat(stat, i);
-		val *= mem_cgroup_stat_desc[i].unit;
-		cb->fill(cb, mem_cgroup_stat_desc[i].msg, val);
-	}
-	/* showing # of active pages */
-	{
-		unsigned long active_anon, inactive_anon;
-		unsigned long active_file, inactive_file;
-		unsigned long unevictable;
-
-		inactive_anon = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_INACTIVE_ANON);
-		active_anon = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_ACTIVE_ANON);
-		inactive_file = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_INACTIVE_FILE);
-		active_file = mem_cgroup_get_all_zonestat(mem_cont,
-						LRU_ACTIVE_FILE);
-		unevictable = mem_cgroup_get_all_zonestat(mem_cont,
-							LRU_UNEVICTABLE);
-
-		cb->fill(cb, "active_anon", (active_anon) * PAGE_SIZE);
-		cb->fill(cb, "inactive_anon", (inactive_anon) * PAGE_SIZE);
-		cb->fill(cb, "active_file", (active_file) * PAGE_SIZE);
-		cb->fill(cb, "inactive_file", (inactive_file) * PAGE_SIZE);
-		cb->fill(cb, "unevictable", unevictable * PAGE_SIZE);
+	for (i = 0; i < NR_MCS_STAT; i++)
+		cb->fill(cb, memcg_stat_strings[i].local_name, mystat.stat[i]);
 
-	}
+	/* Hierarchical information */
 	{
 		unsigned long long limit, memsw_limit;
 		memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit);
@@ -1949,6 +2138,12 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft,
 			cb->fill(cb, "hierarchical_memsw_limit", memsw_limit);
 	}
 
+	memset(&mystat, 0, sizeof(mystat));
+	mem_cgroup_get_total_stat(mem_cont, &mystat);
+	for (i = 0; i < NR_MCS_STAT; i++)
+		cb->fill(cb, memcg_stat_strings[i].total_name, mystat.stat[i]);
+
+
 #ifdef CONFIG_DEBUG_VM
 	cb->fill(cb, "inactive_ratio", calc_inactive_ratio(mem_cont, NULL));
 
@@ -2178,6 +2373,8 @@ static void __mem_cgroup_free(struct mem_cgroup *mem)
 {
 	int node;
 
+	free_css_id(&mem_cgroup_subsys, &mem->css);
+
 	for_each_node_state(node, N_POSSIBLE)
 		free_mem_cgroup_per_zone_info(mem, node);
 
@@ -2228,11 +2425,12 @@ static struct cgroup_subsys_state * __ref
 mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 {
 	struct mem_cgroup *mem, *parent;
+	long error = -ENOMEM;
 	int node;
 
 	mem = mem_cgroup_alloc();
 	if (!mem)
-		return ERR_PTR(-ENOMEM);
+		return ERR_PTR(error);
 
 	for_each_node_state(node, N_POSSIBLE)
 		if (alloc_mem_cgroup_per_zone_info(mem, node))
@@ -2260,7 +2458,7 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 		res_counter_init(&mem->res, NULL);
 		res_counter_init(&mem->memsw, NULL);
 	}
-	mem->last_scanned_child = NULL;
+	mem->last_scanned_child = 0;
 	spin_lock_init(&mem->reclaim_param_lock);
 
 	if (parent)
@@ -2269,26 +2467,22 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont)
 	return &mem->css;
 free_out:
 	__mem_cgroup_free(mem);
-	return ERR_PTR(-ENOMEM);
+	return ERR_PTR(error);
 }
 
-static void mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
+static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss,
 					struct cgroup *cont)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	mem_cgroup_force_empty(mem, false);
+
+	return mem_cgroup_force_empty(mem, false);
 }
 
 static void mem_cgroup_destroy(struct cgroup_subsys *ss,
 				struct cgroup *cont)
 {
 	struct mem_cgroup *mem = mem_cgroup_from_cont(cont);
-	struct mem_cgroup *last_scanned_child = mem->last_scanned_child;
 
-	if (last_scanned_child) {
-		VM_BUG_ON(!mem_cgroup_is_obsolete(last_scanned_child));
-		mem_cgroup_put(last_scanned_child);
-	}
 	mem_cgroup_put(mem);
 }
 
@@ -2327,6 +2521,7 @@ struct cgroup_subsys mem_cgroup_subsys = {
 	.populate = mem_cgroup_populate,
 	.attach = mem_cgroup_move_task,
 	.early_init = 0,
+	.use_id = 1,
 };
 
 #ifdef CONFIG_CGROUP_MEM_RES_CTLR_SWAP
diff --git a/mm/migrate.c b/mm/migrate.c
index a9eff3f092f6..068655d8f883 100644
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -250,7 +250,7 @@ out:
  * The number of remaining references must be:
  * 1 for anonymous pages without a mapping
  * 2 for pages with a mapping
- * 3 for pages with a mapping and PagePrivate set.
+ * 3 for pages with a mapping and PagePrivate/PagePrivate2 set.
  */
 static int migrate_page_move_mapping(struct address_space *mapping,
 		struct page *newpage, struct page *page)
@@ -270,7 +270,7 @@ static int migrate_page_move_mapping(struct address_space *mapping,
 	pslot = radix_tree_lookup_slot(&mapping->page_tree,
  					page_index(page));
 
-	expected_count = 2 + !!PagePrivate(page);
+	expected_count = 2 + !!page_has_private(page);
 	if (page_count(page) != expected_count ||
 			(struct page *)radix_tree_deref_slot(pslot) != page) {
 		spin_unlock_irq(&mapping->tree_lock);
@@ -386,7 +386,7 @@ EXPORT_SYMBOL(fail_migrate_page);
 
 /*
  * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
+ * pages that do not use PagePrivate/PagePrivate2.
  *
  * Pages are locked upon entry and exit.
  */
@@ -522,7 +522,7 @@ static int fallback_migrate_page(struct address_space *mapping,
 	 * Buffers may be managed in a filesystem specific way.
 	 * We must have no buffers or drop them.
 	 */
-	if (PagePrivate(page) &&
+	if (page_has_private(page) &&
 	    !try_to_release_page(page, GFP_KERNEL))
 		return -EAGAIN;
 
@@ -655,7 +655,7 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private,
 	 * free the metadata, so the page can be freed.
 	 */
 	if (!page->mapping) {
-		if (!PageAnon(page) && PagePrivate(page)) {
+		if (!PageAnon(page) && page_has_private(page)) {
 			/*
 			 * Go direct to try_to_free_buffers() here because
 			 * a) that's what try_to_release_page() would do anyway
diff --git a/mm/mmap.c b/mm/mmap.c
index 1abb9185a686..4a3841186c11 100644
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2481,7 +2481,4 @@ void mm_drop_all_locks(struct mm_struct *mm)
  */
 void __init mmap_init(void)
 {
-	vm_area_cachep = kmem_cache_create("vm_area_struct",
-			sizeof(struct vm_area_struct), 0,
-			SLAB_PANIC, NULL);
 }
diff --git a/mm/nommu.c b/mm/nommu.c
index 2fcf47d449b4..72eda4aee2cb 100644
--- a/mm/nommu.c
+++ b/mm/nommu.c
@@ -69,7 +69,7 @@ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT;
 int sysctl_nr_trim_pages = 1; /* page trimming behaviour */
 int heap_stack_gap = 0;
 
-atomic_t mmap_pages_allocated;
+atomic_long_t mmap_pages_allocated;
 
 EXPORT_SYMBOL(mem_map);
 EXPORT_SYMBOL(num_physpages);
@@ -463,12 +463,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk)
  */
 void __init mmap_init(void)
 {
-	vm_region_jar = kmem_cache_create("vm_region_jar",
-					  sizeof(struct vm_region), 0,
-					  SLAB_PANIC, NULL);
-	vm_area_cachep = kmem_cache_create("vm_area_struct",
-					   sizeof(struct vm_area_struct), 0,
-					   SLAB_PANIC, NULL);
+	vm_region_jar = KMEM_CACHE(vm_region, SLAB_PANIC);
 }
 
 /*
@@ -486,27 +481,24 @@ static noinline void validate_nommu_regions(void)
 		return;
 
 	last = rb_entry(lastp, struct vm_region, vm_rb);
-	if (unlikely(last->vm_end <= last->vm_start))
-		BUG();
-	if (unlikely(last->vm_top < last->vm_end))
-		BUG();
+	BUG_ON(unlikely(last->vm_end <= last->vm_start));
+	BUG_ON(unlikely(last->vm_top < last->vm_end));
 
 	while ((p = rb_next(lastp))) {
 		region = rb_entry(p, struct vm_region, vm_rb);
 		last = rb_entry(lastp, struct vm_region, vm_rb);
 
-		if (unlikely(region->vm_end <= region->vm_start))
-			BUG();
-		if (unlikely(region->vm_top < region->vm_end))
-			BUG();
-		if (unlikely(region->vm_start < last->vm_top))
-			BUG();
+		BUG_ON(unlikely(region->vm_end <= region->vm_start));
+		BUG_ON(unlikely(region->vm_top < region->vm_end));
+		BUG_ON(unlikely(region->vm_start < last->vm_top));
 
 		lastp = p;
 	}
 }
 #else
-#define validate_nommu_regions() do {} while(0)
+static void validate_nommu_regions(void)
+{
+}
 #endif
 
 /*
@@ -563,16 +555,17 @@ static void free_page_series(unsigned long from, unsigned long to)
 		struct page *page = virt_to_page(from);
 
 		kdebug("- free %lx", from);
-		atomic_dec(&mmap_pages_allocated);
+		atomic_long_dec(&mmap_pages_allocated);
 		if (page_count(page) != 1)
-			kdebug("free page %p [%d]", page, page_count(page));
+			kdebug("free page %p: refcount not one: %d",
+			       page, page_count(page));
 		put_page(page);
 	}
 }
 
 /*
  * release a reference to a region
- * - the caller must hold the region semaphore, which this releases
+ * - the caller must hold the region semaphore for writing, which this releases
  * - the region may not have been added to the tree yet, in which case vm_top
  *   will equal vm_start
  */
@@ -1096,7 +1089,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 		goto enomem;
 
 	total = 1 << order;
-	atomic_add(total, &mmap_pages_allocated);
+	atomic_long_add(total, &mmap_pages_allocated);
 
 	point = rlen >> PAGE_SHIFT;
 
@@ -1107,7 +1100,7 @@ static int do_mmap_private(struct vm_area_struct *vma,
 			order = ilog2(total - point);
 			n = 1 << order;
 			kdebug("shave %lu/%lu @%lu", n, total - point, total);
-			atomic_sub(n, &mmap_pages_allocated);
+			atomic_long_sub(n, &mmap_pages_allocated);
 			total -= n;
 			set_page_refcounted(pages + total);
 			__free_pages(pages + total, order);
@@ -1536,10 +1529,15 @@ int do_munmap(struct mm_struct *mm, unsigned long start, size_t len)
 	/* find the first potentially overlapping VMA */
 	vma = find_vma(mm, start);
 	if (!vma) {
-		printk(KERN_WARNING
-		       "munmap of memory not mmapped by process %d (%s):"
-		       " 0x%lx-0x%lx\n",
-		       current->pid, current->comm, start, start + len - 1);
+		static int limit = 0;
+		if (limit < 5) {
+			printk(KERN_WARNING
+			       "munmap of memory not mmapped by process %d"
+			       " (%s): 0x%lx-0x%lx\n",
+			       current->pid, current->comm,
+			       start, start + len - 1);
+			limit++;
+		}
 		return -EINVAL;
 	}
 
diff --git a/mm/oom_kill.c b/mm/oom_kill.c
index d3b9bac085b5..2f3166e308d9 100644
--- a/mm/oom_kill.c
+++ b/mm/oom_kill.c
@@ -394,6 +394,7 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order,
 		cpuset_print_task_mems_allowed(current);
 		task_unlock(current);
 		dump_stack();
+		mem_cgroup_print_oom_info(mem, current);
 		show_mem();
 		if (sysctl_oom_dump_tasks)
 			dump_tasks(mem);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0284e528748d..e2f26991fff1 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -331,7 +331,7 @@ static int destroy_compound_page(struct page *page, unsigned long order)
 	for (i = 1; i < nr_pages; i++) {
 		struct page *p = page + i;
 
-		if (unlikely(!PageTail(p) | (p->first_page != page))) {
+		if (unlikely(!PageTail(p) || (p->first_page != page))) {
 			bad_page(page);
 			bad++;
 		}
@@ -2128,7 +2128,7 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 	int n, val;
 	int min_val = INT_MAX;
 	int best_node = -1;
-	node_to_cpumask_ptr(tmp, 0);
+	const struct cpumask *tmp = cpumask_of_node(0);
 
 	/* Use the local node if we haven't already */
 	if (!node_isset(node, *used_node_mask)) {
@@ -2149,8 +2149,8 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 		val += (n < node);
 
 		/* Give preference to headless and unused nodes */
-		node_to_cpumask_ptr_next(tmp, n);
-		if (!cpus_empty(*tmp))
+		tmp = cpumask_of_node(n);
+		if (!cpumask_empty(tmp))
 			val += PENALTY_FOR_NODE_WITH_CPUS;
 
 		/* Slight preference for less loaded node */
diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c
index ceecfbb143fa..791905c991df 100644
--- a/mm/page_cgroup.c
+++ b/mm/page_cgroup.c
@@ -285,12 +285,8 @@ struct swap_cgroup_ctrl {
 
 struct swap_cgroup_ctrl swap_cgroup_ctrl[MAX_SWAPFILES];
 
-/*
- * This 8bytes seems big..maybe we can reduce this when we can use "id" for
- * cgroup rather than pointer.
- */
 struct swap_cgroup {
-	struct mem_cgroup	*val;
+	unsigned short		id;
 };
 #define SC_PER_PAGE	(PAGE_SIZE/sizeof(struct swap_cgroup))
 #define SC_POS_MASK	(SC_PER_PAGE - 1)
@@ -342,10 +338,10 @@ not_enough_page:
  * @ent: swap entry to be recorded into
  * @mem: mem_cgroup to be recorded
  *
- * Returns old value at success, NULL at failure.
- * (Of course, old value can be NULL.)
+ * Returns old value at success, 0 at failure.
+ * (Of course, old value can be 0.)
  */
-struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
+unsigned short swap_cgroup_record(swp_entry_t ent, unsigned short id)
 {
 	int type = swp_type(ent);
 	unsigned long offset = swp_offset(ent);
@@ -354,18 +350,18 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
 	struct swap_cgroup_ctrl *ctrl;
 	struct page *mappage;
 	struct swap_cgroup *sc;
-	struct mem_cgroup *old;
+	unsigned short old;
 
 	if (!do_swap_account)
-		return NULL;
+		return 0;
 
 	ctrl = &swap_cgroup_ctrl[type];
 
 	mappage = ctrl->map[idx];
 	sc = page_address(mappage);
 	sc += pos;
-	old = sc->val;
-	sc->val = mem;
+	old = sc->id;
+	sc->id = id;
 
 	return old;
 }
@@ -374,9 +370,9 @@ struct mem_cgroup *swap_cgroup_record(swp_entry_t ent, struct mem_cgroup *mem)
  * lookup_swap_cgroup - lookup mem_cgroup tied to swap entry
  * @ent: swap entry to be looked up.
  *
- * Returns pointer to mem_cgroup at success. NULL at failure.
+ * Returns CSS ID of mem_cgroup at success. 0 at failure. (0 is invalid ID)
  */
-struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
+unsigned short lookup_swap_cgroup(swp_entry_t ent)
 {
 	int type = swp_type(ent);
 	unsigned long offset = swp_offset(ent);
@@ -385,16 +381,16 @@ struct mem_cgroup *lookup_swap_cgroup(swp_entry_t ent)
 	struct swap_cgroup_ctrl *ctrl;
 	struct page *mappage;
 	struct swap_cgroup *sc;
-	struct mem_cgroup *ret;
+	unsigned short ret;
 
 	if (!do_swap_account)
-		return NULL;
+		return 0;
 
 	ctrl = &swap_cgroup_ctrl[type];
 	mappage = ctrl->map[idx];
 	sc = page_address(mappage);
 	sc += pos;
-	ret = sc->val;
+	ret = sc->id;
 	return ret;
 }
 
@@ -430,13 +426,6 @@ int swap_cgroup_swapon(int type, unsigned long max_pages)
 	}
 	mutex_unlock(&swap_cgroup_mutex);
 
-	printk(KERN_INFO
-		"swap_cgroup: uses %ld bytes of vmalloc for pointer array space"
-		" and %ld bytes to hold mem_cgroup pointers on swap\n",
-		array_size, length * PAGE_SIZE);
-	printk(KERN_INFO
-	"swap_cgroup can be disabled by noswapaccount boot option.\n");
-
 	return 0;
 nomem:
 	printk(KERN_INFO "couldn't allocate enough memory for swap_cgroup.\n");
diff --git a/mm/quicklist.c b/mm/quicklist.c
index 8dbb6805ef35..e66d07d1b4ff 100644
--- a/mm/quicklist.c
+++ b/mm/quicklist.c
@@ -29,7 +29,7 @@ static unsigned long max_pages(unsigned long min_pages)
 	int node = numa_node_id();
 	struct zone *zones = NODE_DATA(node)->node_zones;
 	int num_cpus_on_node;
-	node_to_cpumask_ptr(cpumask_on_node, node);
+	const struct cpumask *cpumask_on_node = cpumask_of_node(node);
 
 	node_free_pages =
 #ifdef CONFIG_ZONE_DMA
diff --git a/mm/readahead.c b/mm/readahead.c
index 9ce303d4b810..133b6d525513 100644
--- a/mm/readahead.c
+++ b/mm/readahead.c
@@ -31,6 +31,42 @@ EXPORT_SYMBOL_GPL(file_ra_state_init);
 
 #define list_to_page(head) (list_entry((head)->prev, struct page, lru))
 
+/*
+ * see if a page needs releasing upon read_cache_pages() failure
+ * - the caller of read_cache_pages() may have set PG_private or PG_fscache
+ *   before calling, such as the NFS fs marking pages that are cached locally
+ *   on disk, thus we need to give the fs a chance to clean up in the event of
+ *   an error
+ */
+static void read_cache_pages_invalidate_page(struct address_space *mapping,
+					     struct page *page)
+{
+	if (page_has_private(page)) {
+		if (!trylock_page(page))
+			BUG();
+		page->mapping = mapping;
+		do_invalidatepage(page, 0);
+		page->mapping = NULL;
+		unlock_page(page);
+	}
+	page_cache_release(page);
+}
+
+/*
+ * release a list of pages, invalidating them first if need be
+ */
+static void read_cache_pages_invalidate_pages(struct address_space *mapping,
+					      struct list_head *pages)
+{
+	struct page *victim;
+
+	while (!list_empty(pages)) {
+		victim = list_to_page(pages);
+		list_del(&victim->lru);
+		read_cache_pages_invalidate_page(mapping, victim);
+	}
+}
+
 /**
  * read_cache_pages - populate an address space with some pages & start reads against them
  * @mapping: the address_space
@@ -52,14 +88,14 @@ int read_cache_pages(struct address_space *mapping, struct list_head *pages,
 		list_del(&page->lru);
 		if (add_to_page_cache_lru(page, mapping,
 					page->index, GFP_KERNEL)) {
-			page_cache_release(page);
+			read_cache_pages_invalidate_page(mapping, page);
 			continue;
 		}
 		page_cache_release(page);
 
 		ret = filler(data, page);
 		if (unlikely(ret)) {
-			put_pages_list(pages);
+			read_cache_pages_invalidate_pages(mapping, pages);
 			break;
 		}
 		task_io_account_read(PAGE_CACHE_SIZE);
diff --git a/mm/slab.c b/mm/slab.c
index 9ec66c3e6ee0..4fc1761c6dc8 100644
--- a/mm/slab.c
+++ b/mm/slab.c
@@ -1169,7 +1169,7 @@ static void __cpuinit cpuup_canceled(long cpu)
 	struct kmem_cache *cachep;
 	struct kmem_list3 *l3 = NULL;
 	int node = cpu_to_node(cpu);
-	node_to_cpumask_ptr(mask, node);
+	const struct cpumask *mask = cpumask_of_node(node);
 
 	list_for_each_entry(cachep, &cache_chain, next) {
 		struct array_cache *nc;
@@ -4049,8 +4049,7 @@ static void cache_reap(struct work_struct *w)
 	struct kmem_cache *searchp;
 	struct kmem_list3 *l3;
 	int node = numa_node_id();
-	struct delayed_work *work =
-		container_of(w, struct delayed_work, work);
+	struct delayed_work *work = to_delayed_work(w);
 
 	if (!mutex_trylock(&cache_chain_mutex))
 		/* Give up. Setup the next iteration. */
diff --git a/mm/swap.c b/mm/swap.c
index 6e83084c1f6c..bede23ce64ea 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -448,8 +448,8 @@ void pagevec_strip(struct pagevec *pvec)
 	for (i = 0; i < pagevec_count(pvec); i++) {
 		struct page *page = pvec->pages[i];
 
-		if (PagePrivate(page) && trylock_page(page)) {
-			if (PagePrivate(page))
+		if (page_has_private(page) && trylock_page(page)) {
+			if (page_has_private(page))
 				try_to_release_page(page, 0);
 			unlock_page(page);
 		}
diff --git a/mm/truncate.c b/mm/truncate.c
index 1229211104f8..55206fab7b99 100644
--- a/mm/truncate.c
+++ b/mm/truncate.c
@@ -50,7 +50,7 @@ void do_invalidatepage(struct page *page, unsigned long offset)
 static inline void truncate_partial_page(struct page *page, unsigned partial)
 {
 	zero_user_segment(page, partial, PAGE_CACHE_SIZE);
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, partial);
 }
 
@@ -99,7 +99,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return;
 
-	if (PagePrivate(page))
+	if (page_has_private(page))
 		do_invalidatepage(page, 0);
 
 	cancel_dirty_page(page, PAGE_CACHE_SIZE);
@@ -126,7 +126,7 @@ invalidate_complete_page(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, 0))
+	if (page_has_private(page) && !try_to_release_page(page, 0))
 		return 0;
 
 	clear_page_mlock(page);
@@ -348,7 +348,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 	if (page->mapping != mapping)
 		return 0;
 
-	if (PagePrivate(page) && !try_to_release_page(page, GFP_KERNEL))
+	if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL))
 		return 0;
 
 	spin_lock_irq(&mapping->tree_lock);
@@ -356,7 +356,7 @@ invalidate_complete_page2(struct address_space *mapping, struct page *page)
 		goto failed;
 
 	clear_page_mlock(page);
-	BUG_ON(PagePrivate(page));
+	BUG_ON(page_has_private(page));
 	__remove_from_page_cache(page);
 	spin_unlock_irq(&mapping->tree_lock);
 	page_cache_release(page);	/* pagecache ref */
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 06e72693b458..39fdfb14eeaa 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -283,7 +283,7 @@ static inline int page_mapping_inuse(struct page *page)
 
 static inline int is_page_cache_freeable(struct page *page)
 {
-	return page_count(page) - !!PagePrivate(page) == 2;
+	return page_count(page) - !!page_has_private(page) == 2;
 }
 
 static int may_write_to_queue(struct backing_dev_info *bdi)
@@ -367,7 +367,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping,
 		 * Some data journaling orphaned pages can have
 		 * page->mapping == NULL while being dirty with clean buffers.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (try_to_free_buffers(page)) {
 				ClearPageDirty(page);
 				printk("%s: orphaned page\n", __func__);
@@ -727,7 +727,7 @@ static unsigned long shrink_page_list(struct list_head *page_list,
 		 * process address space (page_count == 1) it can be freed.
 		 * Otherwise, leave the page on the LRU so it is swappable.
 		 */
-		if (PagePrivate(page)) {
+		if (page_has_private(page)) {
 			if (!try_to_release_page(page, sc->gfp_mask))
 				goto activate_locked;
 			if (!mapping && page_count(page) == 1) {
@@ -1967,7 +1967,7 @@ static int kswapd(void *p)
 	struct reclaim_state reclaim_state = {
 		.reclaimed_slab = 0,
 	};
-	node_to_cpumask_ptr(cpumask, pgdat->node_id);
+	const struct cpumask *cpumask = cpumask_of_node(pgdat->node_id);
 
 	lockdep_set_current_reclaim_state(GFP_KERNEL);
 
@@ -2204,7 +2204,9 @@ static int __devinit cpu_callback(struct notifier_block *nfb,
 	if (action == CPU_ONLINE || action == CPU_ONLINE_FROZEN) {
 		for_each_node_state(nid, N_HIGH_MEMORY) {
 			pg_data_t *pgdat = NODE_DATA(nid);
-			node_to_cpumask_ptr(mask, pgdat->node_id);
+			const struct cpumask *mask;
+
+			mask = cpumask_of_node(pgdat->node_id);
 
 			if (cpumask_any_and(cpu_online_mask, mask) < nr_cpu_ids)
 				/* One of our CPUs online: restore mask */
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 9826766f1274..66f6130976cb 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -891,7 +891,7 @@ static void vmstat_update(struct work_struct *w)
 {
 	refresh_cpu_vm_stats(smp_processor_id());
 	schedule_delayed_work(&__get_cpu_var(vmstat_work),
-		sysctl_stat_interval);
+		round_jiffies_relative(sysctl_stat_interval));
 }
 
 static void __cpuinit start_cpu_timer(int cpu)
@@ -899,7 +899,8 @@ static void __cpuinit start_cpu_timer(int cpu)
 	struct delayed_work *vmstat_work = &per_cpu(vmstat_work, cpu);
 
 	INIT_DELAYED_WORK_DEFERRABLE(vmstat_work, vmstat_update);
-	schedule_delayed_work_on(cpu, vmstat_work, HZ + cpu);
+	schedule_delayed_work_on(cpu, vmstat_work,
+				 __round_jiffies_relative(HZ, cpu));
 }
 
 /*
diff --git a/net/Kconfig b/net/Kconfig
index ec93e7e38b38..ce77db4fcec8 100644
--- a/net/Kconfig
+++ b/net/Kconfig
@@ -140,7 +140,7 @@ config NETFILTER_ADVANCED
 	default y
 	help
 	  If you say Y here you can select between all the netfilter modules.
-	  If you say N the more ununsual ones will not be shown and the
+	  If you say N the more unusual ones will not be shown and the
 	  basic ones needed by most people will default to 'M'.
 
 	  If unsure, say Y.
diff --git a/net/core/dev.c b/net/core/dev.c
index 52fea5b28ca6..91d792d17e09 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -2472,8 +2472,9 @@ static int __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb)
 		return GRO_NORMAL;
 
 	for (p = napi->gro_list; p; p = p->next) {
-		NAPI_GRO_CB(p)->same_flow = !compare_ether_header(
-			skb_mac_header(p), skb_gro_mac_header(skb));
+		NAPI_GRO_CB(p)->same_flow = (p->dev == skb->dev)
+			&& !compare_ether_header(skb_mac_header(p),
+						 skb_gro_mac_header(skb));
 		NAPI_GRO_CB(p)->flush = 0;
 	}
 
diff --git a/net/core/ethtool.c b/net/core/ethtool.c
index 244ca56dffac..d9d5160610d5 100644
--- a/net/core/ethtool.c
+++ b/net/core/ethtool.c
@@ -261,8 +261,7 @@ static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr)
 	ret = 0;
 
 err_out:
-	if (rule_buf)
-		kfree(rule_buf);
+	kfree(rule_buf);
 
 	return ret;
 }
diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c
index 35c5f6a5cb7c..5ba533d234db 100644
--- a/net/ipv4/netfilter/arp_tables.c
+++ b/net/ipv4/netfilter/arp_tables.c
@@ -253,7 +253,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 	indev = in ? in->name : nulldevname;
 	outdev = out ? out->name : nulldevname;
 
-	rcu_read_lock();
+	rcu_read_lock_bh();
 	private = rcu_dereference(table->private);
 	table_base = rcu_dereference(private->entries[smp_processor_id()]);
 
@@ -329,7 +329,7 @@ unsigned int arpt_do_table(struct sk_buff *skb,
 		}
 	} while (!hotdrop);
 
-	rcu_read_unlock();
+	rcu_read_unlock_bh();
 
 	if (hotdrop)
 		return NF_DROP;
diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c
index 82ee7c9049ff..810c0b62c7d4 100644
--- a/net/ipv4/netfilter/ip_tables.c
+++ b/net/ipv4/netfilter/ip_tables.c
@@ -339,7 +339,7 @@ ipt_do_table(struct sk_buff *skb,
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
 
-	rcu_read_lock();
+	rcu_read_lock_bh();
 	private = rcu_dereference(table->private);
 	table_base = rcu_dereference(private->entries[smp_processor_id()]);
 
@@ -437,7 +437,7 @@ ipt_do_table(struct sk_buff *skb,
 		}
 	} while (!hotdrop);
 
-	rcu_read_unlock();
+	rcu_read_unlock_bh();
 
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c
index 2451aeb5ac23..fafbec8b073e 100644
--- a/net/ipv4/tcp.c
+++ b/net/ipv4/tcp.c
@@ -1081,8 +1081,7 @@ out_err:
  *	this, no blocking and very strange errors 8)
  */
 
-static int tcp_recv_urg(struct sock *sk, long timeo,
-			struct msghdr *msg, int len, int flags)
+static int tcp_recv_urg(struct sock *sk, struct msghdr *msg, int len, int flags)
 {
 	struct tcp_sock *tp = tcp_sk(sk);
 
@@ -1697,7 +1696,7 @@ out:
 	return err;
 
 recv_urg:
-	err = tcp_recv_urg(sk, timeo, msg, len, flags);
+	err = tcp_recv_urg(sk, msg, len, flags);
 	goto out;
 }
 
diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c
index c1f259d2d33b..53300fa2359f 100644
--- a/net/ipv4/tcp_output.c
+++ b/net/ipv4/tcp_output.c
@@ -754,6 +754,36 @@ static void tcp_adjust_fackets_out(struct sock *sk, struct sk_buff *skb,
 		tp->fackets_out -= decr;
 }
 
+/* Pcount in the middle of the write queue got changed, we need to do various
+ * tweaks to fix counters
+ */
+static void tcp_adjust_pcount(struct sock *sk, struct sk_buff *skb, int decr)
+{
+	struct tcp_sock *tp = tcp_sk(sk);
+
+	tp->packets_out -= decr;
+
+	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
+		tp->sacked_out -= decr;
+	if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
+		tp->retrans_out -= decr;
+	if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
+		tp->lost_out -= decr;
+
+	/* Reno case is special. Sigh... */
+	if (tcp_is_reno(tp) && decr > 0)
+		tp->sacked_out -= min_t(u32, tp->sacked_out, decr);
+
+	tcp_adjust_fackets_out(sk, skb, decr);
+
+	if (tp->lost_skb_hint &&
+	    before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
+	    (tcp_is_fack(tp) || TCP_SKB_CB(skb)->sacked))
+		tp->lost_cnt_hint -= decr;
+
+	tcp_verify_left_out(tp);
+}
+
 /* Function to create two new TCP segments.  Shrinks the given segment
  * to the specified size and appends a new segment with the rest of the
  * packet to the list.  This won't be called frequently, I hope.
@@ -836,28 +866,8 @@ int tcp_fragment(struct sock *sk, struct sk_buff *skb, u32 len,
 		int diff = old_factor - tcp_skb_pcount(skb) -
 			tcp_skb_pcount(buff);
 
-		tp->packets_out -= diff;
-
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)
-			tp->sacked_out -= diff;
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)
-			tp->retrans_out -= diff;
-
-		if (TCP_SKB_CB(skb)->sacked & TCPCB_LOST)
-			tp->lost_out -= diff;
-
-		/* Adjust Reno SACK estimate. */
-		if (tcp_is_reno(tp) && diff > 0) {
-			tcp_dec_pcount_approx_int(&tp->sacked_out, diff);
-			tcp_verify_left_out(tp);
-		}
-		tcp_adjust_fackets_out(sk, skb, diff);
-
-		if (tp->lost_skb_hint &&
-		    before(TCP_SKB_CB(skb)->seq,
-			   TCP_SKB_CB(tp->lost_skb_hint)->seq) &&
-		    (tcp_is_fack(tp) || TCP_SKB_CB(skb)->sacked))
-			tp->lost_cnt_hint -= diff;
+		if (diff)
+			tcp_adjust_pcount(sk, skb, diff);
 	}
 
 	/* Link BUFF into the send queue. */
@@ -1768,22 +1778,14 @@ static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb)
 	 * packet counting does not break.
 	 */
 	TCP_SKB_CB(skb)->sacked |= TCP_SKB_CB(next_skb)->sacked & TCPCB_EVER_RETRANS;
-	if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_RETRANS)
-		tp->retrans_out -= tcp_skb_pcount(next_skb);
-	if (TCP_SKB_CB(next_skb)->sacked & TCPCB_LOST)
-		tp->lost_out -= tcp_skb_pcount(next_skb);
-	/* Reno case is special. Sigh... */
-	if (tcp_is_reno(tp) && tp->sacked_out)
-		tcp_dec_pcount_approx(&tp->sacked_out, next_skb);
-
-	tcp_adjust_fackets_out(sk, next_skb, tcp_skb_pcount(next_skb));
-	tp->packets_out -= tcp_skb_pcount(next_skb);
 
 	/* changed transmit queue under us so clear hints */
 	tcp_clear_retrans_hints_partial(tp);
 	if (next_skb == tp->retransmit_skb_hint)
 		tp->retransmit_skb_hint = skb;
 
+	tcp_adjust_pcount(sk, next_skb, tcp_skb_pcount(next_skb));
+
 	sk_wmem_free_skb(sk, next_skb);
 }
 
@@ -1891,7 +1893,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb)
 		if (tcp_fragment(sk, skb, cur_mss, cur_mss))
 			return -ENOMEM; /* We'll try again later. */
 	} else {
-		tcp_init_tso_segs(sk, skb, cur_mss);
+		int oldpcount = tcp_skb_pcount(skb);
+
+		if (unlikely(oldpcount > 1)) {
+			tcp_init_tso_segs(sk, skb, cur_mss);
+			tcp_adjust_pcount(sk, skb, oldpcount - tcp_skb_pcount(skb));
+		}
 	}
 
 	tcp_retrans_try_collapse(sk, skb, cur_mss);
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig
index ec992159b5f8..ca8cb326d1d2 100644
--- a/net/ipv6/Kconfig
+++ b/net/ipv6/Kconfig
@@ -22,17 +22,17 @@ menuconfig IPV6
 if IPV6
 
 config IPV6_PRIVACY
-	bool "IPv6: Privacy Extensions support"
+	bool "IPv6: Privacy Extensions (RFC 3041) support"
 	---help---
 	  Privacy Extensions for Stateless Address Autoconfiguration in IPv6
-	  support.  With this option, additional periodically-alter 
-	  pseudo-random global-scope unicast address(es) will assigned to
+	  support.  With this option, additional periodically-altered
+	  pseudo-random global-scope unicast address(es) will be assigned to
 	  your interface(s).
 	
-	  We use our standard pseudo random algorithm to generate randomized
-	  interface identifier, instead of one described in RFC 3041.
+	  We use our standard pseudo-random algorithm to generate the
+          randomized interface identifier, instead of one described in RFC 3041.
 
-	  By default, kernel do not generate temporary addresses.
+	  By default the kernel does not generate temporary addresses.
 	  To use temporary addresses, do
 	
 	        echo 2 >/proc/sys/net/ipv6/conf/all/use_tempaddr 
@@ -43,9 +43,9 @@ config IPV6_ROUTER_PREF
 	bool "IPv6: Router Preference (RFC 4191) support"
 	---help---
 	  Router Preference is an optional extension to the Router
-	  Advertisement message to improve the ability of hosts
-	  to pick more appropriate router, especially when the hosts
-	  is placed in a multi-homed network.
+	  Advertisement message which improves the ability of hosts
+	  to pick an appropriate router, especially when the hosts
+	  are placed in a multi-homed network.
 
 	  If unsure, say N.
 
diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c
index e89cfa3a8f25..dfed176aed37 100644
--- a/net/ipv6/netfilter/ip6_tables.c
+++ b/net/ipv6/netfilter/ip6_tables.c
@@ -365,7 +365,7 @@ ip6t_do_table(struct sk_buff *skb,
 
 	IP_NF_ASSERT(table->valid_hooks & (1 << hook));
 
-	rcu_read_lock();
+	rcu_read_lock_bh();
 	private = rcu_dereference(table->private);
 	table_base = rcu_dereference(private->entries[smp_processor_id()]);
 
@@ -466,7 +466,7 @@ ip6t_do_table(struct sk_buff *skb,
 #ifdef CONFIG_NETFILTER_DEBUG
 	((struct ip6t_entry *)table_base)->comefrom = NETFILTER_LINK_POISON;
 #endif
-	rcu_read_unlock();
+	rcu_read_unlock_bh();
 
 #ifdef DEBUG_ALLOW_ALL
 	return NF_ACCEPT;
diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig
index 60c16162474c..f3d9ae350fb6 100644
--- a/net/mac80211/Kconfig
+++ b/net/mac80211/Kconfig
@@ -33,7 +33,7 @@ choice
 	---help---
 	  This option selects the default rate control algorithm
 	  mac80211 will use. Note that this default can still be
-	  overriden through the ieee80211_default_rc_algo module
+	  overridden through the ieee80211_default_rc_algo module
 	  parameter if different algorithms are available.
 
 config MAC80211_RC_DEFAULT_PID
diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig
index 2c967e4f706c..bb279bf59a1b 100644
--- a/net/netfilter/Kconfig
+++ b/net/netfilter/Kconfig
@@ -52,7 +52,7 @@ config NF_CT_ACCT
 
 	  Please note that currently this option only sets a default state.
 	  You may change it at boot time with nf_conntrack.acct=0/1 kernel
-	  paramater or by loading the nf_conntrack module with acct=0/1.
+	  parameter or by loading the nf_conntrack module with acct=0/1.
 
 	  You may also disable/enable it on a running system with:
 	   sysctl net.netfilter.nf_conntrack_acct=0/1
diff --git a/net/phonet/Kconfig b/net/phonet/Kconfig
index 51a5669573f2..6ec7d55b1769 100644
--- a/net/phonet/Kconfig
+++ b/net/phonet/Kconfig
@@ -6,7 +6,7 @@ config PHONET
 	tristate "Phonet protocols family"
 	help
 	  The Phone Network protocol (PhoNet) is a packet-oriented
-	  communication protocol developped by Nokia for use with its modems.
+	  communication protocol developed by Nokia for use with its modems.
 
 	  This is required for Maemo to use cellular data connectivity (if
 	  supported). It can also be used to control Nokia phones
diff --git a/net/rds/ib.c b/net/rds/ib.c
index 06a7b798d9a7..4933b380985e 100644
--- a/net/rds/ib.c
+++ b/net/rds/ib.c
@@ -51,6 +51,7 @@ MODULE_PARM_DESC(fmr_message_size, " Max size of a RDMA transfer");
 
 struct list_head rds_ib_devices;
 
+/* NOTE: if also grabbing ibdev lock, grab this first */
 DEFINE_SPINLOCK(ib_nodev_conns_lock);
 LIST_HEAD(ib_nodev_conns);
 
@@ -137,7 +138,7 @@ void rds_ib_remove_one(struct ib_device *device)
 		kfree(i_ipaddr);
 	}
 
-	rds_ib_remove_conns(rds_ibdev);
+	rds_ib_destroy_conns(rds_ibdev);
 
 	if (rds_ibdev->mr_pool)
 		rds_ib_destroy_mr_pool(rds_ibdev->mr_pool);
@@ -249,7 +250,7 @@ static int rds_ib_laddr_check(__be32 addr)
 void rds_ib_exit(void)
 {
 	rds_info_deregister_func(RDS_INFO_IB_CONNECTIONS, rds_ib_ic_info);
-	rds_ib_remove_nodev_conns();
+	rds_ib_destroy_nodev_conns();
 	ib_unregister_client(&rds_ib_client);
 	rds_ib_sysctl_exit();
 	rds_ib_recv_exit();
diff --git a/net/rds/ib.h b/net/rds/ib.h
index 8be563a1363a..069206cae733 100644
--- a/net/rds/ib.h
+++ b/net/rds/ib.h
@@ -108,7 +108,12 @@ struct rds_ib_connection {
 
 	/* sending acks */
 	unsigned long		i_ack_flags;
+#ifdef KERNEL_HAS_ATOMIC64
+	atomic64_t		i_ack_next;	/* next ACK to send */
+#else
+	spinlock_t		i_ack_lock;	/* protect i_ack_next */
 	u64			i_ack_next;	/* next ACK to send */
+#endif
 	struct rds_header	*i_ack;
 	struct ib_send_wr	i_ack_wr;
 	struct ib_sge		i_ack_sge;
@@ -267,9 +272,17 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn,
 
 /* ib_rdma.c */
 int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr);
-int rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
-void rds_ib_remove_nodev_conns(void);
-void rds_ib_remove_conns(struct rds_ib_device *rds_ibdev);
+void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
+void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn);
+void __rds_ib_destroy_conns(struct list_head *list, spinlock_t *list_lock);
+static inline void rds_ib_destroy_nodev_conns(void)
+{
+	__rds_ib_destroy_conns(&ib_nodev_conns, &ib_nodev_conns_lock);
+}
+static inline void rds_ib_destroy_conns(struct rds_ib_device *rds_ibdev)
+{
+	__rds_ib_destroy_conns(&rds_ibdev->conn_list, &rds_ibdev->spinlock);
+}
 struct rds_ib_mr_pool *rds_ib_create_mr_pool(struct rds_ib_device *);
 void rds_ib_get_mr_info(struct rds_ib_device *rds_ibdev, struct rds_info_rdma_connection *iinfo);
 void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *);
@@ -355,13 +368,4 @@ rds_ib_data_sge(struct rds_ib_connection *ic, struct ib_sge *sge)
 	return &sge[1];
 }
 
-static inline void rds_ib_set_64bit(u64 *ptr, u64 val)
-{
-#if BITS_PER_LONG == 64
-	*ptr = val;
-#else
-	set_64bit(ptr, val);
-#endif
-}
-
 #endif
diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c
index 0532237bd128..f8e40e1a6038 100644
--- a/net/rds/ib_cm.c
+++ b/net/rds/ib_cm.c
@@ -126,9 +126,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 	err = rds_ib_update_ipaddr(rds_ibdev, conn->c_laddr);
 	if (err)
 		printk(KERN_ERR "rds_ib_update_ipaddr failed (%d)\n", err);
-	err = rds_ib_add_conn(rds_ibdev, conn);
-	if (err)
-		printk(KERN_ERR "rds_ib_add_conn failed (%d)\n", err);
+	rds_ib_add_conn(rds_ibdev, conn);
 
 	/* If the peer gave us the last packet it saw, process this as if
 	 * we had received a regular ACK. */
@@ -616,18 +614,8 @@ void rds_ib_conn_shutdown(struct rds_connection *conn)
 		/*
 		 * Move connection back to the nodev list.
 		 */
-		if (ic->rds_ibdev) {
-
-			spin_lock_irq(&ic->rds_ibdev->spinlock);
-			BUG_ON(list_empty(&ic->ib_node));
-			list_del(&ic->ib_node);
-			spin_unlock_irq(&ic->rds_ibdev->spinlock);
-
-			spin_lock_irq(&ib_nodev_conns_lock);
-			list_add_tail(&ic->ib_node, &ib_nodev_conns);
-			spin_unlock_irq(&ib_nodev_conns_lock);
-			ic->rds_ibdev = NULL;
-		}
+		if (ic->rds_ibdev)
+			rds_ib_remove_conn(ic->rds_ibdev, conn);
 
 		ic->i_cm_id = NULL;
 		ic->i_pd = NULL;
@@ -648,7 +636,11 @@ void rds_ib_conn_shutdown(struct rds_connection *conn)
 
 	/* Clear the ACK state */
 	clear_bit(IB_ACK_IN_FLIGHT, &ic->i_ack_flags);
-	rds_ib_set_64bit(&ic->i_ack_next, 0);
+#ifdef KERNEL_HAS_ATOMIC64
+	atomic64_set(&ic->i_ack_next, 0);
+#else
+	ic->i_ack_next = 0;
+#endif
 	ic->i_ack_recv = 0;
 
 	/* Clear flow control state */
@@ -681,6 +673,9 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 
 	INIT_LIST_HEAD(&ic->ib_node);
 	mutex_init(&ic->i_recv_mutex);
+#ifndef KERNEL_HAS_ATOMIC64
+	spin_lock_init(&ic->i_ack_lock);
+#endif
 
 	/*
 	 * rds_ib_conn_shutdown() waits for these to be emptied so they
@@ -701,11 +696,27 @@ int rds_ib_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 	return 0;
 }
 
+/*
+ * Free a connection. Connection must be shut down and not set for reconnect.
+ */
 void rds_ib_conn_free(void *arg)
 {
 	struct rds_ib_connection *ic = arg;
+	spinlock_t	*lock_ptr;
+
 	rdsdebug("ic %p\n", ic);
+
+	/*
+	 * Conn is either on a dev's list or on the nodev list.
+	 * A race with shutdown() or connect() would cause problems
+	 * (since rds_ibdev would change) but that should never happen.
+	 */
+	lock_ptr = ic->rds_ibdev ? &ic->rds_ibdev->spinlock : &ib_nodev_conns_lock;
+
+	spin_lock_irq(lock_ptr);
 	list_del(&ic->ib_node);
+	spin_unlock_irq(lock_ptr);
+
 	kfree(ic);
 }
 
diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c
index 69a6289ed672..81033af93020 100644
--- a/net/rds/ib_rdma.c
+++ b/net/rds/ib_rdma.c
@@ -139,7 +139,7 @@ int rds_ib_update_ipaddr(struct rds_ib_device *rds_ibdev, __be32 ipaddr)
 	return rds_ib_add_ipaddr(rds_ibdev, ipaddr);
 }
 
-int rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn)
+void rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn)
 {
 	struct rds_ib_connection *ic = conn->c_transport_data;
 
@@ -148,45 +148,44 @@ int rds_ib_add_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn
 	BUG_ON(list_empty(&ib_nodev_conns));
 	BUG_ON(list_empty(&ic->ib_node));
 	list_del(&ic->ib_node);
-	spin_unlock_irq(&ib_nodev_conns_lock);
 
 	spin_lock_irq(&rds_ibdev->spinlock);
 	list_add_tail(&ic->ib_node, &rds_ibdev->conn_list);
 	spin_unlock_irq(&rds_ibdev->spinlock);
+	spin_unlock_irq(&ib_nodev_conns_lock);
 
 	ic->rds_ibdev = rds_ibdev;
-
-	return 0;
 }
 
-void rds_ib_remove_nodev_conns(void)
+void rds_ib_remove_conn(struct rds_ib_device *rds_ibdev, struct rds_connection *conn)
 {
-	struct rds_ib_connection *ic, *_ic;
-	LIST_HEAD(tmp_list);
+	struct rds_ib_connection *ic = conn->c_transport_data;
 
-	/* avoid calling conn_destroy with irqs off */
-	spin_lock_irq(&ib_nodev_conns_lock);
-	list_splice(&ib_nodev_conns, &tmp_list);
-	INIT_LIST_HEAD(&ib_nodev_conns);
-	spin_unlock_irq(&ib_nodev_conns_lock);
+	/* place conn on nodev_conns_list */
+	spin_lock(&ib_nodev_conns_lock);
 
-	list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node) {
-		if (ic->conn->c_passive)
-			rds_conn_destroy(ic->conn->c_passive);
-		rds_conn_destroy(ic->conn);
-	}
+	spin_lock_irq(&rds_ibdev->spinlock);
+	BUG_ON(list_empty(&ic->ib_node));
+	list_del(&ic->ib_node);
+	spin_unlock_irq(&rds_ibdev->spinlock);
+
+	list_add_tail(&ic->ib_node, &ib_nodev_conns);
+
+	spin_unlock(&ib_nodev_conns_lock);
+
+	ic->rds_ibdev = NULL;
 }
 
-void rds_ib_remove_conns(struct rds_ib_device *rds_ibdev)
+void __rds_ib_destroy_conns(struct list_head *list, spinlock_t *list_lock)
 {
 	struct rds_ib_connection *ic, *_ic;
 	LIST_HEAD(tmp_list);
 
 	/* avoid calling conn_destroy with irqs off */
-	spin_lock_irq(&rds_ibdev->spinlock);
-	list_splice(&rds_ibdev->conn_list, &tmp_list);
-	INIT_LIST_HEAD(&rds_ibdev->conn_list);
-	spin_unlock_irq(&rds_ibdev->spinlock);
+	spin_lock_irq(list_lock);
+	list_splice(list, &tmp_list);
+	INIT_LIST_HEAD(list);
+	spin_unlock_irq(list_lock);
 
 	list_for_each_entry_safe(ic, _ic, &tmp_list, ib_node) {
 		if (ic->conn->c_passive)
diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c
index 5061b5502162..36d931573ff4 100644
--- a/net/rds/ib_recv.c
+++ b/net/rds/ib_recv.c
@@ -395,10 +395,37 @@ void rds_ib_recv_init_ack(struct rds_ib_connection *ic)
  * room for it beyond the ring size.  Send completion notices its special
  * wr_id and avoids working with the ring in that case.
  */
+#ifndef KERNEL_HAS_ATOMIC64
 static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq,
 				int ack_required)
 {
-	rds_ib_set_64bit(&ic->i_ack_next, seq);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ic->i_ack_lock, flags);
+	ic->i_ack_next = seq;
+	if (ack_required)
+		set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
+	spin_unlock_irqrestore(&ic->i_ack_lock, flags);
+}
+
+static u64 rds_ib_get_ack(struct rds_ib_connection *ic)
+{
+	unsigned long flags;
+	u64 seq;
+
+	clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
+
+	spin_lock_irqsave(&ic->i_ack_lock, flags);
+	seq = ic->i_ack_next;
+	spin_unlock_irqrestore(&ic->i_ack_lock, flags);
+
+	return seq;
+}
+#else
+static void rds_ib_set_ack(struct rds_ib_connection *ic, u64 seq,
+				int ack_required)
+{
+	atomic64_set(&ic->i_ack_next, seq);
 	if (ack_required) {
 		smp_mb__before_clear_bit();
 		set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
@@ -410,8 +437,10 @@ static u64 rds_ib_get_ack(struct rds_ib_connection *ic)
 	clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
 	smp_mb__after_clear_bit();
 
-	return ic->i_ack_next;
+	return atomic64_read(&ic->i_ack_next);
 }
+#endif
+
 
 static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credits)
 {
@@ -464,6 +493,10 @@ static void rds_ib_send_ack(struct rds_ib_connection *ic, unsigned int adv_credi
  *  -	i_ack_next, which is the last sequence number we received
  *
  * Potentially, send queue and receive queue handlers can run concurrently.
+ * It would be nice to not have to use a spinlock to synchronize things,
+ * but the one problem that rules this out is that 64bit updates are
+ * not atomic on all platforms. Things would be a lot simpler if
+ * we had atomic64 or maybe cmpxchg64 everywhere.
  *
  * Reconnecting complicates this picture just slightly. When we
  * reconnect, we may be seeing duplicate packets. The peer
diff --git a/net/rds/iw.c b/net/rds/iw.c
index 1b56905c4c08..b732efb5b634 100644
--- a/net/rds/iw.c
+++ b/net/rds/iw.c
@@ -51,6 +51,7 @@ MODULE_PARM_DESC(fastreg_message_size, " Max size of a RDMA transfer (fastreg MR
 
 struct list_head rds_iw_devices;
 
+/* NOTE: if also grabbing iwdev lock, grab this first */
 DEFINE_SPINLOCK(iw_nodev_conns_lock);
 LIST_HEAD(iw_nodev_conns);
 
@@ -145,7 +146,7 @@ void rds_iw_remove_one(struct ib_device *device)
 	}
 	spin_unlock_irq(&rds_iwdev->spinlock);
 
-	rds_iw_remove_conns(rds_iwdev);
+	rds_iw_destroy_conns(rds_iwdev);
 
 	if (rds_iwdev->mr_pool)
 		rds_iw_destroy_mr_pool(rds_iwdev->mr_pool);
@@ -258,7 +259,7 @@ static int rds_iw_laddr_check(__be32 addr)
 void rds_iw_exit(void)
 {
 	rds_info_deregister_func(RDS_INFO_IWARP_CONNECTIONS, rds_iw_ic_info);
-	rds_iw_remove_nodev_conns();
+	rds_iw_destroy_nodev_conns();
 	ib_unregister_client(&rds_iw_client);
 	rds_iw_sysctl_exit();
 	rds_iw_recv_exit();
diff --git a/net/rds/iw.h b/net/rds/iw.h
index 0ddda34f2a1c..b4fb27252895 100644
--- a/net/rds/iw.h
+++ b/net/rds/iw.h
@@ -131,7 +131,12 @@ struct rds_iw_connection {
 
 	/* sending acks */
 	unsigned long		i_ack_flags;
+#ifdef KERNEL_HAS_ATOMIC64
+	atomic64_t		i_ack_next;	/* next ACK to send */
+#else
+	spinlock_t		i_ack_lock;	/* protect i_ack_next */
 	u64			i_ack_next;	/* next ACK to send */
+#endif
 	struct rds_header	*i_ack;
 	struct ib_send_wr	i_ack_wr;
 	struct ib_sge		i_ack_sge;
@@ -294,9 +299,17 @@ void rds_iw_cm_connect_complete(struct rds_connection *conn,
 
 /* ib_rdma.c */
 int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_id);
-int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn);
-void rds_iw_remove_nodev_conns(void);
-void rds_iw_remove_conns(struct rds_iw_device *rds_iwdev);
+void rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn);
+void rds_iw_remove_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn);
+void __rds_iw_destroy_conns(struct list_head *list, spinlock_t *list_lock);
+static inline void rds_iw_destroy_nodev_conns(void)
+{
+	__rds_iw_destroy_conns(&iw_nodev_conns, &iw_nodev_conns_lock);
+}
+static inline void rds_iw_destroy_conns(struct rds_iw_device *rds_iwdev)
+{
+	__rds_iw_destroy_conns(&rds_iwdev->conn_list, &rds_iwdev->spinlock);
+}
 struct rds_iw_mr_pool *rds_iw_create_mr_pool(struct rds_iw_device *);
 void rds_iw_get_mr_info(struct rds_iw_device *rds_iwdev, struct rds_info_rdma_connection *iinfo);
 void rds_iw_destroy_mr_pool(struct rds_iw_mr_pool *);
@@ -383,13 +396,4 @@ rds_iw_data_sge(struct rds_iw_connection *ic, struct ib_sge *sge)
 	return &sge[1];
 }
 
-static inline void rds_iw_set_64bit(u64 *ptr, u64 val)
-{
-#if BITS_PER_LONG == 64
-	*ptr = val;
-#else
-	set_64bit(ptr, val);
-#endif
-}
-
 #endif
diff --git a/net/rds/iw_cm.c b/net/rds/iw_cm.c
index 57ecb3d4b8a5..a416b0d492b1 100644
--- a/net/rds/iw_cm.c
+++ b/net/rds/iw_cm.c
@@ -86,9 +86,7 @@ void rds_iw_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even
 	err = rds_iw_update_cm_id(rds_iwdev, ic->i_cm_id);
 	if (err)
 		printk(KERN_ERR "rds_iw_update_ipaddr failed (%d)\n", err);
-	err = rds_iw_add_conn(rds_iwdev, conn);
-	if (err)
-		printk(KERN_ERR "rds_iw_add_conn failed (%d)\n", err);
+	rds_iw_add_conn(rds_iwdev, conn);
 
 	/* If the peer gave us the last packet it saw, process this as if
 	 * we had received a regular ACK. */
@@ -637,19 +635,8 @@ void rds_iw_conn_shutdown(struct rds_connection *conn)
 		 * 	Move connection back to the nodev list.
 		 * 	Remove cm_id from the device cm_id list.
 		 */
-		if (ic->rds_iwdev) {
-
-			spin_lock_irq(&ic->rds_iwdev->spinlock);
-			BUG_ON(list_empty(&ic->iw_node));
-			list_del(&ic->iw_node);
-			spin_unlock_irq(&ic->rds_iwdev->spinlock);
-
-			spin_lock_irq(&iw_nodev_conns_lock);
-			list_add_tail(&ic->iw_node, &iw_nodev_conns);
-			spin_unlock_irq(&iw_nodev_conns_lock);
-			rds_iw_remove_cm_id(ic->rds_iwdev, ic->i_cm_id);
-			ic->rds_iwdev = NULL;
-		}
+		if (ic->rds_iwdev)
+			rds_iw_remove_conn(ic->rds_iwdev, conn);
 
 		rdma_destroy_id(ic->i_cm_id);
 
@@ -672,7 +659,11 @@ void rds_iw_conn_shutdown(struct rds_connection *conn)
 
 	/* Clear the ACK state */
 	clear_bit(IB_ACK_IN_FLIGHT, &ic->i_ack_flags);
-	rds_iw_set_64bit(&ic->i_ack_next, 0);
+#ifdef KERNEL_HAS_ATOMIC64
+	atomic64_set(&ic->i_ack_next, 0);
+#else
+	ic->i_ack_next = 0;
+#endif
 	ic->i_ack_recv = 0;
 
 	/* Clear flow control state */
@@ -706,6 +697,9 @@ int rds_iw_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 
 	INIT_LIST_HEAD(&ic->iw_node);
 	mutex_init(&ic->i_recv_mutex);
+#ifndef KERNEL_HAS_ATOMIC64
+	spin_lock_init(&ic->i_ack_lock);
+#endif
 
 	/*
 	 * rds_iw_conn_shutdown() waits for these to be emptied so they
@@ -726,11 +720,27 @@ int rds_iw_conn_alloc(struct rds_connection *conn, gfp_t gfp)
 	return 0;
 }
 
+/*
+ * Free a connection. Connection must be shut down and not set for reconnect.
+ */
 void rds_iw_conn_free(void *arg)
 {
 	struct rds_iw_connection *ic = arg;
+	spinlock_t	*lock_ptr;
+
 	rdsdebug("ic %p\n", ic);
+
+	/*
+	 * Conn is either on a dev's list or on the nodev list.
+	 * A race with shutdown() or connect() would cause problems
+	 * (since rds_iwdev would change) but that should never happen.
+	 */
+	lock_ptr = ic->rds_iwdev ? &ic->rds_iwdev->spinlock : &iw_nodev_conns_lock;
+
+	spin_lock_irq(lock_ptr);
 	list_del(&ic->iw_node);
+	spin_unlock_irq(lock_ptr);
+
 	kfree(ic);
 }
 
diff --git a/net/rds/iw_rdma.c b/net/rds/iw_rdma.c
index 1c02a8f952d0..dcdb37da80f2 100644
--- a/net/rds/iw_rdma.c
+++ b/net/rds/iw_rdma.c
@@ -196,7 +196,7 @@ int rds_iw_update_cm_id(struct rds_iw_device *rds_iwdev, struct rdma_cm_id *cm_i
 	return rds_iw_add_cm_id(rds_iwdev, cm_id);
 }
 
-int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn)
+void rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn)
 {
 	struct rds_iw_connection *ic = conn->c_transport_data;
 
@@ -205,45 +205,45 @@ int rds_iw_add_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn
 	BUG_ON(list_empty(&iw_nodev_conns));
 	BUG_ON(list_empty(&ic->iw_node));
 	list_del(&ic->iw_node);
-	spin_unlock_irq(&iw_nodev_conns_lock);
 
 	spin_lock_irq(&rds_iwdev->spinlock);
 	list_add_tail(&ic->iw_node, &rds_iwdev->conn_list);
 	spin_unlock_irq(&rds_iwdev->spinlock);
+	spin_unlock_irq(&iw_nodev_conns_lock);
 
 	ic->rds_iwdev = rds_iwdev;
-
-	return 0;
 }
 
-void rds_iw_remove_nodev_conns(void)
+void rds_iw_remove_conn(struct rds_iw_device *rds_iwdev, struct rds_connection *conn)
 {
-	struct rds_iw_connection *ic, *_ic;
-	LIST_HEAD(tmp_list);
+	struct rds_iw_connection *ic = conn->c_transport_data;
 
-	/* avoid calling conn_destroy with irqs off */
-	spin_lock_irq(&iw_nodev_conns_lock);
-	list_splice(&iw_nodev_conns, &tmp_list);
-	INIT_LIST_HEAD(&iw_nodev_conns);
-	spin_unlock_irq(&iw_nodev_conns_lock);
+	/* place conn on nodev_conns_list */
+	spin_lock(&iw_nodev_conns_lock);
 
-	list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node) {
-		if (ic->conn->c_passive)
-			rds_conn_destroy(ic->conn->c_passive);
-		rds_conn_destroy(ic->conn);
-	}
+	spin_lock_irq(&rds_iwdev->spinlock);
+	BUG_ON(list_empty(&ic->iw_node));
+	list_del(&ic->iw_node);
+	spin_unlock_irq(&rds_iwdev->spinlock);
+
+	list_add_tail(&ic->iw_node, &iw_nodev_conns);
+
+	spin_unlock(&iw_nodev_conns_lock);
+
+	rds_iw_remove_cm_id(ic->rds_iwdev, ic->i_cm_id);
+	ic->rds_iwdev = NULL;
 }
 
-void rds_iw_remove_conns(struct rds_iw_device *rds_iwdev)
+void __rds_iw_destroy_conns(struct list_head *list, spinlock_t *list_lock)
 {
 	struct rds_iw_connection *ic, *_ic;
 	LIST_HEAD(tmp_list);
 
 	/* avoid calling conn_destroy with irqs off */
-	spin_lock_irq(&rds_iwdev->spinlock);
-	list_splice(&rds_iwdev->conn_list, &tmp_list);
-	INIT_LIST_HEAD(&rds_iwdev->conn_list);
-	spin_unlock_irq(&rds_iwdev->spinlock);
+	spin_lock_irq(list_lock);
+	list_splice(list, &tmp_list);
+	INIT_LIST_HEAD(list);
+	spin_unlock_irq(list_lock);
 
 	list_for_each_entry_safe(ic, _ic, &tmp_list, iw_node) {
 		if (ic->conn->c_passive)
diff --git a/net/rds/iw_recv.c b/net/rds/iw_recv.c
index a1931f0027a2..fde470fa50d5 100644
--- a/net/rds/iw_recv.c
+++ b/net/rds/iw_recv.c
@@ -395,10 +395,37 @@ void rds_iw_recv_init_ack(struct rds_iw_connection *ic)
  * room for it beyond the ring size.  Send completion notices its special
  * wr_id and avoids working with the ring in that case.
  */
+#ifndef KERNEL_HAS_ATOMIC64
 static void rds_iw_set_ack(struct rds_iw_connection *ic, u64 seq,
 				int ack_required)
 {
-	rds_iw_set_64bit(&ic->i_ack_next, seq);
+	unsigned long flags;
+
+	spin_lock_irqsave(&ic->i_ack_lock, flags);
+	ic->i_ack_next = seq;
+	if (ack_required)
+		set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
+	spin_unlock_irqrestore(&ic->i_ack_lock, flags);
+}
+
+static u64 rds_iw_get_ack(struct rds_iw_connection *ic)
+{
+	unsigned long flags;
+	u64 seq;
+
+	clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
+
+	spin_lock_irqsave(&ic->i_ack_lock, flags);
+	seq = ic->i_ack_next;
+	spin_unlock_irqrestore(&ic->i_ack_lock, flags);
+
+	return seq;
+}
+#else
+static void rds_iw_set_ack(struct rds_iw_connection *ic, u64 seq,
+				int ack_required)
+{
+	atomic64_set(&ic->i_ack_next, seq);
 	if (ack_required) {
 		smp_mb__before_clear_bit();
 		set_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
@@ -410,8 +437,10 @@ static u64 rds_iw_get_ack(struct rds_iw_connection *ic)
 	clear_bit(IB_ACK_REQUESTED, &ic->i_ack_flags);
 	smp_mb__after_clear_bit();
 
-	return ic->i_ack_next;
+	return atomic64_read(&ic->i_ack_next);
 }
+#endif
+
 
 static void rds_iw_send_ack(struct rds_iw_connection *ic, unsigned int adv_credits)
 {
@@ -464,6 +493,10 @@ static void rds_iw_send_ack(struct rds_iw_connection *ic, unsigned int adv_credi
  *  -	i_ack_next, which is the last sequence number we received
  *
  * Potentially, send queue and receive queue handlers can run concurrently.
+ * It would be nice to not have to use a spinlock to synchronize things,
+ * but the one problem that rules this out is that 64bit updates are
+ * not atomic on all platforms. Things would be a lot simpler if
+ * we had atomic64 or maybe cmpxchg64 everywhere.
  *
  * Reconnecting complicates this picture just slightly. When we
  * reconnect, we may be seeing duplicate packets. The peer
diff --git a/net/rds/rds.h b/net/rds/rds.h
index 060400704979..619f0a30a4e5 100644
--- a/net/rds/rds.h
+++ b/net/rds/rds.h
@@ -28,6 +28,10 @@
  */
 #define RDS_PORT	18634
 
+#ifdef ATOMIC64_INIT
+#define KERNEL_HAS_ATOMIC64
+#endif
+
 #ifdef DEBUG
 #define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args)
 #else
diff --git a/net/rds/send.c b/net/rds/send.c
index 1b37364656f0..104fe033203d 100644
--- a/net/rds/send.c
+++ b/net/rds/send.c
@@ -615,7 +615,7 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 {
 	struct rds_message *rm, *tmp;
 	struct rds_connection *conn;
-	unsigned long flags;
+	unsigned long flags, flags2;
 	LIST_HEAD(list);
 	int wake = 0;
 
@@ -651,9 +651,9 @@ void rds_send_drop_to(struct rds_sock *rs, struct sockaddr_in *dest)
 	list_for_each_entry(rm, &list, m_sock_item) {
 		/* We do this here rather than in the loop above, so that
 		 * we don't have to nest m_rs_lock under rs->rs_lock */
-		spin_lock(&rm->m_rs_lock);
+		spin_lock_irqsave(&rm->m_rs_lock, flags2);
 		rm->m_rs = NULL;
-		spin_unlock(&rm->m_rs_lock);
+		spin_unlock_irqrestore(&rm->m_rs_lock, flags2);
 
 		/*
 		 * If we see this flag cleared then we're *sure* that someone
diff --git a/net/sunrpc/Kconfig b/net/sunrpc/Kconfig
index afd91c78ce8e..443c161eb8bd 100644
--- a/net/sunrpc/Kconfig
+++ b/net/sunrpc/Kconfig
@@ -47,7 +47,7 @@ config RPCSEC_GSS_SPKM3
 	select CRYPTO_CBC
 	help
 	  Choose Y here to enable Secure RPC using the SPKM3 public key
-	  GSS-API mechansim (RFC 2025).
+	  GSS-API mechanism (RFC 2025).
 
 	  Secure RPC calls with SPKM3 require an auxiliary userspace
 	  daemon which may be found in the Linux nfs-utils package
diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c
index 9f2f2412a2f3..9b49a6ab8ded 100644
--- a/net/sunrpc/svc.c
+++ b/net/sunrpc/svc.c
@@ -317,8 +317,7 @@ svc_pool_map_set_cpumask(struct task_struct *task, unsigned int pidx)
 	}
 	case SVC_POOL_PERNODE:
 	{
-		node_to_cpumask_ptr(nodecpumask, node);
-		set_cpus_allowed_ptr(task, nodecpumask);
+		set_cpus_allowed_ptr(task, cpumask_of_node(node));
 		break;
 	}
 	}
diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c
index baac91049b0e..9dcc6e7f96ec 100644
--- a/net/unix/af_unix.c
+++ b/net/unix/af_unix.c
@@ -832,7 +832,7 @@ static int unix_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len)
 		 * All right, let's create it.
 		 */
 		mode = S_IFSOCK |
-		       (SOCK_INODE(sock)->i_mode & ~current->fs->umask);
+		       (SOCK_INODE(sock)->i_mode & ~current_umask());
 		err = mnt_want_write(nd.path.mnt);
 		if (err)
 			goto out_mknod_dput;
diff --git a/net/wimax/Kconfig b/net/wimax/Kconfig
index 18495cdcd10d..1b46747a5f5a 100644
--- a/net/wimax/Kconfig
+++ b/net/wimax/Kconfig
@@ -8,7 +8,7 @@
 #
 # As well, enablement of the RFKILL code means we need the INPUT layer
 # support to inject events coming from hw rfkill switches. That
-# dependency could be killed if input.h provided appropiate means to
+# dependency could be killed if input.h provided appropriate means to
 # work when input is disabled.
 
 comment "WiMAX Wireless Broadband support requires CONFIG_INPUT enabled"
diff --git a/scripts/mod/modpost.c b/scripts/mod/modpost.c
index 7e62303133dc..8cc70612984c 100644
--- a/scripts/mod/modpost.c
+++ b/scripts/mod/modpost.c
@@ -1607,12 +1607,12 @@ static void read_symbols(char *modname)
 
 	parse_elf_finish(&info);
 
-	/* Our trick to get versioning for struct_module - it's
+	/* Our trick to get versioning for module struct etc. - it's
 	 * never passed as an argument to an exported function, so
 	 * the automatic versioning doesn't pick it up, but it's really
 	 * important anyhow */
 	if (modversions)
-		mod->unres = alloc_symbol("struct_module", 0, mod->unres);
+		mod->unres = alloc_symbol("module_layout", 0, mod->unres);
 }
 
 #define SZ 500
diff --git a/scripts/package/buildtar b/scripts/package/buildtar
index 28574ae55170..b1fd48db1640 100644
--- a/scripts/package/buildtar
+++ b/scripts/package/buildtar
@@ -75,6 +75,10 @@ case "${ARCH}" in
 	alpha)
 		[ -f "${objtree}/arch/alpha/boot/vmlinux.gz" ] && cp -v -- "${objtree}/arch/alpha/boot/vmlinux.gz" "${tmpdir}/boot/vmlinuz-${KERNELRELEASE}"
 		;;
+	parisc*)
+		[ -f "${KBUILD_IMAGE}" ] && cp -v -- "${KBUILD_IMAGE}" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}"
+		[ -f "${objtree}/lifimage" ] && cp -v -- "${objtree}/lifimage" "${tmpdir}/boot/lifimage-${KERNELRELEASE}"
+		;;
 	vax)
 		[ -f "${objtree}/vmlinux.SYS" ] && cp -v -- "${objtree}/vmlinux.SYS" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}.SYS"
 		[ -f "${objtree}/vmlinux.dsk" ] && cp -v -- "${objtree}/vmlinux.dsk" "${tmpdir}/boot/vmlinux-${KERNELRELEASE}.dsk"
diff --git a/security/device_cgroup.c b/security/device_cgroup.c
index 3aacd0fe7179..5fda7df19723 100644
--- a/security/device_cgroup.c
+++ b/security/device_cgroup.c
@@ -11,6 +11,7 @@
 #include <linux/uaccess.h>
 #include <linux/seq_file.h>
 #include <linux/rcupdate.h>
+#include <linux/mutex.h>
 
 #define ACC_MKNOD 1
 #define ACC_READ  2
@@ -21,9 +22,11 @@
 #define DEV_CHAR  2
 #define DEV_ALL   4  /* this represents all devices */
 
+static DEFINE_MUTEX(devcgroup_mutex);
+
 /*
  * whitelist locking rules:
- * hold cgroup_lock() for update/read.
+ * hold devcgroup_mutex for update/read.
  * hold rcu_read_lock() for read.
  */
 
@@ -67,7 +70,7 @@ static int devcgroup_can_attach(struct cgroup_subsys *ss,
 }
 
 /*
- * called under cgroup_lock()
+ * called under devcgroup_mutex
  */
 static int dev_whitelist_copy(struct list_head *dest, struct list_head *orig)
 {
@@ -92,7 +95,7 @@ free_and_exit:
 
 /* Stupid prototype - don't bother combining existing entries */
 /*
- * called under cgroup_lock()
+ * called under devcgroup_mutex
  */
 static int dev_whitelist_add(struct dev_cgroup *dev_cgroup,
 			struct dev_whitelist_item *wh)
@@ -130,7 +133,7 @@ static void whitelist_item_free(struct rcu_head *rcu)
 }
 
 /*
- * called under cgroup_lock()
+ * called under devcgroup_mutex
  */
 static void dev_whitelist_rm(struct dev_cgroup *dev_cgroup,
 			struct dev_whitelist_item *wh)
@@ -185,8 +188,10 @@ static struct cgroup_subsys_state *devcgroup_create(struct cgroup_subsys *ss,
 		list_add(&wh->list, &dev_cgroup->whitelist);
 	} else {
 		parent_dev_cgroup = cgroup_to_devcgroup(parent_cgroup);
+		mutex_lock(&devcgroup_mutex);
 		ret = dev_whitelist_copy(&dev_cgroup->whitelist,
 				&parent_dev_cgroup->whitelist);
+		mutex_unlock(&devcgroup_mutex);
 		if (ret) {
 			kfree(dev_cgroup);
 			return ERR_PTR(ret);
@@ -273,7 +278,7 @@ static int devcgroup_seq_read(struct cgroup *cgroup, struct cftype *cft,
  * does the access granted to dev_cgroup c contain the access
  * requested in whitelist item refwh.
  * return 1 if yes, 0 if no.
- * call with c->lock held
+ * call with devcgroup_mutex held
  */
 static int may_access_whitelist(struct dev_cgroup *c,
 				       struct dev_whitelist_item *refwh)
@@ -426,11 +431,11 @@ static int devcgroup_access_write(struct cgroup *cgrp, struct cftype *cft,
 				  const char *buffer)
 {
 	int retval;
-	if (!cgroup_lock_live_group(cgrp))
-		return -ENODEV;
+
+	mutex_lock(&devcgroup_mutex);
 	retval = devcgroup_update_access(cgroup_to_devcgroup(cgrp),
 					 cft->private, buffer);
-	cgroup_unlock();
+	mutex_unlock(&devcgroup_mutex);
 	return retval;
 }
 
diff --git a/security/security.c b/security/security.c
index 206e53844d2f..5284255c5cdf 100644
--- a/security/security.c
+++ b/security/security.c
@@ -445,6 +445,7 @@ int security_inode_create(struct inode *dir, struct dentry *dentry, int mode)
 		return 0;
 	return security_ops->inode_create(dir, dentry, mode);
 }
+EXPORT_SYMBOL_GPL(security_inode_create);
 
 int security_inode_link(struct dentry *old_dentry, struct inode *dir,
 			 struct dentry *new_dentry)
@@ -475,6 +476,7 @@ int security_inode_mkdir(struct inode *dir, struct dentry *dentry, int mode)
 		return 0;
 	return security_ops->inode_mkdir(dir, dentry, mode);
 }
+EXPORT_SYMBOL_GPL(security_inode_mkdir);
 
 int security_inode_rmdir(struct inode *dir, struct dentry *dentry)
 {
diff --git a/security/tomoyo/realpath.c b/security/tomoyo/realpath.c
index d47f16b844b2..3bbe01a7a4b5 100644
--- a/security/tomoyo/realpath.c
+++ b/security/tomoyo/realpath.c
@@ -12,6 +12,7 @@
 #include <linux/types.h>
 #include <linux/mount.h>
 #include <linux/mnt_namespace.h>
+#include <linux/fs_struct.h>
 #include "common.h"
 #include "realpath.h"
 
diff --git a/sound/oss/pss.c b/sound/oss/pss.c
index 16517a5a1301..83f5ee236b12 100644
--- a/sound/oss/pss.c
+++ b/sound/oss/pss.c
@@ -46,7 +46,7 @@
  *          load the driver as it did in previous versions.
  * 04-07-1999: Anthony Barbachan <barbcode@xmen.cis.fordham.edu>
  *          Added module parameter pss_firmware to allow the user to tell 
- *          the driver where the fireware file is located.  The default 
+ *          the driver where the firmware file is located.  The default 
  *          setting is the previous hardcoded setting "/etc/sound/pss_synth".
  * 00-03-03: Christoph Hellwig <chhellwig@infradead.org>
  *	    Adapted to module_init/module_exit
diff --git a/sound/sh/aica.c b/sound/sh/aica.c
index f551233c5a08..583a3693df75 100644
--- a/sound/sh/aica.c
+++ b/sound/sh/aica.c
@@ -565,7 +565,7 @@ static int load_aica_firmware(void)
 	err = request_firmware(&fw_entry, "aica_firmware.bin", &pd->dev);
 	if (unlikely(err))
 		return err;
-	/* write firware into memory */
+	/* write firmware into memory */
 	spu_disable();
 	spu_memload(0, fw_entry->data, fw_entry->size);
 	spu_enable();
diff --git a/sound/soc/blackfin/Kconfig b/sound/soc/blackfin/Kconfig
index 0a2f8f9eff53..811596f4c092 100644
--- a/sound/soc/blackfin/Kconfig
+++ b/sound/soc/blackfin/Kconfig
@@ -42,7 +42,7 @@ config SND_BF5XX_AC97
 	  You will also need to select the audio interfaces to support below.
 
 	  Note:
-	  AC97 codecs which do not implment the slot-16 mode will not function
+	  AC97 codecs which do not implement the slot-16 mode will not function
 	  properly with this driver. This driver is known to work with the
 	  Analog Devices line of AC97 codecs.
 
diff --git a/usr/Kconfig b/usr/Kconfig
index 588c588791e2..1c3039f28909 100644
--- a/usr/Kconfig
+++ b/usr/Kconfig
@@ -72,10 +72,8 @@ config RD_LZMA
 	  Support loading of a LZMA encoded initial ramdisk or cpio buffer
 	  If unsure, say N.
 
-if INITRAMFS_SOURCE!=""
-
 choice
-	prompt "Built-in initramfs compression mode"
+	prompt "Built-in initramfs compression mode" if INITRAMFS_SOURCE!=""
 	help
 	  This option decides by which algorithm the builtin initramfs
 	  will be compressed.  Several compression algorithms are
@@ -134,14 +132,3 @@ config INITRAMFS_COMPRESSION_LZMA
 	  smaller with LZMA in comparison to gzip.
 
 endchoice
-
-endif
-
-if INITRAMFS_SOURCE=""
-# The builtin initramfs is so small so we don't want to bug the user...
-
-config INITRAMFS_COMPRESSION_NONE
-	bool
-	default y
-
-endif
diff --git a/usr/Makefile b/usr/Makefile
index b84894b3929d..245145a99c10 100644
--- a/usr/Makefile
+++ b/usr/Makefile
@@ -6,9 +6,6 @@ klibcdirs:;
 PHONY += klibcdirs
 
 
-# No compression
-suffix_$(CONFIG_INITRAMFS_COMPRESSION_NONE)   =
-
 # Gzip, but no bzip2
 suffix_$(CONFIG_INITRAMFS_COMPRESSION_GZIP)   = .gz