Merge remote branch 'catalin/stable-2.6.35'

Conflicts:
	arch/arm/kernel/Makefile
	arch/arm/kernel/entry-armv.S
	arch/arm/mm/mmu.c

41 files changed, 838 insertions, 196 deletions

diff --git a/Documentation/arm/00-INDEX b/Documentation/arm/00-INDEX
index 7f5fc3ba9c9..2d025641ec5 100644
--- a/Documentation/arm/00-INDEX
+++ b/Documentation/arm/00-INDEX
@@ -32,3 +32,5 @@ memory.txt
 	- description of the virtual memory layout
 nwfpe/
 	- NWFPE floating point emulator documentation
+swp_emulation
+	- SWP/SWPB emulation handler/logging description
diff --git a/Documentation/arm/swp_emulation b/Documentation/arm/swp_emulation
new file mode 100644
index 00000000000..af903d22fd9
--- /dev/null
+++ b/Documentation/arm/swp_emulation
@@ -0,0 +1,27 @@
+Software emulation of deprecated SWP instruction (CONFIG_SWP_EMULATE)
+---------------------------------------------------------------------
+
+ARMv6 architecture deprecates use of the SWP/SWPB instructions, and recommeds
+moving to the load-locked/store-conditional instructions LDREX and STREX.
+
+ARMv7 multiprocessing extensions introduce the ability to disable these
+instructions, triggering an undefined instruction exception when executed.
+Trapped instructions are emulated using an LDREX/STREX or LDREXB/STREXB
+sequence. If a memory access fault (an abort) occurs, a segmentation fault is
+signalled to the triggering process.
+
+/proc/cpu/swp_emulation holds some statistics/information, including the PID of
+the last process to trigger the emulation to be invocated. For example:
+---
+Emulated SWP:		12
+Emulated SWPB:		0
+Aborted SWP{B}:		1
+Last process:		314
+---
+
+NOTE: when accessing uncached shared regions, LDREX/STREX rely on an external
+transaction monitoring block called a global monitor to maintain update
+atomicity. If your system does not implement a global monitor, this option can
+cause programs that perform SWP operations to uncached memory to deadlock, as
+the STREX operation will always fail.
+
diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index e39caa8b0c9..47a9084c6c3 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -1030,6 +1030,18 @@ config PL310_ERRATA_588369
 	   is not correctly implemented in PL310 as clean lines are not
 	   invalidated as a result of these operations. Note that this errata
 	   uses Texas Instrument's secure monitor api.
+
+config ARM_ERRATA_720789
+	bool "ARM errata: TLBIASIDIS and TLBIMVAIS operations can broadcast a faulty ASID"
+	depends on CPU_V7 && SMP
+	help
+	  This option enables the workaround for the 720789 Cortex-A9 (prior to
+	  r2p0) erratum. A faulty ASID can be sent to the other CPUs for the
+	  broadcasted CP15 TLB maintenance operations TLBIASIDIS and TLBIMVAIS.
+	  As a consequence of this erratum, some TLB entries which should be
+	  invalidated are not, resulting in an incoherency in the system page
+	  tables. The workaround changes the TLB flushing routines to invalidate
+	  entries regardless of the ASID.
 endmenu
 
 source "arch/arm/common/Kconfig"
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index 6e8f05c8a1c..66db132cf1c 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -18,6 +18,7 @@
 #endif
 
 #include <asm/ptrace.h>
+#include <asm/domain.h>
 
 /*
  * Endian independent macros for shifting bytes within registers.
@@ -183,12 +184,12 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 
-	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort
+	.macro	usraccoff, instr, reg, ptr, inc, off, cond, abort, t=T()
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr, #\off]
+	\instr\cond\()b\()\t\().w \reg, [\ptr, #\off]
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr, #\off]
+	\instr\cond\()\t\().w \reg, [\ptr, #\off]
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
@@ -223,13 +224,13 @@
 
 #else	/* !CONFIG_THUMB2_KERNEL */
 
-	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort
+	.macro	usracc, instr, reg, ptr, inc, cond, rept, abort, t=T()
 	.rept	\rept
 9999:
 	.if	\inc == 1
-	\instr\cond\()bt \reg, [\ptr], #\inc
+	\instr\cond\()b\()\t \reg, [\ptr], #\inc
 	.elseif	\inc == 4
-	\instr\cond\()t \reg, [\ptr], #\inc
+	\instr\cond\()\t \reg, [\ptr], #\inc
 	.else
 	.error	"Unsupported inc macro argument"
 	.endif
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 4656a24058d..042e13994d3 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -137,10 +137,10 @@
 #endif
 
 /*
- * This flag is used to indicate that the page pointed to by a pte
- * is dirty and requires cleaning before returning it to the user.
+ * This flag is used to indicate that the page pointed to by a pte is clean
+ * and does not require cleaning before returning it to the user.
  */
-#define PG_dcache_dirty PG_arch_1
+#define PG_dcache_clean PG_arch_1
 
 /*
  *	MM Cache Management
@@ -405,9 +405,6 @@ static inline void flush_anon_page(struct vm_area_struct *vma,
 #define ARCH_HAS_FLUSH_KERNEL_DCACHE_PAGE
 static inline void flush_kernel_dcache_page(struct page *page)
 {
-	/* highmem pages are always flushed upon kunmap already */
-	if ((cache_is_vivt() || cache_is_vipt_aliasing()) && !PageHighMem(page))
-		__cpuc_flush_dcache_area(page_address(page), PAGE_SIZE);
 }
 
 #define flush_dcache_mmap_lock(mapping) \
diff --git a/arch/arm/include/asm/domain.h b/arch/arm/include/asm/domain.h
index cc7ef408071..af18ceaacf5 100644
--- a/arch/arm/include/asm/domain.h
+++ b/arch/arm/include/asm/domain.h
@@ -45,13 +45,17 @@
  */
 #define DOMAIN_NOACCESS	0
 #define DOMAIN_CLIENT	1
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define DOMAIN_MANAGER	3
+#else
+#define DOMAIN_MANAGER	1
+#endif
 
 #define domain_val(dom,type)	((type) << (2*(dom)))
 
 #ifndef __ASSEMBLY__
 
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 #define set_domain(x)					\
 	do {						\
 	__asm__ __volatile__(				\
@@ -74,5 +78,28 @@
 #define modify_domain(dom,type)	do { } while (0)
 #endif
 
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions (inline assembly)
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)	#instr "t"
+#else
+#define T(instr)	#instr
 #endif
-#endif /* !__ASSEMBLY__ */
+
+#else /* __ASSEMBLY__ */
+
+/*
+ * Generate the T (user) versions of the LDR/STR and related
+ * instructions
+ */
+#ifdef CONFIG_CPU_USE_DOMAINS
+#define T(instr)	instr ## t
+#else
+#define T(instr)	instr
+#endif
+
+#endif /* __ASSEMBLY__ */
+
+#endif /* !__ASM_PROC_DOMAIN_H */
diff --git a/arch/arm/include/asm/elf.h b/arch/arm/include/asm/elf.h
index 6750b8e45a4..5747a8baa41 100644
--- a/arch/arm/include/asm/elf.h
+++ b/arch/arm/include/asm/elf.h
@@ -59,6 +59,8 @@ typedef struct user_fp elf_fpregset_t;
 
 #define R_ARM_THM_CALL		10
 #define R_ARM_THM_JUMP24	30
+#define R_ARM_THM_MOVW_ABS_NC	47
+#define R_ARM_THM_MOVT_ABS	48
 
 /*
  * These are used to set parameters in the core dumps.
diff --git a/arch/arm/include/asm/futex.h b/arch/arm/include/asm/futex.h
index 540a044153a..b33fe7065b3 100644
--- a/arch/arm/include/asm/futex.h
+++ b/arch/arm/include/asm/futex.h
@@ -13,12 +13,13 @@
 #include <linux/preempt.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 #define __futex_atomic_op(insn, ret, oldval, uaddr, oparg)	\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1, [%2]\n"				\
+	"1:	" T(ldr) "	%1, [%2]\n"			\
 	"	" insn "\n"					\
-	"2:	strt	%0, [%2]\n"				\
+	"2:	" T(str) "	%0, [%2]\n"			\
 	"	mov	%0, #0\n"				\
 	"3:\n"							\
 	"	.pushsection __ex_table,\"a\"\n"		\
@@ -97,10 +98,10 @@ futex_atomic_cmpxchg_inatomic(int __user *uaddr, int oldval, int newval)
 	pagefault_disable();	/* implies preempt_disable() */
 
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
-	"1:	ldrt	%0, [%3]\n"
+	"1:	" T(ldr) "	%0, [%3]\n"
 	"	teq	%0, %1\n"
 	"	it	eq	@ explicit IT needed for the 2b label\n"
-	"2:	streqt	%2, [%3]\n"
+	"2:	" T(streq) "	%2, [%3]\n"
 	"3:\n"
 	"	.pushsection __ex_table,\"a\"\n"
 	"	.align	3\n"
diff --git a/arch/arm/include/asm/pgtable.h b/arch/arm/include/asm/pgtable.h
index ab68cf1ef80..ea19775fa53 100644
--- a/arch/arm/include/asm/pgtable.h
+++ b/arch/arm/include/asm/pgtable.h
@@ -278,9 +278,24 @@ extern struct page *empty_zero_page;
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 
-#define set_pte_at(mm,addr,ptep,pteval) do { \
-	set_pte_ext(ptep, pteval, (addr) >= TASK_SIZE ? 0 : PTE_EXT_NG); \
- } while (0)
+#if __LINUX_ARM_ARCH__ < 6
+static inline void __sync_icache_dcache(pte_t pteval)
+{
+}
+#else
+extern void __sync_icache_dcache(pte_t pteval);
+#endif
+
+static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
+			      pte_t *ptep, pte_t pteval)
+{
+	if (addr >= TASK_SIZE)
+		set_pte_ext(ptep, pteval, 0);
+	else {
+		__sync_icache_dcache(pteval);
+		set_pte_ext(ptep, pteval, PTE_EXT_NG);
+	}
+}
 
 /*
  * The following only work if pte_present() is true.
@@ -290,8 +305,13 @@ extern struct page *empty_zero_page;
 #define pte_write(pte)		(pte_val(pte) & L_PTE_WRITE)
 #define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
+#define pte_exec(pte)		(pte_val(pte) & L_PTE_EXEC)
 #define pte_special(pte)	(0)
 
+#define pte_present_user(pte) \
+	((pte_val(pte) & (L_PTE_PRESENT | L_PTE_USER)) == \
+	 (L_PTE_PRESENT | L_PTE_USER))
+
 #define PTE_BIT_FUNC(fn,op) \
 static inline pte_t pte_##fn(pte_t pte) { pte_val(pte) op; return pte; }
 
@@ -317,6 +337,9 @@ static inline pte_t pte_mkspecial(pte_t pte) { return pte; }
 #ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_BUFFERABLE)
+#define __HAVE_PHYS_MEM_ACCESS_PROT
+extern pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+				     unsigned long size, pgprot_t vma_prot);
 #else
 #define pgprot_dmacoherent(prot) \
 	__pgprot_modify(prot, L_PTE_MT_MASK|L_PTE_EXEC, L_PTE_MT_UNCACHED)
diff --git a/arch/arm/include/asm/smp_plat.h b/arch/arm/include/asm/smp_plat.h
index e6215305544..963a338d567 100644
--- a/arch/arm/include/asm/smp_plat.h
+++ b/arch/arm/include/asm/smp_plat.h
@@ -13,9 +13,13 @@ static inline int tlb_ops_need_broadcast(void)
 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 2;
 }
 
+#if !defined(CONFIG_SMP) || __LINUX_ARM_ARCH__ >= 7
+#define cache_ops_need_broadcast()	0
+#else
 static inline int cache_ops_need_broadcast(void)
 {
 	return ((read_cpuid_ext(CPUID_EXT_MMFR3) >> 12) & 0xf) < 1;
 }
+#endif
 
 #endif
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index bd863d8608c..989c9e57d92 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -378,7 +378,11 @@ static inline void local_flush_tlb_mm(struct mm_struct *mm)
 	if (tlb_flag(TLB_V6_I_ASID))
 		asm("mcr p15, 0, %0, c8, c5, 2" : : "r" (asid) : "cc");
 	if (tlb_flag(TLB_V7_UIS_ASID))
+#ifdef CONFIG_ARM_ERRATA_720789
+		asm("mcr p15, 0, %0, c8, c3, 0" : : "r" (zero) : "cc");
+#else
 		asm("mcr p15, 0, %0, c8, c3, 2" : : "r" (asid) : "cc");
+#endif
 
 	if (tlb_flag(TLB_BTB)) {
 		/* flush the branch target cache */
@@ -424,7 +428,11 @@ local_flush_tlb_page(struct vm_area_struct *vma, unsigned long uaddr)
 	if (tlb_flag(TLB_V6_I_PAGE))
 		asm("mcr p15, 0, %0, c8, c5, 1" : : "r" (uaddr) : "cc");
 	if (tlb_flag(TLB_V7_UIS_PAGE))
+#ifdef CONFIG_ARM_ERRATA_720789
+		asm("mcr p15, 0, %0, c8, c3, 3" : : "r" (uaddr & PAGE_MASK) : "cc");
+#else
 		asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (uaddr) : "cc");
+#endif
 
 	if (tlb_flag(TLB_BTB)) {
 		/* flush the branch target cache */
@@ -552,12 +560,20 @@ extern void flush_tlb_kernel_range(unsigned long start, unsigned long end);
 #endif
 
 /*
- * if PG_dcache_dirty is set for the page, we need to ensure that any
+ * If PG_dcache_clean is not set for the page, we need to ensure that any
  * cache entries for the kernels virtual memory range are written
- * back to the page.
+ * back to the page. On ARMv6 and later, the cache coherency is handled via
+ * the set_pte_at() function.
  */
+#if __LINUX_ARM_ARCH__ < 6
 extern void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 	pte_t *ptep);
+#else
+static inline void update_mmu_cache(struct vm_area_struct *vma,
+				    unsigned long addr, pte_t *ptep)
+{
+}
+#endif
 
 #endif
 
diff --git a/arch/arm/include/asm/traps.h b/arch/arm/include/asm/traps.h
index 491960bf426..af5d5d1388c 100644
--- a/arch/arm/include/asm/traps.h
+++ b/arch/arm/include/asm/traps.h
@@ -27,4 +27,6 @@ static inline int in_exception_text(unsigned long ptr)
 extern void __init early_trap_init(void);
 extern void dump_backtrace_entry(unsigned long where, unsigned long from, unsigned long frame);
 
+extern void *vectors_page;
+
 #endif
diff --git a/arch/arm/include/asm/uaccess.h b/arch/arm/include/asm/uaccess.h
index 33e4a48fe10..b293616a1a1 100644
--- a/arch/arm/include/asm/uaccess.h
+++ b/arch/arm/include/asm/uaccess.h
@@ -227,7 +227,7 @@ do {									\
 
 #define __get_user_asm_byte(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrbt	%1,[%2]\n"				\
+	"1:	" T(ldrb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -263,7 +263,7 @@ do {									\
 
 #define __get_user_asm_word(x,addr,err)				\
 	__asm__ __volatile__(					\
-	"1:	ldrt	%1,[%2]\n"				\
+	"1:	" T(ldr) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -308,7 +308,7 @@ do {									\
 
 #define __put_user_asm_byte(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strbt	%1,[%2]\n"				\
+	"1:	" T(strb) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -341,7 +341,7 @@ do {									\
 
 #define __put_user_asm_word(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
-	"1:	strt	%1,[%2]\n"				\
+	"1:	" T(str) "	%1,[%2],#0\n"			\
 	"2:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
@@ -366,10 +366,10 @@ do {									\
 
 #define __put_user_asm_dword(x,__pu_addr,err)			\
 	__asm__ __volatile__(					\
- ARM(	"1:	strt	" __reg_oper1 ", [%1], #4\n"	)	\
- ARM(	"2:	strt	" __reg_oper0 ", [%1]\n"	)	\
- THUMB(	"1:	strt	" __reg_oper1 ", [%1]\n"	)	\
- THUMB(	"2:	strt	" __reg_oper0 ", [%1, #4]\n"	)	\
+ ARM(	"1:	" T(str) "	" __reg_oper1 ", [%1], #4\n"	)	\
+ ARM(	"2:	" T(str) "	" __reg_oper0 ", [%1]\n"	)	\
+ THUMB(	"1:	" T(str) "	" __reg_oper1 ", [%1]\n"	)	\
+ THUMB(	"2:	" T(str) "	" __reg_oper0 ", [%1, #4]\n"	)	\
 	"3:\n"							\
 	"	.pushsection .fixup,\"ax\"\n"			\
 	"	.align	2\n"					\
diff --git a/arch/arm/kernel/Makefile b/arch/arm/kernel/Makefile
index 980b78e3132..d3430eed9b9 100644
--- a/arch/arm/kernel/Makefile
+++ b/arch/arm/kernel/Makefile
@@ -42,6 +42,7 @@ obj-$(CONFIG_KGDB)		+= kgdb.o
 obj-$(CONFIG_ARM_UNWIND)	+= unwind.o
 obj-$(CONFIG_HAVE_TCM)		+= tcm.o
 obj-$(CONFIG_CRASH_DUMP)	+= crash_dump.o
+obj-$(CONFIG_SWP_EMULATE)	+= swp_emulate.o
 
 obj-$(CONFIG_CRUNCH)		+= crunch.o crunch-bits.o
 AFLAGS_crunch-bits.o		:= -Wa,-mcpu=ep9312
diff --git a/arch/arm/kernel/entry-armv.S b/arch/arm/kernel/entry-armv.S
index bb8e93a7640..1e0017a9faa 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -733,7 +733,7 @@ ENTRY(__switch_to)
  THUMB(	stmia	ip!, {r4 - sl, fp}	   )	@ Store most regs on stack
  THUMB(	str	sp, [ip], #4		   )
  THUMB(	str	lr, [ip], #4		   )
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 	ldr	r6, [r2, #TI_CPU_DOMAIN]
 #endif
 	set_tls	r3, r4, r5
@@ -742,7 +742,7 @@ ENTRY(__switch_to)
 	ldr	r8, =__stack_chk_guard
 	ldr	r7, [r7, #TSK_STACK_CANARY]
 #endif
-#ifdef CONFIG_MMU
+#ifdef CONFIG_CPU_USE_DOMAINS
 	mcr	p15, 0, r6, c3, c0, 0		@ Set domain register
 #endif
 	mov	r5, r0
@@ -1184,7 +1184,7 @@ __stubs_start:
 
 	.align	5
 
-/*=============================================================================
+/*============================================================================
  * Undefined FIQs
  *-----------------------------------------------------------------------------
  * Enter in FIQ mode, spsr = ANY CPSR, lr = ANY PC
diff --git a/arch/arm/kernel/fiq.c b/arch/arm/kernel/fiq.c
index 6ff7919613d..d601ef297eb 100644
--- a/arch/arm/kernel/fiq.c
+++ b/arch/arm/kernel/fiq.c
@@ -45,6 +45,7 @@
 #include <asm/fiq.h>
 #include <asm/irq.h>
 #include <asm/system.h>
+#include <asm/traps.h>
 
 static unsigned long no_fiq_insn;
 
@@ -77,7 +78,11 @@ int show_fiq_list(struct seq_file *p, void *v)
 
 void set_fiq_handler(void *start, unsigned int length)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
 	memcpy((void *)0xffff001c, start, length);
+#else
+	memcpy(vectors_page + 0x1c, start, length);
+#endif
 	flush_icache_range(0xffff001c, 0xffff001c + length);
 	if (!vectors_high())
 		flush_icache_range(0x1c, 0x1c + length);
diff --git a/arch/arm/kernel/module.c b/arch/arm/kernel/module.c
index c628bdf6c43..6b4605893f1 100644
--- a/arch/arm/kernel/module.c
+++ b/arch/arm/kernel/module.c
@@ -102,7 +102,9 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 		unsigned long loc;
 		Elf32_Sym *sym;
 		s32 offset;
+#ifdef CONFIG_THUMB2_KERNEL
 		u32 upper, lower, sign, j1, j2;
+#endif
 
 		offset = ELF32_R_SYM(rel->r_info);
 		if (offset < 0 || offset > (symsec->sh_size / sizeof(Elf32_Sym))) {
@@ -185,6 +187,7 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 					(offset & 0x0fff);
 			break;
 
+#ifdef CONFIG_THUMB2_KERNEL
 		case R_ARM_THM_CALL:
 		case R_ARM_THM_JUMP24:
 			upper = *(u16 *)loc;
@@ -233,9 +236,40 @@ apply_relocate(Elf32_Shdr *sechdrs, const char *strtab, unsigned int symindex,
 			*(u16 *)(loc + 2) = (u16)((lower & 0xd000) |
 						  (j1 << 13) | (j2 << 11) |
 						  ((offset >> 1) & 0x07ff));
+			break;
+
+		case R_ARM_THM_MOVW_ABS_NC:
+		case R_ARM_THM_MOVT_ABS:
 			upper = *(u16 *)loc;
 			lower = *(u16 *)(loc + 2);
+
+			/*
+			 * MOVT/MOVW instructions encoding in Thumb-2:
+			 *
+			 * i	= upper[10]
+			 * imm4	= upper[3:0]
+			 * imm3	= lower[14:12]
+			 * imm8	= lower[7:0]
+			 *
+			 * imm16 = imm4:i:imm3:imm8
+			 */
+			offset = ((upper & 0x000f) << 12) |
+				((upper & 0x0400) << 1) |
+				((lower & 0x7000) >> 4) | (lower & 0x00ff);
+			offset = (offset ^ 0x8000) - 0x8000;
+			offset += sym->st_value;
+
+			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));
 			break;
+#endif
 
 		default:
 			printk(KERN_ERR "%s: unknown relocation: %u\n",
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index d5231ae7355..3692a292056 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -224,7 +224,7 @@ int cpu_architecture(void)
 		 * Register 0 and check for VMSAv7 or PMSAv7 */
 		asm("mrc	p15, 0, %0, c0, c1, 4"
 		    : "=r" (mmfr0));
-		if ((mmfr0 & 0x0000000f) == 0x00000003 ||
+		if ((mmfr0 & 0x0000000f) >= 0x00000003 ||
 		    (mmfr0 & 0x000000f0) == 0x00000030)
 			cpu_arch = CPU_ARCH_ARMv7;
 		else if ((mmfr0 & 0x0000000f) == 0x00000002 ||
diff --git a/arch/arm/kernel/swp_emulate.c b/arch/arm/kernel/swp_emulate.c
new file mode 100644
index 00000000000..c254d1dab9e
--- /dev/null
+++ b/arch/arm/kernel/swp_emulate.c
@@ -0,0 +1,260 @@
+/*
+ *  linux/arch/arm/kernel/swp_emulate.c
+ *
+ *  Copyright (C) 2009 ARM Limited
+ *  __user_* functions adapted from include/asm/uaccess.h
+ *
+ * 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.
+ *
+ *  Implements emulation of the SWP/SWPB instructions using load-exclusive and
+ *  store-exclusive for processors that have them disabled (or future ones that
+ *  might not implement them).
+ *
+ *  Syntax of SWP{B} instruction: SWP{B}<c> <Rt>, <Rt2>, [<Rn>]
+ *  Where: Rt  = destination
+ *	   Rt2 = source
+ *	   Rn  = address
+ */
+
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/proc_fs.h>
+#include <linux/sched.h>
+#include <linux/syscalls.h>
+
+#include <asm/traps.h>
+#include <asm/uaccess.h>
+
+/*
+ * Error-checking SWP macros implemented using ldrex{b}/strex{b}
+ */
+#define __user_swpX_asm(data, addr, res, B)			\
+	__asm__ __volatile__(					\
+	"	mov		r3, %1\n"			\
+	"0:	ldrex"B"	%1, [%2]\n"			\
+	"1:	strex"B"	%0, r3, [%2]\n"			\
+	"	cmp		%0, #0\n"			\
+	"	movne		%0, %3\n"			\
+	"2:\n"							\
+	"	.section	 .fixup,\"ax\"\n"		\
+	"	.align		2\n"				\
+	"3:	mov		%0, %4\n"			\
+	"	b		2b\n"				\
+	"	.previous\n"					\
+	"	.section	 __ex_table,\"a\"\n"		\
+	"	.align		3\n"				\
+	"	.long		0b, 3b\n"			\
+	"	.long		1b, 3b\n"			\
+	"	.previous"					\
+	: "=&r" (res), "+r" (data)				\
+	: "r" (addr), "i" (-EAGAIN), "i" (-EFAULT)		\
+	: "cc", "r3")
+
+#define __user_swp_asm(data, addr, res) __user_swpX_asm(data, addr, res, "")
+#define __user_swpb_asm(data, addr, res) __user_swpX_asm(data, addr, res, "b")
+
+/*
+ * Macros/defines for extracting register numbers from instruction.
+ */
+#define EXTRACT_REG_NUM(instruction, offset) \
+  (((instruction) & (0xf << (offset))) >> (offset))
+#define RN_OFFSET  16
+#define RT_OFFSET  12
+#define RT2_OFFSET  0
+/*
+ * Bit 22 of the instruction encoding distinguishes between
+ * the SWP and SWPB variants (bit set means SWPB).
+ */
+#define TYPE_SWPB (1 << 22)
+
+static unsigned long long swpcounter;
+static unsigned long long swpbcounter;
+static unsigned long long abtcounter;
+static long		  previous_pid;
+
+#ifdef CONFIG_PROC_FS
+static int proc_read_status(char *page, char **start, off_t off, int count,
+			    int *eof, void *data)
+{
+	char *p = page;
+	int len;
+
+	p += sprintf(p, "Emulated SWP:\t\t%llu\n", swpcounter);
+	p += sprintf(p, "Emulated SWPB:\t\t%llu\n", swpbcounter);
+	p += sprintf(p, "Aborted SWP{B}:\t\t%llu\n", abtcounter);
+	if (previous_pid != 0)
+		p += sprintf(p, "Last process:\t\t%ld\n", previous_pid);
+
+	len = (p - page) - off;
+	if (len < 0)
+		len = 0;
+
+	*eof = (len <= count) ? 1 : 0;
+	*start = page + off;
+
+	return len;
+}
+#endif
+
+/*
+ * Set up process info to signal segmentation fault - called on access error.
+ */
+static void set_segfault(struct pt_regs *regs, unsigned long addr)
+{
+	siginfo_t info;
+
+	if (find_vma(current->mm, addr) == NULL)
+		info.si_code = SEGV_MAPERR;
+	else
+		info.si_code = SEGV_ACCERR;
+
+	info.si_signo = SIGSEGV;
+	info.si_errno = 0;
+	info.si_addr  = (void *) instruction_pointer(regs);
+
+	pr_debug("SWP{B} emulation: access caused memory abort!\n");
+	arm_notify_die("Illegal memory access", regs, &info, 0, 0);
+
+	abtcounter++;
+}
+
+static int emulate_swpX(unsigned int address, unsigned int *data,
+			unsigned int type)
+{
+	unsigned int res = 0;
+
+	if ((type != TYPE_SWPB) && (address & 0x3)) {
+		/* SWP to unaligned address not permitted */
+		pr_debug("SWP instruction on unaligned pointer!\n");
+		return -EFAULT;
+	}
+
+	while (1) {
+		/*
+		 * Barrier required between accessing protected resource and
+		 * releasing a lock for it. Legacy code might not have done
+		 * this, and we cannot determine that this is not the case
+		 * being emulated, so insert always.
+		 */
+		smp_mb();
+
+		if (type == TYPE_SWPB)
+			__user_swpb_asm(*data, address, res);
+		else
+			__user_swp_asm(*data, address, res);
+
+		if (likely(res != -EAGAIN) || signal_pending(current))
+			break;
+
+		cond_resched();
+	}
+
+	if (res == 0) {
+		/*
+		 * Barrier also required between aquiring a lock for a
+		 * protected resource and accessing the resource. Inserted for
+		 * same reason as above.
+		 */
+		smp_mb();
+
+		if (type == TYPE_SWPB)
+			swpbcounter++;
+		else
+			swpcounter++;
+	}
+
+	return res;
+}
+
+/*
+ * swp_handler logs the id of calling process, dissects the instruction, sanity
+ * checks the memory location, calls emulate_swpX for the actual operation and
+ * deals with fixup/error handling before returning
+ */
+static int swp_handler(struct pt_regs *regs, unsigned int instr)
+{
+	unsigned int address, destreg, data, type;
+	unsigned int res = 0;
+
+	if (current->pid != previous_pid) {
+		pr_debug("\"%s\" (%ld) uses deprecated SWP{B} instruction\n",
+			 current->comm, (unsigned long)current->pid);
+		previous_pid = current->pid;
+	}
+
+	address = regs->uregs[EXTRACT_REG_NUM(instr, RN_OFFSET)];
+	data	= regs->uregs[EXTRACT_REG_NUM(instr, RT2_OFFSET)];
+	destreg = EXTRACT_REG_NUM(instr, RT_OFFSET);
+
+	type = instr & TYPE_SWPB;
+
+	pr_debug("addr in r%d->0x%08x, dest is r%d, source in r%d->0x%08x)\n",
+		 EXTRACT_REG_NUM(instr, RN_OFFSET), address,
+		 destreg, EXTRACT_REG_NUM(instr, RT2_OFFSET), data);
+
+	/* Check access in reasonable access range for both SWP and SWPB */
+	if (!access_ok(VERIFY_WRITE, (address & ~3), 4)) {
+		pr_debug("SWP{B} emulation: access to %p not allowed!\n",
+			 (void *)address);
+		res = -EFAULT;
+	} else {
+		res = emulate_swpX(address, &data, type);
+	}
+
+	if (res == 0) {
+		/*
+		 * On successful emulation, revert the adjustment to the PC
+		 * made in kernel/traps.c in order to resume execution at the
+		 * instruction following the SWP{B}.
+		 */
+		regs->ARM_pc += 4;
+		regs->uregs[destreg] = data;
+	} else if (res == -EFAULT) {
+		/*
+		 * Memory errors do not mean emulation failed.
+		 * Set up signal info to return SEGV, then return OK
+		 */
+		set_segfault(regs, address);
+	}
+
+	return 0;
+}
+
+/*
+ * Only emulate SWP/SWPB executed in ARM state/User mode.
+ * The kernel must be SWP free and SWP{B} does not exist in Thumb/ThumbEE.
+ */
+static struct undef_hook swp_hook = {
+	.instr_mask = 0x0fb00ff0,
+	.instr_val  = 0x01000090,
+	.cpsr_mask  = MODE_MASK | PSR_T_BIT | PSR_J_BIT,
+	.cpsr_val   = USR_MODE,
+	.fn	    = swp_handler
+};
+
+/*
+ * Register handler and create status file in /proc/cpu
+ * Invoked as late_initcall, since not needed before init spawned.
+ */
+static int __init swp_emulation_init(void)
+{
+#ifdef CONFIG_PROC_FS
+	struct proc_dir_entry *res;
+
+	res = create_proc_entry("cpu/swp_emulation", S_IRUGO, NULL);
+
+	if (!res)
+		return -ENOMEM;
+
+	res->read_proc = proc_read_status;
+#endif /* CONFIG_PROC_FS */
+
+	printk(KERN_NOTICE "Registering SWP/SWPB emulation handler\n");
+	register_undef_hook(&swp_hook);
+
+	return 0;
+}
+
+late_initcall(swp_emulation_init);
diff --git a/arch/arm/kernel/traps.c b/arch/arm/kernel/traps.c
index cda78d59aa3..87abca01805 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -37,6 +37,8 @@
 
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
 
+void *vectors_page;
+
 #ifdef CONFIG_DEBUG_USER
 unsigned int user_debug;
 
@@ -759,7 +761,11 @@ static void __init kuser_get_tls_init(unsigned long vectors)
 
 void __init early_trap_init(void)
 {
+#if defined(CONFIG_CPU_USE_DOMAINS)
 	unsigned long vectors = CONFIG_VECTORS_BASE;
+#else
+	unsigned long vectors = (unsigned long)vectors_page;
+#endif
 	extern char __stubs_start[], __stubs_end[];
 	extern char __vectors_start[], __vectors_end[];
 	extern char __kuser_helper_start[], __kuser_helper_end[];
@@ -783,10 +789,10 @@ void __init early_trap_init(void)
 	 * Copy signal return handlers into the vector page, and
 	 * set sigreturn to be a pointer to these.
 	 */
-	memcpy((void *)KERN_SIGRETURN_CODE, sigreturn_codes,
-	       sizeof(sigreturn_codes));
-	memcpy((void *)KERN_RESTART_CODE, syscall_restart_code,
-	       sizeof(syscall_restart_code));
+	memcpy((void *)(vectors + KERN_SIGRETURN_CODE - CONFIG_VECTORS_BASE),
+	       sigreturn_codes, sizeof(sigreturn_codes));
+	memcpy((void *)(vectors + KERN_RESTART_CODE - CONFIG_VECTORS_BASE),
+	       syscall_restart_code, sizeof(syscall_restart_code));
 
 	flush_icache_range(vectors, vectors + PAGE_SIZE);
 	modify_domain(DOMAIN_USER, DOMAIN_CLIENT);
diff --git a/arch/arm/lib/getuser.S b/arch/arm/lib/getuser.S
index b1631a7dbe7..1b049cd7a49 100644
--- a/arch/arm/lib/getuser.S
+++ b/arch/arm/lib/getuser.S
@@ -28,20 +28,21 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__get_user_1)
-1:	ldrbt	r2, [r0]
+1:	T(ldrb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_1)
 
 ENTRY(__get_user_2)
 #ifdef CONFIG_THUMB2_KERNEL
-2:	ldrbt	r2, [r0]
-3:	ldrbt	r3, [r0, #1]
+2:	T(ldrb)	r2, [r0]
+3:	T(ldrb)	r3, [r0, #1]
 #else
-2:	ldrbt	r2, [r0], #1
-3:	ldrbt	r3, [r0]
+2:	T(ldrb)	r2, [r0], #1
+3:	T(ldrb)	r3, [r0]
 #endif
 #ifndef __ARMEB__
 	orr	r2, r2, r3, lsl #8
@@ -53,7 +54,7 @@ ENTRY(__get_user_2)
 ENDPROC(__get_user_2)
 
 ENTRY(__get_user_4)
-4:	ldrt	r2, [r0]
+4:	T(ldr)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__get_user_4)
diff --git a/arch/arm/lib/putuser.S b/arch/arm/lib/putuser.S
index 5a01a23c6c0..c023fc11e86 100644
--- a/arch/arm/lib/putuser.S
+++ b/arch/arm/lib/putuser.S
@@ -28,9 +28,10 @@
  */
 #include <linux/linkage.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 ENTRY(__put_user_1)
-1:	strbt	r2, [r0]
+1:	T(strb)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_1)
@@ -39,19 +40,19 @@ ENTRY(__put_user_2)
 	mov	ip, r2, lsr #8
 #ifdef CONFIG_THUMB2_KERNEL
 #ifndef __ARMEB__
-2:	strbt	r2, [r0]
-3:	strbt	ip, [r0, #1]
+2:	T(strb)	r2, [r0]
+3:	T(strb)	ip, [r0, #1]
 #else
-2:	strbt	ip, [r0]
-3:	strbt	r2, [r0, #1]
+2:	T(strb)	ip, [r0]
+3:	T(strb)	r2, [r0, #1]
 #endif
 #else	/* !CONFIG_THUMB2_KERNEL */
 #ifndef __ARMEB__
-2:	strbt	r2, [r0], #1
-3:	strbt	ip, [r0]
+2:	T(strb)	r2, [r0], #1
+3:	T(strb)	ip, [r0]
 #else
-2:	strbt	ip, [r0], #1
-3:	strbt	r2, [r0]
+2:	T(strb)	ip, [r0], #1
+3:	T(strb)	r2, [r0]
 #endif
 #endif	/* CONFIG_THUMB2_KERNEL */
 	mov	r0, #0
@@ -59,18 +60,18 @@ ENTRY(__put_user_2)
 ENDPROC(__put_user_2)
 
 ENTRY(__put_user_4)
-4:	strt	r2, [r0]
+4:	T(str)	r2, [r0]
 	mov	r0, #0
 	mov	pc, lr
 ENDPROC(__put_user_4)
 
 ENTRY(__put_user_8)
 #ifdef CONFIG_THUMB2_KERNEL
-5:	strt	r2, [r0]
-6:	strt	r3, [r0, #4]
+5:	T(str)	r2, [r0]
+6:	T(str)	r3, [r0, #4]
 #else
-5:	strt	r2, [r0], #4
-6:	strt	r3, [r0]
+5:	T(str)	r2, [r0], #4
+6:	T(str)	r3, [r0]
 #endif
 	mov	r0, #0
 	mov	pc, lr
diff --git a/arch/arm/lib/uaccess.S b/arch/arm/lib/uaccess.S
index fee9f6f88ad..d0ece2aeb70 100644
--- a/arch/arm/lib/uaccess.S
+++ b/arch/arm/lib/uaccess.S
@@ -14,6 +14,7 @@
 #include <linux/linkage.h>
 #include <asm/assembler.h>
 #include <asm/errno.h>
+#include <asm/domain.h>
 
 		.text
 
@@ -31,11 +32,11 @@
 		rsb	ip, ip, #4
 		cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		sub	r2, r2, ip
 		b	.Lc2u_dest_aligned
 
@@ -58,7 +59,7 @@ ENTRY(__copy_to_user)
 		addmi	ip, r2, #4
 		bmi	.Lc2u_0nowords
 		ldr	r3, [r1], #4
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -87,18 +88,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
 		ldrne	r3, [r1], #4
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_0fupi
 .Lc2u_0nowords:	teq	ip, #0
 		beq	.Lc2u_finished
 .Lc2u_nowords:	cmp	ip, #2
 		ldrb	r3, [r1], #1
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #1
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_not_enough:
@@ -119,7 +120,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #8
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #24
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -154,18 +155,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #8
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #24
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_1fupi
 .Lc2u_1nowords:	mov	r3, r7, get_byte_1
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_2
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		movgt	r3, r7, get_byte_3
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_2fupi:	subs	r2, r2, #4
@@ -174,7 +175,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #16
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #16
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -209,18 +210,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #16
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #16
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_2fupi
 .Lc2u_2nowords:	mov	r3, r7, get_byte_2
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		movge	r3, r7, get_byte_3
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 
 .Lc2u_3fupi:	subs	r2, r2, #4
@@ -229,7 +230,7 @@ USER(		strgtbt	r3, [r0], #1)			@ May fault
 		mov	r3, r7, pull #24
 		ldr	r7, [r1], #4
 		orr	r3, r3, r7, push #8
-USER(		strt	r3, [r0], #4)			@ May fault
+USER(		T(str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
 		movs	ip, ip, lsr #32 - PAGE_SHIFT
@@ -264,18 +265,18 @@ USER(		strt	r3, [r0], #4)			@ May fault
 		movne	r3, r7, pull #24
 		ldrne	r7, [r1], #4
 		orrne	r3, r3, r7, push #8
-		strnet	r3, [r0], #4			@ Shouldnt fault
+		T(strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_3fupi
 .Lc2u_3nowords:	mov	r3, r7, get_byte_3
 		teq	ip, #0
 		beq	.Lc2u_finished
 		cmp	ip, #2
-USER(		strbt	r3, [r0], #1)			@ May fault
+USER(		T(strb)	r3, [r0], #1)			@ May fault
 		ldrgeb	r3, [r1], #1
-USER(		strgebt	r3, [r0], #1)			@ May fault
+USER(		T(strgeb) r3, [r0], #1)			@ May fault
 		ldrgtb	r3, [r1], #0
-USER(		strgtbt	r3, [r0], #1)			@ May fault
+USER(		T(strgtb) r3, [r0], #1)			@ May fault
 		b	.Lc2u_finished
 ENDPROC(__copy_to_user)
 
@@ -294,11 +295,11 @@ ENDPROC(__copy_to_user)
 .Lcfu_dest_not_aligned:
 		rsb	ip, ip, #4
 		cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		sub	r2, r2, ip
 		b	.Lcfu_dest_aligned
@@ -321,7 +322,7 @@ ENTRY(__copy_from_user)
 .Lcfu_0fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_0nowords
-USER(		ldrt	r3, [r1], #4)
+USER(		T(ldr)	r3, [r1], #4)
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT	@ On each page, use a ld/st??t instruction
 		rsb	ip, ip, #0
@@ -350,18 +351,18 @@ USER(		ldrt	r3, [r1], #4)
 		ldmneia	r1!, {r3 - r4}			@ Shouldnt fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		ldrnet	r3, [r1], #4			@ Shouldnt fault
+		T(ldrne) r3, [r1], #4			@ Shouldnt fault
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_0fupi
 .Lcfu_0nowords:	teq	ip, #0
 		beq	.Lcfu_finished
 .Lcfu_nowords:	cmp	ip, #2
-USER(		ldrbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrb)	r3, [r1], #1)			@ May fault
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -374,7 +375,7 @@ USER(		ldrgtbt	r3, [r1], #1)			@ May fault
 
 .Lcfu_src_not_aligned:
 		bic	r1, r1, #3
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		cmp	ip, #2
 		bgt	.Lcfu_3fupi
 		beq	.Lcfu_2fupi
@@ -382,7 +383,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_1nowords
 		mov	r3, r7, pull #8
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #24
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -417,7 +418,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #8
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #24
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -437,7 +438,7 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_2nowords
 		mov	r3, r7, pull #16
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #16
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -473,7 +474,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #16
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #16
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -485,7 +486,7 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		strb	r3, [r0], #1
 		movge	r3, r7, get_byte_3
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #0)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #0)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 
@@ -493,7 +494,7 @@ USER(		ldrgtbt	r3, [r1], #0)			@ May fault
 		addmi	ip, r2, #4
 		bmi	.Lcfu_3nowords
 		mov	r3, r7, pull #24
-USER(		ldrt	r7, [r1], #4)			@ May fault
+USER(		T(ldr)	r7, [r1], #4)			@ May fault
 		orr	r3, r3, r7, push #8
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
@@ -528,7 +529,7 @@ USER(		ldrt	r7, [r1], #4)			@ May fault
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
 		movne	r3, r7, pull #24
-USER(		ldrnet	r7, [r1], #4)			@ May fault
+USER(		T(ldrne) r7, [r1], #4)			@ May fault
 		orrne	r3, r3, r7, push #8
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
@@ -538,9 +539,9 @@ USER(		ldrnet	r7, [r1], #4)			@ May fault
 		beq	.Lcfu_finished
 		cmp	ip, #2
 		strb	r3, [r0], #1
-USER(		ldrgebt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgeb) r3, [r1], #1)			@ May fault
 		strgeb	r3, [r0], #1
-USER(		ldrgtbt	r3, [r1], #1)			@ May fault
+USER(		T(ldrgtb) r3, [r1], #1)			@ May fault
 		strgtb	r3, [r0], #1
 		b	.Lcfu_finished
 ENDPROC(__copy_from_user)
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 87ec141fcaa..cea459661f8 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -398,7 +398,7 @@ config CPU_V6
 # ARMv6k
 config CPU_32v6K
 	bool "Support ARM V6K processor extensions" if !SMP
-	depends on CPU_V6
+	depends on CPU_V6 || CPU_V7
 	default y if SMP && !(ARCH_MX3 || ARCH_OMAP2)
 	help
 	  Say Y here if your ARMv6 processor supports the 'K' extension.
@@ -599,6 +599,14 @@ config CPU_CP15_MPU
 	help
 	  Processor has the CP15 register, which has MPU related registers.
 
+config CPU_USE_DOMAINS
+	bool
+	depends on MMU
+	default y if !CPU_32v6K
+	help
+	  This option enables or disables the use of domain switching
+	  via the set_fs() function.
+
 #
 # CPU supports 36-bit I/O
 #
@@ -628,6 +636,33 @@ config ARM_THUMBEE
 	  Say Y here if you have a CPU with the ThumbEE extension and code to
 	  make use of it. Say N for code that can run on CPUs without ThumbEE.
 
+config SWP_EMULATE
+	bool "Emulate SWP/SWPB instructions"
+	depends on CPU_V7
+	select HAVE_PROC_CPU if PROC_FS
+	default y if SMP
+	help
+	  ARMv6 architecture deprecates use of the SWP/SWPB instructions.
+	  ARMv7 multiprocessing extensions introduce the ability to disable
+	  these instructions, triggering an undefined instruction exception
+	  when executed. Say Y here to enable software emulation of these
+	  instructions for userspace (not kernel) using LDREX/STREX.
+	  Also creates /proc/cpu/swp_emulation for statistics.
+
+	  In some older versions of glibc [<=2.8] SWP is used during futex
+	  trylock() operations with the assumption that the code will not
+	  be preempted. This invalid assumption may be more likely to fail
+	  with SWP emulation enabled, leading to deadlock of the user
+	  application.
+
+	  NOTE: when accessing uncached shared regions, LDREX/STREX rely
+	  on an external transaction monitoring block called a global
+	  monitor to maintain update atomicity. If your system does not
+	  implement a global monitor, this option can cause programs that
+	  perform SWP operations to uncached memory to deadlock.
+
+	  If unsure, say Y.
+
 config CPU_BIG_ENDIAN
 	bool "Build big-endian kernel"
 	depends on ARCH_SUPPORTS_BIG_ENDIAN
@@ -778,6 +813,14 @@ config CACHE_L2X0
 	help
 	  This option enables the L2x0 PrimeCell.
 
+config CACHE_PL310
+	bool
+	depends on CACHE_L2X0
+	default y if CPU_V7 && !CPU_V6
+	help
+	  This option enables optimisations for the PL310 cache
+	  controller.
+
 config CACHE_TAUROS2
 	bool "Enable the Tauros2 L2 cache controller"
 	depends on (ARCH_DOVE || ARCH_MMP)
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 9982eb385c0..edb43ff7aee 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -29,13 +29,22 @@ static void __iomem *l2x0_base;
 static DEFINE_SPINLOCK(l2x0_lock);
 static uint32_t l2x0_way_mask;	/* Bitmask of active ways */
 
-static inline void cache_wait(void __iomem *reg, unsigned long mask)
+static inline void cache_wait_way(void __iomem *reg, unsigned long mask)
 {
-	/* wait for the operation to complete */
+	/* wait for cache operation by line or way to complete */
 	while (readl_relaxed(reg) & mask)
 		;
 }
 
+#ifdef CONFIG_CACHE_PL310
+static inline void cache_wait(void __iomem *reg, unsigned long mask)
+{
+	/* cache operations by line are atomic on PL310 */
+}
+#else
+#define cache_wait	cache_wait_way
+#endif
+
 static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
@@ -110,7 +119,7 @@ static inline void l2x0_inv_all(void)
 	/* invalidate all ways */
 	spin_lock_irqsave(&l2x0_lock, flags);
 	writel_relaxed(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
-	cache_wait(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
+	cache_wait_way(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
 	cache_sync();
 	spin_unlock_irqrestore(&l2x0_lock, flags);
 }
diff --git a/arch/arm/mm/copypage-v4mc.c b/arch/arm/mm/copypage-v4mc.c
index 598c51ad507..b8061519ce7 100644
--- a/arch/arm/mm/copypage-v4mc.c
+++ b/arch/arm/mm/copypage-v4mc.c
@@ -73,7 +73,7 @@ void v4_mc_copy_user_highpage(struct page *to, struct page *from,
 {
 	void *kto = kmap_atomic(to, KM_USER1);
 
-	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
 	spin_lock(&minicache_lock);
diff --git a/arch/arm/mm/copypage-v6.c b/arch/arm/mm/copypage-v6.c
index f55fa1044f7..bdba6c65c90 100644
--- a/arch/arm/mm/copypage-v6.c
+++ b/arch/arm/mm/copypage-v6.c
@@ -79,7 +79,7 @@ static void v6_copy_user_highpage_aliasing(struct page *to,
 	unsigned int offset = CACHE_COLOUR(vaddr);
 	unsigned long kfrom, kto;
 
-	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
 	/* FIXME: not highmem safe */
diff --git a/arch/arm/mm/copypage-xscale.c b/arch/arm/mm/copypage-xscale.c
index 9920c0ae209..649bbcd325b 100644
--- a/arch/arm/mm/copypage-xscale.c
+++ b/arch/arm/mm/copypage-xscale.c
@@ -95,7 +95,7 @@ void xscale_mc_copy_user_highpage(struct page *to, struct page *from,
 {
 	void *kto = kmap_atomic(to, KM_USER1);
 
-	if (test_and_clear_bit(PG_dcache_dirty, &from->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &from->flags))
 		__flush_dcache_page(page_mapping(from), from);
 
 	spin_lock(&minicache_lock);
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index c704eed63c5..ba93c4910b8 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -521,6 +521,12 @@ void ___dma_page_dev_to_cpu(struct page *page, unsigned long off,
 		outer_inv_range(paddr, paddr + size);
 
 	dma_cache_maint_page(page, off, size, dir, dmac_unmap_area);
+
+	/*
+	 * Mark the D-cache clean for this page to avoid extra flushing.
+	 */
+	if (dir != DMA_TO_DEVICE && off == 0 && size >= PAGE_SIZE)
+		set_bit(PG_dcache_clean, &page->flags);
 }
 EXPORT_SYMBOL(___dma_page_dev_to_cpu);
 
diff --git a/arch/arm/mm/fault-armv.c b/arch/arm/mm/fault-armv.c
index 9b906dec1ca..8440d952ba6 100644
--- a/arch/arm/mm/fault-armv.c
+++ b/arch/arm/mm/fault-armv.c
@@ -28,6 +28,7 @@
 
 static unsigned long shared_pte_mask = L_PTE_MT_BUFFERABLE;
 
+#if __LINUX_ARM_ARCH__ < 6
 /*
  * We take the easy way out of this problem - we make the
  * PTE uncacheable.  However, we leave the write buffer on.
@@ -141,7 +142,7 @@ make_coherent(struct address_space *mapping, struct vm_area_struct *vma,
  * a page table, or changing an existing PTE.  Basically, there are two
  * things that we need to take care of:
  *
- *  1. If PG_dcache_dirty is set for the page, we need to ensure
+ *  1. If PG_dcache_clean is not set for the page, we need to ensure
  *     that any cache entries for the kernels virtual memory
  *     range are written back to the page.
  *  2. If we have multiple shared mappings of the same space in
@@ -168,10 +169,8 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 		return;
 
 	mapping = page_mapping(page);
-#ifndef CONFIG_SMP
-	if (test_and_clear_bit(PG_dcache_dirty, &page->flags))
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
 		__flush_dcache_page(mapping, page);
-#endif
 	if (mapping) {
 		if (cache_is_vivt())
 			make_coherent(mapping, vma, addr, ptep, pfn);
@@ -179,6 +178,7 @@ void update_mmu_cache(struct vm_area_struct *vma, unsigned long addr,
 			__flush_icache_all();
 	}
 }
+#endif	/* __LINUX_ARM_ARCH__ < 6 */
 
 /*
  * Check whether the write buffer has physical address aliasing
diff --git a/arch/arm/mm/flush.c b/arch/arm/mm/flush.c
index c6844cb9b50..03a4934a167 100644
--- a/arch/arm/mm/flush.c
+++ b/arch/arm/mm/flush.c
@@ -17,6 +17,7 @@
 #include <asm/smp_plat.h>
 #include <asm/system.h>
 #include <asm/tlbflush.h>
+#include <asm/smp_plat.h>
 
 #include "mm.h"
 
@@ -93,12 +94,10 @@ void flush_cache_page(struct vm_area_struct *vma, unsigned long user_addr, unsig
 #define flush_pfn_alias(pfn,vaddr)	do { } while (0)
 #endif
 
-#ifdef CONFIG_SMP
 static void flush_ptrace_access_other(void *args)
 {
 	__flush_icache_all();
 }
-#endif
 
 static
 void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
@@ -120,13 +119,11 @@ void flush_ptrace_access(struct vm_area_struct *vma, struct page *page,
 
 	/* VIPT non-aliasing cache */
 	if (vma->vm_flags & VM_EXEC) {
-		unsigned long addr = (unsigned long)kaddr;
-		__cpuc_coherent_kern_range(addr, addr + len);
-#ifdef CONFIG_SMP
+		__cpuc_flush_dcache_area(kaddr, len);
+		__flush_icache_all();
 		if (cache_ops_need_broadcast())
 			smp_call_function(flush_ptrace_access_other,
 					  NULL, 1);
-#endif
 	}
 }
 
@@ -215,6 +212,36 @@ static void __flush_dcache_aliases(struct address_space *mapping, struct page *p
 	flush_dcache_mmap_unlock(mapping);
 }
 
+#if __LINUX_ARM_ARCH__ >= 6
+void __sync_icache_dcache(pte_t pteval)
+{
+	unsigned long pfn;
+	struct page *page;
+	struct address_space *mapping;
+
+	if (!pte_present_user(pteval))
+		return;
+	if (cache_is_vipt_nonaliasing() && !pte_exec(pteval))
+		/* only flush non-aliasing VIPT caches for exec mappings */
+		return;
+	pfn = pte_pfn(pteval);
+	if (!pfn_valid(pfn))
+		return;
+
+	page = pfn_to_page(pfn);
+	if (cache_is_vipt_aliasing())
+		mapping = page_mapping(page);
+	else
+		mapping = NULL;
+
+	if (!test_and_set_bit(PG_dcache_clean, &page->flags))
+		__flush_dcache_page(mapping, page);
+	/* pte_exec() already checked above for non-aliasing VIPT cache */
+	if (cache_is_vipt_nonaliasing() || pte_exec(pteval))
+		__flush_icache_all();
+}
+#endif
+
 /*
  * Ensure cache coherency between kernel mapping and userspace mapping
  * of this page.
@@ -246,17 +273,16 @@ void flush_dcache_page(struct page *page)
 
 	mapping = page_mapping(page);
 
-#ifndef CONFIG_SMP
-	if (!PageHighMem(page) && mapping && !mapping_mapped(mapping))
-		set_bit(PG_dcache_dirty, &page->flags);
-	else
-#endif
-	{
+	if (!cache_ops_need_broadcast() &&
+	    mapping && !mapping_mapped(mapping))
+		clear_bit(PG_dcache_clean, &page->flags);
+	else {
 		__flush_dcache_page(mapping, page);
 		if (mapping && cache_is_vivt())
 			__flush_dcache_aliases(mapping, page);
 		else if (mapping)
 			__flush_icache_all();
+		set_bit(PG_dcache_clean, &page->flags);
 	}
 }
 EXPORT_SYMBOL(flush_dcache_page);
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 6e1c4f6a2b3..920fb3b3827 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -15,6 +15,7 @@
 #include <linux/nodemask.h>
 #include <linux/memblock.h>
 #include <linux/sort.h>
+#include <linux/fs.h>
 
 #include <asm/cputype.h>
 #include <asm/sections.h>
@@ -24,6 +25,7 @@
 #include <asm/smp_plat.h>
 #include <asm/tlb.h>
 #include <asm/highmem.h>
+#include <asm/traps.h>
 
 #include <asm/mach/arch.h>
 #include <asm/mach/map.h>
@@ -498,6 +500,19 @@ static void __init build_mem_type_table(void)
 	}
 }
 
+#ifdef CONFIG_ARM_DMA_MEM_BUFFERABLE
+pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn,
+			      unsigned long size, pgprot_t vma_prot)
+{
+	if (!pfn_valid(pfn))
+		return pgprot_noncached(vma_prot);
+	else if (file->f_flags & O_SYNC)
+		return pgprot_writecombine(vma_prot);
+	return vma_prot;
+}
+EXPORT_SYMBOL(phys_mem_access_prot);
+#endif
+
 #define vectors_base()	(vectors_high() ? 0xffff0000 : 0)
 
 static void __init *early_alloc(unsigned long sz)
@@ -883,12 +898,11 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 {
 	struct map_desc map;
 	unsigned long addr;
-	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors = early_alloc(PAGE_SIZE);
+	vectors_page = early_alloc(PAGE_SIZE);
 
 	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -928,7 +942,7 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 	 * location (0xffff0000).  If we aren't using high-vectors, also
 	 * create a mapping at the low-vectors virtual address.
 	 */
-	map.pfn = __phys_to_pfn(virt_to_phys(vectors));
+	map.pfn = __phys_to_pfn(virt_to_phys(vectors_page));
 	map.virtual = 0xffff0000;
 	map.length = PAGE_SIZE;
 	map.type = MT_HIGH_VECTORS;
diff --git a/arch/arm/mm/proc-macros.S b/arch/arm/mm/proc-macros.S
index 7d63beaf974..337f10256cd 100644
--- a/arch/arm/mm/proc-macros.S
+++ b/arch/arm/mm/proc-macros.S
@@ -99,6 +99,10 @@
  *  110x   0   1   0	r/w	r/o
  *  11x0   0   1   0	r/w	r/o
  *  1111   0   1   1	r/w	r/w
+ *
+ * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
+ *  110x   1   1   1	r/o	r/o
+ *  11x0   1   1   1	r/o	r/o
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -138,8 +142,11 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
diff --git a/arch/arm/mm/proc-v7.S b/arch/arm/mm/proc-v7.S
index 6a8506d99ee..d5d9b585c68 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -149,8 +149,11 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
+#ifdef CONFIG_CPU_USE_DOMAINS
+	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
 	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
+#endif
 
 	tst	r1, #L_PTE_EXEC
 	orreq	r3, r3, #PTE_EXT_XN
@@ -237,8 +240,6 @@ __v7_setup:
 	mcr	p15, 0, r10, c2, c0, 2		@ TTB control register
 	orr	r4, r4, #TTB_FLAGS
 	mcr	p15, 0, r4, c2, c0, 1		@ load TTB1
-	mov	r10, #0x1f			@ domains 0, 1 = manager
-	mcr	p15, 0, r10, c3, c0, 0		@ load domain access register
 	/*
 	 * Memory region attributes with SCTLR.TRE=1
 	 *
@@ -277,6 +278,10 @@ __v7_setup:
 #ifdef CONFIG_CPU_ENDIAN_BE8
 	orr	r6, r6, #1 << 25		@ big-endian page tables
 #endif
+#ifdef CONFIG_SWP_EMULATE
+	orr     r5, r5, #(1 << 10)              @ set SW bit in "clear"
+	bic     r6, r6, #(1 << 10)              @ clear it in "mmuset"
+#endif
    	mrc	p15, 0, r0, c1, c0, 0		@ read control register
 	bic	r0, r0, r5			@ clear bits them
 	orr	r0, r0, r6			@ set them
diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c
index cc559741b0f..7a7b01a0fff 100644
--- a/drivers/net/smsc911x.c
+++ b/drivers/net/smsc911x.c
@@ -84,8 +84,7 @@ struct smsc911x_data {
 	 */
 	spinlock_t mac_lock;
 
-	/* spinlock to ensure 16-bit accesses are serialised.
-	 * unused with a 32-bit bus */
+	/* spinlock to ensure register accesses are serialised */
 	spinlock_t dev_lock;
 
 	struct phy_device *phy_dev;
@@ -118,37 +117,33 @@ struct smsc911x_data {
 	unsigned int hashlo;
 };
 
-/* The 16-bit access functions are significantly slower, due to the locking
- * necessary.  If your bus hardware can be configured to do this for you
- * (in response to a single 32-bit operation from software), you should use
- * the 32-bit access functions instead. */
-
-static inline u32 smsc911x_reg_read(struct smsc911x_data *pdata, u32 reg)
+static inline u32 __smsc911x_reg_read(struct smsc911x_data *pdata, u32 reg)
 {
 	if (pdata->config.flags & SMSC911X_USE_32BIT)
 		return readl(pdata->ioaddr + reg);
 
-	if (pdata->config.flags & SMSC911X_USE_16BIT) {
-		u32 data;
-		unsigned long flags;
-
-		/* these two 16-bit reads must be performed consecutively, so
-		 * must not be interrupted by our own ISR (which would start
-		 * another read operation) */
-		spin_lock_irqsave(&pdata->dev_lock, flags);
-		data = ((readw(pdata->ioaddr + reg) & 0xFFFF) |
+	if (pdata->config.flags & SMSC911X_USE_16BIT)
+		return ((readw(pdata->ioaddr + reg) & 0xFFFF) |
 			((readw(pdata->ioaddr + reg + 2) & 0xFFFF) << 16));
-		spin_unlock_irqrestore(&pdata->dev_lock, flags);
-
-		return data;
-	}
 
 	BUG();
 	return 0;
 }
 
-static inline void smsc911x_reg_write(struct smsc911x_data *pdata, u32 reg,
-				      u32 val)
+static inline u32 smsc911x_reg_read(struct smsc911x_data *pdata, u32 reg)
+{
+	u32 data;
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdata->dev_lock, flags);
+	data = __smsc911x_reg_read(pdata, reg);
+	spin_unlock_irqrestore(&pdata->dev_lock, flags);
+
+	return data;
+}
+
+static inline void __smsc911x_reg_write(struct smsc911x_data *pdata, u32 reg,
+					u32 val)
 {
 	if (pdata->config.flags & SMSC911X_USE_32BIT) {
 		writel(val, pdata->ioaddr + reg);
@@ -156,44 +151,54 @@ static inline void smsc911x_reg_write(struct smsc911x_data *pdata, u32 reg,
 	}
 
 	if (pdata->config.flags & SMSC911X_USE_16BIT) {
-		unsigned long flags;
-
-		/* these two 16-bit writes must be performed consecutively, so
-		 * must not be interrupted by our own ISR (which would start
-		 * another read operation) */
-		spin_lock_irqsave(&pdata->dev_lock, flags);
 		writew(val & 0xFFFF, pdata->ioaddr + reg);
 		writew((val >> 16) & 0xFFFF, pdata->ioaddr + reg + 2);
-		spin_unlock_irqrestore(&pdata->dev_lock, flags);
 		return;
 	}
 
 	BUG();
 }
 
+static inline void smsc911x_reg_write(struct smsc911x_data *pdata, u32 reg,
+				      u32 val)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdata->dev_lock, flags);
+	__smsc911x_reg_write(pdata, reg, val);
+	spin_unlock_irqrestore(&pdata->dev_lock, flags);
+}
+
 /* Writes a packet to the TX_DATA_FIFO */
 static inline void
 smsc911x_tx_writefifo(struct smsc911x_data *pdata, unsigned int *buf,
 		      unsigned int wordcount)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdata->dev_lock, flags);
+
 	if (pdata->config.flags & SMSC911X_SWAP_FIFO) {
 		while (wordcount--)
-			smsc911x_reg_write(pdata, TX_DATA_FIFO, swab32(*buf++));
-		return;
+			__smsc911x_reg_write(pdata, TX_DATA_FIFO,
+					     swab32(*buf++));
+		goto out;
 	}
 
 	if (pdata->config.flags & SMSC911X_USE_32BIT) {
 		writesl(pdata->ioaddr + TX_DATA_FIFO, buf, wordcount);
-		return;
+		goto out;
 	}
 
 	if (pdata->config.flags & SMSC911X_USE_16BIT) {
 		while (wordcount--)
-			smsc911x_reg_write(pdata, TX_DATA_FIFO, *buf++);
-		return;
+			__smsc911x_reg_write(pdata, TX_DATA_FIFO, *buf++);
+		goto out;
 	}
 
 	BUG();
+out:
+	spin_unlock_irqrestore(&pdata->dev_lock, flags);
 }
 
 /* Reads a packet out of the RX_DATA_FIFO */
@@ -201,24 +206,31 @@ static inline void
 smsc911x_rx_readfifo(struct smsc911x_data *pdata, unsigned int *buf,
 		     unsigned int wordcount)
 {
+	unsigned long flags;
+
+	spin_lock_irqsave(&pdata->dev_lock, flags);
+
 	if (pdata->config.flags & SMSC911X_SWAP_FIFO) {
 		while (wordcount--)
-			*buf++ = swab32(smsc911x_reg_read(pdata, RX_DATA_FIFO));
-		return;
+			*buf++ = swab32(__smsc911x_reg_read(pdata,
+							    RX_DATA_FIFO));
+		goto out;
 	}
 
 	if (pdata->config.flags & SMSC911X_USE_32BIT) {
 		readsl(pdata->ioaddr + RX_DATA_FIFO, buf, wordcount);
-		return;
+		goto out;
 	}
 
 	if (pdata->config.flags & SMSC911X_USE_16BIT) {
 		while (wordcount--)
-			*buf++ = smsc911x_reg_read(pdata, RX_DATA_FIFO);
-		return;
+			*buf++ = __smsc911x_reg_read(pdata, RX_DATA_FIFO);
+		goto out;
 	}
 
 	BUG();
+out:
+	spin_unlock_irqrestore(&pdata->dev_lock, flags);
 }
 
 /* waits for MAC not busy, with timeout.  Only called by smsc911x_mac_read
diff --git a/lib/Kconfig.debug b/lib/Kconfig.debug
index e722e9d6222..95ab402db9c 100644
--- a/lib/Kconfig.debug
+++ b/lib/Kconfig.debug
@@ -400,6 +400,13 @@ config DEBUG_KMEMLEAK_TEST
 
 	  If unsure, say N.
 
+config DEBUG_KMEMLEAK_DEFAULT_OFF
+	bool "Default kmemleak to off"
+	depends on DEBUG_KMEMLEAK
+	help
+	  Say Y here to disable kmemleak by default. It can then be enabled
+	  on the command line via kmemleak=on.
+
 config DEBUG_PREEMPT
 	bool "Debug preemptible kernel"
 	depends on DEBUG_KERNEL && PREEMPT && TRACE_IRQFLAGS_SUPPORT
diff --git a/lib/scatterlist.c b/lib/scatterlist.c
index 9afa25b52a8..a5ec42868f9 100644
--- a/lib/scatterlist.c
+++ b/lib/scatterlist.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/scatterlist.h>
 #include <linux/highmem.h>
+#include <linux/kmemleak.h>
 
 /**
  * sg_next - return the next scatterlist entry in a list
@@ -115,17 +116,29 @@ EXPORT_SYMBOL(sg_init_one);
  */
 static struct scatterlist *sg_kmalloc(unsigned int nents, gfp_t gfp_mask)
 {
-	if (nents == SG_MAX_SINGLE_ALLOC)
-		return (struct scatterlist *) __get_free_page(gfp_mask);
-	else
+	if (nents == SG_MAX_SINGLE_ALLOC) {
+		/*
+		 * Kmemleak doesn't track page allocations as they are not
+		 * commonly used (in a raw form) for kernel data structures.
+		 * As we chain together a list of pages and then a normal
+		 * kmalloc (tracked by kmemleak), in order to for that last
+		 * allocation not to become decoupled (and thus a
+		 * false-positive) we need to inform kmemleak of all the
+		 * intermediate allocations.
+		 */
+		void *ptr = (void *) __get_free_page(gfp_mask);
+		kmemleak_alloc(ptr, PAGE_SIZE, 1, gfp_mask);
+		return ptr;
+	} else
 		return kmalloc(nents * sizeof(struct scatterlist), gfp_mask);
 }
 
 static void sg_kfree(struct scatterlist *sg, unsigned int nents)
 {
-	if (nents == SG_MAX_SINGLE_ALLOC)
+	if (nents == SG_MAX_SINGLE_ALLOC) {
+		kmemleak_free(sg);
 		free_page((unsigned long) sg);
-	else
+	} else
 		kfree(sg);
 }
 
diff --git a/mm/kmemleak.c b/mm/kmemleak.c
index 2c0d032ac89..5f2eb5b2365 100644
--- a/mm/kmemleak.c
+++ b/mm/kmemleak.c
@@ -211,6 +211,9 @@ static signed long jiffies_scan_wait;
 static int kmemleak_stack_scan = 1;
 /* protects the memory scanning, parameters and debug/kmemleak file access */
 static DEFINE_MUTEX(scan_mutex);
+/* setting kmemleak=on, will set this var, skipping the disable */
+static int kmemleak_skip_disable;
+
 
 /*
  * Early object allocation/freeing logging. Kmemleak is initialized after the
@@ -398,7 +401,9 @@ static struct kmemleak_object *lookup_object(unsigned long ptr, int alias)
 		object = prio_tree_entry(node, struct kmemleak_object,
 					 tree_node);
 		if (!alias && object->pointer != ptr) {
-			kmemleak_warn("Found object by alias");
+			pr_warning("Found object by alias at 0x%08lx\n", ptr);
+			dump_stack();
+			dump_object_info(object);
 			object = NULL;
 		}
 	} else
@@ -838,10 +843,19 @@ out:
 	rcu_read_unlock();
 }
 
-/*
- * Memory allocation function callback. This function is called from the
- * kernel allocators when a new block is allocated (kmem_cache_alloc, kmalloc,
- * vmalloc etc.).
+/**
+ * kmemleak_alloc - register a newly allocated object
+ * @ptr:	pointer to beginning of the object
+ * @size:	size of the object
+ * @min_count:	minimum number of references to this object. If during memory
+ *		scanning a number of references less than @min_count is found,
+ *		the object is reported as a memory leak. If @min_count is 0,
+ *		the object is never reported as a leak. If @min_count is -1,
+ *		the object is ignored (not scanned and not reported as a leak)
+ * @gfp:	kmalloc() flags used for kmemleak internal memory allocations
+ *
+ * This function is called from the kernel allocators when a new object
+ * (memory block) is allocated (kmem_cache_alloc, kmalloc, vmalloc etc.).
  */
 void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count,
 			  gfp_t gfp)
@@ -855,9 +869,12 @@ void __ref kmemleak_alloc(const void *ptr, size_t size, int min_count,
 }
 EXPORT_SYMBOL_GPL(kmemleak_alloc);
 
-/*
- * Memory freeing function callback. This function is called from the kernel
- * allocators when a block is freed (kmem_cache_free, kfree, vfree etc.).
+/**
+ * kmemleak_free - unregister a previously registered object
+ * @ptr:	pointer to beginning of the object
+ *
+ * This function is called from the kernel allocators when an object (memory
+ * block) is freed (kmem_cache_free, kfree, vfree etc.).
  */
 void __ref kmemleak_free(const void *ptr)
 {
@@ -870,9 +887,14 @@ void __ref kmemleak_free(const void *ptr)
 }
 EXPORT_SYMBOL_GPL(kmemleak_free);
 
-/*
- * Partial memory freeing function callback. This function is usually called
- * from bootmem allocator when (part of) a memory block is freed.
+/**
+ * kmemleak_free_part - partially unregister a previously registered object
+ * @ptr:	pointer to the beginning or inside the object. This also
+ *		represents the start of the range to be freed
+ * @size:	size to be unregistered
+ *
+ * This function is called when only a part of a memory block is freed
+ * (usually from the bootmem allocator).
  */
 void __ref kmemleak_free_part(const void *ptr, size_t size)
 {
@@ -885,9 +907,12 @@ void __ref kmemleak_free_part(const void *ptr, size_t size)
 }
 EXPORT_SYMBOL_GPL(kmemleak_free_part);
 
-/*
- * Mark an already allocated memory block as a false positive. This will cause
- * the block to no longer be reported as leak and always be scanned.
+/**
+ * kmemleak_not_leak - mark an allocated object as false positive
+ * @ptr:	pointer to beginning of the object
+ *
+ * Calling this function on an object will cause the memory block to no longer
+ * be reported as leak and always be scanned.
  */
 void __ref kmemleak_not_leak(const void *ptr)
 {
@@ -900,10 +925,14 @@ void __ref kmemleak_not_leak(const void *ptr)
 }
 EXPORT_SYMBOL(kmemleak_not_leak);
 
-/*
- * Ignore a memory block. This is usually done when it is known that the
- * corresponding block is not a leak and does not contain any references to
- * other allocated memory blocks.
+/**
+ * kmemleak_ignore - ignore an allocated object
+ * @ptr:	pointer to beginning of the object
+ *
+ * Calling this function on an object will cause the memory block to be
+ * ignored (not scanned and not reported as a leak). This is usually done when
+ * it is known that the corresponding block is not a leak and does not contain
+ * any references to other allocated memory blocks.
  */
 void __ref kmemleak_ignore(const void *ptr)
 {
@@ -916,8 +945,16 @@ void __ref kmemleak_ignore(const void *ptr)
 }
 EXPORT_SYMBOL(kmemleak_ignore);
 
-/*
- * Limit the range to be scanned in an allocated memory block.
+/**
+ * kmemleak_scan_area - limit the range to be scanned in an allocated object
+ * @ptr:	pointer to beginning or inside the object. This also
+ *		represents the start of the scan area
+ * @size:	size of the scan area
+ * @gfp:	kmalloc() flags used for kmemleak internal memory allocations
+ *
+ * This function is used when it is known that only certain parts of an object
+ * contain references to other objects. Kmemleak will only scan these areas
+ * reducing the number false negatives.
  */
 void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 {
@@ -930,8 +967,14 @@ void __ref kmemleak_scan_area(const void *ptr, size_t size, gfp_t gfp)
 }
 EXPORT_SYMBOL(kmemleak_scan_area);
 
-/*
- * Inform kmemleak not to scan the given memory block.
+/**
+ * kmemleak_no_scan - do not scan an allocated object
+ * @ptr:	pointer to beginning of the object
+ *
+ * This function notifies kmemleak not to scan the given memory block. Useful
+ * in situations where it is known that the given object does not contain any
+ * references to other objects. Kmemleak will not scan such objects reducing
+ * the number of false negatives.
  */
 void __ref kmemleak_no_scan(const void *ptr)
 {
@@ -1602,7 +1645,9 @@ static int kmemleak_boot_config(char *str)
 		return -EINVAL;
 	if (strcmp(str, "off") == 0)
 		kmemleak_disable();
-	else if (strcmp(str, "on") != 0)
+	else if (strcmp(str, "on") == 0)
+		kmemleak_skip_disable = 1;
+	else
 		return -EINVAL;
 	return 0;
 }
@@ -1616,6 +1661,13 @@ void __init kmemleak_init(void)
 	int i;
 	unsigned long flags;
 
+#ifdef CONFIG_DEBUG_KMEMLEAK_DEFAULT_OFF
+	if (!kmemleak_skip_disable) {
+		kmemleak_disable();
+		return;
+	}
+#endif
+
 	jiffies_min_age = msecs_to_jiffies(MSECS_MIN_AGE);
 	jiffies_scan_wait = msecs_to_jiffies(SECS_SCAN_WAIT * 1000);
 
diff --git a/scripts/kconfig/expr.h b/scripts/kconfig/expr.h
index 891cd9ce9ba..75a31e4552f 100644
--- a/scripts/kconfig/expr.h
+++ b/scripts/kconfig/expr.h
@@ -83,6 +83,7 @@ struct symbol {
 	tristate visible;
 	int flags;
 	struct property *prop;
+	struct expr_value dir_dep;
 	struct expr_value rev_dep;
 };
 
@@ -163,6 +164,7 @@ struct menu {
 	struct symbol *sym;
 	struct property *prompt;
 	struct expr *dep;
+	struct expr *dir_dep;
 	unsigned int flags;
 	char *help;
 	struct file *file;
diff --git a/scripts/kconfig/menu.c b/scripts/kconfig/menu.c
index 203632cc30b..8a8d03547c2 100644
--- a/scripts/kconfig/menu.c
+++ b/scripts/kconfig/menu.c
@@ -105,6 +105,7 @@ static struct expr *menu_check_dep(struct expr *e)
 void menu_add_dep(struct expr *dep)
 {
 	current_entry->dep = expr_alloc_and(current_entry->dep, menu_check_dep(dep));
+	current_entry->dir_dep = current_entry->dep;
 }
 
 void menu_set_type(int type)
@@ -288,6 +289,10 @@ void menu_finalize(struct menu *parent)
 		for (menu = parent->list; menu; menu = menu->next)
 			menu_finalize(menu);
 	} else if (sym) {
+		/* ignore inherited dependencies for dir_dep */
+		sym->dir_dep.expr = expr_transform(expr_copy(parent->dir_dep));
+		sym->dir_dep.expr = expr_eliminate_dups(sym->dir_dep.expr);
+
 		basedep = parent->prompt ? parent->prompt->visible.expr : NULL;
 		basedep = expr_trans_compare(basedep, E_UNEQUAL, &symbol_no);
 		basedep = expr_eliminate_dups(expr_transform(basedep));
diff --git a/scripts/kconfig/symbol.c b/scripts/kconfig/symbol.c
index 2e7a048e0cf..174b230a52b 100644
--- a/scripts/kconfig/symbol.c
+++ b/scripts/kconfig/symbol.c
@@ -205,6 +205,16 @@ static void sym_calc_visibility(struct symbol *sym)
 	}
 	if (sym_is_choice_value(sym))
 		return;
+	/* defaulting to "yes" if no explicit "depends on" are given */
+	tri = yes;
+	if (sym->dir_dep.expr)
+		tri = expr_calc_value(sym->dir_dep.expr);
+	if (tri == mod)
+		tri = yes;
+	if (sym->dir_dep.tri != tri) {
+		sym->dir_dep.tri = tri;
+		sym_set_changed(sym);
+	}
 	tri = no;
 	if (sym->rev_dep.expr)
 		tri = expr_calc_value(sym->rev_dep.expr);
@@ -321,6 +331,14 @@ void sym_calc_value(struct symbol *sym)
 				}
 			}
 		calc_newval:
+			if (sym->dir_dep.tri == no && sym->rev_dep.tri != no) {
+				fprintf(stderr, "warning: (");
+				expr_fprint(sym->rev_dep.expr, stderr);
+				fprintf(stderr, ") selects %s which has unmet direct dependencies (",
+					sym->name);
+				expr_fprint(sym->dir_dep.expr, stderr);
+				fprintf(stderr, ")\n");
+			}
 			newval.tri = EXPR_OR(newval.tri, sym->rev_dep.tri);
 		}
 		if (newval.tri == mod && sym_get_type(sym) == S_BOOLEAN)