Merge branch 'v6v7' into devel

Conflicts:
	arch/arm/include/asm/cacheflush.h
	arch/arm/include/asm/proc-fns.h
	arch/arm/mm/Kconfig

28 files changed, 191 insertions, 189 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 1fd3f280b58..ababf41517d 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -7,7 +7,7 @@ config ARM
 	select HAVE_MEMBLOCK
 	select RTC_LIB
 	select SYS_SUPPORTS_APM_EMULATION
-	select GENERIC_ATOMIC64 if (!CPU_32v6K || !AEABI)
+	select GENERIC_ATOMIC64 if (CPU_V6 || !CPU_32v6K || !AEABI)
 	select HAVE_OPROFILE if (HAVE_PERF_EVENTS)
 	select HAVE_ARCH_KGDB
 	select HAVE_KPROBES if (!XIP_KERNEL && !THUMB2_KERNEL)
@@ -24,7 +24,7 @@ config ARM
 	select HAVE_PERF_EVENTS
 	select PERF_USE_VMALLOC
 	select HAVE_REGS_AND_STACK_ACCESS_API
-	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V7))
+	select HAVE_HW_BREAKPOINT if (PERF_EVENTS && (CPU_V6 || CPU_V6K || CPU_V7))
 	select HAVE_C_RECORDMCOUNT
 	select HAVE_GENERIC_HARDIRQS
 	select HAVE_SPARSE_IRQ
@@ -456,6 +456,7 @@ config ARCH_IXP4XX
 
 config ARCH_DOVE
 	bool "Marvell Dove"
+	select CPU_V6K
 	select PCI
 	select ARCH_REQUIRE_GPIOLIB
 	select GENERIC_CLOCKEVENTS
@@ -1059,7 +1060,7 @@ config XSCALE_PMU
 	default y
 
 config CPU_HAS_PMU
-	depends on (CPU_V6 || CPU_V7 || XSCALE_PMU) && \
+	depends on (CPU_V6 || CPU_V6K || CPU_V7 || XSCALE_PMU) && \
 		   (!ARCH_OMAP3 || OMAP3_EMU)
 	default y
 	bool
@@ -1075,7 +1076,7 @@ endif
 
 config ARM_ERRATA_411920
 	bool "ARM errata: Invalidation of the Instruction Cache operation can fail"
-	depends on CPU_V6
+	depends on CPU_V6 || CPU_V6K
 	help
 	  Invalidation of the Instruction Cache operation can
 	  fail. This erratum is present in 1136 (before r1p4), 1156 and 1176.
@@ -1318,6 +1319,7 @@ source "kernel/time/Kconfig"
 config SMP
 	bool "Symmetric Multi-Processing (EXPERIMENTAL)"
 	depends on EXPERIMENTAL
+	depends on CPU_V6K || CPU_V7
 	depends on GENERIC_CLOCKEVENTS
 	depends on REALVIEW_EB_ARM11MP || REALVIEW_EB_A9MP || \
 		 MACH_REALVIEW_PB11MP || MACH_REALVIEW_PBX || ARCH_OMAP4 || \
@@ -1429,7 +1431,7 @@ config HZ
 
 config THUMB2_KERNEL
 	bool "Compile the kernel in Thumb-2 mode (EXPERIMENTAL)"
-	depends on CPU_V7 && !CPU_V6 && EXPERIMENTAL
+	depends on CPU_V7 && !CPU_V6 && !CPU_V6K && EXPERIMENTAL
 	select AEABI
 	select ARM_ASM_UNIFIED
 	help
@@ -1963,7 +1965,7 @@ config FPE_FASTFPE
 
 config VFP
 	bool "VFP-format floating point maths"
-	depends on CPU_V6 || CPU_ARM926T || CPU_V7 || CPU_FEROCEON
+	depends on CPU_V6 || CPU_V6K || CPU_ARM926T || CPU_V7 || CPU_FEROCEON
 	help
 	  Say Y to include VFP support code in the kernel. This is needed
 	  if your hardware includes a VFP unit.
diff --git a/arch/arm/Makefile b/arch/arm/Makefile
index 55eca9ed760..1e20c414d5c 100644
--- a/arch/arm/Makefile
+++ b/arch/arm/Makefile
@@ -89,6 +89,7 @@ tune-$(CONFIG_CPU_XSCALE)	:=$(call cc-option,-mtune=xscale,-mtune=strongarm110)
 tune-$(CONFIG_CPU_XSC3)		:=$(call cc-option,-mtune=xscale,-mtune=strongarm110) -Wa,-mcpu=xscale
 tune-$(CONFIG_CPU_FEROCEON)	:=$(call cc-option,-mtune=marvell-f,-mtune=xscale)
 tune-$(CONFIG_CPU_V6)		:=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
+tune-$(CONFIG_CPU_V6K)		:=$(call cc-option,-mtune=arm1136j-s,-mtune=strongarm)
 
 ifeq ($(CONFIG_AEABI),y)
 CFLAGS_ABI	:=-mabi=aapcs-linux -mno-thumb-interwork
diff --git a/arch/arm/boot/compressed/head.S b/arch/arm/boot/compressed/head.S
index 39859216af0..84ac4d65631 100644
--- a/arch/arm/boot/compressed/head.S
+++ b/arch/arm/boot/compressed/head.S
@@ -21,7 +21,7 @@
 
 #if defined(CONFIG_DEBUG_ICEDCC)
 
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 		.macro	loadsp, rb, tmp
 		.endm
 		.macro	writeb, ch, rb
diff --git a/arch/arm/boot/compressed/misc.c b/arch/arm/boot/compressed/misc.c
index e653a6d3c8d..4657e877bf8 100644
--- a/arch/arm/boot/compressed/misc.c
+++ b/arch/arm/boot/compressed/misc.c
@@ -36,7 +36,7 @@ extern void error(char *x);
 
 #ifdef CONFIG_DEBUG_ICEDCC
 
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 
 static void icedcc_putc(int ch)
 {
diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h
index 7b1bb2bbaf8..af54ed102f5 100644
--- a/arch/arm/include/asm/bitops.h
+++ b/arch/arm/include/asm/bitops.h
@@ -149,14 +149,18 @@ ____atomic_test_and_change_bit(unsigned int bit, volatile unsigned long *p)
  */
 
 /*
+ * Native endian assembly bitops.  nr = 0 -> word 0 bit 0.
+ */
+extern void _set_bit(int nr, volatile unsigned long * p);
+extern void _clear_bit(int nr, volatile unsigned long * p);
+extern void _change_bit(int nr, volatile unsigned long * p);
+extern int _test_and_set_bit(int nr, volatile unsigned long * p);
+extern int _test_and_clear_bit(int nr, volatile unsigned long * p);
+extern int _test_and_change_bit(int nr, volatile unsigned long * p);
+
+/*
  * Little endian assembly bitops.  nr = 0 -> byte 0 bit 0.
  */
-extern void _set_bit_le(int nr, volatile unsigned long * p);
-extern void _clear_bit_le(int nr, volatile unsigned long * p);
-extern void _change_bit_le(int nr, volatile unsigned long * p);
-extern int _test_and_set_bit_le(int nr, volatile unsigned long * p);
-extern int _test_and_clear_bit_le(int nr, volatile unsigned long * p);
-extern int _test_and_change_bit_le(int nr, volatile unsigned long * p);
 extern int _find_first_zero_bit_le(const void * p, unsigned size);
 extern int _find_next_zero_bit_le(const void * p, int size, int offset);
 extern int _find_first_bit_le(const unsigned long *p, unsigned size);
@@ -165,12 +169,6 @@ extern int _find_next_bit_le(const unsigned long *p, int size, int offset);
 /*
  * Big endian assembly bitops.  nr = 0 -> byte 3 bit 0.
  */
-extern void _set_bit_be(int nr, volatile unsigned long * p);
-extern void _clear_bit_be(int nr, volatile unsigned long * p);
-extern void _change_bit_be(int nr, volatile unsigned long * p);
-extern int _test_and_set_bit_be(int nr, volatile unsigned long * p);
-extern int _test_and_clear_bit_be(int nr, volatile unsigned long * p);
-extern int _test_and_change_bit_be(int nr, volatile unsigned long * p);
 extern int _find_first_zero_bit_be(const void * p, unsigned size);
 extern int _find_next_zero_bit_be(const void * p, int size, int offset);
 extern int _find_first_bit_be(const unsigned long *p, unsigned size);
@@ -180,33 +178,26 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 /*
  * The __* form of bitops are non-atomic and may be reordered.
  */
-#define	ATOMIC_BITOP_LE(name,nr,p)		\
-	(__builtin_constant_p(nr) ?		\
-	 ____atomic_##name(nr, p) :		\
-	 _##name##_le(nr,p))
-
-#define	ATOMIC_BITOP_BE(name,nr,p)		\
-	(__builtin_constant_p(nr) ?		\
-	 ____atomic_##name(nr, p) :		\
-	 _##name##_be(nr,p))
+#define ATOMIC_BITOP(name,nr,p)			\
+	(__builtin_constant_p(nr) ? ____atomic_##name(nr, p) : _##name(nr,p))
 #else
-#define ATOMIC_BITOP_LE(name,nr,p)	_##name##_le(nr,p)
-#define ATOMIC_BITOP_BE(name,nr,p)	_##name##_be(nr,p)
+#define ATOMIC_BITOP(name,nr,p)		_##name(nr,p)
 #endif
 
-#define NONATOMIC_BITOP(name,nr,p)		\
-	(____nonatomic_##name(nr, p))
+/*
+ * Native endian atomic definitions.
+ */
+#define set_bit(nr,p)			ATOMIC_BITOP(set_bit,nr,p)
+#define clear_bit(nr,p)			ATOMIC_BITOP(clear_bit,nr,p)
+#define change_bit(nr,p)		ATOMIC_BITOP(change_bit,nr,p)
+#define test_and_set_bit(nr,p)		ATOMIC_BITOP(test_and_set_bit,nr,p)
+#define test_and_clear_bit(nr,p)	ATOMIC_BITOP(test_and_clear_bit,nr,p)
+#define test_and_change_bit(nr,p)	ATOMIC_BITOP(test_and_change_bit,nr,p)
 
 #ifndef __ARMEB__
 /*
  * These are the little endian, atomic definitions.
  */
-#define set_bit(nr,p)			ATOMIC_BITOP_LE(set_bit,nr,p)
-#define clear_bit(nr,p)			ATOMIC_BITOP_LE(clear_bit,nr,p)
-#define change_bit(nr,p)		ATOMIC_BITOP_LE(change_bit,nr,p)
-#define test_and_set_bit(nr,p)		ATOMIC_BITOP_LE(test_and_set_bit,nr,p)
-#define test_and_clear_bit(nr,p)	ATOMIC_BITOP_LE(test_and_clear_bit,nr,p)
-#define test_and_change_bit(nr,p)	ATOMIC_BITOP_LE(test_and_change_bit,nr,p)
 #define find_first_zero_bit(p,sz)	_find_first_zero_bit_le(p,sz)
 #define find_next_zero_bit(p,sz,off)	_find_next_zero_bit_le(p,sz,off)
 #define find_first_bit(p,sz)		_find_first_bit_le(p,sz)
@@ -215,16 +206,9 @@ extern int _find_next_bit_be(const unsigned long *p, int size, int offset);
 #define WORD_BITOFF_TO_LE(x)		((x))
 
 #else
-
 /*
  * These are the big endian, atomic definitions.
  */
-#define set_bit(nr,p)			ATOMIC_BITOP_BE(set_bit,nr,p)
-#define clear_bit(nr,p)			ATOMIC_BITOP_BE(clear_bit,nr,p)
-#define change_bit(nr,p)		ATOMIC_BITOP_BE(change_bit,nr,p)
-#define test_and_set_bit(nr,p)		ATOMIC_BITOP_BE(test_and_set_bit,nr,p)
-#define test_and_clear_bit(nr,p)	ATOMIC_BITOP_BE(test_and_clear_bit,nr,p)
-#define test_and_change_bit(nr,p)	ATOMIC_BITOP_BE(test_and_change_bit,nr,p)
 #define find_first_zero_bit(p,sz)	_find_first_zero_bit_be(p,sz)
 #define find_next_zero_bit(p,sz,off)	_find_next_zero_bit_be(p,sz,off)
 #define find_first_bit(p,sz)		_find_first_bit_be(p,sz)
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 18a56640d97..d5d8d5c7268 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -187,7 +187,8 @@ extern void copy_to_user_page(struct vm_area_struct *, struct page *,
  * Optimized __flush_icache_all for the common cases. Note that UP ARMv7
  * will fall through to use __flush_icache_all_generic.
  */
-#if (defined(CONFIG_CPU_V7) && defined(CONFIG_CPU_V6)) ||		\
+#if (defined(CONFIG_CPU_V7) && \
+     (defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K))) || \
 	defined(CONFIG_SMP_ON_UP)
 #define __flush_icache_preferred	__cpuc_flush_icache_all
 #elif __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
diff --git a/arch/arm/include/asm/glue-cache.h b/arch/arm/include/asm/glue-cache.h
index 0591d35001e..c7afbc552c7 100644
--- a/arch/arm/include/asm/glue-cache.h
+++ b/arch/arm/include/asm/glue-cache.h
@@ -109,7 +109,7 @@
 # define MULTI_CACHE 1
 #endif
 
-#if defined(CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 //# ifdef _CACHE
 #  define MULTI_CACHE 1
 //# else
diff --git a/arch/arm/include/asm/glue-proc.h b/arch/arm/include/asm/glue-proc.h
index 6469521d092..e2be7f14266 100644
--- a/arch/arm/include/asm/glue-proc.h
+++ b/arch/arm/include/asm/glue-proc.h
@@ -230,7 +230,7 @@
 # endif
 #endif
 
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 # ifdef CPU_NAME
 #  undef  MULTI_CPU
 #  define MULTI_CPU
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 17eb355707d..fdd3820edff 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -5,17 +5,52 @@
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
+/*
+ * sev and wfe are ARMv6K extensions.  Uniprocessor ARMv6 may not have the K
+ * extensions, so when running on UP, we have to patch these instructions away.
+ */
+#define ALT_SMP(smp, up)					\
+	"9998:	" smp "\n"					\
+	"	.pushsection \".alt.smp.init\", \"a\"\n"	\
+	"	.long	9998b\n"				\
+	"	" up "\n"					\
+	"	.popsection\n"
+
+#ifdef CONFIG_THUMB2_KERNEL
+#define SEV		ALT_SMP("sev.w", "nop.w")
+/*
+ * For Thumb-2, special care is needed to ensure that the conditional WFE
+ * instruction really does assemble to exactly 4 bytes (as required by
+ * the SMP_ON_UP fixup code).   By itself "wfene" might cause the
+ * assembler to insert a extra (16-bit) IT instruction, depending on the
+ * presence or absence of neighbouring conditional instructions.
+ *
+ * To avoid this unpredictableness, an approprite IT is inserted explicitly:
+ * the assembler won't change IT instructions which are explicitly present
+ * in the input.
+ */
+#define WFE(cond)	ALT_SMP(		\
+	"it " cond "\n\t"			\
+	"wfe" cond ".n",			\
+						\
+	"nop.w"					\
+)
+#else
+#define SEV		ALT_SMP("sev", "nop")
+#define WFE(cond)	ALT_SMP("wfe" cond, "nop")
+#endif
+
 static inline void dsb_sev(void)
 {
 #if __LINUX_ARM_ARCH__ >= 7
 	__asm__ __volatile__ (
 		"dsb\n"
-		"sev"
+		SEV
 	);
-#elif defined(CONFIG_CPU_32v6K)
+#else
 	__asm__ __volatile__ (
 		"mcr p15, 0, %0, c7, c10, 4\n"
-		"sev"
+		SEV
 		: : "r" (0)
 	);
 #endif
@@ -46,9 +81,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%1]\n"
 "	teq	%0, #0\n"
-#ifdef CONFIG_CPU_32v6K
-"	wfene\n"
-#endif
+	WFE("ne")
 "	strexeq	%0, %2, [%1]\n"
 "	teqeq	%0, #0\n"
 "	bne	1b"
@@ -107,9 +140,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%1]\n"
 "	teq	%0, #0\n"
-#ifdef CONFIG_CPU_32v6K
-"	wfene\n"
-#endif
+	WFE("ne")
 "	strexeq	%0, %2, [%1]\n"
 "	teq	%0, #0\n"
 "	bne	1b"
@@ -176,9 +207,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 "1:	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
 "	strexpl	%1, %0, [%2]\n"
-#ifdef CONFIG_CPU_32v6K
-"	wfemi\n"
-#endif
+	WFE("mi")
 "	rsbpls	%0, %1, #0\n"
 "	bmi	1b"
 	: "=&r" (tmp), "=&r" (tmp2)
diff --git a/arch/arm/include/asm/system.h b/arch/arm/include/asm/system.h
index 97f6d60297d..9a87823642d 100644
--- a/arch/arm/include/asm/system.h
+++ b/arch/arm/include/asm/system.h
@@ -347,6 +347,7 @@ void cpu_idle_wait(void);
 #include <asm-generic/cmpxchg-local.h>
 
 #if __LINUX_ARM_ARCH__ < 6
+/* min ARCH < ARMv6 */
 
 #ifdef CONFIG_SMP
 #error "SMP is not supported on this platform"
@@ -365,7 +366,7 @@ void cpu_idle_wait(void);
 #include <asm-generic/cmpxchg.h>
 #endif
 
-#else	/* __LINUX_ARM_ARCH__ >= 6 */
+#else	/* min ARCH >= ARMv6 */
 
 extern void __bad_cmpxchg(volatile void *ptr, int size);
 
@@ -379,7 +380,7 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 	unsigned long oldval, res;
 
 	switch (size) {
-#ifdef CONFIG_CPU_32v6K
+#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
 	case 1:
 		do {
 			asm volatile("@ __cmpxchg1\n"
@@ -404,7 +405,7 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 				: "memory", "cc");
 		} while (res);
 		break;
-#endif /* CONFIG_CPU_32v6K */
+#endif
 	case 4:
 		do {
 			asm volatile("@ __cmpxchg4\n"
@@ -450,12 +451,12 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 	unsigned long ret;
 
 	switch (size) {
-#ifndef CONFIG_CPU_32v6K
+#ifdef CONFIG_CPU_V6	/* min ARCH == ARMv6 */
 	case 1:
 	case 2:
 		ret = __cmpxchg_local_generic(ptr, old, new, size);
 		break;
-#endif	/* !CONFIG_CPU_32v6K */
+#endif
 	default:
 		ret = __cmpxchg(ptr, old, new, size);
 	}
@@ -469,7 +470,7 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 				       (unsigned long)(n),		\
 				       sizeof(*(ptr))))
 
-#ifdef CONFIG_CPU_32v6K
+#ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
 
 /*
  * Note : ARMv7-M (currently unsupported by Linux) does not support
@@ -524,11 +525,11 @@ static inline unsigned long long __cmpxchg64_mb(volatile void *ptr,
 					 (unsigned long long)(o),	\
 					 (unsigned long long)(n)))
 
-#else	/* !CONFIG_CPU_32v6K */
+#else /* min ARCH = ARMv6 */
 
 #define cmpxchg64_local(ptr, o, n) __cmpxchg64_local_generic((ptr), (o), (n))
 
-#endif	/* CONFIG_CPU_32v6K */
+#endif
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
diff --git a/arch/arm/include/asm/tls.h b/arch/arm/include/asm/tls.h
index e71d6ff8d10..60843eb0f61 100644
--- a/arch/arm/include/asm/tls.h
+++ b/arch/arm/include/asm/tls.h
@@ -28,15 +28,14 @@
 #define tls_emu		1
 #define has_tls_reg		1
 #define set_tls		set_tls_none
-#elif __LINUX_ARM_ARCH__ >= 7 ||					\
-	(__LINUX_ARM_ARCH__ == 6 && defined(CONFIG_CPU_32v6K))
-#define tls_emu		0
-#define has_tls_reg		1
-#define set_tls		set_tls_v6k
-#elif __LINUX_ARM_ARCH__ == 6
+#elif defined(CONFIG_CPU_V6)
 #define tls_emu		0
 #define has_tls_reg		(elf_hwcap & HWCAP_TLS)
 #define set_tls		set_tls_v6
+#elif defined(CONFIG_CPU_32v6K)
+#define tls_emu		0
+#define has_tls_reg		1
+#define set_tls		set_tls_v6k
 #else
 #define tls_emu		0
 #define has_tls_reg		0
diff --git a/arch/arm/kernel/armksyms.c b/arch/arm/kernel/armksyms.c
index e5e1e538767..d5d4185f0c2 100644
--- a/arch/arm/kernel/armksyms.c
+++ b/arch/arm/kernel/armksyms.c
@@ -140,24 +140,18 @@ EXPORT_SYMBOL(__aeabi_ulcmp);
 #endif
 
 	/* bitops */
-EXPORT_SYMBOL(_set_bit_le);
-EXPORT_SYMBOL(_test_and_set_bit_le);
-EXPORT_SYMBOL(_clear_bit_le);
-EXPORT_SYMBOL(_test_and_clear_bit_le);
-EXPORT_SYMBOL(_change_bit_le);
-EXPORT_SYMBOL(_test_and_change_bit_le);
+EXPORT_SYMBOL(_set_bit);
+EXPORT_SYMBOL(_test_and_set_bit);
+EXPORT_SYMBOL(_clear_bit);
+EXPORT_SYMBOL(_test_and_clear_bit);
+EXPORT_SYMBOL(_change_bit);
+EXPORT_SYMBOL(_test_and_change_bit);
 EXPORT_SYMBOL(_find_first_zero_bit_le);
 EXPORT_SYMBOL(_find_next_zero_bit_le);
 EXPORT_SYMBOL(_find_first_bit_le);
 EXPORT_SYMBOL(_find_next_bit_le);
 
 #ifdef __ARMEB__
-EXPORT_SYMBOL(_set_bit_be);
-EXPORT_SYMBOL(_test_and_set_bit_be);
-EXPORT_SYMBOL(_clear_bit_be);
-EXPORT_SYMBOL(_test_and_clear_bit_be);
-EXPORT_SYMBOL(_change_bit_be);
-EXPORT_SYMBOL(_test_and_change_bit_be);
 EXPORT_SYMBOL(_find_first_zero_bit_be);
 EXPORT_SYMBOL(_find_next_zero_bit_be);
 EXPORT_SYMBOL(_find_first_bit_be);
diff --git a/arch/arm/kernel/debug.S b/arch/arm/kernel/debug.S
index a0f07521ca8..d2d983be096 100644
--- a/arch/arm/kernel/debug.S
+++ b/arch/arm/kernel/debug.S
@@ -25,7 +25,7 @@
 		.macro	addruart, rp, rv
 		.endm
 
-#if defined(CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 
 		.macro	senduart, rd, rx
 		mcr	p14, 0, \rd, c0, c5, 0
diff --git a/arch/arm/kernel/entry-header.S b/arch/arm/kernel/entry-header.S
index ae946490016..051166c2a93 100644
--- a/arch/arm/kernel/entry-header.S
+++ b/arch/arm/kernel/entry-header.S
@@ -76,13 +76,13 @@
 #ifndef CONFIG_THUMB2_KERNEL
 	.macro	svc_exit, rpsr
 	msr	spsr_cxsf, \rpsr
-#if defined(CONFIG_CPU_32v6K)
-	clrex					@ clear the exclusive monitor
-	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
-#elif defined (CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6)
 	ldr	r0, [sp]
 	strex	r1, r2, [sp]			@ clear the exclusive monitor
 	ldmib	sp, {r1 - pc}^			@ load r1 - pc, cpsr
+#elif defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
+	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
 #else
 	ldmia	sp, {r0 - pc}^			@ load r0 - pc, cpsr
 #endif
@@ -92,10 +92,10 @@
 	ldr	r1, [sp, #\offset + S_PSR]	@ get calling cpsr
 	ldr	lr, [sp, #\offset + S_PC]!	@ get pc
 	msr	spsr_cxsf, r1			@ save in spsr_svc
-#if defined(CONFIG_CPU_32v6K)
-	clrex					@ clear the exclusive monitor
-#elif defined (CONFIG_CPU_V6)
+#if defined(CONFIG_CPU_V6)
 	strex	r1, r2, [sp]			@ clear the exclusive monitor
+#elif defined(CONFIG_CPU_32v6K)
+	clrex					@ clear the exclusive monitor
 #endif
 	.if	\fast
 	ldmdb	sp, {r1 - lr}^			@ get calling r1 - lr
diff --git a/arch/arm/kernel/perf_event_v6.c b/arch/arm/kernel/perf_event_v6.c
index c058bfc8532..6fc2d228db5 100644
--- a/arch/arm/kernel/perf_event_v6.c
+++ b/arch/arm/kernel/perf_event_v6.c
@@ -30,7 +30,7 @@
  * enable the interrupt.
  */
 
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 enum armv6_perf_types {
 	ARMV6_PERFCTR_ICACHE_MISS	    = 0x0,
 	ARMV6_PERFCTR_IBUF_STALL	    = 0x1,
@@ -669,4 +669,4 @@ static const struct arm_pmu *__init armv6mpcore_pmu_init(void)
 {
 	return NULL;
 }
-#endif	/* CONFIG_CPU_V6 */
+#endif	/* CONFIG_CPU_V6 || CONFIG_CPU_V6K */
diff --git a/arch/arm/lib/bitops.h b/arch/arm/lib/bitops.h
index d42252918bf..10d868a5a48 100644
--- a/arch/arm/lib/bitops.h
+++ b/arch/arm/lib/bitops.h
@@ -1,44 +1,52 @@
-
-#if __LINUX_ARM_ARCH__ >= 6 && defined(CONFIG_CPU_32v6K)
+#if __LINUX_ARM_ARCH__ >= 6
 	.macro	bitop, instr
+	ands	ip, r1, #3
+	strneb	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
-	and	r3, r0, #7		@ Get bit offset
-	add	r1, r1, r0, lsr #3	@ Get byte offset
+	and	r3, r0, #31		@ Get bit offset
+	mov	r0, r0, lsr #5
+	add	r1, r1, r0, lsl #2	@ Get word offset
 	mov	r3, r2, lsl r3
-1:	ldrexb	r2, [r1]
+1:	ldrex	r2, [r1]
 	\instr	r2, r2, r3
-	strexb	r0, r2, [r1]
+	strex	r0, r2, [r1]
 	cmp	r0, #0
 	bne	1b
-	mov	pc, lr
+	bx	lr
 	.endm
 
 	.macro	testop, instr, store
-	and	r3, r0, #7		@ Get bit offset
+	ands	ip, r1, #3
+	strneb	r1, [ip]		@ assert word-aligned
 	mov	r2, #1
-	add	r1, r1, r0, lsr #3	@ Get byte offset
+	and	r3, r0, #31		@ Get bit offset
+	mov	r0, r0, lsr #5
+	add	r1, r1, r0, lsl #2	@ Get word offset
 	mov	r3, r2, lsl r3		@ create mask
 	smp_dmb
-1:	ldrexb	r2, [r1]
+1:	ldrex	r2, [r1]
 	ands	r0, r2, r3		@ save old value of bit
-	\instr	r2, r2, r3			@ toggle bit
-	strexb	ip, r2, [r1]
+	\instr	r2, r2, r3		@ toggle bit
+	strex	ip, r2, [r1]
 	cmp	ip, #0
 	bne	1b
 	smp_dmb
 	cmp	r0, #0
 	movne	r0, #1
-2:	mov	pc, lr
+2:	bx	lr
 	.endm
 #else
 	.macro	bitop, instr
-	and	r2, r0, #7
+	ands	ip, r1, #3
+	strneb	r1, [ip]		@ assert word-aligned
+	and	r2, r0, #31
+	mov	r0, r0, lsr #5
 	mov	r3, #1
 	mov	r3, r3, lsl r2
 	save_and_disable_irqs ip
-	ldrb	r2, [r1, r0, lsr #3]
+	ldr	r2, [r1, r0, lsl #2]
 	\instr	r2, r2, r3
-	strb	r2, [r1, r0, lsr #3]
+	str	r2, [r1, r0, lsl #2]
 	restore_irqs ip
 	mov	pc, lr
 	.endm
@@ -52,11 +60,13 @@
  * to avoid dirtying the data cache.
  */
 	.macro	testop, instr, store
-	add	r1, r1, r0, lsr #3
-	and	r3, r0, #7
-	mov	r0, #1
+	ands	ip, r1, #3
+	strneb	r1, [ip]		@ assert word-aligned
+	and	r3, r0, #31
+	mov	r0, r0, lsr #5
 	save_and_disable_irqs ip
-	ldrb	r2, [r1]
+	ldr	r2, [r1, r0, lsl #2]!
+	mov	r0, #1
 	tst	r2, r0, lsl r3
 	\instr	r2, r2, r0, lsl r3
 	\store	r2, [r1]
diff --git a/arch/arm/lib/changebit.S b/arch/arm/lib/changebit.S
index 80f3115cbee..68ed5b62e83 100644
--- a/arch/arm/lib/changebit.S
+++ b/arch/arm/lib/changebit.S
@@ -12,12 +12,6 @@
 #include "bitops.h"
                 .text
 
-/* Purpose  : Function to change a bit
- * Prototype: int change_bit(int bit, void *addr)
- */
-ENTRY(_change_bit_be)
-		eor	r0, r0, #0x18		@ big endian byte ordering
-ENTRY(_change_bit_le)
+ENTRY(_change_bit)
 	bitop	eor
-ENDPROC(_change_bit_be)
-ENDPROC(_change_bit_le)
+ENDPROC(_change_bit)
diff --git a/arch/arm/lib/clearbit.S b/arch/arm/lib/clearbit.S
index 1a63e43a1df..4c04c3b51ee 100644
--- a/arch/arm/lib/clearbit.S
+++ b/arch/arm/lib/clearbit.S
@@ -12,13 +12,6 @@
 #include "bitops.h"
                 .text
 
-/*
- * Purpose  : Function to clear a bit
- * Prototype: int clear_bit(int bit, void *addr)
- */
-ENTRY(_clear_bit_be)
-		eor	r0, r0, #0x18		@ big endian byte ordering
-ENTRY(_clear_bit_le)
+ENTRY(_clear_bit)
 	bitop	bic
-ENDPROC(_clear_bit_be)
-ENDPROC(_clear_bit_le)
+ENDPROC(_clear_bit)
diff --git a/arch/arm/lib/setbit.S b/arch/arm/lib/setbit.S
index 1dd7176c4b2..bbee5c66a23 100644
--- a/arch/arm/lib/setbit.S
+++ b/arch/arm/lib/setbit.S
@@ -12,13 +12,6 @@
 #include "bitops.h"
 		.text
 
-/*
- * Purpose  : Function to set a bit
- * Prototype: int set_bit(int bit, void *addr)
- */
-ENTRY(_set_bit_be)
-		eor	r0, r0, #0x18		@ big endian byte ordering
-ENTRY(_set_bit_le)
+ENTRY(_set_bit)
 	bitop	orr
-ENDPROC(_set_bit_be)
-ENDPROC(_set_bit_le)
+ENDPROC(_set_bit)
diff --git a/arch/arm/lib/testchangebit.S b/arch/arm/lib/testchangebit.S
index 5c98dc567f0..15a4d431f22 100644
--- a/arch/arm/lib/testchangebit.S
+++ b/arch/arm/lib/testchangebit.S
@@ -12,9 +12,6 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_test_and_change_bit_be)
-		eor	r0, r0, #0x18		@ big endian byte ordering
-ENTRY(_test_and_change_bit_le)
-	testop	eor, strb
-ENDPROC(_test_and_change_bit_be)
-ENDPROC(_test_and_change_bit_le)
+ENTRY(_test_and_change_bit)
+	testop	eor, str
+ENDPROC(_test_and_change_bit)
diff --git a/arch/arm/lib/testclearbit.S b/arch/arm/lib/testclearbit.S
index 543d7094d18..521b66b5b95 100644
--- a/arch/arm/lib/testclearbit.S
+++ b/arch/arm/lib/testclearbit.S
@@ -12,9 +12,6 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_test_and_clear_bit_be)
-		eor	r0, r0, #0x18		@ big endian byte ordering
-ENTRY(_test_and_clear_bit_le)
-	testop	bicne, strneb
-ENDPROC(_test_and_clear_bit_be)
-ENDPROC(_test_and_clear_bit_le)
+ENTRY(_test_and_clear_bit)
+	testop	bicne, strne
+ENDPROC(_test_and_clear_bit)
diff --git a/arch/arm/lib/testsetbit.S b/arch/arm/lib/testsetbit.S
index 0b3f390401c..1c98cc2185b 100644
--- a/arch/arm/lib/testsetbit.S
+++ b/arch/arm/lib/testsetbit.S
@@ -12,9 +12,6 @@
 #include "bitops.h"
                 .text
 
-ENTRY(_test_and_set_bit_be)
-		eor	r0, r0, #0x18		@ big endian byte ordering
-ENTRY(_test_and_set_bit_le)
-	testop	orreq, streqb
-ENDPROC(_test_and_set_bit_be)
-ENDPROC(_test_and_set_bit_le)
+ENTRY(_test_and_set_bit)
+	testop	orreq, streq
+ENDPROC(_test_and_set_bit)
diff --git a/arch/arm/mach-dove/Kconfig b/arch/arm/mach-dove/Kconfig
index a4ed3900912..dd937c526a4 100644
--- a/arch/arm/mach-dove/Kconfig
+++ b/arch/arm/mach-dove/Kconfig
@@ -9,7 +9,7 @@ config MACH_DOVE_DB
 	  Say 'Y' here if you want your kernel to support the
 	  Marvell DB-MV88AP510 Development Board.
 
- config MACH_CM_A510
+config MACH_CM_A510
 	bool "CompuLab CM-A510 Board"
 	help
 	  Say 'Y' here if you want your kernel to support the
diff --git a/arch/arm/mach-realview/Kconfig b/arch/arm/mach-realview/Kconfig
index 7ca138a943a..b9a9805e482 100644
--- a/arch/arm/mach-realview/Kconfig
+++ b/arch/arm/mach-realview/Kconfig
@@ -19,7 +19,7 @@ config REALVIEW_EB_A9MP
 config REALVIEW_EB_ARM11MP
 	bool "Support ARM11MPCore Tile"
 	depends on MACH_REALVIEW_EB
-	select CPU_V6
+	select CPU_V6K
 	select ARCH_HAS_BARRIERS if SMP
 	help
 	  Enable support for the ARM11MPCore tile fitted to the Realview(R)
@@ -36,7 +36,7 @@ config REALVIEW_EB_ARM11MP_REVB
 
 config MACH_REALVIEW_PB11MP
 	bool "Support RealView(R) Platform Baseboard for ARM11MPCore"
-	select CPU_V6
+	select CPU_V6K
 	select ARM_GIC
 	select HAVE_PATA_PLATFORM
 	select ARCH_HAS_BARRIERS if SMP
@@ -45,6 +45,7 @@ config MACH_REALVIEW_PB11MP
 	  the ARM11MPCore.  This platform has an on-board ARM11MPCore and has
 	  support for PCI-E and Compact Flash.
 
+# ARMv6 CPU without K extensions, but does have the new exclusive ops
 config MACH_REALVIEW_PB1176
 	bool "Support RealView(R) Platform Baseboard for ARM1176JZF-S"
 	select CPU_V6
diff --git a/arch/arm/mm/Kconfig b/arch/arm/mm/Kconfig
index 05b26a03c20..89266382b53 100644
--- a/arch/arm/mm/Kconfig
+++ b/arch/arm/mm/Kconfig
@@ -390,7 +390,7 @@ config CPU_PJ4
 
 # ARMv6
 config CPU_V6
-	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX || ARCH_DOVE
+	bool "Support ARM V6 processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
 	select CPU_32v6
 	select CPU_ABRT_EV6
 	select CPU_PABRT_V6
@@ -402,16 +402,18 @@ config CPU_V6
 	select CPU_TLB_V6 if MMU
 
 # ARMv6k
-config CPU_32v6K
-	bool "Support ARM V6K processor extensions" if !SMP
-	depends on CPU_V6 || CPU_V7
-	default y if SMP
-	help
-	  Say Y here if your ARMv6 processor supports the 'K' extension.
-	  This enables the kernel to use some instructions not present
-	  on previous processors, and as such a kernel build with this
-	  enabled will not boot on processors with do not support these
-	  instructions.
+config CPU_V6K
+	bool "Support ARM V6K processor" if ARCH_INTEGRATOR || MACH_REALVIEW_EB || MACH_REALVIEW_PBX
+	select CPU_32v6
+	select CPU_32v6K
+	select CPU_ABRT_EV6
+	select CPU_PABRT_V6
+	select CPU_CACHE_V6
+	select CPU_CACHE_VIPT
+	select CPU_CP15_MMU
+	select CPU_HAS_ASID if MMU
+	select CPU_COPY_V6 if MMU
+	select CPU_TLB_V6 if MMU
 
 # ARMv7
 config CPU_V7
@@ -433,25 +435,33 @@ config CPU_32v3
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v4
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v4T
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v5
 	bool
 	select TLS_REG_EMUL if SMP || !MMU
 	select NEEDS_SYSCALL_FOR_CMPXCHG if SMP
+	select CPU_USE_DOMAINS if MMU
 
 config CPU_32v6
 	bool
 	select TLS_REG_EMUL if !CPU_32v6K && !MMU
+	select CPU_USE_DOMAINS if CPU_V6 && MMU
+
+config CPU_32v6K
+	bool
 
 config CPU_32v7
 	bool
@@ -607,8 +617,6 @@ config CPU_CP15_MPU
 
 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.
@@ -623,7 +631,7 @@ comment "Processor Features"
 
 config ARM_THUMB
 	bool "Support Thumb user binaries"
-	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V7 || CPU_FEROCEON
+	depends on CPU_ARM720T || CPU_ARM740T || CPU_ARM920T || CPU_ARM922T || CPU_ARM925T || CPU_ARM926T || CPU_ARM940T || CPU_ARM946E || CPU_ARM1020 || CPU_ARM1020E || CPU_ARM1022 || CPU_ARM1026 || CPU_XSCALE || CPU_XSC3 || CPU_MOHAWK || CPU_V6 || CPU_V6K || CPU_V7 || CPU_FEROCEON
 	default y
 	help
 	  Say Y if you want to include kernel support for running user space
@@ -644,7 +652,7 @@ config ARM_THUMBEE
 
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
-	depends on !CPU_USE_DOMAINS && CPU_V7 && !CPU_V6
+	depends on !CPU_USE_DOMAINS && CPU_V7
 	select HAVE_PROC_CPU if PROC_FS
 	default y if SMP
 	help
@@ -681,7 +689,7 @@ config CPU_BIG_ENDIAN
 config CPU_ENDIAN_BE8
 	bool
 	depends on CPU_BIG_ENDIAN
-	default CPU_V6 || CPU_V7
+	default CPU_V6 || CPU_V6K || CPU_V7
 	help
 	  Support for the BE-8 (big-endian) mode on ARMv6 and ARMv7 processors.
 
@@ -747,7 +755,7 @@ config CPU_CACHE_ROUND_ROBIN
 
 config CPU_BPREDICT_DISABLE
 	bool "Disable branch prediction"
-	depends on CPU_ARM1020 || CPU_V6 || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526
+	depends on CPU_ARM1020 || CPU_V6 || CPU_V6K || CPU_MOHAWK || CPU_XSC3 || CPU_V7 || CPU_FA526
 	help
 	  Say Y here to disable branch prediction.  If unsure, say N.
 
@@ -767,7 +775,7 @@ config NEEDS_SYSCALL_FOR_CMPXCHG
 
 config DMA_CACHE_RWFO
 	bool "Enable read/write for ownership DMA cache maintenance"
-	depends on CPU_V6 && SMP
+	depends on CPU_V6K && SMP
 	default y
 	help
 	  The Snoop Control Unit on ARM11MPCore does not detect the
@@ -823,7 +831,7 @@ config CACHE_L2X0
 config CACHE_PL310
 	bool
 	depends on CACHE_L2X0
-	default y if CPU_V7 && !CPU_V6
+	default y if CPU_V7 && !(CPU_V6 || CPU_V6K)
 	help
 	  This option enables optimisations for the PL310 cache
 	  controller.
@@ -856,10 +864,10 @@ config ARM_L1_CACHE_SHIFT
 	default 5
 
 config ARM_DMA_MEM_BUFFERABLE
-	bool "Use non-cacheable memory for DMA" if CPU_V6 && !CPU_V7
+	bool "Use non-cacheable memory for DMA" if (CPU_V6 || CPU_V6K) && !CPU_V7
 	depends on !(MACH_REALVIEW_PB1176 || REALVIEW_EB_ARM11MP || \
 		     MACH_REALVIEW_PB11MP)
-	default y if CPU_V6 || CPU_V7
+	default y if CPU_V6 || CPU_V6K || CPU_V7
 	help
 	  Historically, the kernel has used strongly ordered mappings to
 	  provide DMA coherent memory.  With the advent of ARMv7, mapping
diff --git a/arch/arm/mm/Makefile b/arch/arm/mm/Makefile
index 00d74a04af3..bca7e61928c 100644
--- a/arch/arm/mm/Makefile
+++ b/arch/arm/mm/Makefile
@@ -90,6 +90,7 @@ obj-$(CONFIG_CPU_XSC3)		+= proc-xsc3.o
 obj-$(CONFIG_CPU_MOHAWK)	+= proc-mohawk.o
 obj-$(CONFIG_CPU_FEROCEON)	+= proc-feroceon.o
 obj-$(CONFIG_CPU_V6)		+= proc-v6.o
+obj-$(CONFIG_CPU_V6K)		+= proc-v6.o
 obj-$(CONFIG_CPU_V7)		+= proc-v7.o
 
 AFLAGS_proc-v6.o	:=-Wa,-march=armv6
diff --git a/arch/arm/mm/abort-ev6.S b/arch/arm/mm/abort-ev6.S
index f332df7f0d3..1478aa52214 100644
--- a/arch/arm/mm/abort-ev6.S
+++ b/arch/arm/mm/abort-ev6.S
@@ -20,11 +20,11 @@
  */
 	.align	5
 ENTRY(v6_early_abort)
-#ifdef CONFIG_CPU_32v6K
-	clrex
-#else
+#ifdef CONFIG_CPU_V6
 	sub	r1, sp, #4			@ Get unused stack location
 	strex	r0, r1, [r1]			@ Clear the exclusive monitor
+#elif defined(CONFIG_CPU_32v6K)
+	clrex
 #endif
 	mrc	p15, 0, r1, c5, c0, 0		@ get FSR
 	mrc	p15, 0, r0, c6, c0, 0		@ get FAR
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index b0a98305055..afe209e1e1f 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -31,7 +31,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr,
 	struct mm_struct *mm = current->mm;
 	struct vm_area_struct *vma;
 	unsigned long start_addr;
-#ifdef CONFIG_CPU_V6
+#if defined(CONFIG_CPU_V6) || defined(CONFIG_CPU_V6K)
 	unsigned int cache_type;
 	int do_align = 0, aliasing = 0;