Merge branch 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm

Pull ARM changes from Russell King:

 - Perf updates from Will Deacon:
   - Support for Qualcomm Krait processors (run perf on your phone!)
   - Support for Cortex-A12 (run perf stat on your FPGA!)
   - Support for perf_sample_event_took, allowing us to automatically decrease
     the sample rate if we can't handle the PMU interrupts quickly enough
     (run perf record on your FPGA!).

 - Basic uprobes support from David Long:
     This patch series adds basic uprobes support to ARM. It is based on
     patches developed earlier by Rabin Vincent. That approach of adding
     hooks into the kprobes instruction parsing code was not well received.
     This approach separates the ARM instruction parsing code in kprobes out
     into a separate set of functions which can be used by both kprobes and
     uprobes. Both kprobes and uprobes then provide their own semantic action
     tables to process the results of the parsing.

 - ARMv7M (microcontroller) updates from Uwe Kleine-König

 - OMAP DMA updates (recently added Vinod's Ack even though they've been
   sitting in linux-next for a few months) to reduce the reliance of
   omap-dma on the code in arch/arm.

 - SA11x0 changes from Dmitry Eremin-Solenikov and Alexander Shiyan

 - Support for Cortex-A12 CPU

 - Align support for ARMv6 with ARMv7 so they can cooperate better in a
   single zImage.

 - Addition of first AT_HWCAP2 feature bits for ARMv8 crypto support.

 - Removal of IRQ_DISABLED from various ARM files

 - Improved efficiency of virt_to_page() for single zImage

 - Patch from Ulf Hansson to permit runtime PM callbacks to be available for
   AMBA devices for suspend/resume as well.

 - Finally kill asm/system.h on ARM.

* 'for-linus' of git://ftp.arm.linux.org.uk/~rmk/linux-arm: (89 commits)
  dmaengine: omap-dma: more consolidation of CCR register setup
  dmaengine: omap-dma: move IRQ handling to omap-dma
  dmaengine: omap-dma: move register read/writes into omap-dma.c
  ARM: omap: dma: get rid of 'p' allocation and clean up
  ARM: omap: move dma channel allocation into plat-omap code
  ARM: omap: dma: get rid of errata global
  ARM: omap: clean up DMA register accesses
  ARM: omap: remove almost-const variables
  ARM: omap: remove references to disable_irq_lch
  dmaengine: omap-dma: cleanup errata 3.3 handling
  dmaengine: omap-dma: provide register read/write functions
  dmaengine: omap-dma: use cached CCR value when enabling DMA
  dmaengine: omap-dma: move barrier to omap_dma_start_desc()
  dmaengine: omap-dma: move clnk_ctrl setting to preparation functions
  dmaengine: omap-dma: improve efficiency loading C.SA/C.EI/C.FI registers
  dmaengine: omap-dma: consolidate clearing channel status register
  dmaengine: omap-dma: move CCR buffering disable errata out of the fast path
  dmaengine: omap-dma: provide register definitions
  dmaengine: omap-dma: consolidate setup of CCR
  dmaengine: omap-dma: consolidate setup of CSDP
  ...

Documentation/devicetree/bindings/arm/pmu.txt

@@ -9,6 +9,7 @@ Required properties:
 - compatible : should be one of
 	"arm,armv8-pmuv3"
 	"arm,cortex-a15-pmu"
+	"arm,cortex-a12-pmu"
 	"arm,cortex-a9-pmu"
 	"arm,cortex-a8-pmu"
 	"arm,cortex-a7-pmu"
@@ -16,7 +17,14 @@ Required properties:
 	"arm,arm11mpcore-pmu"
 	"arm,arm1176-pmu"
 	"arm,arm1136-pmu"
-- interrupts : 1 combined interrupt or 1 per core.
+	"qcom,krait-pmu"
+- interrupts : 1 combined interrupt or 1 per core. If the interrupt is a per-cpu
+               interrupt (PPI) then 1 interrupt should be specified.
+
+Optional properties:
+
+- qcom,no-pc-write : Indicates that this PMU doesn't support the 0xc and 0xd
+                     events.
 
 Example:
 

arch/Kconfig

@@ -86,9 +86,7 @@ config KPROBES_ON_FTRACE
 	 optimize on top of function tracing.
 
 config UPROBES
-	bool "Transparent user-space probes (EXPERIMENTAL)"
-	depends on UPROBE_EVENT && PERF_EVENTS
-	default n
+	def_bool n
 	select PERCPU_RWSEM
 	help
 	  Uprobes is the user-space counterpart to kprobes: they
@@ -101,8 +99,6 @@ config UPROBES
 	    managed by the kernel and kept transparent to the probed
 	    application. )
 
-	  If in doubt, say "N".
-
 config HAVE_64BIT_ALIGNED_ACCESS
 	def_bool 64BIT && !HAVE_EFFICIENT_UNALIGNED_ACCESS
 	help

arch/arm/Kconfig

@@ -207,6 +207,9 @@ config ZONE_DMA
 config NEED_DMA_MAP_STATE
        def_bool y
 
+config ARCH_SUPPORTS_UPROBES
+	def_bool y
+
 config ARCH_HAS_DMA_SET_COHERENT_MASK
 	bool
 
@@ -2271,7 +2274,7 @@ source "kernel/power/Kconfig"
 config ARCH_SUSPEND_POSSIBLE
 	depends on !ARCH_S5PC100
 	depends on CPU_ARM920T || CPU_ARM926T || CPU_FEROCEON || CPU_SA1100 || \
-		CPU_V6 || CPU_V6K || CPU_V7 || CPU_XSC3 || CPU_XSCALE || CPU_MOHAWK
+		CPU_V6 || CPU_V6K || CPU_V7 || CPU_V7M || CPU_XSC3 || CPU_XSCALE || CPU_MOHAWK
 	def_bool y
 
 config ARM_CPU_SUSPEND

arch/arm/common/Makefile

@@ -13,6 +13,7 @@ obj-$(CONFIG_SHARP_SCOOP)	+= scoop.o
 obj-$(CONFIG_PCI_HOST_ITE8152)  += it8152.o
 obj-$(CONFIG_ARM_TIMER_SP804)	+= timer-sp.o
 obj-$(CONFIG_MCPM)		+= mcpm_head.o mcpm_entry.o mcpm_platsmp.o vlock.o
+CFLAGS_REMOVE_mcpm_entry.o	= -pg
 AFLAGS_mcpm_head.o		:= -march=armv7-a
 AFLAGS_vlock.o			:= -march=armv7-a
 obj-$(CONFIG_TI_PRIV_EDMA)	+= edma.o

arch/arm/common/scoop.c

@@ -232,8 +232,6 @@ static int scoop_probe(struct platform_device *pdev)
 
 	return 0;
 
-	if (devptr->gpio.base != -1)
-		temp = gpiochip_remove(&devptr->gpio);
 err_gpio:
 	platform_set_drvdata(pdev, NULL);
 err_ioremap:

arch/arm/include/asm/assembler.h

@@ -30,8 +30,8 @@
  * Endian independent macros for shifting bytes within registers.
  */
 #ifndef __ARMEB__
-#define pull            lsr
-#define push            lsl
+#define lspull          lsr
+#define lspush          lsl
 #define get_byte_0      lsl #0
 #define get_byte_1	lsr #8
 #define get_byte_2	lsr #16
@@ -41,8 +41,8 @@
 #define put_byte_2	lsl #16
 #define put_byte_3	lsl #24
 #else
-#define pull            lsl
-#define push            lsr
+#define lspull          lsl
+#define lspush          lsr
 #define get_byte_0	lsr #24
 #define get_byte_1	lsr #16
 #define get_byte_2	lsr #8

arch/arm/include/asm/atomic.h

@@ -60,6 +60,7 @@ static inline int atomic_add_return(int i, atomic_t *v)
 	int result;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic_add_return\n"
 "1:	ldrex	%0, [%3]\n"
@@ -99,6 +100,7 @@ static inline int atomic_sub_return(int i, atomic_t *v)
 	int result;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic_sub_return\n"
 "1:	ldrex	%0, [%3]\n"
@@ -121,6 +123,7 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	unsigned long res;
 
 	smp_mb();
+	prefetchw(&ptr->counter);
 
 	do {
 		__asm__ __volatile__("@ atomic_cmpxchg\n"
@@ -138,6 +141,33 @@ static inline int atomic_cmpxchg(atomic_t *ptr, int old, int new)
 	return oldval;
 }
 
+static inline int __atomic_add_unless(atomic_t *v, int a, int u)
+{
+	int oldval, newval;
+	unsigned long tmp;
+
+	smp_mb();
+	prefetchw(&v->counter);
+
+	__asm__ __volatile__ ("@ atomic_add_unless\n"
+"1:	ldrex	%0, [%4]\n"
+"	teq	%0, %5\n"
+"	beq	2f\n"
+"	add	%1, %0, %6\n"
+"	strex	%2, %1, [%4]\n"
+"	teq	%2, #0\n"
+"	bne	1b\n"
+"2:"
+	: "=&r" (oldval), "=&r" (newval), "=&r" (tmp), "+Qo" (v->counter)
+	: "r" (&v->counter), "r" (u), "r" (a)
+	: "cc");
+
+	if (oldval != u)
+		smp_mb();
+
+	return oldval;
+}
+
 #else /* ARM_ARCH_6 */
 
 #ifdef CONFIG_SMP
@@ -186,10 +216,6 @@ static inline int atomic_cmpxchg(atomic_t *v, int old, int new)
 	return ret;
 }
 
-#endif /* __LINUX_ARM_ARCH__ */
-
-#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
-
 static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 {
 	int c, old;
@@ -200,6 +226,10 @@ static inline int __atomic_add_unless(atomic_t *v, int a, int u)
 	return c;
 }
 
+#endif /* __LINUX_ARM_ARCH__ */
+
+#define atomic_xchg(v, new) (xchg(&((v)->counter), new))
+
 #define atomic_inc(v)		atomic_add(1, v)
 #define atomic_dec(v)		atomic_sub(1, v)
 
@@ -299,6 +329,7 @@ static inline long long atomic64_add_return(long long i, atomic64_t *v)
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_add_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
@@ -340,6 +371,7 @@ static inline long long atomic64_sub_return(long long i, atomic64_t *v)
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_sub_return\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
@@ -364,6 +396,7 @@ static inline long long atomic64_cmpxchg(atomic64_t *ptr, long long old,
 	unsigned long res;
 
 	smp_mb();
+	prefetchw(&ptr->counter);
 
 	do {
 		__asm__ __volatile__("@ atomic64_cmpxchg\n"
@@ -388,6 +421,7 @@ static inline long long atomic64_xchg(atomic64_t *ptr, long long new)
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&ptr->counter);
 
 	__asm__ __volatile__("@ atomic64_xchg\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
@@ -409,6 +443,7 @@ static inline long long atomic64_dec_if_positive(atomic64_t *v)
 	unsigned long tmp;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_dec_if_positive\n"
 "1:	ldrexd	%0, %H0, [%3]\n"
@@ -436,6 +471,7 @@ static inline int atomic64_add_unless(atomic64_t *v, long long a, long long u)
 	int ret = 1;
 
 	smp_mb();
+	prefetchw(&v->counter);
 
 	__asm__ __volatile__("@ atomic64_add_unless\n"
 "1:	ldrexd	%0, %H0, [%4]\n"

arch/arm/include/asm/cmpxchg.h

@@ -2,6 +2,7 @@
 #define __ASM_ARM_CMPXCHG_H
 
 #include <linux/irqflags.h>
+#include <linux/prefetch.h>
 #include <asm/barrier.h>
 
 #if defined(CONFIG_CPU_SA1100) || defined(CONFIG_CPU_SA110)
@@ -35,6 +36,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size
 #endif
 
 	smp_mb();
+	prefetchw((const void *)ptr);
 
 	switch (size) {
 #if __LINUX_ARM_ARCH__ >= 6
@@ -138,6 +140,8 @@ static inline unsigned long __cmpxchg(volatile void *ptr, unsigned long old,
 {
 	unsigned long oldval, res;
 
+	prefetchw((const void *)ptr);
+
 	switch (size) {
 #ifndef CONFIG_CPU_V6	/* min ARCH >= ARMv6K */
 	case 1:
@@ -230,6 +234,8 @@ static inline unsigned long long __cmpxchg64(unsigned long long *ptr,
 	unsigned long long oldval;
 	unsigned long res;
 
+	prefetchw(ptr);
+
 	__asm__ __volatile__(
 "1:	ldrexd		%1, %H1, [%3]\n"
 "	teq		%1, %4\n"

arch/arm/include/asm/cputype.h

@@ -71,6 +71,7 @@
 #define ARM_CPU_PART_CORTEX_A5		0xC050
 #define ARM_CPU_PART_CORTEX_A15		0xC0F0
 #define ARM_CPU_PART_CORTEX_A7		0xC070
+#define ARM_CPU_PART_CORTEX_A12		0xC0D0
 
 #define ARM_CPU_XSCALE_ARCH_MASK	0xe000
 #define ARM_CPU_XSCALE_ARCH_V1		0x2000

arch/arm/include/asm/floppy.h

@@ -25,7 +25,7 @@
 
 #define fd_inb(port)		inb((port))
 #define fd_request_irq()	request_irq(IRQ_FLOPPYDISK,floppy_interrupt,\
-					    IRQF_DISABLED,"floppy",NULL)
+					    0,"floppy",NULL)
 #define fd_free_irq()		free_irq(IRQ_FLOPPYDISK,NULL)
 #define fd_disable_irq()	disable_irq(IRQ_FLOPPYDISK)
 #define fd_enable_irq()		enable_irq(IRQ_FLOPPYDISK)

arch/arm/include/asm/futex.h

@@ -3,11 +3,6 @@
 
 #ifdef __KERNEL__
 
-#if defined(CONFIG_CPU_USE_DOMAINS) && defined(CONFIG_SMP)
-/* ARM doesn't provide unprivileged exclusive memory accessors */
-#include <asm-generic/futex.h>
-#else
-
 #include <linux/futex.h>
 #include <linux/uaccess.h>
 #include <asm/errno.h>
@@ -28,6 +23,7 @@
 
 #define __futex_atomic_op(insn, ret, oldval, tmp, uaddr, oparg)	\
 	smp_mb();						\
+	prefetchw(uaddr);					\
 	__asm__ __volatile__(					\
 	"1:	ldrex	%1, [%3]\n"				\
 	"	" insn "\n"					\
@@ -51,6 +47,8 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 		return -EFAULT;
 
 	smp_mb();
+	/* Prefetching cannot fault */
+	prefetchw(uaddr);
 	__asm__ __volatile__("@futex_atomic_cmpxchg_inatomic\n"
 	"1:	ldrex	%1, [%4]\n"
 	"	teq	%1, %2\n"
@@ -164,6 +162,5 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 	return ret;
 }
 
-#endif /* !(CPU_USE_DOMAINS && SMP) */
 #endif /* __KERNEL__ */
 #endif /* _ASM_ARM_FUTEX_H */

arch/arm/include/asm/hw_breakpoint.h

@@ -51,6 +51,7 @@ static inline void decode_ctrl_reg(u32 reg,
 #define ARM_DEBUG_ARCH_V7_ECP14	3
 #define ARM_DEBUG_ARCH_V7_MM	4
 #define ARM_DEBUG_ARCH_V7_1	5
+#define ARM_DEBUG_ARCH_V8	6
 
 /* Breakpoint */
 #define ARM_BREAKPOINT_EXECUTE	0

arch/arm/include/asm/hwcap.h

@@ -9,6 +9,7 @@
  * instruction set this cpu supports.
  */
 #define ELF_HWCAP	(elf_hwcap)
-extern unsigned int elf_hwcap;
+#define ELF_HWCAP2	(elf_hwcap2)
+extern unsigned int elf_hwcap, elf_hwcap2;
 #endif
 #endif

arch/arm/include/asm/jump_label.h

@@ -4,7 +4,6 @@
 #ifdef __KERNEL__
 
 #include <linux/types.h>
-#include <asm/system.h>
 
 #define JUMP_LABEL_NOP_SIZE 4
 

arch/arm/include/asm/kprobes.h

@@ -18,7 +18,7 @@
 
 #include <linux/types.h>
 #include <linux/ptrace.h>
-#include <linux/percpu.h>
+#include <linux/notifier.h>
 
 #define __ARCH_WANT_KPROBES_INSN_SLOT
 #define MAX_INSN_SIZE			2
@@ -28,21 +28,10 @@
 #define kretprobe_blacklist_size	0
 
 typedef u32 kprobe_opcode_t;
-
 struct kprobe;
-typedef void (kprobe_insn_handler_t)(struct kprobe *, struct pt_regs *);
-typedef unsigned long (kprobe_check_cc)(unsigned long);
-typedef void (kprobe_insn_singlestep_t)(struct kprobe *, struct pt_regs *);
-typedef void (kprobe_insn_fn_t)(void);
+#include <asm/probes.h>
 
-/* Architecture specific copy of original instruction. */
-struct arch_specific_insn {
-	kprobe_opcode_t			*insn;
-	kprobe_insn_handler_t		*insn_handler;
-	kprobe_check_cc			*insn_check_cc;
-	kprobe_insn_singlestep_t	*insn_singlestep;
-	kprobe_insn_fn_t		*insn_fn;
-};
+#define	arch_specific_insn	arch_probes_insn
 
 struct prev_kprobe {
 	struct kprobe *kp;

arch/arm/include/asm/memory.h

@@ -166,9 +166,17 @@
  * Physical vs virtual RAM address space conversion.  These are
  * private definitions which should NOT be used outside memory.h
  * files.  Use virt_to_phys/phys_to_virt/__pa/__va instead.
+ *
+ * PFNs are used to describe any physical page; this means
+ * PFN 0 == physical address 0.
  */
-#ifndef __virt_to_phys
-#ifdef CONFIG_ARM_PATCH_PHYS_VIRT
+#if defined(__virt_to_phys)
+#define PHYS_OFFSET	PLAT_PHYS_OFFSET
+#define PHYS_PFN_OFFSET	((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
+
+#define virt_to_pfn(kaddr) (__pa(kaddr) >> PAGE_SHIFT)
+
+#elif defined(CONFIG_ARM_PATCH_PHYS_VIRT)
 
 /*
  * Constants used to force the right instruction encodings and shifts
@@ -177,12 +185,17 @@
 #define __PV_BITS_31_24	0x81000000
 #define __PV_BITS_7_0	0x81
 
-extern u64 __pv_phys_offset;
+extern unsigned long __pv_phys_pfn_offset;
 extern u64 __pv_offset;
 extern void fixup_pv_table(const void *, unsigned long);
 extern const void *__pv_table_begin, *__pv_table_end;
 
-#define PHYS_OFFSET __pv_phys_offset
+#define PHYS_OFFSET	((phys_addr_t)__pv_phys_pfn_offset << PAGE_SHIFT)
+#define PHYS_PFN_OFFSET	(__pv_phys_pfn_offset)
+
+#define virt_to_pfn(kaddr) \
+	((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \
+	 PHYS_PFN_OFFSET)
 
 #define __pv_stub(from,to,instr,type)			\
 	__asm__("@ __pv_stub\n"				\
@@ -243,6 +256,7 @@ static inline unsigned long __phys_to_virt(phys_addr_t x)
 #else
 
 #define PHYS_OFFSET	PLAT_PHYS_OFFSET
+#define PHYS_PFN_OFFSET	((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
 
 static inline phys_addr_t __virt_to_phys(unsigned long x)
 {
@@ -254,18 +268,11 @@ static inline unsigned long __phys_to_virt(phys_addr_t x)
 	return x - PHYS_OFFSET + PAGE_OFFSET;
 }
 
-#endif
-#endif
+#define virt_to_pfn(kaddr) \
+	((((unsigned long)(kaddr) - PAGE_OFFSET) >> PAGE_SHIFT) + \
+	 PHYS_PFN_OFFSET)
 
-/*
- * PFNs are used to describe any physical page; this means
- * PFN 0 == physical address 0.
- *
- * This is the PFN of the first RAM page in the kernel
- * direct-mapped view.  We assume this is the first page
- * of RAM in the mem_map as well.
- */
-#define PHYS_PFN_OFFSET	((unsigned long)(PHYS_OFFSET >> PAGE_SHIFT))
+#endif
 
 /*
  * These are *only* valid on the kernel direct mapped RAM memory.
@@ -343,9 +350,9 @@ static inline __deprecated void *bus_to_virt(unsigned long x)
  */
 #define ARCH_PFN_OFFSET		PHYS_PFN_OFFSET
 
-#define virt_to_page(kaddr)	pfn_to_page(__pa(kaddr) >> PAGE_SHIFT)
+#define virt_to_page(kaddr)	pfn_to_page(virt_to_pfn(kaddr))
 #define virt_addr_valid(kaddr)	(((unsigned long)(kaddr) >= PAGE_OFFSET && (unsigned long)(kaddr) < (unsigned long)high_memory) \
-					&& pfn_valid(__pa(kaddr) >> PAGE_SHIFT) )
+					&& pfn_valid(virt_to_pfn(kaddr)))
 
 #endif
 

arch/arm/include/asm/pgtable-2level.h

@@ -140,6 +140,7 @@
 #define L_PTE_MT_DEV_NONSHARED	(_AT(pteval_t, 0x0c) << 2)	/* 1100 */
 #define L_PTE_MT_DEV_WC		(_AT(pteval_t, 0x09) << 2)	/* 1001 */
 #define L_PTE_MT_DEV_CACHED	(_AT(pteval_t, 0x0b) << 2)	/* 1011 */
+#define L_PTE_MT_VECTORS	(_AT(pteval_t, 0x0f) << 2)	/* 1111 */
 #define L_PTE_MT_MASK		(_AT(pteval_t, 0x0f) << 2)
 
 #ifndef __ASSEMBLY__

arch/arm/include/asm/pgtable.h

@@ -216,13 +216,16 @@ static inline pte_t *pmd_page_vaddr(pmd_t pmd)
 
 #define pte_none(pte)		(!pte_val(pte))
 #define pte_present(pte)	(pte_val(pte) & L_PTE_PRESENT)
+#define pte_valid(pte)		(pte_val(pte) & L_PTE_VALID)
+#define pte_accessible(mm, pte)	(mm_tlb_flush_pending(mm) ? pte_present(pte) : pte_valid(pte))
 #define pte_write(pte)		(!(pte_val(pte) & L_PTE_RDONLY))
 #define pte_dirty(pte)		(pte_val(pte) & L_PTE_DIRTY)
 #define pte_young(pte)		(pte_val(pte) & L_PTE_YOUNG)
 #define pte_exec(pte)		(!(pte_val(pte) & L_PTE_XN))
 #define pte_special(pte)	(0)
 
-#define pte_present_user(pte)  (pte_present(pte) && (pte_val(pte) & L_PTE_USER))
+#define pte_valid_user(pte)	\
+	(pte_valid(pte) && (pte_val(pte) & L_PTE_USER) && pte_young(pte))
 
 #if __LINUX_ARM_ARCH__ < 6
 static inline void __sync_icache_dcache(pte_t pteval)
@@ -237,7 +240,7 @@ static inline void set_pte_at(struct mm_struct *mm, unsigned long addr,
 {
 	unsigned long ext = 0;
 
-	if (addr < TASK_SIZE && pte_present_user(pteval)) {
+	if (addr < TASK_SIZE && pte_valid_user(pteval)) {
 		__sync_icache_dcache(pteval);
 		ext |= PTE_EXT_NG;
 	}

arch/arm/include/asm/pmu.h

@@ -71,6 +71,8 @@ struct arm_pmu {
 	void		(*disable)(struct perf_event *event);
 	int		(*get_event_idx)(struct pmu_hw_events *hw_events,
 					 struct perf_event *event);
+	void		(*clear_event_idx)(struct pmu_hw_events *hw_events,
+					 struct perf_event *event);
 	int		(*set_event_filter)(struct hw_perf_event *evt,
 					    struct perf_event_attr *attr);
 	u32		(*read_counter)(struct perf_event *event);

arch/arm/include/asm/probes.h

+/*
+ * arch/arm/include/asm/probes.h
+ *
+ * Original contents copied from arch/arm/include/asm/kprobes.h
+ * which contains the following notice...
+ *
+ * Copyright (C) 2006, 2007 Motorola Inc.
+ *
+ * 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.
+ *
+ * This program is distributed in the hope that it will be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
+ * General Public License for more details.
+ */
+
+#ifndef _ASM_PROBES_H
+#define _ASM_PROBES_H
+
+typedef u32 probes_opcode_t;
+
+struct arch_probes_insn;
+typedef void (probes_insn_handler_t)(probes_opcode_t,
+				     struct arch_probes_insn *,
+				     struct pt_regs *);
+typedef unsigned long (probes_check_cc)(unsigned long);
+typedef void (probes_insn_singlestep_t)(probes_opcode_t,
+					struct arch_probes_insn *,
+					struct pt_regs *);
+typedef void (probes_insn_fn_t)(void);
+
+/* Architecture specific copy of original instruction. */
+struct arch_probes_insn {
+	probes_opcode_t			*insn;
+	probes_insn_handler_t		*insn_handler;
+	probes_check_cc			*insn_check_cc;
+	probes_insn_singlestep_t	*insn_singlestep;
+	probes_insn_fn_t		*insn_fn;
+};
+
+#endif

arch/arm/include/asm/ptrace.h

@@ -27,9 +27,13 @@ struct pt_regs {
 #define thumb_mode(regs) (0)
 #endif
 
+#ifndef CONFIG_CPU_V7M
 #define isa_mode(regs) \
-	((((regs)->ARM_cpsr & PSR_J_BIT) >> 23) | \
-	 (((regs)->ARM_cpsr & PSR_T_BIT) >> 5))
+	((((regs)->ARM_cpsr & PSR_J_BIT) >> (__ffs(PSR_J_BIT) - 1)) | \
+	 (((regs)->ARM_cpsr & PSR_T_BIT) >> (__ffs(PSR_T_BIT))))
+#else
+#define isa_mode(regs) 1 /* Thumb */
+#endif
 
 #define processor_mode(regs) \
 	((regs)->ARM_cpsr & MODE_MASK)
@@ -80,6 +84,12 @@ static inline long regs_return_value(struct pt_regs *regs)
 
 #define instruction_pointer(regs)	(regs)->ARM_pc
 
+static inline void instruction_pointer_set(struct pt_regs *regs,
+					   unsigned long val)
+{
+	instruction_pointer(regs) = val;
+}
+
 #ifdef CONFIG_SMP
 extern unsigned long profile_pc(struct pt_regs *regs);
 #else

arch/arm/include/asm/sync_bitops.h

@@ -2,7 +2,6 @@
 #define __ASM_SYNC_BITOPS_H__
 
 #include <asm/bitops.h>
-#include <asm/system.h>
 
 /* sync_bitops functions are equivalent to the SMP implementation of the
  * original functions, independently from CONFIG_SMP being defined.

arch/arm/include/asm/system.h

-/* FILE TO BE DELETED. DO NOT ADD STUFF HERE! */
-#include <asm/barrier.h>
-#include <asm/compiler.h>
-#include <asm/cmpxchg.h>
-#include <asm/switch_to.h>
-#include <asm/system_info.h>
-#include <asm/system_misc.h>

arch/arm/include/asm/thread_info.h

@@ -153,6 +153,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define TIF_SIGPENDING		0
 #define TIF_NEED_RESCHED	1
 #define TIF_NOTIFY_RESUME	2	/* callback before returning to user */
+#define TIF_UPROBE		7
 #define TIF_SYSCALL_TRACE	8
 #define TIF_SYSCALL_AUDIT	9
 #define TIF_SYSCALL_TRACEPOINT	10
@@ -165,6 +166,7 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 #define _TIF_SIGPENDING		(1 << TIF_SIGPENDING)
 #define _TIF_NEED_RESCHED	(1 << TIF_NEED_RESCHED)
 #define _TIF_NOTIFY_RESUME	(1 << TIF_NOTIFY_RESUME)
+#define _TIF_UPROBE		(1 << TIF_UPROBE)
 #define _TIF_SYSCALL_TRACE	(1 << TIF_SYSCALL_TRACE)
 #define _TIF_SYSCALL_AUDIT	(1 << TIF_SYSCALL_AUDIT)
 #define _TIF_SYSCALL_TRACEPOINT	(1 << TIF_SYSCALL_TRACEPOINT)
@@ -178,7 +180,8 @@ extern int vfp_restore_user_hwstate(struct user_vfp __user *,
 /*
  * Change these and you break ASM code in entry-common.S
  */
-#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | _TIF_NOTIFY_RESUME)
+#define _TIF_WORK_MASK		(_TIF_NEED_RESCHED | _TIF_SIGPENDING | \
+				 _TIF_NOTIFY_RESUME | _TIF_UPROBE)
 
 #endif /* __KERNEL__ */
 #endif /* __ASM_ARM_THREAD_INFO_H */

arch/arm/include/asm/uaccess.h

@@ -19,7 +19,7 @@
 #include <asm/unified.h>
 #include <asm/compiler.h>
 
-#if __LINUX_ARM_ARCH__ < 6
+#ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 #include <asm-generic/uaccess-unaligned.h>
 #else
 #define __get_user_unaligned __get_user

arch/arm/include/asm/unistd.h

@@ -48,6 +48,5 @@
  */
 #define __IGNORE_fadvise64_64
 #define __IGNORE_migrate_pages
-#define __IGNORE_kcmp
 
 #endif /* __ASM_ARM_UNISTD_H */

arch/arm/include/asm/uprobes.h

+/*
+ * Copyright (C) 2012 Rabin Vincent <rabin at rab.in>
+ *
+ * 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_UPROBES_H
+#define _ASM_UPROBES_H
+
+#include <asm/probes.h>
+#include <asm/opcodes.h>
+
+typedef u32 uprobe_opcode_t;
+
+#define MAX_UINSN_BYTES		4
+#define UPROBE_XOL_SLOT_BYTES	64
+
+#define UPROBE_SWBP_ARM_INSN	0xe7f001f9
+#define UPROBE_SS_ARM_INSN	0xe7f001fa
+#define UPROBE_SWBP_INSN	__opcode_to_mem_arm(UPROBE_SWBP_ARM_INSN)
+#define UPROBE_SWBP_INSN_SIZE	4
+
+struct arch_uprobe_task {
+	u32 backup;
+	unsigned long	saved_trap_no;
+};
+
+struct arch_uprobe {
+	u8 insn[MAX_UINSN_BYTES];
+	unsigned long ixol[2];
+	uprobe_opcode_t bpinsn;
+	bool simulate;
+	u32 pcreg;
+	void (*prehandler)(struct arch_uprobe *auprobe,
+			   struct arch_uprobe_task *autask,
+			   struct pt_regs *regs);
+	void (*posthandler)(struct arch_uprobe *auprobe,
+			    struct arch_uprobe_task *autask,
+			    struct pt_regs *regs);
+	struct arch_probes_insn asi;
+};
+
+#endif

arch/arm/include/uapi/asm/hwcap.h

@@ -28,4 +28,13 @@
 #define HWCAP_LPAE	(1 << 20)
 #define HWCAP_EVTSTRM	(1 << 21)
 
+/*
+ * HWCAP2 flags - for elf_hwcap2 (in kernel) and AT_HWCAP2
+ */
+#define HWCAP2_AES	(1 << 0)
+#define HWCAP2_PMULL	(1 << 1)
+#define HWCAP2_SHA1	(1 << 2)
+#define HWCAP2_SHA2	(1 << 3)
+#define HWCAP2_CRC32	(1 << 4)
+
 #endif /* _UAPI__ASMARM_HWCAP_H */

arch/arm/kernel/Makefile

@@ -50,11 +50,12 @@ obj-$(CONFIG_DYNAMIC_FTRACE)	+= ftrace.o insn.o
 obj-$(CONFIG_FUNCTION_GRAPH_TRACER)	+= ftrace.o insn.o
 obj-$(CONFIG_JUMP_LABEL)	+= jump_label.o insn.o patch.o
 obj-$(CONFIG_KEXEC)		+= machine_kexec.o relocate_kernel.o
-obj-$(CONFIG_KPROBES)		+= kprobes.o kprobes-common.o patch.o
+obj-$(CONFIG_UPROBES)		+= probes.o probes-arm.o uprobes.o uprobes-arm.o
+obj-$(CONFIG_KPROBES)		+= probes.o kprobes.o kprobes-common.o patch.o
 ifdef CONFIG_THUMB2_KERNEL
-obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o
+obj-$(CONFIG_KPROBES)		+= kprobes-thumb.o probes-thumb.o
 else
-obj-$(CONFIG_KPROBES)		+= kprobes-arm.o
+obj-$(CONFIG_KPROBES)		+= kprobes-arm.o probes-arm.o
 endif
 obj-$(CONFIG_ARM_KPROBES_TEST)	+= test-kprobes.o
 test-kprobes-objs		:= kprobes-test.o

arch/arm/kernel/armksyms.c

@@ -158,6 +158,6 @@ EXPORT_SYMBOL(__gnu_mcount_nc);
 #endif
 
 #ifdef CONFIG_ARM_PATCH_PHYS_VIRT
-EXPORT_SYMBOL(__pv_phys_offset);
+EXPORT_SYMBOL(__pv_phys_pfn_offset);
 EXPORT_SYMBOL(__pv_offset);
 #endif

arch/arm/kernel/bios32.c

@@ -605,41 +605,10 @@ resource_size_t pcibios_align_resource(void *data, const struct resource *res,
  */
 int pcibios_enable_device(struct pci_dev *dev, int mask)
 {
-	u16 cmd, old_cmd;
-	int idx;
-	struct resource *r;
-
-	pci_read_config_word(dev, PCI_COMMAND, &cmd);
-	old_cmd = cmd;
-	for (idx = 0; idx < 6; idx++) {
-		/* Only set up the requested stuff */
-		if (!(mask & (1 << idx)))
-			continue;
-
-		r = dev->resource + idx;
-		if (!r->start && r->end) {
-			printk(KERN_ERR "PCI: Device %s not available because"
-			       " of resource collisions\n", pci_name(dev));
-			return -EINVAL;
-		}
-		if (r->flags & IORESOURCE_IO)
-			cmd |= PCI_COMMAND_IO;
-		if (r->flags & IORESOURCE_MEM)
-			cmd |= PCI_COMMAND_MEMORY;
-	}
+	if (pci_has_flag(PCI_PROBE_ONLY))
+		return 0;
 
-	/*
-	 * Bridges (eg, cardbus bridges) need to be fully enabled
-	 */
-	if ((dev->class >> 16) == PCI_BASE_CLASS_BRIDGE)
-		cmd |= PCI_COMMAND_IO | PCI_COMMAND_MEMORY;
-
-	if (cmd != old_cmd) {
-		printk("PCI: enabling device %s (%04x -> %04x)\n",
-		       pci_name(dev), old_cmd, cmd);
-		pci_write_config_word(dev, PCI_COMMAND, cmd);
-	}
-	return 0;
+	return pci_enable_resources(dev, mask);
 }
 
 int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma,

arch/arm/kernel/head.S

@@ -584,9 +584,10 @@ __fixup_pv_table:
 	subs	r3, r0, r3	@ PHYS_OFFSET - PAGE_OFFSET
 	add	r4, r4, r3	@ adjust table start address
 	add	r5, r5, r3	@ adjust table end address
-	add	r6, r6, r3	@ adjust __pv_phys_offset address
+	add	r6, r6, r3	@ adjust __pv_phys_pfn_offset address
 	add	r7, r7, r3	@ adjust __pv_offset address
-	str	r8, [r6, #LOW_OFFSET]	@ save computed PHYS_OFFSET to __pv_phys_offset
+	mov	r0, r8, lsr #12	@ convert to PFN
+	str	r0, [r6, #LOW_OFFSET]	@ save computed PHYS_OFFSET to __pv_phys_pfn_offset
 	strcc	ip, [r7, #HIGH_OFFSET]	@ save to __pv_offset high bits
 	mov	r6, r3, lsr #24	@ constant for add/sub instructions
 	teq	r3, r6, lsl #24 @ must be 16MiB aligned
@@ -600,7 +601,7 @@ ENDPROC(__fixup_pv_table)
 1:	.long	.
 	.long	__pv_table_begin
 	.long	__pv_table_end
-2:	.long	__pv_phys_offset
+2:	.long	__pv_phys_pfn_offset
 	.long	__pv_offset
 
 	.text
@@ -688,11 +689,11 @@ ENTRY(fixup_pv_table)
 ENDPROC(fixup_pv_table)
 
 	.data
-	.globl	__pv_phys_offset
-	.type	__pv_phys_offset, %object
-__pv_phys_offset:
-	.quad	0
-	.size	__pv_phys_offset, . -__pv_phys_offset
+	.globl	__pv_phys_pfn_offset
+	.type	__pv_phys_pfn_offset, %object
+__pv_phys_pfn_offset:
+	.word	0
+	.size	__pv_phys_pfn_offset, . -__pv_phys_pfn_offset
 
 	.globl	__pv_offset
 	.type	__pv_offset, %object

arch/arm/kernel/hw_breakpoint.c

@@ -167,7 +167,7 @@ static int debug_arch_supported(void)
 /* Can we determine the watchpoint access type from the fsr? */
 static int debug_exception_updates_fsr(void)
 {
-	return 0;
+	return get_debug_arch() >= ARM_DEBUG_ARCH_V8;
 }
 
 /* Determine number of WRP registers available. */
@@ -257,6 +257,7 @@ static int enable_monitor_mode(void)
 		break;
 	case ARM_DEBUG_ARCH_V7_ECP14:
 	case ARM_DEBUG_ARCH_V7_1:
+	case ARM_DEBUG_ARCH_V8:
 		ARM_DBG_WRITE(c0, c2, 2, (dscr | ARM_DSCR_MDBGEN));
 		isb();
 		break;

arch/arm/kernel/kprobes-test-arm.c

@@ -10,6 +10,7 @@
 
 #include <linux/kernel.h>
 #include <linux/module.h>
+#include <asm/system_info.h>
 
 #include "kprobes-test.h"
 

arch/arm/kernel/kprobes-test.c

@@ -201,10 +201,14 @@
 #include <linux/module.h>
 #include <linux/slab.h>
 #include <linux/kprobes.h>
-
+#include <linux/errno.h>
+#include <linux/stddef.h>
+#include <linux/bug.h>
 #include <asm/opcodes.h>
 
 #include "kprobes.h"
+#include "probes-arm.h"
+#include "probes-thumb.h"
 #include "kprobes-test.h"
 
 
@@ -1608,7 +1612,7 @@ static int __init run_all_tests(void)
 		goto out;
 
 	pr_info("ARM instruction simulation\n");
-	ret = run_test_cases(kprobe_arm_test_cases, kprobe_decode_arm_table);
+	ret = run_test_cases(kprobe_arm_test_cases, probes_decode_arm_table);
 	if (ret)
 		goto out;
 
@@ -1631,13 +1635,13 @@ static int __init run_all_tests(void)
 
 	pr_info("16-bit Thumb instruction simulation\n");
 	ret = run_test_cases(kprobe_thumb16_test_cases,
-				kprobe_decode_thumb16_table);
+				probes_decode_thumb16_table);
 	if (ret)
 		goto out;
 
 	pr_info("32-bit Thumb instruction simulation\n");
 	ret = run_test_cases(kprobe_thumb32_test_cases,
-				kprobe_decode_thumb32_table);
+				probes_decode_thumb32_table);
 	if (ret)
 		goto out;
 #endif

arch/arm/kernel/kprobes.c

@@ -27,8 +27,12 @@
 #include <linux/stringify.h>
 #include <asm/traps.h>
 #include <asm/cacheflush.h>
+#include <linux/percpu.h>
+#include <linux/bug.h>
 
 #include "kprobes.h"
+#include "probes-arm.h"
+#include "probes-thumb.h"
 #include "patch.h"
 
 #define MIN_STACK_SIZE(addr) 				\
@@ -54,6 +58,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	unsigned long addr = (unsigned long)p->addr;
 	bool thumb;
 	kprobe_decode_insn_t *decode_insn;
+	const union decode_action *actions;
 	int is;
 
 	if (in_exception_text(addr))
@@ -66,21 +71,25 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 	if (is_wide_instruction(insn)) {
 		insn <<= 16;
 		insn |= ((u16 *)addr)[1];
-		decode_insn = thumb32_kprobe_decode_insn;
-	} else
-		decode_insn = thumb16_kprobe_decode_insn;
+		decode_insn = thumb32_probes_decode_insn;
+		actions = kprobes_t32_actions;
+	} else {
+		decode_insn = thumb16_probes_decode_insn;
+		actions = kprobes_t16_actions;
+	}
 #else /* !CONFIG_THUMB2_KERNEL */
 	thumb = false;
 	if (addr & 0x3)
 		return -EINVAL;
 	insn = *p->addr;
-	decode_insn = arm_kprobe_decode_insn;
+	decode_insn = arm_probes_decode_insn;
+	actions = kprobes_arm_actions;
 #endif
 
 	p->opcode = insn;
 	p->ainsn.insn = tmp_insn;
 
-	switch ((*decode_insn)(insn, &p->ainsn)) {
+	switch ((*decode_insn)(insn, &p->ainsn, true, actions)) {
 	case INSN_REJECTED:	/* not supported */
 		return -EINVAL;
 
@@ -92,7 +101,7 @@ int __kprobes arch_prepare_kprobe(struct kprobe *p)
 			p->ainsn.insn[is] = tmp_insn[is];
 		flush_insns(p->ainsn.insn,
 				sizeof(p->ainsn.insn[0]) * MAX_INSN_SIZE);
-		p->ainsn.insn_fn = (kprobe_insn_fn_t *)
+		p->ainsn.insn_fn = (probes_insn_fn_t *)
 					((uintptr_t)p->ainsn.insn | thumb);
 		break;
 
@@ -197,7 +206,7 @@ singlestep_skip(struct kprobe *p, struct pt_regs *regs)
 static inline void __kprobes
 singlestep(struct kprobe *p, struct pt_regs *regs, struct kprobe_ctlblk *kcb)
 {
-	p->ainsn.insn_singlestep(p, regs);
+	p->ainsn.insn_singlestep(p->opcode, &p->ainsn, regs);
 }
 
 /*
@@ -607,7 +616,7 @@ static struct undef_hook kprobes_arm_break_hook = {
 
 int __init arch_init_kprobes()
 {
-	arm_kprobe_decode_init();
+	arm_probes_decode_init();
 #ifdef CONFIG_THUMB2_KERNEL
 	register_undef_hook(&kprobes_thumb16_break_hook);
 	register_undef_hook(&kprobes_thumb32_break_hook);

arch/arm/kernel/perf_event.c

@@ -16,6 +16,8 @@
 #include <linux/platform_device.h>
 #include <linux/pm_runtime.h>
 #include <linux/uaccess.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
 
 #include <asm/irq_regs.h>
 #include <asm/pmu.h>
@@ -205,6 +207,8 @@ armpmu_del(struct perf_event *event, int flags)
 	armpmu_stop(event, PERF_EF_UPDATE);
 	hw_events->events[idx] = NULL;
 	clear_bit(idx, hw_events->used_mask);
+	if (armpmu->clear_event_idx)
+		armpmu->clear_event_idx(hw_events, event);
 
 	perf_event_update_userpage(event);
 }
@@ -295,14 +299,27 @@ validate_group(struct perf_event *event)
 
 static irqreturn_t armpmu_dispatch_irq(int irq, void *dev)
 {
-	struct arm_pmu *armpmu = (struct arm_pmu *) dev;
-	struct platform_device *plat_device = armpmu->plat_device;
-	struct arm_pmu_platdata *plat = dev_get_platdata(&plat_device->dev);
+	struct arm_pmu *armpmu;
+	struct platform_device *plat_device;
+	struct arm_pmu_platdata *plat;
+	int ret;
+	u64 start_clock, finish_clock;
 
+	if (irq_is_percpu(irq))
+		dev = *(void **)dev;
+	armpmu = dev;
+	plat_device = armpmu->plat_device;
+	plat = dev_get_platdata(&plat_device->dev);
+
+	start_clock = sched_clock();
 	if (plat && plat->handle_irq)
-		return plat->handle_irq(irq, dev, armpmu->handle_irq);
+		ret = plat->handle_irq(irq, dev, armpmu->handle_irq);
 	else
-		return armpmu->handle_irq(irq, dev);
+		ret = armpmu->handle_irq(irq, dev);
+	finish_clock = sched_clock();
+
+	perf_sample_event_took(finish_clock - start_clock);
+	return ret;
 }
 
 static void

arch/arm/kernel/perf_event_cpu.c

@@ -25,6 +25,8 @@
 #include <linux/platform_device.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
+#include <linux/irq.h>
+#include <linux/irqdesc.h>
 
 #include <asm/cputype.h>
 #include <asm/irq_regs.h>
@@ -33,6 +35,7 @@
 /* Set at runtime when we know what CPU type we are. */
 static struct arm_pmu *cpu_pmu;
 
+static DEFINE_PER_CPU(struct arm_pmu *, percpu_pmu);
 static DEFINE_PER_CPU(struct perf_event * [ARMPMU_MAX_HWEVENTS], hw_events);
 static DEFINE_PER_CPU(unsigned long [BITS_TO_LONGS(ARMPMU_MAX_HWEVENTS)], used_mask);
 static DEFINE_PER_CPU(struct pmu_hw_events, cpu_hw_events);
@@ -71,6 +74,26 @@ static struct pmu_hw_events *cpu_pmu_get_cpu_events(void)
 	return this_cpu_ptr(&cpu_hw_events);
 }
 
+static void cpu_pmu_enable_percpu_irq(void *data)
+{
+	struct arm_pmu *cpu_pmu = data;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int irq = platform_get_irq(pmu_device, 0);
+
+	enable_percpu_irq(irq, IRQ_TYPE_NONE);
+	cpumask_set_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
+}
+
+static void cpu_pmu_disable_percpu_irq(void *data)
+{
+	struct arm_pmu *cpu_pmu = data;
+	struct platform_device *pmu_device = cpu_pmu->plat_device;
+	int irq = platform_get_irq(pmu_device, 0);
+
+	cpumask_clear_cpu(smp_processor_id(), &cpu_pmu->active_irqs);
+	disable_percpu_irq(irq);
+}
+
 static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 {
 	int i, irq, irqs;
@@ -78,12 +101,18 @@ static void cpu_pmu_free_irq(struct arm_pmu *cpu_pmu)
 
 	irqs = min(pmu_device->num_resources, num_possible_cpus());
 
-	for (i = 0; i < irqs; ++i) {
-		if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
-			continue;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq >= 0)
-			free_irq(irq, cpu_pmu);
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		on_each_cpu(cpu_pmu_disable_percpu_irq, cpu_pmu, 1);
+		free_percpu_irq(irq, &percpu_pmu);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			if (!cpumask_test_and_clear_cpu(i, &cpu_pmu->active_irqs))
+				continue;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq >= 0)
+				free_irq(irq, cpu_pmu);
+		}
 	}
 }
 
@@ -101,33 +130,44 @@ static int cpu_pmu_request_irq(struct arm_pmu *cpu_pmu, irq_handler_t handler)
 		return -ENODEV;
 	}
 
-	for (i = 0; i < irqs; ++i) {
-		err = 0;
-		irq = platform_get_irq(pmu_device, i);
-		if (irq < 0)
-			continue;
-
-		/*
-		 * If we have a single PMU interrupt that we can't shift,
-		 * assume that we're running on a uniprocessor machine and
-		 * continue. Otherwise, continue without this interrupt.
-		 */
-		if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
-			pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
-				    irq, i);
-			continue;
-		}
-
-		err = request_irq(irq, handler,
-				  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
-				  cpu_pmu);
+	irq = platform_get_irq(pmu_device, 0);
+	if (irq >= 0 && irq_is_percpu(irq)) {
+		err = request_percpu_irq(irq, handler, "arm-pmu", &percpu_pmu);
 		if (err) {
 			pr_err("unable to request IRQ%d for ARM PMU counters\n",
 				irq);
 			return err;
 		}
-
-		cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		on_each_cpu(cpu_pmu_enable_percpu_irq, cpu_pmu, 1);
+	} else {
+		for (i = 0; i < irqs; ++i) {
+			err = 0;
+			irq = platform_get_irq(pmu_device, i);
+			if (irq < 0)
+				continue;
+
+			/*
+			 * If we have a single PMU interrupt that we can't shift,
+			 * assume that we're running on a uniprocessor machine and
+			 * continue. Otherwise, continue without this interrupt.
+			 */
+			if (irq_set_affinity(irq, cpumask_of(i)) && irqs > 1) {
+				pr_warning("unable to set irq affinity (irq=%d, cpu=%u)\n",
+					    irq, i);
+				continue;
+			}
+
+			err = request_irq(irq, handler,
+					  IRQF_NOBALANCING | IRQF_NO_THREAD, "arm-pmu",
+					  cpu_pmu);
+			if (err) {
+				pr_err("unable to request IRQ%d for ARM PMU counters\n",
+					irq);
+				return err;
+			}
+
+			cpumask_set_cpu(i, &cpu_pmu->active_irqs);
+		}
 	}
 
 	return 0;
@@ -141,6 +181,7 @@ static void cpu_pmu_init(struct arm_pmu *cpu_pmu)
 		events->events = per_cpu(hw_events, cpu);
 		events->used_mask = per_cpu(used_mask, cpu);
 		raw_spin_lock_init(&events->pmu_lock);
+		per_cpu(percpu_pmu, cpu) = cpu_pmu;
 	}
 
 	cpu_pmu->get_hw_events	= cpu_pmu_get_cpu_events;
@@ -181,6 +222,7 @@ static struct notifier_block cpu_pmu_hotplug_notifier = {
  */
 static struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,cortex-a15-pmu",	.data = armv7_a15_pmu_init},
+	{.compatible = "arm,cortex-a12-pmu",	.data = armv7_a12_pmu_init},
 	{.compatible = "arm,cortex-a9-pmu",	.data = armv7_a9_pmu_init},
 	{.compatible = "arm,cortex-a8-pmu",	.data = armv7_a8_pmu_init},
 	{.compatible = "arm,cortex-a7-pmu",	.data = armv7_a7_pmu_init},
@@ -188,6 +230,7 @@ static struct of_device_id cpu_pmu_of_device_ids[] = {
 	{.compatible = "arm,arm11mpcore-pmu",	.data = armv6mpcore_pmu_init},
 	{.compatible = "arm,arm1176-pmu",	.data = armv6pmu_init},
 	{.compatible = "arm,arm1136-pmu",	.data = armv6pmu_init},
+	{.compatible = "qcom,krait-pmu",	.data = krait_pmu_init},
 	{},
 };
 
@@ -225,15 +268,6 @@ static int probe_current_pmu(struct arm_pmu *pmu)
 		case ARM_CPU_PART_CORTEX_A9:
 			ret = armv7_a9_pmu_init(pmu);
 			break;
-		case ARM_CPU_PART_CORTEX_A5:
-			ret = armv7_a5_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A15:
-			ret = armv7_a15_pmu_init(pmu);
-			break;
-		case ARM_CPU_PART_CORTEX_A7:
-			ret = armv7_a7_pmu_init(pmu);
-			break;
 		}
 	/* Intel CPUs [xscale]. */
 	} else if (implementor == ARM_CPU_IMP_INTEL) {
@@ -270,6 +304,9 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		return -ENOMEM;
 	}
 
+	cpu_pmu = pmu;
+	cpu_pmu->plat_device = pdev;
+
 	if (node && (of_id = of_match_node(cpu_pmu_of_device_ids, pdev->dev.of_node))) {
 		init_fn = of_id->data;
 		ret = init_fn(pmu);
@@ -282,8 +319,6 @@ static int cpu_pmu_device_probe(struct platform_device *pdev)
 		goto out_free;
 	}
 
-	cpu_pmu = pmu;
-	cpu_pmu->plat_device = pdev;
 	cpu_pmu_init(cpu_pmu);
 	ret = armpmu_register(cpu_pmu, PERF_TYPE_RAW);
 

arch/arm/kernel/probes-arm.h

+/*
+ * arch/arm/kernel/probes-arm.h
+ *
+ * Copyright 2013 Linaro Ltd.
+ * Written by: David A. Long
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#ifndef _ARM_KERNEL_PROBES_ARM_H
+#define  _ARM_KERNEL_PROBES_ARM_H
+
+enum probes_arm_action {
+	PROBES_EMULATE_NONE,
+	PROBES_SIMULATE_NOP,
+	PROBES_PRELOAD_IMM,
+	PROBES_PRELOAD_REG,
+	PROBES_BRANCH_IMM,
+	PROBES_BRANCH_REG,
+	PROBES_MRS,
+	PROBES_CLZ,
+	PROBES_SATURATING_ARITHMETIC,
+	PROBES_MUL1,
+	PROBES_MUL2,
+	PROBES_SWP,
+	PROBES_LDRSTRD,
+	PROBES_LOAD,
+	PROBES_STORE,
+	PROBES_LOAD_EXTRA,
+	PROBES_STORE_EXTRA,
+	PROBES_MOV_IP_SP,
+	PROBES_DATA_PROCESSING_REG,
+	PROBES_DATA_PROCESSING_IMM,
+	PROBES_MOV_HALFWORD,
+	PROBES_SEV,
+	PROBES_WFE,
+	PROBES_SATURATE,
+	PROBES_REV,
+	PROBES_MMI,
+	PROBES_PACK,
+	PROBES_EXTEND,
+	PROBES_EXTEND_ADD,
+	PROBES_MUL_ADD_LONG,
+	PROBES_MUL_ADD,
+	PROBES_BITFIELD,
+	PROBES_BRANCH,
+	PROBES_LDMSTM,
+	NUM_PROBES_ARM_ACTIONS
+};
+
+void __kprobes simulate_bbl(probes_opcode_t opcode,
+	struct arch_probes_insn *asi, struct pt_regs *regs);
+void __kprobes simulate_blx1(probes_opcode_t opcode,
+	struct arch_probes_insn *asi, struct pt_regs *regs);
+void __kprobes simulate_blx2bx(probes_opcode_t opcode,
+	struct arch_probes_insn *asi, struct pt_regs *regs);
+void __kprobes simulate_mrs(probes_opcode_t opcode,
+	struct arch_probes_insn *asi, struct pt_regs *regs);
+void __kprobes simulate_mov_ipsp(probes_opcode_t opcode,
+	struct arch_probes_insn *asi, struct pt_regs *regs);
+
+extern const union decode_item probes_decode_arm_table[];
+
+enum probes_insn arm_probes_decode_insn(probes_opcode_t,
+		struct arch_probes_insn *, bool emulate,
+		const union decode_action *actions);
+
+#endif

arch/arm/kernel/probes-thumb.h

+/*
+ * arch/arm/kernel/probes-thumb.h
+ *
+ * Copyright 2013 Linaro Ltd.
+ * Written by: David A. Long
+ *
+ * The code contained herein is licensed under the GNU General Public
+ * License. You may obtain a copy of the GNU General Public License
+ * Version 2 or later at the following locations:
+ *
+ * http://www.opensource.org/licenses/gpl-license.html
+ * http://www.gnu.org/copyleft/gpl.html
+ */
+
+#ifndef _ARM_KERNEL_PROBES_THUMB_H
+#define  _ARM_KERNEL_PROBES_THUMB_H
+
+/*
+ * True if current instruction is in an IT block.
+ */
+#define in_it_block(cpsr)	((cpsr & 0x06000c00) != 0x00000000)
+
+/*
+ * Return the condition code to check for the currently executing instruction.
+ * This is in ITSTATE<7:4> which is in CPSR<15:12> but is only valid if
+ * in_it_block returns true.
+ */
+#define current_cond(cpsr)	((cpsr >> 12) & 0xf)
+
+enum probes_t32_action {
+	PROBES_T32_EMULATE_NONE,
+	PROBES_T32_SIMULATE_NOP,
+	PROBES_T32_LDMSTM,
+	PROBES_T32_LDRDSTRD,
+	PROBES_T32_TABLE_BRANCH,
+	PROBES_T32_TST,
+	PROBES_T32_CMP,
+	PROBES_T32_MOV,
+	PROBES_T32_ADDSUB,
+	PROBES_T32_LOGICAL,
+	PROBES_T32_ADDWSUBW_PC,
+	PROBES_T32_ADDWSUBW,
+	PROBES_T32_MOVW,
+	PROBES_T32_SAT,
+	PROBES_T32_BITFIELD,
+	PROBES_T32_SEV,
+	PROBES_T32_WFE,
+	PROBES_T32_MRS,
+	PROBES_T32_BRANCH_COND,
+	PROBES_T32_BRANCH,
+	PROBES_T32_PLDI,
+	PROBES_T32_LDR_LIT,
+	PROBES_T32_LDRSTR,
+	PROBES_T32_SIGN_EXTEND,
+	PROBES_T32_MEDIA,
+	PROBES_T32_REVERSE,
+	PROBES_T32_MUL_ADD,
+	PROBES_T32_MUL_ADD2,
+	PROBES_T32_MUL_ADD_LONG,
+	NUM_PROBES_T32_ACTIONS
+};
+
+enum probes_t16_action {
+	PROBES_T16_ADD_SP,
+	PROBES_T16_CBZ,
+	PROBES_T16_SIGN_EXTEND,
+	PROBES_T16_PUSH,
+	PROBES_T16_POP,
+	PROBES_T16_SEV,
+	PROBES_T16_WFE,
+	PROBES_T16_IT,
+	PROBES_T16_CMP,
+	PROBES_T16_ADDSUB,
+	PROBES_T16_LOGICAL,
+	PROBES_T16_BLX,
+	PROBES_T16_HIREGOPS,
+	PROBES_T16_LDR_LIT,
+	PROBES_T16_LDRHSTRH,
+	PROBES_T16_LDRSTR,
+	PROBES_T16_ADR,
+	PROBES_T16_LDMSTM,
+	PROBES_T16_BRANCH_COND,
+	PROBES_T16_BRANCH,
+	NUM_PROBES_T16_ACTIONS
+};
+
+extern const union decode_item probes_decode_thumb32_table[];
+extern const union decode_item probes_decode_thumb16_table[];
+
+enum probes_insn __kprobes
+thumb16_probes_decode_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+		bool emulate, const union decode_action *actions);
+enum probes_insn __kprobes
+thumb32_probes_decode_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+		bool emulate, const union decode_action *actions);
+
+#endif

arch/arm/kernel/process.c

@@ -47,14 +47,14 @@ unsigned long __stack_chk_guard __read_mostly;
 EXPORT_SYMBOL(__stack_chk_guard);
 #endif
 
-static const char *processor_modes[] = {
+static const char *processor_modes[] __maybe_unused = {
   "USER_26", "FIQ_26" , "IRQ_26" , "SVC_26" , "UK4_26" , "UK5_26" , "UK6_26" , "UK7_26" ,
   "UK8_26" , "UK9_26" , "UK10_26", "UK11_26", "UK12_26", "UK13_26", "UK14_26", "UK15_26",
   "USER_32", "FIQ_32" , "IRQ_32" , "SVC_32" , "UK4_32" , "UK5_32" , "UK6_32" , "ABT_32" ,
   "UK8_32" , "UK9_32" , "UK10_32", "UND_32" , "UK12_32", "UK13_32", "UK14_32", "SYS_32"
 };
 
-static const char *isa_modes[] = {
+static const char *isa_modes[] __maybe_unused = {
   "ARM" , "Thumb" , "Jazelle", "ThumbEE"
 };
 
@@ -270,12 +270,17 @@ void __show_regs(struct pt_regs *regs)
 	buf[3] = flags & PSR_V_BIT ? 'V' : 'v';
 	buf[4] = '\0';
 
+#ifndef CONFIG_CPU_V7M
 	printk("Flags: %s  IRQs o%s  FIQs o%s  Mode %s  ISA %s  Segment %s\n",
 		buf, interrupts_enabled(regs) ? "n" : "ff",
 		fast_interrupts_enabled(regs) ? "n" : "ff",
 		processor_modes[processor_mode(regs)],
 		isa_modes[isa_mode(regs)],
 		get_fs() == get_ds() ? "kernel" : "user");
+#else
+	printk("xPSR: %08lx\n", regs->ARM_cpsr);
+#endif
+
 #ifdef CONFIG_CPU_CP15
 	{
 		unsigned int ctrl;

arch/arm/kernel/setup.c

@@ -100,6 +100,9 @@ EXPORT_SYMBOL(system_serial_high);
 unsigned int elf_hwcap __read_mostly;
 EXPORT_SYMBOL(elf_hwcap);
 
+unsigned int elf_hwcap2 __read_mostly;
+EXPORT_SYMBOL(elf_hwcap2);
+
 
 #ifdef MULTI_CPU
 struct processor processor __read_mostly;
@@ -1005,6 +1008,15 @@ static const char *hwcap_str[] = {
 	NULL
 };
 
+static const char *hwcap2_str[] = {
+	"aes",
+	"pmull",
+	"sha1",
+	"sha2",
+	"crc32",
+	NULL
+};
+
 static int c_show(struct seq_file *m, void *v)
 {
 	int i, j;
@@ -1028,6 +1040,10 @@ static int c_show(struct seq_file *m, void *v)
 			if (elf_hwcap & (1 << j))
 				seq_printf(m, "%s ", hwcap_str[j]);
 
+		for (j = 0; hwcap2_str[j]; j++)
+			if (elf_hwcap2 & (1 << j))
+				seq_printf(m, "%s ", hwcap2_str[j]);
+
 		seq_printf(m, "\nCPU implementer\t: 0x%02x\n", cpuid >> 24);
 		seq_printf(m, "CPU architecture: %s\n",
 			   proc_arch[cpu_architecture()]);

arch/arm/kernel/signal.c

@@ -13,6 +13,7 @@
 #include <linux/personality.h>
 #include <linux/uaccess.h>
 #include <linux/tracehook.h>
+#include <linux/uprobes.h>
 
 #include <asm/elf.h>
 #include <asm/cacheflush.h>
@@ -590,6 +591,9 @@ do_work_pending(struct pt_regs *regs, unsigned int thread_flags, int syscall)
 					return restart;
 				}
 				syscall = 0;
+			} else if (thread_flags & _TIF_UPROBE) {
+				clear_thread_flag(TIF_UPROBE);
+				uprobe_notify_resume(regs);
 			} else {
 				clear_thread_flag(TIF_NOTIFY_RESUME);
 				tracehook_notify_resume(regs);

arch/arm/kernel/unwind.c

@@ -68,6 +68,12 @@ EXPORT_SYMBOL(__aeabi_unwind_cpp_pr2);
 struct unwind_ctrl_block {
 	unsigned long vrs[16];		/* virtual register set */
 	const unsigned long *insn;	/* pointer to the current instructions word */
+	unsigned long sp_high;		/* highest value of sp allowed */
+	/*
+	 * 1 : check for stack overflow for each register pop.
+	 * 0 : save overhead if there is plenty of stack remaining.
+	 */
+	int check_each_pop;
 	int entries;			/* number of entries left to interpret */
 	int byte;			/* current byte number in the instructions word */
 };
@@ -235,12 +241,85 @@ static unsigned long unwind_get_byte(struct unwind_ctrl_block *ctrl)
 	return ret;
 }
 
+/* Before poping a register check whether it is feasible or not */
+static int unwind_pop_register(struct unwind_ctrl_block *ctrl,
+				unsigned long **vsp, unsigned int reg)
+{
+	if (unlikely(ctrl->check_each_pop))
+		if (*vsp >= (unsigned long *)ctrl->sp_high)
+			return -URC_FAILURE;
+
+	ctrl->vrs[reg] = *(*vsp)++;
+	return URC_OK;
+}
+
+/* Helper functions to execute the instructions */
+static int unwind_exec_pop_subset_r4_to_r13(struct unwind_ctrl_block *ctrl,
+						unsigned long mask)
+{
+	unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+	int load_sp, reg = 4;
+
+	load_sp = mask & (1 << (13 - 4));
+	while (mask) {
+		if (mask & 1)
+			if (unwind_pop_register(ctrl, &vsp, reg))
+				return -URC_FAILURE;
+		mask >>= 1;
+		reg++;
+	}
+	if (!load_sp)
+		ctrl->vrs[SP] = (unsigned long)vsp;
+
+	return URC_OK;
+}
+
+static int unwind_exec_pop_r4_to_rN(struct unwind_ctrl_block *ctrl,
+					unsigned long insn)
+{
+	unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+	int reg;
+
+	/* pop R4-R[4+bbb] */
+	for (reg = 4; reg <= 4 + (insn & 7); reg++)
+		if (unwind_pop_register(ctrl, &vsp, reg))
+				return -URC_FAILURE;
+
+	if (insn & 0x80)
+		if (unwind_pop_register(ctrl, &vsp, 14))
+				return -URC_FAILURE;
+
+	ctrl->vrs[SP] = (unsigned long)vsp;
+
+	return URC_OK;
+}
+
+static int unwind_exec_pop_subset_r0_to_r3(struct unwind_ctrl_block *ctrl,
+						unsigned long mask)
+{
+	unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
+	int reg = 0;
+
+	/* pop R0-R3 according to mask */
+	while (mask) {
+		if (mask & 1)
+			if (unwind_pop_register(ctrl, &vsp, reg))
+				return -URC_FAILURE;
+		mask >>= 1;
+		reg++;
+	}
+	ctrl->vrs[SP] = (unsigned long)vsp;
+
+	return URC_OK;
+}
+
 /*
  * Execute the current unwind instruction.
  */
 static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 {
 	unsigned long insn = unwind_get_byte(ctrl);
+	int ret = URC_OK;
 
 	pr_debug("%s: insn = %08lx\n", __func__, insn);
 
@@ -250,8 +329,6 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		ctrl->vrs[SP] -= ((insn & 0x3f) << 2) + 4;
 	else if ((insn & 0xf0) == 0x80) {
 		unsigned long mask;
-		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
-		int load_sp, reg = 4;
 
 		insn = (insn << 8) | unwind_get_byte(ctrl);
 		mask = insn & 0x0fff;
@@ -261,29 +338,16 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 			return -URC_FAILURE;
 		}
 
-		/* pop R4-R15 according to mask */
-		load_sp = mask & (1 << (13 - 4));
-		while (mask) {
-			if (mask & 1)
-				ctrl->vrs[reg] = *vsp++;
-			mask >>= 1;
-			reg++;
-		}
-		if (!load_sp)
-			ctrl->vrs[SP] = (unsigned long)vsp;
+		ret = unwind_exec_pop_subset_r4_to_r13(ctrl, mask);
+		if (ret)
+			goto error;
 	} else if ((insn & 0xf0) == 0x90 &&
 		   (insn & 0x0d) != 0x0d)
 		ctrl->vrs[SP] = ctrl->vrs[insn & 0x0f];
 	else if ((insn & 0xf0) == 0xa0) {
-		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
-		int reg;
-
-		/* pop R4-R[4+bbb] */
-		for (reg = 4; reg <= 4 + (insn & 7); reg++)
-			ctrl->vrs[reg] = *vsp++;
-		if (insn & 0x80)
-			ctrl->vrs[14] = *vsp++;
-		ctrl->vrs[SP] = (unsigned long)vsp;
+		ret = unwind_exec_pop_r4_to_rN(ctrl, insn);
+		if (ret)
+			goto error;
 	} else if (insn == 0xb0) {
 		if (ctrl->vrs[PC] == 0)
 			ctrl->vrs[PC] = ctrl->vrs[LR];
@@ -291,8 +355,6 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 		ctrl->entries = 0;
 	} else if (insn == 0xb1) {
 		unsigned long mask = unwind_get_byte(ctrl);
-		unsigned long *vsp = (unsigned long *)ctrl->vrs[SP];
-		int reg = 0;
 
 		if (mask == 0 || mask & 0xf0) {
 			pr_warning("unwind: Spare encoding %04lx\n",
@@ -300,14 +362,9 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 			return -URC_FAILURE;
 		}
 
-		/* pop R0-R3 according to mask */
-		while (mask) {
-			if (mask & 1)
-				ctrl->vrs[reg] = *vsp++;
-			mask >>= 1;
-			reg++;
-		}
-		ctrl->vrs[SP] = (unsigned long)vsp;
+		ret = unwind_exec_pop_subset_r0_to_r3(ctrl, mask);
+		if (ret)
+			goto error;
 	} else if (insn == 0xb2) {
 		unsigned long uleb128 = unwind_get_byte(ctrl);
 
@@ -320,7 +377,8 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
 	pr_debug("%s: fp = %08lx sp = %08lx lr = %08lx pc = %08lx\n", __func__,
 		 ctrl->vrs[FP], ctrl->vrs[SP], ctrl->vrs[LR], ctrl->vrs[PC]);
 
-	return URC_OK;
+error:
+	return ret;
 }
 
 /*
@@ -329,13 +387,13 @@ static int unwind_exec_insn(struct unwind_ctrl_block *ctrl)
  */
 int unwind_frame(struct stackframe *frame)
 {
-	unsigned long high, low;
+	unsigned long low;
 	const struct unwind_idx *idx;
 	struct unwind_ctrl_block ctrl;
 
-	/* only go to a higher address on the stack */
+	/* store the highest address on the stack to avoid crossing it*/
 	low = frame->sp;
-	high = ALIGN(low, THREAD_SIZE);
+	ctrl.sp_high = ALIGN(low, THREAD_SIZE);
 
 	pr_debug("%s(pc = %08lx lr = %08lx sp = %08lx)\n", __func__,
 		 frame->pc, frame->lr, frame->sp);
@@ -382,11 +440,16 @@ int unwind_frame(struct stackframe *frame)
 		return -URC_FAILURE;
 	}
 
+	ctrl.check_each_pop = 0;
+
 	while (ctrl.entries > 0) {
-		int urc = unwind_exec_insn(&ctrl);
+		int urc;
+		if ((ctrl.sp_high - ctrl.vrs[SP]) < sizeof(ctrl.vrs))
+			ctrl.check_each_pop = 1;
+		urc = unwind_exec_insn(&ctrl);
 		if (urc < 0)
 			return urc;
-		if (ctrl.vrs[SP] < low || ctrl.vrs[SP] >= high)
+		if (ctrl.vrs[SP] < low || ctrl.vrs[SP] >= ctrl.sp_high)
 			return -URC_FAILURE;
 	}
 

arch/arm/kernel/uprobes.h

+/*
+ * Copyright (C) 2012 Rabin Vincent <rabin at rab.in>
+ *
+ * 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 __ARM_KERNEL_UPROBES_H
+#define __ARM_KERNEL_UPROBES_H
+
+enum probes_insn uprobe_decode_ldmstm(probes_opcode_t insn,
+				      struct arch_probes_insn *asi,
+				      const struct decode_header *d);
+
+enum probes_insn decode_ldr(probes_opcode_t insn,
+			    struct arch_probes_insn *asi,
+			    const struct decode_header *d);
+
+enum probes_insn
+decode_rd12rn16rm0rs8_rwflags(probes_opcode_t insn,
+			      struct arch_probes_insn *asi,
+			      const struct decode_header *d);
+
+enum probes_insn
+decode_wb_pc(probes_opcode_t insn, struct arch_probes_insn *asi,
+	     const struct decode_header *d, bool alu);
+
+enum probes_insn
+decode_pc_ro(probes_opcode_t insn, struct arch_probes_insn *asi,
+	     const struct decode_header *d);
+
+extern const union decode_action uprobes_probes_actions[];
+
+#endif

arch/arm/lib/bitops.h

@@ -37,6 +37,11 @@ UNWIND(	.fnstart	)
 	add	r1, r1, r0, lsl #2	@ Get word offset
 	mov	r3, r2, lsl r3		@ create mask
 	smp_dmb
+#if __LINUX_ARM_ARCH__ >= 7 && defined(CONFIG_SMP)
+	.arch_extension	mp
+	ALT_SMP(W(pldw)	[r1])
+	ALT_UP(W(nop))
+#endif
 1:	ldrex	r2, [r1]
 	ands	r0, r2, r3		@ save old value of bit
 	\instr	r2, r2, r3		@ toggle bit

arch/arm/lib/copy_template.S

@@ -197,24 +197,24 @@
 
 12:	PLD(	pld	[r1, #124]		)
 13:		ldr4w	r1, r4, r5, r6, r7, abort=19f
-		mov	r3, lr, pull #\pull
+		mov	r3, lr, lspull #\pull
 		subs	r2, r2, #32
 		ldr4w	r1, r8, r9, ip, lr, abort=19f
-		orr	r3, r3, r4, push #\push
-		mov	r4, r4, pull #\pull
-		orr	r4, r4, r5, push #\push
-		mov	r5, r5, pull #\pull
-		orr	r5, r5, r6, push #\push
-		mov	r6, r6, pull #\pull
-		orr	r6, r6, r7, push #\push
-		mov	r7, r7, pull #\pull
-		orr	r7, r7, r8, push #\push
-		mov	r8, r8, pull #\pull
-		orr	r8, r8, r9, push #\push
-		mov	r9, r9, pull #\pull
-		orr	r9, r9, ip, push #\push
-		mov	ip, ip, pull #\pull
-		orr	ip, ip, lr, push #\push
+		orr	r3, r3, r4, lspush #\push
+		mov	r4, r4, lspull #\pull
+		orr	r4, r4, r5, lspush #\push
+		mov	r5, r5, lspull #\pull
+		orr	r5, r5, r6, lspush #\push
+		mov	r6, r6, lspull #\pull
+		orr	r6, r6, r7, lspush #\push
+		mov	r7, r7, lspull #\pull
+		orr	r7, r7, r8, lspush #\push
+		mov	r8, r8, lspull #\pull
+		orr	r8, r8, r9, lspush #\push
+		mov	r9, r9, lspull #\pull
+		orr	r9, r9, ip, lspush #\push
+		mov	ip, ip, lspull #\pull
+		orr	ip, ip, lr, lspush #\push
 		str8w	r0, r3, r4, r5, r6, r7, r8, r9, ip, , abort=19f
 		bge	12b
 	PLD(	cmn	r2, #96			)
@@ -225,10 +225,10 @@
 14:		ands	ip, r2, #28
 		beq	16f
 
-15:		mov	r3, lr, pull #\pull
+15:		mov	r3, lr, lspull #\pull
 		ldr1w	r1, lr, abort=21f
 		subs	ip, ip, #4
-		orr	r3, r3, lr, push #\push
+		orr	r3, r3, lr, lspush #\push
 		str1w	r0, r3, abort=21f
 		bgt	15b
 	CALGN(	cmp	r2, #0			)

arch/arm/mach-cns3xxx/core.c

@@ -155,7 +155,7 @@ static irqreturn_t cns3xxx_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction cns3xxx_timer_irq = {
 	.name		= "timer",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= cns3xxx_timer_interrupt,
 };