diff --git a/Documentation/arm/SA1100/Victor b/Documentation/arm/SA1100/Victor
deleted file mode 100644
index 9cff415da5a7..000000000000
--- a/Documentation/arm/SA1100/Victor
+++ /dev/null
@@ -1,16 +0,0 @@
-Victor is known as a "digital talking book player" manufactured by
-VisuAide, Inc. to be used by blind people.
-
-For more information related to Victor, see:
-
-	http://www.humanware.com/en-usa/products
-
-Of course Victor is using Linux as its main operating system.
-The Victor implementation for Linux is maintained by Nicolas Pitre:
-
-	nico@visuaide.com
-	nico@fluxnic.net
-
-For any comments, please feel free to contact me through the above
-addresses.
-
diff --git a/Documentation/arm/memory.txt b/Documentation/arm/memory.txt
index 4178ebda6e66..546a39048eb0 100644
--- a/Documentation/arm/memory.txt
+++ b/Documentation/arm/memory.txt
@@ -54,7 +54,7 @@ VMALLOC_START	VMALLOC_END-1	vmalloc() / ioremap() space.
 				located here through iotable_init().
 				VMALLOC_START is based upon the value
 				of the high_memory variable, and VMALLOC_END
-				is equal to 0xff000000.
+				is equal to 0xff800000.
 
 PAGE_OFFSET	high_memory-1	Kernel direct-mapped RAM region.
 				This maps the platforms RAM, and typically
diff --git a/Documentation/devicetree/bindings/arm/twd.txt b/Documentation/devicetree/bindings/arm/twd.txt
index 75b8610939fa..383ea19c2bf0 100644
--- a/Documentation/devicetree/bindings/arm/twd.txt
+++ b/Documentation/devicetree/bindings/arm/twd.txt
@@ -19,6 +19,11 @@ interrupts.
 - reg : Specify the base address and the size of the TWD timer
 	register window.
 
+Optional
+
+- always-on : a boolean property. If present, the timer is powered through
+  an always-on power domain, therefore it never loses context.
+
 Example:
 
 	twd-timer@2c000600 {
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 639411f73ca9..823f90ea65c4 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1411,7 +1411,6 @@ config HAVE_ARM_ARCH_TIMER
 
 config HAVE_ARM_TWD
 	bool
-	depends on SMP
 	select CLKSRC_OF if OF
 	help
 	  This options enables support for the ARM timer and watchdog unit
@@ -1471,6 +1470,8 @@ choice
 
 	config VMSPLIT_3G
 		bool "3G/1G user/kernel split"
+	config VMSPLIT_3G_OPT
+		bool "3G/1G user/kernel split (for full 1G low memory)"
 	config VMSPLIT_2G
 		bool "2G/2G user/kernel split"
 	config VMSPLIT_1G
@@ -1482,6 +1483,7 @@ config PAGE_OFFSET
 	default PHYS_OFFSET if !MMU
 	default 0x40000000 if VMSPLIT_1G
 	default 0x80000000 if VMSPLIT_2G
+	default 0xB0000000 if VMSPLIT_3G_OPT
 	default 0xC0000000
 
 config NR_CPUS
@@ -1696,8 +1698,9 @@ config HIGHMEM
 	  If unsure, say n.
 
 config HIGHPTE
-	bool "Allocate 2nd-level pagetables from highmem"
+	bool "Allocate 2nd-level pagetables from highmem" if EXPERT
 	depends on HIGHMEM
+	default y
 	help
 	  The VM uses one page of physical memory for each page table.
 	  For systems with a lot of processes, this can use a lot of
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 916a2744d5c6..97882f9bad12 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -39,6 +39,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 
 	switch (size) {
 #if __LINUX_ARM_ARCH__ >= 6
+#ifndef CONFIG_CPU_V6 /* MIN ARCH >= V6K */
 	case 1:
 		asm volatile("@	__xchg1\n"
 		"1:	ldrexb	%0, [%3]\n"
@@ -49,6 +50,17 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 			: "r" (x), "r" (ptr)
 			: "memory", "cc");
 		break;
+	case 2:
+		asm volatile("@	__xchg2\n"
+		"1:	ldrexh	%0, [%3]\n"
+		"	strexh	%1, %2, [%3]\n"
+		"	teq	%1, #0\n"
+		"	bne	1b"
+			: "=&r" (ret), "=&r" (tmp)
+			: "r" (x), "r" (ptr)
+			: "memory", "cc");
+		break;
+#endif
 	case 4:
 		asm volatile("@	__xchg4\n"
 		"1:	ldrex	%0, [%3]\n"
diff --git a/arch/arm/include/asm/irqflags.h b/arch/arm/include/asm/irqflags.h
index 43908146a5cf..e6b70d9d084e 100644
--- a/arch/arm/include/asm/irqflags.h
+++ b/arch/arm/include/asm/irqflags.h
@@ -54,6 +54,14 @@ static inline void arch_local_irq_disable(void)
 
 #define local_fiq_enable()  __asm__("cpsie f	@ __stf" : : : "memory", "cc")
 #define local_fiq_disable() __asm__("cpsid f	@ __clf" : : : "memory", "cc")
+
+#ifndef CONFIG_CPU_V7M
+#define local_abt_enable()  __asm__("cpsie a	@ __sta" : : : "memory", "cc")
+#define local_abt_disable() __asm__("cpsid a	@ __cla" : : : "memory", "cc")
+#else
+#define local_abt_enable()	do { } while (0)
+#define local_abt_disable()	do { } while (0)
+#endif
 #else
 
 /*
@@ -136,6 +144,8 @@ static inline void arch_local_irq_disable(void)
 	: "memory", "cc");					\
 	})
 
+#define local_abt_enable()	do { } while (0)
+#define local_abt_disable()	do { } while (0)
 #endif
 
 /*
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index cb3a40717edd..5c1ad11aa392 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -47,7 +47,7 @@ struct machine_desc {
 	unsigned		l2c_aux_val;	/* L2 cache aux value	*/
 	unsigned		l2c_aux_mask;	/* L2 cache aux mask	*/
 	void			(*l2c_write_sec)(unsigned long, unsigned);
-	struct smp_operations	*smp;		/* SMP operations	*/
+	const struct smp_operations	*smp;	/* SMP operations	*/
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **);
 	void			(*dt_fixup)(void);
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index 98d58bb04ac5..c79b57bf71c4 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -76,10 +76,12 @@
  */
 #define XIP_VIRT_ADDR(physaddr)  (MODULES_VADDR + ((physaddr) & 0x000fffff))
 
+#if !defined(CONFIG_SMP) && !defined(CONFIG_ARM_LPAE)
 /*
  * Allow 16MB-aligned ioremap pages
  */
 #define IOREMAP_MAX_ORDER	24
+#endif
 
 #else /* CONFIG_MMU */
 
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index f40354198bad..348caabb7625 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -43,7 +43,7 @@
  */
 #define VMALLOC_OFFSET		(8*1024*1024)
 #define VMALLOC_START		(((unsigned long)high_memory + VMALLOC_OFFSET) & ~(VMALLOC_OFFSET-1))
-#define VMALLOC_END		0xff000000UL
+#define VMALLOC_END		0xff800000UL
 
 #define LIBRARY_TEXT_START	0x0c000000
 
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index ef356659b4f4..3d6dc8b460e4 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -112,7 +112,7 @@ struct smp_operations {
 
 struct of_cpu_method {
 	const char *method;
-	struct smp_operations *ops;
+	const struct smp_operations *ops;
 };
 
 #define CPU_METHOD_OF_DECLARE(name, _method, _ops)			\
@@ -122,6 +122,6 @@ struct of_cpu_method {
 /*
  * set platform specific SMP operations
  */
-extern void smp_set_ops(struct smp_operations *);
+extern void smp_set_ops(const struct smp_operations *);
 
 #endif /* ifndef __ASM_ARM_SMP_H */
diff --git a/arch/arm/include/asm/unistd.h b/arch/arm/include/asm/unistd.h
index 7cba573c2cc9..7b84657fba35 100644
--- a/arch/arm/include/asm/unistd.h
+++ b/arch/arm/include/asm/unistd.h
@@ -21,13 +21,6 @@
  */
 #define __NR_syscalls  (392)
 
-/*
- * *NOTE*: This is a ghost syscall private to the kernel.  Only the
- * __kuser_cmpxchg code in entry-armv.S should be aware of its
- * existence.  Don't ever use this from user code.
- */
-#define __ARM_NR_cmpxchg		(__ARM_NR_BASE+0x00fff0)
-
 #define __ARCH_WANT_STAT64
 #define __ARCH_WANT_SYS_GETHOSTNAME
 #define __ARCH_WANT_SYS_PAUSE
diff --git a/arch/arm/kernel/devtree.c b/arch/arm/kernel/devtree.c
index 11c54de9f8cf..65addcbf5b30 100644
--- a/arch/arm/kernel/devtree.c
+++ b/arch/arm/kernel/devtree.c
@@ -101,6 +101,7 @@ void __init arm_dt_init_cpu_maps(void)
 		if (of_property_read_u32(cpu, "reg", &hwid)) {
 			pr_debug(" * %s missing reg property\n",
 				     cpu->full_name);
+			of_node_put(cpu);
 			return;
 		}
 
@@ -108,8 +109,10 @@ void __init arm_dt_init_cpu_maps(void)
 		 * 8 MSBs must be set to 0 in the DT since the reg property
 		 * defines the MPIDR[23:0].
 		 */
-		if (hwid & ~MPIDR_HWID_BITMASK)
+		if (hwid & ~MPIDR_HWID_BITMASK) {
+			of_node_put(cpu);
 			return;
+		}
 
 		/*
 		 * Duplicate MPIDRs are a recipe for disaster.
@@ -119,9 +122,11 @@ void __init arm_dt_init_cpu_maps(void)
 		 * to avoid matching valid MPIDR[23:0] values.
 		 */
 		for (j = 0; j < cpuidx; j++)
-			if (WARN(tmp_map[j] == hwid, "Duplicate /cpu reg "
-						     "properties in the DT\n"))
+			if (WARN(tmp_map[j] == hwid,
+				 "Duplicate /cpu reg properties in the DT\n")) {
+				of_node_put(cpu);
 				return;
+			}
 
 		/*
 		 * Build a stashed array of MPIDR values. Numbering scheme
@@ -143,6 +148,7 @@ void __init arm_dt_init_cpu_maps(void)
 					       "max cores %u, capping them\n",
 					       cpuidx, nr_cpu_ids)) {
 			cpuidx = nr_cpu_ids;
+			of_node_put(cpu);
 			break;
 		}
 
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 3e1c26eb32b4..3ce377f7251f 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -427,8 +427,7 @@ ENDPROC(__fiq_abt)
 	.endm
 
 	.macro	kuser_cmpxchg_check
-#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS) && \
-    !defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
+#if !defined(CONFIG_CPU_32v6K) && defined(CONFIG_KUSER_HELPERS)
 #ifndef CONFIG_MMU
 #warning "NPTL on non MMU needs fixing"
 #else
@@ -859,20 +858,7 @@ __kuser_helper_start:
 
 __kuser_cmpxchg64:				@ 0xffff0f60
 
-#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
-
-	/*
-	 * Poor you.  No fast solution possible...
-	 * The kernel itself must perform the operation.
-	 * A special ghost syscall is used for that (see traps.c).
-	 */
-	stmfd	sp!, {r7, lr}
-	ldr	r7, 1f			@ it's 20 bits
-	swi	__ARM_NR_cmpxchg64
-	ldmfd	sp!, {r7, pc}
-1:	.word	__ARM_NR_cmpxchg64
-
-#elif defined(CONFIG_CPU_32v6K)
+#if defined(CONFIG_CPU_32v6K)
 
 	stmfd	sp!, {r4, r5, r6, r7}
 	ldrd	r4, r5, [r0]			@ load old val
@@ -948,20 +934,7 @@ __kuser_memory_barrier:				@ 0xffff0fa0
 
 __kuser_cmpxchg:				@ 0xffff0fc0
 
-#if defined(CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG)
-
-	/*
-	 * Poor you.  No fast solution possible...
-	 * The kernel itself must perform the operation.
-	 * A special ghost syscall is used for that (see traps.c).
-	 */
-	stmfd	sp!, {r7, lr}
-	ldr	r7, 1f			@ it's 20 bits
-	swi	__ARM_NR_cmpxchg
-	ldmfd	sp!, {r7, pc}
-1:	.word	__ARM_NR_cmpxchg
-
-#elif __LINUX_ARM_ARCH__ < 6
+#if __LINUX_ARM_ARCH__ < 6
 
 #ifdef CONFIG_MMU
 
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index dc7d0a95bd36..6284779d64ee 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -35,7 +35,6 @@
 #include <asm/cputype.h>
 #include <asm/current.h>
 #include <asm/hw_breakpoint.h>
-#include <asm/kdebug.h>
 #include <asm/traps.h>
 
 /* Breakpoint currently in use for each BRP. */
diff --git a/arch/arm/kernel/kgdb.c b/arch/arm/kernel/kgdb.c
index fd9eefce0a7b..9232caee7060 100644
--- a/arch/arm/kernel/kgdb.c
+++ b/arch/arm/kernel/kgdb.c
@@ -74,7 +74,7 @@ int dbg_set_reg(int regno, void *mem, struct pt_regs *regs)
 void
 sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
 {
-	struct pt_regs *thread_regs;
+	struct thread_info *ti;
 	int regno;
 
 	/* Just making sure... */
@@ -86,24 +86,17 @@ sleeping_thread_to_gdb_regs(unsigned long *gdb_regs, struct task_struct *task)
 		gdb_regs[regno] = 0;
 
 	/* Otherwise, we have only some registers from switch_to() */
-	thread_regs		= task_pt_regs(task);
-	gdb_regs[_R0]		= thread_regs->ARM_r0;
-	gdb_regs[_R1]		= thread_regs->ARM_r1;
-	gdb_regs[_R2]		= thread_regs->ARM_r2;
-	gdb_regs[_R3]		= thread_regs->ARM_r3;
-	gdb_regs[_R4]		= thread_regs->ARM_r4;
-	gdb_regs[_R5]		= thread_regs->ARM_r5;
-	gdb_regs[_R6]		= thread_regs->ARM_r6;
-	gdb_regs[_R7]		= thread_regs->ARM_r7;
-	gdb_regs[_R8]		= thread_regs->ARM_r8;
-	gdb_regs[_R9]		= thread_regs->ARM_r9;
-	gdb_regs[_R10]		= thread_regs->ARM_r10;
-	gdb_regs[_FP]		= thread_regs->ARM_fp;
-	gdb_regs[_IP]		= thread_regs->ARM_ip;
-	gdb_regs[_SPT]		= thread_regs->ARM_sp;
-	gdb_regs[_LR]		= thread_regs->ARM_lr;
-	gdb_regs[_PC]		= thread_regs->ARM_pc;
-	gdb_regs[_CPSR]		= thread_regs->ARM_cpsr;
+	ti			= task_thread_info(task);
+	gdb_regs[_R4]		= ti->cpu_context.r4;
+	gdb_regs[_R5]		= ti->cpu_context.r5;
+	gdb_regs[_R6]		= ti->cpu_context.r6;
+	gdb_regs[_R7]		= ti->cpu_context.r7;
+	gdb_regs[_R8]		= ti->cpu_context.r8;
+	gdb_regs[_R9]		= ti->cpu_context.r9;
+	gdb_regs[_R10]		= ti->cpu_context.sl;
+	gdb_regs[_FP]		= ti->cpu_context.fp;
+	gdb_regs[_SPT]		= ti->cpu_context.sp;
+	gdb_regs[_PC]		= ti->cpu_context.pc;
 }
 
 void kgdb_arch_set_pc(struct pt_regs *regs, unsigned long pc)
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 48185a773852..b26361355dae 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -80,7 +80,7 @@ static DECLARE_COMPLETION(cpu_running);
 
 static struct smp_operations smp_ops;
 
-void __init smp_set_ops(struct smp_operations *ops)
+void __init smp_set_ops(const struct smp_operations *ops)
 {
 	if (ops)
 		smp_ops = *ops;
@@ -400,6 +400,7 @@ asmlinkage void secondary_start_kernel(void)
 
 	local_irq_enable();
 	local_fiq_enable();
+	local_abt_enable();
 
 	/*
 	 * OK, it's off to the idle thread for us
@@ -748,6 +749,15 @@ core_initcall(register_cpufreq_notifier);
 
 static void raise_nmi(cpumask_t *mask)
 {
+	/*
+	 * Generate the backtrace directly if we are running in a calling
+	 * context that is not preemptible by the backtrace IPI. Note
+	 * that nmi_cpu_backtrace() automatically removes the current cpu
+	 * from mask.
+	 */
+	if (cpumask_test_cpu(smp_processor_id(), mask) && irqs_disabled())
+		nmi_cpu_backtrace(NULL);
+
 	smp_cross_call(mask, IPI_CPU_BACKTRACE);
 }
 
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index e9035cda1485..1bfa7a7f5533 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -23,7 +23,6 @@
 #include <linux/of_irq.h>
 #include <linux/of_address.h>
 
-#include <asm/smp_plat.h>
 #include <asm/smp_twd.h>
 
 /* set up by the platform code */
@@ -34,6 +33,8 @@ static unsigned long twd_timer_rate;
 static DEFINE_PER_CPU(bool, percpu_setup_called);
 
 static struct clock_event_device __percpu *twd_evt;
+static unsigned int twd_features =
+		CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT;
 static int twd_ppi;
 
 static int twd_shutdown(struct clock_event_device *clk)
@@ -294,8 +295,7 @@ static void twd_timer_setup(void)
 	writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
 
 	clk->name = "local_timer";
-	clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
-			CLOCK_EVT_FEAT_C3STOP;
+	clk->features = twd_features;
 	clk->rating = 350;
 	clk->set_state_shutdown = twd_shutdown;
 	clk->set_state_periodic = twd_set_periodic;
@@ -350,6 +350,8 @@ static int __init twd_local_timer_common_register(struct device_node *np)
 		goto out_irq;
 
 	twd_get_clock(np);
+	if (!of_property_read_bool(np, "always-on"))
+		twd_features |= CLOCK_EVT_FEAT_C3STOP;
 
 	/*
 	 * Immediately configure the timer on the boot CPU, unless we need
@@ -392,9 +394,6 @@ static void __init twd_local_timer_of_register(struct device_node *np)
 {
 	int err;
 
-	if (!is_smp() || !setup_max_cpus)
-		return;
-
 	twd_ppi = irq_of_parse_and_map(np, 0);
 	if (!twd_ppi) {
 		err = -EINVAL;
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 969f9d9e665f..bc698383e822 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -625,58 +625,6 @@ asmlinkage int arm_syscall(int no, struct pt_regs *regs)
 		set_tls(regs->ARM_r0);
 		return 0;
 
-#ifdef CONFIG_NEEDS_SYSCALL_FOR_CMPXCHG
-	/*
-	 * Atomically store r1 in *r2 if *r2 is equal to r0 for user space.
-	 * Return zero in r0 if *MEM was changed or non-zero if no exchange
-	 * happened.  Also set the user C flag accordingly.
-	 * If access permissions have to be fixed up then non-zero is
-	 * returned and the operation has to be re-attempted.
-	 *
-	 * *NOTE*: This is a ghost syscall private to the kernel.  Only the
-	 * __kuser_cmpxchg code in entry-armv.S should be aware of its
-	 * existence.  Don't ever use this from user code.
-	 */
-	case NR(cmpxchg):
-	for (;;) {
-		extern void do_DataAbort(unsigned long addr, unsigned int fsr,
-					 struct pt_regs *regs);
-		unsigned long val;
-		unsigned long addr = regs->ARM_r2;
-		struct mm_struct *mm = current->mm;
-		pgd_t *pgd; pmd_t *pmd; pte_t *pte;
-		spinlock_t *ptl;
-
-		regs->ARM_cpsr &= ~PSR_C_BIT;
-		down_read(&mm->mmap_sem);
-		pgd = pgd_offset(mm, addr);
-		if (!pgd_present(*pgd))
-			goto bad_access;
-		pmd = pmd_offset(pgd, addr);
-		if (!pmd_present(*pmd))
-			goto bad_access;
-		pte = pte_offset_map_lock(mm, pmd, addr, &ptl);
-		if (!pte_present(*pte) || !pte_write(*pte) || !pte_dirty(*pte)) {
-			pte_unmap_unlock(pte, ptl);
-			goto bad_access;
-		}
-		val = *(unsigned long *)addr;
-		val -= regs->ARM_r0;
-		if (val == 0) {
-			*(unsigned long *)addr = regs->ARM_r1;
-			regs->ARM_cpsr |= PSR_C_BIT;
-		}
-		pte_unmap_unlock(pte, ptl);
-		up_read(&mm->mmap_sem);
-		return val;
-
-		bad_access:
-		up_read(&mm->mmap_sem);
-		/* simulate a write access fault */
-		do_DataAbort(addr, 15 + (1 << 11), regs);
-	}
-#endif
-
 	default:
 		/* Calls 9f00xx..9f07ff are defined to return -ENOSYS
 		   if not implemented, rather than raising SIGILL.  This
diff --git a/arch/arm/lib/clear_user.S b/arch/arm/lib/clear_user.S
index 970d6c043774..e936352ccb00 100644
--- a/arch/arm/lib/clear_user.S
+++ b/arch/arm/lib/clear_user.S
@@ -9,6 +9,7 @@
  */
 #include <linux/linkage.h>
 #include <asm/assembler.h>
+#include <asm/unwind.h>
 
 		.text
 
@@ -20,6 +21,8 @@
  */
 ENTRY(__clear_user_std)
 WEAK(arm_clear_user)
+UNWIND(.fnstart)
+UNWIND(.save {r1, lr})
 		stmfd	sp!, {r1, lr}
 		mov	r2, #0
 		cmp	r1, #4
@@ -44,6 +47,7 @@ WEAK(arm_clear_user)
 USER(		strnebt	r2, [r0])
 		mov	r0, #0
 		ldmfd	sp!, {r1, pc}
+UNWIND(.fnend)
 ENDPROC(arm_clear_user)
 ENDPROC(__clear_user_std)
 
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index df7537f12469..c21941349b3e 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -419,28 +419,24 @@ config CPU_THUMBONLY
 config CPU_32v3
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v4
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v4T
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
 config CPU_32v5
 	bool
 	select CPU_USE_DOMAINS if MMU
-	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
 	select NEED_KUSER_HELPERS
 	select TLS_REG_EMUL if SMP || !MMU
 
@@ -805,14 +801,6 @@ config TLS_REG_EMUL
 	  a few prototypes like that in existence) and therefore access to
 	  that required register must be emulated.
 
-config NEEDS_SYSCALL_FOR_CMPXCHG
-	bool
-	select NEED_KUSER_HELPERS
-	help
-	  SMP on a pre-ARMv6 processor?  Well OK then.
-	  Forget about fast user space cmpxchg support.
-	  It is just not possible.
-
 config NEED_KUSER_HELPERS
 	bool
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index 1a7815e5421b..ad4eb2d26e16 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -1407,12 +1407,19 @@ static int arm_iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma,
 	unsigned long uaddr = vma->vm_start;
 	unsigned long usize = vma->vm_end - vma->vm_start;
 	struct page **pages = __iommu_get_pages(cpu_addr, attrs);
+	unsigned long nr_pages = PAGE_ALIGN(size) >> PAGE_SHIFT;
+	unsigned long off = vma->vm_pgoff;
 
 	vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot);
 
 	if (!pages)
 		return -ENXIO;
 
+	if (off >= nr_pages || (usize >> PAGE_SHIFT) > nr_pages - off)
+		return -ENXIO;
+
+	pages += off;
+
 	do {
 		int ret = vm_insert_page(vma, uaddr, *pages++);
 		if (ret) {
diff --git a/arch/arm/mm/fault.c b/arch/arm/mm/fault.c
index 0d629b8f973f..daafcf121ce0 100644
--- a/arch/arm/mm/fault.c
+++ b/arch/arm/mm/fault.c
@@ -593,6 +593,28 @@ do_PrefetchAbort(unsigned long addr, unsigned int ifsr, struct pt_regs *regs)
 	arm_notify_die("", regs, &info, ifsr, 0);
 }
 
+/*
+ * Abort handler to be used only during first unmasking of asynchronous aborts
+ * on the boot CPU. This makes sure that the machine will not die if the
+ * firmware/bootloader left an imprecise abort pending for us to trip over.
+ */
+static int __init early_abort_handler(unsigned long addr, unsigned int fsr,
+				      struct pt_regs *regs)
+{
+	pr_warn("Hit pending asynchronous external abort (FSR=0x%08x) during "
+		"first unmask, this is most likely caused by a "
+		"firmware/bootloader bug.\n", fsr);
+
+	return 0;
+}
+
+void __init early_abt_enable(void)
+{
+	fsr_info[22].fn = early_abort_handler;
+	local_abt_enable();
+	fsr_info[22].fn = do_bad;
+}
+
 #ifndef CONFIG_ARM_LPAE
 static int __init exceptions_init(void)
 {
diff --git a/arch/arm/mm/fault.h b/arch/arm/mm/fault.h
index cf08bdfbe0d6..05ec5e0df32d 100644
--- a/arch/arm/mm/fault.h
+++ b/arch/arm/mm/fault.h
@@ -24,5 +24,6 @@ static inline int fsr_fs(unsigned int fsr)
 
 void do_bad_area(unsigned long addr, unsigned int fsr, struct pt_regs *regs);
 unsigned long search_exception_table(unsigned long addr);
+void early_abt_enable(void);
 
 #endif	/* __ARCH_ARM_FAULT_H */
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 7cd15143a507..4867f5daf82c 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -38,6 +38,7 @@
 #include <asm/mach/pci.h>
 #include <asm/fixmap.h>
 
+#include "fault.h"
 #include "mm.h"
 #include "tcm.h"
 
@@ -1363,6 +1364,9 @@ static void __init devicemaps_init(const struct machine_desc *mdesc)
 	 */
 	local_flush_tlb_all();
 	flush_cache_all();
+
+	/* Enable asynchronous aborts */
+	early_abt_enable();
 }
 
 static void __init kmap_init(void)
diff --git a/arch/arm/vdso/vdsomunge.c b/arch/arm/vdso/vdsomunge.c
index 0cebd98cd88c..f6455273b2f8 100644
--- a/arch/arm/vdso/vdsomunge.c
+++ b/arch/arm/vdso/vdsomunge.c
@@ -66,7 +66,7 @@
 	((((x) & 0x000000ff) << 24) | \
 	 (((x) & 0x0000ff00) <<  8) | \
 	 (((x) & 0x00ff0000) >>  8) | \
-	 (((x) & 0xff000000) << 24))
+	 (((x) & 0xff000000) >> 24))
 
 #if __BYTE_ORDER__ == __ORDER_LITTLE_ENDIAN__
 #define HOST_ORDER ELFDATA2LSB
diff --git a/include/linux/amba/bus.h b/include/linux/amba/bus.h
index 50fc66868402..9006c4e75cf7 100644
--- a/include/linux/amba/bus.h
+++ b/include/linux/amba/bus.h
@@ -41,8 +41,6 @@ struct amba_driver {
 	int			(*probe)(struct amba_device *, const struct amba_id *);
 	int			(*remove)(struct amba_device *);
 	void			(*shutdown)(struct amba_device *);
-	int			(*suspend)(struct amba_device *, pm_message_t);
-	int			(*resume)(struct amba_device *);
 	const struct amba_id	*id_table;
 };
 
diff --git a/lib/nmi_backtrace.c b/lib/nmi_backtrace.c
index 88d3d32e5923..6019c53c669e 100644
--- a/lib/nmi_backtrace.c
+++ b/lib/nmi_backtrace.c
@@ -43,6 +43,12 @@ static void print_seq_line(struct nmi_seq_buf *s, int start, int end)
 	printk("%.*s", (end - start) + 1, buf);
 }
 
+/*
+ * When raise() is called it will be is passed a pointer to the
+ * backtrace_mask. Architectures that call nmi_cpu_backtrace()
+ * directly from their raise() functions may rely on the mask
+ * they are passed being updated as a side effect of this call.
+ */
 void nmi_trigger_all_cpu_backtrace(bool include_self,
 				   void (*raise)(cpumask_t *mask))
 {
@@ -149,7 +155,10 @@ bool nmi_cpu_backtrace(struct pt_regs *regs)
 		/* Replace printk to write into the NMI seq */
 		this_cpu_write(printk_func, nmi_vprintk);
 		pr_warn("NMI backtrace for cpu %d\n", cpu);
-		show_regs(regs);
+		if (regs)
+			show_regs(regs);
+		else
+			dump_stack();
 		this_cpu_write(printk_func, printk_func_save);
 
 		cpumask_clear_cpu(cpu, to_cpumask(backtrace_mask));