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

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

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

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

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

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

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

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

29 files changed, 501 insertions, 151 deletions

diff --git a/arch/arm/include/asm/Kbuild b/arch/arm/include/asm/Kbuild
index 1a7024b4135..c38b58c8020 100644
--- a/arch/arm/include/asm/Kbuild
+++ b/arch/arm/include/asm/Kbuild
@@ -24,6 +24,7 @@ generic-y += sembuf.h
 generic-y += serial.h
 generic-y += shmbuf.h
 generic-y += siginfo.h
+generic-y += simd.h
 generic-y += sizes.h
 generic-y += socket.h
 generic-y += sockios.h
diff --git a/arch/arm/include/asm/assembler.h b/arch/arm/include/asm/assembler.h
index fcc1b5bf697..5c228516057 100644
--- a/arch/arm/include/asm/assembler.h
+++ b/arch/arm/include/asm/assembler.h
@@ -53,6 +53,13 @@
 #define put_byte_3      lsl #0
 #endif
 
+/* Select code for any configuration running in BE8 mode */
+#ifdef CONFIG_CPU_ENDIAN_BE8
+#define ARM_BE8(code...) code
+#else
+#define ARM_BE8(code...)
+#endif
+
 /*
  * Data preload for architectures that support it
  */
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index da1c77d3932..62d2cb53b06 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -12,6 +12,7 @@
 #define __ASM_ARM_ATOMIC_H
 
 #include <linux/compiler.h>
+#include <linux/prefetch.h>
 #include <linux/types.h>
 #include <linux/irqflags.h>
 #include <asm/barrier.h>
@@ -41,6 +42,7 @@ static inline void atomic_add(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic_add\n"
 "1:	ldrex	%0, [%3]\n"
 "	add	%0, %0, %4\n"
@@ -79,6 +81,7 @@ static inline void atomic_sub(int i, atomic_t *v)
 	unsigned long tmp;
 	int result;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic_sub\n"
 "1:	ldrex	%0, [%3]\n"
 "	sub	%0, %0, %4\n"
@@ -114,7 +117,8 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 
 static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 {
-	unsigned long oldval, res;
+	int oldval;
+	unsigned long res;
 
 	smp_mb();
 
@@ -134,21 +138,6 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	return oldval;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned long tmp, tmp2;
-
-	__asm__ __volatile__("@ atomic_clear_mask\n"
-"1:	ldrex	%0, [%3]\n"
-"	bic	%0, %0, %4\n"
-"	strex	%1, %0, [%3]\n"
-"	teq	%1, #0\n"
-"	bne	1b"
-	: "=&r" (tmp), "=&r" (tmp2), "+Qo" (*addr)
-	: "r" (addr), "Ir" (mask)
-	: "cc");
-}
-
 #else /* ARM_ARCH_6 */
 
 #ifdef CONFIG_SMP
@@ -197,15 +186,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-static inline void atomic_clear_mask(unsigned long mask, unsigned long *addr)
-{
-	unsigned long flags;
-
-	raw_local_irq_save(flags);
-	*addr &= ~mask;
-	raw_local_irq_restore(flags);
-}
-
 #endif /* __LINUX_ARM_ARCH__ */
 
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
@@ -238,15 +218,15 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 
 #ifndef CONFIG_GENERIC_ATOMIC64
 typedef struct {
-	u64 __aligned(8) counter;
+	long long counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i) { (i) }
 
 #ifdef CONFIG_ARM_LPAE
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
-	u64 result;
+	long long result;
 
 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrd	%0, %H0, [%1]"
@@ -257,7 +237,7 @@ static inline u64 atomic64_read(const atomic64_t *v)
 	return result;
 }
 
-static inline void atomic64_set(atomic64_t *v, u64 i)
+static inline void atomic64_set(atomic64_t *v, long long i)
 {
 	__asm__ __volatile__("@ atomic64_set\n"
 "	strd	%2, %H2, [%1]"
@@ -266,9 +246,9 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
 	);
 }
 #else
-static inline u64 atomic64_read(const atomic64_t *v)
+static inline long long atomic64_read(const atomic64_t *v)
 {
-	u64 result;
+	long long result;
 
 	__asm__ __volatile__("@ atomic64_read\n"
 "	ldrexd	%0, %H0, [%1]"
@@ -279,10 +259,11 @@ static inline u64 atomic64_read(const atomic64_t *v)
 	return result;
 }
 
-static inline void atomic64_set(atomic64_t *v, u64 i)
+static inline void atomic64_set(atomic64_t *v, long long i)
 {
-	u64 tmp;
+	long long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_set\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
 "	strexd	%0, %3, %H3, [%2]\n"
@@ -294,15 +275,16 @@ static inline void atomic64_set(atomic64_t *v, u64 i)
 }
 #endif
 
-static inline void atomic64_add(u64 i, atomic64_t *v)
+static inline void atomic64_add(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_add\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -311,17 +293,17 @@ static inline void atomic64_add(u64 i, atomic64_t *v)
 	: "cc");
 }
 
-static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
+static inline long long atomic64_add_return(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_add_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	adds	%0, %0, %4\n"
-"	adc	%H0, %H0, %H4\n"
+"	adds	%Q0, %Q0, %Q4\n"
+"	adc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -334,15 +316,16 @@ static inline u64 atomic64_add_return(u64 i, atomic64_t *v)
 	return result;
 }
 
-static inline void atomic64_sub(u64 i, atomic64_t *v)
+static inline void atomic64_sub(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
+	prefetchw(&v->counter);
 	__asm__ __volatile__("@ atomic64_sub\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -351,17 +334,17 @@ static inline void atomic64_sub(u64 i, atomic64_t *v)
 	: "cc");
 }
 
-static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
+static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_sub_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, %4\n"
-"	sbc	%H0, %H0, %H4\n"
+"	subs	%Q0, %Q0, %Q4\n"
+"	sbc	%R0, %R0, %R4\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
 "	bne	1b"
@@ -374,9 +357,10 @@ static inline u64 atomic64_sub_return(u64 i, atomic64_t *v)
 	return result;
 }
 
-static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
+static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
+					long long new)
 {
-	u64 oldval;
+	long long oldval;
 	unsigned long res;
 
 	smp_mb();
@@ -398,9 +382,9 @@ static inline u64 atomic64_cmpxchg(atomic64_t *ptr, u64 old, u64 new)
 	return oldval;
 }
 
-static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
+static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
@@ -419,18 +403,18 @@ static inline u64 atomic64_xchg(atomic64_t *ptr, u64 new)
 	return result;
 }
 
-static inline u64 atomic64_dec_if_positive(atomic64_t *v)
+static inline long long atomic64_dec_if_positive(atomic64_t *v)
 {
-	u64 result;
+	long long result;
 	unsigned long tmp;
 
 	smp_mb();
 
 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
-"	subs	%0, %0, #1\n"
-"	sbc	%H0, %H0, #0\n"
-"	teq	%H0, #0\n"
+"	subs	%Q0, %Q0, #1\n"
+"	sbc	%R0, %R0, #0\n"
+"	teq	%R0, #0\n"
 "	bmi	2f\n"
 "	strexd	%1, %0, %H0, [%3]\n"
 "	teq	%1, #0\n"
@@ -445,9 +429,9 @@ static inline u64 atomic64_dec_if_positive(atomic64_t *v)
 	return result;
 }
 
-static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
+static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 {
-	u64 val;
+	long long val;
 	unsigned long tmp;
 	int ret = 1;
 
@@ -459,8 +443,8 @@ static inline int atomic64_add_unless(atomic64_t *v, u64 a, u64 u)
 "	teqeq	%H0, %H5\n"
 "	moveq	%1, #0\n"
 "	beq	2f\n"
-"	adds	%0, %0, %6\n"
-"	adc	%H0, %H0, %H6\n"
+"	adds	%Q0, %Q0, %Q6\n"
+"	adc	%R0, %R0, %R6\n"
 "	strexd	%2, %0, %H0, [%4]\n"
 "	teq	%2, #0\n"
 "	bne	1b\n"
diff --git a/arch/arm/include/asm/bL_switcher.h b/arch/arm/include/asm/bL_switcher.h
new file mode 100644
index 00000000000..1714800fa11
--- /dev/null
+++ b/arch/arm/include/asm/bL_switcher.h
@@ -0,0 +1,77 @@
+/*
+ * arch/arm/include/asm/bL_switcher.h
+ *
+ * Created by:  Nicolas Pitre, April 2012
+ * Copyright:   (C) 2012-2013  Linaro Limited
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#ifndef ASM_BL_SWITCHER_H
+#define ASM_BL_SWITCHER_H
+
+#include <linux/compiler.h>
+#include <linux/types.h>
+
+typedef void (*bL_switch_completion_handler)(void *cookie);
+
+int bL_switch_request_cb(unsigned int cpu, unsigned int new_cluster_id,
+			 bL_switch_completion_handler completer,
+			 void *completer_cookie);
+static inline int bL_switch_request(unsigned int cpu, unsigned int new_cluster_id)
+{
+	return bL_switch_request_cb(cpu, new_cluster_id, NULL, NULL);
+}
+
+/*
+ * Register here to be notified about runtime enabling/disabling of
+ * the switcher.
+ *
+ * The notifier chain is called with the switcher activation lock held:
+ * the switcher will not be enabled or disabled during callbacks.
+ * Callbacks must not call bL_switcher_{get,put}_enabled().
+ */
+#define BL_NOTIFY_PRE_ENABLE	0
+#define BL_NOTIFY_POST_ENABLE	1
+#define BL_NOTIFY_PRE_DISABLE	2
+#define BL_NOTIFY_POST_DISABLE	3
+
+#ifdef CONFIG_BL_SWITCHER
+
+int bL_switcher_register_notifier(struct notifier_block *nb);
+int bL_switcher_unregister_notifier(struct notifier_block *nb);
+
+/*
+ * Use these functions to temporarily prevent enabling/disabling of
+ * the switcher.
+ * bL_switcher_get_enabled() returns true if the switcher is currently
+ * enabled.  Each call to bL_switcher_get_enabled() must be followed
+ * by a call to bL_switcher_put_enabled().  These functions are not
+ * recursive.
+ */
+bool bL_switcher_get_enabled(void);
+void bL_switcher_put_enabled(void);
+
+int bL_switcher_trace_trigger(void);
+int bL_switcher_get_logical_index(u32 mpidr);
+
+#else
+static inline int bL_switcher_register_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline int bL_switcher_unregister_notifier(struct notifier_block *nb)
+{
+	return 0;
+}
+
+static inline bool bL_switcher_get_enabled(void) { return false; }
+static inline void bL_switcher_put_enabled(void) { }
+static inline int bL_switcher_trace_trigger(void) { return 0; }
+static inline int bL_switcher_get_logical_index(u32 mpidr) { return -EUNATCH; }
+#endif /* CONFIG_BL_SWITCHER */
+
+#endif
diff --git a/arch/arm/include/asm/bug.h b/arch/arm/include/asm/bug.h
index 7af5c6c3653..b274bde2490 100644
--- a/arch/arm/include/asm/bug.h
+++ b/arch/arm/include/asm/bug.h
@@ -2,6 +2,8 @@
 #define _ASMARM_BUG_H
 
 #include <linux/linkage.h>
+#include <linux/types.h>
+#include <asm/opcodes.h>
 
 #ifdef CONFIG_BUG
 
@@ -12,10 +14,10 @@
  */
 #ifdef CONFIG_THUMB2_KERNEL
 #define BUG_INSTR_VALUE 0xde02
-#define BUG_INSTR_TYPE ".hword "
+#define BUG_INSTR(__value) __inst_thumb16(__value)
 #else
 #define BUG_INSTR_VALUE 0xe7f001f2
-#define BUG_INSTR_TYPE ".word "
+#define BUG_INSTR(__value) __inst_arm(__value)
 #endif
 
 
@@ -33,7 +35,7 @@
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	asm volatile("1:\t" BUG_INSTR_TYPE #__value "\n"	\
+	asm volatile("1:\t" BUG_INSTR(__value) "\n"  \
 		".pushsection .rodata.str, \"aMS\", %progbits, 1\n" \
 		"2:\t.asciz " #__file "\n" 			\
 		".popsection\n" 				\
@@ -48,7 +50,7 @@ do {								\
 
 #define __BUG(__file, __line, __value)				\
 do {								\
-	asm volatile(BUG_INSTR_TYPE #__value);			\
+	asm volatile(BUG_INSTR(__value) "\n");			\
 	unreachable();						\
 } while (0)
 #endif  /* CONFIG_DEBUG_BUGVERBOSE */
diff --git a/arch/arm/include/asm/cacheflush.h b/arch/arm/include/asm/cacheflush.h
index 15f2d5bf887..ee753f1749c 100644
--- a/arch/arm/include/asm/cacheflush.h
+++ b/arch/arm/include/asm/cacheflush.h
@@ -435,4 +435,50 @@ static inline void __sync_cache_range_r(volatile void *p, size_t size)
 #define sync_cache_w(ptr) __sync_cache_range_w(ptr, sizeof *(ptr))
 #define sync_cache_r(ptr) __sync_cache_range_r(ptr, sizeof *(ptr))
 
+/*
+ * Disabling cache access for one CPU in an ARMv7 SMP system is tricky.
+ * To do so we must:
+ *
+ * - Clear the SCTLR.C bit to prevent further cache allocations
+ * - Flush the desired level of cache
+ * - Clear the ACTLR "SMP" bit to disable local coherency
+ *
+ * ... and so without any intervening memory access in between those steps,
+ * not even to the stack.
+ *
+ * WARNING -- After this has been called:
+ *
+ * - No ldrex/strex (and similar) instructions must be used.
+ * - The CPU is obviously no longer coherent with the other CPUs.
+ * - This is unlikely to work as expected if Linux is running non-secure.
+ *
+ * Note:
+ *
+ * - This is known to apply to several ARMv7 processor implementations,
+ *   however some exceptions may exist.  Caveat emptor.
+ *
+ * - The clobber list is dictated by the call to v7_flush_dcache_*.
+ *   fp is preserved to the stack explicitly prior disabling the cache
+ *   since adding it to the clobber list is incompatible with having
+ *   CONFIG_FRAME_POINTER=y.  ip is saved as well if ever r12-clobbering
+ *   trampoline are inserted by the linker and to keep sp 64-bit aligned.
+ */
+#define v7_exit_coherency_flush(level) \
+	asm volatile( \
+	"stmfd	sp!, {fp, ip} \n\t" \
+	"mrc	p15, 0, r0, c1, c0, 0	@ get SCTLR \n\t" \
+	"bic	r0, r0, #"__stringify(CR_C)" \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 0	@ set SCTLR \n\t" \
+	"isb	\n\t" \
+	"bl	v7_flush_dcache_"__stringify(level)" \n\t" \
+	"clrex	\n\t" \
+	"mrc	p15, 0, r0, c1, c0, 1	@ get ACTLR \n\t" \
+	"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t" \
+	"mcr	p15, 0, r0, c1, c0, 1	@ set ACTLR \n\t" \
+	"isb	\n\t" \
+	"dsb	\n\t" \
+	"ldmfd	sp!, {fp, ip}" \
+	: : : "r0","r1","r2","r3","r4","r5","r6","r7", \
+	      "r9","r10","lr","memory" )
+
 #endif
diff --git a/arch/arm/include/asm/cmpxchg.h b/arch/arm/include/asm/cmpxchg.h
index 4f009c10540..df2fbba7efc 100644
--- a/arch/arm/include/asm/cmpxchg.h
+++ b/arch/arm/include/asm/cmpxchg.h
@@ -223,6 +223,42 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 	return ret;
 }
 
+static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
+					     unsigned long long old,
+					     unsigned long long new)
+{
+	unsigned long long oldval;
+	unsigned long res;
+
+	__asm__ __volatile__(
+"1:	ldrexd		%1, %H1, [%3]\n"
+"	teq		%1, %4\n"
+"	teqeq		%H1, %H4\n"
+"	bne		2f\n"
+"	strexd		%0, %5, %H5, [%3]\n"
+"	teq		%0, #0\n"
+"	bne		1b\n"
+"2:"
+	: "=&r" (res), "=&r" (oldval), "+Qo" (*ptr)
+	: "r" (ptr), "r" (old), "r" (new)
+	: "cc");
+
+	return oldval;
+}
+
+static inline unsigned long long __cmpxchg64_mb(unsigned long long *ptr,
+						unsigned long long old,
+						unsigned long long new)
+{
+	unsigned long long ret;
+
+	smp_mb();
+	ret = __cmpxchg64(ptr, old, new);
+	smp_mb();
+
+	return ret;
+}
+
 #define cmpxchg_local(ptr,o,n)						\
 	((__typeof__(*(ptr)))__cmpxchg_local((ptr),			\
 				       (unsigned long)(o),		\
@@ -230,18 +266,16 @@ static inline unsigned long __cmpxchg_local(volatile void *ptr,
 				       sizeof(*(ptr))))
 
 #define cmpxchg64(ptr, o, n)						\
-	((__typeof__(*(ptr)))atomic64_cmpxchg(container_of((ptr),	\
-						atomic64_t,		\
-						counter),		\
-					      (unsigned long long)(o),	\
-					      (unsigned long long)(n)))
-
-#define cmpxchg64_local(ptr, o, n)					\
-	((__typeof__(*(ptr)))local64_cmpxchg(container_of((ptr),	\
-						local64_t,		\
-						a),			\
-					     (unsigned long long)(o),	\
-					     (unsigned long long)(n)))
+	((__typeof__(*(ptr)))__cmpxchg64_mb((ptr),			\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n)))
+
+#define cmpxchg64_relaxed(ptr, o, n)					\
+	((__typeof__(*(ptr)))__cmpxchg64((ptr),				\
+					(unsigned long long)(o),	\
+					(unsigned long long)(n)))
+
+#define cmpxchg64_local(ptr, o, n)	cmpxchg64_relaxed((ptr), (o), (n))
 
 #endif	/* __LINUX_ARM_ARCH__ >= 6 */
 
diff --git a/arch/arm/include/asm/cputype.h b/arch/arm/include/asm/cputype.h
index 9672e978d50..acdde76b39b 100644
--- a/arch/arm/include/asm/cputype.h
+++ b/arch/arm/include/asm/cputype.h
@@ -10,6 +10,7 @@
 #define CPUID_TLBTYPE	3
 #define CPUID_MPUIR	4
 #define CPUID_MPIDR	5
+#define CPUID_REVIDR	6
 
 #ifdef CONFIG_CPU_V7M
 #define CPUID_EXT_PFR0	0x40
diff --git a/arch/arm/include/asm/hardirq.h b/arch/arm/include/asm/hardirq.h
index 2740c2a2df6..fe3ea776dc3 100644
--- a/arch/arm/include/asm/hardirq.h
+++ b/arch/arm/include/asm/hardirq.h
@@ -5,7 +5,7 @@
 #include <linux/threads.h>
 #include <asm/irq.h>
 
-#define NR_IPI	6
+#define NR_IPI	8
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/hardware/coresight.h b/arch/arm/include/asm/hardware/coresight.h
index 0cf7a6b842f..ad774f37c47 100644
--- a/arch/arm/include/asm/hardware/coresight.h
+++ b/arch/arm/include/asm/hardware/coresight.h
@@ -24,8 +24,8 @@
 #define TRACER_TIMEOUT 10000
 
 #define etm_writel(t, v, x) \
-	(__raw_writel((v), (t)->etm_regs + (x)))
-#define etm_readl(t, x) (__raw_readl((t)->etm_regs + (x)))
+	(writel_relaxed((v), (t)->etm_regs + (x)))
+#define etm_readl(t, x) (readl_relaxed((t)->etm_regs + (x)))
 
 /* CoreSight Management Registers */
 #define CSMR_LOCKACCESS 0xfb0
@@ -142,8 +142,8 @@
 #define ETBFF_TRIGFL		BIT(10)
 
 #define etb_writel(t, v, x) \
-	(__raw_writel((v), (t)->etb_regs + (x)))
-#define etb_readl(t, x) (__raw_readl((t)->etb_regs + (x)))
+	(writel_relaxed((v), (t)->etb_regs + (x)))
+#define etb_readl(t, x) (readl_relaxed((t)->etb_regs + (x)))
 
 #define etm_lock(t) do { etm_writel((t), 0, CSMR_LOCKACCESS); } while (0)
 #define etm_unlock(t) \
diff --git a/arch/arm/include/asm/kgdb.h b/arch/arm/include/asm/kgdb.h
index 48066ce9ea3..0a9d5dd9329 100644
--- a/arch/arm/include/asm/kgdb.h
+++ b/arch/arm/include/asm/kgdb.h
@@ -11,6 +11,7 @@
 #define __ARM_KGDB_H__
 
 #include <linux/ptrace.h>
+#include <asm/opcodes.h>
 
 /*
  * GDB assumes that we're a user process being debugged, so
@@ -41,7 +42,7 @@
 
 static inline void arch_kgdb_breakpoint(void)
 {
-	asm(".word 0xe7ffdeff");
+	asm(__inst_arm(0xe7ffdeff));
 }
 
 extern void kgdb_handle_bus_error(void);
diff --git a/arch/arm/include/asm/mach/arch.h b/arch/arm/include/asm/mach/arch.h
index 402a2bc6aa6..17a3fa2979e 100644
--- a/arch/arm/include/asm/mach/arch.h
+++ b/arch/arm/include/asm/mach/arch.h
@@ -49,6 +49,7 @@ struct machine_desc {
 	bool			(*smp_init)(void);
 	void			(*fixup)(struct tag *, char **,
 					 struct meminfo *);
+	void			(*init_meminfo)(void);
 	void			(*reserve)(void);/* reserve mem blocks	*/
 	void			(*map_io)(void);/* IO mapping function	*/
 	void			(*init_early)(void);
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index fc82a88f5b6..608516ebabf 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -42,6 +42,14 @@ extern void mcpm_entry_point(void);
 void mcpm_set_entry_vector(unsigned cpu, unsigned cluster, void *ptr);
 
 /*
+ * This sets an early poke i.e a value to be poked into some address
+ * from very early assembly code before the CPU is ungated.  The
+ * address must be physical, and if 0 then nothing will happen.
+ */
+void mcpm_set_early_poke(unsigned cpu, unsigned cluster,
+			 unsigned long poke_phys_addr, unsigned long poke_val);
+
+/*
  * CPU/cluster power operations API for higher subsystems to use.
  */
 
@@ -81,10 +89,40 @@ int mcpm_cpu_power_up(unsigned int cpu, unsigned int cluster);
  *
  * This will return if mcpm_platform_register() has not been called
  * previously in which case the caller should take appropriate action.
+ *
+ * On success, the CPU is not guaranteed to be truly halted until
+ * mcpm_cpu_power_down_finish() subsequently returns non-zero for the
+ * specified cpu.  Until then, other CPUs should make sure they do not
+ * trash memory the target CPU might be executing/accessing.
  */
 void mcpm_cpu_power_down(void);
 
 /**
+ * mcpm_cpu_power_down_finish - wait for a specified CPU to halt, and
+ *	make sure it is powered off
+ *
+ * @cpu: CPU number within given cluster
+ * @cluster: cluster number for the CPU
+ *
+ * Call this function to ensure that a pending powerdown has taken
+ * effect and the CPU is safely parked before performing non-mcpm
+ * operations that may affect the CPU (such as kexec trashing the
+ * kernel text).
+ *
+ * It is *not* necessary to call this function if you only need to
+ * serialise a pending powerdown with mcpm_cpu_power_up() or a wakeup
+ * event.
+ *
+ * Do not call this function unless the specified CPU has already
+ * called mcpm_cpu_power_down() or has committed to doing so.
+ *
+ * @return:
+ *	- zero if the CPU is in a safely parked state
+ *	- nonzero otherwise (e.g., timeout)
+ */
+int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster);
+
+/**
  * mcpm_cpu_suspend - bring the calling CPU in a suspended state
  *
  * @expected_residency: duration in microseconds the CPU is expected
@@ -126,6 +164,7 @@ int mcpm_cpu_powered_up(void);
 struct mcpm_platform_ops {
 	int (*power_up)(unsigned int cpu, unsigned int cluster);
 	void (*power_down)(void);
+	int (*power_down_finish)(unsigned int cpu, unsigned int cluster);
 	void (*suspend)(u64);
 	void (*powered_up)(void);
 };
diff --git a/arch/arm/include/asm/memory.h b/arch/arm/include/asm/memory.h
index e750a938fd3..4dd21457ef9 100644
--- a/arch/arm/include/asm/memory.h
+++ b/arch/arm/include/asm/memory.h
@@ -172,8 +172,13 @@
  * so that all we need to do is modify the 8-bit constant field.
  */
 #define __PV_BITS_31_24	0x81000000
+#define __PV_BITS_7_0	0x81
+
+extern u64 __pv_phys_offset;
+extern u64 __pv_offset;
+extern void fixup_pv_table(const void *, unsigned long);
+extern const void *__pv_table_begin, *__pv_table_end;
 
-extern unsigned long __pv_phys_offset;
 #define PHYS_OFFSET __pv_phys_offset
 
 #define __pv_stub(from,to,instr,type)			\
@@ -185,22 +190,58 @@ extern unsigned long __pv_phys_offset;
 	: "=r" (to)					\
 	: "r" (from), "I" (type))
 
-static inline unsigned long __virt_to_phys(unsigned long x)
+#define __pv_stub_mov_hi(t)				\
+	__asm__ volatile("@ __pv_stub_mov\n"		\
+	"1:	mov	%R0, %1\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	1b\n"				\
+	"	.popsection\n"				\
+	: "=r" (t)					\
+	: "I" (__PV_BITS_7_0))
+
+#define __pv_add_carry_stub(x, y)			\
+	__asm__ volatile("@ __pv_add_carry_stub\n"	\
+	"1:	adds	%Q0, %1, %2\n"			\
+	"	adc	%R0, %R0, #0\n"			\
+	"	.pushsection .pv_table,\"a\"\n"		\
+	"	.long	1b\n"				\
+	"	.popsection\n"				\
+	: "+r" (y)					\
+	: "r" (x), "I" (__PV_BITS_31_24)		\
+	: "cc")
+
+static inline phys_addr_t __virt_to_phys(unsigned long x)
 {
-	unsigned long t;
-	__pv_stub(x, t, "add", __PV_BITS_31_24);
+	phys_addr_t t;
+
+	if (sizeof(phys_addr_t) == 4) {
+		__pv_stub(x, t, "add", __PV_BITS_31_24);
+	} else {
+		__pv_stub_mov_hi(t);
+		__pv_add_carry_stub(x, t);
+	}
 	return t;
 }
 
-static inline unsigned long __phys_to_virt(unsigned long x)
+static inline unsigned long __phys_to_virt(phys_addr_t x)
 {
 	unsigned long t;
 	__pv_stub(x, t, "sub", __PV_BITS_31_24);
 	return t;
 }
+
 #else
-#define __virt_to_phys(x)	((x) - PAGE_OFFSET + PHYS_OFFSET)
-#define __phys_to_virt(x)	((x) - PHYS_OFFSET + PAGE_OFFSET)
+
+static inline phys_addr_t __virt_to_phys(unsigned long x)
+{
+	return (phys_addr_t)x - PAGE_OFFSET + PHYS_OFFSET;
+}
+
+static inline unsigned long __phys_to_virt(phys_addr_t x)
+{
+	return x - PHYS_OFFSET + PAGE_OFFSET;
+}
+
 #endif
 #endif
 #endif /* __ASSEMBLY__ */
@@ -238,16 +279,33 @@ static inline phys_addr_t virt_to_phys(const volatile void *x)
 
 static inline void *phys_to_virt(phys_addr_t x)
 {
-	return (void *)(__phys_to_virt((unsigned long)(x)));
+	return (void *)__phys_to_virt(x);
 }
 
 /*
  * Drivers should NOT use these either.
  */
 #define __pa(x)			__virt_to_phys((unsigned long)(x))
-#define __va(x)			((void *)__phys_to_virt((unsigned long)(x)))
+#define __va(x)			((void *)__phys_to_virt((phys_addr_t)(x)))
 #define pfn_to_kaddr(pfn)	__va((pfn) << PAGE_SHIFT)
 
+extern phys_addr_t (*arch_virt_to_idmap)(unsigned long x);
+
+/*
+ * These are for systems that have a hardware interconnect supported alias of
+ * physical memory for idmap purposes.  Most cases should leave these
+ * untouched.
+ */
+static inline phys_addr_t __virt_to_idmap(unsigned long x)
+{
+	if (arch_virt_to_idmap)
+		return arch_virt_to_idmap(x);
+	else
+		return __virt_to_phys(x);
+}
+
+#define virt_to_idmap(x)	__virt_to_idmap((unsigned long)(x))
+
 /*
  * Virtual <-> DMA view memory address translations
  * Again, these are *only* valid on the kernel direct mapped RAM
diff --git a/arch/arm/include/asm/mmu.h b/arch/arm/include/asm/mmu.h
index 6f18da09668..64fd15159b7 100644
--- a/arch/arm/include/asm/mmu.h
+++ b/arch/arm/include/asm/mmu.h
@@ -16,7 +16,7 @@ typedef struct {
 #ifdef CONFIG_CPU_HAS_ASID
 #define ASID_BITS	8
 #define ASID_MASK	((~0ULL) << ASID_BITS)
-#define ASID(mm)	((mm)->context.id.counter & ~ASID_MASK)
+#define ASID(mm)	((unsigned int)((mm)->context.id.counter & ~ASID_MASK))
 #else
 #define ASID(mm)	(0)
 #endif
diff --git a/arch/arm/include/asm/pgtable-2level.h b/arch/arm/include/asm/pgtable-2level.h
index f97ee02386e..86a659a1952 100644
--- a/arch/arm/include/asm/pgtable-2level.h
+++ b/arch/arm/include/asm/pgtable-2level.h
@@ -181,6 +181,13 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 
 #define set_pte_ext(ptep,pte,ext) cpu_set_pte_ext(ptep,pte,ext)
 
+/*
+ * We don't have huge page support for short descriptors, for the moment
+ * define empty stubs for use by pin_page_for_write.
+ */
+#define pmd_hugewillfault(pmd)	(0)
+#define pmd_thp_or_huge(pmd)	(0)
+
 #endif /* __ASSEMBLY__ */
 
 #endif /* _ASM_PGTABLE_2LEVEL_H */
diff --git a/arch/arm/include/asm/pgtable-3level.h b/arch/arm/include/asm/pgtable-3level.h
index 5689c18c85f..39c54cfa03e 100644
--- a/arch/arm/include/asm/pgtable-3level.h
+++ b/arch/arm/include/asm/pgtable-3level.h
@@ -206,6 +206,9 @@ static inline pmd_t *pmd_offset(pud_t *pud, unsigned long addr)
 #define __HAVE_ARCH_PMD_WRITE
 #define pmd_write(pmd)		(!(pmd_val(pmd) & PMD_SECT_RDONLY))
 
+#define pmd_hugewillfault(pmd)	(!pmd_young(pmd) || !pmd_write(pmd))
+#define pmd_thp_or_huge(pmd)	(pmd_huge(pmd) || pmd_trans_huge(pmd))
+
 #ifdef CONFIG_TRANSPARENT_HUGEPAGE
 #define pmd_trans_huge(pmd)	(pmd_val(pmd) && !(pmd_val(pmd) & PMD_TABLE_BIT))
 #define pmd_trans_splitting(pmd) (pmd_val(pmd) & PMD_SECT_SPLITTING)
diff --git a/arch/arm/include/asm/processor.h b/arch/arm/include/asm/processor.h
index 413f3876341..c3d5fc124a0 100644
--- a/arch/arm/include/asm/processor.h
+++ b/arch/arm/include/asm/processor.h
@@ -22,6 +22,7 @@
 #include <asm/hw_breakpoint.h>
 #include <asm/ptrace.h>
 #include <asm/types.h>
+#include <asm/unified.h>
 
 #ifdef __KERNEL__
 #define STACK_TOP	((current->personality & ADDR_LIMIT_32BIT) ? \
@@ -87,6 +88,17 @@ unsigned long get_wchan(struct task_struct *p);
 #define KSTK_EIP(tsk)	task_pt_regs(tsk)->ARM_pc
 #define KSTK_ESP(tsk)	task_pt_regs(tsk)->ARM_sp
 
+#ifdef CONFIG_SMP
+#define __ALT_SMP_ASM(smp, up)						\
+	"9998:	" smp "\n"						\
+	"	.pushsection \".alt.smp.init\", \"a\"\n"		\
+	"	.long	9998b\n"					\
+	"	" up "\n"						\
+	"	.popsection\n"
+#else
+#define __ALT_SMP_ASM(smp, up)	up
+#endif
+
 /*
  * Prefetching support - only ARMv5.
  */
@@ -97,17 +109,22 @@ static inline void prefetch(const void *ptr)
 {
 	__asm__ __volatile__(
 		"pld\t%a0"
-		:
-		: "p" (ptr)
-		: "cc");
+		:: "p" (ptr));
 }
 
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
 #define ARCH_HAS_PREFETCHW
-#define prefetchw(ptr)	prefetch(ptr)
-
-#define ARCH_HAS_SPINLOCK_PREFETCH
-#define spin_lock_prefetch(x) do { } while (0)
-
+static inline void prefetchw(const void *ptr)
+{
+	__asm__ __volatile__(
+		".arch_extension	mp\n"
+		__ALT_SMP_ASM(
+			WASM(pldw)		"\t%a0",
+			WASM(pld)		"\t%a0"
+		)
+		:: "p" (ptr));
+}
+#endif
 #endif
 
 #define HAVE_ARCH_PICK_MMAP_LAYOUT
diff --git a/arch/arm/include/asm/setup.h b/arch/arm/include/asm/setup.h
index c50f0560950..8d6a089dfb7 100644
--- a/arch/arm/include/asm/setup.h
+++ b/arch/arm/include/asm/setup.h
@@ -49,7 +49,7 @@ extern struct meminfo meminfo;
 #define bank_phys_end(bank)	((bank)->start + (bank)->size)
 #define bank_phys_size(bank)	(bank)->size
 
-extern int arm_add_memory(phys_addr_t start, phys_addr_t size);
+extern int arm_add_memory(u64 start, u64 size);
 extern void early_print(const char *str, ...);
 extern void dump_machine_table(void);
 
diff --git a/arch/arm/include/asm/smp.h b/arch/arm/include/asm/smp.h
index a8cae71cace..22a3b9b5d4a 100644
--- a/arch/arm/include/asm/smp.h
+++ b/arch/arm/include/asm/smp.h
@@ -84,6 +84,8 @@ extern void arch_send_call_function_single_ipi(int cpu);
 extern void arch_send_call_function_ipi_mask(const struct cpumask *mask);
 extern void arch_send_wakeup_ipi_mask(const struct cpumask *mask);
 
+extern int register_ipi_completion(struct completion *completion, int cpu);
+
 struct smp_operations {
 #ifdef CONFIG_SMP
 	/*
diff --git a/arch/arm/include/asm/spinlock.h b/arch/arm/include/asm/spinlock.h
index 4f2c28060c9..ef3c6072aa4 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -5,21 +5,13 @@
 #error SMP not supported on pre-ARMv6 CPUs
 #endif
 
-#include <asm/processor.h>
+#include <linux/prefetch.h>
 
 /*
  * 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
@@ -31,17 +23,18 @@
  * the assembler won't change IT instructions which are explicitly present
  * in the input.
  */
-#define WFE(cond)	ALT_SMP(		\
+#define WFE(cond)	__ALT_SMP_ASM(		\
 	"it " cond "\n\t"			\
 	"wfe" cond ".n",			\
 						\
 	"nop.w"					\
 )
 #else
-#define SEV		ALT_SMP("sev", "nop")
-#define WFE(cond)	ALT_SMP("wfe" cond, "nop")
+#define WFE(cond)	__ALT_SMP_ASM("wfe" cond, "nop")
 #endif
 
+#define SEV		__ALT_SMP_ASM(WASM(sev), WASM(nop))
+
 static inline void dsb_sev(void)
 {
 #if __LINUX_ARM_ARCH__ >= 7
@@ -77,6 +70,7 @@ static inline void arch_spin_lock(arch_spinlock_t *lock)
 	u32 newval;
 	arch_spinlock_t lockval;
 
+	prefetchw(&lock->slock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%3]\n"
 "	add	%1, %0, %4\n"
@@ -100,6 +94,7 @@ static inline int arch_spin_trylock(arch_spinlock_t *lock)
 	unsigned long contended, res;
 	u32 slock;
 
+	prefetchw(&lock->slock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%3]\n"
@@ -127,10 +122,14 @@ static inline void arch_spin_unlock(arch_spinlock_t *lock)
 	dsb_sev();
 }
 
+static inline int arch_spin_value_unlocked(arch_spinlock_t lock)
+{
+	return lock.tickets.owner == lock.tickets.next;
+}
+
 static inline int arch_spin_is_locked(arch_spinlock_t *lock)
 {
-	struct __raw_tickets tickets = ACCESS_ONCE(lock->tickets);
-	return tickets.owner != tickets.next;
+	return !arch_spin_value_unlocked(ACCESS_ONCE(*lock));
 }
 
 static inline int arch_spin_is_contended(arch_spinlock_t *lock)
@@ -152,6 +151,7 @@ static inline void arch_write_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp;
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%1]\n"
 "	teq	%0, #0\n"
@@ -170,6 +170,7 @@ static inline int arch_write_trylock(arch_rwlock_t *rw)
 {
 	unsigned long contended, res;
 
+	prefetchw(&rw->lock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%2]\n"
@@ -203,7 +204,7 @@ static inline void arch_write_unlock(arch_rwlock_t *rw)
 }
 
 /* write_can_lock - would write_trylock() succeed? */
-#define arch_write_can_lock(x)		((x)->lock == 0)
+#define arch_write_can_lock(x)		(ACCESS_ONCE((x)->lock) == 0)
 
 /*
  * Read locks are a bit more hairy:
@@ -221,6 +222,7 @@ static inline void arch_read_lock(arch_rwlock_t *rw)
 {
 	unsigned long tmp, tmp2;
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%2]\n"
 "	adds	%0, %0, #1\n"
@@ -241,6 +243,7 @@ static inline void arch_read_unlock(arch_rwlock_t *rw)
 
 	smp_mb();
 
+	prefetchw(&rw->lock);
 	__asm__ __volatile__(
 "1:	ldrex	%0, [%2]\n"
 "	sub	%0, %0, #1\n"
@@ -259,6 +262,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 {
 	unsigned long contended, res;
 
+	prefetchw(&rw->lock);
 	do {
 		__asm__ __volatile__(
 		"	ldrex	%0, [%2]\n"
@@ -280,7 +284,7 @@ static inline int arch_read_trylock(arch_rwlock_t *rw)
 }
 
 /* read_can_lock - would read_trylock() succeed? */
-#define arch_read_can_lock(x)		((x)->lock < 0x80000000)
+#define arch_read_can_lock(x)		(ACCESS_ONCE((x)->lock) < 0x80000000)
 
 #define arch_read_lock_flags(lock, flags) arch_read_lock(lock)
 #define arch_write_lock_flags(lock, flags) arch_write_lock(lock)
diff --git a/arch/arm/include/asm/spinlock_types.h b/arch/arm/include/asm/spinlock_types.h
index b262d2f8b47..47663fcb10a 100644
--- a/arch/arm/include/asm/spinlock_types.h
+++ b/arch/arm/include/asm/spinlock_types.h
@@ -25,7 +25,7 @@ typedef struct {
 #define __ARCH_SPIN_LOCK_UNLOCKED	{ { 0 } }
 
 typedef struct {
-	volatile unsigned int lock;
+	u32 lock;
 } arch_rwlock_t;
 
 #define __ARCH_RW_LOCK_UNLOCKED		{ 0 }
diff --git a/arch/arm/include/asm/tlbflush.h b/arch/arm/include/asm/tlbflush.h
index 38960264040..def9e570199 100644
--- a/arch/arm/include/asm/tlbflush.h
+++ b/arch/arm/include/asm/tlbflush.h
@@ -560,37 +560,6 @@ static inline void __flush_bp_all(void)
 		asm("mcr p15, 0, %0, c7, c1, 6" : : "r" (zero));
 }
 
-#include <asm/cputype.h>
-#ifdef CONFIG_ARM_ERRATA_798181
-static inline int erratum_a15_798181(void)
-{
-	unsigned int midr = read_cpuid_id();
-
-	/* Cortex-A15 r0p0..r3p2 affected */
-	if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2)
-		return 0;
-	return 1;
-}
-
-static inline void dummy_flush_tlb_a15_erratum(void)
-{
-	/*
-	 * Dummy TLBIMVAIS. Using the unmapped address 0 and ASID 0.
-	 */
-	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
-	dsb(ish);
-}
-#else
-static inline int erratum_a15_798181(void)
-{
-	return 0;
-}
-
-static inline void dummy_flush_tlb_a15_erratum(void)
-{
-}
-#endif
-
 /*
  *	flush_pmd_entry
  *
@@ -697,4 +666,21 @@ extern void flush_bp_all(void);
 
 #endif
 
+#ifndef __ASSEMBLY__
+#ifdef CONFIG_ARM_ERRATA_798181
+extern void erratum_a15_798181_init(void);
+#else
+static inline void erratum_a15_798181_init(void) {}
+#endif
+extern bool (*erratum_a15_798181_handler)(void);
+
+static inline bool erratum_a15_798181(void)
+{
+	if (unlikely(IS_ENABLED(CONFIG_ARM_ERRATA_798181) &&
+		erratum_a15_798181_handler))
+		return erratum_a15_798181_handler();
+	return false;
+}
+#endif
+
 #endif
diff --git a/arch/arm/include/asm/unified.h b/arch/arm/include/asm/unified.h
index f5989f46b4d..b88beaba6b4 100644
--- a/arch/arm/include/asm/unified.h
+++ b/arch/arm/include/asm/unified.h
@@ -38,6 +38,8 @@
 #ifdef __ASSEMBLY__
 #define W(instr)	instr.w
 #define BSYM(sym)	sym + 1
+#else
+#define WASM(instr)	#instr ".w"
 #endif
 
 #else	/* !CONFIG_THUMB2_KERNEL */
@@ -50,6 +52,8 @@
 #ifdef __ASSEMBLY__
 #define W(instr)	instr
 #define BSYM(sym)	sym
+#else
+#define WASM(instr)	#instr
 #endif
 
 #endif	/* CONFIG_THUMB2_KERNEL */
diff --git a/arch/arm/include/debug/efm32.S b/arch/arm/include/debug/efm32.S
new file mode 100644
index 00000000000..2265a199280
--- /dev/null
+++ b/arch/arm/include/debug/efm32.S
@@ -0,0 +1,45 @@
+/*
+ * Copyright (C) 2013 Pengutronix
+ * Uwe Kleine-Koenig <u.kleine-koenig@pengutronix.de>
+ *
+ * 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.
+ */
+
+#define UARTn_CMD		0x000c
+#define UARTn_CMD_TXEN			0x0004
+
+#define	UARTn_STATUS		0x0010
+#define	UARTn_STATUS_TXC		0x0020
+#define	UARTn_STATUS_TXBL		0x0040
+
+#define	UARTn_TXDATA		0x0034
+
+		.macro	addruart, rx, tmp
+		ldr	\rx, =(CONFIG_DEBUG_UART_PHYS)
+
+		/*
+		 * enable TX. The driver might disable it to save energy. We
+		 * don't care about disabling at the end as during debug power
+		 * consumption isn't that important.
+		 */
+		ldr	\tmp, =(UARTn_CMD_TXEN)
+		str	\tmp, [\rx, #UARTn_CMD]
+		.endm
+
+		.macro	senduart,rd,rx
+		strb	\rd, [\rx, #UARTn_TXDATA]
+		.endm
+
+		.macro	waituart,rd,rx
+1001:		ldr	\rd, [\rx, #UARTn_STATUS]
+		tst	\rd, #UARTn_STATUS_TXBL
+		beq	1001b
+		.endm
+
+		.macro	busyuart,rd,rx
+1001:		ldr	\rd, [\rx, UARTn_STATUS]
+		tst	\rd, #UARTn_STATUS_TXC
+		bne	1001b
+		.endm
diff --git a/arch/arm/include/debug/msm.S b/arch/arm/include/debug/msm.S
index 9166e1bc470..9d653d47590 100644
--- a/arch/arm/include/debug/msm.S
+++ b/arch/arm/include/debug/msm.S
@@ -46,6 +46,11 @@
 #define MSM_DEBUG_UART_PHYS	0x16440000
 #endif
 
+#ifdef CONFIG_DEBUG_MSM8974_UART
+#define MSM_DEBUG_UART_BASE	0xFA71E000
+#define MSM_DEBUG_UART_PHYS	0xF991E000
+#endif
+
 	.macro	addruart, rp, rv, tmp
 #ifdef MSM_DEBUG_UART_PHYS
 	ldr	\rp, =MSM_DEBUG_UART_PHYS
diff --git a/arch/arm/include/debug/pl01x.S b/arch/arm/include/debug/pl01x.S
index 37c6895b87e..92ef808a233 100644
--- a/arch/arm/include/debug/pl01x.S
+++ b/arch/arm/include/debug/pl01x.S
@@ -25,12 +25,14 @@
 
 		.macro	waituart,rd,rx
 1001:		ldr	\rd, [\rx, #UART01x_FR]
+ ARM_BE8(	rev	\rd, \rd )
 		tst	\rd, #UART01x_FR_TXFF
 		bne	1001b
 		.endm
 
 		.macro	busyuart,rd,rx
 1001:		ldr	\rd, [\rx, #UART01x_FR]
+ ARM_BE8(	rev	\rd, \rd )
 		tst	\rd, #UART01x_FR_BUSY
 		bne	1001b
 		.endm
diff --git a/arch/arm/include/uapi/asm/Kbuild b/arch/arm/include/uapi/asm/Kbuild
index 18d76fd5a2a..70a1c9da30c 100644
--- a/arch/arm/include/uapi/asm/Kbuild
+++ b/arch/arm/include/uapi/asm/Kbuild
@@ -7,6 +7,7 @@ header-y += hwcap.h
 header-y += ioctls.h
 header-y += kvm_para.h
 header-y += mman.h
+header-y += perf_regs.h
 header-y += posix_types.h
 header-y += ptrace.h
 header-y += setup.h
diff --git a/arch/arm/include/uapi/asm/perf_regs.h b/arch/arm/include/uapi/asm/perf_regs.h
new file mode 100644
index 00000000000..ce59448458b
--- /dev/null
+++ b/arch/arm/include/uapi/asm/perf_regs.h
@@ -0,0 +1,23 @@
+#ifndef _ASM_ARM_PERF_REGS_H
+#define _ASM_ARM_PERF_REGS_H
+
+enum perf_event_arm_regs {
+	PERF_REG_ARM_R0,
+	PERF_REG_ARM_R1,
+	PERF_REG_ARM_R2,
+	PERF_REG_ARM_R3,
+	PERF_REG_ARM_R4,
+	PERF_REG_ARM_R5,
+	PERF_REG_ARM_R6,
+	PERF_REG_ARM_R7,
+	PERF_REG_ARM_R8,
+	PERF_REG_ARM_R9,
+	PERF_REG_ARM_R10,
+	PERF_REG_ARM_FP,
+	PERF_REG_ARM_IP,
+	PERF_REG_ARM_SP,
+	PERF_REG_ARM_LR,
+	PERF_REG_ARM_PC,
+	PERF_REG_ARM_MAX,
+};
+#endif /* _ASM_ARM_PERF_REGS_H */