Merge remote branch 'catalin/rebased'linaro_merge_100616

Conflicts:
	arch/arm/kernel/entry-armv.S

24 files changed, 337 insertions, 159 deletions

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/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 0a96e8c1b82..029f8407329 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/system.h b/arch/arm/include/asm/system.h
index 5f4f4800273..3b2abcf3a4a 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -141,10 +141,14 @@ extern unsigned int user_debug;
 
 #ifdef CONFIG_ARCH_HAS_BARRIERS
 #include <mach/barriers.h>
-#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE) || defined(CONFIG_SMP)
+#elif defined(CONFIG_ARM_DMA_MEM_BUFFERABLE)
 #define mb()		do { dsb(); outer_sync(); } while (0)
 #define rmb()		dmb()
 #define wmb()		mb()
+#elif defined(CONFIG_SMP)
+#define mb()		dsb()
+#define rmb()		dmb()
+#define wmb()		mb()
 #else
 #define mb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
 #define rmb()	do { if (arch_is_coherent()) dmb(); else barrier(); } while (0)
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/entry-armv.S b/arch/arm/kernel/entry-armv.S
index 2d14081b26b..c125abc2dc7 100644
--- a/arch/arm/kernel/entry-armv.S
+++ b/arch/arm/kernel/entry-armv.S
@@ -736,7 +736,7 @@ 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
 #if defined(CONFIG_HAS_TLS_REG)
@@ -750,7 +750,7 @@ 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
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/head.S b/arch/arm/kernel/head.S
index eb62bf94721..82ea9245b82 100644
--- a/arch/arm/kernel/head.S
+++ b/arch/arm/kernel/head.S
@@ -302,6 +302,8 @@ __create_page_tables:
 	movhi	r3, #0x0800
 	add	r6, r0, r3
 	ldr	r3, [r8, #MACHINFO_PHYSIO]
+	mov	r3, r3, lsr #20			@ 1MB-aligned address
+	mov	r3, r3, lsl #20
 	orr	r3, r3, r7
 1:	str	r3, [r0], #4
 	add	r3, r3, #1 << 20
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 122d999bdc7..4080a8913c7 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -219,7 +219,7 @@ 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/traps.c b/arch/arm/kernel/traps.c
index 1621e5327b2..6bc57c58726 100644
--- a/arch/arm/kernel/traps.c
+++ b/arch/arm/kernel/traps.c
@@ -36,6 +36,8 @@
 
 static const char *handler[]= { "prefetch abort", "data abort", "address exception", "interrupt" };
 
+void *vectors_page;
+
 #ifdef CONFIG_DEBUG_USER
 unsigned int user_debug;
 
@@ -745,7 +747,11 @@ void __init trap_init(void)
 
 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[];
@@ -764,10 +770,10 @@ 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 346ae14824a..9f10a9b4f7b 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -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 !HAS_TLS_REG
+	help
+	  This option enables or disables the use of domain switching
+	  via the set_fs() function.
+
 #
 # CPU supports 36-bit I/O
 #
@@ -735,6 +743,25 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 	  Forget about fast user space cmpxchg support.
 	  It is just not possible.
 
+config DMA_CACHE_RWFO
+	bool "Enable read/write for ownership DMA cache maintenance"
+	depends on CPU_V6 && SMP
+	default y
+	help
+	  The Snoop Control Unit on ARM11MPCore does not detect the
+	  cache maintenance operations and the dma_{map,unmap}_area()
+	  functions may leave stale cache entries on other CPUs. By
+	  enabling this option, Read or Write For Ownership in the ARMv6
+	  DMA cache maintenance functions is performed. These LDR/STR
+	  instructions change the cache line state to shared or modified
+	  so that the cache operation has the desired effect.
+
+	  Note that the workaround is only valid on processors that do
+	  not perform speculative loads into the D-cache. For such
+	  processors, if cache maintenance operations are not broadcast
+	  in hardware, other workarounds are needed (e.g. cache
+	  maintenance broadcasting in software via FIQ).
+
 config OUTER_CACHE
 	bool
 
@@ -770,6 +797,13 @@ config CACHE_L2X0
 	help
 	  This option enables the L2x0 PrimeCell.
 
+config CACHE_PL310
+	bool
+	depends on CACHE_L2X0
+	default y if CPU_V7
+	help
+	  This option enables support for the PL310 cache controller.
+
 config CACHE_TAUROS2
 	bool "Enable the Tauros2 L2 cache controller"
 	depends on (ARCH_DOVE || ARCH_MMP)
@@ -794,6 +828,8 @@ config ARM_L1_CACHE_SHIFT
 
 config ARM_DMA_MEM_BUFFERABLE
 	bool "Use non-cacheable memory for DMA" if CPU_V6 && !CPU_V7
+	depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \
+		     MACH_REALVIEW_PB11MP)
 	default y if CPU_V6 || CPU_V7
 	help
 	  Historically, the kernel has used strongly ordered mappings to
diff --git a/arch/arm/mm/cache-l2x0.c b/arch/arm/mm/cache-l2x0.c
index 9819869d2bc..e4fa95c6e0b 100644
--- a/arch/arm/mm/cache-l2x0.c
+++ b/arch/arm/mm/cache-l2x0.c
@@ -26,16 +26,39 @@
 #define CACHE_LINE_SIZE		32
 
 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_always(void __iomem *reg, unsigned long mask)
 {
 	/* wait for the operation to complete */
 	while (readl(reg) & mask)
 		;
 }
 
+#ifdef CONFIG_CACHE_PL310
+
+static inline void cache_wait(void __iomem *reg, unsigned long mask)
+{
+	/* cache operations are atomic */
+}
+
+#define _l2x0_lock(lock, flags)		((void)(flags))
+#define _l2x0_unlock(lock, flags)	((void)(flags))
+
+#define block_end(start, end)		(end)
+
+#else	/* !CONFIG_CACHE_PL310 */
+
+#define cache_wait			cache_wait_always
+
+static DEFINE_SPINLOCK(l2x0_lock);
+#define _l2x0_lock(lock, flags)		spin_lock_irqsave(lock, flags)
+#define _l2x0_unlock(lock, flags)	spin_unlock_irqrestore(lock, flags)
+
+#define block_end(start, end)		((start) + min((end) - (start), 4096UL))
+
+#endif	/* CONFIG_CACHE_PL310 */
+
 static inline void cache_sync(void)
 {
 	void __iomem *base = l2x0_base;
@@ -98,9 +121,9 @@ static void l2x0_cache_sync(void)
 {
 	unsigned long flags;
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	_l2x0_lock(&l2x0_lock, flags);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	_l2x0_unlock(&l2x0_lock, flags);
 }
 
 static inline void l2x0_inv_all(void)
@@ -108,11 +131,11 @@ static inline void l2x0_inv_all(void)
 	unsigned long flags;
 
 	/* invalidate all ways */
-	spin_lock_irqsave(&l2x0_lock, flags);
+	_l2x0_lock(&l2x0_lock, flags);
 	writel(l2x0_way_mask, l2x0_base + L2X0_INV_WAY);
 	cache_wait(l2x0_base + L2X0_INV_WAY, l2x0_way_mask);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	_l2x0_unlock(&l2x0_lock, flags);
 }
 
 static void l2x0_inv_range(unsigned long start, unsigned long end)
@@ -120,7 +143,7 @@ static void l2x0_inv_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	_l2x0_lock(&l2x0_lock, flags);
 	if (start & (CACHE_LINE_SIZE - 1)) {
 		start &= ~(CACHE_LINE_SIZE - 1);
 		debug_writel(0x03);
@@ -137,7 +160,7 @@ static void l2x0_inv_range(unsigned long start, unsigned long end)
 	}
 
 	while (start < end) {
-		unsigned long blk_end = start + min(end - start, 4096UL);
+		unsigned long blk_end = block_end(start, end);
 
 		while (start < blk_end) {
 			l2x0_inv_line(start);
@@ -145,13 +168,13 @@ static void l2x0_inv_range(unsigned long start, unsigned long end)
 		}
 
 		if (blk_end < end) {
-			spin_unlock_irqrestore(&l2x0_lock, flags);
-			spin_lock_irqsave(&l2x0_lock, flags);
+			_l2x0_unlock(&l2x0_lock, flags);
+			_l2x0_lock(&l2x0_lock, flags);
 		}
 	}
 	cache_wait(base + L2X0_INV_LINE_PA, 1);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	_l2x0_unlock(&l2x0_lock, flags);
 }
 
 static void l2x0_clean_range(unsigned long start, unsigned long end)
@@ -159,10 +182,10 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	_l2x0_lock(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
-		unsigned long blk_end = start + min(end - start, 4096UL);
+		unsigned long blk_end = block_end(start, end);
 
 		while (start < blk_end) {
 			l2x0_clean_line(start);
@@ -170,13 +193,13 @@ static void l2x0_clean_range(unsigned long start, unsigned long end)
 		}
 
 		if (blk_end < end) {
-			spin_unlock_irqrestore(&l2x0_lock, flags);
-			spin_lock_irqsave(&l2x0_lock, flags);
+			_l2x0_unlock(&l2x0_lock, flags);
+			_l2x0_lock(&l2x0_lock, flags);
 		}
 	}
 	cache_wait(base + L2X0_CLEAN_LINE_PA, 1);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	_l2x0_unlock(&l2x0_lock, flags);
 }
 
 static void l2x0_flush_range(unsigned long start, unsigned long end)
@@ -184,10 +207,10 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 	void __iomem *base = l2x0_base;
 	unsigned long flags;
 
-	spin_lock_irqsave(&l2x0_lock, flags);
+	_l2x0_lock(&l2x0_lock, flags);
 	start &= ~(CACHE_LINE_SIZE - 1);
 	while (start < end) {
-		unsigned long blk_end = start + min(end - start, 4096UL);
+		unsigned long blk_end = block_end(start, end);
 
 		debug_writel(0x03);
 		while (start < blk_end) {
@@ -197,13 +220,13 @@ static void l2x0_flush_range(unsigned long start, unsigned long end)
 		debug_writel(0x00);
 
 		if (blk_end < end) {
-			spin_unlock_irqrestore(&l2x0_lock, flags);
-			spin_lock_irqsave(&l2x0_lock, flags);
+			_l2x0_unlock(&l2x0_lock, flags);
+			_l2x0_lock(&l2x0_lock, flags);
 		}
 	}
 	cache_wait(base + L2X0_CLEAN_INV_LINE_PA, 1);
 	cache_sync();
-	spin_unlock_irqrestore(&l2x0_lock, flags);
+	_l2x0_unlock(&l2x0_lock, flags);
 }
 
 void __init l2x0_init(void __iomem *base, __u32 aux_val, __u32 aux_mask)
diff --git a/arch/arm/mm/cache-v6.S b/arch/arm/mm/cache-v6.S
index e46ecd84713..86aa689ef1a 100644
--- a/arch/arm/mm/cache-v6.S
+++ b/arch/arm/mm/cache-v6.S
@@ -211,8 +211,9 @@ v6_dma_inv_range:
 	mcrne	p15, 0, r1, c7, c15, 1		@ clean & invalidate unified line
 #endif
 1:
-#ifdef CONFIG_SMP
-	str	r0, [r0]			@ write for ownership
+#ifdef CONFIG_DMA_CACHE_RWFO
+	ldr	r2, [r0]			@ read for ownership
+	str	r2, [r0]			@ write for ownership
 #endif
 #ifdef HARVARD_CACHE
 	mcr	p15, 0, r0, c7, c6, 1		@ invalidate D line
@@ -234,7 +235,7 @@ v6_dma_inv_range:
 v6_dma_clean_range:
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
-#ifdef CONFIG_SMP
+#ifdef CONFIG_DMA_CACHE_RWFO
 	ldr	r2, [r0]			@ read for ownership
 #endif
 #ifdef HARVARD_CACHE
@@ -257,7 +258,7 @@ v6_dma_clean_range:
 ENTRY(v6_dma_flush_range)
 	bic	r0, r0, #D_CACHE_LINE_SIZE - 1
 1:
-#ifdef CONFIG_SMP
+#ifdef CONFIG_DMA_CACHE_RWFO
 	ldr	r2, [r0]			@ read for ownership
 	str	r2, [r0]			@ write for ownership
 #endif
@@ -283,9 +284,13 @@ ENTRY(v6_dma_map_area)
 	add	r1, r1, r0
 	teq	r2, #DMA_FROM_DEVICE
 	beq	v6_dma_inv_range
+#ifndef CONFIG_DMA_CACHE_RWFO
+	b	v6_dma_clean_range
+#else
 	teq	r2, #DMA_TO_DEVICE
 	beq	v6_dma_clean_range
 	b	v6_dma_flush_range
+#endif
 ENDPROC(v6_dma_map_area)
 
 /*
@@ -295,6 +300,11 @@ ENDPROC(v6_dma_map_area)
  *	- dir	- DMA direction
  */
 ENTRY(v6_dma_unmap_area)
+#ifndef CONFIG_DMA_CACHE_RWFO
+	add	r1, r1, r0
+	teq	r2, #DMA_TO_DEVICE
+	bne	v6_dma_inv_range
+#endif
 	mov	pc, lr
 ENDPROC(v6_dma_unmap_area)
 
diff --git a/arch/arm/mm/dma-mapping.c b/arch/arm/mm/dma-mapping.c
index fedbcfb8eed..7d1b2db2817 100644
--- a/arch/arm/mm/dma-mapping.c
+++ b/arch/arm/mm/dma-mapping.c
@@ -28,6 +28,7 @@ struct dma_map_ops *dma_ops;
 EXPORT_SYMBOL(dma_ops);
 
 /* Sanity check size */
+#ifdef CONFIG_MMU
 #if (CONSISTENT_DMA_SIZE % SZ_2M)
 #error "CONSISTENT_DMA_SIZE must be multiple of 2MiB"
 #endif
@@ -35,6 +36,7 @@ EXPORT_SYMBOL(dma_ops);
 #define CONSISTENT_OFFSET(x)	(((unsigned long)(x) - CONSISTENT_BASE) >> PAGE_SHIFT)
 #define CONSISTENT_PTE_INDEX(x) (((unsigned long)(x) - CONSISTENT_BASE) >> PGDIR_SHIFT)
 #define NUM_CONSISTENT_PTES (CONSISTENT_DMA_SIZE >> PGDIR_SHIFT)
+#endif
 
 static u64 get_coherent_dma_mask(struct device *dev)
 {
diff --git a/arch/arm/mm/mmu.c b/arch/arm/mm/mmu.c
index 28589417118..499e22d7823 100644
--- a/arch/arm/mm/mmu.c
+++ b/arch/arm/mm/mmu.c
@@ -25,6 +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>
@@ -935,12 +936,11 @@ static void __init devicemaps_init(struct machine_desc *mdesc)
 {
 	struct map_desc map;
 	unsigned long addr;
-	void *vectors;
 
 	/*
 	 * Allocate the vector page early.
 	 */
-	vectors = alloc_bootmem_low_pages(PAGE_SIZE);
+	vectors_page = alloc_bootmem_low_pages(PAGE_SIZE);
 
 	for (addr = VMALLOC_END; addr; addr += PGDIR_SIZE)
 		pmd_clear(pmd_off_k(addr));
@@ -980,7 +980,7 @@ 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 7aaf88a3b7a..c1c3fe0aa30 100644
--- a/arch/arm/mm/proc-v7.S
+++ b/arch/arm/mm/proc-v7.S
@@ -152,8 +152,11 @@ 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
@@ -240,8 +243,6 @@ __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
 	 *
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