Merge branch 'misc' into for-next

34 files changed, 466 insertions, 278 deletions

diff --git a/arch/arm/Kconfig b/arch/arm/Kconfig
index 1ad6fb6c094..df0c609272e 100644
--- a/arch/arm/Kconfig
+++ b/arch/arm/Kconfig
@@ -5,6 +5,7 @@ config ARM
 	select ARCH_HAS_ATOMIC64_DEC_IF_POSITIVE
 	select ARCH_HAS_TICK_BROADCAST if GENERIC_CLOCKEVENTS_BROADCAST
 	select ARCH_HAVE_CUSTOM_GPIO_H
+	select ARCH_USE_CMPXCHG_LOCKREF
 	select ARCH_WANT_IPC_PARSE_VERSION
 	select BUILDTIME_EXTABLE_SORT if MMU
 	select CLONE_BACKWARDS
@@ -1091,11 +1092,6 @@ config IWMMXT
 	  Enable support for iWMMXt context switching at run time if
 	  running on a CPU that supports it.
 
-config XSCALE_PMU
-	bool
-	depends on CPU_XSCALE
-	default y
-
 config MULTI_IRQ_HANDLER
 	bool
 	help
diff --git a/arch/arm/Kconfig.debug b/arch/arm/Kconfig.debug
index 9762c84b419..a8f305b07f2 100644
--- a/arch/arm/Kconfig.debug
+++ b/arch/arm/Kconfig.debug
@@ -318,6 +318,7 @@ choice
 	config DEBUG_MSM_UART1
 		bool "Kernel low-level debugging messages via MSM UART1"
 		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the first serial port on MSM devices.
@@ -325,6 +326,7 @@ choice
 	config DEBUG_MSM_UART2
 		bool "Kernel low-level debugging messages via MSM UART2"
 		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the second serial port on MSM devices.
@@ -332,6 +334,7 @@ choice
 	config DEBUG_MSM_UART3
 		bool "Kernel low-level debugging messages via MSM UART3"
 		depends on ARCH_MSM7X00A || ARCH_MSM7X30 || ARCH_QSD8X50
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the third serial port on MSM devices.
@@ -340,6 +343,7 @@ choice
 		bool "Kernel low-level debugging messages via MSM 8660 UART"
 		depends on ARCH_MSM8X60
 		select MSM_HAS_DEBUG_UART_HS
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the serial port on MSM 8660 devices.
@@ -348,10 +352,20 @@ choice
 		bool "Kernel low-level debugging messages via MSM 8960 UART"
 		depends on ARCH_MSM8960
 		select MSM_HAS_DEBUG_UART_HS
+		select DEBUG_MSM_UART
 		help
 		  Say Y here if you want the debug print routines to direct
 		  their output to the serial port on MSM 8960 devices.
 
+	config DEBUG_MSM8974_UART
+		bool "Kernel low-level debugging messages via MSM 8974 UART"
+		depends on ARCH_MSM8974
+		select MSM_HAS_DEBUG_UART_HS
+		select DEBUG_MSM_UART
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to the serial port on MSM 8974 devices.
+
 	config DEBUG_MVEBU_UART
 		bool "Kernel low-level debugging messages via MVEBU UART (old bootloaders)"
 		depends on ARCH_MVEBU
@@ -834,6 +848,20 @@ choice
 		  options; the platform specific options are deprecated
 		  and will be soon removed.
 
+	config DEBUG_LL_UART_EFM32
+		bool "Kernel low-level debugging via efm32 UART"
+		depends on ARCH_EFM32
+		help
+		  Say Y here if you want the debug print routines to direct
+		  their output to an UART or USART port on efm32 based
+		  machines. Use the following addresses for DEBUG_UART_PHYS:
+
+		    0x4000c000 | USART0
+		    0x4000c400 | USART1
+		    0x4000c800 | USART2
+		    0x4000e000 | UART0
+		    0x4000e400 | UART1
+
 	config DEBUG_LL_UART_PL01X
 		bool "Kernel low-level debugging via ARM Ltd PL01x Primecell UART"
 		help
@@ -880,11 +908,16 @@ config DEBUG_STI_UART
 	bool
 	depends on ARCH_STI
 
+config DEBUG_MSM_UART
+	bool
+	depends on ARCH_MSM
+
 config DEBUG_LL_INCLUDE
 	string
 	default "debug/8250.S" if DEBUG_LL_UART_8250 || DEBUG_UART_8250
 	default "debug/pl01x.S" if DEBUG_LL_UART_PL01X || DEBUG_UART_PL01X
 	default "debug/exynos.S" if DEBUG_EXYNOS_UART
+	default "debug/efm32.S" if DEBUG_LL_UART_EFM32
 	default "debug/icedcc.S" if DEBUG_ICEDCC
 	default "debug/imx.S" if DEBUG_IMX1_UART || \
 				 DEBUG_IMX25_UART || \
@@ -895,11 +928,7 @@ config DEBUG_LL_INCLUDE
 				 DEBUG_IMX53_UART ||\
 				 DEBUG_IMX6Q_UART || \
 				 DEBUG_IMX6SL_UART
-	default "debug/msm.S" if DEBUG_MSM_UART1 || \
-				 DEBUG_MSM_UART2 || \
-				 DEBUG_MSM_UART3 || \
-				 DEBUG_MSM8660_UART || \
-				 DEBUG_MSM8960_UART
+	default "debug/msm.S" if DEBUG_MSM_UART
 	default "debug/omap2plus.S" if DEBUG_OMAP2PLUS_UART
 	default "debug/sirf.S" if DEBUG_SIRFPRIMA2_UART1 || DEBUG_SIRFMARCO_UART1
 	default "debug/sti.S" if DEBUG_STI_UART
@@ -951,6 +980,7 @@ config DEBUG_UART_PHYS
 	default 0x20064000 if DEBUG_RK29_UART1 || DEBUG_RK3X_UART2
 	default 0x20068000 if DEBUG_RK29_UART2 || DEBUG_RK3X_UART3
 	default 0x20201000 if DEBUG_BCM2835
+	default 0x4000e400 if DEBUG_LL_UART_EFM32
 	default 0x40090000 if ARCH_LPC32XX
 	default 0x40100000 if DEBUG_PXA_UART1
 	default 0x42000000 if ARCH_GEMINI
@@ -981,6 +1011,7 @@ config DEBUG_UART_PHYS
 	default 0xfff36000 if DEBUG_HIGHBANK_UART
 	default 0xfffff700 if ARCH_IOP33X
 	depends on DEBUG_LL_UART_8250 || DEBUG_LL_UART_PL01X || \
+		DEBUG_LL_UART_EFM32 || \
 		DEBUG_UART_8250 || DEBUG_UART_PL01X
 
 config DEBUG_UART_VIRT
diff --git a/arch/arm/common/mcpm_entry.c b/arch/arm/common/mcpm_entry.c
index 990250965f2..6c03d0152e7 100644
--- a/arch/arm/common/mcpm_entry.c
+++ b/arch/arm/common/mcpm_entry.c
@@ -90,6 +90,21 @@ void mcpm_cpu_power_down(void)
 	BUG();
 }
 
+int mcpm_cpu_power_down_finish(unsigned int cpu, unsigned int cluster)
+{
+	int ret;
+
+	if (WARN_ON_ONCE(!platform_ops || !platform_ops->power_down_finish))
+		return -EUNATCH;
+
+	ret = platform_ops->power_down_finish(cpu, cluster);
+	if (ret)
+		pr_warn("%s: cpu %u, cluster %u failed to power down (%d)\n",
+			__func__, cpu, cluster, ret);
+
+	return ret;
+}
+
 void mcpm_cpu_suspend(u64 expected_residency)
 {
 	phys_reset_t phys_reset;
diff --git a/arch/arm/common/mcpm_platsmp.c b/arch/arm/common/mcpm_platsmp.c
index 1bc34c7567f..177251a4dd9 100644
--- a/arch/arm/common/mcpm_platsmp.c
+++ b/arch/arm/common/mcpm_platsmp.c
@@ -19,14 +19,23 @@
 #include <asm/smp.h>
 #include <asm/smp_plat.h>
 
+static void cpu_to_pcpu(unsigned int cpu,
+			unsigned int *pcpu, unsigned int *pcluster)
+{
+	unsigned int mpidr;
+
+	mpidr = cpu_logical_map(cpu);
+	*pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
+	*pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+}
+
 static int mcpm_boot_secondary(unsigned int cpu, struct task_struct *idle)
 {
-	unsigned int mpidr, pcpu, pcluster, ret;
+	unsigned int pcpu, pcluster, ret;
 	extern void secondary_startup(void);
 
-	mpidr = cpu_logical_map(cpu);
-	pcpu = MPIDR_AFFINITY_LEVEL(mpidr, 0);
-	pcluster = MPIDR_AFFINITY_LEVEL(mpidr, 1);
+	cpu_to_pcpu(cpu, &pcpu, &pcluster);
+
 	pr_debug("%s: logical CPU %d is physical CPU %d cluster %d\n",
 		 __func__, cpu, pcpu, pcluster);
 
@@ -47,6 +56,15 @@ static void mcpm_secondary_init(unsigned int cpu)
 
 #ifdef CONFIG_HOTPLUG_CPU
 
+static int mcpm_cpu_kill(unsigned int cpu)
+{
+	unsigned int pcpu, pcluster;
+
+	cpu_to_pcpu(cpu, &pcpu, &pcluster);
+
+	return !mcpm_cpu_power_down_finish(pcpu, pcluster);
+}
+
 static int mcpm_cpu_disable(unsigned int cpu)
 {
 	/*
@@ -73,6 +91,7 @@ static struct smp_operations __initdata mcpm_smp_ops = {
 	.smp_boot_secondary	= mcpm_boot_secondary,
 	.smp_secondary_init	= mcpm_secondary_init,
 #ifdef CONFIG_HOTPLUG_CPU
+	.cpu_kill		= mcpm_cpu_kill,
 	.cpu_disable		= mcpm_cpu_disable,
 	.cpu_die		= mcpm_cpu_die,
 #endif
diff --git a/arch/arm/common/timer-sp.c b/arch/arm/common/timer-sp.c
index e901d0f3e0b..ce922d0ea7a 100644
--- a/arch/arm/common/timer-sp.c
+++ b/arch/arm/common/timer-sp.c
@@ -175,7 +175,7 @@ static struct clock_event_device sp804_clockevent = {
 
 static struct irqaction sp804_timer_irq = {
 	.name		= "timer",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= sp804_timer_interrupt,
 	.dev_id		= &sp804_clockevent,
 };
diff --git a/arch/arm/include/asm/atomic.h b/arch/arm/include/asm/atomic.h
index da1c77d3932..f8a4336ed8f 100644
--- a/arch/arm/include/asm/atomic.h
+++ b/arch/arm/include/asm/atomic.h
@@ -114,7 +114,8 @@ 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 +135,6 @@ 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 +183,6 @@ 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 +215,15 @@ 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 +234,7 @@ 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 +243,9 @@ 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]"
@@ -279,9 +256,9 @@ 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;
 
 	__asm__ __volatile__("@ atomic64_set\n"
 "1:	ldrexd	%0, %H0, [%2]\n"
@@ -294,9 +271,9 @@ 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;
 
 	__asm__ __volatile__("@ atomic64_add\n"
@@ -311,9 +288,9 @@ 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();
@@ -334,9 +311,9 @@ 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;
 
 	__asm__ __volatile__("@ atomic64_sub\n"
@@ -351,9 +328,9 @@ 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();
@@ -374,9 +351,10 @@ 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 +376,9 @@ 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();
@@ -419,9 +397,9 @@ 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();
@@ -445,9 +423,9 @@ 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;
 
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..3d7351c844a 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	7
 
 typedef struct {
 	unsigned int __softirq_pending;
diff --git a/arch/arm/include/asm/mcpm.h b/arch/arm/include/asm/mcpm.h
index fc82a88f5b6..1cf26010a6f 100644
--- a/arch/arm/include/asm/mcpm.h
+++ b/arch/arm/include/asm/mcpm.h
@@ -81,10 +81,40 @@ 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 +156,7 @@ 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/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/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/spinlock.h b/arch/arm/include/asm/spinlock.h
index 4f2c28060c9..ed6c22919e4 100644
--- a/arch/arm/include/asm/spinlock.h
+++ b/arch/arm/include/asm/spinlock.h
@@ -127,10 +127,14 @@ 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)
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/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/kernel/hw_breakpoint.c b/arch/arm/kernel/hw_breakpoint.c
index 7b95de60135..3d446605cbf 100644
--- a/arch/arm/kernel/hw_breakpoint.c
+++ b/arch/arm/kernel/hw_breakpoint.c
@@ -344,13 +344,13 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		/* Breakpoint */
 		ctrl_base = ARM_BASE_BCR;
 		val_base = ARM_BASE_BVR;
-		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
 		ctrl_base = ARM_BASE_WCR;
 		val_base = ARM_BASE_WVR;
-		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -396,12 +396,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		base = ARM_BASE_BCR;
-		slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
 		base = ARM_BASE_WCR;
-		slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -697,7 +697,7 @@ static void watchpoint_handler(unsigned long addr, unsigned int fsr,
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+	slots = this_cpu_ptr(wp_on_reg);
 
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
@@ -768,7 +768,7 @@ static void watchpoint_single_step_handler(unsigned long pc)
 	struct perf_event *wp, **slots;
 	struct arch_hw_breakpoint *info;
 
-	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+	slots = this_cpu_ptr(wp_on_reg);
 
 	for (i = 0; i < core_num_wrps; ++i) {
 		rcu_read_lock();
@@ -802,7 +802,7 @@ static void breakpoint_handler(unsigned long unknown, struct pt_regs *regs)
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+	slots = this_cpu_ptr(bp_on_reg);
 
 	/* The exception entry code places the amended lr in the PC. */
 	addr = regs->ARM_pc;
diff --git a/arch/arm/kernel/kprobes.c b/arch/arm/kernel/kprobes.c
index 170e9f34003..a7b621ece23 100644
--- a/arch/arm/kernel/kprobes.c
+++ b/arch/arm/kernel/kprobes.c
@@ -171,13 +171,13 @@ static void __kprobes save_previous_kprobe(struct kprobe_ctlblk *kcb)
 
 static void __kprobes restore_previous_kprobe(struct kprobe_ctlblk *kcb)
 {
-	__get_cpu_var(current_kprobe) = kcb->prev_kprobe.kp;
+	__this_cpu_write(current_kprobe, kcb->prev_kprobe.kp);
 	kcb->kprobe_status = kcb->prev_kprobe.status;
 }
 
 static void __kprobes set_current_kprobe(struct kprobe *p)
 {
-	__get_cpu_var(current_kprobe) = p;
+	__this_cpu_write(current_kprobe, p);
 }
 
 static void __kprobes
@@ -421,10 +421,10 @@ static __used __kprobes void *trampoline_handler(struct pt_regs *regs)
 			continue;
 
 		if (ri->rp && ri->rp->handler) {
-			__get_cpu_var(current_kprobe) = &ri->rp->kp;
+			__this_cpu_write(current_kprobe, &ri->rp->kp);
 			get_kprobe_ctlblk()->kprobe_status = KPROBE_HIT_ACTIVE;
 			ri->rp->handler(ri, regs);
-			__get_cpu_var(current_kprobe) = NULL;
+			__this_cpu_write(current_kprobe, NULL);
 		}
 
 		orig_ret_address = (unsigned long)ri->ret_addr;
diff --git a/arch/arm/kernel/perf_event_cpu.c b/arch/arm/kernel/perf_event_cpu.c
index 8d6147b2001..d85055cd24b 100644
--- a/arch/arm/kernel/perf_event_cpu.c
+++ b/arch/arm/kernel/perf_event_cpu.c
@@ -68,7 +68,7 @@ EXPORT_SYMBOL_GPL(perf_num_counters);
 
 static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
 {
-	return &__get_cpu_var(cpu_hw_events);
+	return this_cpu_ptr(&cpu_hw_events);
 }
 
 static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
diff --git a/arch/arm/kernel/setup.c b/arch/arm/kernel/setup.c
index 0e1e2b3afa4..53c3901f7ee 100644
--- a/arch/arm/kernel/setup.c
+++ b/arch/arm/kernel/setup.c
@@ -599,6 +599,8 @@ static void __init setup_processor(void)
 	elf_hwcap &= ~(HWCAP_THUMB | HWCAP_IDIVT);
 #endif
 
+	erratum_a15_798181_init();
+
 	feat_v6_fixup();
 
 	cacheid_init();
@@ -619,9 +621,10 @@ void __init dump_machine_table(void)
 		/* can't use cpu_relax() here as it may require MMU setup */;
 }
 
-int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
+int __init arm_add_memory(u64 start, u64 size)
 {
 	struct membank *bank = &meminfo.bank[meminfo.nr_banks];
+	u64 aligned_start;
 
 	if (meminfo.nr_banks >= NR_BANKS) {
 		printk(KERN_CRIT "NR_BANKS too low, "
@@ -634,10 +637,16 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 	 * Size is appropriately rounded down, start is rounded up.
 	 */
 	size -= start & ~PAGE_MASK;
-	bank->start = PAGE_ALIGN(start);
+	aligned_start = PAGE_ALIGN(start);
+
+#ifndef CONFIG_ARCH_PHYS_ADDR_T_64BIT
+	if (aligned_start > ULONG_MAX) {
+		printk(KERN_CRIT "Ignoring memory at 0x%08llx outside "
+		       "32-bit physical address space\n", (long long)start);
+		return -EINVAL;
+	}
 
-#ifndef CONFIG_ARM_LPAE
-	if (bank->start + size < bank->start) {
+	if (aligned_start + size > ULONG_MAX) {
 		printk(KERN_CRIT "Truncating memory at 0x%08llx to fit in "
 			"32-bit physical address space\n", (long long)start);
 		/*
@@ -645,10 +654,11 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 		 * 32 bits, we use ULONG_MAX as the upper limit rather than 4GB.
 		 * This means we lose a page after masking.
 		 */
-		size = ULONG_MAX - bank->start;
+		size = ULONG_MAX - aligned_start;
 	}
 #endif
 
+	bank->start = aligned_start;
 	bank->size = size & ~(phys_addr_t)(PAGE_SIZE - 1);
 
 	/*
@@ -669,8 +679,8 @@ int __init arm_add_memory(phys_addr_t start, phys_addr_t size)
 static int __init early_mem(char *p)
 {
 	static int usermem __initdata = 0;
-	phys_addr_t size;
-	phys_addr_t start;
+	u64 size;
+	u64 start;
 	char *endp;
 
 	/*
diff --git a/arch/arm/kernel/smp.c b/arch/arm/kernel/smp.c
index 72024ea8a3a..e115cbb0d25 100644
--- a/arch/arm/kernel/smp.c
+++ b/arch/arm/kernel/smp.c
@@ -25,6 +25,7 @@
 #include <linux/clockchips.h>
 #include <linux/completion.h>
 #include <linux/cpufreq.h>
+#include <linux/irq_work.h>
 
 #include <linux/atomic.h>
 #include <asm/smp.h>
@@ -66,6 +67,7 @@ enum ipi_msg_type {
 	IPI_CALL_FUNC,
 	IPI_CALL_FUNC_SINGLE,
 	IPI_CPU_STOP,
+	IPI_IRQ_WORK,
 };
 
 static DECLARE_COMPLETION(cpu_running);
@@ -448,6 +450,14 @@ void arch_send_call_function_single_ipi(int cpu)
 	smp_cross_call(cpumask_of(cpu), IPI_CALL_FUNC_SINGLE);
 }
 
+#ifdef CONFIG_IRQ_WORK
+void arch_irq_work_raise(void)
+{
+	if (is_smp())
+		smp_cross_call(cpumask_of(smp_processor_id()), IPI_IRQ_WORK);
+}
+#endif
+
 static const char *ipi_types[NR_IPI] = {
 #define S(x,s)	[x] = s
 	S(IPI_WAKEUP, "CPU wakeup interrupts"),
@@ -456,6 +466,7 @@ static const char *ipi_types[NR_IPI] = {
 	S(IPI_CALL_FUNC, "Function call interrupts"),
 	S(IPI_CALL_FUNC_SINGLE, "Single function call interrupts"),
 	S(IPI_CPU_STOP, "CPU stop interrupts"),
+	S(IPI_IRQ_WORK, "IRQ work interrupts"),
 };
 
 void show_ipi_list(struct seq_file *p, int prec)
@@ -565,6 +576,14 @@ void handle_IPI(int ipinr, struct pt_regs *regs)
 		irq_exit();
 		break;
 
+#ifdef CONFIG_IRQ_WORK
+	case IPI_IRQ_WORK:
+		irq_enter();
+		irq_work_run();
+		irq_exit();
+		break;
+#endif
+
 	default:
 		printk(KERN_CRIT "CPU%u: Unknown IPI message 0x%x\n",
 		       cpu, ipinr);
diff --git a/arch/arm/kernel/smp_tlb.c b/arch/arm/kernel/smp_tlb.c
index 83ccca303df..95d063620b7 100644
--- a/arch/arm/kernel/smp_tlb.c
+++ b/arch/arm/kernel/smp_tlb.c
@@ -70,6 +70,40 @@ static inline void ipi_flush_bp_all(void *ignored)
 	local_flush_bp_all();
 }
 
+#ifdef CONFIG_ARM_ERRATA_798181
+bool (*erratum_a15_798181_handler)(void);
+
+static bool erratum_a15_798181_partial(void)
+{
+	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
+	dsb(ish);
+	return false;
+}
+
+static bool erratum_a15_798181_broadcast(void)
+{
+	asm("mcr p15, 0, %0, c8, c3, 1" : : "r" (0));
+	dsb(ish);
+	return true;
+}
+
+void erratum_a15_798181_init(void)
+{
+	unsigned int midr = read_cpuid_id();
+	unsigned int revidr = read_cpuid(CPUID_REVIDR);
+
+	/* Cortex-A15 r0p0..r3p2 w/o ECO fix affected */
+	if ((midr & 0xff0ffff0) != 0x410fc0f0 || midr > 0x413fc0f2 ||
+	    (revidr & 0x210) == 0x210) {
+		return;
+	}
+	if (revidr & 0x10)
+		erratum_a15_798181_handler = erratum_a15_798181_partial;
+	else
+		erratum_a15_798181_handler = erratum_a15_798181_broadcast;
+}
+#endif
+
 static void ipi_flush_tlb_a15_erratum(void *arg)
 {
 	dmb();
@@ -80,7 +114,6 @@ static void broadcast_tlb_a15_erratum(void)
 	if (!erratum_a15_798181())
 		return;
 
-	dummy_flush_tlb_a15_erratum();
 	smp_call_function(ipi_flush_tlb_a15_erratum, NULL, 1);
 }
 
@@ -92,7 +125,6 @@ static void broadcast_tlb_mm_a15_erratum(struct mm_struct *mm)
 	if (!erratum_a15_798181())
 		return;
 
-	dummy_flush_tlb_a15_erratum();
 	this_cpu = get_cpu();
 	a15_erratum_get_cpumask(this_cpu, mm, &mask);
 	smp_call_function_many(&mask, ipi_flush_tlb_a15_erratum, NULL, 1);
diff --git a/arch/arm/kvm/arm.c b/arch/arm/kvm/arm.c
index 9c697db2787..aea7ccb8d39 100644
--- a/arch/arm/kvm/arm.c
+++ b/arch/arm/kvm/arm.c
@@ -65,7 +65,7 @@ static bool vgic_present;
 static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 {
 	BUG_ON(preemptible());
-	__get_cpu_var(kvm_arm_running_vcpu) = vcpu;
+	__this_cpu_write(kvm_arm_running_vcpu, vcpu);
 }
 
 /**
@@ -75,7 +75,7 @@ static void kvm_arm_set_running_vcpu(struct kvm_vcpu *vcpu)
 struct kvm_vcpu *kvm_arm_get_running_vcpu(void)
 {
 	BUG_ON(preemptible());
-	return __get_cpu_var(kvm_arm_running_vcpu);
+	return __this_cpu_read(kvm_arm_running_vcpu);
 }
 
 /**
@@ -815,7 +815,7 @@ static void cpu_init_hyp_mode(void *dummy)
 
 	boot_pgd_ptr = kvm_mmu_get_boot_httbr();
 	pgd_ptr = kvm_mmu_get_httbr();
-	stack_page = __get_cpu_var(kvm_arm_hyp_stack_page);
+	stack_page = __this_cpu_read(kvm_arm_hyp_stack_page);
 	hyp_stack_ptr = stack_page + PAGE_SIZE;
 	vector_ptr = (unsigned long)__kvm_hyp_vector;
 
diff --git a/arch/arm/lib/uaccess_with_memcpy.c b/arch/arm/lib/uaccess_with_memcpy.c
index 025f742dd4d..3e58d710013 100644
--- a/arch/arm/lib/uaccess_with_memcpy.c
+++ b/arch/arm/lib/uaccess_with_memcpy.c
@@ -18,6 +18,7 @@
 #include <linux/hardirq.h> /* for in_atomic() */
 #include <linux/gfp.h>
 #include <linux/highmem.h>
+#include <linux/hugetlb.h>
 #include <asm/current.h>
 #include <asm/page.h>
 
@@ -40,7 +41,35 @@ pin_page_for_write(const void __user *_addr, pte_t **ptep, spinlock_t **ptlp)
 		return 0;
 
 	pmd = pmd_offset(pud, addr);
-	if (unlikely(pmd_none(*pmd) || pmd_bad(*pmd)))
+	if (unlikely(pmd_none(*pmd)))
+		return 0;
+
+	/*
+	 * A pmd can be bad if it refers to a HugeTLB or THP page.
+	 *
+	 * Both THP and HugeTLB pages have the same pmd layout
+	 * and should not be manipulated by the pte functions.
+	 *
+	 * Lock the page table for the destination and check
+	 * to see that it's still huge and whether or not we will
+	 * need to fault on write, or if we have a splitting THP.
+	 */
+	if (unlikely(pmd_thp_or_huge(*pmd))) {
+		ptl = &current->mm->page_table_lock;
+		spin_lock(ptl);
+		if (unlikely(!pmd_thp_or_huge(*pmd)
+			|| pmd_hugewillfault(*pmd)
+			|| pmd_trans_splitting(*pmd))) {
+			spin_unlock(ptl);
+			return 0;
+		}
+
+		*ptep = NULL;
+		*ptlp = ptl;
+		return 1;
+	}
+
+	if (unlikely(pmd_bad(*pmd)))
 		return 0;
 
 	pte = pte_offset_map_lock(current->mm, pmd, addr, &ptl);
@@ -94,7 +123,10 @@ __copy_to_user_memcpy(void __user *to, const void *from, unsigned long n)
 		from += tocopy;
 		n -= tocopy;
 
-		pte_unmap_unlock(pte, ptl);
+		if (pte)
+			pte_unmap_unlock(pte, ptl);
+		else
+			spin_unlock(ptl);
 	}
 	if (!atomic)
 		up_read(&current->mm->mmap_sem);
@@ -147,7 +179,10 @@ __clear_user_memset(void __user *addr, unsigned long n)
 		addr += tocopy;
 		n -= tocopy;
 
-		pte_unmap_unlock(pte, ptl);
+		if (pte)
+			pte_unmap_unlock(pte, ptl);
+		else
+			spin_unlock(ptl);
 	}
 	up_read(&current->mm->mmap_sem);
 
diff --git a/arch/arm/mach-footbridge/netwinder-hw.c b/arch/arm/mach-footbridge/netwinder-hw.c
index 1fd2cf097e3..eb1fa5c8472 100644
--- a/arch/arm/mach-footbridge/netwinder-hw.c
+++ b/arch/arm/mach-footbridge/netwinder-hw.c
@@ -692,14 +692,14 @@ static void netwinder_led_set(struct led_classdev *cdev,
 	unsigned long flags;
 	u32 reg;
 
-	spin_lock_irqsave(&nw_gpio_lock, flags);
+	raw_spin_lock_irqsave(&nw_gpio_lock, flags);
 	reg = nw_gpio_read();
 	if (b != LED_OFF)
 		reg &= ~led->mask;
 	else
 		reg |= led->mask;
 	nw_gpio_modify_op(led->mask, reg);
-	spin_unlock_irqrestore(&nw_gpio_lock, flags);
+	raw_spin_unlock_irqrestore(&nw_gpio_lock, flags);
 }
 
 static enum led_brightness netwinder_led_get(struct led_classdev *cdev)
@@ -709,9 +709,9 @@ static enum led_brightness netwinder_led_get(struct led_classdev *cdev)
 	unsigned long flags;
 	u32 reg;
 
-	spin_lock_irqsave(&nw_gpio_lock, flags);
+	raw_spin_lock_irqsave(&nw_gpio_lock, flags);
 	reg = nw_gpio_read();
-	spin_unlock_irqrestore(&nw_gpio_lock, flags);
+	raw_spin_unlock_irqrestore(&nw_gpio_lock, flags);
 
 	return (reg & led->mask) ? LED_OFF : LED_FULL;
 }
diff --git a/arch/arm/mach-vexpress/dcscb.c b/arch/arm/mach-vexpress/dcscb.c
index 3a6384c6c43..14d49968873 100644
--- a/arch/arm/mach-vexpress/dcscb.c
+++ b/arch/arm/mach-vexpress/dcscb.c
@@ -133,38 +133,8 @@ static void dcscb_power_down(void)
 	if (last_man && __mcpm_outbound_enter_critical(cpu, cluster)) {
 		arch_spin_unlock(&dcscb_lock);
 
-		/*
-		 * Flush all cache levels for this cluster.
-		 *
-		 * To do so we do:
-		 * - Clear the SCTLR.C bit to prevent further cache allocations
-		 * - Flush the whole cache
-		 * - Clear the ACTLR "SMP" bit to disable local coherency
-		 *
-		 * Let's do it in the safest possible way i.e. with
-		 * no memory access within the following sequence
-		 * including to the stack.
-		 *
-		 * Note: fp is preserved to the stack explicitly prior doing
-		 * this since adding it to the clobber list is incompatible
-		 * with having CONFIG_FRAME_POINTER=y.
-		 */
-		asm volatile(
-		"str	fp, [sp, #-4]! \n\t"
-		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
-		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
-		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
-		"isb	\n\t"
-		"bl	v7_flush_dcache_all \n\t"
-		"clrex	\n\t"
-		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
-		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
-		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
-		"isb	\n\t"
-		"dsb	\n\t"
-		"ldr	fp, [sp], #4"
-		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
-		      "r9","r10","lr","memory");
+		/* Flush all cache levels for this cluster. */
+		v7_exit_coherency_flush(all);
 
 		/*
 		 * This is a harmless no-op.  On platforms with a real
@@ -183,26 +153,8 @@ static void dcscb_power_down(void)
 	} else {
 		arch_spin_unlock(&dcscb_lock);
 
-		/*
-		 * Flush the local CPU cache.
-		 * Let's do it in the safest possible way as above.
-		 */
-		asm volatile(
-		"str	fp, [sp, #-4]! \n\t"
-		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
-		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
-		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
-		"isb	\n\t"
-		"bl	v7_flush_dcache_louis \n\t"
-		"clrex	\n\t"
-		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
-		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
-		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
-		"isb	\n\t"
-		"dsb	\n\t"
-		"ldr	fp, [sp], #4"
-		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
-		      "r9","r10","lr","memory");
+		/* Disable and flush the local CPU cache. */
+		v7_exit_coherency_flush(louis);
 	}
 
 	__mcpm_cpu_down(cpu, cluster);
diff --git a/arch/arm/mach-vexpress/tc2_pm.c b/arch/arm/mach-vexpress/tc2_pm.c
index e6eb4819291..4eb92ebfd95 100644
--- a/arch/arm/mach-vexpress/tc2_pm.c
+++ b/arch/arm/mach-vexpress/tc2_pm.c
@@ -156,32 +156,7 @@ static void tc2_pm_down(u64 residency)
 			: : "r" (0x400) );
 		}
 
-		/*
-		 * We need to disable and flush the whole (L1 and L2) cache.
-		 * Let's do it in the safest possible way i.e. with
-		 * no memory access within the following sequence
-		 * including the stack.
-		 *
-		 * Note: fp is preserved to the stack explicitly prior doing
-		 * this since adding it to the clobber list is incompatible
-		 * with having CONFIG_FRAME_POINTER=y.
-		 */
-		asm volatile(
-		"str	fp, [sp, #-4]! \n\t"
-		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
-		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
-		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
-		"isb	\n\t"
-		"bl	v7_flush_dcache_all \n\t"
-		"clrex	\n\t"
-		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
-		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
-		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
-		"isb	\n\t"
-		"dsb	\n\t"
-		"ldr	fp, [sp], #4"
-		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
-		      "r9","r10","lr","memory");
+		v7_exit_coherency_flush(all);
 
 		cci_disable_port_by_cpu(mpidr);
 
@@ -197,26 +172,7 @@ static void tc2_pm_down(u64 residency)
 
 		arch_spin_unlock(&tc2_pm_lock);
 
-		/*
-		 * We need to disable and flush only the L1 cache.
-		 * Let's do it in the safest possible way as above.
-		 */
-		asm volatile(
-		"str	fp, [sp, #-4]! \n\t"
-		"mrc	p15, 0, r0, c1, c0, 0	@ get CR \n\t"
-		"bic	r0, r0, #"__stringify(CR_C)" \n\t"
-		"mcr	p15, 0, r0, c1, c0, 0	@ set CR \n\t"
-		"isb	\n\t"
-		"bl	v7_flush_dcache_louis \n\t"
-		"clrex	\n\t"
-		"mrc	p15, 0, r0, c1, c0, 1	@ get AUXCR \n\t"
-		"bic	r0, r0, #(1 << 6)	@ disable local coherency \n\t"
-		"mcr	p15, 0, r0, c1, c0, 1	@ set AUXCR \n\t"
-		"isb	\n\t"
-		"dsb	\n\t"
-		"ldr	fp, [sp], #4"
-		: : : "r0","r1","r2","r3","r4","r5","r6","r7",
-		      "r9","r10","lr","memory");
+		v7_exit_coherency_flush(louis);
 	}
 
 	__mcpm_cpu_down(cpu, cluster);
diff --git a/arch/arm/mm/mmap.c b/arch/arm/mm/mmap.c
index 0c6356255fe..d27158c38eb 100644
--- a/arch/arm/mm/mmap.c
+++ b/arch/arm/mm/mmap.c
@@ -202,13 +202,11 @@ int valid_phys_addr_range(phys_addr_t addr, size_t size)
 }
 
 /*
- * We don't use supersection mappings for mmap() on /dev/mem, which
- * means that we can't map the memory area above the 4G barrier into
- * userspace.
+ * Do not allow /dev/mem mappings beyond the supported physical range.
  */
 int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
 {
-	return !(pfn + (size >> PAGE_SHIFT) > 0x00100000);
+	return (pfn + (size >> PAGE_SHIFT)) <= (1 + (PHYS_MASK >> PAGE_SHIFT));
 }
 
 #ifdef CONFIG_STRICT_DEVMEM
diff --git a/arch/arm64/include/asm/atomic.h b/arch/arm64/include/asm/atomic.h
index 83636446857..01de5aaa3ed 100644
--- a/arch/arm64/include/asm/atomic.h
+++ b/arch/arm64/include/asm/atomic.h
@@ -126,20 +126,6 @@ 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:	ldxr	%0, %2\n"
-"	bic	%0, %0, %3\n"
-"	stxr	%w1, %0, %2\n"
-"	cbnz	%w1, 1b"
-	: "=&r" (tmp), "=&r" (tmp2), "+Q" (*addr)
-	: "Ir" (mask)
-	: "cc");
-}
-
 #define atomic_xchg(v, new) (xchg(&((v)->counter), new))
 
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
diff --git a/arch/arm64/kernel/debug-monitors.c b/arch/arm64/kernel/debug-monitors.c
index cbfacf7fb43..6a0a9b132d7 100644
--- a/arch/arm64/kernel/debug-monitors.c
+++ b/arch/arm64/kernel/debug-monitors.c
@@ -27,7 +27,6 @@
 #include <linux/uaccess.h>
 
 #include <asm/debug-monitors.h>
-#include <asm/local.h>
 #include <asm/cputype.h>
 #include <asm/system_misc.h>
 
@@ -89,8 +88,8 @@ early_param("nodebugmon", early_debug_disable);
  * Keep track of debug users on each core.
  * The ref counts are per-cpu so we use a local_t type.
  */
-static DEFINE_PER_CPU(local_t, mde_ref_count);
-static DEFINE_PER_CPU(local_t, kde_ref_count);
+static DEFINE_PER_CPU(int, mde_ref_count);
+static DEFINE_PER_CPU(int, kde_ref_count);
 
 void enable_debug_monitors(enum debug_el el)
 {
@@ -98,11 +97,11 @@ void enable_debug_monitors(enum debug_el el)
 
 	WARN_ON(preemptible());
 
-	if (local_inc_return(&__get_cpu_var(mde_ref_count)) == 1)
+	if (this_cpu_inc_return(mde_ref_count) == 1)
 		enable = DBG_MDSCR_MDE;
 
 	if (el == DBG_ACTIVE_EL1 &&
-	    local_inc_return(&__get_cpu_var(kde_ref_count)) == 1)
+	    this_cpu_inc_return(kde_ref_count) == 1)
 		enable |= DBG_MDSCR_KDE;
 
 	if (enable && debug_enabled) {
@@ -118,11 +117,11 @@ void disable_debug_monitors(enum debug_el el)
 
 	WARN_ON(preemptible());
 
-	if (local_dec_and_test(&__get_cpu_var(mde_ref_count)))
+	if (this_cpu_dec_return(mde_ref_count) == 0)
 		disable = ~DBG_MDSCR_MDE;
 
 	if (el == DBG_ACTIVE_EL1 &&
-	    local_dec_and_test(&__get_cpu_var(kde_ref_count)))
+	    this_cpu_dec_return(kde_ref_count) == 0)
 		disable &= ~DBG_MDSCR_KDE;
 
 	if (disable) {
diff --git a/arch/arm64/kernel/hw_breakpoint.c b/arch/arm64/kernel/hw_breakpoint.c
index 329218ca9ff..ff516f6691e 100644
--- a/arch/arm64/kernel/hw_breakpoint.c
+++ b/arch/arm64/kernel/hw_breakpoint.c
@@ -184,14 +184,14 @@ int arch_install_hw_breakpoint(struct perf_event *bp)
 		/* Breakpoint */
 		ctrl_reg = AARCH64_DBG_REG_BCR;
 		val_reg = AARCH64_DBG_REG_BVR;
-		slots = __get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 		reg_enable = !debug_info->bps_disabled;
 	} else {
 		/* Watchpoint */
 		ctrl_reg = AARCH64_DBG_REG_WCR;
 		val_reg = AARCH64_DBG_REG_WVR;
-		slots = __get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 		reg_enable = !debug_info->wps_disabled;
 	}
@@ -230,12 +230,12 @@ void arch_uninstall_hw_breakpoint(struct perf_event *bp)
 	if (info->ctrl.type == ARM_BREAKPOINT_EXECUTE) {
 		/* Breakpoint */
 		base = AARCH64_DBG_REG_BCR;
-		slots = __get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 	} else {
 		/* Watchpoint */
 		base = AARCH64_DBG_REG_WCR;
-		slots = __get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 	}
 
@@ -505,11 +505,11 @@ static void toggle_bp_registers(int reg, enum debug_el el, int enable)
 
 	switch (reg) {
 	case AARCH64_DBG_REG_BCR:
-		slots = __get_cpu_var(bp_on_reg);
+		slots = this_cpu_ptr(bp_on_reg);
 		max_slots = core_num_brps;
 		break;
 	case AARCH64_DBG_REG_WCR:
-		slots = __get_cpu_var(wp_on_reg);
+		slots = this_cpu_ptr(wp_on_reg);
 		max_slots = core_num_wrps;
 		break;
 	default:
@@ -546,7 +546,7 @@ static int breakpoint_handler(unsigned long unused, unsigned int esr,
 	struct debug_info *debug_info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(bp_on_reg);
+	slots = this_cpu_ptr(bp_on_reg);
 	addr = instruction_pointer(regs);
 	debug_info = &current->thread.debug;
 
@@ -596,7 +596,7 @@ unlock:
 			user_enable_single_step(current);
 	} else {
 		toggle_bp_registers(AARCH64_DBG_REG_BCR, DBG_ACTIVE_EL1, 0);
-		kernel_step = &__get_cpu_var(stepping_kernel_bp);
+		kernel_step = this_cpu_ptr(&stepping_kernel_bp);
 
 		if (*kernel_step != ARM_KERNEL_STEP_NONE)
 			return 0;
@@ -623,7 +623,7 @@ static int watchpoint_handler(unsigned long addr, unsigned int esr,
 	struct arch_hw_breakpoint *info;
 	struct arch_hw_breakpoint_ctrl ctrl;
 
-	slots = (struct perf_event **)__get_cpu_var(wp_on_reg);
+	slots = this_cpu_ptr(wp_on_reg);
 	debug_info = &current->thread.debug;
 
 	for (i = 0; i < core_num_wrps; ++i) {
@@ -698,7 +698,7 @@ unlock:
 			user_enable_single_step(current);
 	} else {
 		toggle_bp_registers(AARCH64_DBG_REG_WCR, DBG_ACTIVE_EL1, 0);
-		kernel_step = &__get_cpu_var(stepping_kernel_bp);
+		kernel_step = this_cpu_ptr(&stepping_kernel_bp);
 
 		if (*kernel_step != ARM_KERNEL_STEP_NONE)
 			return 0;
@@ -722,7 +722,7 @@ int reinstall_suspended_bps(struct pt_regs *regs)
 	struct debug_info *debug_info = &current->thread.debug;
 	int handled_exception = 0, *kernel_step;
 
-	kernel_step = &__get_cpu_var(stepping_kernel_bp);
+	kernel_step = this_cpu_ptr(&stepping_kernel_bp);
 
 	/*
 	 * Called from single-step exception handler.
diff --git a/arch/arm64/kernel/perf_event.c b/arch/arm64/kernel/perf_event.c
index cea1594ff93..6983ed5a351 100644
--- a/arch/arm64/kernel/perf_event.c
+++ b/arch/arm64/kernel/perf_event.c
@@ -1044,7 +1044,7 @@ static irqreturn_t armv8pmu_handle_irq(int irq_num, void *dev)
 	 */
 	regs = get_irq_regs();
 
-	cpuc = &__get_cpu_var(cpu_hw_events);
+	cpuc = this_cpu_ptr(&cpu_hw_events);
 	for (idx = 0; idx < cpu_pmu->num_events; ++idx) {
 		struct perf_event *event = cpuc->events[idx];
 		struct hw_perf_event *hwc;
@@ -1257,7 +1257,7 @@ device_initcall(register_pmu_driver);
 
 static struct pmu_hw_events *armpmu_get_cpu_events(void)
 {
-	return &__get_cpu_var(cpu_hw_events);
+	return this_cpu_ptr(&cpu_hw_events);
 }
 
 static void __init cpu_pmu_init(struct arm_pmu *armpmu)