Merge commit 'v2.6.32-rc3'

28 files changed, 880 insertions, 253 deletions

diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index ff89d0b3abc5..79087dd6d869 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -2,16 +2,19 @@
 # Makefile for the linux kernel.
 #
 
-AFLAGS_head.o := -DTEXT_OFFSET=$(TEXT_OFFSET)
+CPPFLAGS_vmlinux.lds := -DTEXT_OFFSET=$(TEXT_OFFSET)
+AFLAGS_head.o        := -DTEXT_OFFSET=$(TEXT_OFFSET)
 
 ifdef CONFIG_DYNAMIC_FTRACE
 CFLAGS_REMOVE_ftrace.o = -pg
 endif
 
+CFLAGS_REMOVE_return_address.o = -pg
+
 # Object file lists.
 
 obj-y		:= compat.o elf.o entry-armv.o entry-common.o irq.o \
-		   process.o ptrace.o setup.o signal.o \
+		   process.o ptrace.o return_address.o setup.o signal.o \
 		   sys_arm.o stacktrace.o time.o traps.o
 
 obj-$(CONFIG_ISA_DMA_API)	+= dma.o
@@ -32,6 +35,7 @@ obj-$(CONFIG_OABI_COMPAT)	+= sys_oabi-compat.o
 obj-$(CONFIG_ARM_THUMBEE)	+= thumbee.o
 obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
+obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 
 obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
 AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index 531e1860e546..0e627705f746 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -186,4 +186,5 @@ EXPORT_SYMBOL(_find_next_bit_be);
 
 #ifdef CONFIG_FUNCTION_TRACER
 EXPORT_SYMBOL(mcount);
+EXPORT_SYMBOL(__gnu_mcount_nc);
 #endif
diff --git a/arch/arm/kernel/calls.S b/arch/arm/kernel/calls.S
index f776e72a4cb8..fafce1b5c69f 100644
--- a/arch/arm/kernel/calls.S
+++ b/arch/arm/kernel/calls.S
@@ -81,7 +81,7 @@
 		CALL(sys_ni_syscall)		/* was sys_ssetmask */
 /* 70 */	CALL(sys_setreuid16)
 		CALL(sys_setregid16)
-		CALL(sys_sigsuspend_wrapper)
+		CALL(sys_sigsuspend)
 		CALL(sys_sigpending)
 		CALL(sys_sethostname)
 /* 75 */	CALL(sys_setrlimit)
@@ -188,7 +188,7 @@
 		CALL(sys_rt_sigpending)
 		CALL(sys_rt_sigtimedwait)
 		CALL(sys_rt_sigqueueinfo)
-		CALL(sys_rt_sigsuspend_wrapper)
+		CALL(sys_rt_sigsuspend)
 /* 180 */	CALL(ABI(sys_pread64, sys_oabi_pread64))
 		CALL(ABI(sys_pwrite64, sys_oabi_pwrite64))
 		CALL(sys_chown16)
@@ -344,8 +344,8 @@
 		CALL(sys_readlinkat)
 		CALL(sys_fchmodat)
 		CALL(sys_faccessat)
-/* 335 */	CALL(sys_ni_syscall)		/* eventually pselect6 */
-		CALL(sys_ni_syscall)		/* eventually ppoll */
+/* 335 */	CALL(sys_pselect6)
+		CALL(sys_ppoll)
 		CALL(sys_unshare)
 		CALL(sys_set_robust_list)
 		CALL(sys_get_robust_list)
@@ -355,7 +355,7 @@
 		CALL(sys_vmsplice)
 		CALL(sys_move_pages)
 /* 345 */	CALL(sys_getcpu)
-		CALL(sys_ni_syscall)		/* eventually epoll_pwait */
+		CALL(sys_epoll_pwait)
 		CALL(sys_kexec_load)
 		CALL(sys_utimensat)
 		CALL(sys_signalfd)
@@ -373,7 +373,7 @@
 		CALL(sys_preadv)
 		CALL(sys_pwritev)
 		CALL(sys_rt_tgsigqueueinfo)
-		CALL(sys_perf_counter_open)
+		CALL(sys_perf_event_open)
 #ifndef syscalls_counted
 .equ syscalls_padding, ((NR_syscalls + 3) & ~3) - NR_syscalls
 #define syscalls_counted
diff --git a/arch/arm/kernel/crunch.c b/arch/arm/kernel/crunch.c
index 99995c2b2312..769abe15cf91 100644
--- a/arch/arm/kernel/crunch.c
+++ b/arch/arm/kernel/crunch.c
@@ -31,7 +31,7 @@ void crunch_task_release(struct thread_info *thread)
 
 static int crunch_enabled(u32 devcfg)
 {
-	return !!(devcfg & EP93XX_SYSCON_DEVICE_CONFIG_CRUNCH_ENABLE);
+	return !!(devcfg & EP93XX_SYSCON_DEVCFG_CPENA);
 }
 
 static int crunch_do(struct notifier_block *self, unsigned long cmd, void *t)
@@ -56,11 +56,16 @@ static int crunch_do(struct notifier_block *self, unsigned long cmd, void *t)
 		break;
 
 	case THREAD_NOTIFY_SWITCH:
-		devcfg = __raw_readl(EP93XX_SYSCON_DEVICE_CONFIG);
+		devcfg = __raw_readl(EP93XX_SYSCON_DEVCFG);
 		if (crunch_enabled(devcfg) || crunch_owner == crunch_state) {
-			devcfg ^= EP93XX_SYSCON_DEVICE_CONFIG_CRUNCH_ENABLE;
+			/*
+			 * We don't use ep93xx_syscon_swlocked_write() here
+			 * because we are on the context switch path and
+			 * preemption is already disabled.
+			 */
+			devcfg ^= EP93XX_SYSCON_DEVCFG_CPENA;
 			__raw_writel(0xaa, EP93XX_SYSCON_SWLOCK);
-			__raw_writel(devcfg, EP93XX_SYSCON_DEVICE_CONFIG);
+			__raw_writel(devcfg, EP93XX_SYSCON_DEVCFG);
 		}
 		break;
 	}
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index fc8af43c5000..322410be573c 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -34,7 +34,7 @@
 	@
 	@ routine called with r0 = irq number, r1 = struct pt_regs *
 	@
-	adrne	lr, 1b
+	adrne	lr, BSYM(1b)
 	bne	asm_do_IRQ
 
 #ifdef CONFIG_SMP
@@ -46,13 +46,13 @@
 	 */
 	test_for_ipi r0, r6, r5, lr
 	movne	r0, sp
-	adrne	lr, 1b
+	adrne	lr, BSYM(1b)
 	bne	do_IPI
 
 #ifdef CONFIG_LOCAL_TIMERS
 	test_for_ltirq r0, r6, r5, lr
 	movne	r0, sp
-	adrne	lr, 1b
+	adrne	lr, BSYM(1b)
 	bne	do_local_timer
 #endif
 #endif
@@ -70,7 +70,10 @@
  */
 	.macro	inv_entry, reason
 	sub	sp, sp, #S_FRAME_SIZE
-	stmib	sp, {r1 - lr}
+ ARM(	stmib	sp, {r1 - lr}		)
+ THUMB(	stmia	sp, {r0 - r12}		)
+ THUMB(	str	sp, [sp, #S_SP]		)
+ THUMB(	str	lr, [sp, #S_LR]		)
 	mov	r1, #\reason
 	.endm
 
@@ -126,17 +129,24 @@ ENDPROC(__und_invalid)
 	.macro	svc_entry, stack_hole=0
  UNWIND(.fnstart		)
  UNWIND(.save {r0 - pc}		)
-	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole)
+	sub	sp, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+#ifdef CONFIG_THUMB2_KERNEL
+ SPFIX(	str	r0, [sp]	)	@ temporarily saved
+ SPFIX(	mov	r0, sp		)
+ SPFIX(	tst	r0, #4		)	@ test original stack alignment
+ SPFIX(	ldr	r0, [sp]	)	@ restored
+#else
  SPFIX(	tst	sp, #4		)
- SPFIX(	bicne	sp, sp, #4	)
-	stmib	sp, {r1 - r12}
+#endif
+ SPFIX(	subeq	sp, sp, #4	)
+	stmia	sp, {r1 - r12}
 
 	ldmia	r0, {r1 - r3}
-	add	r5, sp, #S_SP		@ here for interlock avoidance
+	add	r5, sp, #S_SP - 4	@ here for interlock avoidance
 	mov	r4, #-1			@  ""  ""      ""       ""
-	add	r0, sp, #(S_FRAME_SIZE + \stack_hole)
- SPFIX(	addne	r0, r0, #4	)
-	str	r1, [sp]		@ save the "real" r0 copied
+	add	r0, sp, #(S_FRAME_SIZE + \stack_hole - 4)
+ SPFIX(	addeq	r0, r0, #4	)
+	str	r1, [sp, #-4]!		@ save the "real" r0 copied
 					@ from the exception stack
 
 	mov	r1, lr
@@ -151,6 +161,8 @@ ENDPROC(__und_invalid)
 	@  r4 - orig_r0 (see pt_regs definition in ptrace.h)
 	@
 	stmia	r5, {r0 - r4}
+
+	asm_trace_hardirqs_off
 	.endm
 
 	.align	5
@@ -196,9 +208,8 @@ __dabt_svc:
 	@
 	@ restore SPSR and restart the instruction
 	@
-	ldr	r0, [sp, #S_PSR]
-	msr	spsr_cxsf, r0
-	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+	ldr	r2, [sp, #S_PSR]
+	svc_exit r2				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__dabt_svc)
 
@@ -206,9 +217,6 @@ ENDPROC(__dabt_svc)
 __irq_svc:
 	svc_entry
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
 #ifdef CONFIG_PREEMPT
 	get_thread_info tsk
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
@@ -225,13 +233,12 @@ __irq_svc:
 	tst	r0, #_TIF_NEED_RESCHED
 	blne	svc_preempt
 #endif
-	ldr	r0, [sp, #S_PSR]		@ irqs are already disabled
-	msr	spsr_cxsf, r0
+	ldr	r4, [sp, #S_PSR]		@ irqs are already disabled
 #ifdef CONFIG_TRACE_IRQFLAGS
-	tst	r0, #PSR_I_BIT
+	tst	r4, #PSR_I_BIT
 	bleq	trace_hardirqs_on
 #endif
-	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+	svc_exit r4				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__irq_svc)
 
@@ -265,8 +272,16 @@ __und_svc:
 	@
 	@  r0 - instruction
 	@
+#ifndef	CONFIG_THUMB2_KERNEL
 	ldr	r0, [r2, #-4]
-	adr	r9, 1f
+#else
+	ldrh	r0, [r2, #-2]			@ Thumb instruction at LR - 2
+	and	r9, r0, #0xf800
+	cmp	r9, #0xe800			@ 32-bit instruction if xx >= 0
+	ldrhhs	r9, [r2]			@ bottom 16 bits
+	orrhs	r0, r9, r0, lsl #16
+#endif
+	adr	r9, BSYM(1f)
 	bl	call_fpe
 
 	mov	r0, sp				@ struct pt_regs *regs
@@ -280,9 +295,8 @@ __und_svc:
 	@
 	@ restore SPSR and restart the instruction
 	@
-	ldr	lr, [sp, #S_PSR]		@ Get SVC cpsr
-	msr	spsr_cxsf, lr
-	ldmia	sp, {r0 - pc}^			@ Restore SVC registers
+	ldr	r2, [sp, #S_PSR]		@ Get SVC cpsr
+	svc_exit r2				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__und_svc)
 
@@ -297,22 +311,16 @@ __pabt_svc:
 	tst	r3, #PSR_I_BIT
 	biceq	r9, r9, #PSR_I_BIT
 
-	@
-	@ set args, then call main handler
-	@
-	@  r0 - address of faulting instruction
-	@  r1 - pointer to registers on stack
-	@
-#ifdef MULTI_PABORT
 	mov	r0, r2			@ pass address of aborted instruction.
+#ifdef MULTI_PABORT
 	ldr	r4, .LCprocfns
 	mov	lr, pc
 	ldr	pc, [r4, #PROCESSOR_PABT_FUNC]
 #else
-	CPU_PABORT_HANDLER(r0, r2)
+	bl	CPU_PABORT_HANDLER
 #endif
 	msr	cpsr_c, r9			@ Maybe enable interrupts
-	mov	r1, sp				@ regs
+	mov	r2, sp				@ regs
 	bl	do_PrefetchAbort		@ call abort handler
 
 	@
@@ -323,9 +331,8 @@ __pabt_svc:
 	@
 	@ restore SPSR and restart the instruction
 	@
-	ldr	r0, [sp, #S_PSR]
-	msr	spsr_cxsf, r0
-	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+	ldr	r2, [sp, #S_PSR]
+	svc_exit r2				@ return from exception
  UNWIND(.fnend		)
 ENDPROC(__pabt_svc)
 
@@ -353,7 +360,8 @@ ENDPROC(__pabt_svc)
  UNWIND(.fnstart	)
  UNWIND(.cantunwind	)	@ don't unwind the user space
 	sub	sp, sp, #S_FRAME_SIZE
-	stmib	sp, {r1 - r12}
+ ARM(	stmib	sp, {r1 - r12}	)
+ THUMB(	stmia	sp, {r0 - r12}	)
 
 	ldmia	r0, {r1 - r3}
 	add	r0, sp, #S_PC		@ here for interlock avoidance
@@ -372,7 +380,8 @@ ENDPROC(__pabt_svc)
 	@ Also, separately save sp_usr and lr_usr
 	@
 	stmia	r0, {r2 - r4}
-	stmdb	r0, {sp, lr}^
+ ARM(	stmdb	r0, {sp, lr}^			)
+ THUMB(	store_user_sp_lr r0, r1, S_SP - S_PC	)
 
 	@
 	@ Enable the alignment trap while in kernel mode
@@ -383,6 +392,8 @@ ENDPROC(__pabt_svc)
 	@ Clear FP to mark the first stack frame
 	@
 	zero_fp
+
+	asm_trace_hardirqs_off
 	.endm
 
 	.macro	kuser_cmpxchg_check
@@ -427,7 +438,7 @@ __dabt_usr:
 	@
 	enable_irq
 	mov	r2, sp
-	adr	lr, ret_from_exception
+	adr	lr, BSYM(ret_from_exception)
 	b	do_DataAbort
  UNWIND(.fnend		)
 ENDPROC(__dabt_usr)
@@ -437,9 +448,6 @@ __irq_usr:
 	usr_entry
 	kuser_cmpxchg_check
 
-#ifdef CONFIG_TRACE_IRQFLAGS
-	bl	trace_hardirqs_off
-#endif
 	get_thread_info tsk
 #ifdef CONFIG_PREEMPT
 	ldr	r8, [tsk, #TI_PREEMPT]		@ get preempt count
@@ -452,7 +460,9 @@ __irq_usr:
 	ldr	r0, [tsk, #TI_PREEMPT]
 	str	r8, [tsk, #TI_PREEMPT]
 	teq	r0, r7
-	strne	r0, [r0, -r0]
+ ARM(	strne	r0, [r0, -r0]	)
+ THUMB(	movne	r0, #0		)
+ THUMB(	strne	r0, [r0]	)
 #endif
 #ifdef CONFIG_TRACE_IRQFLAGS
 	bl	trace_hardirqs_on
@@ -476,9 +486,10 @@ __und_usr:
 	@
 	@  r0 - instruction
 	@
-	adr	r9, ret_from_exception
-	adr	lr, __und_usr_unknown
+	adr	r9, BSYM(ret_from_exception)
+	adr	lr, BSYM(__und_usr_unknown)
 	tst	r3, #PSR_T_BIT			@ Thumb mode?
+	itet	eq				@ explicit IT needed for the 1f label
 	subeq	r4, r2, #4			@ ARM instr at LR - 4
 	subne	r4, r2, #2			@ Thumb instr at LR - 2
 1:	ldreqt	r0, [r4]
@@ -488,7 +499,10 @@ __und_usr:
 	beq	call_fpe
 	@ Thumb instruction
 #if __LINUX_ARM_ARCH__ >= 7
-2:	ldrht	r5, [r4], #2
+2:
+ ARM(	ldrht	r5, [r4], #2	)
+ THUMB(	ldrht	r5, [r4]	)
+ THUMB(	add	r4, r4, #2	)
 	and	r0, r5, #0xf800			@ mask bits 111x x... .... ....
 	cmp	r0, #0xe800			@ 32bit instruction if xx != 0
 	blo	__und_usr_unknown
@@ -577,9 +591,11 @@ call_fpe:
 	moveq	pc, lr
 	get_thread_info r10			@ get current thread
 	and	r8, r0, #0x00000f00		@ mask out CP number
+ THUMB(	lsr	r8, r8, #8		)
 	mov	r7, #1
 	add	r6, r10, #TI_USED_CP
-	strb	r7, [r6, r8, lsr #8]		@ set appropriate used_cp[]
+ ARM(	strb	r7, [r6, r8, lsr #8]	)	@ set appropriate used_cp[]
+ THUMB(	strb	r7, [r6, r8]		)	@ set appropriate used_cp[]
 #ifdef CONFIG_IWMMXT
 	@ Test if we need to give access to iWMMXt coprocessors
 	ldr	r5, [r10, #TI_FLAGS]
@@ -587,36 +603,38 @@ call_fpe:
 	movcss	r7, r5, lsr #(TIF_USING_IWMMXT + 1)
 	bcs	iwmmxt_task_enable
 #endif
-	add	pc, pc, r8, lsr #6
-	mov	r0, r0
-
-	mov	pc, lr				@ CP#0
-	b	do_fpe				@ CP#1 (FPE)
-	b	do_fpe				@ CP#2 (FPE)
-	mov	pc, lr				@ CP#3
+ ARM(	add	pc, pc, r8, lsr #6	)
+ THUMB(	lsl	r8, r8, #2		)
+ THUMB(	add	pc, r8			)
+	nop
+
+	W(mov)	pc, lr				@ CP#0
+	W(b)	do_fpe				@ CP#1 (FPE)
+	W(b)	do_fpe				@ CP#2 (FPE)
+	W(mov)	pc, lr				@ CP#3
 #ifdef CONFIG_CRUNCH
 	b	crunch_task_enable		@ CP#4 (MaverickCrunch)
 	b	crunch_task_enable		@ CP#5 (MaverickCrunch)
 	b	crunch_task_enable		@ CP#6 (MaverickCrunch)
 #else
-	mov	pc, lr				@ CP#4
-	mov	pc, lr				@ CP#5
-	mov	pc, lr				@ CP#6
+	W(mov)	pc, lr				@ CP#4
+	W(mov)	pc, lr				@ CP#5
+	W(mov)	pc, lr				@ CP#6
 #endif
-	mov	pc, lr				@ CP#7
-	mov	pc, lr				@ CP#8
-	mov	pc, lr				@ CP#9
+	W(mov)	pc, lr				@ CP#7
+	W(mov)	pc, lr				@ CP#8
+	W(mov)	pc, lr				@ CP#9
 #ifdef CONFIG_VFP
-	b	do_vfp				@ CP#10 (VFP)
-	b	do_vfp				@ CP#11 (VFP)
+	W(b)	do_vfp				@ CP#10 (VFP)
+	W(b)	do_vfp				@ CP#11 (VFP)
 #else
-	mov	pc, lr				@ CP#10 (VFP)
-	mov	pc, lr				@ CP#11 (VFP)
+	W(mov)	pc, lr				@ CP#10 (VFP)
+	W(mov)	pc, lr				@ CP#11 (VFP)
 #endif
-	mov	pc, lr				@ CP#12
-	mov	pc, lr				@ CP#13
-	mov	pc, lr				@ CP#14 (Debug)
-	mov	pc, lr				@ CP#15 (Control)
+	W(mov)	pc, lr				@ CP#12
+	W(mov)	pc, lr				@ CP#13
+	W(mov)	pc, lr				@ CP#14 (Debug)
+	W(mov)	pc, lr				@ CP#15 (Control)
 
 #ifdef CONFIG_NEON
 	.align	6
@@ -662,12 +680,14 @@ ENTRY(fp_enter)
 	.word	no_fp
 	.previous
 
-no_fp:	mov	pc, lr
+ENTRY(no_fp)
+	mov	pc, lr
+ENDPROC(no_fp)
 
 __und_usr_unknown:
 	enable_irq
 	mov	r0, sp
-	adr	lr, ret_from_exception
+	adr	lr, BSYM(ret_from_exception)
 	b	do_undefinstr
 ENDPROC(__und_usr_unknown)
 
@@ -675,16 +695,16 @@ ENDPROC(__und_usr_unknown)
 __pabt_usr:
 	usr_entry
 
-#ifdef MULTI_PABORT
 	mov	r0, r2			@ pass address of aborted instruction.
+#ifdef MULTI_PABORT
 	ldr	r4, .LCprocfns
 	mov	lr, pc
 	ldr	pc, [r4, #PROCESSOR_PABT_FUNC]
 #else
-	CPU_PABORT_HANDLER(r0, r2)
+	bl	CPU_PABORT_HANDLER
 #endif
 	enable_irq				@ Enable interrupts
-	mov	r1, sp				@ regs
+	mov	r2, sp				@ regs
 	bl	do_PrefetchAbort		@ call abort handler
  UNWIND(.fnend		)
 	/* fall through */
@@ -711,17 +731,13 @@ ENTRY(__switch_to)
  UNWIND(.cantunwind	)
 	add	ip, r1, #TI_CPU_SAVE
 	ldr	r3, [r2, #TI_TP_VALUE]
-	stmia	ip!, {r4 - sl, fp, sp, lr}	@ Store most regs on stack
+ ARM(	stmia	ip!, {r4 - sl, fp, sp, lr} )	@ Store most regs on stack
+ THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
+ THUMB(	str	sp, [ip], #4		   )
+ THUMB(	str	lr, [ip], #4		   )
 #ifdef CONFIG_MMU
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
-#if __LINUX_ARM_ARCH__ >= 6
-#ifdef CONFIG_CPU_32v6K
-	clrex
-#else
-	strex	r5, r4, [ip]			@ Clear exclusive monitor
-#endif
-#endif
 #if defined(CONFIG_HAS_TLS_REG)
 	mcr	p15, 0, r3, c13, c0, 3		@ set TLS register
 #elif !defined(CONFIG_TLS_REG_EMUL)
@@ -736,8 +752,12 @@ ENTRY(__switch_to)
 	ldr	r0, =thread_notify_head
 	mov	r1, #THREAD_NOTIFY_SWITCH
 	bl	atomic_notifier_call_chain
+ THUMB(	mov	ip, r4			   )
 	mov	r0, r5
-	ldmia	r4, {r4 - sl, fp, sp, pc}	@ Load all regs saved previously
+ ARM(	ldmia	r4, {r4 - sl, fp, sp, pc}  )	@ Load all regs saved previously
+ THUMB(	ldmia	ip!, {r4 - sl, fp}	   )	@ Load all regs saved previously
+ THUMB(	ldr	sp, [ip], #4		   )
+ THUMB(	ldr	pc, [ip]		   )
  UNWIND(.fnend		)
 ENDPROC(__switch_to)
 
@@ -772,6 +792,7 @@ ENDPROC(__switch_to)
  * if your compiled code is not going to use the new instructions for other
  * purpose.
  */
+ THUMB(	.arm	)
 
 	.macro	usr_ret, reg
 #ifdef CONFIG_ARM_THUMB
@@ -1020,6 +1041,7 @@ __kuser_helper_version:				@ 0xffff0ffc
 	.globl	__kuser_helper_end
 __kuser_helper_end:
 
+ THUMB(	.thumb	)
 
 /*
  * Vector stubs.
@@ -1054,17 +1076,23 @@ vector_\name:
 	@ Prepare for SVC32 mode.  IRQs remain disabled.
 	@
 	mrs	r0, cpsr
-	eor	r0, r0, #(\mode ^ SVC_MODE)
+	eor	r0, r0, #(\mode ^ SVC_MODE | PSR_ISETSTATE)
 	msr	spsr_cxsf, r0
 
 	@
 	@ the branch table must immediately follow this code
 	@
 	and	lr, lr, #0x0f
+ THUMB(	adr	r0, 1f			)
+ THUMB(	ldr	lr, [r0, lr, lsl #2]	)
 	mov	r0, sp
-	ldr	lr, [pc, lr, lsl #2]
+ ARM(	ldr	lr, [pc, lr, lsl #2]	)
 	movs	pc, lr			@ branch to handler in SVC mode
 ENDPROC(vector_\name)
+
+	.align	2
+	@ handler addresses follow this label
+1:
 	.endm
 
 	.globl	__stubs_start
@@ -1202,14 +1230,16 @@ __stubs_end:
 
 	.globl	__vectors_start
 __vectors_start:
-	swi	SYS_ERROR0
-	b	vector_und + stubs_offset
-	ldr	pc, .LCvswi + stubs_offset
-	b	vector_pabt + stubs_offset
-	b	vector_dabt + stubs_offset
-	b	vector_addrexcptn + stubs_offset
-	b	vector_irq + stubs_offset
-	b	vector_fiq + stubs_offset
+ ARM(	swi	SYS_ERROR0	)
+ THUMB(	svc	#0		)
+ THUMB(	nop			)
+	W(b)	vector_und + stubs_offset
+	W(ldr)	pc, .LCvswi + stubs_offset
+	W(b)	vector_pabt + stubs_offset
+	W(b)	vector_dabt + stubs_offset
+	W(b)	vector_addrexcptn + stubs_offset
+	W(b)	vector_irq + stubs_offset
+	W(b)	vector_fiq + stubs_offset
 
 	.globl	__vectors_end
 __vectors_end:
diff --git a/arch/arm/kernel/entry-common.S b/arch/arm/kernel/entry-common.S
index 8c3de1a350b5..f0fe95b7085d 100644
--- a/arch/arm/kernel/entry-common.S
+++ b/arch/arm/kernel/entry-common.S
@@ -33,14 +33,7 @@ ret_fast_syscall:
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
 
-	@ fast_restore_user_regs
-	ldr	r1, [sp, #S_OFF + S_PSR]	@ get calling cpsr
-	ldr	lr, [sp, #S_OFF + S_PC]!	@ get pc
-	msr	spsr_cxsf, r1			@ save in spsr_svc
-	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
-	mov	r0, r0
-	add	sp, sp, #S_FRAME_SIZE - S_PC
-	movs	pc, lr				@ return & move spsr_svc into cpsr
+	restore_user_regs fast = 1, offset = S_OFF
  UNWIND(.fnend		)
 
 /*
@@ -51,7 +44,7 @@ fast_work_pending:
 work_pending:
 	tst	r1, #_TIF_NEED_RESCHED
 	bne	work_resched
-	tst	r1, #_TIF_SIGPENDING
+	tst	r1, #_TIF_SIGPENDING|_TIF_NOTIFY_RESUME
 	beq	no_work_pending
 	mov	r0, sp				@ 'regs'
 	mov	r2, why				@ 'syscall'
@@ -73,14 +66,7 @@ no_work_pending:
 	/* perform architecture specific actions before user return */
 	arch_ret_to_user r1, lr
 
-	@ slow_restore_user_regs
-	ldr	r1, [sp, #S_PSR]		@ get calling cpsr
-	ldr	lr, [sp, #S_PC]!		@ get pc
-	msr	spsr_cxsf, r1			@ save in spsr_svc
-	ldmdb	sp, {r0 - lr}^			@ get calling r0 - lr
-	mov	r0, r0
-	add	sp, sp, #S_FRAME_SIZE - S_PC
-	movs	pc, lr				@ return & move spsr_svc into cpsr
+	restore_user_regs fast = 0, offset = 0
 ENDPROC(ret_to_user)
 
 /*
@@ -132,6 +118,25 @@ ftrace_call:
 
 #else
 
+ENTRY(__gnu_mcount_nc)
+	stmdb sp!, {r0-r3, lr}
+	ldr r0, =ftrace_trace_function
+	ldr r2, [r0]
+	adr r0, ftrace_stub
+	cmp r0, r2
+	bne gnu_trace
+	ldmia sp!, {r0-r3, ip, lr}
+	mov pc, ip
+
+gnu_trace:
+	ldr r1, [sp, #20]			@ lr of instrumented routine
+	mov r0, lr
+	sub r0, r0, #MCOUNT_INSN_SIZE
+	mov lr, pc
+	mov pc, r2
+	ldmia sp!, {r0-r3, ip, lr}
+	mov pc, ip
+
 ENTRY(mcount)
 	stmdb sp!, {r0-r3, lr}
 	ldr r0, =ftrace_trace_function
@@ -182,8 +187,10 @@ ftrace_stub:
 ENTRY(vector_swi)
 	sub	sp, sp, #S_FRAME_SIZE
 	stmia	sp, {r0 - r12}			@ Calling r0 - r12
-	add	r8, sp, #S_PC
-	stmdb	r8, {sp, lr}^			@ Calling sp, lr
+ ARM(	add	r8, sp, #S_PC		)
+ ARM(	stmdb	r8, {sp, lr}^		)	@ Calling sp, lr
+ THUMB(	mov	r8, sp			)
+ THUMB(	store_user_sp_lr r8, r10, S_SP	)	@ calling sp, lr
 	mrs	r8, spsr			@ called from non-FIQ mode, so ok.
 	str	lr, [sp, #S_PC]			@ Save calling PC
 	str	r8, [sp, #S_PSR]		@ Save CPSR
@@ -272,7 +279,7 @@ ENTRY(vector_swi)
 	bne	__sys_trace
 
 	cmp	scno, #NR_syscalls		@ check upper syscall limit
-	adr	lr, ret_fast_syscall		@ return address
+	adr	lr, BSYM(ret_fast_syscall)	@ return address
 	ldrcc	pc, [tbl, scno, lsl #2]		@ call sys_* routine
 
 	add	r1, sp, #S_OFF
@@ -293,7 +300,7 @@ __sys_trace:
 	mov	r0, #0				@ trace entry [IP = 0]
 	bl	syscall_trace
 
-	adr	lr, __sys_trace_return		@ return address
+	adr	lr, BSYM(__sys_trace_return)	@ return address
 	mov	scno, r0			@ syscall number (possibly new)
 	add	r1, sp, #S_R0 + S_OFF		@ pointer to regs
 	cmp	scno, #NR_syscalls		@ check upper syscall limit
@@ -373,16 +380,6 @@ sys_clone_wrapper:
 		b	sys_clone
 ENDPROC(sys_clone_wrapper)
 
-sys_sigsuspend_wrapper:
-		add	r3, sp, #S_OFF
-		b	sys_sigsuspend
-ENDPROC(sys_sigsuspend_wrapper)
-
-sys_rt_sigsuspend_wrapper:
-		add	r2, sp, #S_OFF
-		b	sys_rt_sigsuspend
-ENDPROC(sys_rt_sigsuspend_wrapper)
-
 sys_sigreturn_wrapper:
 		add	r0, sp, #S_OFF
 		b	sys_sigreturn
@@ -428,13 +425,6 @@ sys_mmap2:
 #endif
 ENDPROC(sys_mmap2)
 
-ENTRY(pabort_ifar)
-		mrc	p15, 0, r0, cr6, cr0, 2
-ENTRY(pabort_noifar)
-		mov	pc, lr
-ENDPROC(pabort_ifar)
-ENDPROC(pabort_noifar)
-
 #ifdef CONFIG_OABI_COMPAT
 
 /*
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index 87ab4e157997..ac34c0d9384b 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -36,11 +36,6 @@
 #endif
 	.endm
 
-	.macro	get_thread_info, rd
-	mov	\rd, sp, lsr #13
-	mov	\rd, \rd, lsl #13
-	.endm
-
 	.macro	alignment_trap, rtemp
 #ifdef CONFIG_ALIGNMENT_TRAP
 	ldr	\rtemp, .LCcralign
@@ -49,6 +44,109 @@
 #endif
 	.endm
 
+	@
+	@ Store/load the USER SP and LR registers by switching to the SYS
+	@ mode. Useful in Thumb-2 mode where "stm/ldm rd, {sp, lr}^" is not
+	@ available. Should only be called from SVC mode
+	@
+	.macro	store_user_sp_lr, rd, rtemp, offset = 0
+	mrs	\rtemp, cpsr
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch to the SYS mode
+
+	str	sp, [\rd, #\offset]		@ save sp_usr
+	str	lr, [\rd, #\offset + 4]		@ save lr_usr
+
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
+	.endm
+
+	.macro	load_user_sp_lr, rd, rtemp, offset = 0
+	mrs	\rtemp, cpsr
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch to the SYS mode
+
+	ldr	sp, [\rd, #\offset]		@ load sp_usr
+	ldr	lr, [\rd, #\offset + 4]		@ load lr_usr
+
+	eor	\rtemp, \rtemp, #(SVC_MODE ^ SYSTEM_MODE)
+	msr	cpsr_c, \rtemp			@ switch back to the SVC mode
+	.endm
+
+#ifndef CONFIG_THUMB2_KERNEL
+	.macro	svc_exit, rpsr
+	msr	spsr_cxsf, \rpsr
+#if defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
+	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#elif defined (CONFIG_CPU_V6)
+	ldr	r0, [sp]
+	strex	r1, r2, [sp]			@ clear the exclusive monitor
+	ldmib	sp, {r1 - pc}^			@ load r1 - pc, cpsr
+#else
+	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
+#endif
+	.endm
+
+	.macro	restore_user_regs, fast = 0, offset = 0
+	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
+	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
+	msr	spsr_cxsf, r1			@ save in spsr_svc
+#if defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
+#elif defined (CONFIG_CPU_V6)
+	strex	r1, r2, [sp]			@ clear the exclusive monitor
+#endif
+	.if	\fast
+	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
+	.else
+	ldmdb	sp, {r0 - lr}^			@ get calling r0 - lr
+	.endif
+	add	sp, sp, #S_FRAME_SIZE - S_PC
+	movs	pc, lr				@ return & move spsr_svc into cpsr
+	.endm
+
+	.macro	get_thread_info, rd
+	mov	\rd, sp, lsr #13
+	mov	\rd, \rd, lsl #13
+	.endm
+#else	/* CONFIG_THUMB2_KERNEL */
+	.macro	svc_exit, rpsr
+	clrex					@ clear the exclusive monitor
+	ldr	r0, [sp, #S_SP]			@ top of the stack
+	ldr	r1, [sp, #S_PC]			@ return address
+	tst	r0, #4				@ orig stack 8-byte aligned?
+	stmdb	r0, {r1, \rpsr}			@ rfe context
+	ldmia	sp, {r0 - r12}
+	ldr	lr, [sp, #S_LR]
+	addeq	sp, sp, #S_FRAME_SIZE - 8	@ aligned
+	addne	sp, sp, #S_FRAME_SIZE - 4	@ not aligned
+	rfeia	sp!
+	.endm
+
+	.macro	restore_user_regs, fast = 0, offset = 0
+	clrex					@ clear the exclusive monitor
+	mov	r2, sp
+	load_user_sp_lr r2, r3, \offset + S_SP	@ calling sp, lr
+	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
+	ldr	lr, [sp, #\offset + S_PC]	@ get pc
+	add	sp, sp, #\offset + S_SP
+	msr	spsr_cxsf, r1			@ save in spsr_svc
+	.if	\fast
+	ldmdb	sp, {r1 - r12}			@ get calling r1 - r12
+	.else
+	ldmdb	sp, {r0 - r12}			@ get calling r0 - r12
+	.endif
+	add	sp, sp, #S_FRAME_SIZE - S_SP
+	movs	pc, lr				@ return & move spsr_svc into cpsr
+	.endm
+
+	.macro	get_thread_info, rd
+	mov	\rd, sp
+	lsr	\rd, \rd, #13
+	mov	\rd, \rd, lsl #13
+	.endm
+#endif	/* !CONFIG_THUMB2_KERNEL */
 
 /*
  * These are the registers used in the syscall handler, and allow us to
diff --git a/arch/arm/kernel/head-common.S b/arch/arm/kernel/head-common.S
index 991952c644d1..885a7214418d 100644
--- a/arch/arm/kernel/head-common.S
+++ b/arch/arm/kernel/head-common.S
@@ -13,7 +13,9 @@
 
 #define ATAG_CORE 0x54410001
 #define ATAG_CORE_SIZE ((2*4 + 3*4) >> 2)
+#define ATAG_CORE_SIZE_EMPTY ((2*4) >> 2)
 
+	.align	2
 	.type	__switch_data, %object
 __switch_data:
 	.long	__mmap_switched
@@ -51,7 +53,9 @@ __mmap_switched:
 	strcc	fp, [r6],#4
 	bcc	1b
 
-	ldmia	r3, {r4, r5, r6, r7, sp}
+ ARM(	ldmia	r3, {r4, r5, r6, r7, sp})
+ THUMB(	ldmia	r3, {r4, r5, r6, r7}	)
+ THUMB(	ldr	sp, [r3, #16]		)
 	str	r9, [r4]			@ Save processor ID
 	str	r1, [r5]			@ Save machine type
 	str	r2, [r6]			@ Save atags pointer
@@ -155,7 +159,8 @@ ENDPROC(__error)
  */
 __lookup_processor_type:
 	adr	r3, 3f
-	ldmda	r3, {r5 - r7}
+	ldmia	r3, {r5 - r7}
+	add	r3, r3, #8
 	sub	r3, r3, r7			@ get offset between virt&phys
 	add	r5, r5, r3			@ convert virt addresses to
 	add	r6, r6, r3			@ physical address space
@@ -185,9 +190,10 @@ ENDPROC(lookup_processor_type)
  * Look in <asm/procinfo.h> and arch/arm/kernel/arch.[ch] for
  * more information about the __proc_info and __arch_info structures.
  */
-	.long	__proc_info_begin
+	.align	2
+3:	.long	__proc_info_begin
 	.long	__proc_info_end
-3:	.long	.
+4:	.long	.
 	.long	__arch_info_begin
 	.long	__arch_info_end
 
@@ -203,7 +209,7 @@ ENDPROC(lookup_processor_type)
  *  r5 = mach_info pointer in physical address space
  */
 __lookup_machine_type:
-	adr	r3, 3b
+	adr	r3, 4b
 	ldmia	r3, {r4, r5, r6}
 	sub	r3, r3, r4			@ get offset between virt&phys
 	add	r5, r5, r3			@ convert virt addresses to
@@ -246,7 +252,8 @@ __vet_atags:
 	bne	1f
 
 	ldr	r5, [r2, #0]			@ is first tag ATAG_CORE?
-	subs	r5, r5, #ATAG_CORE_SIZE
+	cmp	r5, #ATAG_CORE_SIZE
+	cmpne	r5, #ATAG_CORE_SIZE_EMPTY
 	bne	1f
 	ldr	r5, [r2, #4]
 	ldr	r6, =ATAG_CORE
diff --git a/arch/arm/kernel/head-nommu.S b/arch/arm/kernel/head-nommu.S
index cc87e1765ed2..e5dfc2895e24 100644
--- a/arch/arm/kernel/head-nommu.S
+++ b/arch/arm/kernel/head-nommu.S
@@ -34,7 +34,7 @@
  */
 	.section ".text.head", "ax"
 ENTRY(stext)
-	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | SVC_MODE @ ensure svc mode
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
 #ifndef CONFIG_CPU_CP15
 	ldr	r9, =CONFIG_PROCESSOR_ID
@@ -50,8 +50,10 @@ ENTRY(stext)
 
 	ldr	r13, __switch_data		@ address to jump to after
 						@ the initialization is done
-	adr	lr, __after_proc_init		@ return (PIC) address
-	add	pc, r10, #PROCINFO_INITFUNC
+	adr	lr, BSYM(__after_proc_init)	@ return (PIC) address
+ ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
+ THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
+ THUMB(	mov	pc, r12				)
 ENDPROC(stext)
 
 /*
@@ -59,7 +61,10 @@ ENDPROC(stext)
  */
 __after_proc_init:
 #ifdef CONFIG_CPU_CP15
-	mrc	p15, 0, r0, c1, c0, 0		@ read control reg
+	/*
+	 * CP15 system control register value returned in r0 from
+	 * the CPU init function.
+	 */
 #ifdef CONFIG_ALIGNMENT_TRAP
 	orr	r0, r0, #CR_A
 #else
@@ -82,7 +87,8 @@ __after_proc_init:
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 #endif /* CONFIG_CPU_CP15 */
 
-	mov	pc, r13				@ clear the BSS and jump
+	mov	r3, r13
+	mov	pc, r3				@ clear the BSS and jump
 						@ to start_kernel
 ENDPROC(__after_proc_init)
 	.ltorg
diff --git a/arch/arm/kernel/head.S b/arch/arm/kernel/head.S
index 21e17dc94cb5..38ccbe1d3b2c 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -76,7 +76,7 @@
  */
 	.section ".text.head", "ax"
 ENTRY(stext)
-	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | SVC_MODE @ ensure svc mode
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9 @ ensure svc mode
 						@ and irqs disabled
 	mrc	p15, 0, r9, c0, c0		@ get processor id
 	bl	__lookup_processor_type		@ r5=procinfo r9=cpuid
@@ -97,8 +97,10 @@ ENTRY(stext)
 	 */
 	ldr	r13, __switch_data		@ address to jump to after
 						@ mmu has been enabled
-	adr	lr, __enable_mmu		@ return (PIC) address
-	add	pc, r10, #PROCINFO_INITFUNC
+	adr	lr, BSYM(__enable_mmu)		@ return (PIC) address
+ ARM(	add	pc, r10, #PROCINFO_INITFUNC	)
+ THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
+ THUMB(	mov	pc, r12				)
 ENDPROC(stext)
 
 #if defined(CONFIG_SMP)
@@ -110,7 +112,7 @@ 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.
 	 */
-	msr	cpsr_c, #PSR_F_BIT | PSR_I_BIT | SVC_MODE
+	setmode	PSR_F_BIT | PSR_I_BIT | SVC_MODE, r9
 	mrc	p15, 0, r9, c0, c0		@ get processor id
 	bl	__lookup_processor_type
 	movs	r10, r5				@ invalid processor?
@@ -121,12 +123,15 @@ ENTRY(secondary_startup)
 	 * Use the page tables supplied from  __cpu_up.
 	 */
 	adr	r4, __secondary_data
-	ldmia	r4, {r5, r7, r13}		@ address to jump to after
+	ldmia	r4, {r5, r7, r12}		@ address to jump to after
 	sub	r4, r4, r5			@ mmu has been enabled
 	ldr	r4, [r7, r4]			@ get secondary_data.pgdir
-	adr	lr, __enable_mmu		@ return address
-	add	pc, r10, #PROCINFO_INITFUNC	@ initialise processor
-						@ (return control reg)
+	adr	lr, BSYM(__enable_mmu)		@ return address
+	mov	r13, r12			@ __secondary_switched address
+ ARM(	add	pc, r10, #PROCINFO_INITFUNC	) @ initialise processor
+						  @ (return control reg)
+ THUMB(	add	r12, r10, #PROCINFO_INITFUNC	)
+ THUMB(	mov	pc, r12				)
 ENDPROC(secondary_startup)
 
 	/*
@@ -193,8 +198,8 @@ __turn_mmu_on:
 	mcr	p15, 0, r0, c1, c0, 0		@ write control reg
 	mrc	p15, 0, r3, c0, c0, 0		@ read id reg
 	mov	r3, r3
-	mov	r3, r3
-	mov	pc, r13
+	mov	r3, r13
+	mov	pc, r3
 ENDPROC(__turn_mmu_on)
 
 
@@ -235,7 +240,8 @@ __create_page_tables:
 	 * will be removed by paging_init().  We use our current program
 	 * counter to determine corresponding section base address.
 	 */
-	mov	r6, pc, lsr #20			@ start of kernel section
+	mov	r6, pc
+	mov	r6, r6, lsr #20			@ start of kernel section
 	orr	r3, r7, r6, lsl #20		@ flags + kernel base
 	str	r3, [r4, r6, lsl #2]		@ identity mapping
 
diff --git a/arch/arm/kernel/init_task.c b/arch/arm/kernel/init_task.c
index 3f470866bb89..e7cbb50dc356 100644
--- a/arch/arm/kernel/init_task.c
+++ b/arch/arm/kernel/init_task.c
@@ -24,9 +24,8 @@ static struct sighand_struct init_sighand = INIT_SIGHAND(init_sighand);
  *
  * The things we do for performance..
  */
-union thread_union init_thread_union
-	__attribute__((__section__(".data.init_task"))) =
-		{ INIT_THREAD_INFO(init_task) };
+union thread_union init_thread_union __init_task_data =
+	{ INIT_THREAD_INFO(init_task) };
 
 /*
  * Initial task structure.
diff --git a/arch/arm/kernel/irq.c b/arch/arm/kernel/irq.c
index b7c3490eaa24..c9a8619f3856 100644
--- a/arch/arm/kernel/irq.c
+++ b/arch/arm/kernel/irq.c
@@ -86,7 +86,7 @@ int show_interrupts(struct seq_file *p, void *v)
 unlock:
 		spin_unlock_irqrestore(&irq_desc[i].lock, flags);
 	} else if (i == NR_IRQS) {
-#ifdef CONFIG_ARCH_ACORN
+#ifdef CONFIG_FIQ
 		show_fiq_list(p, v);
 #endif
 #ifdef CONFIG_SMP
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index f692efddd449..60c62c377fa9 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -22,6 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
 #include <linux/module.h>
+#include <linux/stop_machine.h>
 #include <linux/stringify.h>
 #include <asm/traps.h>
 #include <asm/cacheflush.h>
@@ -83,10 +84,24 @@ void __kprobes arch_arm_kprobe(struct kprobe *p)
 	flush_insns(p->addr, 1);
 }
 
+/*
+ * The actual disarming is done here on each CPU and synchronized using
+ * stop_machine. This synchronization is necessary on SMP to avoid removing
+ * a probe between the moment the 'Undefined Instruction' exception is raised
+ * and the moment the exception handler reads the faulting instruction from
+ * memory.
+ */
+int __kprobes __arch_disarm_kprobe(void *p)
+{
+	struct kprobe *kp = p;
+	*kp->addr = kp->opcode;
+	flush_insns(kp->addr, 1);
+	return 0;
+}
+
 void __kprobes arch_disarm_kprobe(struct kprobe *p)
 {
-	*p->addr = p->opcode;
-	flush_insns(p->addr, 1);
+	stop_machine(__arch_disarm_kprobe, p, &cpu_online_map);
 }
 
 void __kprobes arch_remove_kprobe(struct kprobe *p)
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index bac03c81489d..f28c5e9c51ea 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -102,6 +102,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 		unsigned long loc;
 		Elf32_Sym *sym;
 		s32 offset;
+		u32 upper, lower, sign, j1, j2;
 
 		offset = ELF32_R_SYM(rel->r_info);
 		if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) {
@@ -184,6 +185,58 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 					(offset & 0x0fff);
 			break;
 
+		case R_ARM_THM_CALL:
+		case R_ARM_THM_JUMP24:
+			upper = *(u16 *)loc;
+			lower = *(u16 *)(loc + 2);
+
+			/*
+			 * 25 bit signed address range (Thumb-2 BL and B.W
+			 * instructions):
+			 *   S:I1:I2:imm10:imm11:0
+			 * where:
+			 *   S     = upper[10]   = offset[24]
+			 *   I1    = ~(J1 ^ S)   = offset[23]
+			 *   I2    = ~(J2 ^ S)   = offset[22]
+			 *   imm10 = upper[9:0]  = offset[21:12]
+			 *   imm11 = lower[10:0] = offset[11:1]
+			 *   J1    = lower[13]
+			 *   J2    = lower[11]
+			 */
+			sign = (upper >> 10) & 1;
+			j1 = (lower >> 13) & 1;
+			j2 = (lower >> 11) & 1;
+			offset = (sign << 24) | ((~(j1 ^ sign) & 1) << 23) |
+				((~(j2 ^ sign) & 1) << 22) |
+				((upper & 0x03ff) << 12) |
+				((lower & 0x07ff) << 1);
+			if (offset & 0x01000000)
+				offset -= 0x02000000;
+			offset += sym->st_value - loc;
+
+			/* only Thumb addresses allowed (no interworking) */
+			if (!(offset & 1) ||
+			    offset <= (s32)0xff000000 ||
+			    offset >= (s32)0x01000000) {
+				printk(KERN_ERR
+				       "%s: relocation out of range, section "
+				       "%d reloc %d sym '%s'\n", module->name,
+				       relindex, i, strtab + sym->st_name);
+				return -ENOEXEC;
+			}
+
+			sign = (offset >> 24) & 1;
+			j1 = sign ^ (~(offset >> 23) & 1);
+			j2 = sign ^ (~(offset >> 22) & 1);
+			*(u16 *)loc = (u16)((upper & 0xf800) | (sign << 10) |
+					    ((offset >> 12) & 0x03ff));
+			*(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
+						  (j1 << 13) | (j2 << 11) |
+						  ((offset >> 1) & 0x07ff));
+			upper = *(u16 *)loc;
+			lower = *(u16 *)(loc + 2);
+			break;
+
 		default:
 			printk(KERN_ERR "%s: unknown relocation: %u\n",
 			       module->name, ELF32_R_TYPE(rel->r_info));
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index 39196dff478c..790fbee92ec5 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -388,7 +388,7 @@ pid_t kernel_thread(int (*fn)(void *), void *arg, unsigned long flags)
 	regs.ARM_r2 = (unsigned long)fn;
 	regs.ARM_r3 = (unsigned long)kernel_thread_exit;
 	regs.ARM_pc = (unsigned long)kernel_thread_helper;
-	regs.ARM_cpsr = SVC_MODE | PSR_ENDSTATE;
+	regs.ARM_cpsr = SVC_MODE | PSR_ENDSTATE | PSR_ISETSTATE;
 
 	return do_fork(flags|CLONE_VM|CLONE_UNTRACED, 0, &regs, 0, NULL, NULL);
 }
diff --git a/arch/arm/kernel/ptrace.c b/arch/arm/kernel/ptrace.c
index 89882a1d0187..a2ea3854cb3c 100644
--- a/arch/arm/kernel/ptrace.c
+++ b/arch/arm/kernel/ptrace.c
@@ -521,7 +521,13 @@ static int ptrace_read_user(struct task_struct *tsk, unsigned long off,
 		return -EIO;
 
 	tmp = 0;
-	if (off < sizeof(struct pt_regs))
+	if (off == PT_TEXT_ADDR)
+		tmp = tsk->mm->start_code;
+	else if (off == PT_DATA_ADDR)
+		tmp = tsk->mm->start_data;
+	else if (off == PT_TEXT_END_ADDR)
+		tmp = tsk->mm->end_code;
+	else if (off < sizeof(struct pt_regs))
 		tmp = get_user_reg(tsk, off >> 2);
 
 	return put_user(tmp, ret);
diff --git a/arch/arm/kernel/return_address.c b/arch/arm/kernel/return_address.c
new file mode 100644
index 000000000000..df246da4ceca
--- /dev/null
+++ b/arch/arm/kernel/return_address.c
@@ -0,0 +1,71 @@
+/*
+ * arch/arm/kernel/return_address.c
+ *
+ * Copyright (C) 2009 Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ * for Pengutronix
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published by
+ * the Free Software Foundation.
+ */
+#include <linux/module.h>
+
+#if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND)
+#include <linux/sched.h>
+
+#include <asm/stacktrace.h>
+
+struct return_address_data {
+	unsigned int level;
+	void *addr;
+};
+
+static int save_return_addr(struct stackframe *frame, void *d)
+{
+	struct return_address_data *data = d;
+
+	if (!data->level) {
+		data->addr = (void *)frame->lr;
+
+		return 1;
+	} else {
+		--data->level;
+		return 0;
+	}
+}
+
+void *return_address(unsigned int level)
+{
+	struct return_address_data data;
+	struct stackframe frame;
+	register unsigned long current_sp asm ("sp");
+
+	data.level = level + 1;
+
+	frame.fp = (unsigned long)__builtin_frame_address(0);
+	frame.sp = current_sp;
+	frame.lr = (unsigned long)__builtin_return_address(0);
+	frame.pc = (unsigned long)return_address;
+
+	walk_stackframe(&frame, save_return_addr, &data);
+
+	if (!data.level)
+		return data.addr;
+	else
+		return NULL;
+}
+
+#else /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) */
+
+#if defined(CONFIG_ARM_UNWIND)
+#warning "TODO: return_address should use unwind tables"
+#endif
+
+void *return_address(unsigned int level)
+{
+	return NULL;
+}
+
+#endif /* if defined(CONFIG_FRAME_POINTER) && !defined(CONFIG_ARM_UNWIND) / else */
+
+EXPORT_SYMBOL_GPL(return_address);
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index bc5e4128f9f3..c6c57b640b6b 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -25,6 +25,7 @@
 #include <linux/smp.h>
 #include <linux/fs.h>
 
+#include <asm/unified.h>
 #include <asm/cpu.h>
 #include <asm/cputype.h>
 #include <asm/elf.h>
@@ -44,6 +45,7 @@
 
 #include "compat.h"
 #include "atags.h"
+#include "tcm.h"
 
 #ifndef MEM_SIZE
 #define MEM_SIZE	(16*1024*1024)
@@ -327,25 +329,38 @@ void cpu_init(void)
 	}
 
 	/*
+	 * Define the placement constraint for the inline asm directive below.
+	 * In Thumb-2, msr with an immediate value is not allowed.
+	 */
+#ifdef CONFIG_THUMB2_KERNEL
+#define PLC	"r"
+#else
+#define PLC	"I"
+#endif
+
+	/*
 	 * setup stacks for re-entrant exception handlers
 	 */
 	__asm__ (
 	"msr	cpsr_c, %1\n\t"
-	"add	sp, %0, %2\n\t"
+	"add	r14, %0, %2\n\t"
+	"mov	sp, r14\n\t"
 	"msr	cpsr_c, %3\n\t"
-	"add	sp, %0, %4\n\t"
+	"add	r14, %0, %4\n\t"
+	"mov	sp, r14\n\t"
 	"msr	cpsr_c, %5\n\t"
-	"add	sp, %0, %6\n\t"
+	"add	r14, %0, %6\n\t"
+	"mov	sp, r14\n\t"
 	"msr	cpsr_c, %7"
 	    :
 	    : "r" (stk),
-	      "I" (PSR_F_BIT | PSR_I_BIT | IRQ_MODE),
+	      PLC (PSR_F_BIT | PSR_I_BIT | IRQ_MODE),
 	      "I" (offsetof(struct stack, irq[0])),
-	      "I" (PSR_F_BIT | PSR_I_BIT | ABT_MODE),
+	      PLC (PSR_F_BIT | PSR_I_BIT | ABT_MODE),
 	      "I" (offsetof(struct stack, abt[0])),
-	      "I" (PSR_F_BIT | PSR_I_BIT | UND_MODE),
+	      PLC (PSR_F_BIT | PSR_I_BIT | UND_MODE),
 	      "I" (offsetof(struct stack, und[0])),
-	      "I" (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
+	      PLC (PSR_F_BIT | PSR_I_BIT | SVC_MODE)
 	    : "r14");
 }
 
@@ -735,6 +750,7 @@ void __init setup_arch(char **cmdline_p)
 #endif
 
 	cpu_init();
+	tcm_init();
 
 	/*
 	 * Set up various architecture-specific pointers
diff --git a/arch/arm/kernel/signal.c b/arch/arm/kernel/signal.c
index f6bc5d442782..1423a3419789 100644
--- a/arch/arm/kernel/signal.c
+++ b/arch/arm/kernel/signal.c
@@ -12,6 +12,7 @@
 #include <linux/personality.h>
 #include <linux/freezer.h>
 #include <linux/uaccess.h>
+#include <linux/tracehook.h>
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -47,57 +48,22 @@ const unsigned long sigreturn_codes[7] = {
 	MOV_R7_NR_RT_SIGRETURN, SWI_SYS_RT_SIGRETURN, SWI_THUMB_RT_SIGRETURN,
 };
 
-static int do_signal(sigset_t *oldset, struct pt_regs * regs, int syscall);
-
 /*
  * atomically swap in the new signal mask, and wait for a signal.
  */
-asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask, struct pt_regs *regs)
+asmlinkage int sys_sigsuspend(int restart, unsigned long oldmask, old_sigset_t mask)
 {
-	sigset_t saveset;
-
 	mask &= _BLOCKABLE;
 	spin_lock_irq(&current->sighand->siglock);
-	saveset = current->blocked;
+	current->saved_sigmask = current->blocked;
 	siginitset(&current->blocked, mask);
 	recalc_sigpending();
 	spin_unlock_irq(&current->sighand->siglock);
-	regs->ARM_r0 = -EINTR;
 
-	while (1) {
-		current->state = TASK_INTERRUPTIBLE;
-		schedule();
-		if (do_signal(&saveset, regs, 0))
-			return regs->ARM_r0;
-	}
-}
-
-asmlinkage int
-sys_rt_sigsuspend(sigset_t __user *unewset, size_t sigsetsize, struct pt_regs *regs)
-{
-	sigset_t saveset, newset;
-
-	/* XXX: Don't preclude handling different sized sigset_t's. */
-	if (sigsetsize != sizeof(sigset_t))
-		return -EINVAL;
-
-	if (copy_from_user(&newset, unewset, sizeof(newset)))
-		return -EFAULT;
-	sigdelsetmask(&newset, ~_BLOCKABLE);
-
-	spin_lock_irq(&current->sighand->siglock);
-	saveset = current->blocked;
-	current->blocked = newset;
-	recalc_sigpending();
-	spin_unlock_irq(&current->sighand->siglock);
-	regs->ARM_r0 = -EINTR;
-
-	while (1) {
-		current->state = TASK_INTERRUPTIBLE;
-		schedule();
-		if (do_signal(&saveset, regs, 0))
-			return regs->ARM_r0;
-	}
+	current->state = TASK_INTERRUPTIBLE;
+	schedule();
+	set_restore_sigmask();
+	return -ERESTARTNOHAND;
 }
 
 asmlinkage int 
@@ -545,7 +511,7 @@ static inline void setup_syscall_restart(struct pt_regs *regs)
 /*
  * OK, we're invoking a handler
  */	
-static void
+static int
 handle_signal(unsigned long sig, struct k_sigaction *ka,
 	      siginfo_t *info, sigset_t *oldset,
 	      struct pt_regs * regs, int syscall)
@@ -596,7 +562,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
 
 	if (ret != 0) {
 		force_sigsegv(sig, tsk);
-		return;
+		return ret;
 	}
 
 	/*
@@ -610,6 +576,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
 	recalc_sigpending();
 	spin_unlock_irq(&tsk->sighand->siglock);
 
+	return 0;
 }
 
 /*
@@ -621,7 +588,7 @@ handle_signal(unsigned long sig, struct k_sigaction *ka,
  * the kernel can handle, and then we build all the user-level signal handling
  * stack-frames in one go after that.
  */
-static int do_signal(sigset_t *oldset, struct pt_regs *regs, int syscall)
+static void do_signal(struct pt_regs *regs, int syscall)
 {
 	struct k_sigaction ka;
 	siginfo_t info;
@@ -634,7 +601,7 @@ static int do_signal(sigset_t *oldset, struct pt_regs *regs, int syscall)
 	 * if so.
 	 */
 	if (!user_mode(regs))
-		return 0;
+		return;
 
 	if (try_to_freeze())
 		goto no_signal;
@@ -643,9 +610,24 @@ static int do_signal(sigset_t *oldset, struct pt_regs *regs, int syscall)
 
 	signr = get_signal_to_deliver(&info, &ka, regs, NULL);
 	if (signr > 0) {
-		handle_signal(signr, &ka, &info, oldset, regs, syscall);
+		sigset_t *oldset;
+
+		if (test_thread_flag(TIF_RESTORE_SIGMASK))
+			oldset = &current->saved_sigmask;
+		else
+			oldset = &current->blocked;
+		if (handle_signal(signr, &ka, &info, oldset, regs, syscall) == 0) {
+			/*
+			 * A signal was successfully delivered; the saved
+			 * sigmask will have been stored in the signal frame,
+			 * and will be restored by sigreturn, so we can simply
+			 * clear the TIF_RESTORE_SIGMASK flag.
+			 */
+			if (test_thread_flag(TIF_RESTORE_SIGMASK))
+				clear_thread_flag(TIF_RESTORE_SIGMASK);
+		}
 		single_step_set(current);
-		return 1;
+		return;
 	}
 
  no_signal:
@@ -697,14 +679,28 @@ static int do_signal(sigset_t *oldset, struct pt_regs *regs, int syscall)
 		    regs->ARM_r0 == -ERESTARTNOINTR) {
 			setup_syscall_restart(regs);
 		}
+
+		/* If there's no signal to deliver, we just put the saved sigmask
+		 * back.
+		 */
+		if (test_thread_flag(TIF_RESTORE_SIGMASK)) {
+			clear_thread_flag(TIF_RESTORE_SIGMASK);
+			sigprocmask(SIG_SETMASK, &current->saved_sigmask, NULL);
+		}
 	}
 	single_step_set(current);
-	return 0;
 }
 
 asmlinkage void
 do_notify_resume(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 {
 	if (thread_flags & _TIF_SIGPENDING)
-		do_signal(&current->blocked, regs, syscall);
+		do_signal(regs, syscall);
+
+	if (thread_flags & _TIF_NOTIFY_RESUME) {
+		clear_thread_flag(TIF_NOTIFY_RESUME);
+		tracehook_notify_resume(regs);
+		if (current->replacement_session_keyring)
+			key_replace_session_keyring();
+	}
 }
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index de885fd256c5..57162af53dc9 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -36,6 +36,7 @@
 #include <asm/tlbflush.h>
 #include <asm/ptrace.h>
 #include <asm/localtimer.h>
+#include <asm/smp_plat.h>
 
 /*
  * as from 2.5, kernels no longer have an init_tasks structure
@@ -153,7 +154,7 @@ int __cpuinit __cpu_up(unsigned int cpu)
 /*
  * __cpu_disable runs on the processor to be shutdown.
  */
-int __cpuexit __cpu_disable(void)
+int __cpu_disable(void)
 {
 	unsigned int cpu = smp_processor_id();
 	struct task_struct *p;
@@ -189,7 +190,7 @@ int __cpuexit __cpu_disable(void)
 	read_lock(&tasklist_lock);
 	for_each_process(p) {
 		if (p->mm)
-			cpu_clear(cpu, p->mm->cpu_vm_mask);
+			cpumask_clear_cpu(cpu, mm_cpumask(p->mm));
 	}
 	read_unlock(&tasklist_lock);
 
@@ -200,7 +201,7 @@ int __cpuexit __cpu_disable(void)
  * called on the thread which is asking for a CPU to be shutdown -
  * waits until shutdown has completed, or it is timed out.
  */
-void __cpuexit __cpu_die(unsigned int cpu)
+void __cpu_die(unsigned int cpu)
 {
 	if (!platform_cpu_kill(cpu))
 		printk("CPU%u: unable to kill\n", cpu);
@@ -214,7 +215,7 @@ void __cpuexit __cpu_die(unsigned int cpu)
  * of the other hotplug-cpu capable cores, so presumably coming
  * out of idle fixes this.
  */
-void __cpuexit cpu_die(void)
+void __ref cpu_die(void)
 {
 	unsigned int cpu = smp_processor_id();
 
@@ -257,7 +258,7 @@ asmlinkage void __cpuinit secondary_start_kernel(void)
 	atomic_inc(&mm->mm_users);
 	atomic_inc(&mm->mm_count);
 	current->active_mm = mm;
-	cpu_set(cpu, mm->cpu_vm_mask);
+	cpumask_set_cpu(cpu, mm_cpumask(mm));
 	cpu_switch_mm(mm->pgd, mm);
 	enter_lazy_tlb(mm, current);
 	local_flush_tlb_all();
@@ -586,12 +587,6 @@ struct tlb_args {
 	unsigned long ta_end;
 };
 
-/* all SMP configurations have the extended CPUID registers */
-static inline int tlb_ops_need_broadcast(void)
-{
-	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
-}
-
 static inline void ipi_flush_tlb_all(void *ignored)
 {
 	local_flush_tlb_all();
@@ -643,7 +638,7 @@ void flush_tlb_all(void)
 void flush_tlb_mm(struct mm_struct *mm)
 {
 	if (tlb_ops_need_broadcast())
-		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, &mm->cpu_vm_mask);
+		on_each_cpu_mask(ipi_flush_tlb_mm, mm, 1, mm_cpumask(mm));
 	else
 		local_flush_tlb_mm(mm);
 }
@@ -654,7 +649,7 @@ void flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 		struct tlb_args ta;
 		ta.ta_vma = vma;
 		ta.ta_start = uaddr;
-		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+		on_each_cpu_mask(ipi_flush_tlb_page, &ta, 1, mm_cpumask(vma->vm_mm));
 	} else
 		local_flush_tlb_page(vma, uaddr);
 }
@@ -677,7 +672,7 @@ void flush_tlb_range(struct vm_area_struct *vma,
 		ta.ta_vma = vma;
 		ta.ta_start = start;
 		ta.ta_end = end;
-		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, &vma->vm_mm->cpu_vm_mask);
+		on_each_cpu_mask(ipi_flush_tlb_range, &ta, 1, mm_cpumask(vma->vm_mm));
 	} else
 		local_flush_tlb_range(vma, start, end);
 }
diff --git a/arch/arm/kernel/smp_twd.c b/arch/arm/kernel/smp_twd.c
index d8c88c633c6f..a73a34dccf2a 100644
--- a/arch/arm/kernel/smp_twd.c
+++ b/arch/arm/kernel/smp_twd.c
@@ -166,10 +166,12 @@ void __cpuinit twd_timer_setup(struct clock_event_device *clk)
 	clockevents_register_device(clk);
 }
 
+#ifdef CONFIG_HOTPLUG_CPU
 /*
  * take a local timer down
  */
-void __cpuexit twd_timer_stop(void)
+void twd_timer_stop(void)
 {
 	__raw_writel(0, twd_base + TWD_TIMER_CONTROL);
 }
+#endif
diff --git a/arch/arm/kernel/stacktrace.c b/arch/arm/kernel/stacktrace.c
index 9f444e5cc165..20b7411e47fd 100644
--- a/arch/arm/kernel/stacktrace.c
+++ b/arch/arm/kernel/stacktrace.c
@@ -21,7 +21,7 @@
  * Note that with framepointer enabled, even the leaf functions have the same
  * prologue and epilogue, therefore we can ignore the LR value in this case.
  */
-int unwind_frame(struct stackframe *frame)
+int notrace unwind_frame(struct stackframe *frame)
 {
 	unsigned long high, low;
 	unsigned long fp = frame->fp;
@@ -43,7 +43,7 @@ int unwind_frame(struct stackframe *frame)
 }
 #endif
 
-void walk_stackframe(struct stackframe *frame,
+void notrace walk_stackframe(struct stackframe *frame,
 		     int (*fn)(struct stackframe *, void *), void *data)
 {
 	while (1) {
diff --git a/arch/arm/kernel/sys_arm.c b/arch/arm/kernel/sys_arm.c
index b3ec641b5cf8..78ecaac65206 100644
--- a/arch/arm/kernel/sys_arm.c
+++ b/arch/arm/kernel/sys_arm.c
@@ -25,7 +25,6 @@
 #include <linux/mman.h>
 #include <linux/fs.h>
 #include <linux/file.h>
-#include <linux/utsname.h>
 #include <linux/ipc.h>
 #include <linux/uaccess.h>
 
diff --git a/arch/arm/kernel/tcm.c b/arch/arm/kernel/tcm.c
new file mode 100644
index 000000000000..e50303868f1b
--- /dev/null
+++ b/arch/arm/kernel/tcm.c
@@ -0,0 +1,246 @@
+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/ioport.h>
+#include <linux/genalloc.h>
+#include <linux/string.h> /* memcpy */
+#include <asm/page.h> /* PAGE_SHIFT */
+#include <asm/cputype.h>
+#include <asm/mach/map.h>
+#include <mach/memory.h>
+#include "tcm.h"
+
+/* Scream and warn about misuse */
+#if !defined(ITCM_OFFSET) || !defined(ITCM_END) || \
+    !defined(DTCM_OFFSET) || !defined(DTCM_END)
+#error "TCM support selected but offsets not defined!"
+#endif
+
+static struct gen_pool *tcm_pool;
+
+/* TCM section definitions from the linker */
+extern char __itcm_start, __sitcm_text, __eitcm_text;
+extern char __dtcm_start, __sdtcm_data, __edtcm_data;
+
+/*
+ * TCM memory resources
+ */
+static struct resource dtcm_res = {
+	.name = "DTCM RAM",
+	.start = DTCM_OFFSET,
+	.end = DTCM_END,
+	.flags = IORESOURCE_MEM
+};
+
+static struct resource itcm_res = {
+	.name = "ITCM RAM",
+	.start = ITCM_OFFSET,
+	.end = ITCM_END,
+	.flags = IORESOURCE_MEM
+};
+
+static struct map_desc dtcm_iomap[] __initdata = {
+	{
+		.virtual	= DTCM_OFFSET,
+		.pfn		= __phys_to_pfn(DTCM_OFFSET),
+		.length		= (DTCM_END - DTCM_OFFSET + 1),
+		.type		= MT_UNCACHED
+	}
+};
+
+static struct map_desc itcm_iomap[] __initdata = {
+	{
+		.virtual	= ITCM_OFFSET,
+		.pfn		= __phys_to_pfn(ITCM_OFFSET),
+		.length		= (ITCM_END - ITCM_OFFSET + 1),
+		.type		= MT_UNCACHED
+	}
+};
+
+/*
+ * Allocate a chunk of TCM memory
+ */
+void *tcm_alloc(size_t len)
+{
+	unsigned long vaddr;
+
+	if (!tcm_pool)
+		return NULL;
+
+	vaddr = gen_pool_alloc(tcm_pool, len);
+	if (!vaddr)
+		return NULL;
+
+	return (void *) vaddr;
+}
+EXPORT_SYMBOL(tcm_alloc);
+
+/*
+ * Free a chunk of TCM memory
+ */
+void tcm_free(void *addr, size_t len)
+{
+	gen_pool_free(tcm_pool, (unsigned long) addr, len);
+}
+EXPORT_SYMBOL(tcm_free);
+
+
+static void __init setup_tcm_bank(u8 type, u32 offset, u32 expected_size)
+{
+	const int tcm_sizes[16] = { 0, -1, -1, 4, 8, 16, 32, 64, 128,
+				    256, 512, 1024, -1, -1, -1, -1 };
+	u32 tcm_region;
+	int tcm_size;
+
+	/* Read the special TCM region register c9, 0 */
+	if (!type)
+		asm("mrc	p15, 0, %0, c9, c1, 0"
+		    : "=r" (tcm_region));
+	else
+		asm("mrc	p15, 0, %0, c9, c1, 1"
+		    : "=r" (tcm_region));
+
+	tcm_size = tcm_sizes[(tcm_region >> 2) & 0x0f];
+	if (tcm_size < 0) {
+		pr_err("CPU: %sTCM of unknown size!\n",
+			type ? "I" : "D");
+	} else {
+		pr_info("CPU: found %sTCM %dk @ %08x, %senabled\n",
+			type ? "I" : "D",
+			tcm_size,
+			(tcm_region & 0xfffff000U),
+			(tcm_region & 1) ? "" : "not ");
+	}
+
+	if (tcm_size != expected_size) {
+		pr_crit("CPU: %sTCM was detected %dk but expected %dk!\n",
+		       type ? "I" : "D",
+		       tcm_size,
+		       expected_size);
+		/* Adjust to the expected size? what can we do... */
+	}
+
+	/* Force move the TCM bank to where we want it, enable */
+	tcm_region = offset | (tcm_region & 0x00000ffeU) | 1;
+
+	if (!type)
+		asm("mcr	p15, 0, %0, c9, c1, 0"
+		    : /* No output operands */
+		    : "r" (tcm_region));
+	else
+		asm("mcr	p15, 0, %0, c9, c1, 1"
+		    : /* No output operands */
+		    : "r" (tcm_region));
+
+	pr_debug("CPU: moved %sTCM %dk to %08x, enabled\n",
+		 type ? "I" : "D",
+		 tcm_size,
+		 (tcm_region & 0xfffff000U));
+}
+
+/*
+ * This initializes the TCM memory
+ */
+void __init tcm_init(void)
+{
+	u32 tcm_status = read_cpuid_tcmstatus();
+	char *start;
+	char *end;
+	char *ram;
+
+	/* Setup DTCM if present */
+	if (tcm_status & (1 << 16)) {
+		setup_tcm_bank(0, DTCM_OFFSET,
+			       (DTCM_END - DTCM_OFFSET + 1) >> 10);
+		request_resource(&iomem_resource, &dtcm_res);
+		iotable_init(dtcm_iomap, 1);
+		/* Copy data from RAM to DTCM */
+		start = &__sdtcm_data;
+		end   = &__edtcm_data;
+		ram   = &__dtcm_start;
+		memcpy(start, ram, (end-start));
+		pr_debug("CPU DTCM: copied data from %p - %p\n", start, end);
+	}
+
+	/* Setup ITCM if present */
+	if (tcm_status & 1) {
+		setup_tcm_bank(1, ITCM_OFFSET,
+			       (ITCM_END - ITCM_OFFSET + 1) >> 10);
+		request_resource(&iomem_resource, &itcm_res);
+		iotable_init(itcm_iomap, 1);
+		/* Copy code from RAM to ITCM */
+		start = &__sitcm_text;
+		end   = &__eitcm_text;
+		ram   = &__itcm_start;
+		memcpy(start, ram, (end-start));
+		pr_debug("CPU ITCM: copied code from %p - %p\n", start, end);
+	}
+}
+
+/*
+ * This creates the TCM memory pool and has to be done later,
+ * during the core_initicalls, since the allocator is not yet
+ * up and running when the first initialization runs.
+ */
+static int __init setup_tcm_pool(void)
+{
+	u32 tcm_status = read_cpuid_tcmstatus();
+	u32 dtcm_pool_start = (u32) &__edtcm_data;
+	u32 itcm_pool_start = (u32) &__eitcm_text;
+	int ret;
+
+	/*
+	 * Set up malloc pool, 2^2 = 4 bytes granularity since
+	 * the TCM is sometimes just 4 KiB. NB: pages and cache
+	 * line alignments does not matter in TCM!
+	 */
+	tcm_pool = gen_pool_create(2, -1);
+
+	pr_debug("Setting up TCM memory pool\n");
+
+	/* Add the rest of DTCM to the TCM pool */
+	if (tcm_status & (1 << 16)) {
+		if (dtcm_pool_start < DTCM_END) {
+			ret = gen_pool_add(tcm_pool, dtcm_pool_start,
+					   DTCM_END - dtcm_pool_start + 1, -1);
+			if (ret) {
+				pr_err("CPU DTCM: could not add DTCM " \
+				       "remainder to pool!\n");
+				return ret;
+			}
+			pr_debug("CPU DTCM: Added %08x bytes @ %08x to " \
+				 "the TCM memory pool\n",
+				 DTCM_END - dtcm_pool_start + 1,
+				 dtcm_pool_start);
+		}
+	}
+
+	/* Add the rest of ITCM to the TCM pool */
+	if (tcm_status & 1) {
+		if (itcm_pool_start < ITCM_END) {
+			ret = gen_pool_add(tcm_pool, itcm_pool_start,
+					   ITCM_END - itcm_pool_start + 1, -1);
+			if (ret) {
+				pr_err("CPU ITCM: could not add ITCM " \
+				       "remainder to pool!\n");
+				return ret;
+			}
+			pr_debug("CPU ITCM: Added %08x bytes @ %08x to " \
+				 "the TCM memory pool\n",
+				 ITCM_END - itcm_pool_start + 1,
+				 itcm_pool_start);
+		}
+	}
+	return 0;
+}
+
+core_initcall(setup_tcm_pool);
diff --git a/arch/arm/kernel/tcm.h b/arch/arm/kernel/tcm.h
new file mode 100644
index 000000000000..8015ad434a40
--- /dev/null
+++ b/arch/arm/kernel/tcm.h
@@ -0,0 +1,17 @@
+/*
+ * Copyright (C) 2008-2009 ST-Ericsson AB
+ * License terms: GNU General Public License (GPL) version 2
+ * TCM memory handling for ARM systems
+ *
+ * Author: Linus Walleij <linus.walleij@stericsson.com>
+ * Author: Rickard Andersson <rickard.andersson@stericsson.com>
+ */
+
+#ifdef CONFIG_HAVE_TCM
+void __init tcm_init(void);
+#else
+/* No TCM support, just blank inlines to be optimized out */
+inline void tcm_init(void)
+{
+}
+#endif
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index 57eb0f6f6005..467b69ed1021 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -418,12 +418,14 @@ static int bad_syscall(int n, struct pt_regs *regs)
 static inline void
 do_cache_op(unsigned long start, unsigned long end, int flags)
 {
+	struct mm_struct *mm = current->active_mm;
 	struct vm_area_struct *vma;
 
 	if (end < start || flags)
 		return;
 
-	vma = find_vma(current->active_mm, start);
+	down_read(&mm->mmap_sem);
+	vma = find_vma(mm, start);
 	if (vma && vma->vm_start < end) {
 		if (start < vma->vm_start)
 			start = vma->vm_start;
@@ -432,6 +434,7 @@ do_cache_op(unsigned long start, unsigned long end, int flags)
 
 		flush_cache_user_range(vma, start, end);
 	}
+	up_read(&mm->mmap_sem);
 }
 
 /*
diff --git a/arch/arm/kernel/unwind.c b/arch/arm/kernel/unwind.c
index dd56e11f339a..39baf1128bfa 100644
--- a/arch/arm/kernel/unwind.c
+++ b/arch/arm/kernel/unwind.c
@@ -62,7 +62,11 @@ struct unwind_ctrl_block {
 };
 
 enum regs {
+#ifdef CONFIG_THUMB2_KERNEL
+	FP = 7,
+#else
 	FP = 11,
+#endif
 	SP = 13,
 	LR = 14,
 	PC = 15
diff --git a/arch/arm/kernel/vmlinux.lds.S b/arch/arm/kernel/vmlinux.lds.S
index 69371028a202..aecf87dfbaec 100644
--- a/arch/arm/kernel/vmlinux.lds.S
+++ b/arch/arm/kernel/vmlinux.lds.S
@@ -83,6 +83,7 @@ SECTIONS
 		EXIT_TEXT
 		EXIT_DATA
 		*(.exitcall.exit)
+		*(.discard)
 		*(.ARM.exidx.exit.text)
 		*(.ARM.extab.exit.text)
 #ifndef CONFIG_HOTPLUG_CPU
@@ -198,6 +199,63 @@ SECTIONS
 	}
 	_edata_loc = __data_loc + SIZEOF(.data);
 
+#ifdef CONFIG_HAVE_TCM
+        /*
+	 * We align everything to a page boundary so we can
+	 * free it after init has commenced and TCM contents have
+	 * been copied to its destination.
+	 */
+	.tcm_start : {
+		. = ALIGN(PAGE_SIZE);
+		__tcm_start = .;
+		__itcm_start = .;
+	}
+
+	/*
+	 * Link these to the ITCM RAM
+	 * Put VMA to the TCM address and LMA to the common RAM
+	 * and we'll upload the contents from RAM to TCM and free
+	 * the used RAM after that.
+	 */
+	.text_itcm ITCM_OFFSET : AT(__itcm_start)
+	{
+		__sitcm_text = .;
+		*(.tcm.text)
+		*(.tcm.rodata)
+		. = ALIGN(4);
+		__eitcm_text = .;
+	}
+
+	/*
+	 * Reset the dot pointer, this is needed to create the
+	 * relative __dtcm_start below (to be used as extern in code).
+	 */
+	. = ADDR(.tcm_start) + SIZEOF(.tcm_start) + SIZEOF(.text_itcm);
+
+	.dtcm_start : {
+		__dtcm_start = .;
+	}
+
+	/* TODO: add remainder of ITCM as well, that can be used for data! */
+	.data_dtcm DTCM_OFFSET : AT(__dtcm_start)
+	{
+		. = ALIGN(4);
+		__sdtcm_data = .;
+		*(.tcm.data)
+		. = ALIGN(4);
+		__edtcm_data = .;
+	}
+
+	/* Reset the dot pointer or the linker gets confused */
+	. = ADDR(.dtcm_start) + SIZEOF(.data_dtcm);
+
+	/* End marker for freeing TCM copy in linked object */
+	.tcm_end : AT(ADDR(.dtcm_start) + SIZEOF(.data_dtcm)){
+		. = ALIGN(PAGE_SIZE);
+		__tcm_end = .;
+	}
+#endif
+
 	.bss : {
 		__bss_start = .;	/* BSS				*/
 		*(.bss)