Merge tag 'v4.1.43' into 4.1-2.0.x-imx

Linux 4.1.43

* tag 'v4.1.43': (182 commits)
  Linux 4.1.43
  HID: core: prevent out-of-bound readings
  ipvs: SNAT packet replies only for NATed connections
  Revert "dmaengine: ep93xx: Don't drain the transfers in terminate_all()"
  staging: comedi: ni_mio_common: fix E series ni_ai_insn_read() data
  kvm: vmx: Do not disable intercepts for BNDCFGS
  tracing: Use SOFTIRQ_OFFSET for softirq dectection for more accurate results
  PM / QoS: return -EINVAL for bogus strings
  sched/topology: Optimize build_group_mask()
  sched/topology: Fix overlapping sched_group_mask
  crypto: caam - fix signals handling
  crypto: atmel - only treat EBUSY as transient if backlog
  crypto: talitos - Extend max key length for SHA384/512-HMAC and AEAD
  Add "shutdown" to "struct class".
  mnt: Make propagate_umount less slow for overlapping mount propagation trees
  mnt: In propgate_umount handle visiting mounts in any order
  mnt: In umount propagation reparent in a separate pass
  vt: fix unchecked __put_user() in tioclinux ioctls
  exec: Limit arg stack to at most 75% of _STK_LIM
  s390: reduce ELF_ET_DYN_BASE
  ...

26 files changed, 184 insertions, 96 deletions

diff --git a/arch/arm/boot/dts/bcm5301x.dtsi b/arch/arm/boot/dts/bcm5301x.dtsi
index 78aec6270c2f..90fbda066122 100644
--- a/arch/arm/boot/dts/bcm5301x.dtsi
+++ b/arch/arm/boot/dts/bcm5301x.dtsi
@@ -54,14 +54,14 @@
 		timer@0200 {
 			compatible = "arm,cortex-a9-global-timer";
 			reg = <0x0200 0x100>;
-			interrupts = <GIC_PPI 11 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 11 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&clk_periph>;
 		};
 
 		local-timer@0600 {
 			compatible = "arm,cortex-a9-twd-timer";
 			reg = <0x0600 0x100>;
-			interrupts = <GIC_PPI 13 IRQ_TYPE_LEVEL_HIGH>;
+			interrupts = <GIC_PPI 13 IRQ_TYPE_EDGE_RISING>;
 			clocks = <&clk_periph>;
 		};
 
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index d2315ffd8f12..f13ae153fb24 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -112,12 +112,8 @@ int dump_task_regs(struct task_struct *t, elf_gregset_t *elfregs);
 #define CORE_DUMP_USE_REGSET
 #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	(TASK_SIZE / 3 * 2)
+/* This is the base location for PIE (ET_DYN with INTERP) loads. */
+#define ELF_ET_DYN_BASE		0x400000UL
 
 /* When the program starts, a1 contains a pointer to a function to be 
    registered with atexit, as per the SVR4 ABI.  A value of 0 means we 
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 7186382672b5..d89d35b40e47 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -1136,15 +1136,15 @@ void __init sanity_check_meminfo(void)
 
 	high_memory = __va(arm_lowmem_limit - 1) + 1;
 
+	if (!memblock_limit)
+		memblock_limit = arm_lowmem_limit;
+
 	/*
 	 * Round the memblock limit down to a pmd size.  This
 	 * helps to ensure that we will allocate memory from the
 	 * last full pmd, which should be mapped.
 	 */
-	if (memblock_limit)
-		memblock_limit = round_down(memblock_limit, PMD_SIZE);
-	if (!memblock_limit)
-		memblock_limit = arm_lowmem_limit;
+	memblock_limit = round_down(memblock_limit, PMD_SIZE);
 
 	memblock_set_current_limit(memblock_limit);
 }
diff --git a/arch/arm64/include/asm/barrier.h b/arch/arm64/include/asm/barrier.h
index 71f19c4dc0de..ffe7850afdbd 100644
--- a/arch/arm64/include/asm/barrier.h
+++ b/arch/arm64/include/asm/barrier.h
@@ -63,23 +63,33 @@ do {									\
 
 #define smp_store_release(p, v)						\
 do {									\
+	union { typeof(*p) __val; char __c[1]; } __u =			\
+		{ .__val = (__force typeof(*p)) (v) }; 			\
 	compiletime_assert_atomic_type(*p);				\
 	switch (sizeof(*p)) {						\
 	case 1:								\
 		asm volatile ("stlrb %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u8 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 2:								\
 		asm volatile ("stlrh %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u16 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 4:								\
 		asm volatile ("stlr %w1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u32 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	case 8:								\
 		asm volatile ("stlr %1, %0"				\
-				: "=Q" (*p) : "r" (v) : "memory");	\
+				: "=Q" (*p)				\
+				: "r" (*(__u64 *)__u.__c)		\
+				: "memory");				\
 		break;							\
 	}								\
 } while (0)
diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c
index 7ac3920b1356..802dd71ed0b3 100644
--- a/arch/arm64/kernel/armv8_deprecated.c
+++ b/arch/arm64/kernel/armv8_deprecated.c
@@ -298,7 +298,8 @@ static void register_insn_emulation_sysctl(struct ctl_table *table)
 	"	.quad		1b, 4b\n"			\
 	"	.popsection\n"					\
 	: "=&r" (res), "+r" (data), "=&r" (temp)		\
-	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "r" ((unsigned long)addr), "i" (-EAGAIN),		\
+	  "i" (-EFAULT)						\
 	: "memory")
 
 #define __user_swp_asm(data, addr, res, temp) \
diff --git a/arch/mips/kernel/entry.S b/arch/mips/kernel/entry.S
index 7791840cf22c..db07793f7b43 100644
--- a/arch/mips/kernel/entry.S
+++ b/arch/mips/kernel/entry.S
@@ -11,6 +11,7 @@
 #include <asm/asm.h>
 #include <asm/asmmacro.h>
 #include <asm/compiler.h>
+#include <asm/irqflags.h>
 #include <asm/regdef.h>
 #include <asm/mipsregs.h>
 #include <asm/stackframe.h>
@@ -137,6 +138,7 @@ work_pending:
 	andi	t0, a2, _TIF_NEED_RESCHED # a2 is preloaded with TI_FLAGS
 	beqz	t0, work_notifysig
 work_resched:
+	TRACE_IRQS_OFF
 	jal	schedule
 
 	local_irq_disable		# make sure need_resched and
@@ -173,6 +175,7 @@ syscall_exit_work:
 	beqz	t0, work_pending	# trace bit set?
 	local_irq_enable		# could let syscall_trace_leave()
 					# call schedule() instead
+	TRACE_IRQS_ON
 	move	a0, sp
 	jal	syscall_trace_leave
 	b	resume_userspace
diff --git a/arch/mips/kernel/pm-cps.c b/arch/mips/kernel/pm-cps.c
index 06147179a175..cd25b616075d 100644
--- a/arch/mips/kernel/pm-cps.c
+++ b/arch/mips/kernel/pm-cps.c
@@ -55,7 +55,6 @@ DECLARE_BITMAP(state_support, CPS_PM_STATE_COUNT);
  * state. Actually per-core rather than per-CPU.
  */
 static DEFINE_PER_CPU_ALIGNED(u32*, ready_count);
-static DEFINE_PER_CPU_ALIGNED(void*, ready_count_alloc);
 
 /* Indicates online CPUs coupled with the current CPU */
 static DEFINE_PER_CPU_ALIGNED(cpumask_t, online_coupled);
@@ -624,7 +623,6 @@ static int __init cps_gen_core_entries(unsigned cpu)
 {
 	enum cps_pm_state state;
 	unsigned core = cpu_data[cpu].core;
-	unsigned dlinesz = cpu_data[cpu].dcache.linesz;
 	void *entry_fn, *core_rc;
 
 	for (state = CPS_PM_NC_WAIT; state < CPS_PM_STATE_COUNT; state++) {
@@ -644,16 +642,11 @@ static int __init cps_gen_core_entries(unsigned cpu)
 	}
 
 	if (!per_cpu(ready_count, core)) {
-		core_rc = kmalloc(dlinesz * 2, GFP_KERNEL);
+		core_rc = kmalloc(sizeof(u32), GFP_KERNEL);
 		if (!core_rc) {
 			pr_err("Failed allocate core %u ready_count\n", core);
 			return -ENOMEM;
 		}
-		per_cpu(ready_count_alloc, core) = core_rc;
-
-		/* Ensure ready_count is aligned to a cacheline boundary */
-		core_rc += dlinesz - 1;
-		core_rc = (void *)((unsigned long)core_rc & ~(dlinesz - 1));
 		per_cpu(ready_count, core) = core_rc;
 	}
 
diff --git a/arch/mips/kernel/traps.c b/arch/mips/kernel/traps.c
index 74403953e407..2e29b1aed924 100644
--- a/arch/mips/kernel/traps.c
+++ b/arch/mips/kernel/traps.c
@@ -193,6 +193,8 @@ void show_stack(struct task_struct *task, unsigned long *sp)
 {
 	struct pt_regs regs;
 	mm_segment_t old_fs = get_fs();
+
+	regs.cp0_status = KSU_KERNEL;
 	if (sp) {
 		regs.regs[29] = (unsigned long)sp;
 		regs.regs[31] = 0;
diff --git a/arch/mips/ralink/mt7620.c b/arch/mips/ralink/mt7620.c
index 2ea5ff6dc22e..c57215a66181 100644
--- a/arch/mips/ralink/mt7620.c
+++ b/arch/mips/ralink/mt7620.c
@@ -98,31 +98,31 @@ static struct rt2880_pmx_group mt7620a_pinmux_data[] = {
 };
 
 static struct rt2880_pmx_func pwm1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 19, 1),
+	FUNC("sdxc d6", 3, 19, 1),
 	FUNC("utif", 2, 19, 1),
 	FUNC("gpio", 1, 19, 1),
-	FUNC("pwm", 0, 19, 1),
+	FUNC("pwm1", 0, 19, 1),
 };
 
 static struct rt2880_pmx_func pwm0_grp_mt7628[] = {
-	FUNC("sdcx", 3, 18, 1),
+	FUNC("sdxc d7", 3, 18, 1),
 	FUNC("utif", 2, 18, 1),
 	FUNC("gpio", 1, 18, 1),
-	FUNC("pwm", 0, 18, 1),
+	FUNC("pwm0", 0, 18, 1),
 };
 
 static struct rt2880_pmx_func uart2_grp_mt7628[] = {
-	FUNC("sdcx", 3, 20, 2),
+	FUNC("sdxc d5 d4", 3, 20, 2),
 	FUNC("pwm", 2, 20, 2),
 	FUNC("gpio", 1, 20, 2),
-	FUNC("uart", 0, 20, 2),
+	FUNC("uart2", 0, 20, 2),
 };
 
 static struct rt2880_pmx_func uart1_grp_mt7628[] = {
-	FUNC("sdcx", 3, 45, 2),
+	FUNC("sw_r", 3, 45, 2),
 	FUNC("pwm", 2, 45, 2),
 	FUNC("gpio", 1, 45, 2),
-	FUNC("uart", 0, 45, 2),
+	FUNC("uart1", 0, 45, 2),
 };
 
 static struct rt2880_pmx_func i2c_grp_mt7628[] = {
@@ -134,21 +134,21 @@ static struct rt2880_pmx_func i2c_grp_mt7628[] = {
 
 static struct rt2880_pmx_func refclk_grp_mt7628[] = { FUNC("reclk", 0, 36, 1) };
 static struct rt2880_pmx_func perst_grp_mt7628[] = { FUNC("perst", 0, 37, 1) };
-static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 15, 38) };
+static struct rt2880_pmx_func wdt_grp_mt7628[] = { FUNC("wdt", 0, 38, 1) };
 static struct rt2880_pmx_func spi_grp_mt7628[] = { FUNC("spi", 0, 7, 4) };
 
 static struct rt2880_pmx_func sd_mode_grp_mt7628[] = {
 	FUNC("jtag", 3, 22, 8),
 	FUNC("utif", 2, 22, 8),
 	FUNC("gpio", 1, 22, 8),
-	FUNC("sdcx", 0, 22, 8),
+	FUNC("sdxc", 0, 22, 8),
 };
 
 static struct rt2880_pmx_func uart0_grp_mt7628[] = {
 	FUNC("-", 3, 12, 2),
 	FUNC("-", 2, 12, 2),
 	FUNC("gpio", 1, 12, 2),
-	FUNC("uart", 0, 12, 2),
+	FUNC("uart0", 0, 12, 2),
 };
 
 static struct rt2880_pmx_func i2s_grp_mt7628[] = {
@@ -162,7 +162,7 @@ static struct rt2880_pmx_func spi_cs1_grp_mt7628[] = {
 	FUNC("-", 3, 6, 1),
 	FUNC("refclk", 2, 6, 1),
 	FUNC("gpio", 1, 6, 1),
-	FUNC("spi", 0, 6, 1),
+	FUNC("spi cs1", 0, 6, 1),
 };
 
 static struct rt2880_pmx_func spis_grp_mt7628[] = {
@@ -179,28 +179,44 @@ static struct rt2880_pmx_func gpio_grp_mt7628[] = {
 	FUNC("gpio", 0, 11, 1),
 };
 
-#define MT7628_GPIO_MODE_MASK	0x3
-
-#define MT7628_GPIO_MODE_PWM1	30
-#define MT7628_GPIO_MODE_PWM0	28
-#define MT7628_GPIO_MODE_UART2	26
-#define MT7628_GPIO_MODE_UART1	24
-#define MT7628_GPIO_MODE_I2C	20
-#define MT7628_GPIO_MODE_REFCLK	18
-#define MT7628_GPIO_MODE_PERST	16
-#define MT7628_GPIO_MODE_WDT	14
-#define MT7628_GPIO_MODE_SPI	12
-#define MT7628_GPIO_MODE_SDMODE	10
-#define MT7628_GPIO_MODE_UART0	8
-#define MT7628_GPIO_MODE_I2S	6
-#define MT7628_GPIO_MODE_CS1	4
-#define MT7628_GPIO_MODE_SPIS	2
-#define MT7628_GPIO_MODE_GPIO	0
+static struct rt2880_pmx_func wled_kn_grp_mt7628[] = {
+	FUNC("rsvd", 3, 35, 1),
+	FUNC("rsvd", 2, 35, 1),
+	FUNC("gpio", 1, 35, 1),
+	FUNC("wled_kn", 0, 35, 1),
+};
+
+static struct rt2880_pmx_func wled_an_grp_mt7628[] = {
+	FUNC("rsvd", 3, 44, 1),
+	FUNC("rsvd", 2, 44, 1),
+	FUNC("gpio", 1, 44, 1),
+	FUNC("wled_an", 0, 44, 1),
+};
+
+#define MT7628_GPIO_MODE_MASK		0x3
+
+#define MT7628_GPIO_MODE_WLED_KN	48
+#define MT7628_GPIO_MODE_WLED_AN	32
+#define MT7628_GPIO_MODE_PWM1		30
+#define MT7628_GPIO_MODE_PWM0		28
+#define MT7628_GPIO_MODE_UART2		26
+#define MT7628_GPIO_MODE_UART1		24
+#define MT7628_GPIO_MODE_I2C		20
+#define MT7628_GPIO_MODE_REFCLK		18
+#define MT7628_GPIO_MODE_PERST		16
+#define MT7628_GPIO_MODE_WDT		14
+#define MT7628_GPIO_MODE_SPI		12
+#define MT7628_GPIO_MODE_SDMODE		10
+#define MT7628_GPIO_MODE_UART0		8
+#define MT7628_GPIO_MODE_I2S		6
+#define MT7628_GPIO_MODE_CS1		4
+#define MT7628_GPIO_MODE_SPIS		2
+#define MT7628_GPIO_MODE_GPIO		0
 
 static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
-	GRP_G("pmw1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm1", pwm1_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM1),
-	GRP_G("pmw1", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
+	GRP_G("pwm0", pwm0_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_PWM0),
 	GRP_G("uart2", uart2_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_UART2),
@@ -224,6 +240,10 @@ static struct rt2880_pmx_group mt7628an_pinmux_data[] = {
 				1, MT7628_GPIO_MODE_SPIS),
 	GRP_G("gpio", gpio_grp_mt7628, MT7628_GPIO_MODE_MASK,
 				1, MT7628_GPIO_MODE_GPIO),
+	GRP_G("wled_an", wled_an_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_AN),
+	GRP_G("wled_kn", wled_kn_grp_mt7628, MT7628_GPIO_MODE_MASK,
+				1, MT7628_GPIO_MODE_WLED_KN),
 	{ 0 }
 };
 
diff --git a/arch/parisc/include/asm/dma-mapping.h b/arch/parisc/include/asm/dma-mapping.h
index d0eae5f2bd87..4fb62add2636 100644
--- a/arch/parisc/include/asm/dma-mapping.h
+++ b/arch/parisc/include/asm/dma-mapping.h
@@ -39,6 +39,8 @@ struct hppa_dma_ops {
 ** flush/purge and allocate "regular" cacheable pages for everything.
 */
 
+#define DMA_ERROR_CODE	(~(dma_addr_t)0)
+
 #ifdef CONFIG_PA11
 extern struct hppa_dma_ops pcxl_dma_ops;
 extern struct hppa_dma_ops pcx_dma_ops;
@@ -209,12 +211,13 @@ parisc_walk_tree(struct device *dev)
 			break;
 		}
 	}
-	BUG_ON(!dev->platform_data);
 	return dev->platform_data;
 }
-		
-#define GET_IOC(dev) (HBA_DATA(parisc_walk_tree(dev))->iommu)
-	
+
+#define GET_IOC(dev) ({					\
+	void *__pdata = parisc_walk_tree(dev);		\
+	__pdata ? HBA_DATA(__pdata)->iommu : NULL;	\
+})
 
 #ifdef CONFIG_IOMMU_CCIO
 struct parisc_device;
diff --git a/arch/parisc/kernel/syscall_table.S b/arch/parisc/kernel/syscall_table.S
index 8eefb12d1d33..3781b8c0fad9 100644
--- a/arch/parisc/kernel/syscall_table.S
+++ b/arch/parisc/kernel/syscall_table.S
@@ -361,7 +361,7 @@
 	ENTRY_SAME(ni_syscall)	/* 263: reserved for vserver */
 	ENTRY_SAME(add_key)
 	ENTRY_SAME(request_key)		/* 265 */
-	ENTRY_SAME(keyctl)
+	ENTRY_COMP(keyctl)
 	ENTRY_SAME(ioprio_set)
 	ENTRY_SAME(ioprio_get)
 	ENTRY_SAME(inotify_init)
diff --git a/arch/parisc/mm/fault.c b/arch/parisc/mm/fault.c
index 50d64a7fc672..3b7c02f9b726 100644
--- a/arch/parisc/mm/fault.c
+++ b/arch/parisc/mm/fault.c
@@ -303,7 +303,7 @@ bad_area:
 		case 15:	/* Data TLB miss fault/Data page fault */
 			/* send SIGSEGV when outside of vma */
 			if (!vma ||
-			    address < vma->vm_start || address > vma->vm_end) {
+			    address < vma->vm_start || address >= vma->vm_end) {
 				si.si_signo = SIGSEGV;
 				si.si_code = SEGV_MAPERR;
 				break;
diff --git a/arch/powerpc/include/asm/elf.h b/arch/powerpc/include/asm/elf.h
index ee46ffef608e..743ad7a400d6 100644
--- a/arch/powerpc/include/asm/elf.h
+++ b/arch/powerpc/include/asm/elf.h
@@ -23,12 +23,13 @@
 #define CORE_DUMP_USE_REGSET
 #define ELF_EXEC_PAGESIZE	PAGE_SIZE
 
-/* 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	0x20000000
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(is_32bit_task() ? 0x000400000UL : \
+						   0x100000000UL)
 
 #define ELF_CORE_EFLAGS (is_elf2_task() ? 2 : 0)
 
diff --git a/arch/powerpc/kernel/eeh.c b/arch/powerpc/kernel/eeh.c
index b264937bba68..9340d05bcdc9 100644
--- a/arch/powerpc/kernel/eeh.c
+++ b/arch/powerpc/kernel/eeh.c
@@ -306,9 +306,17 @@ void eeh_slot_error_detail(struct eeh_pe *pe, int severity)
 	 *
 	 * For pHyp, we have to enable IO for log retrieval. Otherwise,
 	 * 0xFF's is always returned from PCI config space.
+	 *
+	 * When the @severity is EEH_LOG_PERM, the PE is going to be
+	 * removed. Prior to that, the drivers for devices included in
+	 * the PE will be closed. The drivers rely on working IO path
+	 * to bring the devices to quiet state. Otherwise, PCI traffic
+	 * from those devices after they are removed is like to cause
+	 * another unexpected EEH error.
 	 */
 	if (!(pe->type & EEH_PE_PHB)) {
-		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG))
+		if (eeh_has_flag(EEH_ENABLE_IO_FOR_LOG) ||
+		    severity == EEH_LOG_PERM)
 			eeh_pci_enable(pe, EEH_OPT_THAW_MMIO);
 
 		/*
diff --git a/arch/powerpc/kernel/eeh_driver.c b/arch/powerpc/kernel/eeh_driver.c
index 0a4f23a070ab..ffca0bf5b8b4 100644
--- a/arch/powerpc/kernel/eeh_driver.c
+++ b/arch/powerpc/kernel/eeh_driver.c
@@ -651,7 +651,7 @@ static int eeh_reset_device(struct eeh_pe *pe, struct pci_bus *bus)
  */
 #define MAX_WAIT_FOR_RECOVERY 300
 
-static void eeh_handle_normal_event(struct eeh_pe *pe)
+static bool eeh_handle_normal_event(struct eeh_pe *pe)
 {
 	struct pci_bus *frozen_bus;
 	int rc = 0;
@@ -661,7 +661,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	if (!frozen_bus) {
 		pr_err("%s: Cannot find PCI bus for PHB#%d-PE#%x\n",
 			__func__, pe->phb->global_number, pe->addr);
-		return;
+		return false;
 	}
 
 	eeh_pe_update_time_stamp(pe);
@@ -778,7 +778,7 @@ static void eeh_handle_normal_event(struct eeh_pe *pe)
 	pr_info("EEH: Notify device driver to resume\n");
 	eeh_pe_dev_traverse(pe, eeh_report_resume, NULL);
 
-	return;
+	return false;
 
 excess_failures:
 	/*
@@ -819,7 +819,11 @@ perm_error:
 		pci_lock_rescan_remove();
 		pcibios_remove_pci_devices(frozen_bus);
 		pci_unlock_rescan_remove();
+
+		/* The passed PE should no longer be used */
+		return true;
 	}
+	return false;
 }
 
 static void eeh_handle_special_event(void)
@@ -885,7 +889,14 @@ static void eeh_handle_special_event(void)
 		 */
 		if (rc == EEH_NEXT_ERR_FROZEN_PE ||
 		    rc == EEH_NEXT_ERR_FENCED_PHB) {
-			eeh_handle_normal_event(pe);
+			/*
+			 * eeh_handle_normal_event() can make the PE stale if it
+			 * determines that the PE cannot possibly be recovered.
+			 * Don't modify the PE state if that's the case.
+			 */
+			if (eeh_handle_normal_event(pe))
+				continue;
+
 			eeh_pe_state_clear(pe, EEH_PE_RECOVERING);
 		} else {
 			pci_lock_rescan_remove();
diff --git a/arch/powerpc/kernel/kprobes.c b/arch/powerpc/kernel/kprobes.c
index 7c053f281406..1138fec3dd65 100644
--- a/arch/powerpc/kernel/kprobes.c
+++ b/arch/powerpc/kernel/kprobes.c
@@ -514,6 +514,15 @@ int __kprobes setjmp_pre_handler(struct kprobe *p, struct pt_regs *regs)
 #endif
 #endif
 
+	/*
+	 * jprobes use jprobe_return() which skips the normal return
+	 * path of the function, and this messes up the accounting of the
+	 * function graph tracer.
+	 *
+	 * Pause function graph tracing while performing the jprobe function.
+	 */
+	pause_graph_tracing();
+
 	return 1;
 }
 
@@ -536,6 +545,8 @@ int __kprobes longjmp_break_handler(struct kprobe *p, struct pt_regs *regs)
 	 * saved regs...
 	 */
 	memcpy(regs, &kcb->jprobe_saved_regs, sizeof(struct pt_regs));
+	/* It's OK to start function graph tracing again */
+	unpause_graph_tracing();
 	preempt_enable_no_resched();
 	return 1;
 }
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index 63c37fd2b7a6..c1e10ffadd17 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -2238,6 +2238,27 @@ static int kvmppc_vcpu_run_hv(struct kvm_run *run, struct kvm_vcpu *vcpu)
 		return -EINVAL;
 	}
 
+	/*
+	 * Don't allow entry with a suspended transaction, because
+	 * the guest entry/exit code will lose it.
+	 * If the guest has TM enabled, save away their TM-related SPRs
+	 * (they will get restored by the TM unavailable interrupt).
+	 */
+#ifdef CONFIG_PPC_TRANSACTIONAL_MEM
+	if (cpu_has_feature(CPU_FTR_TM) && current->thread.regs &&
+	    (current->thread.regs->msr & MSR_TM)) {
+		if (MSR_TM_ACTIVE(current->thread.regs->msr)) {
+			run->exit_reason = KVM_EXIT_FAIL_ENTRY;
+			run->fail_entry.hardware_entry_failure_reason = 0;
+			return -EINVAL;
+		}
+		current->thread.tm_tfhar = mfspr(SPRN_TFHAR);
+		current->thread.tm_tfiar = mfspr(SPRN_TFIAR);
+		current->thread.tm_texasr = mfspr(SPRN_TEXASR);
+		current->thread.regs->msr &= ~MSR_TM;
+	}
+#endif
+
 	kvmppc_core_prepare_to_enter(vcpu);
 
 	/* No need to go into the guest when all we'll do is come back out */
diff --git a/arch/s390/include/asm/ctl_reg.h b/arch/s390/include/asm/ctl_reg.h
index d7697ab802f6..8e136b88cdf4 100644
--- a/arch/s390/include/asm/ctl_reg.h
+++ b/arch/s390/include/asm/ctl_reg.h
@@ -15,7 +15,9 @@
 	BUILD_BUG_ON(sizeof(addrtype) != (high - low + 1) * sizeof(long));\
 	asm volatile(							\
 		"	lctlg	%1,%2,%0\n"				\
-		: : "Q" (*(addrtype *)(&array)), "i" (low), "i" (high));\
+		:							\
+		: "Q" (*(addrtype *)(&array)), "i" (low), "i" (high)	\
+		: "memory");						\
 }
 
 #define __ctl_store(array, low, high) {					\
diff --git a/arch/s390/include/asm/elf.h b/arch/s390/include/asm/elf.h
index 3ad48f22de78..f133ce08b270 100644
--- a/arch/s390/include/asm/elf.h
+++ b/arch/s390/include/asm/elf.h
@@ -154,14 +154,13 @@ extern unsigned int vdso_enabled;
 #define CORE_DUMP_USE_REGSET
 #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. 64-bit
-   tasks are aligned to 4GB. */
-#define ELF_ET_DYN_BASE (is_32bit_task() ? \
-				(STACK_TOP / 3 * 2) : \
-				(STACK_TOP / 3 * 2) & ~((1UL << 32) - 1))
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(is_compat_task() ? 0x000400000UL : \
+						    0x100000000UL)
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports. */
diff --git a/arch/s390/mm/vmem.c b/arch/s390/mm/vmem.c
index ef7d6c8fea66..f354fd84adeb 100644
--- a/arch/s390/mm/vmem.c
+++ b/arch/s390/mm/vmem.c
@@ -372,7 +372,7 @@ void __init vmem_map_init(void)
 	ro_end = (unsigned long)&_eshared & PAGE_MASK;
 	for_each_memblock(memory, reg) {
 		start = reg->base;
-		end = reg->base + reg->size - 1;
+		end = reg->base + reg->size;
 		if (start >= ro_end || end <= ro_start)
 			vmem_add_mem(start, end - start, 0);
 		else if (start >= ro_start && end <= ro_end)
diff --git a/arch/x86/include/asm/elf.h b/arch/x86/include/asm/elf.h
index 3b5b7a9c866d..2903ff34174c 100644
--- a/arch/x86/include/asm/elf.h
+++ b/arch/x86/include/asm/elf.h
@@ -245,12 +245,13 @@ extern int force_personality32;
 #define CORE_DUMP_USE_REGSET
 #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		(TASK_SIZE / 3 * 2)
+/*
+ * This is the base location for PIE (ET_DYN with INTERP) loads. On
+ * 64-bit, this is raised to 4GB to leave the entire 32-bit address
+ * space open for things that want to use the area for 32-bit pointers.
+ */
+#define ELF_ET_DYN_BASE		(mmap_is_ia32() ? 0x000400000UL : \
+						  0x100000000UL)
 
 /* This yields a mask that user programs can use to figure out what
    instruction set this CPU supports.  This could be done in user space,
diff --git a/arch/x86/kvm/vmx.c b/arch/x86/kvm/vmx.c
index 99a15e38fa06..32e29f926e5a 100644
--- a/arch/x86/kvm/vmx.c
+++ b/arch/x86/kvm/vmx.c
@@ -2118,7 +2118,7 @@ static int nested_vmx_check_exception(struct kvm_vcpu *vcpu, unsigned nr)
 	if (!(vmcs12->exception_bitmap & (1u << nr)))
 		return 0;
 
-	nested_vmx_vmexit(vcpu, to_vmx(vcpu)->exit_reason,
+	nested_vmx_vmexit(vcpu, EXIT_REASON_EXCEPTION_NMI,
 			  vmcs_read32(VM_EXIT_INTR_INFO),
 			  vmcs_readl(EXIT_QUALIFICATION));
 	return 1;
@@ -6153,7 +6153,6 @@ static __init int hardware_setup(void)
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_CS, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_ESP, false);
 	vmx_disable_intercept_for_msr(MSR_IA32_SYSENTER_EIP, false);
-	vmx_disable_intercept_for_msr(MSR_IA32_BNDCFGS, true);
 
 	memcpy(vmx_msr_bitmap_legacy_x2apic,
 			vmx_msr_bitmap_legacy, PAGE_SIZE);
diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c
index c730e4708c7d..9d7ea42482e3 100644
--- a/arch/x86/kvm/x86.c
+++ b/arch/x86/kvm/x86.c
@@ -4910,6 +4910,8 @@ static bool emulator_get_segment(struct x86_emulate_ctxt *ctxt, u16 *selector,
 
 	if (var.unusable) {
 		memset(desc, 0, sizeof(*desc));
+		if (base3)
+			*base3 = 0;
 		return false;
 	}
 
@@ -6049,7 +6051,8 @@ static int emulator_fix_hypercall(struct x86_emulate_ctxt *ctxt)
 
 	kvm_x86_ops->patch_hypercall(vcpu, instruction);
 
-	return emulator_write_emulated(ctxt, rip, instruction, 3, NULL);
+	return emulator_write_emulated(ctxt, rip, instruction, 3,
+		&ctxt->exception);
 }
 
 /*
diff --git a/arch/x86/lib/copy_user_64.S b/arch/x86/lib/copy_user_64.S
index fa997dfaef24..2f1c52e252b0 100644
--- a/arch/x86/lib/copy_user_64.S
+++ b/arch/x86/lib/copy_user_64.S
@@ -112,7 +112,7 @@ ENTRY(copy_user_generic_unrolled)
 	movl %edx,%ecx
 	andl $63,%edx
 	shrl $6,%ecx
-	jz 17f
+	jz .L_copy_short_string
 1:	movq (%rsi),%r8
 2:	movq 1*8(%rsi),%r9
 3:	movq 2*8(%rsi),%r10
@@ -133,7 +133,8 @@ ENTRY(copy_user_generic_unrolled)
 	leaq 64(%rdi),%rdi
 	decl %ecx
 	jnz 1b
-17:	movl %edx,%ecx
+.L_copy_short_string:
+	movl %edx,%ecx
 	andl $7,%edx
 	shrl $3,%ecx
 	jz 20f
@@ -251,6 +252,8 @@ ENDPROC(copy_user_generic_string)
 ENTRY(copy_user_enhanced_fast_string)
 	CFI_STARTPROC
 	ASM_STAC
+	cmpl $64,%edx
+	jb .L_copy_short_string	/* less then 64 bytes, avoid the costly 'rep' */
 	movl %edx,%ecx
 1:	rep
 	movsb
diff --git a/arch/x86/mm/mpx.c b/arch/x86/mm/mpx.c
index 6a3c774eaff6..c2fea3af515d 100644
--- a/arch/x86/mm/mpx.c
+++ b/arch/x86/mm/mpx.c
@@ -312,7 +312,7 @@ siginfo_t *mpx_generate_siginfo(struct pt_regs *regs,
 	 * We were not able to extract an address from the instruction,
 	 * probably because there was something invalid in it.
 	 */
-	if (info->si_addr == (void *)-1) {
+	if (info->si_addr == (void __user *)-1) {
 		err = -EINVAL;
 		goto err_out;
 	}
diff --git a/arch/x86/tools/relocs.c b/arch/x86/tools/relocs.c
index 0c2fae8d929d..73eb7fd4aec4 100644
--- a/arch/x86/tools/relocs.c
+++ b/arch/x86/tools/relocs.c
@@ -992,11 +992,12 @@ static void emit_relocs(int as_text, int use_real_mode)
 		die("Segment relocations found but --realmode not specified\n");
 
 	/* Order the relocations for more efficient processing */
-	sort_relocs(&relocs16);
 	sort_relocs(&relocs32);
 #if ELF_BITS == 64
 	sort_relocs(&relocs32neg);
 	sort_relocs(&relocs64);
+#else
+	sort_relocs(&relocs16);
 #endif
 
 	/* Print the relocations */