Merge branch 'for-linus' of git://git.linaro.org/people/rmk/linux-arm

Pull ARM updates from Russell King:
 "Included in this series are:

   1. BE8 (modern big endian) changes for ARM from Ben Dooks
   2. big.Little support from Nicolas Pitre and Dave Martin
   3. support for LPAE systems with all system memory above 4GB
   4. Perf updates from Will Deacon
   5. Additional prefetching and other performance improvements from Will.
   6. Neon-optimised AES implementation fro Ard.
   7. A number of smaller fixes scattered around the place.

  There is a rather horrid merge conflict in tools/perf - I was never
  notified of the conflict because it originally occurred between Will's
  tree and other stuff.  Consequently I have a resolution which Will
  forwarded me, which I'll forward on immediately after sending this
  mail.

  The other notable thing is I'm expecting some build breakage in the
  crypto stuff on ARM only with Ard's AES patches.  These were merged
  into a stable git branch which others had already pulled, so there's
  little I can do about this.  The problem is caused because these
  patches have a dependency on some code in the crypto git tree - I
  tried requesting a branch I can pull to resolve these, and all I got
  each time from the crypto people was "we'll revert our patches then"
  which would only make things worse since I still don't have the
  dependent patches.  I've no idea what's going on there or how to
  resolve that, and since I can't split these patches from the rest of
  this pull request, I'm rather stuck with pushing this as-is or
  reverting Ard's patches.

  Since it should "come out in the wash" I've left them in - the only
  build problems they seem to cause at the moment are with randconfigs,
  and since it's a new feature anyway.  However, if by -rc1 the
  dependencies aren't in, I think it'd be best to revert Ard's patches"

I resolved the perf conflict roughly as per the patch sent by Russell,
but there may be some differences.  Any errors are likely mine.  Let's
see how the crypto issues work out..

* 'for-linus' of git://git.linaro.org/people/rmk/linux-arm: (110 commits)
  ARM: 7868/1: arm/arm64: remove atomic_clear_mask() in "include/asm/atomic.h"
  ARM: 7867/1: include: asm: use 'int' instead of 'unsigned long' for 'oldval' in atomic_cmpxchg().
  ARM: 7866/1: include: asm: use 'long long' instead of 'u64' within atomic.h
  ARM: 7871/1: amba: Extend number of IRQS
  ARM: 7887/1: Don't smp_cross_call() on UP devices in arch_irq_work_raise()
  ARM: 7872/1: Support arch_irq_work_raise() via self IPIs
  ARM: 7880/1: Clear the IT state independent of the Thumb-2 mode
  ARM: 7878/1: nommu: Implement dummy early_paging_init()
  ARM: 7876/1: clear Thumb-2 IT state on exception handling
  ARM: 7874/2: bL_switcher: Remove cpu_hotplug_driver_{lock,unlock}()
  ARM: footbridge: fix build warnings for netwinder
  ARM: 7873/1: vfp: clear vfp_current_hw_state for dying cpu
  ARM: fix misplaced arch_virt_to_idmap()
  ARM: 7848/1: mcpm: Implement cpu_kill() to synchronise on powerdown
  ARM: 7847/1: mcpm: Factor out logical-to-physical CPU translation
  ARM: 7869/1: remove unused XSCALE_PMU Kconfig param
  ARM: 7864/1: Handle 64-bit memory in case of 32-bit phys_addr_t
  ARM: 7863/1: Let arm_add_memory() always use 64-bit arguments
  ARM: 7862/1: pcpu: replace __get_cpu_var_uses
  ARM: 7861/1: cacheflush: consolidate single-CPU ARMv7 cache disabling code
  ...

21 files changed, 389 insertions, 143 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 5140df5f23aa..a30fc9be9e9e 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -17,7 +17,8 @@ CFLAGS_REMOVE_return_address.o = -pg
 
 obj-y		:= elf.o entry-common.o irq.o opcodes.o \
 		   process.o ptrace.o return_address.o \
-		   setup.o signal.o stacktrace.o sys_arm.o time.o traps.o
+		   setup.o signal.o sigreturn_codes.o \
+		   stacktrace.o sys_arm.o time.o traps.o
 
 obj-$(CONFIG_ATAGS)		+= atags_parse.o
 obj-$(CONFIG_ATAGS_PROC)	+= atags_proc.o
@@ -78,6 +79,7 @@ obj-$(CONFIG_CPU_XSC3)		+= xscale-cp0.o
 obj-$(CONFIG_CPU_MOHAWK)	+= xscale-cp0.o
 obj-$(CONFIG_CPU_PJ4)		+= pj4-cp0.o
 obj-$(CONFIG_IWMMXT)		+= iwmmxt.o
+obj-$(CONFIG_PERF_EVENTS)	+= perf_regs.o
 obj-$(CONFIG_HW_PERF_EVENTS)	+= perf_event.o perf_event_cpu.o
 AFLAGS_iwmmxt.o			:= -Wa,-mcpu=iwmmxt
 obj-$(CONFIG_ARM_CPU_TOPOLOGY)  += topology.o
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 60d3b738d420..1f031ddd0667 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -155,4 +155,5 @@ EXPORT_SYMBOL(__gnu_mcount_nc);
 
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
 EXPORT_SYMBOL(__pv_phys_offset);
+EXPORT_SYMBOL(__pv_offset);
 #endif
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 9cbe70c8b0ef..b3fb8c9e1ff2 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -192,6 +192,7 @@ __dabt_svc:
 	svc_entry
 	mov	r2, sp
 	dabt_helper
+ THUMB(	ldr	r5, [sp, #S_PSR]	)	@ potentially updated CPSR
 	svc_exit r5				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_svc)
@@ -416,9 +417,8 @@ __und_usr:
 	bne	__und_usr_thumb
 	sub	r4, r2, #4			@ ARM instr at LR - 4
 1:	ldrt	r0, [r4]
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r0, r0				@ little endian instruction
-#endif
+ ARM_BE8(rev	r0, r0)				@ little endian instruction
+
 	@ r0 = 32-bit ARM instruction which caused the exception
 	@ r2 = PC value for the following instruction (:= regs->ARM_pc)
 	@ r4 = PC value for the faulting instruction
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index bc6bd9683ba4..a2dcafdf1bc8 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -393,9 +393,7 @@ ENTRY(vector_swi)
 #else
  USER(	ldr	r10, [lr, #-4]		)	@ get SWI instruction
 #endif
-#ifdef CONFIG_CPU_ENDIAN_BE8
-	rev	r10, r10			@ little endian instruction
-#endif
+ ARM_BE8(rev	r10, r10)			@ little endian instruction
 
 #elif defined(CONFIG_AEABI)
 
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 476de57dcef2..7801866e626a 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -77,6 +77,7 @@
 
 	__HEAD
 ENTRY(stext)
+ ARM_BE8(setend	be )			@ ensure we are in BE8 mode
 
  THUMB(	adr	r9, BSYM(1f)	)	@ Kernel is always entered in ARM.
  THUMB(	bx	r9		)	@ If this is a Thumb-2 kernel,
@@ -352,6 +353,9 @@ ENTRY(secondary_startup)
 	 * the processor type - there is no need to check the machine type
 	 * as it has already been validated by the primary processor.
 	 */
+
+ ARM_BE8(setend	be)				@ ensure we are in BE8 mode
+
 #ifdef CONFIG_ARM_VIRT_EXT
 	bl	__hyp_stub_install_secondary
 #endif
@@ -555,6 +559,14 @@ ENTRY(fixup_smp)
 	ldmfd	sp!, {r4 - r6, pc}
 ENDPROC(fixup_smp)
 
+#ifdef __ARMEB__
+#define LOW_OFFSET	0x4
+#define HIGH_OFFSET	0x0
+#else
+#define LOW_OFFSET	0x0
+#define HIGH_OFFSET	0x4
+#endif
+
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
 
 /* __fixup_pv_table - patch the stub instructions with the delta between
@@ -565,17 +577,20 @@ ENDPROC(fixup_smp)
 	__HEAD
 __fixup_pv_table:
 	adr	r0, 1f
-	ldmia	r0, {r3-r5, r7}
-	sub	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
+	ldmia	r0, {r3-r7}
+	mvn	ip, #0
+	subs	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
 	add	r4, r4, r3	@ adjust table start address
 	add	r5, r5, r3	@ adjust table end address
-	add	r7, r7, r3	@ adjust __pv_phys_offset address
-	str	r8, [r7]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	add	r6, r6, r3	@ adjust __pv_phys_offset address
+	add	r7, r7, r3	@ adjust __pv_offset address
+	str	r8, [r6, #LOW_OFFSET]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	strcc	ip, [r7, #HIGH_OFFSET]	@ save to __pv_offset high bits
 	mov	r6, r3, lsr #24	@ constant for add/sub instructions
 	teq	r3, r6, lsl #24 @ must be 16MiB aligned
 THUMB(	it	ne		@ cross section branch )
 	bne	__error
-	str	r6, [r7, #4]	@ save to __pv_offset
+	str	r3, [r7, #LOW_OFFSET]	@ save to __pv_offset low bits
 	b	__fixup_a_pv_table
 ENDPROC(__fixup_pv_table)
 
@@ -584,10 +599,19 @@ ENDPROC(__fixup_pv_table)
 	.long	__pv_table_begin
 	.long	__pv_table_end
 2:	.long	__pv_phys_offset
+	.long	__pv_offset
 
 	.text
 __fixup_a_pv_table:
+	adr	r0, 3f
+	ldr	r6, [r0]
+	add	r6, r6, r3
+	ldr	r0, [r6, #HIGH_OFFSET]	@ pv_offset high word
+	ldr	r6, [r6, #LOW_OFFSET]	@ pv_offset low word
+	mov	r6, r6, lsr #24
+	cmn	r0, #1
 #ifdef CONFIG_THUMB2_KERNEL
+	moveq	r0, #0x200000	@ set bit 21, mov to mvn instruction
 	lsls	r6, #24
 	beq	2f
 	clz	r7, r6
@@ -601,18 +625,42 @@ __fixup_a_pv_table:
 	b	2f
 1:	add     r7, r3
 	ldrh	ip, [r7, #2]
-	and	ip, 0x8f00
-	orr	ip, r6	@ mask in offset bits 31-24
+ARM_BE8(rev16	ip, ip)
+	tst	ip, #0x4000
+	and	ip, #0x8f00
+	orrne	ip, r6	@ mask in offset bits 31-24
+	orreq	ip, r0	@ mask in offset bits 7-0
+ARM_BE8(rev16	ip, ip)
 	strh	ip, [r7, #2]
+	bne	2f
+	ldrh	ip, [r7]
+ARM_BE8(rev16	ip, ip)
+	bic	ip, #0x20
+	orr	ip, ip, r0, lsr #16
+ARM_BE8(rev16	ip, ip)
+	strh	ip, [r7]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
 	bcc	1b
 	bx	lr
 #else
+	moveq	r0, #0x400000	@ set bit 22, mov to mvn instruction
 	b	2f
 1:	ldr	ip, [r7, r3]
+#ifdef CONFIG_CPU_ENDIAN_BE8
+	@ in BE8, we load data in BE, but instructions still in LE
+	bic	ip, ip, #0xff000000
+	tst	ip, #0x000f0000	@ check the rotation field
+	orrne	ip, ip, r6, lsl #24 @ mask in offset bits 31-24
+	biceq	ip, ip, #0x00004000 @ clear bit 22
+	orreq	ip, ip, r0, lsl #24 @ mask in offset bits 7-0
+#else
 	bic	ip, ip, #0x000000ff
-	orr	ip, ip, r6	@ mask in offset bits 31-24
+	tst	ip, #0xf00	@ check the rotation field
+	orrne	ip, ip, r6	@ mask in offset bits 31-24
+	biceq	ip, ip, #0x400000	@ clear bit 22
+	orreq	ip, ip, r0	@ mask in offset bits 7-0
+#endif
 	str	ip, [r7, r3]
 2:	cmp	r4, r5
 	ldrcc	r7, [r4], #4	@ use branch for delay slot
@@ -621,28 +669,30 @@ __fixup_a_pv_table:
 #endif
 ENDPROC(__fixup_a_pv_table)
 
+	.align
+3:	.long __pv_offset
+
 ENTRY(fixup_pv_table)
 	stmfd	sp!, {r4 - r7, lr}
-	ldr	r2, 2f			@ get address of __pv_phys_offset
 	mov	r3, #0			@ no offset
 	mov	r4, r0			@ r0 = table start
 	add	r5, r0, r1		@ r1 = table size
-	ldr	r6, [r2, #4]		@ get __pv_offset
 	bl	__fixup_a_pv_table
 	ldmfd	sp!, {r4 - r7, pc}
 ENDPROC(fixup_pv_table)
 
-	.align
-2:	.long	__pv_phys_offset
-
 	.data
 	.globl	__pv_phys_offset
 	.type	__pv_phys_offset, %object
 __pv_phys_offset:
-	.long	0
-	.size	__pv_phys_offset, . - __pv_phys_offset
+	.quad	0
+	.size	__pv_phys_offset, . -__pv_phys_offset
+
+	.globl	__pv_offset
+	.type	__pv_offset, %object
 __pv_offset:
-	.long	0
+	.quad	0
+	.size	__pv_offset, . -__pv_offset
 #endif
 
 #include "head-common.S"
diff --git a/arch/arm/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 7b95de601357..3d446605cbf8 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -344,13 +344,13 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		/* Breakpoint */
 		ctrl_base = ARM_BASE_BCR;
 		val_base = ARM_BASE_BVR;
-		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
 		ctrl_base = ARM_BASE_WCR;
 		val_base = ARM_BASE_WVR;
-		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -396,12 +396,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		base = ARM_BASE_BCR;
-		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
 		base = ARM_BASE_WCR;
-		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -697,7 +697,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+	slots = this_cpu_ptr(wp_on_reg);
 
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
@@ -768,7 +768,7 @@ static void watchpoint_single_step_handler(unsigned long pc)
 	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
 
-	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+	slots = this_cpu_ptr(wp_on_reg);
 
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
@@ -802,7 +802,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+	slots = this_cpu_ptr(bp_on_reg);
 
 	/* The exception entry code places the amended lr in the PC. */
 	addr = regs->ARM_pc;
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 170e9f34003f..a7b621ece23d 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -171,13 +171,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
 static void __kprobes set_current_kprobe(struct kprobe *p)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static void __kprobes
@@ -421,10 +421,10 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			continue;
 
 		if (ri->rp && ri->rp->handler) {
-			__get_cpu_var(current_kprobe) = &ri->rp->kp;
+			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
 			ri->rp->handler(ri, regs);
-			__get_cpu_var(current_kprobe) = NULL;
+			__this_cpu_write(current_kprobe, NULL);
 		}
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index c9dfff3b8008..45e478157278 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -24,6 +24,7 @@
 #include <asm/sections.h>
 #include <asm/smp_plat.h>
 #include <asm/unwind.h>
+#include <asm/opcodes.h>
 
 #ifdef CONFIG_XIP_KERNEL
 /*
@@ -60,6 +61,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 		Elf32_Sym *sym;
 		const char *symname;
 		s32 offset;
+		u32 tmp;
 #ifdef CONFIG_THUMB2_KERNEL
 		u32 upper, lower, sign, j1, j2;
 #endif
@@ -95,7 +97,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 		case R_ARM_PC24:
 		case R_ARM_CALL:
 		case R_ARM_JUMP24:
-			offset = (*(u32 *)loc & 0x00ffffff) << 2;
+			offset = __mem_to_opcode_arm(*(u32 *)loc);
+			offset = (offset & 0x00ffffff) << 2;
 			if (offset & 0x02000000)
 				offset -= 0x04000000;
 
@@ -111,9 +114,10 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			}
 
 			offset >>= 2;
+			offset &= 0x00ffffff;
 
-			*(u32 *)loc &= 0xff000000;
-			*(u32 *)loc |= offset & 0x00ffffff;
+			*(u32 *)loc &= __opcode_to_mem_arm(0xff000000);
+			*(u32 *)loc |= __opcode_to_mem_arm(offset);
 			break;
 
 	       case R_ARM_V4BX:
@@ -121,8 +125,8 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			* other bits to re-code instruction as
 			* MOV PC,Rm.
 			*/
-		       *(u32 *)loc &= 0xf000000f;
-		       *(u32 *)loc |= 0x01a0f000;
+		       *(u32 *)loc &= __opcode_to_mem_arm(0xf000000f);
+		       *(u32 *)loc |= __opcode_to_mem_arm(0x01a0f000);
 		       break;
 
 		case R_ARM_PREL31:
@@ -132,7 +136,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 
 		case R_ARM_MOVW_ABS_NC:
 		case R_ARM_MOVT_ABS:
-			offset = *(u32 *)loc;
+			offset = tmp = __mem_to_opcode_arm(*(u32 *)loc);
 			offset = ((offset & 0xf0000) >> 4) | (offset & 0xfff);
 			offset = (offset ^ 0x8000) - 0x8000;
 
@@ -140,16 +144,18 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (ELF32_R_TYPE(rel->r_info) == R_ARM_MOVT_ABS)
 				offset >>= 16;
 
-			*(u32 *)loc &= 0xfff0f000;
-			*(u32 *)loc |= ((offset & 0xf000) << 4) |
-					(offset & 0x0fff);
+			tmp &= 0xfff0f000;
+			tmp |= ((offset & 0xf000) << 4) |
+				(offset & 0x0fff);
+
+			*(u32 *)loc = __opcode_to_mem_arm(tmp);
 			break;
 
 #ifdef CONFIG_THUMB2_KERNEL
 		case R_ARM_THM_CALL:
 		case R_ARM_THM_JUMP24:
-			upper = *(u16 *)loc;
-			lower = *(u16 *)(loc + 2);
+			upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+			lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
 			/*
 			 * 25 bit signed address range (Thumb-2 BL and B.W
@@ -198,17 +204,20 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			sign = (offset >> 24) & 1;
 			j1 = sign ^ (~(offset >> 23) & 1);
 			j2 = sign ^ (~(offset >> 22) & 1);
-			*(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
+			upper = (u16)((upper & 0xf800) | (sign << 10) |
 					    ((offset >> 12) & 0x03ff));
-			*(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
-						  (j1 << 13) | (j2 << 11) |
-						  ((offset >> 1) & 0x07ff));
+			lower = (u16)((lower & 0xd000) |
+				      (j1 << 13) | (j2 << 11) |
+				      ((offset >> 1) & 0x07ff));
+
+			*(u16 *)loc = __opcode_to_mem_thumb16(upper);
+			*(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
 			break;
 
 		case R_ARM_THM_MOVW_ABS_NC:
 		case R_ARM_THM_MOVT_ABS:
-			upper = *(u16 *)loc;
-			lower = *(u16 *)(loc + 2);
+			upper = __mem_to_opcode_thumb16(*(u16 *)loc);
+			lower = __mem_to_opcode_thumb16(*(u16 *)(loc + 2));
 
 			/*
 			 * MOVT/MOVW instructions encoding in Thumb-2:
@@ -229,12 +238,14 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			if (ELF32_R_TYPE(rel->r_info) == R_ARM_THM_MOVT_ABS)
 				offset >>= 16;
 
-			*(u16 *)loc = (u16)((upper & 0xfbf0) |
-					    ((offset & 0xf000) >> 12) |
-					    ((offset & 0x0800) >> 1));
-			*(u16 *)(loc + 2) = (u16)((lower & 0x8f00) |
-						  ((offset & 0x0700) << 4) |
-						  (offset & 0x00ff));
+			upper = (u16)((upper & 0xfbf0) |
+				      ((offset & 0xf000) >> 12) |
+				      ((offset & 0x0800) >> 1));
+			lower = (u16)((lower & 0x8f00) |
+				      ((offset & 0x0700) << 4) |
+				      (offset & 0x00ff));
+			*(u16 *)loc = __opcode_to_mem_thumb16(upper);
+			*(u16 *)(loc + 2) = __opcode_to_mem_thumb16(lower);
 			break;
 #endif
 
diff --git a/arch/arm/kernel/perf_event.c b/arch/arm/kernel/perf_event.c
index e186ee1e63f6..bc3f2efa0d86 100644
--- a/arch/arm/kernel/perf_event.c
+++ b/arch/arm/kernel/perf_event.c
@@ -256,12 +256,11 @@ validate_event(struct pmu_hw_events *hw_events,
 	       struct perf_event *event)
 {
 	struct arm_pmu *armpmu = to_arm_pmu(event->pmu);
-	struct pmu *leader_pmu = event->group_leader->pmu;
 
 	if (is_software_event(event))
 		return 1;
 
-	if (event->pmu != leader_pmu || event->state < PERF_EVENT_STATE_OFF)
+	if (event->state < PERF_EVENT_STATE_OFF)
 		return 1;
 
 	if (event->state == PERF_EVENT_STATE_OFF && !event->attr.enable_on_exec)
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 8d6147b2001f..d85055cd24ba 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 
 static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
 {
-	return &__get_cpu_var(cpu_hw_events);
+	return this_cpu_ptr(&cpu_hw_events);
 }
 
 static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
diff --git a/arch/arm/kernel/perf_regs.c b/arch/arm/kernel/perf_regs.c
new file mode 100644
index 000000000000..6e4379c67cbc
--- /dev/null
+++ b/arch/arm/kernel/perf_regs.c
@@ -0,0 +1,30 @@
+
+#include <linux/errno.h>
+#include <linux/kernel.h>
+#include <linux/perf_event.h>
+#include <linux/bug.h>
+#include <asm/perf_regs.h>
+#include <asm/ptrace.h>
+
+u64 perf_reg_value(struct pt_regs *regs, int idx)
+{
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM_MAX))
+		return 0;
+
+	return regs->uregs[idx];
+}
+
+#define REG_RESERVED (~((1ULL << PERF_REG_ARM_MAX) - 1))
+
+int perf_reg_validate(u64 mask)
+{
+	if (!mask || mask & REG_RESERVED)
+		return -EINVAL;
+
+	return 0;
+}
+
+u64 perf_reg_abi(struct task_struct *task)
+{
+	return PERF_SAMPLE_REGS_ABI_32;
+}
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 5d65438685d8..6a1b8a81b1ae 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -73,6 +73,8 @@ __setup("fpe=", fpe_setup);
 #endif
 
 extern void paging_init(const struct machine_desc *desc);
+extern void early_paging_init(const struct machine_desc *,
+			      struct proc_info_list *);
 extern void sanity_check_meminfo(void);
 extern enum reboot_mode reboot_mode;
 extern void setup_dma_zone(const struct machine_desc *desc);
@@ -599,6 +601,8 @@ static void __init setup_processor(void)
 	elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
 #endif
 
+	erratum_a15_798181_init();
+
 	feat_v6_fixup();
 
 	cacheid_init();
@@ -619,9 +623,10 @@ void __init dump_machine_table(void)
 		/* can't use cpu_relax() here as it may require MMU setup */;
 }
 
-int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
+int __init arm_add_memory(u64 start, u64 size)
 {
 	struct membank *bank = &meminfo.bank[meminfo.nr_banks];
+	u64 aligned_start;
 
 	if (meminfo.nr_banks >= NR_BANKS) {
 		printk(KERN_CRIT "NR_BANKS too low, "
@@ -634,10 +639,16 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 	 * Size is appropriately rounded down, start is rounded up.
 	 */
 	size -= start & ~PAGE_MASK;
-	bank->start = PAGE_ALIGN(start);
+	aligned_start = PAGE_ALIGN(start);
 
-#ifndef CONFIG_ARM_LPAE
-	if (bank->start + size < bank->start) {
+#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
+	if (aligned_start > ULONG_MAX) {
+		printk(KERN_CRIT "Ignoring memory at 0x%08llx outside "
+		       "32-bit physical address space\n", (long long)start);
+		return -EINVAL;
+	}
+
+	if (aligned_start + size > ULONG_MAX) {
 		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
 			"32-bit physical address space\n", (long long)start);
 		/*
@@ -645,10 +656,11 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 		 * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
 		 * This means we lose a page after masking.
 		 */
-		size = ULONG_MAX - bank->start;
+		size = ULONG_MAX - aligned_start;
 	}
 #endif
 
+	bank->start = aligned_start;
 	bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
 
 	/*
@@ -669,8 +681,8 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 static int __init early_mem(char *p)
 {
 	static int usermem __initdata = 0;
-	phys_addr_t size;
-	phys_addr_t start;
+	u64 size;
+	u64 start;
 	char *endp;
 
 	/*
@@ -878,6 +890,8 @@ void __init setup_arch(char **cmdline_p)
 	parse_early_param();
 
 	sort(&meminfo.bank, meminfo.nr_banks, sizeof(meminfo.bank[0]), meminfo_cmp, NULL);
+
+	early_paging_init(mdesc, lookup_processor_type(read_cpuid_id()));
 	sanity_check_meminfo();
 	arm_memblock_init(&meminfo, mdesc);
 
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index ab3304225272..04d63880037f 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -21,29 +21,7 @@
 #include <asm/unistd.h>
 #include <asm/vfp.h>
 
-/*
- * For ARM syscalls, we encode the syscall number into the instruction.
- */
-#define SWI_SYS_SIGRETURN	(0xef000000|(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE))
-#define SWI_SYS_RT_SIGRETURN	(0xef000000|(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE))
-
-/*
- * With EABI, the syscall number has to be loaded into r7.
- */
-#define MOV_R7_NR_SIGRETURN	(0xe3a07000 | (__NR_sigreturn - __NR_SYSCALL_BASE))
-#define MOV_R7_NR_RT_SIGRETURN	(0xe3a07000 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
-
-/*
- * For Thumb syscalls, we pass the syscall number via r7.  We therefore
- * need two 16-bit instructions.
- */
-#define SWI_THUMB_SIGRETURN	(0xdf00 << 16 | 0x2700 | (__NR_sigreturn - __NR_SYSCALL_BASE))
-#define SWI_THUMB_RT_SIGRETURN	(0xdf00 << 16 | 0x2700 | (__NR_rt_sigreturn - __NR_SYSCALL_BASE))
-
-static const unsigned long sigreturn_codes[7] = {
-	MOV_R7_NR_SIGRETURN,    SWI_SYS_SIGRETURN,    SWI_THUMB_SIGRETURN,
-	MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN,
-};
+extern const unsigned long sigreturn_codes[7];
 
 static unsigned long signal_return_offset;
 
@@ -375,12 +353,18 @@ setup_return(struct pt_regs *regs, struct ksignal *ksig,
 		 */
 		thumb = handler & 1;
 
-		if (thumb) {
-			cpsr |= PSR_T_BIT;
 #if __LINUX_ARM_ARCH__ >= 7
-			/* clear the If-Then Thumb-2 execution state */
-			cpsr &= ~PSR_IT_MASK;
+		/*
+		 * Clear the If-Then Thumb-2 execution state
+		 * ARM spec requires this to be all 000s in ARM mode
+		 * Snapdragon S4/Krait misbehaves on a Thumb=>ARM
+		 * signal transition without this.
+		 */
+		cpsr &= ~PSR_IT_MASK;
 #endif
+
+		if (thumb) {
+			cpsr |= PSR_T_BIT;
 		} else
 			cpsr &= ~PSR_T_BIT;
 	}
diff --git a/arch/arm/kernel/sigreturn_codes.S b/arch/arm/kernel/sigreturn_codes.S
new file mode 100644
index 000000000000..3c5d0f2170fd
--- /dev/null
+++ b/arch/arm/kernel/sigreturn_codes.S
@@ -0,0 +1,80 @@
+/*
+ * sigreturn_codes.S - code sinpets for sigreturn syscalls
+ *
+ * Created by:	Victor Kamensky, 2013-08-13
+ * Copyright:	(C) 2013  Linaro Limited
+ *
+ * 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.
+ */
+
+#include <asm/unistd.h>
+
+/*
+ * For ARM syscalls, we encode the syscall number into the instruction.
+ * With EABI, the syscall number has to be loaded into r7. As result
+ * ARM syscall sequence snippet will have move and svc in .arm encoding
+ *
+ * For Thumb syscalls, we pass the syscall number via r7.  We therefore
+ * need two 16-bit instructions in .thumb encoding
+ *
+ * Please note sigreturn_codes code are not executed in place. Instead
+ * they just copied by kernel into appropriate places. Code inside of
+ * arch/arm/kernel/signal.c is very sensitive to layout of these code
+ * snippets.
+ */
+
+#if __LINUX_ARM_ARCH__ <= 4
+	/*
+	 * Note we manually set minimally required arch that supports
+	 * required thumb opcodes for early arch versions. It is OK
+	 * for this file to be used in combination with other
+	 * lower arch variants, since these code snippets are only
+	 * used as input data.
+	 */
+	.arch armv4t
+#endif
+
+	.section .rodata
+	.global sigreturn_codes
+	.type	sigreturn_codes, #object
+
+	.arm
+
+sigreturn_codes:
+
+	/* ARM sigreturn syscall code snippet */
+	mov	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
+	swi	#(__NR_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+
+	/* Thumb sigreturn syscall code snippet */
+	.thumb
+	movs	r7, #(__NR_sigreturn - __NR_SYSCALL_BASE)
+	swi	#0
+
+	/* ARM sigreturn_rt syscall code snippet */
+	.arm
+	mov	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
+	swi	#(__NR_rt_sigreturn)|(__NR_OABI_SYSCALL_BASE)
+
+	/* Thumb sigreturn_rt syscall code snippet */
+	.thumb
+	movs	r7, #(__NR_rt_sigreturn - __NR_SYSCALL_BASE)
+	swi	#0
+
+	/*
+	 * Note on addtional space: setup_return in signal.c
+	 * algorithm uses two words copy regardless whether
+	 * it is thumb case or not, so we need additional
+	 * word after real last entry.
+	 */
+	.arm
+	.space	4
+
+	.size	sigreturn_codes, . - sigreturn_codes
diff --git a/arch/arm/kernel/sleep.S b/arch/arm/kernel/sleep.S
index db1536b8b30b..b907d9b790ab 100644
--- a/arch/arm/kernel/sleep.S
+++ b/arch/arm/kernel/sleep.S
@@ -55,6 +55,7 @@
  * specific registers and some other data for resume.
  *  r0 = suspend function arg0
  *  r1 = suspend function
+ *  r2 = MPIDR value the resuming CPU will use
  */
 ENTRY(__cpu_suspend)
 	stmfd	sp!, {r4 - r11, lr}
@@ -67,23 +68,18 @@ ENTRY(__cpu_suspend)
 	mov	r5, sp			@ current virtual SP
 	add	r4, r4, #12		@ Space for pgd, virt sp, phys resume fn
 	sub	sp, sp, r4		@ allocate CPU state on stack
-	stmfd	sp!, {r0, r1}		@ save suspend func arg and pointer
-	add	r0, sp, #8		@ save pointer to save block
-	mov	r1, r4			@ size of save block
-	mov	r2, r5			@ virtual SP
 	ldr	r3, =sleep_save_sp
+	stmfd	sp!, {r0, r1}		@ save suspend func arg and pointer
 	ldr	r3, [r3, #SLEEP_SAVE_SP_VIRT]
-	ALT_SMP(mrc p15, 0, r9, c0, c0, 5)
-        ALT_UP_B(1f)
-	ldr	r8, =mpidr_hash
-	/*
-	 * This ldmia relies on the memory layout of the mpidr_hash
-	 * struct mpidr_hash.
-	 */
-	ldmia	r8, {r4-r7}	@ r4 = mpidr mask (r5,r6,r7) = l[0,1,2] shifts
-	compute_mpidr_hash	lr, r5, r6, r7, r9, r4
-	add	r3, r3, lr, lsl #2
-1:
+	ALT_SMP(ldr r0, =mpidr_hash)
+	ALT_UP_B(1f)
+	/* This ldmia relies on the memory layout of the mpidr_hash struct */
+	ldmia	r0, {r1, r6-r8}	@ r1 = mpidr mask (r6,r7,r8) = l[0,1,2] shifts
+	compute_mpidr_hash	r0, r6, r7, r8, r2, r1
+	add	r3, r3, r0, lsl #2
+1:	mov	r2, r5			@ virtual SP
+	mov	r1, r4			@ size of save block
+	add	r0, sp, #8		@ pointer to save block
 	bl	__cpu_suspend_save
 	adr	lr, BSYM(cpu_suspend_abort)
 	ldmfd	sp!, {r0, pc}		@ call suspend fn
@@ -130,6 +126,7 @@ ENDPROC(cpu_resume_after_mmu)
 	.data
 	.align
 ENTRY(cpu_resume)
+ARM_BE8(setend be)			@ ensure we are in BE mode
 	mov	r1, #0
 	ALT_SMP(mrc p15, 0, r0, c0, c0, 5)
 	ALT_UP_B(1f)
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 72024ea8a3a6..dc894ab3622b 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -25,6 +25,7 @@
 #include <linux/clockchips.h>
 #include <linux/completion.h>
 #include <linux/cpufreq.h>
+#include <linux/irq_work.h>
 
 #include <linux/atomic.h>
 #include <asm/smp.h>
@@ -66,6 +67,8 @@ enum ipi_msg_type {
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
+	IPI_IRQ_WORK,
+	IPI_COMPLETION,
 };
 
 static DECLARE_COMPLETION(cpu_running);
@@ -80,7 +83,7 @@ void __init smp_set_ops(struct smp_operations *ops)
 
 static unsigned long get_arch_pgd(pgd_t *pgd)
 {
-	phys_addr_t pgdir = virt_to_phys(pgd);
+	phys_addr_t pgdir = virt_to_idmap(pgd);
 	BUG_ON(pgdir & ARCH_PGD_MASK);
 	return pgdir >> ARCH_PGD_SHIFT;
 }
@@ -448,6 +451,14 @@ void arch_send_call_function_single_ipi(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	if (is_smp())
+		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+}
+#endif
+
 static const char *ipi_types[NR_IPI] = {
 #define S(x,s)	[x] = s
 	S(IPI_WAKEUP, "CPU wakeup interrupts"),
@@ -456,6 +467,8 @@ static const char *ipi_types[NR_IPI] = {
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_IRQ_WORK, "IRQ work interrupts"),
+	S(IPI_COMPLETION, "completion interrupts"),
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -515,6 +528,19 @@ static void ipi_cpu_stop(unsigned int cpu)
 		cpu_relax();
 }
 
+static DEFINE_PER_CPU(struct completion *, cpu_completion);
+
+int register_ipi_completion(struct completion *completion, int cpu)
+{
+	per_cpu(cpu_completion, cpu) = completion;
+	return IPI_COMPLETION;
+}
+
+static void ipi_complete(unsigned int cpu)
+{
+	complete(per_cpu(cpu_completion, cpu));
+}
+
 /*
  * Main handler for inter-processor interrupts
  */
@@ -565,6 +591,20 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+#ifdef CONFIG_IRQ_WORK
+	case IPI_IRQ_WORK:
+		irq_enter();
+		irq_work_run();
+		irq_exit();
+		break;
+#endif
+
+	case IPI_COMPLETION:
+		irq_enter();
+		ipi_complete(cpu);
+		irq_exit();
+		break;
+
 	default:
 		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
 		       cpu, ipinr);
diff --git a/arch/arm/kernel/smp_scu.c b/arch/arm/kernel/smp_scu.c
index 5bc1a63284e3..1aafa0d785eb 100644
--- a/arch/arm/kernel/smp_scu.c
+++ b/arch/arm/kernel/smp_scu.c
@@ -28,7 +28,7 @@
  */
 unsigned int __init scu_get_core_count(void __iomem *scu_base)
 {
-	unsigned int ncores = __raw_readl(scu_base + SCU_CONFIG);
+	unsigned int ncores = readl_relaxed(scu_base + SCU_CONFIG);
 	return (ncores & 0x03) + 1;
 }
 
@@ -42,19 +42,19 @@ void scu_enable(void __iomem *scu_base)
 #ifdef CONFIG_ARM_ERRATA_764369
 	/* Cortex-A9 only */
 	if ((read_cpuid_id() & 0xff0ffff0) == 0x410fc090) {
-		scu_ctrl = __raw_readl(scu_base + 0x30);
+		scu_ctrl = readl_relaxed(scu_base + 0x30);
 		if (!(scu_ctrl & 1))
-			__raw_writel(scu_ctrl | 0x1, scu_base + 0x30);
+			writel_relaxed(scu_ctrl | 0x1, scu_base + 0x30);
 	}
 #endif
 
-	scu_ctrl = __raw_readl(scu_base + SCU_CTRL);
+	scu_ctrl = readl_relaxed(scu_base + SCU_CTRL);
 	/* already enabled? */
 	if (scu_ctrl & 1)
 		return;
 
 	scu_ctrl |= 1;
-	__raw_writel(scu_ctrl, scu_base + SCU_CTRL);
+	writel_relaxed(scu_ctrl, scu_base + SCU_CTRL);
 
 	/*
 	 * Ensure that the data accessed by CPU0 before the SCU was
@@ -80,9 +80,9 @@ int scu_power_mode(void __iomem *scu_base, unsigned int mode)
 	if (mode > 3 || mode == 1 || cpu > 3)
 		return -EINVAL;
 
-	val = __raw_readb(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
+	val = readb_relaxed(scu_base + SCU_CPU_STATUS + cpu) & ~0x03;
 	val |= mode;
-	__raw_writeb(val, scu_base + SCU_CPU_STATUS + cpu);
+	writeb_relaxed(val, scu_base + SCU_CPU_STATUS + cpu);
 
 	return 0;
 }
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 83ccca303df8..95d063620b76 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -70,6 +70,40 @@ static inline void ipi_flush_bp_all(void *ignored)
 	local_flush_bp_all();
 }
 
+#ifdef CONFIG_ARM_ERRATA_798181
+bool (*erratum_a15_798181_handler)(void);
+
+static bool erratum_a15_798181_partial(void)
+{
+	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
+	dsb(ish);
+	return false;
+}
+
+static bool erratum_a15_798181_broadcast(void)
+{
+	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
+	dsb(ish);
+	return true;
+}
+
+void erratum_a15_798181_init(void)
+{
+	unsigned int midr = read_cpuid_id();
+	unsigned int revidr = read_cpuid(CPUID_REVIDR);
+
+	/* Cortex-A15 r0p0..r3p2 w/o ECO fix affected */
+	if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2 ||
+	    (revidr & 0x210) == 0x210) {
+		return;
+	}
+	if (revidr & 0x10)
+		erratum_a15_798181_handler = erratum_a15_798181_partial;
+	else
+		erratum_a15_798181_handler = erratum_a15_798181_broadcast;
+}
+#endif
+
 static void ipi_flush_tlb_a15_erratum(void *arg)
 {
 	dmb();
@@ -80,7 +114,6 @@ static void broadcast_tlb_a15_erratum(void)
 	if (!erratum_a15_798181())
 		return;
 
-	dummy_flush_tlb_a15_erratum();
 	smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1);
 }
 
@@ -92,7 +125,6 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 	if (!erratum_a15_798181())
 		return;
 
-	dummy_flush_tlb_a15_erratum();
 	this_cpu = get_cpu();
 	a15_erratum_get_cpumask(this_cpu, mm, &mask);
 	smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index 2985c9f0905d..6591e26fc13f 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -45,7 +45,7 @@ static void twd_set_mode(enum clock_event_mode mode,
 	case CLOCK_EVT_MODE_PERIODIC:
 		ctrl = TWD_TIMER_CONTROL_ENABLE | TWD_TIMER_CONTROL_IT_ENABLE
 			| TWD_TIMER_CONTROL_PERIODIC;
-		__raw_writel(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
+		writel_relaxed(DIV_ROUND_CLOSEST(twd_timer_rate, HZ),
 			twd_base + TWD_TIMER_LOAD);
 		break;
 	case CLOCK_EVT_MODE_ONESHOT:
@@ -58,18 +58,18 @@ static void twd_set_mode(enum clock_event_mode mode,
 		ctrl = 0;
 	}
 
-	__raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+	writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
 }
 
 static int twd_set_next_event(unsigned long evt,
 			struct clock_event_device *unused)
 {
-	unsigned long ctrl = __raw_readl(twd_base + TWD_TIMER_CONTROL);
+	unsigned long ctrl = readl_relaxed(twd_base + TWD_TIMER_CONTROL);
 
 	ctrl |= TWD_TIMER_CONTROL_ENABLE;
 
-	__raw_writel(evt, twd_base + TWD_TIMER_COUNTER);
-	__raw_writel(ctrl, twd_base + TWD_TIMER_CONTROL);
+	writel_relaxed(evt, twd_base + TWD_TIMER_COUNTER);
+	writel_relaxed(ctrl, twd_base + TWD_TIMER_CONTROL);
 
 	return 0;
 }
@@ -82,8 +82,8 @@ static int twd_set_next_event(unsigned long evt,
  */
 static int twd_timer_ack(void)
 {
-	if (__raw_readl(twd_base + TWD_TIMER_INTSTAT)) {
-		__raw_writel(1, twd_base + TWD_TIMER_INTSTAT);
+	if (readl_relaxed(twd_base + TWD_TIMER_INTSTAT)) {
+		writel_relaxed(1, twd_base + TWD_TIMER_INTSTAT);
 		return 1;
 	}
 
@@ -211,15 +211,15 @@ static void twd_calibrate_rate(void)
 		waitjiffies += 5;
 
 				 /* enable, no interrupt or reload */
-		__raw_writel(0x1, twd_base + TWD_TIMER_CONTROL);
+		writel_relaxed(0x1, twd_base + TWD_TIMER_CONTROL);
 
 				 /* maximum value */
-		__raw_writel(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
+		writel_relaxed(0xFFFFFFFFU, twd_base + TWD_TIMER_COUNTER);
 
 		while (get_jiffies_64() < waitjiffies)
 			udelay(10);
 
-		count = __raw_readl(twd_base + TWD_TIMER_COUNTER);
+		count = readl_relaxed(twd_base + TWD_TIMER_COUNTER);
 
 		twd_timer_rate = (0xFFFFFFFFU - count) * (HZ / 5);
 
@@ -277,7 +277,7 @@ static void twd_timer_setup(void)
 	 * bother with the below.
 	 */
 	if (per_cpu(percpu_setup_called, cpu)) {
-		__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
+		writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
 		clockevents_register_device(clk);
 		enable_percpu_irq(clk->irq, 0);
 		return;
@@ -290,7 +290,7 @@ static void twd_timer_setup(void)
 	 * The following is done once per CPU the first time .setup() is
 	 * called.
 	 */
-	__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
+	writel_relaxed(0, twd_base + TWD_TIMER_CONTROL);
 
 	clk->name = "local_timer";
 	clk->features = CLOCK_EVT_FEAT_PERIODIC | CLOCK_EVT_FEAT_ONESHOT |
diff --git a/arch/arm/kernel/suspend.c b/arch/arm/kernel/suspend.c
index 41cf3cbf756d..2835d35234ca 100644
--- a/arch/arm/kernel/suspend.c
+++ b/arch/arm/kernel/suspend.c
@@ -10,7 +10,7 @@
 #include <asm/suspend.h>
 #include <asm/tlbflush.h>
 
-extern int __cpu_suspend(unsigned long, int (*)(unsigned long));
+extern int __cpu_suspend(unsigned long, int (*)(unsigned long), u32 cpuid);
 extern void cpu_resume_mmu(void);
 
 #ifdef CONFIG_MMU
@@ -21,6 +21,7 @@ extern void cpu_resume_mmu(void);
 int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
 	struct mm_struct *mm = current->active_mm;
+	u32 __mpidr = cpu_logical_map(smp_processor_id());
 	int ret;
 
 	if (!idmap_pgd)
@@ -32,7 +33,7 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 	 * resume (indicated by a zero return code), we need to switch
 	 * back to the correct page tables.
 	 */
-	ret = __cpu_suspend(arg, fn);
+	ret = __cpu_suspend(arg, fn, __mpidr);
 	if (ret == 0) {
 		cpu_switch_mm(mm->pgd, mm);
 		local_flush_bp_all();
@@ -44,7 +45,8 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 #else
 int cpu_suspend(unsigned long arg, int (*fn)(unsigned long))
 {
-	return __cpu_suspend(arg, fn);
+	u32 __mpidr = cpu_logical_map(smp_processor_id());
+	return __cpu_suspend(arg, fn, __mpidr);
 }
 #define	idmap_pgd	NULL
 #endif
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 8fcda140358d..6125f259b7b5 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -34,6 +34,7 @@
 #include <asm/unwind.h>
 #include <asm/tls.h>
 #include <asm/system_misc.h>
+#include <asm/opcodes.h>
 
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
 
@@ -341,15 +342,17 @@ void arm_notify_die(const char *str, struct pt_regs *regs,
 int is_valid_bugaddr(unsigned long pc)
 {
 #ifdef CONFIG_THUMB2_KERNEL
-	unsigned short bkpt;
+	u16 bkpt;
+	u16 insn = __opcode_to_mem_thumb16(BUG_INSTR_VALUE);
 #else
-	unsigned long bkpt;
+	u32 bkpt;
+	u32 insn = __opcode_to_mem_arm(BUG_INSTR_VALUE);
 #endif
 
 	if (probe_kernel_address((unsigned *)pc, bkpt))
 		return 0;
 
-	return bkpt == BUG_INSTR_VALUE;
+	return bkpt == insn;
 }
 
 #endif
@@ -402,25 +405,28 @@ asmlinkage void __exception do_undefinstr(struct pt_regs *regs)
 	if (processor_mode(regs) == SVC_MODE) {
 #ifdef CONFIG_THUMB2_KERNEL
 		if (thumb_mode(regs)) {
-			instr = ((u16 *)pc)[0];
+			instr = __mem_to_opcode_thumb16(((u16 *)pc)[0]);
 			if (is_wide_instruction(instr)) {
-				instr <<= 16;
-				instr |= ((u16 *)pc)[1];
+				u16 inst2;
+				inst2 = __mem_to_opcode_thumb16(((u16 *)pc)[1]);
+				instr = __opcode_thumb32_compose(instr, inst2);
 			}
 		} else
 #endif
-			instr = *(u32 *) pc;
+			instr = __mem_to_opcode_arm(*(u32 *) pc);
 	} else if (thumb_mode(regs)) {
 		if (get_user(instr, (u16 __user *)pc))
 			goto die_sig;
+		instr = __mem_to_opcode_thumb16(instr);
 		if (is_wide_instruction(instr)) {
 			unsigned int instr2;
 			if (get_user(instr2, (u16 __user *)pc+1))
 				goto die_sig;
-			instr <<= 16;
-			instr |= instr2;
+			instr2 = __mem_to_opcode_thumb16(instr2);
+			instr = __opcode_thumb32_compose(instr, instr2);
 		}
 	} else if (get_user(instr, (u32 __user *)pc)) {
+		instr = __mem_to_opcode_arm(instr);
 		goto die_sig;
 	}