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

@@ -0,0 +1,43 @@
+/*
+ * 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

@@ -1,7 +0,0 @@
-/* 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

@@ -0,0 +1,45 @@
+/*
+ * 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-arm.c

@@ -60,13 +60,10 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
-#include <linux/module.h>
+#include <linux/ptrace.h>
 
 #include "kprobes.h"
-
-#define sign_extend(x, signbit) ((x) | (0 - ((x) & (1 << (signbit)))))
-
-#define branch_displacement(insn) sign_extend(((insn) & 0xffffff) << 2, 25)
+#include "probes-arm.h"
 
 #if  __LINUX_ARM_ARCH__ >= 6
 #define BLX(reg)	"blx	"reg"		\n\t"
@@ -75,92 +72,11 @@
 			"mov	pc, "reg"	\n\t"
 #endif
 
-/*
- * To avoid the complications of mimicing single-stepping on a
- * processor without a Next-PC or a single-step mode, and to
- * avoid having to deal with the side-effects of boosting, we
- * simulate or emulate (almost) all ARM instructions.
- *
- * "Simulation" is where the instruction's behavior is duplicated in
- * C code.  "Emulation" is where the original instruction is rewritten
- * and executed, often by altering its registers.
- *
- * By having all behavior of the kprobe'd instruction completed before
- * returning from the kprobe_handler(), all locks (scheduler and
- * interrupt) can safely be released.  There is no need for secondary
- * breakpoints, no race with MP or preemptable kernels, nor having to
- * clean up resources counts at a later time impacting overall system
- * performance.  By rewriting the instruction, only the minimum registers
- * need to be loaded and saved back optimizing performance.
- *
- * Calling the insnslot_*_rwflags version of a function doesn't hurt
- * anything even when the CPSR flags aren't updated by the
- * instruction.  It's just a little slower in return for saving
- * a little space by not having a duplicate function that doesn't
- * update the flags.  (The same optimization can be said for
- * instructions that do or don't perform register writeback)
- * Also, instructions can either read the flags, only write the
- * flags, or read and write the flags.  To save combinations
- * rather than for sheer performance, flag functions just assume
- * read and write of flags.
- */
-
-static void __kprobes simulate_bbl(struct kprobe *p, struct pt_regs *regs)
-{
-	kprobe_opcode_t insn = p->opcode;
-	long iaddr = (long)p->addr;
-	int disp  = branch_displacement(insn);
-
-	if (insn & (1 << 24))
-		regs->ARM_lr = iaddr + 4;
-
-	regs->ARM_pc = iaddr + 8 + disp;
-}
-
-static void __kprobes simulate_blx1(struct kprobe *p, struct pt_regs *regs)
-{
-	kprobe_opcode_t insn = p->opcode;
-	long iaddr = (long)p->addr;
-	int disp = branch_displacement(insn);
-
-	regs->ARM_lr = iaddr + 4;
-	regs->ARM_pc = iaddr + 8 + disp + ((insn >> 23) & 0x2);
-	regs->ARM_cpsr |= PSR_T_BIT;
-}
-
-static void __kprobes simulate_blx2bx(struct kprobe *p, struct pt_regs *regs)
-{
-	kprobe_opcode_t insn = p->opcode;
-	int rm = insn & 0xf;
-	long rmv = regs->uregs[rm];
-
-	if (insn & (1 << 5))
-		regs->ARM_lr = (long)p->addr + 4;
-
-	regs->ARM_pc = rmv & ~0x1;
-	regs->ARM_cpsr &= ~PSR_T_BIT;
-	if (rmv & 0x1)
-		regs->ARM_cpsr |= PSR_T_BIT;
-}
-
-static void __kprobes simulate_mrs(struct kprobe *p, struct pt_regs *regs)
-{
-	kprobe_opcode_t insn = p->opcode;
-	int rd = (insn >> 12) & 0xf;
-	unsigned long mask = 0xf8ff03df; /* Mask out execution state */
-	regs->uregs[rd] = regs->ARM_cpsr & mask;
-}
-
-static void __kprobes simulate_mov_ipsp(struct kprobe *p, struct pt_regs *regs)
-{
-	regs->uregs[12] = regs->uregs[13];
-}
-
 static void __kprobes
-emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs)
+emulate_ldrdstrd(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = (unsigned long)p->addr + 8;
+	unsigned long pc = regs->ARM_pc + 4;
 	int rt = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
@@ -175,7 +91,7 @@ emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs)
 		BLX("%[fn]")
 		: "=r" (rtv), "=r" (rt2v), "=r" (rnv)
 		: "0" (rtv), "1" (rt2v), "2" (rnv), "r" (rmv),
-		  [fn] "r" (p->ainsn.insn_fn)
+		  [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -186,10 +102,10 @@ emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_ldr(struct kprobe *p, struct pt_regs *regs)
+emulate_ldr(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = (unsigned long)p->addr + 8;
+	unsigned long pc = regs->ARM_pc + 4;
 	int rt = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
@@ -202,7 +118,7 @@ emulate_ldr(struct kprobe *p, struct pt_regs *regs)
 	__asm__ __volatile__ (
 		BLX("%[fn]")
 		: "=r" (rtv), "=r" (rnv)
-		: "1" (rnv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn)
+		: "1" (rnv), "r" (rmv), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -216,11 +132,11 @@ emulate_ldr(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_str(struct kprobe *p, struct pt_regs *regs)
+emulate_str(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long rtpc = (unsigned long)p->addr + str_pc_offset;
-	unsigned long rnpc = (unsigned long)p->addr + 8;
+	unsigned long rtpc = regs->ARM_pc - 4 + str_pc_offset;
+	unsigned long rnpc = regs->ARM_pc + 4;
 	int rt = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
@@ -234,7 +150,7 @@ emulate_str(struct kprobe *p, struct pt_regs *regs)
 	__asm__ __volatile__ (
 		BLX("%[fn]")
 		: "=r" (rnv)
-		: "r" (rtv), "0" (rnv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn)
+		: "r" (rtv), "0" (rnv), "r" (rmv), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -243,10 +159,10 @@ emulate_str(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_rd12rn16rm0rs8_rwflags(struct kprobe *p, struct pt_regs *regs)
+emulate_rd12rn16rm0rs8_rwflags(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = (unsigned long)p->addr + 8;
+	unsigned long pc = regs->ARM_pc + 4;
 	int rd = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
@@ -266,7 +182,7 @@ emulate_rd12rn16rm0rs8_rwflags(struct kprobe *p, struct pt_regs *regs)
 		"mrs	%[cpsr], cpsr		\n\t"
 		: "=r" (rdv), [cpsr] "=r" (cpsr)
 		: "0" (rdv), "r" (rnv), "r" (rmv), "r" (rsv),
-		  "1" (cpsr), [fn] "r" (p->ainsn.insn_fn)
+		  "1" (cpsr), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -278,9 +194,9 @@ emulate_rd12rn16rm0rs8_rwflags(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_rd12rn16rm0_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
+emulate_rd12rn16rm0_rwflags_nopc(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rd = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
@@ -296,7 +212,7 @@ emulate_rd12rn16rm0_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
 		"mrs	%[cpsr], cpsr		\n\t"
 		: "=r" (rdv), [cpsr] "=r" (cpsr)
 		: "0" (rdv), "r" (rnv), "r" (rmv),
-		  "1" (cpsr), [fn] "r" (p->ainsn.insn_fn)
+		  "1" (cpsr), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -305,9 +221,10 @@ emulate_rd12rn16rm0_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_rd16rn12rm0rs8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
+emulate_rd16rn12rm0rs8_rwflags_nopc(probes_opcode_t insn,
+	struct arch_probes_insn *asi,
+	struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rd = (insn >> 16) & 0xf;
 	int rn = (insn >> 12) & 0xf;
 	int rm = insn & 0xf;
@@ -325,7 +242,7 @@ emulate_rd16rn12rm0rs8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
 		"mrs	%[cpsr], cpsr		\n\t"
 		: "=r" (rdv), [cpsr] "=r" (cpsr)
 		: "0" (rdv), "r" (rnv), "r" (rmv), "r" (rsv),
-		  "1" (cpsr), [fn] "r" (p->ainsn.insn_fn)
+		  "1" (cpsr), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -334,9 +251,9 @@ emulate_rd16rn12rm0rs8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_rd12rm0_noflags_nopc(struct kprobe *p, struct pt_regs *regs)
+emulate_rd12rm0_noflags_nopc(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rd = (insn >> 12) & 0xf;
 	int rm = insn & 0xf;
 
@@ -346,7 +263,7 @@ emulate_rd12rm0_noflags_nopc(struct kprobe *p, struct pt_regs *regs)
 	__asm__ __volatile__ (
 		BLX("%[fn]")
 		: "=r" (rdv)
-		: "0" (rdv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn)
+		: "0" (rdv), "r" (rmv), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -354,9 +271,10 @@ emulate_rd12rm0_noflags_nopc(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_rdlo12rdhi16rn0rm8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
+emulate_rdlo12rdhi16rn0rm8_rwflags_nopc(probes_opcode_t insn,
+	struct arch_probes_insn *asi,
+	struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rdlo = (insn >> 12) & 0xf;
 	int rdhi = (insn >> 16) & 0xf;
 	int rn = insn & 0xf;
@@ -374,7 +292,7 @@ emulate_rdlo12rdhi16rn0rm8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
 		"mrs	%[cpsr], cpsr		\n\t"
 		: "=r" (rdlov), "=r" (rdhiv), [cpsr] "=r" (cpsr)
 		: "0" (rdlov), "1" (rdhiv), "r" (rnv), "r" (rmv),
-		  "2" (cpsr), [fn] "r" (p->ainsn.insn_fn)
+		  "2" (cpsr), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -383,623 +301,43 @@ emulate_rdlo12rdhi16rn0rm8_rwflags_nopc(struct kprobe *p, struct pt_regs *regs)
 	regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK);
 }
 
-/*
- * For the instruction masking and comparisons in all the "space_*"
- * functions below, Do _not_ rearrange the order of tests unless
- * you're very, very sure of what you are doing.  For the sake of
- * efficiency, the masks for some tests sometimes assume other test
- * have been done prior to them so the number of patterns to test
- * for an instruction set can be as broad as possible to reduce the
- * number of tests needed.
- */
-
-static const union decode_item arm_1111_table[] = {
-	/* Unconditional instructions					*/
-
-	/* memory hint		1111 0100 x001 xxxx xxxx xxxx xxxx xxxx */
-	/* PLDI (immediate)	1111 0100 x101 xxxx xxxx xxxx xxxx xxxx */
-	/* PLDW (immediate)	1111 0101 x001 xxxx xxxx xxxx xxxx xxxx */
-	/* PLD (immediate)	1111 0101 x101 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_SIMULATE	(0xfe300000, 0xf4100000, kprobe_simulate_nop),
-
-	/* memory hint		1111 0110 x001 xxxx xxxx xxxx xxx0 xxxx */
-	/* PLDI (register)	1111 0110 x101 xxxx xxxx xxxx xxx0 xxxx */
-	/* PLDW (register)	1111 0111 x001 xxxx xxxx xxxx xxx0 xxxx */
-	/* PLD (register)	1111 0111 x101 xxxx xxxx xxxx xxx0 xxxx */
-	DECODE_SIMULATE	(0xfe300010, 0xf6100000, kprobe_simulate_nop),
-
-	/* BLX (immediate)	1111 101x xxxx xxxx xxxx xxxx xxxx xxxx */
-	DECODE_SIMULATE	(0xfe000000, 0xfa000000, simulate_blx1),
-
-	/* CPS			1111 0001 0000 xxx0 xxxx xxxx xx0x xxxx */
-	/* SETEND		1111 0001 0000 0001 xxxx xxxx 0000 xxxx */
-	/* SRS			1111 100x x1x0 xxxx xxxx xxxx xxxx xxxx */
-	/* RFE			1111 100x x0x1 xxxx xxxx xxxx xxxx xxxx */
-
-	/* Coprocessor instructions... */
-	/* MCRR2		1111 1100 0100 xxxx xxxx xxxx xxxx xxxx */
-	/* MRRC2		1111 1100 0101 xxxx xxxx xxxx xxxx xxxx */
-	/* LDC2			1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
-	/* STC2			1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
-	/* CDP2			1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
-	/* MCR2			1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
-	/* MRC2			1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
-
-	/* Other unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_0001_0xx0____0xxx_table[] = {
-	/* Miscellaneous instructions					*/
-
-	/* MRS cpsr		cccc 0001 0000 xxxx xxxx xxxx 0000 xxxx */
-	DECODE_SIMULATEX(0x0ff000f0, 0x01000000, simulate_mrs,
-						 REGS(0, NOPC, 0, 0, 0)),
-
-	/* BX			cccc 0001 0010 xxxx xxxx xxxx 0001 xxxx */
-	DECODE_SIMULATE	(0x0ff000f0, 0x01200010, simulate_blx2bx),
-
-	/* BLX (register)	cccc 0001 0010 xxxx xxxx xxxx 0011 xxxx */
-	DECODE_SIMULATEX(0x0ff000f0, 0x01200030, simulate_blx2bx,
-						 REGS(0, 0, 0, 0, NOPC)),
-
-	/* CLZ			cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */
-	DECODE_EMULATEX	(0x0ff000f0, 0x01600010, emulate_rd12rm0_noflags_nopc,
-						 REGS(0, NOPC, 0, 0, NOPC)),
-
-	/* QADD			cccc 0001 0000 xxxx xxxx xxxx 0101 xxxx */
-	/* QSUB			cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx */
-	/* QDADD		cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx */
-	/* QDSUB		cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx */
-	DECODE_EMULATEX	(0x0f9000f0, 0x01000050, emulate_rd12rn16rm0_rwflags_nopc,
-						 REGS(NOPC, NOPC, 0, 0, NOPC)),
-
-	/* BXJ			cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */
-	/* MSR			cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */
-	/* MRS spsr		cccc 0001 0100 xxxx xxxx xxxx 0000 xxxx */
-	/* BKPT			1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */
-	/* SMC			cccc 0001 0110 xxxx xxxx xxxx 0111 xxxx */
-	/* And unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_0001_0xx0____1xx0_table[] = {
-	/* Halfword multiply and multiply-accumulate			*/
-
-	/* SMLALxy		cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */
-	DECODE_EMULATEX	(0x0ff00090, 0x01400080, emulate_rdlo12rdhi16rn0rm8_rwflags_nopc,
-						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
-
-	/* SMULWy		cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */
-	DECODE_OR	(0x0ff000b0, 0x012000a0),
-	/* SMULxy		cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */
-	DECODE_EMULATEX	(0x0ff00090, 0x01600080, emulate_rd16rn12rm0rs8_rwflags_nopc,
-						 REGS(NOPC, 0, NOPC, 0, NOPC)),
-
-	/* SMLAxy		cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx */
-	DECODE_OR	(0x0ff00090, 0x01000080),
-	/* SMLAWy		cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx */
-	DECODE_EMULATEX	(0x0ff000b0, 0x01200080, emulate_rd16rn12rm0rs8_rwflags_nopc,
-						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
-
-	DECODE_END
+const union decode_action kprobes_arm_actions[NUM_PROBES_ARM_ACTIONS] = {
+	[PROBES_EMULATE_NONE] = {.handler = probes_emulate_none},
+	[PROBES_SIMULATE_NOP] = {.handler = probes_simulate_nop},
+	[PROBES_PRELOAD_IMM] = {.handler = probes_simulate_nop},
+	[PROBES_PRELOAD_REG] = {.handler = probes_simulate_nop},
+	[PROBES_BRANCH_IMM] = {.handler = simulate_blx1},
+	[PROBES_MRS] = {.handler = simulate_mrs},
+	[PROBES_BRANCH_REG] = {.handler = simulate_blx2bx},
+	[PROBES_CLZ] = {.handler = emulate_rd12rm0_noflags_nopc},
+	[PROBES_SATURATING_ARITHMETIC] = {
+		.handler = emulate_rd12rn16rm0_rwflags_nopc},
+	[PROBES_MUL1] = {.handler = emulate_rdlo12rdhi16rn0rm8_rwflags_nopc},
+	[PROBES_MUL2] = {.handler = emulate_rd16rn12rm0rs8_rwflags_nopc},
+	[PROBES_SWP] = {.handler = emulate_rd12rn16rm0_rwflags_nopc},
+	[PROBES_LDRSTRD] = {.handler = emulate_ldrdstrd},
+	[PROBES_LOAD_EXTRA] = {.handler = emulate_ldr},
+	[PROBES_LOAD] = {.handler = emulate_ldr},
+	[PROBES_STORE_EXTRA] = {.handler = emulate_str},
+	[PROBES_STORE] = {.handler = emulate_str},
+	[PROBES_MOV_IP_SP] = {.handler = simulate_mov_ipsp},
+	[PROBES_DATA_PROCESSING_REG] = {
+		.handler = emulate_rd12rn16rm0rs8_rwflags},
+	[PROBES_DATA_PROCESSING_IMM] = {
+		.handler = emulate_rd12rn16rm0rs8_rwflags},
+	[PROBES_MOV_HALFWORD] = {.handler = emulate_rd12rm0_noflags_nopc},
+	[PROBES_SEV] = {.handler = probes_emulate_none},
+	[PROBES_WFE] = {.handler = probes_simulate_nop},
+	[PROBES_SATURATE] = {.handler = emulate_rd12rn16rm0_rwflags_nopc},
+	[PROBES_REV] = {.handler = emulate_rd12rm0_noflags_nopc},
+	[PROBES_MMI] = {.handler = emulate_rd12rn16rm0_rwflags_nopc},
+	[PROBES_PACK] = {.handler = emulate_rd12rn16rm0_rwflags_nopc},
+	[PROBES_EXTEND] = {.handler = emulate_rd12rm0_noflags_nopc},
+	[PROBES_EXTEND_ADD] = {.handler = emulate_rd12rn16rm0_rwflags_nopc},
+	[PROBES_MUL_ADD_LONG] = {
+		.handler = emulate_rdlo12rdhi16rn0rm8_rwflags_nopc},
+	[PROBES_MUL_ADD] = {.handler = emulate_rd16rn12rm0rs8_rwflags_nopc},
+	[PROBES_BITFIELD] = {.handler = emulate_rd12rm0_noflags_nopc},
+	[PROBES_BRANCH] = {.handler = simulate_bbl},
+	[PROBES_LDMSTM] = {.decoder = kprobe_decode_ldmstm}
 };
-
-static const union decode_item arm_cccc_0000_____1001_table[] = {
-	/* Multiply and multiply-accumulate				*/
-
-	/* MUL			cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx */
-	/* MULS			cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx */
-	DECODE_EMULATEX	(0x0fe000f0, 0x00000090, emulate_rd16rn12rm0rs8_rwflags_nopc,
-						 REGS(NOPC, 0, NOPC, 0, NOPC)),
-
-	/* MLA			cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx */
-	/* MLAS			cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx */
-	DECODE_OR	(0x0fe000f0, 0x00200090),
-	/* MLS			cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx */
-	DECODE_EMULATEX	(0x0ff000f0, 0x00600090, emulate_rd16rn12rm0rs8_rwflags_nopc,
-						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
-
-	/* UMAAL		cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx */
-	DECODE_OR	(0x0ff000f0, 0x00400090),
-	/* UMULL		cccc 0000 1000 xxxx xxxx xxxx 1001 xxxx */
-	/* UMULLS		cccc 0000 1001 xxxx xxxx xxxx 1001 xxxx */
-	/* UMLAL		cccc 0000 1010 xxxx xxxx xxxx 1001 xxxx */
-	/* UMLALS		cccc 0000 1011 xxxx xxxx xxxx 1001 xxxx */
-	/* SMULL		cccc 0000 1100 xxxx xxxx xxxx 1001 xxxx */
-	/* SMULLS		cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx */
-	/* SMLAL		cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx */
-	/* SMLALS		cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx */
-	DECODE_EMULATEX	(0x0f8000f0, 0x00800090, emulate_rdlo12rdhi16rn0rm8_rwflags_nopc,
-						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
-
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_0001_____1001_table[] = {
-	/* Synchronization primitives					*/
-
-#if __LINUX_ARM_ARCH__ < 6
-	/* Deprecated on ARMv6 and may be UNDEFINED on v7		*/
-	/* SMP/SWPB		cccc 0001 0x00 xxxx xxxx xxxx 1001 xxxx */
-	DECODE_EMULATEX	(0x0fb000f0, 0x01000090, emulate_rd12rn16rm0_rwflags_nopc,
-						 REGS(NOPC, NOPC, 0, 0, NOPC)),
-#endif
-	/* LDREX/STREX{,D,B,H}	cccc 0001 1xxx xxxx xxxx xxxx 1001 xxxx */
-	/* And unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_000x_____1xx1_table[] = {
-	/* Extra load/store instructions				*/
-
-	/* STRHT		cccc 0000 xx10 xxxx xxxx xxxx 1011 xxxx */
-	/* ???			cccc 0000 xx10 xxxx xxxx xxxx 11x1 xxxx */
-	/* LDRHT		cccc 0000 xx11 xxxx xxxx xxxx 1011 xxxx */
-	/* LDRSBT		cccc 0000 xx11 xxxx xxxx xxxx 1101 xxxx */
-	/* LDRSHT		cccc 0000 xx11 xxxx xxxx xxxx 1111 xxxx */
-	DECODE_REJECT	(0x0f200090, 0x00200090),
-
-	/* LDRD/STRD lr,pc,{...	cccc 000x x0x0 xxxx 111x xxxx 1101 xxxx */
-	DECODE_REJECT	(0x0e10e0d0, 0x0000e0d0),
-
-	/* LDRD (register)	cccc 000x x0x0 xxxx xxxx xxxx 1101 xxxx */
-	/* STRD (register)	cccc 000x x0x0 xxxx xxxx xxxx 1111 xxxx */
-	DECODE_EMULATEX	(0x0e5000d0, 0x000000d0, emulate_ldrdstrd,
-						 REGS(NOPCWB, NOPCX, 0, 0, NOPC)),
-
-	/* LDRD (immediate)	cccc 000x x1x0 xxxx xxxx xxxx 1101 xxxx */
-	/* STRD (immediate)	cccc 000x x1x0 xxxx xxxx xxxx 1111 xxxx */
-	DECODE_EMULATEX	(0x0e5000d0, 0x004000d0, emulate_ldrdstrd,
-						 REGS(NOPCWB, NOPCX, 0, 0, 0)),
-
-	/* STRH (register)	cccc 000x x0x0 xxxx xxxx xxxx 1011 xxxx */
-	DECODE_EMULATEX	(0x0e5000f0, 0x000000b0, emulate_str,
-						 REGS(NOPCWB, NOPC, 0, 0, NOPC)),
-
-	/* LDRH (register)	cccc 000x x0x1 xxxx xxxx xxxx 1011 xxxx */
-	/* LDRSB (register)	cccc 000x x0x1 xxxx xxxx xxxx 1101 xxxx */
-	/* LDRSH (register)	cccc 000x x0x1 xxxx xxxx xxxx 1111 xxxx */
-	DECODE_EMULATEX	(0x0e500090, 0x00100090, emulate_ldr,
-						 REGS(NOPCWB, NOPC, 0, 0, NOPC)),
-
-	/* STRH (immediate)	cccc 000x x1x0 xxxx xxxx xxxx 1011 xxxx */
-	DECODE_EMULATEX	(0x0e5000f0, 0x004000b0, emulate_str,
-						 REGS(NOPCWB, NOPC, 0, 0, 0)),
-
-	/* LDRH (immediate)	cccc 000x x1x1 xxxx xxxx xxxx 1011 xxxx */
-	/* LDRSB (immediate)	cccc 000x x1x1 xxxx xxxx xxxx 1101 xxxx */
-	/* LDRSH (immediate)	cccc 000x x1x1 xxxx xxxx xxxx 1111 xxxx */
-	DECODE_EMULATEX	(0x0e500090, 0x00500090, emulate_ldr,
-						 REGS(NOPCWB, NOPC, 0, 0, 0)),
-
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_000x_table[] = {
-	/* Data-processing (register)					*/
-
-	/* <op>S PC, ...	cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx */
-	DECODE_REJECT	(0x0e10f000, 0x0010f000),
-
-	/* MOV IP, SP		1110 0001 1010 0000 1100 0000 0000 1101 */
-	DECODE_SIMULATE	(0xffffffff, 0xe1a0c00d, simulate_mov_ipsp),
-
-	/* TST (register)	cccc 0001 0001 xxxx xxxx xxxx xxx0 xxxx */
-	/* TEQ (register)	cccc 0001 0011 xxxx xxxx xxxx xxx0 xxxx */
-	/* CMP (register)	cccc 0001 0101 xxxx xxxx xxxx xxx0 xxxx */
-	/* CMN (register)	cccc 0001 0111 xxxx xxxx xxxx xxx0 xxxx */
-	DECODE_EMULATEX	(0x0f900010, 0x01100000, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(ANY, 0, 0, 0, ANY)),
-
-	/* MOV (register)	cccc 0001 101x xxxx xxxx xxxx xxx0 xxxx */
-	/* MVN (register)	cccc 0001 111x xxxx xxxx xxxx xxx0 xxxx */
-	DECODE_EMULATEX	(0x0fa00010, 0x01a00000, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(0, ANY, 0, 0, ANY)),
-
-	/* AND (register)	cccc 0000 000x xxxx xxxx xxxx xxx0 xxxx */
-	/* EOR (register)	cccc 0000 001x xxxx xxxx xxxx xxx0 xxxx */
-	/* SUB (register)	cccc 0000 010x xxxx xxxx xxxx xxx0 xxxx */
-	/* RSB (register)	cccc 0000 011x xxxx xxxx xxxx xxx0 xxxx */
-	/* ADD (register)	cccc 0000 100x xxxx xxxx xxxx xxx0 xxxx */
-	/* ADC (register)	cccc 0000 101x xxxx xxxx xxxx xxx0 xxxx */
-	/* SBC (register)	cccc 0000 110x xxxx xxxx xxxx xxx0 xxxx */
-	/* RSC (register)	cccc 0000 111x xxxx xxxx xxxx xxx0 xxxx */
-	/* ORR (register)	cccc 0001 100x xxxx xxxx xxxx xxx0 xxxx */
-	/* BIC (register)	cccc 0001 110x xxxx xxxx xxxx xxx0 xxxx */
-	DECODE_EMULATEX	(0x0e000010, 0x00000000, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(ANY, ANY, 0, 0, ANY)),
-
-	/* TST (reg-shift reg)	cccc 0001 0001 xxxx xxxx xxxx 0xx1 xxxx */
-	/* TEQ (reg-shift reg)	cccc 0001 0011 xxxx xxxx xxxx 0xx1 xxxx */
-	/* CMP (reg-shift reg)	cccc 0001 0101 xxxx xxxx xxxx 0xx1 xxxx */
-	/* CMN (reg-shift reg)	cccc 0001 0111 xxxx xxxx xxxx 0xx1 xxxx */
-	DECODE_EMULATEX	(0x0f900090, 0x01100010, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(ANY, 0, NOPC, 0, ANY)),
-
-	/* MOV (reg-shift reg)	cccc 0001 101x xxxx xxxx xxxx 0xx1 xxxx */
-	/* MVN (reg-shift reg)	cccc 0001 111x xxxx xxxx xxxx 0xx1 xxxx */
-	DECODE_EMULATEX	(0x0fa00090, 0x01a00010, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(0, ANY, NOPC, 0, ANY)),
-
-	/* AND (reg-shift reg)	cccc 0000 000x xxxx xxxx xxxx 0xx1 xxxx */
-	/* EOR (reg-shift reg)	cccc 0000 001x xxxx xxxx xxxx 0xx1 xxxx */
-	/* SUB (reg-shift reg)	cccc 0000 010x xxxx xxxx xxxx 0xx1 xxxx */
-	/* RSB (reg-shift reg)	cccc 0000 011x xxxx xxxx xxxx 0xx1 xxxx */
-	/* ADD (reg-shift reg)	cccc 0000 100x xxxx xxxx xxxx 0xx1 xxxx */
-	/* ADC (reg-shift reg)	cccc 0000 101x xxxx xxxx xxxx 0xx1 xxxx */
-	/* SBC (reg-shift reg)	cccc 0000 110x xxxx xxxx xxxx 0xx1 xxxx */
-	/* RSC (reg-shift reg)	cccc 0000 111x xxxx xxxx xxxx 0xx1 xxxx */
-	/* ORR (reg-shift reg)	cccc 0001 100x xxxx xxxx xxxx 0xx1 xxxx */
-	/* BIC (reg-shift reg)	cccc 0001 110x xxxx xxxx xxxx 0xx1 xxxx */
-	DECODE_EMULATEX	(0x0e000090, 0x00000010, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(ANY, ANY, NOPC, 0, ANY)),
-
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_001x_table[] = {
-	/* Data-processing (immediate)					*/
-
-	/* MOVW			cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */
-	/* MOVT			cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0fb00000, 0x03000000, emulate_rd12rm0_noflags_nopc,
-						 REGS(0, NOPC, 0, 0, 0)),
-
-	/* YIELD		cccc 0011 0010 0000 xxxx xxxx 0000 0001 */
-	DECODE_OR	(0x0fff00ff, 0x03200001),
-	/* SEV			cccc 0011 0010 0000 xxxx xxxx 0000 0100 */
-	DECODE_EMULATE	(0x0fff00ff, 0x03200004, kprobe_emulate_none),
-	/* NOP			cccc 0011 0010 0000 xxxx xxxx 0000 0000 */
-	/* WFE			cccc 0011 0010 0000 xxxx xxxx 0000 0010 */
-	/* WFI			cccc 0011 0010 0000 xxxx xxxx 0000 0011 */
-	DECODE_SIMULATE	(0x0fff00fc, 0x03200000, kprobe_simulate_nop),
-	/* DBG			cccc 0011 0010 0000 xxxx xxxx ffff xxxx */
-	/* unallocated hints	cccc 0011 0010 0000 xxxx xxxx xxxx xxxx */
-	/* MSR (immediate)	cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0x0fb00000, 0x03200000),
-
-	/* <op>S PC, ...	cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx */
-	DECODE_REJECT	(0x0e10f000, 0x0210f000),
-
-	/* TST (immediate)	cccc 0011 0001 xxxx xxxx xxxx xxxx xxxx */
-	/* TEQ (immediate)	cccc 0011 0011 xxxx xxxx xxxx xxxx xxxx */
-	/* CMP (immediate)	cccc 0011 0101 xxxx xxxx xxxx xxxx xxxx */
-	/* CMN (immediate)	cccc 0011 0111 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0f900000, 0x03100000, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(ANY, 0, 0, 0, 0)),
-
-	/* MOV (immediate)	cccc 0011 101x xxxx xxxx xxxx xxxx xxxx */
-	/* MVN (immediate)	cccc 0011 111x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0fa00000, 0x03a00000, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(0, ANY, 0, 0, 0)),
-
-	/* AND (immediate)	cccc 0010 000x xxxx xxxx xxxx xxxx xxxx */
-	/* EOR (immediate)	cccc 0010 001x xxxx xxxx xxxx xxxx xxxx */
-	/* SUB (immediate)	cccc 0010 010x xxxx xxxx xxxx xxxx xxxx */
-	/* RSB (immediate)	cccc 0010 011x xxxx xxxx xxxx xxxx xxxx */
-	/* ADD (immediate)	cccc 0010 100x xxxx xxxx xxxx xxxx xxxx */
-	/* ADC (immediate)	cccc 0010 101x xxxx xxxx xxxx xxxx xxxx */
-	/* SBC (immediate)	cccc 0010 110x xxxx xxxx xxxx xxxx xxxx */
-	/* RSC (immediate)	cccc 0010 111x xxxx xxxx xxxx xxxx xxxx */
-	/* ORR (immediate)	cccc 0011 100x xxxx xxxx xxxx xxxx xxxx */
-	/* BIC (immediate)	cccc 0011 110x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0e000000, 0x02000000, emulate_rd12rn16rm0rs8_rwflags,
-						 REGS(ANY, ANY, 0, 0, 0)),
-
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_0110_____xxx1_table[] = {
-	/* Media instructions						*/
-
-	/* SEL			cccc 0110 1000 xxxx xxxx xxxx 1011 xxxx */
-	DECODE_EMULATEX	(0x0ff000f0, 0x068000b0, emulate_rd12rn16rm0_rwflags_nopc,
-						 REGS(NOPC, NOPC, 0, 0, NOPC)),
-
-	/* SSAT			cccc 0110 101x xxxx xxxx xxxx xx01 xxxx */
-	/* USAT			cccc 0110 111x xxxx xxxx xxxx xx01 xxxx */
-	DECODE_OR(0x0fa00030, 0x06a00010),
-	/* SSAT16		cccc 0110 1010 xxxx xxxx xxxx 0011 xxxx */
-	/* USAT16		cccc 0110 1110 xxxx xxxx xxxx 0011 xxxx */
-	DECODE_EMULATEX	(0x0fb000f0, 0x06a00030, emulate_rd12rn16rm0_rwflags_nopc,
-						 REGS(0, NOPC, 0, 0, NOPC)),
-
-	/* REV			cccc 0110 1011 xxxx xxxx xxxx 0011 xxxx */
-	/* REV16		cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */
-	/* RBIT			cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */
-	/* REVSH		cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */
-	DECODE_EMULATEX	(0x0fb00070, 0x06b00030, emulate_rd12rm0_noflags_nopc,
-						 REGS(0, NOPC, 0, 0, NOPC)),
-
-	/* ???			cccc 0110 0x00 xxxx xxxx xxxx xxx1 xxxx */
-	DECODE_REJECT	(0x0fb00010, 0x06000010),
-	/* ???			cccc 0110 0xxx xxxx xxxx xxxx 1011 xxxx */
-	DECODE_REJECT	(0x0f8000f0, 0x060000b0),
-	/* ???			cccc 0110 0xxx xxxx xxxx xxxx 1101 xxxx */
-	DECODE_REJECT	(0x0f8000f0, 0x060000d0),
-	/* SADD16		cccc 0110 0001 xxxx xxxx xxxx 0001 xxxx */
-	/* SADDSUBX		cccc 0110 0001 xxxx xxxx xxxx 0011 xxxx */
-	/* SSUBADDX		cccc 0110 0001 xxxx xxxx xxxx 0101 xxxx */
-	/* SSUB16		cccc 0110 0001 xxxx xxxx xxxx 0111 xxxx */
-	/* SADD8		cccc 0110 0001 xxxx xxxx xxxx 1001 xxxx */
-	/* SSUB8		cccc 0110 0001 xxxx xxxx xxxx 1111 xxxx */
-	/* QADD16		cccc 0110 0010 xxxx xxxx xxxx 0001 xxxx */
-	/* QADDSUBX		cccc 0110 0010 xxxx xxxx xxxx 0011 xxxx */
-	/* QSUBADDX		cccc 0110 0010 xxxx xxxx xxxx 0101 xxxx */
-	/* QSUB16		cccc 0110 0010 xxxx xxxx xxxx 0111 xxxx */
-	/* QADD8		cccc 0110 0010 xxxx xxxx xxxx 1001 xxxx */
-	/* QSUB8		cccc 0110 0010 xxxx xxxx xxxx 1111 xxxx */
-	/* SHADD16		cccc 0110 0011 xxxx xxxx xxxx 0001 xxxx */
-	/* SHADDSUBX		cccc 0110 0011 xxxx xxxx xxxx 0011 xxxx */
-	/* SHSUBADDX		cccc 0110 0011 xxxx xxxx xxxx 0101 xxxx */
-	/* SHSUB16		cccc 0110 0011 xxxx xxxx xxxx 0111 xxxx */
-	/* SHADD8		cccc 0110 0011 xxxx xxxx xxxx 1001 xxxx */
-	/* SHSUB8		cccc 0110 0011 xxxx xxxx xxxx 1111 xxxx */
-	/* UADD16		cccc 0110 0101 xxxx xxxx xxxx 0001 xxxx */
-	/* UADDSUBX		cccc 0110 0101 xxxx xxxx xxxx 0011 xxxx */
-	/* USUBADDX		cccc 0110 0101 xxxx xxxx xxxx 0101 xxxx */
-	/* USUB16		cccc 0110 0101 xxxx xxxx xxxx 0111 xxxx */
-	/* UADD8		cccc 0110 0101 xxxx xxxx xxxx 1001 xxxx */
-	/* USUB8		cccc 0110 0101 xxxx xxxx xxxx 1111 xxxx */
-	/* UQADD16		cccc 0110 0110 xxxx xxxx xxxx 0001 xxxx */
-	/* UQADDSUBX		cccc 0110 0110 xxxx xxxx xxxx 0011 xxxx */
-	/* UQSUBADDX		cccc 0110 0110 xxxx xxxx xxxx 0101 xxxx */
-	/* UQSUB16		cccc 0110 0110 xxxx xxxx xxxx 0111 xxxx */
-	/* UQADD8		cccc 0110 0110 xxxx xxxx xxxx 1001 xxxx */
-	/* UQSUB8		cccc 0110 0110 xxxx xxxx xxxx 1111 xxxx */
-	/* UHADD16		cccc 0110 0111 xxxx xxxx xxxx 0001 xxxx */
-	/* UHADDSUBX		cccc 0110 0111 xxxx xxxx xxxx 0011 xxxx */
-	/* UHSUBADDX		cccc 0110 0111 xxxx xxxx xxxx 0101 xxxx */
-	/* UHSUB16		cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx */
-	/* UHADD8		cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx */
-	/* UHSUB8		cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx */
-	DECODE_EMULATEX	(0x0f800010, 0x06000010, emulate_rd12rn16rm0_rwflags_nopc,
-						 REGS(NOPC, NOPC, 0, 0, NOPC)),
-
-	/* PKHBT		cccc 0110 1000 xxxx xxxx xxxx x001 xxxx */
-	/* PKHTB		cccc 0110 1000 xxxx xxxx xxxx x101 xxxx */
-	DECODE_EMULATEX	(0x0ff00030, 0x06800010, emulate_rd12rn16rm0_rwflags_nopc,
-						 REGS(NOPC, NOPC, 0, 0, NOPC)),
-
-	/* ???			cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx */
-	/* ???			cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx */
-	DECODE_REJECT	(0x0fb000f0, 0x06900070),
-
-	/* SXTB16		cccc 0110 1000 1111 xxxx xxxx 0111 xxxx */
-	/* SXTB			cccc 0110 1010 1111 xxxx xxxx 0111 xxxx */
-	/* SXTH			cccc 0110 1011 1111 xxxx xxxx 0111 xxxx */
-	/* UXTB16		cccc 0110 1100 1111 xxxx xxxx 0111 xxxx */
-	/* UXTB			cccc 0110 1110 1111 xxxx xxxx 0111 xxxx */
-	/* UXTH			cccc 0110 1111 1111 xxxx xxxx 0111 xxxx */
-	DECODE_EMULATEX	(0x0f8f00f0, 0x068f0070, emulate_rd12rm0_noflags_nopc,
-						 REGS(0, NOPC, 0, 0, NOPC)),
-
-	/* SXTAB16		cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx */
-	/* SXTAB		cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx */
-	/* SXTAH		cccc 0110 1011 xxxx xxxx xxxx 0111 xxxx */
-	/* UXTAB16		cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx */
-	/* UXTAB		cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx */
-	/* UXTAH		cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx */
-	DECODE_EMULATEX	(0x0f8000f0, 0x06800070, emulate_rd12rn16rm0_rwflags_nopc,
-						 REGS(NOPCX, NOPC, 0, 0, NOPC)),
-
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_0111_____xxx1_table[] = {
-	/* Media instructions						*/
-
-	/* UNDEFINED		cccc 0111 1111 xxxx xxxx xxxx 1111 xxxx */
-	DECODE_REJECT	(0x0ff000f0, 0x07f000f0),
-
-	/* SMLALD		cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */
-	/* SMLSLD		cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */
-	DECODE_EMULATEX	(0x0ff00090, 0x07400010, emulate_rdlo12rdhi16rn0rm8_rwflags_nopc,
-						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
-
-	/* SMUAD		cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx */
-	/* SMUSD		cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx */
-	DECODE_OR	(0x0ff0f090, 0x0700f010),
-	/* SMMUL		cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx */
-	DECODE_OR	(0x0ff0f0d0, 0x0750f010),
-	/* USAD8		cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx */
-	DECODE_EMULATEX	(0x0ff0f0f0, 0x0780f010, emulate_rd16rn12rm0rs8_rwflags_nopc,
-						 REGS(NOPC, 0, NOPC, 0, NOPC)),
-
-	/* SMLAD		cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx */
-	/* SMLSD		cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx */
-	DECODE_OR	(0x0ff00090, 0x07000010),
-	/* SMMLA		cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx */
-	DECODE_OR	(0x0ff000d0, 0x07500010),
-	/* USADA8		cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx */
-	DECODE_EMULATEX	(0x0ff000f0, 0x07800010, emulate_rd16rn12rm0rs8_rwflags_nopc,
-						 REGS(NOPC, NOPCX, NOPC, 0, NOPC)),
-
-	/* SMMLS		cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx */
-	DECODE_EMULATEX	(0x0ff000d0, 0x075000d0, emulate_rd16rn12rm0rs8_rwflags_nopc,
-						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
-
-	/* SBFX			cccc 0111 101x xxxx xxxx xxxx x101 xxxx */
-	/* UBFX			cccc 0111 111x xxxx xxxx xxxx x101 xxxx */
-	DECODE_EMULATEX	(0x0fa00070, 0x07a00050, emulate_rd12rm0_noflags_nopc,
-						 REGS(0, NOPC, 0, 0, NOPC)),
-
-	/* BFC			cccc 0111 110x xxxx xxxx xxxx x001 1111 */
-	DECODE_EMULATEX	(0x0fe0007f, 0x07c0001f, emulate_rd12rm0_noflags_nopc,
-						 REGS(0, NOPC, 0, 0, 0)),
-
-	/* BFI			cccc 0111 110x xxxx xxxx xxxx x001 xxxx */
-	DECODE_EMULATEX	(0x0fe00070, 0x07c00010, emulate_rd12rm0_noflags_nopc,
-						 REGS(0, NOPC, 0, 0, NOPCX)),
-
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_01xx_table[] = {
-	/* Load/store word and unsigned byte				*/
-
-	/* LDRB/STRB pc,[...]	cccc 01xx x0xx xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0x0c40f000, 0x0440f000),
-
-	/* STRT			cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRT			cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */
-	/* STRBT		cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRBT		cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0x0d200000, 0x04200000),
-
-	/* STR (immediate)	cccc 010x x0x0 xxxx xxxx xxxx xxxx xxxx */
-	/* STRB (immediate)	cccc 010x x1x0 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0e100000, 0x04000000, emulate_str,
-						 REGS(NOPCWB, ANY, 0, 0, 0)),
-
-	/* LDR (immediate)	cccc 010x x0x1 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRB (immediate)	cccc 010x x1x1 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0e100000, 0x04100000, emulate_ldr,
-						 REGS(NOPCWB, ANY, 0, 0, 0)),
-
-	/* STR (register)	cccc 011x x0x0 xxxx xxxx xxxx xxxx xxxx */
-	/* STRB (register)	cccc 011x x1x0 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0e100000, 0x06000000, emulate_str,
-						 REGS(NOPCWB, ANY, 0, 0, NOPC)),
-
-	/* LDR (register)	cccc 011x x0x1 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRB (register)	cccc 011x x1x1 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0x0e100000, 0x06100000, emulate_ldr,
-						 REGS(NOPCWB, ANY, 0, 0, NOPC)),
-
-	DECODE_END
-};
-
-static const union decode_item arm_cccc_100x_table[] = {
-	/* Block data transfer instructions				*/
-
-	/* LDM			cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */
-	/* STM			cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_CUSTOM	(0x0e400000, 0x08000000, kprobe_decode_ldmstm),
-
-	/* STM (user registers)	cccc 100x x1x0 xxxx xxxx xxxx xxxx xxxx */
-	/* LDM (user registers)	cccc 100x x1x1 xxxx 0xxx xxxx xxxx xxxx */
-	/* LDM (exception ret)	cccc 100x x1x1 xxxx 1xxx xxxx xxxx xxxx */
-	DECODE_END
-};
-
-const union decode_item kprobe_decode_arm_table[] = {
-	/*
-	 * Unconditional instructions
-	 *			1111 xxxx xxxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xf0000000, 0xf0000000, arm_1111_table),
-
-	/*
-	 * Miscellaneous instructions
-	 *			cccc 0001 0xx0 xxxx xxxx xxxx 0xxx xxxx
-	 */
-	DECODE_TABLE	(0x0f900080, 0x01000000, arm_cccc_0001_0xx0____0xxx_table),
-
-	/*
-	 * Halfword multiply and multiply-accumulate
-	 *			cccc 0001 0xx0 xxxx xxxx xxxx 1xx0 xxxx
-	 */
-	DECODE_TABLE	(0x0f900090, 0x01000080, arm_cccc_0001_0xx0____1xx0_table),
-
-	/*
-	 * Multiply and multiply-accumulate
-	 *			cccc 0000 xxxx xxxx xxxx xxxx 1001 xxxx
-	 */
-	DECODE_TABLE	(0x0f0000f0, 0x00000090, arm_cccc_0000_____1001_table),
-
-	/*
-	 * Synchronization primitives
-	 *			cccc 0001 xxxx xxxx xxxx xxxx 1001 xxxx
-	 */
-	DECODE_TABLE	(0x0f0000f0, 0x01000090, arm_cccc_0001_____1001_table),
-
-	/*
-	 * Extra load/store instructions
-	 *			cccc 000x xxxx xxxx xxxx xxxx 1xx1 xxxx
-	 */
-	DECODE_TABLE	(0x0e000090, 0x00000090, arm_cccc_000x_____1xx1_table),
-
-	/*
-	 * Data-processing (register)
-	 *			cccc 000x xxxx xxxx xxxx xxxx xxx0 xxxx
-	 * Data-processing (register-shifted register)
-	 *			cccc 000x xxxx xxxx xxxx xxxx 0xx1 xxxx
-	 */
-	DECODE_TABLE	(0x0e000000, 0x00000000, arm_cccc_000x_table),
-
-	/*
-	 * Data-processing (immediate)
-	 *			cccc 001x xxxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0x0e000000, 0x02000000, arm_cccc_001x_table),
-
-	/*
-	 * Media instructions
-	 *			cccc 011x xxxx xxxx xxxx xxxx xxx1 xxxx
-	 */
-	DECODE_TABLE	(0x0f000010, 0x06000010, arm_cccc_0110_____xxx1_table),
-	DECODE_TABLE	(0x0f000010, 0x07000010, arm_cccc_0111_____xxx1_table),
-
-	/*
-	 * Load/store word and unsigned byte
-	 *			cccc 01xx xxxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0x0c000000, 0x04000000, arm_cccc_01xx_table),
-
-	/*
-	 * Block data transfer instructions
-	 *			cccc 100x xxxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0x0e000000, 0x08000000, arm_cccc_100x_table),
-
-	/* B			cccc 1010 xxxx xxxx xxxx xxxx xxxx xxxx */
-	/* BL			cccc 1011 xxxx xxxx xxxx xxxx xxxx xxxx */
-	DECODE_SIMULATE	(0x0e000000, 0x0a000000, simulate_bbl),
-
-	/*
-	 * Supervisor Call, and coprocessor instructions
-	 */
-
-	/* MCRR			cccc 1100 0100 xxxx xxxx xxxx xxxx xxxx */
-	/* MRRC			cccc 1100 0101 xxxx xxxx xxxx xxxx xxxx */
-	/* LDC			cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
-	/* STC			cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
-	/* CDP			cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
-	/* MCR			cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
-	/* MRC			cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
-	/* SVC			cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0x0c000000, 0x0c000000),
-
-	DECODE_END
-};
-#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
-EXPORT_SYMBOL_GPL(kprobe_decode_arm_table);
-#endif
-
-static void __kprobes arm_singlestep(struct kprobe *p, struct pt_regs *regs)
-{
-	regs->ARM_pc += 4;
-	p->ainsn.insn_handler(p, regs);
-}
-
-/* Return:
- *   INSN_REJECTED     If instruction is one not allowed to kprobe,
- *   INSN_GOOD         If instruction is supported and uses instruction slot,
- *   INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
- *
- * For instructions we don't want to kprobe (INSN_REJECTED return result):
- *   These are generally ones that modify the processor state making
- *   them "hard" to simulate such as switches processor modes or
- *   make accesses in alternate modes.  Any of these could be simulated
- *   if the work was put into it, but low return considering they
- *   should also be very rare.
- */
-enum kprobe_insn __kprobes
-arm_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
-{
-	asi->insn_singlestep = arm_singlestep;
-	asi->insn_check_cc = kprobe_condition_checks[insn>>28];
-	return kprobe_decode_insn(insn, asi, kprobe_decode_arm_table, false);
-}

arch/arm/kernel/kprobes-common.c

@@ -13,178 +13,14 @@
 
 #include <linux/kernel.h>
 #include <linux/kprobes.h>
-#include <asm/system_info.h>
 
 #include "kprobes.h"
 
 
-#ifndef find_str_pc_offset
-
-/*
- * For STR and STM instructions, an ARM core may choose to use either
- * a +8 or a +12 displacement from the current instruction's address.
- * Whichever value is chosen for a given core, it must be the same for
- * both instructions and may not change.  This function measures it.
- */
-
-int str_pc_offset;
-
-void __init find_str_pc_offset(void)
-{
-	int addr, scratch, ret;
-
-	__asm__ (
-		"sub	%[ret], pc, #4		\n\t"
-		"str	pc, %[addr]		\n\t"
-		"ldr	%[scr], %[addr]		\n\t"
-		"sub	%[ret], %[scr], %[ret]	\n\t"
-		: [ret] "=r" (ret), [scr] "=r" (scratch), [addr] "+m" (addr));
-
-	str_pc_offset = ret;
-}
-
-#endif /* !find_str_pc_offset */
-
-
-#ifndef test_load_write_pc_interworking
-
-bool load_write_pc_interworks;
-
-void __init test_load_write_pc_interworking(void)
-{
-	int arch = cpu_architecture();
-	BUG_ON(arch == CPU_ARCH_UNKNOWN);
-	load_write_pc_interworks = arch >= CPU_ARCH_ARMv5T;
-}
-
-#endif /* !test_load_write_pc_interworking */
-
-
-#ifndef test_alu_write_pc_interworking
-
-bool alu_write_pc_interworks;
-
-void __init test_alu_write_pc_interworking(void)
-{
-	int arch = cpu_architecture();
-	BUG_ON(arch == CPU_ARCH_UNKNOWN);
-	alu_write_pc_interworks = arch >= CPU_ARCH_ARMv7;
-}
-
-#endif /* !test_alu_write_pc_interworking */
-
-
-void __init arm_kprobe_decode_init(void)
-{
-	find_str_pc_offset();
-	test_load_write_pc_interworking();
-	test_alu_write_pc_interworking();
-}
-
-
-static unsigned long __kprobes __check_eq(unsigned long cpsr)
-{
-	return cpsr & PSR_Z_BIT;
-}
-
-static unsigned long __kprobes __check_ne(unsigned long cpsr)
-{
-	return (~cpsr) & PSR_Z_BIT;
-}
-
-static unsigned long __kprobes __check_cs(unsigned long cpsr)
-{
-	return cpsr & PSR_C_BIT;
-}
-
-static unsigned long __kprobes __check_cc(unsigned long cpsr)
-{
-	return (~cpsr) & PSR_C_BIT;
-}
-
-static unsigned long __kprobes __check_mi(unsigned long cpsr)
-{
-	return cpsr & PSR_N_BIT;
-}
-
-static unsigned long __kprobes __check_pl(unsigned long cpsr)
-{
-	return (~cpsr) & PSR_N_BIT;
-}
-
-static unsigned long __kprobes __check_vs(unsigned long cpsr)
-{
-	return cpsr & PSR_V_BIT;
-}
-
-static unsigned long __kprobes __check_vc(unsigned long cpsr)
-{
-	return (~cpsr) & PSR_V_BIT;
-}
-
-static unsigned long __kprobes __check_hi(unsigned long cpsr)
-{
-	cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
-	return cpsr & PSR_C_BIT;
-}
-
-static unsigned long __kprobes __check_ls(unsigned long cpsr)
-{
-	cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
-	return (~cpsr) & PSR_C_BIT;
-}
-
-static unsigned long __kprobes __check_ge(unsigned long cpsr)
-{
-	cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-	return (~cpsr) & PSR_N_BIT;
-}
-
-static unsigned long __kprobes __check_lt(unsigned long cpsr)
-{
-	cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-	return cpsr & PSR_N_BIT;
-}
-
-static unsigned long __kprobes __check_gt(unsigned long cpsr)
-{
-	unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-	temp |= (cpsr << 1);			 /* PSR_N_BIT |= PSR_Z_BIT */
-	return (~temp) & PSR_N_BIT;
-}
-
-static unsigned long __kprobes __check_le(unsigned long cpsr)
-{
-	unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
-	temp |= (cpsr << 1);			 /* PSR_N_BIT |= PSR_Z_BIT */
-	return temp & PSR_N_BIT;
-}
-
-static unsigned long __kprobes __check_al(unsigned long cpsr)
-{
-	return true;
-}
-
-kprobe_check_cc * const kprobe_condition_checks[16] = {
-	&__check_eq, &__check_ne, &__check_cs, &__check_cc,
-	&__check_mi, &__check_pl, &__check_vs, &__check_vc,
-	&__check_hi, &__check_ls, &__check_ge, &__check_lt,
-	&__check_gt, &__check_le, &__check_al, &__check_al
-};
-
-
-void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs)
-{
-}
-
-void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs)
-{
-	p->ainsn.insn_fn();
-}
-
-static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes simulate_ldm1stm1(probes_opcode_t insn,
+		struct arch_probes_insn *asi,
+		struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rn = (insn >> 16) & 0xf;
 	int lbit = insn & (1 << 20);
 	int wbit = insn & (1 << 21);
@@ -223,24 +59,31 @@ static void __kprobes simulate_ldm1stm1(struct kprobe *p, struct pt_regs *regs)
 	}
 }
 
-static void __kprobes simulate_stm1_pc(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes simulate_stm1_pc(probes_opcode_t insn,
+	struct arch_probes_insn *asi,
+	struct pt_regs *regs)
 {
-	regs->ARM_pc = (long)p->addr + str_pc_offset;
-	simulate_ldm1stm1(p, regs);
-	regs->ARM_pc = (long)p->addr + 4;
+	unsigned long addr = regs->ARM_pc - 4;
+
+	regs->ARM_pc = (long)addr + str_pc_offset;
+	simulate_ldm1stm1(insn, asi, regs);
+	regs->ARM_pc = (long)addr + 4;
 }
 
-static void __kprobes simulate_ldm1_pc(struct kprobe *p, struct pt_regs *regs)
+static void __kprobes simulate_ldm1_pc(probes_opcode_t insn,
+	struct arch_probes_insn *asi,
+	struct pt_regs *regs)
 {
-	simulate_ldm1stm1(p, regs);
+	simulate_ldm1stm1(insn, asi, regs);
 	load_write_pc(regs->ARM_pc, regs);
 }
 
 static void __kprobes
-emulate_generic_r0_12_noflags(struct kprobe *p, struct pt_regs *regs)
+emulate_generic_r0_12_noflags(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
 	register void *rregs asm("r1") = regs;
-	register void *rfn asm("lr") = p->ainsn.insn_fn;
+	register void *rfn asm("lr") = asi->insn_fn;
 
 	__asm__ __volatile__ (
 		"stmdb	sp!, {%[regs], r11}	\n\t"
@@ -264,22 +107,27 @@ emulate_generic_r0_12_noflags(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-emulate_generic_r2_14_noflags(struct kprobe *p, struct pt_regs *regs)
+emulate_generic_r2_14_noflags(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	emulate_generic_r0_12_noflags(p, (struct pt_regs *)(regs->uregs+2));
+	emulate_generic_r0_12_noflags(insn, asi,
+		(struct pt_regs *)(regs->uregs+2));
 }
 
 static void __kprobes
-emulate_ldm_r3_15(struct kprobe *p, struct pt_regs *regs)
+emulate_ldm_r3_15(probes_opcode_t insn,
+	struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	emulate_generic_r0_12_noflags(p, (struct pt_regs *)(regs->uregs+3));
+	emulate_generic_r0_12_noflags(insn, asi,
+		(struct pt_regs *)(regs->uregs+3));
 	load_write_pc(regs->ARM_pc, regs);
 }
 
-enum kprobe_insn __kprobes
-kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+enum probes_insn __kprobes
+kprobe_decode_ldmstm(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *h)
 {
-	kprobe_insn_handler_t *handler = 0;
+	probes_insn_handler_t *handler = 0;
 	unsigned reglist = insn & 0xffff;
 	int is_ldm = insn & 0x100000;
 	int rn = (insn >> 16) & 0xf;
@@ -319,260 +167,3 @@ kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	return INSN_GOOD_NO_SLOT;
 }
 
-
-/*
- * Prepare an instruction slot to receive an instruction for emulating.
- * This is done by placing a subroutine return after the location where the
- * instruction will be placed. We also modify ARM instructions to be
- * unconditional as the condition code will already be checked before any
- * emulation handler is called.
- */
-static kprobe_opcode_t __kprobes
-prepare_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
-								bool thumb)
-{
-#ifdef CONFIG_THUMB2_KERNEL
-	if (thumb) {
-		u16 *thumb_insn = (u16 *)asi->insn;
-		thumb_insn[1] = 0x4770; /* Thumb bx lr */
-		thumb_insn[2] = 0x4770; /* Thumb bx lr */
-		return insn;
-	}
-	asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
-#else
-	asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
-#endif
-	/* Make an ARM instruction unconditional */
-	if (insn < 0xe0000000)
-		insn = (insn | 0xe0000000) & ~0x10000000;
-	return insn;
-}
-
-/*
- * Write a (probably modified) instruction into the slot previously prepared by
- * prepare_emulated_insn
- */
-static void  __kprobes
-set_emulated_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
-								bool thumb)
-{
-#ifdef CONFIG_THUMB2_KERNEL
-	if (thumb) {
-		u16 *ip = (u16 *)asi->insn;
-		if (is_wide_instruction(insn))
-			*ip++ = insn >> 16;
-		*ip++ = insn;
-		return;
-	}
-#endif
-	asi->insn[0] = insn;
-}
-
-/*
- * When we modify the register numbers encoded in an instruction to be emulated,
- * the new values come from this define. For ARM and 32-bit Thumb instructions
- * this gives...
- *
- *	bit position	  16  12   8   4   0
- *	---------------+---+---+---+---+---+
- *	register	 r2  r0  r1  --  r3
- */
-#define INSN_NEW_BITS		0x00020103
-
-/* Each nibble has same value as that at INSN_NEW_BITS bit 16 */
-#define INSN_SAMEAS16_BITS	0x22222222
-
-/*
- * Validate and modify each of the registers encoded in an instruction.
- *
- * Each nibble in regs contains a value from enum decode_reg_type. For each
- * non-zero value, the corresponding nibble in pinsn is validated and modified
- * according to the type.
- */
-static bool __kprobes decode_regs(kprobe_opcode_t* pinsn, u32 regs)
-{
-	kprobe_opcode_t insn = *pinsn;
-	kprobe_opcode_t mask = 0xf; /* Start at least significant nibble */
-
-	for (; regs != 0; regs >>= 4, mask <<= 4) {
-
-		kprobe_opcode_t new_bits = INSN_NEW_BITS;
-
-		switch (regs & 0xf) {
-
-		case REG_TYPE_NONE:
-			/* Nibble not a register, skip to next */
-			continue;
-
-		case REG_TYPE_ANY:
-			/* Any register is allowed */
-			break;
-
-		case REG_TYPE_SAMEAS16:
-			/* Replace register with same as at bit position 16 */
-			new_bits = INSN_SAMEAS16_BITS;
-			break;
-
-		case REG_TYPE_SP:
-			/* Only allow SP (R13) */
-			if ((insn ^ 0xdddddddd) & mask)
-				goto reject;
-			break;
-
-		case REG_TYPE_PC:
-			/* Only allow PC (R15) */
-			if ((insn ^ 0xffffffff) & mask)
-				goto reject;
-			break;
-
-		case REG_TYPE_NOSP:
-			/* Reject SP (R13) */
-			if (((insn ^ 0xdddddddd) & mask) == 0)
-				goto reject;
-			break;
-
-		case REG_TYPE_NOSPPC:
-		case REG_TYPE_NOSPPCX:
-			/* Reject SP and PC (R13 and R15) */
-			if (((insn ^ 0xdddddddd) & 0xdddddddd & mask) == 0)
-				goto reject;
-			break;
-
-		case REG_TYPE_NOPCWB:
-			if (!is_writeback(insn))
-				break; /* No writeback, so any register is OK */
-			/* fall through... */
-		case REG_TYPE_NOPC:
-		case REG_TYPE_NOPCX:
-			/* Reject PC (R15) */
-			if (((insn ^ 0xffffffff) & mask) == 0)
-				goto reject;
-			break;
-		}
-
-		/* Replace value of nibble with new register number... */
-		insn &= ~mask;
-		insn |= new_bits & mask;
-	}
-
-	*pinsn = insn;
-	return true;
-
-reject:
-	return false;
-}
-
-static const int decode_struct_sizes[NUM_DECODE_TYPES] = {
-	[DECODE_TYPE_TABLE]	= sizeof(struct decode_table),
-	[DECODE_TYPE_CUSTOM]	= sizeof(struct decode_custom),
-	[DECODE_TYPE_SIMULATE]	= sizeof(struct decode_simulate),
-	[DECODE_TYPE_EMULATE]	= sizeof(struct decode_emulate),
-	[DECODE_TYPE_OR]	= sizeof(struct decode_or),
-	[DECODE_TYPE_REJECT]	= sizeof(struct decode_reject)
-};
-
-/*
- * kprobe_decode_insn operates on data tables in order to decode an ARM
- * architecture instruction onto which a kprobe has been placed.
- *
- * These instruction decoding tables are a concatenation of entries each
- * of which consist of one of the following structs:
- *
- *	decode_table
- *	decode_custom
- *	decode_simulate
- *	decode_emulate
- *	decode_or
- *	decode_reject
- *
- * Each of these starts with a struct decode_header which has the following
- * fields:
- *
- *	type_regs
- *	mask
- *	value
- *
- * The least significant DECODE_TYPE_BITS of type_regs contains a value
- * from enum decode_type, this indicates which of the decode_* structs
- * the entry contains. The value DECODE_TYPE_END indicates the end of the
- * table.
- *
- * When the table is parsed, each entry is checked in turn to see if it
- * matches the instruction to be decoded using the test:
- *
- *	(insn & mask) == value
- *
- * If no match is found before the end of the table is reached then decoding
- * fails with INSN_REJECTED.
- *
- * When a match is found, decode_regs() is called to validate and modify each
- * of the registers encoded in the instruction; the data it uses to do this
- * is (type_regs >> DECODE_TYPE_BITS). A validation failure will cause decoding
- * to fail with INSN_REJECTED.
- *
- * Once the instruction has passed the above tests, further processing
- * depends on the type of the table entry's decode struct.
- *
- */
-int __kprobes
-kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
-				const union decode_item *table, bool thumb)
-{
-	const struct decode_header *h = (struct decode_header *)table;
-	const struct decode_header *next;
-	bool matched = false;
-
-	insn = prepare_emulated_insn(insn, asi, thumb);
-
-	for (;; h = next) {
-		enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK;
-		u32 regs = h->type_regs.bits >> DECODE_TYPE_BITS;
-
-		if (type == DECODE_TYPE_END)
-			return INSN_REJECTED;
-
-		next = (struct decode_header *)
-				((uintptr_t)h + decode_struct_sizes[type]);
-
-		if (!matched && (insn & h->mask.bits) != h->value.bits)
-			continue;
-
-		if (!decode_regs(&insn, regs))
-			return INSN_REJECTED;
-
-		switch (type) {
-
-		case DECODE_TYPE_TABLE: {
-			struct decode_table *d = (struct decode_table *)h;
-			next = (struct decode_header *)d->table.table;
-			break;
-		}
-
-		case DECODE_TYPE_CUSTOM: {
-			struct decode_custom *d = (struct decode_custom *)h;
-			return (*d->decoder.decoder)(insn, asi);
-		}
-
-		case DECODE_TYPE_SIMULATE: {
-			struct decode_simulate *d = (struct decode_simulate *)h;
-			asi->insn_handler = d->handler.handler;
-			return INSN_GOOD_NO_SLOT;
-		}
-
-		case DECODE_TYPE_EMULATE: {
-			struct decode_emulate *d = (struct decode_emulate *)h;
-			asi->insn_handler = d->handler.handler;
-			set_emulated_insn(insn, asi, thumb);
-			return INSN_GOOD;
-		}
-
-		case DECODE_TYPE_OR:
-			matched = true;
-			break;
-
-		case DECODE_TYPE_REJECT:
-		default:
-			return INSN_REJECTED;
-		}
-		}
-	}

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-thumb.c

@@ -8,41 +8,25 @@
  * published by the Free Software Foundation.
  */
 
+#include <linux/types.h>
 #include <linux/kernel.h>
+#include <linux/ptrace.h>
 #include <linux/kprobes.h>
-#include <linux/module.h>
 
 #include "kprobes.h"
+#include "probes-thumb.h"
 
+/* These emulation encodings are functionally equivalent... */
+#define t32_emulate_rd8rn16rm0ra12_noflags \
+		t32_emulate_rdlo12rdhi8rn16rm0_noflags
 
-/*
- * 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)
-
-/*
- * Return the PC value for a probe in thumb code.
- * This is the address of the probed instruction plus 4.
- * We subtract one because the address will have bit zero set to indicate
- * a pointer to thumb code.
- */
-static inline unsigned long __kprobes thumb_probe_pc(struct kprobe *p)
-{
-	return (unsigned long)p->addr - 1 + 4;
-}
+/* t32 thumb actions */
 
 static void __kprobes
-t32_simulate_table_branch(struct kprobe *p, struct pt_regs *regs)
+t32_simulate_table_branch(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
 
@@ -59,19 +43,19 @@ t32_simulate_table_branch(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t32_simulate_mrs(struct kprobe *p, struct pt_regs *regs)
+t32_simulate_mrs(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rd = (insn >> 8) & 0xf;
 	unsigned long mask = 0xf8ff03df; /* Mask out execution state */
 	regs->uregs[rd] = regs->ARM_cpsr & mask;
 }
 
 static void __kprobes
-t32_simulate_cond_branch(struct kprobe *p, struct pt_regs *regs)
+t32_simulate_cond_branch(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc;
 
 	long offset = insn & 0x7ff;		/* imm11 */
 	offset += (insn & 0x003f0000) >> 5;	/* imm6 */
@@ -82,20 +66,21 @@ t32_simulate_cond_branch(struct kprobe *p, struct pt_regs *regs)
 	regs->ARM_pc = pc + (offset * 2);
 }
 
-static enum kprobe_insn __kprobes
-t32_decode_cond_branch(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static enum probes_insn __kprobes
+t32_decode_cond_branch(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *d)
 {
 	int cc = (insn >> 22) & 0xf;
-	asi->insn_check_cc = kprobe_condition_checks[cc];
+	asi->insn_check_cc = probes_condition_checks[cc];
 	asi->insn_handler = t32_simulate_cond_branch;
 	return INSN_GOOD_NO_SLOT;
 }
 
 static void __kprobes
-t32_simulate_branch(struct kprobe *p, struct pt_regs *regs)
+t32_simulate_branch(probes_opcode_t insn,
+		    struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc;
 
 	long offset = insn & 0x7ff;		/* imm11 */
 	offset += (insn & 0x03ff0000) >> 5;	/* imm10 */
@@ -108,7 +93,7 @@ t32_simulate_branch(struct kprobe *p, struct pt_regs *regs)
 
 	if (insn & (1 << 14)) {
 		/* BL or BLX */
-		regs->ARM_lr = (unsigned long)p->addr + 4;
+		regs->ARM_lr = regs->ARM_pc | 1;
 		if (!(insn & (1 << 12))) {
 			/* BLX so switch to ARM mode */
 			regs->ARM_cpsr &= ~PSR_T_BIT;
@@ -120,10 +105,10 @@ t32_simulate_branch(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t32_simulate_ldr_literal(struct kprobe *p, struct pt_regs *regs)
+t32_simulate_ldr_literal(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long addr = thumb_probe_pc(p) & ~3;
+	unsigned long addr = regs->ARM_pc & ~3;
 	int rt = (insn >> 12) & 0xf;
 	unsigned long rtv;
 
@@ -157,10 +142,11 @@ t32_simulate_ldr_literal(struct kprobe *p, struct pt_regs *regs)
 	regs->uregs[rt] = rtv;
 }
 
-static enum kprobe_insn __kprobes
-t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static enum probes_insn __kprobes
+t32_decode_ldmstm(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *d)
 {
-	enum kprobe_insn ret = kprobe_decode_ldmstm(insn, asi);
+	enum probes_insn ret = kprobe_decode_ldmstm(insn, asi, d);
 
 	/* Fixup modified instruction to have halfwords in correct order...*/
 	insn = asi->insn[0];
@@ -171,10 +157,10 @@ t32_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 }
 
 static void __kprobes
-t32_emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs)
+t32_emulate_ldrdstrd(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p) & ~3;
+	unsigned long pc = regs->ARM_pc & ~3;
 	int rt1 = (insn >> 12) & 0xf;
 	int rt2 = (insn >> 8) & 0xf;
 	int rn = (insn >> 16) & 0xf;
@@ -187,7 +173,7 @@ t32_emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs)
 	__asm__ __volatile__ (
 		"blx    %[fn]"
 		: "=r" (rt1v), "=r" (rt2v), "=r" (rnv)
-		: "0" (rt1v), "1" (rt2v), "2" (rnv), [fn] "r" (p->ainsn.insn_fn)
+		: "0" (rt1v), "1" (rt2v), "2" (rnv), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -198,9 +184,9 @@ t32_emulate_ldrdstrd(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t32_emulate_ldrstr(struct kprobe *p, struct pt_regs *regs)
+t32_emulate_ldrstr(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rt = (insn >> 12) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
@@ -212,7 +198,7 @@ t32_emulate_ldrstr(struct kprobe *p, struct pt_regs *regs)
 	__asm__ __volatile__ (
 		"blx    %[fn]"
 		: "=r" (rtv), "=r" (rnv)
-		: "0" (rtv), "1" (rnv), "r" (rmv), [fn] "r" (p->ainsn.insn_fn)
+		: "0" (rtv), "1" (rnv), "r" (rmv), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -224,9 +210,9 @@ t32_emulate_ldrstr(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t32_emulate_rd8rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs)
+t32_emulate_rd8rn16rm0_rwflags(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rd = (insn >> 8) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 	int rm = insn & 0xf;
@@ -242,7 +228,7 @@ t32_emulate_rd8rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs)
 		"mrs	%[cpsr], cpsr		\n\t"
 		: "=r" (rdv), [cpsr] "=r" (cpsr)
 		: "0" (rdv), "r" (rnv), "r" (rmv),
-		  "1" (cpsr), [fn] "r" (p->ainsn.insn_fn)
+		  "1" (cpsr), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -251,10 +237,10 @@ t32_emulate_rd8rn16rm0_rwflags(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t32_emulate_rd8pc16_noflags(struct kprobe *p, struct pt_regs *regs)
+t32_emulate_rd8pc16_noflags(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc;
 	int rd = (insn >> 8) & 0xf;
 
 	register unsigned long rdv asm("r1") = regs->uregs[rd];
@@ -263,7 +249,7 @@ t32_emulate_rd8pc16_noflags(struct kprobe *p, struct pt_regs *regs)
 	__asm__ __volatile__ (
 		"blx    %[fn]"
 		: "=r" (rdv)
-		: "0" (rdv), "r" (rnv), [fn] "r" (p->ainsn.insn_fn)
+		: "0" (rdv), "r" (rnv), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -271,9 +257,9 @@ t32_emulate_rd8pc16_noflags(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t32_emulate_rd8rn16_noflags(struct kprobe *p, struct pt_regs *regs)
+t32_emulate_rd8rn16_noflags(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rd = (insn >> 8) & 0xf;
 	int rn = (insn >> 16) & 0xf;
 
@@ -283,7 +269,7 @@ t32_emulate_rd8rn16_noflags(struct kprobe *p, struct pt_regs *regs)
 	__asm__ __volatile__ (
 		"blx    %[fn]"
 		: "=r" (rdv)
-		: "0" (rdv), "r" (rnv), [fn] "r" (p->ainsn.insn_fn)
+		: "0" (rdv), "r" (rnv), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -291,9 +277,10 @@ t32_emulate_rd8rn16_noflags(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t32_emulate_rdlo12rdhi8rn16rm0_noflags(struct kprobe *p, struct pt_regs *regs)
+t32_emulate_rdlo12rdhi8rn16rm0_noflags(probes_opcode_t insn,
+		struct arch_probes_insn *asi,
+		struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rdlo = (insn >> 12) & 0xf;
 	int rdhi = (insn >> 8) & 0xf;
 	int rn = (insn >> 16) & 0xf;
@@ -308,674 +295,43 @@ t32_emulate_rdlo12rdhi8rn16rm0_noflags(struct kprobe *p, struct pt_regs *regs)
 		"blx    %[fn]"
 		: "=r" (rdlov), "=r" (rdhiv)
 		: "0" (rdlov), "1" (rdhiv), "r" (rnv), "r" (rmv),
-		  [fn] "r" (p->ainsn.insn_fn)
+		  [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
 	regs->uregs[rdlo] = rdlov;
 	regs->uregs[rdhi] = rdhiv;
 }
-
-/* These emulation encodings are functionally equivalent... */
-#define t32_emulate_rd8rn16rm0ra12_noflags \
-		t32_emulate_rdlo12rdhi8rn16rm0_noflags
-
-static const union decode_item t32_table_1110_100x_x0xx[] = {
-	/* Load/store multiple instructions */
-
-	/* Rn is PC		1110 100x x0xx 1111 xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfe4f0000, 0xe80f0000),
-
-	/* SRS			1110 1000 00x0 xxxx xxxx xxxx xxxx xxxx */
-	/* RFE			1110 1000 00x1 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xffc00000, 0xe8000000),
-	/* SRS			1110 1001 10x0 xxxx xxxx xxxx xxxx xxxx */
-	/* RFE			1110 1001 10x1 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xffc00000, 0xe9800000),
-
-	/* STM Rn, {...pc}	1110 100x x0x0 xxxx 1xxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfe508000, 0xe8008000),
-	/* LDM Rn, {...lr,pc}	1110 100x x0x1 xxxx 11xx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfe50c000, 0xe810c000),
-	/* LDM/STM Rn, {...sp}	1110 100x x0xx xxxx xx1x xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfe402000, 0xe8002000),
-
-	/* STMIA		1110 1000 10x0 xxxx xxxx xxxx xxxx xxxx */
-	/* LDMIA		1110 1000 10x1 xxxx xxxx xxxx xxxx xxxx */
-	/* STMDB		1110 1001 00x0 xxxx xxxx xxxx xxxx xxxx */
-	/* LDMDB		1110 1001 00x1 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_CUSTOM	(0xfe400000, 0xe8000000, t32_decode_ldmstm),
-
-	DECODE_END
-};
-
-static const union decode_item t32_table_1110_100x_x1xx[] = {
-	/* Load/store dual, load/store exclusive, table branch */
-
-	/* STRD (immediate)	1110 1000 x110 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRD (immediate)	1110 1000 x111 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_OR	(0xff600000, 0xe8600000),
-	/* STRD (immediate)	1110 1001 x1x0 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRD (immediate)	1110 1001 x1x1 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xff400000, 0xe9400000, t32_emulate_ldrdstrd,
-						 REGS(NOPCWB, NOSPPC, NOSPPC, 0, 0)),
-
-	/* TBB			1110 1000 1101 xxxx xxxx xxxx 0000 xxxx */
-	/* TBH			1110 1000 1101 xxxx xxxx xxxx 0001 xxxx */
-	DECODE_SIMULATEX(0xfff000e0, 0xe8d00000, t32_simulate_table_branch,
-						 REGS(NOSP, 0, 0, 0, NOSPPC)),
-
-	/* STREX		1110 1000 0100 xxxx xxxx xxxx xxxx xxxx */
-	/* LDREX		1110 1000 0101 xxxx xxxx xxxx xxxx xxxx */
-	/* STREXB		1110 1000 1100 xxxx xxxx xxxx 0100 xxxx */
-	/* STREXH		1110 1000 1100 xxxx xxxx xxxx 0101 xxxx */
-	/* STREXD		1110 1000 1100 xxxx xxxx xxxx 0111 xxxx */
-	/* LDREXB		1110 1000 1101 xxxx xxxx xxxx 0100 xxxx */
-	/* LDREXH		1110 1000 1101 xxxx xxxx xxxx 0101 xxxx */
-	/* LDREXD		1110 1000 1101 xxxx xxxx xxxx 0111 xxxx */
-	/* And unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item t32_table_1110_101x[] = {
-	/* Data-processing (shifted register)				*/
-
-	/* TST			1110 1010 0001 xxxx xxxx 1111 xxxx xxxx */
-	/* TEQ			1110 1010 1001 xxxx xxxx 1111 xxxx xxxx */
-	DECODE_EMULATEX	(0xff700f00, 0xea100f00, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOSPPC, 0, 0, 0, NOSPPC)),
-
-	/* CMN			1110 1011 0001 xxxx xxxx 1111 xxxx xxxx */
-	DECODE_OR	(0xfff00f00, 0xeb100f00),
-	/* CMP			1110 1011 1011 xxxx xxxx 1111 xxxx xxxx */
-	DECODE_EMULATEX	(0xfff00f00, 0xebb00f00, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOPC, 0, 0, 0, NOSPPC)),
-
-	/* MOV			1110 1010 010x 1111 xxxx xxxx xxxx xxxx */
-	/* MVN			1110 1010 011x 1111 xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xffcf0000, 0xea4f0000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(0, 0, NOSPPC, 0, NOSPPC)),
-
-	/* ???			1110 1010 101x xxxx xxxx xxxx xxxx xxxx */
-	/* ???			1110 1010 111x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xffa00000, 0xeaa00000),
-	/* ???			1110 1011 001x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xffe00000, 0xeb200000),
-	/* ???			1110 1011 100x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xffe00000, 0xeb800000),
-	/* ???			1110 1011 111x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xffe00000, 0xebe00000),
-
-	/* ADD/SUB SP, SP, Rm, LSL #0..3				*/
-	/*			1110 1011 x0xx 1101 x000 1101 xx00 xxxx */
-	DECODE_EMULATEX	(0xff4f7f30, 0xeb0d0d00, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(SP, 0, SP, 0, NOSPPC)),
-
-	/* ADD/SUB SP, SP, Rm, shift					*/
-	/*			1110 1011 x0xx 1101 xxxx 1101 xxxx xxxx */
-	DECODE_REJECT	(0xff4f0f00, 0xeb0d0d00),
-
-	/* ADD/SUB Rd, SP, Rm, shift					*/
-	/*			1110 1011 x0xx 1101 xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xff4f0000, 0xeb0d0000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(SP, 0, NOPC, 0, NOSPPC)),
-
-	/* AND			1110 1010 000x xxxx xxxx xxxx xxxx xxxx */
-	/* BIC			1110 1010 001x xxxx xxxx xxxx xxxx xxxx */
-	/* ORR			1110 1010 010x xxxx xxxx xxxx xxxx xxxx */
-	/* ORN			1110 1010 011x xxxx xxxx xxxx xxxx xxxx */
-	/* EOR			1110 1010 100x xxxx xxxx xxxx xxxx xxxx */
-	/* PKH			1110 1010 110x xxxx xxxx xxxx xxxx xxxx */
-	/* ADD			1110 1011 000x xxxx xxxx xxxx xxxx xxxx */
-	/* ADC			1110 1011 010x xxxx xxxx xxxx xxxx xxxx */
-	/* SBC			1110 1011 011x xxxx xxxx xxxx xxxx xxxx */
-	/* SUB			1110 1011 101x xxxx xxxx xxxx xxxx xxxx */
-	/* RSB			1110 1011 110x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfe000000, 0xea000000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)),
-
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_0x0x___0[] = {
-	/* Data-processing (modified immediate)				*/
-
-	/* TST			1111 0x00 0001 xxxx 0xxx 1111 xxxx xxxx */
-	/* TEQ			1111 0x00 1001 xxxx 0xxx 1111 xxxx xxxx */
-	DECODE_EMULATEX	(0xfb708f00, 0xf0100f00, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOSPPC, 0, 0, 0, 0)),
-
-	/* CMN			1111 0x01 0001 xxxx 0xxx 1111 xxxx xxxx */
-	DECODE_OR	(0xfbf08f00, 0xf1100f00),
-	/* CMP			1111 0x01 1011 xxxx 0xxx 1111 xxxx xxxx */
-	DECODE_EMULATEX	(0xfbf08f00, 0xf1b00f00, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOPC, 0, 0, 0, 0)),
-
-	/* MOV			1111 0x00 010x 1111 0xxx xxxx xxxx xxxx */
-	/* MVN			1111 0x00 011x 1111 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfbcf8000, 0xf04f0000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(0, 0, NOSPPC, 0, 0)),
-
-	/* ???			1111 0x00 101x xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfbe08000, 0xf0a00000),
-	/* ???			1111 0x00 110x xxxx 0xxx xxxx xxxx xxxx */
-	/* ???			1111 0x00 111x xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfbc08000, 0xf0c00000),
-	/* ???			1111 0x01 001x xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfbe08000, 0xf1200000),
-	/* ???			1111 0x01 100x xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfbe08000, 0xf1800000),
-	/* ???			1111 0x01 111x xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfbe08000, 0xf1e00000),
-
-	/* ADD Rd, SP, #imm	1111 0x01 000x 1101 0xxx xxxx xxxx xxxx */
-	/* SUB Rd, SP, #imm	1111 0x01 101x 1101 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfb4f8000, 0xf10d0000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(SP, 0, NOPC, 0, 0)),
-
-	/* AND			1111 0x00 000x xxxx 0xxx xxxx xxxx xxxx */
-	/* BIC			1111 0x00 001x xxxx 0xxx xxxx xxxx xxxx */
-	/* ORR			1111 0x00 010x xxxx 0xxx xxxx xxxx xxxx */
-	/* ORN			1111 0x00 011x xxxx 0xxx xxxx xxxx xxxx */
-	/* EOR			1111 0x00 100x xxxx 0xxx xxxx xxxx xxxx */
-	/* ADD			1111 0x01 000x xxxx 0xxx xxxx xxxx xxxx */
-	/* ADC			1111 0x01 010x xxxx 0xxx xxxx xxxx xxxx */
-	/* SBC			1111 0x01 011x xxxx 0xxx xxxx xxxx xxxx */
-	/* SUB			1111 0x01 101x xxxx 0xxx xxxx xxxx xxxx */
-	/* RSB			1111 0x01 110x xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfa008000, 0xf0000000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOSPPC, 0, NOSPPC, 0, 0)),
-
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_0x1x___0[] = {
-	/* Data-processing (plain binary immediate)			*/
-
-	/* ADDW Rd, PC, #imm	1111 0x10 0000 1111 0xxx xxxx xxxx xxxx */
-	DECODE_OR	(0xfbff8000, 0xf20f0000),
-	/* SUBW	Rd, PC, #imm	1111 0x10 1010 1111 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfbff8000, 0xf2af0000, t32_emulate_rd8pc16_noflags,
-						 REGS(PC, 0, NOSPPC, 0, 0)),
-
-	/* ADDW SP, SP, #imm	1111 0x10 0000 1101 0xxx 1101 xxxx xxxx */
-	DECODE_OR	(0xfbff8f00, 0xf20d0d00),
-	/* SUBW	SP, SP, #imm	1111 0x10 1010 1101 0xxx 1101 xxxx xxxx */
-	DECODE_EMULATEX	(0xfbff8f00, 0xf2ad0d00, t32_emulate_rd8rn16_noflags,
-						 REGS(SP, 0, SP, 0, 0)),
-
-	/* ADDW			1111 0x10 0000 xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_OR	(0xfbf08000, 0xf2000000),
-	/* SUBW			1111 0x10 1010 xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfbf08000, 0xf2a00000, t32_emulate_rd8rn16_noflags,
-						 REGS(NOPCX, 0, NOSPPC, 0, 0)),
-
-	/* MOVW			1111 0x10 0100 xxxx 0xxx xxxx xxxx xxxx */
-	/* MOVT			1111 0x10 1100 xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfb708000, 0xf2400000, t32_emulate_rd8rn16_noflags,
-						 REGS(0, 0, NOSPPC, 0, 0)),
-
-	/* SSAT16		1111 0x11 0010 xxxx 0000 xxxx 00xx xxxx */
-	/* SSAT			1111 0x11 00x0 xxxx 0xxx xxxx xxxx xxxx */
-	/* USAT16		1111 0x11 1010 xxxx 0000 xxxx 00xx xxxx */
-	/* USAT			1111 0x11 10x0 xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfb508000, 0xf3000000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOSPPC, 0, NOSPPC, 0, 0)),
-
-	/* SFBX			1111 0x11 0100 xxxx 0xxx xxxx xxxx xxxx */
-	/* UFBX			1111 0x11 1100 xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfb708000, 0xf3400000, t32_emulate_rd8rn16_noflags,
-						 REGS(NOSPPC, 0, NOSPPC, 0, 0)),
-
-	/* BFC			1111 0x11 0110 1111 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfbff8000, 0xf36f0000, t32_emulate_rd8rn16_noflags,
-						 REGS(0, 0, NOSPPC, 0, 0)),
-
-	/* BFI			1111 0x11 0110 xxxx 0xxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfbf08000, 0xf3600000, t32_emulate_rd8rn16_noflags,
-						 REGS(NOSPPCX, 0, NOSPPC, 0, 0)),
-
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_0xxx___1[] = {
-	/* Branches and miscellaneous control				*/
-
-	/* YIELD		1111 0011 1010 xxxx 10x0 x000 0000 0001 */
-	DECODE_OR	(0xfff0d7ff, 0xf3a08001),
-	/* SEV			1111 0011 1010 xxxx 10x0 x000 0000 0100 */
-	DECODE_EMULATE	(0xfff0d7ff, 0xf3a08004, kprobe_emulate_none),
-	/* NOP			1111 0011 1010 xxxx 10x0 x000 0000 0000 */
-	/* WFE			1111 0011 1010 xxxx 10x0 x000 0000 0010 */
-	/* WFI			1111 0011 1010 xxxx 10x0 x000 0000 0011 */
-	DECODE_SIMULATE	(0xfff0d7fc, 0xf3a08000, kprobe_simulate_nop),
-
-	/* MRS Rd, CPSR		1111 0011 1110 xxxx 10x0 xxxx xxxx xxxx */
-	DECODE_SIMULATEX(0xfff0d000, 0xf3e08000, t32_simulate_mrs,
-						 REGS(0, 0, NOSPPC, 0, 0)),
-
-	/*
-	 * Unsupported instructions
-	 *			1111 0x11 1xxx xxxx 10x0 xxxx xxxx xxxx
-	 *
-	 * MSR			1111 0011 100x xxxx 10x0 xxxx xxxx xxxx
-	 * DBG hint		1111 0011 1010 xxxx 10x0 x000 1111 xxxx
-	 * Unallocated hints	1111 0011 1010 xxxx 10x0 x000 xxxx xxxx
-	 * CPS			1111 0011 1010 xxxx 10x0 xxxx xxxx xxxx
-	 * CLREX/DSB/DMB/ISB	1111 0011 1011 xxxx 10x0 xxxx xxxx xxxx
-	 * BXJ			1111 0011 1100 xxxx 10x0 xxxx xxxx xxxx
-	 * SUBS PC,LR,#<imm8>	1111 0011 1101 xxxx 10x0 xxxx xxxx xxxx
-	 * MRS Rd, SPSR		1111 0011 1111 xxxx 10x0 xxxx xxxx xxxx
-	 * SMC			1111 0111 1111 xxxx 1000 xxxx xxxx xxxx
-	 * UNDEFINED		1111 0111 1111 xxxx 1010 xxxx xxxx xxxx
-	 * ???			1111 0111 1xxx xxxx 1010 xxxx xxxx xxxx
-	 */
-	DECODE_REJECT	(0xfb80d000, 0xf3808000),
-
-	/* Bcc			1111 0xxx xxxx xxxx 10x0 xxxx xxxx xxxx */
-	DECODE_CUSTOM	(0xf800d000, 0xf0008000, t32_decode_cond_branch),
-
-	/* BLX			1111 0xxx xxxx xxxx 11x0 xxxx xxxx xxx0 */
-	DECODE_OR	(0xf800d001, 0xf000c000),
-	/* B			1111 0xxx xxxx xxxx 10x1 xxxx xxxx xxxx */
-	/* BL			1111 0xxx xxxx xxxx 11x1 xxxx xxxx xxxx */
-	DECODE_SIMULATE	(0xf8009000, 0xf0009000, t32_simulate_branch),
-
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_100x_x0x1__1111[] = {
-	/* Memory hints							*/
-
-	/* PLD (literal)	1111 1000 x001 1111 1111 xxxx xxxx xxxx */
-	/* PLI (literal)	1111 1001 x001 1111 1111 xxxx xxxx xxxx */
-	DECODE_SIMULATE	(0xfe7ff000, 0xf81ff000, kprobe_simulate_nop),
-
-	/* PLD{W} (immediate)	1111 1000 10x1 xxxx 1111 xxxx xxxx xxxx */
-	DECODE_OR	(0xffd0f000, 0xf890f000),
-	/* PLD{W} (immediate)	1111 1000 00x1 xxxx 1111 1100 xxxx xxxx */
-	DECODE_OR	(0xffd0ff00, 0xf810fc00),
-	/* PLI (immediate)	1111 1001 1001 xxxx 1111 xxxx xxxx xxxx */
-	DECODE_OR	(0xfff0f000, 0xf990f000),
-	/* PLI (immediate)	1111 1001 0001 xxxx 1111 1100 xxxx xxxx */
-	DECODE_SIMULATEX(0xfff0ff00, 0xf910fc00, kprobe_simulate_nop,
-						 REGS(NOPCX, 0, 0, 0, 0)),
-
-	/* PLD{W} (register)	1111 1000 00x1 xxxx 1111 0000 00xx xxxx */
-	DECODE_OR	(0xffd0ffc0, 0xf810f000),
-	/* PLI (register)	1111 1001 0001 xxxx 1111 0000 00xx xxxx */
-	DECODE_SIMULATEX(0xfff0ffc0, 0xf910f000, kprobe_simulate_nop,
-						 REGS(NOPCX, 0, 0, 0, NOSPPC)),
-
-	/* Other unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_100x[] = {
-	/* Store/Load single data item					*/
-
-	/* ???			1111 100x x11x xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfe600000, 0xf8600000),
-
-	/* ???			1111 1001 0101 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xfff00000, 0xf9500000),
-
-	/* ???			1111 100x 0xxx xxxx xxxx 10x0 xxxx xxxx */
-	DECODE_REJECT	(0xfe800d00, 0xf8000800),
-
-	/* STRBT		1111 1000 0000 xxxx xxxx 1110 xxxx xxxx */
-	/* STRHT		1111 1000 0010 xxxx xxxx 1110 xxxx xxxx */
-	/* STRT			1111 1000 0100 xxxx xxxx 1110 xxxx xxxx */
-	/* LDRBT		1111 1000 0001 xxxx xxxx 1110 xxxx xxxx */
-	/* LDRSBT		1111 1001 0001 xxxx xxxx 1110 xxxx xxxx */
-	/* LDRHT		1111 1000 0011 xxxx xxxx 1110 xxxx xxxx */
-	/* LDRSHT		1111 1001 0011 xxxx xxxx 1110 xxxx xxxx */
-	/* LDRT			1111 1000 0101 xxxx xxxx 1110 xxxx xxxx */
-	DECODE_REJECT	(0xfe800f00, 0xf8000e00),
-
-	/* STR{,B,H} Rn,[PC...]	1111 1000 xxx0 1111 xxxx xxxx xxxx xxxx */
-	DECODE_REJECT	(0xff1f0000, 0xf80f0000),
-
-	/* STR{,B,H} PC,[Rn...]	1111 1000 xxx0 xxxx 1111 xxxx xxxx xxxx */
-	DECODE_REJECT	(0xff10f000, 0xf800f000),
-
-	/* LDR (literal)	1111 1000 x101 1111 xxxx xxxx xxxx xxxx */
-	DECODE_SIMULATEX(0xff7f0000, 0xf85f0000, t32_simulate_ldr_literal,
-						 REGS(PC, ANY, 0, 0, 0)),
-
-	/* STR (immediate)	1111 1000 0100 xxxx xxxx 1xxx xxxx xxxx */
-	/* LDR (immediate)	1111 1000 0101 xxxx xxxx 1xxx xxxx xxxx */
-	DECODE_OR	(0xffe00800, 0xf8400800),
-	/* STR (immediate)	1111 1000 1100 xxxx xxxx xxxx xxxx xxxx */
-	/* LDR (immediate)	1111 1000 1101 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xffe00000, 0xf8c00000, t32_emulate_ldrstr,
-						 REGS(NOPCX, ANY, 0, 0, 0)),
-
-	/* STR (register)	1111 1000 0100 xxxx xxxx 0000 00xx xxxx */
-	/* LDR (register)	1111 1000 0101 xxxx xxxx 0000 00xx xxxx */
-	DECODE_EMULATEX	(0xffe00fc0, 0xf8400000, t32_emulate_ldrstr,
-						 REGS(NOPCX, ANY, 0, 0, NOSPPC)),
-
-	/* LDRB (literal)	1111 1000 x001 1111 xxxx xxxx xxxx xxxx */
-	/* LDRSB (literal)	1111 1001 x001 1111 xxxx xxxx xxxx xxxx */
-	/* LDRH (literal)	1111 1000 x011 1111 xxxx xxxx xxxx xxxx */
-	/* LDRSH (literal)	1111 1001 x011 1111 xxxx xxxx xxxx xxxx */
-	DECODE_SIMULATEX(0xfe5f0000, 0xf81f0000, t32_simulate_ldr_literal,
-						 REGS(PC, NOSPPCX, 0, 0, 0)),
-
-	/* STRB (immediate)	1111 1000 0000 xxxx xxxx 1xxx xxxx xxxx */
-	/* STRH (immediate)	1111 1000 0010 xxxx xxxx 1xxx xxxx xxxx */
-	/* LDRB (immediate)	1111 1000 0001 xxxx xxxx 1xxx xxxx xxxx */
-	/* LDRSB (immediate)	1111 1001 0001 xxxx xxxx 1xxx xxxx xxxx */
-	/* LDRH (immediate)	1111 1000 0011 xxxx xxxx 1xxx xxxx xxxx */
-	/* LDRSH (immediate)	1111 1001 0011 xxxx xxxx 1xxx xxxx xxxx */
-	DECODE_OR	(0xfec00800, 0xf8000800),
-	/* STRB (immediate)	1111 1000 1000 xxxx xxxx xxxx xxxx xxxx */
-	/* STRH (immediate)	1111 1000 1010 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRB (immediate)	1111 1000 1001 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRSB (immediate)	1111 1001 1001 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRH (immediate)	1111 1000 1011 xxxx xxxx xxxx xxxx xxxx */
-	/* LDRSH (immediate)	1111 1001 1011 xxxx xxxx xxxx xxxx xxxx */
-	DECODE_EMULATEX	(0xfec00000, 0xf8800000, t32_emulate_ldrstr,
-						 REGS(NOPCX, NOSPPCX, 0, 0, 0)),
-
-	/* STRB (register)	1111 1000 0000 xxxx xxxx 0000 00xx xxxx */
-	/* STRH (register)	1111 1000 0010 xxxx xxxx 0000 00xx xxxx */
-	/* LDRB (register)	1111 1000 0001 xxxx xxxx 0000 00xx xxxx */
-	/* LDRSB (register)	1111 1001 0001 xxxx xxxx 0000 00xx xxxx */
-	/* LDRH (register)	1111 1000 0011 xxxx xxxx 0000 00xx xxxx */
-	/* LDRSH (register)	1111 1001 0011 xxxx xxxx 0000 00xx xxxx */
-	DECODE_EMULATEX	(0xfe800fc0, 0xf8000000, t32_emulate_ldrstr,
-						 REGS(NOPCX, NOSPPCX, 0, 0, NOSPPC)),
-
-	/* Other unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_1010___1111[] = {
-	/* Data-processing (register)					*/
-
-	/* ???			1111 1010 011x xxxx 1111 xxxx 1xxx xxxx */
-	DECODE_REJECT	(0xffe0f080, 0xfa60f080),
-
-	/* SXTH			1111 1010 0000 1111 1111 xxxx 1xxx xxxx */
-	/* UXTH			1111 1010 0001 1111 1111 xxxx 1xxx xxxx */
-	/* SXTB16		1111 1010 0010 1111 1111 xxxx 1xxx xxxx */
-	/* UXTB16		1111 1010 0011 1111 1111 xxxx 1xxx xxxx */
-	/* SXTB			1111 1010 0100 1111 1111 xxxx 1xxx xxxx */
-	/* UXTB			1111 1010 0101 1111 1111 xxxx 1xxx xxxx */
-	DECODE_EMULATEX	(0xff8ff080, 0xfa0ff080, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(0, 0, NOSPPC, 0, NOSPPC)),
-
-
-	/* ???			1111 1010 1xxx xxxx 1111 xxxx 0x11 xxxx */
-	DECODE_REJECT	(0xff80f0b0, 0xfa80f030),
-	/* ???			1111 1010 1x11 xxxx 1111 xxxx 0xxx xxxx */
-	DECODE_REJECT	(0xffb0f080, 0xfab0f000),
-
-	/* SADD16		1111 1010 1001 xxxx 1111 xxxx 0000 xxxx */
-	/* SASX			1111 1010 1010 xxxx 1111 xxxx 0000 xxxx */
-	/* SSAX			1111 1010 1110 xxxx 1111 xxxx 0000 xxxx */
-	/* SSUB16		1111 1010 1101 xxxx 1111 xxxx 0000 xxxx */
-	/* SADD8		1111 1010 1000 xxxx 1111 xxxx 0000 xxxx */
-	/* SSUB8		1111 1010 1100 xxxx 1111 xxxx 0000 xxxx */
-
-	/* QADD16		1111 1010 1001 xxxx 1111 xxxx 0001 xxxx */
-	/* QASX			1111 1010 1010 xxxx 1111 xxxx 0001 xxxx */
-	/* QSAX			1111 1010 1110 xxxx 1111 xxxx 0001 xxxx */
-	/* QSUB16		1111 1010 1101 xxxx 1111 xxxx 0001 xxxx */
-	/* QADD8		1111 1010 1000 xxxx 1111 xxxx 0001 xxxx */
-	/* QSUB8		1111 1010 1100 xxxx 1111 xxxx 0001 xxxx */
-
-	/* SHADD16		1111 1010 1001 xxxx 1111 xxxx 0010 xxxx */
-	/* SHASX		1111 1010 1010 xxxx 1111 xxxx 0010 xxxx */
-	/* SHSAX		1111 1010 1110 xxxx 1111 xxxx 0010 xxxx */
-	/* SHSUB16		1111 1010 1101 xxxx 1111 xxxx 0010 xxxx */
-	/* SHADD8		1111 1010 1000 xxxx 1111 xxxx 0010 xxxx */
-	/* SHSUB8		1111 1010 1100 xxxx 1111 xxxx 0010 xxxx */
-
-	/* UADD16		1111 1010 1001 xxxx 1111 xxxx 0100 xxxx */
-	/* UASX			1111 1010 1010 xxxx 1111 xxxx 0100 xxxx */
-	/* USAX			1111 1010 1110 xxxx 1111 xxxx 0100 xxxx */
-	/* USUB16		1111 1010 1101 xxxx 1111 xxxx 0100 xxxx */
-	/* UADD8		1111 1010 1000 xxxx 1111 xxxx 0100 xxxx */
-	/* USUB8		1111 1010 1100 xxxx 1111 xxxx 0100 xxxx */
-
-	/* UQADD16		1111 1010 1001 xxxx 1111 xxxx 0101 xxxx */
-	/* UQASX		1111 1010 1010 xxxx 1111 xxxx 0101 xxxx */
-	/* UQSAX		1111 1010 1110 xxxx 1111 xxxx 0101 xxxx */
-	/* UQSUB16		1111 1010 1101 xxxx 1111 xxxx 0101 xxxx */
-	/* UQADD8		1111 1010 1000 xxxx 1111 xxxx 0101 xxxx */
-	/* UQSUB8		1111 1010 1100 xxxx 1111 xxxx 0101 xxxx */
-
-	/* UHADD16		1111 1010 1001 xxxx 1111 xxxx 0110 xxxx */
-	/* UHASX		1111 1010 1010 xxxx 1111 xxxx 0110 xxxx */
-	/* UHSAX		1111 1010 1110 xxxx 1111 xxxx 0110 xxxx */
-	/* UHSUB16		1111 1010 1101 xxxx 1111 xxxx 0110 xxxx */
-	/* UHADD8		1111 1010 1000 xxxx 1111 xxxx 0110 xxxx */
-	/* UHSUB8		1111 1010 1100 xxxx 1111 xxxx 0110 xxxx */
-	DECODE_OR	(0xff80f080, 0xfa80f000),
-
-	/* SXTAH		1111 1010 0000 xxxx 1111 xxxx 1xxx xxxx */
-	/* UXTAH		1111 1010 0001 xxxx 1111 xxxx 1xxx xxxx */
-	/* SXTAB16		1111 1010 0010 xxxx 1111 xxxx 1xxx xxxx */
-	/* UXTAB16		1111 1010 0011 xxxx 1111 xxxx 1xxx xxxx */
-	/* SXTAB		1111 1010 0100 xxxx 1111 xxxx 1xxx xxxx */
-	/* UXTAB		1111 1010 0101 xxxx 1111 xxxx 1xxx xxxx */
-	DECODE_OR	(0xff80f080, 0xfa00f080),
-
-	/* QADD			1111 1010 1000 xxxx 1111 xxxx 1000 xxxx */
-	/* QDADD		1111 1010 1000 xxxx 1111 xxxx 1001 xxxx */
-	/* QSUB			1111 1010 1000 xxxx 1111 xxxx 1010 xxxx */
-	/* QDSUB		1111 1010 1000 xxxx 1111 xxxx 1011 xxxx */
-	DECODE_OR	(0xfff0f0c0, 0xfa80f080),
-
-	/* SEL			1111 1010 1010 xxxx 1111 xxxx 1000 xxxx */
-	DECODE_OR	(0xfff0f0f0, 0xfaa0f080),
-
-	/* LSL			1111 1010 000x xxxx 1111 xxxx 0000 xxxx */
-	/* LSR			1111 1010 001x xxxx 1111 xxxx 0000 xxxx */
-	/* ASR			1111 1010 010x xxxx 1111 xxxx 0000 xxxx */
-	/* ROR			1111 1010 011x xxxx 1111 xxxx 0000 xxxx */
-	DECODE_EMULATEX	(0xff80f0f0, 0xfa00f000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)),
-
-	/* CLZ			1111 1010 1010 xxxx 1111 xxxx 1000 xxxx */
-	DECODE_OR	(0xfff0f0f0, 0xfab0f080),
-
-	/* REV			1111 1010 1001 xxxx 1111 xxxx 1000 xxxx */
-	/* REV16		1111 1010 1001 xxxx 1111 xxxx 1001 xxxx */
-	/* RBIT			1111 1010 1001 xxxx 1111 xxxx 1010 xxxx */
-	/* REVSH		1111 1010 1001 xxxx 1111 xxxx 1011 xxxx */
-	DECODE_EMULATEX	(0xfff0f0c0, 0xfa90f080, t32_emulate_rd8rn16_noflags,
-						 REGS(NOSPPC, 0, NOSPPC, 0, SAMEAS16)),
-
-	/* Other unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_1011_0[] = {
-	/* Multiply, multiply accumulate, and absolute difference	*/
-
-	/* ???			1111 1011 0000 xxxx 1111 xxxx 0001 xxxx */
-	DECODE_REJECT	(0xfff0f0f0, 0xfb00f010),
-	/* ???			1111 1011 0111 xxxx 1111 xxxx 0001 xxxx */
-	DECODE_REJECT	(0xfff0f0f0, 0xfb70f010),
-
-	/* SMULxy		1111 1011 0001 xxxx 1111 xxxx 00xx xxxx */
-	DECODE_OR	(0xfff0f0c0, 0xfb10f000),
-	/* MUL			1111 1011 0000 xxxx 1111 xxxx 0000 xxxx */
-	/* SMUAD{X}		1111 1011 0010 xxxx 1111 xxxx 000x xxxx */
-	/* SMULWy		1111 1011 0011 xxxx 1111 xxxx 000x xxxx */
-	/* SMUSD{X}		1111 1011 0100 xxxx 1111 xxxx 000x xxxx */
-	/* SMMUL{R}		1111 1011 0101 xxxx 1111 xxxx 000x xxxx */
-	/* USAD8		1111 1011 0111 xxxx 1111 xxxx 0000 xxxx */
-	DECODE_EMULATEX	(0xff80f0e0, 0xfb00f000, t32_emulate_rd8rn16rm0_rwflags,
-						 REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)),
-
-	/* ???			1111 1011 0111 xxxx xxxx xxxx 0001 xxxx */
-	DECODE_REJECT	(0xfff000f0, 0xfb700010),
-
-	/* SMLAxy		1111 1011 0001 xxxx xxxx xxxx 00xx xxxx */
-	DECODE_OR	(0xfff000c0, 0xfb100000),
-	/* MLA			1111 1011 0000 xxxx xxxx xxxx 0000 xxxx */
-	/* MLS			1111 1011 0000 xxxx xxxx xxxx 0001 xxxx */
-	/* SMLAD{X}		1111 1011 0010 xxxx xxxx xxxx 000x xxxx */
-	/* SMLAWy		1111 1011 0011 xxxx xxxx xxxx 000x xxxx */
-	/* SMLSD{X}		1111 1011 0100 xxxx xxxx xxxx 000x xxxx */
-	/* SMMLA{R}		1111 1011 0101 xxxx xxxx xxxx 000x xxxx */
-	/* SMMLS{R}		1111 1011 0110 xxxx xxxx xxxx 000x xxxx */
-	/* USADA8		1111 1011 0111 xxxx xxxx xxxx 0000 xxxx */
-	DECODE_EMULATEX	(0xff8000c0, 0xfb000000, t32_emulate_rd8rn16rm0ra12_noflags,
-						 REGS(NOSPPC, NOSPPCX, NOSPPC, 0, NOSPPC)),
-
-	/* Other unallocated instructions...				*/
-	DECODE_END
-};
-
-static const union decode_item t32_table_1111_1011_1[] = {
-	/* Long multiply, long multiply accumulate, and divide		*/
-
-	/* UMAAL		1111 1011 1110 xxxx xxxx xxxx 0110 xxxx */
-	DECODE_OR	(0xfff000f0, 0xfbe00060),
-	/* SMLALxy		1111 1011 1100 xxxx xxxx xxxx 10xx xxxx */
-	DECODE_OR	(0xfff000c0, 0xfbc00080),
-	/* SMLALD{X}		1111 1011 1100 xxxx xxxx xxxx 110x xxxx */
-	/* SMLSLD{X}		1111 1011 1101 xxxx xxxx xxxx 110x xxxx */
-	DECODE_OR	(0xffe000e0, 0xfbc000c0),
-	/* SMULL		1111 1011 1000 xxxx xxxx xxxx 0000 xxxx */
-	/* UMULL		1111 1011 1010 xxxx xxxx xxxx 0000 xxxx */
-	/* SMLAL		1111 1011 1100 xxxx xxxx xxxx 0000 xxxx */
-	/* UMLAL		1111 1011 1110 xxxx xxxx xxxx 0000 xxxx */
-	DECODE_EMULATEX	(0xff9000f0, 0xfb800000, t32_emulate_rdlo12rdhi8rn16rm0_noflags,
-						 REGS(NOSPPC, NOSPPC, NOSPPC, 0, NOSPPC)),
-
-	/* SDIV			1111 1011 1001 xxxx xxxx xxxx 1111 xxxx */
-	/* UDIV			1111 1011 1011 xxxx xxxx xxxx 1111 xxxx */
-	/* Other unallocated instructions...				*/
-	DECODE_END
-};
-
-const union decode_item kprobe_decode_thumb32_table[] = {
-
-	/*
-	 * Load/store multiple instructions
-	 *			1110 100x x0xx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xfe400000, 0xe8000000, t32_table_1110_100x_x0xx),
-
-	/*
-	 * Load/store dual, load/store exclusive, table branch
-	 *			1110 100x x1xx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xfe400000, 0xe8400000, t32_table_1110_100x_x1xx),
-
-	/*
-	 * Data-processing (shifted register)
-	 *			1110 101x xxxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xfe000000, 0xea000000, t32_table_1110_101x),
-
-	/*
-	 * Coprocessor instructions
-	 *			1110 11xx xxxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_REJECT	(0xfc000000, 0xec000000),
-
-	/*
-	 * Data-processing (modified immediate)
-	 *			1111 0x0x xxxx xxxx 0xxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xfa008000, 0xf0000000, t32_table_1111_0x0x___0),
-
-	/*
-	 * Data-processing (plain binary immediate)
-	 *			1111 0x1x xxxx xxxx 0xxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xfa008000, 0xf2000000, t32_table_1111_0x1x___0),
-
-	/*
-	 * Branches and miscellaneous control
-	 *			1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xf8008000, 0xf0008000, t32_table_1111_0xxx___1),
-
-	/*
-	 * Advanced SIMD element or structure load/store instructions
-	 *			1111 1001 xxx0 xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_REJECT	(0xff100000, 0xf9000000),
-
-	/*
-	 * Memory hints
-	 *			1111 100x x0x1 xxxx 1111 xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xfe50f000, 0xf810f000, t32_table_1111_100x_x0x1__1111),
-
-	/*
-	 * Store single data item
-	 *			1111 1000 xxx0 xxxx xxxx xxxx xxxx xxxx
-	 * Load single data items
-	 *			1111 100x xxx1 xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xfe000000, 0xf8000000, t32_table_1111_100x),
-
-	/*
-	 * Data-processing (register)
-	 *			1111 1010 xxxx xxxx 1111 xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xff00f000, 0xfa00f000, t32_table_1111_1010___1111),
-
-	/*
-	 * Multiply, multiply accumulate, and absolute difference
-	 *			1111 1011 0xxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xff800000, 0xfb000000, t32_table_1111_1011_0),
-
-	/*
-	 * Long multiply, long multiply accumulate, and divide
-	 *			1111 1011 1xxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xff800000, 0xfb800000, t32_table_1111_1011_1),
-
-	/*
-	 * Coprocessor instructions
-	 *			1111 11xx xxxx xxxx xxxx xxxx xxxx xxxx
-	 */
-	DECODE_END
-};
-#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
-EXPORT_SYMBOL_GPL(kprobe_decode_thumb32_table);
-#endif
+/* t16 thumb actions */
 
 static void __kprobes
-t16_simulate_bxblx(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_bxblx(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc + 2;
 	int rm = (insn >> 3) & 0xf;
 	unsigned long rmv = (rm == 15) ? pc : regs->uregs[rm];
 
 	if (insn & (1 << 7)) /* BLX ? */
-		regs->ARM_lr = (unsigned long)p->addr + 2;
+		regs->ARM_lr = regs->ARM_pc | 1;
 
 	bx_write_pc(rmv, regs);
 }
 
 static void __kprobes
-t16_simulate_ldr_literal(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_ldr_literal(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long* base = (unsigned long *)(thumb_probe_pc(p) & ~3);
+	unsigned long *base = (unsigned long *)((regs->ARM_pc + 2) & ~3);
 	long index = insn & 0xff;
 	int rt = (insn >> 8) & 0x7;
 	regs->uregs[rt] = base[index];
 }
 
 static void __kprobes
-t16_simulate_ldrstr_sp_relative(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_ldrstr_sp_relative(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	unsigned long* base = (unsigned long *)regs->ARM_sp;
 	long index = insn & 0xff;
 	int rt = (insn >> 8) & 0x7;
@@ -986,20 +342,20 @@ t16_simulate_ldrstr_sp_relative(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t16_simulate_reladr(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_reladr(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	unsigned long base = (insn & 0x800) ? regs->ARM_sp
-					    : (thumb_probe_pc(p) & ~3);
+					    : ((regs->ARM_pc + 2) & ~3);
 	long offset = insn & 0xff;
 	int rt = (insn >> 8) & 0x7;
 	regs->uregs[rt] = base + offset * 4;
 }
 
 static void __kprobes
-t16_simulate_add_sp_imm(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_add_sp_imm(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	long imm = insn & 0x7f;
 	if (insn & 0x80) /* SUB */
 		regs->ARM_sp -= imm * 4;
@@ -1008,21 +364,22 @@ t16_simulate_add_sp_imm(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t16_simulate_cbz(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_cbz(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
 	int rn = insn & 0x7;
-	kprobe_opcode_t nonzero = regs->uregs[rn] ? insn : ~insn;
+	probes_opcode_t nonzero = regs->uregs[rn] ? insn : ~insn;
 	if (nonzero & 0x800) {
 		long i = insn & 0x200;
 		long imm5 = insn & 0xf8;
-		unsigned long pc = thumb_probe_pc(p);
+		unsigned long pc = regs->ARM_pc + 2;
 		regs->ARM_pc = pc + (i >> 3) + (imm5 >> 2);
 	}
 }
 
 static void __kprobes
-t16_simulate_it(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_it(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
 	/*
 	 * The 8 IT state bits are split into two parts in CPSR:
@@ -1030,7 +387,6 @@ t16_simulate_it(struct kprobe *p, struct pt_regs *regs)
 	 *	ITSTATE<7:2> are in CPSR<15:10>
 	 * The new IT state is in the lower byte of insn.
 	 */
-	kprobe_opcode_t insn = p->opcode;
 	unsigned long cpsr = regs->ARM_cpsr;
 	cpsr &= ~PSR_IT_MASK;
 	cpsr |= (insn & 0xfc) << 8;
@@ -1039,50 +395,54 @@ t16_simulate_it(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t16_singlestep_it(struct kprobe *p, struct pt_regs *regs)
+t16_singlestep_it(probes_opcode_t insn,
+		  struct arch_probes_insn *asi, struct pt_regs *regs)
 {
 	regs->ARM_pc += 2;
-	t16_simulate_it(p, regs);
+	t16_simulate_it(insn, asi, regs);
 }
 
-static enum kprobe_insn __kprobes
-t16_decode_it(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static enum probes_insn __kprobes
+t16_decode_it(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *d)
 {
 	asi->insn_singlestep = t16_singlestep_it;
 	return INSN_GOOD_NO_SLOT;
 }
 
 static void __kprobes
-t16_simulate_cond_branch(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_cond_branch(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc + 2;
 	long offset = insn & 0x7f;
 	offset -= insn & 0x80; /* Apply sign bit */
 	regs->ARM_pc = pc + (offset * 2);
 }
 
-static enum kprobe_insn __kprobes
-t16_decode_cond_branch(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static enum probes_insn __kprobes
+t16_decode_cond_branch(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *d)
 {
 	int cc = (insn >> 8) & 0xf;
-	asi->insn_check_cc = kprobe_condition_checks[cc];
+	asi->insn_check_cc = probes_condition_checks[cc];
 	asi->insn_handler = t16_simulate_cond_branch;
 	return INSN_GOOD_NO_SLOT;
 }
 
 static void __kprobes
-t16_simulate_branch(struct kprobe *p, struct pt_regs *regs)
+t16_simulate_branch(probes_opcode_t insn,
+		   struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc + 2;
 	long offset = insn & 0x3ff;
 	offset -= insn & 0x400; /* Apply sign bit */
 	regs->ARM_pc = pc + (offset * 2);
 }
 
 static unsigned long __kprobes
-t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs)
+t16_emulate_loregs(probes_opcode_t insn,
+		   struct arch_probes_insn *asi, struct pt_regs *regs)
 {
 	unsigned long oldcpsr = regs->ARM_cpsr;
 	unsigned long newcpsr;
@@ -1095,7 +455,7 @@ t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs)
 		"mrs	%[newcpsr], cpsr	\n\t"
 		: [newcpsr] "=r" (newcpsr)
 		: [oldcpsr] "r" (oldcpsr), [regs] "r" (regs),
-		  [fn] "r" (p->ainsn.insn_fn)
+		  [fn] "r" (asi->insn_fn)
 		: "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7",
 		  "lr", "memory", "cc"
 		);
@@ -1104,24 +464,26 @@ t16_emulate_loregs(struct kprobe *p, struct pt_regs *regs)
 }
 
 static void __kprobes
-t16_emulate_loregs_rwflags(struct kprobe *p, struct pt_regs *regs)
+t16_emulate_loregs_rwflags(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	regs->ARM_cpsr = t16_emulate_loregs(p, regs);
+	regs->ARM_cpsr = t16_emulate_loregs(insn, asi, regs);
 }
 
 static void __kprobes
-t16_emulate_loregs_noitrwflags(struct kprobe *p, struct pt_regs *regs)
+t16_emulate_loregs_noitrwflags(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	unsigned long cpsr = t16_emulate_loregs(p, regs);
+	unsigned long cpsr = t16_emulate_loregs(insn, asi, regs);
 	if (!in_it_block(cpsr))
 		regs->ARM_cpsr = cpsr;
 }
 
 static void __kprobes
-t16_emulate_hiregs(struct kprobe *p, struct pt_regs *regs)
+t16_emulate_hiregs(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
-	kprobe_opcode_t insn = p->opcode;
-	unsigned long pc = thumb_probe_pc(p);
+	unsigned long pc = regs->ARM_pc + 2;
 	int rdn = (insn & 0x7) | ((insn & 0x80) >> 4);
 	int rm = (insn >> 3) & 0xf;
 
@@ -1137,7 +499,7 @@ t16_emulate_hiregs(struct kprobe *p, struct pt_regs *regs)
 		"blx    %[fn]			\n\t"
 		"mrs	%[cpsr], cpsr		\n\t"
 		: "=r" (rdnv), [cpsr] "=r" (cpsr)
-		: "0" (rdnv), "r" (rmv), "1" (cpsr), [fn] "r" (p->ainsn.insn_fn)
+		: "0" (rdnv), "r" (rmv), "1" (cpsr), [fn] "r" (asi->insn_fn)
 		: "lr", "memory", "cc"
 	);
 
@@ -1148,8 +510,9 @@ t16_emulate_hiregs(struct kprobe *p, struct pt_regs *regs)
 	regs->ARM_cpsr = (regs->ARM_cpsr & ~APSR_MASK) | (cpsr & APSR_MASK);
 }
 
-static enum kprobe_insn __kprobes
-t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static enum probes_insn __kprobes
+t16_decode_hiregs(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *d)
 {
 	insn &= ~0x00ff;
 	insn |= 0x001; /* Set Rdn = R1 and Rm = R0 */
@@ -1159,7 +522,8 @@ t16_decode_hiregs(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 }
 
 static void __kprobes
-t16_emulate_push(struct kprobe *p, struct pt_regs *regs)
+t16_emulate_push(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
 	__asm__ __volatile__ (
 		"ldr	r9, [%[regs], #13*4]	\n\t"
@@ -1168,14 +532,15 @@ t16_emulate_push(struct kprobe *p, struct pt_regs *regs)
 		"blx	%[fn]			\n\t"
 		"str	r9, [%[regs], #13*4]	\n\t"
 		:
-		: [regs] "r" (regs), [fn] "r" (p->ainsn.insn_fn)
+		: [regs] "r" (regs), [fn] "r" (asi->insn_fn)
 		: "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r8", "r9",
 		  "lr", "memory", "cc"
 		);
 }
 
-static enum kprobe_insn __kprobes
-t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static enum probes_insn __kprobes
+t16_decode_push(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *d)
 {
 	/*
 	 * To simulate a PUSH we use a Thumb-2 "STMDB R9!, {registers}"
@@ -1189,7 +554,8 @@ t16_decode_push(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 }
 
 static void __kprobes
-t16_emulate_pop_nopc(struct kprobe *p, struct pt_regs *regs)
+t16_emulate_pop_nopc(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
 	__asm__ __volatile__ (
 		"ldr	r9, [%[regs], #13*4]	\n\t"
@@ -1198,14 +564,15 @@ t16_emulate_pop_nopc(struct kprobe *p, struct pt_regs *regs)
 		"stmia	%[regs], {r0-r7}	\n\t"
 		"str	r9, [%[regs], #13*4]	\n\t"
 		:
-		: [regs] "r" (regs), [fn] "r" (p->ainsn.insn_fn)
+		: [regs] "r" (regs), [fn] "r" (asi->insn_fn)
 		: "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r9",
 		  "lr", "memory", "cc"
 		);
 }
 
 static void __kprobes
-t16_emulate_pop_pc(struct kprobe *p, struct pt_regs *regs)
+t16_emulate_pop_pc(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
 {
 	register unsigned long pc asm("r8");
 
@@ -1216,7 +583,7 @@ t16_emulate_pop_pc(struct kprobe *p, struct pt_regs *regs)
 		"stmia	%[regs], {r0-r7}	\n\t"
 		"str	r9, [%[regs], #13*4]	\n\t"
 		: "=r" (pc)
-		: [regs] "r" (regs), [fn] "r" (p->ainsn.insn_fn)
+		: [regs] "r" (regs), [fn] "r" (asi->insn_fn)
 		: "r0", "r1", "r2", "r3", "r4", "r5", "r6", "r7", "r9",
 		  "lr", "memory", "cc"
 		);
@@ -1224,8 +591,9 @@ t16_emulate_pop_pc(struct kprobe *p, struct pt_regs *regs)
 	bx_write_pc(pc, regs);
 }
 
-static enum kprobe_insn __kprobes
-t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi)
+static enum probes_insn __kprobes
+t16_decode_pop(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *d)
 {
 	/*
 	 * To simulate a POP we use a Thumb-2 "LDMDB R9!, {registers}"
@@ -1239,231 +607,56 @@ t16_decode_pop(kprobe_opcode_t insn, struct arch_specific_insn *asi)
 	return INSN_GOOD;
 }
 
-static const union decode_item t16_table_1011[] = {
-	/* Miscellaneous 16-bit instructions		    */
-
-	/* ADD (SP plus immediate)	1011 0000 0xxx xxxx */
-	/* SUB (SP minus immediate)	1011 0000 1xxx xxxx */
-	DECODE_SIMULATE	(0xff00, 0xb000, t16_simulate_add_sp_imm),
-
-	/* CBZ				1011 00x1 xxxx xxxx */
-	/* CBNZ				1011 10x1 xxxx xxxx */
-	DECODE_SIMULATE	(0xf500, 0xb100, t16_simulate_cbz),
-
-	/* SXTH				1011 0010 00xx xxxx */
-	/* SXTB				1011 0010 01xx xxxx */
-	/* UXTH				1011 0010 10xx xxxx */
-	/* UXTB				1011 0010 11xx xxxx */
-	/* REV				1011 1010 00xx xxxx */
-	/* REV16			1011 1010 01xx xxxx */
-	/* ???				1011 1010 10xx xxxx */
-	/* REVSH			1011 1010 11xx xxxx */
-	DECODE_REJECT	(0xffc0, 0xba80),
-	DECODE_EMULATE	(0xf500, 0xb000, t16_emulate_loregs_rwflags),
-
-	/* PUSH				1011 010x xxxx xxxx */
-	DECODE_CUSTOM	(0xfe00, 0xb400, t16_decode_push),
-	/* POP				1011 110x xxxx xxxx */
-	DECODE_CUSTOM	(0xfe00, 0xbc00, t16_decode_pop),
-
-	/*
-	 * If-Then, and hints
-	 *				1011 1111 xxxx xxxx
-	 */
-
-	/* YIELD			1011 1111 0001 0000 */
-	DECODE_OR	(0xffff, 0xbf10),
-	/* SEV				1011 1111 0100 0000 */
-	DECODE_EMULATE	(0xffff, 0xbf40, kprobe_emulate_none),
-	/* NOP				1011 1111 0000 0000 */
-	/* WFE				1011 1111 0010 0000 */
-	/* WFI				1011 1111 0011 0000 */
-	DECODE_SIMULATE	(0xffcf, 0xbf00, kprobe_simulate_nop),
-	/* Unassigned hints		1011 1111 xxxx 0000 */
-	DECODE_REJECT	(0xff0f, 0xbf00),
-	/* IT				1011 1111 xxxx xxxx */
-	DECODE_CUSTOM	(0xff00, 0xbf00, t16_decode_it),
-
-	/* SETEND			1011 0110 010x xxxx */
-	/* CPS				1011 0110 011x xxxx */
-	/* BKPT				1011 1110 xxxx xxxx */
-	/* And unallocated instructions...		    */
-	DECODE_END
+const union decode_action kprobes_t16_actions[NUM_PROBES_T16_ACTIONS] = {
+	[PROBES_T16_ADD_SP] = {.handler = t16_simulate_add_sp_imm},
+	[PROBES_T16_CBZ] = {.handler = t16_simulate_cbz},
+	[PROBES_T16_SIGN_EXTEND] = {.handler = t16_emulate_loregs_rwflags},
+	[PROBES_T16_PUSH] = {.decoder = t16_decode_push},
+	[PROBES_T16_POP] = {.decoder = t16_decode_pop},
+	[PROBES_T16_SEV] = {.handler = probes_emulate_none},
+	[PROBES_T16_WFE] = {.handler = probes_simulate_nop},
+	[PROBES_T16_IT] = {.decoder = t16_decode_it},
+	[PROBES_T16_CMP] = {.handler = t16_emulate_loregs_rwflags},
+	[PROBES_T16_ADDSUB] = {.handler = t16_emulate_loregs_noitrwflags},
+	[PROBES_T16_LOGICAL] = {.handler = t16_emulate_loregs_noitrwflags},
+	[PROBES_T16_LDR_LIT] = {.handler = t16_simulate_ldr_literal},
+	[PROBES_T16_BLX] = {.handler = t16_simulate_bxblx},
+	[PROBES_T16_HIREGOPS] = {.decoder = t16_decode_hiregs},
+	[PROBES_T16_LDRHSTRH] = {.handler = t16_emulate_loregs_rwflags},
+	[PROBES_T16_LDRSTR] = {.handler = t16_simulate_ldrstr_sp_relative},
+	[PROBES_T16_ADR] = {.handler = t16_simulate_reladr},
+	[PROBES_T16_LDMSTM] = {.handler = t16_emulate_loregs_rwflags},
+	[PROBES_T16_BRANCH_COND] = {.decoder = t16_decode_cond_branch},
+	[PROBES_T16_BRANCH] = {.handler = t16_simulate_branch},
 };
 
-const union decode_item kprobe_decode_thumb16_table[] = {
-
-	/*
-	 * Shift (immediate), add, subtract, move, and compare
-	 *				00xx xxxx xxxx xxxx
-	 */
-
-	/* CMP (immediate)		0010 1xxx xxxx xxxx */
-	DECODE_EMULATE	(0xf800, 0x2800, t16_emulate_loregs_rwflags),
-
-	/* ADD (register)		0001 100x xxxx xxxx */
-	/* SUB (register)		0001 101x xxxx xxxx */
-	/* LSL (immediate)		0000 0xxx xxxx xxxx */
-	/* LSR (immediate)		0000 1xxx xxxx xxxx */
-	/* ASR (immediate)		0001 0xxx xxxx xxxx */
-	/* ADD (immediate, Thumb)	0001 110x xxxx xxxx */
-	/* SUB (immediate, Thumb)	0001 111x xxxx xxxx */
-	/* MOV (immediate)		0010 0xxx xxxx xxxx */
-	/* ADD (immediate, Thumb)	0011 0xxx xxxx xxxx */
-	/* SUB (immediate, Thumb)	0011 1xxx xxxx xxxx */
-	DECODE_EMULATE	(0xc000, 0x0000, t16_emulate_loregs_noitrwflags),
-
-	/*
-	 * 16-bit Thumb data-processing instructions
-	 *				0100 00xx xxxx xxxx
-	 */
-
-	/* TST (register)		0100 0010 00xx xxxx */
-	DECODE_EMULATE	(0xffc0, 0x4200, t16_emulate_loregs_rwflags),
-	/* CMP (register)		0100 0010 10xx xxxx */
-	/* CMN (register)		0100 0010 11xx xxxx */
-	DECODE_EMULATE	(0xff80, 0x4280, t16_emulate_loregs_rwflags),
-	/* AND (register)		0100 0000 00xx xxxx */
-	/* EOR (register)		0100 0000 01xx xxxx */
-	/* LSL (register)		0100 0000 10xx xxxx */
-	/* LSR (register)		0100 0000 11xx xxxx */
-	/* ASR (register)		0100 0001 00xx xxxx */
-	/* ADC (register)		0100 0001 01xx xxxx */
-	/* SBC (register)		0100 0001 10xx xxxx */
-	/* ROR (register)		0100 0001 11xx xxxx */
-	/* RSB (immediate)		0100 0010 01xx xxxx */
-	/* ORR (register)		0100 0011 00xx xxxx */
-	/* MUL				0100 0011 00xx xxxx */
-	/* BIC (register)		0100 0011 10xx xxxx */
-	/* MVN (register)		0100 0011 10xx xxxx */
-	DECODE_EMULATE	(0xfc00, 0x4000, t16_emulate_loregs_noitrwflags),
-
-	/*
-	 * Special data instructions and branch and exchange
-	 *				0100 01xx xxxx xxxx
-	 */
-
-	/* BLX pc			0100 0111 1111 1xxx */
-	DECODE_REJECT	(0xfff8, 0x47f8),
-
-	/* BX (register)		0100 0111 0xxx xxxx */
-	/* BLX (register)		0100 0111 1xxx xxxx */
-	DECODE_SIMULATE (0xff00, 0x4700, t16_simulate_bxblx),
-
-	/* ADD pc, pc			0100 0100 1111 1111 */
-	DECODE_REJECT	(0xffff, 0x44ff),
-
-	/* ADD (register)		0100 0100 xxxx xxxx */
-	/* CMP (register)		0100 0101 xxxx xxxx */
-	/* MOV (register)		0100 0110 xxxx xxxx */
-	DECODE_CUSTOM	(0xfc00, 0x4400, t16_decode_hiregs),
-
-	/*
-	 * Load from Literal Pool
-	 * LDR (literal)		0100 1xxx xxxx xxxx
-	 */
-	DECODE_SIMULATE	(0xf800, 0x4800, t16_simulate_ldr_literal),
-
-	/*
-	 * 16-bit Thumb Load/store instructions
-	 *				0101 xxxx xxxx xxxx
-	 *				011x xxxx xxxx xxxx
-	 *				100x xxxx xxxx xxxx
-	 */
-
-	/* STR (register)		0101 000x xxxx xxxx */
-	/* STRH (register)		0101 001x xxxx xxxx */
-	/* STRB (register)		0101 010x xxxx xxxx */
-	/* LDRSB (register)		0101 011x xxxx xxxx */
-	/* LDR (register)		0101 100x xxxx xxxx */
-	/* LDRH (register)		0101 101x xxxx xxxx */
-	/* LDRB (register)		0101 110x xxxx xxxx */
-	/* LDRSH (register)		0101 111x xxxx xxxx */
-	/* STR (immediate, Thumb)	0110 0xxx xxxx xxxx */
-	/* LDR (immediate, Thumb)	0110 1xxx xxxx xxxx */
-	/* STRB (immediate, Thumb)	0111 0xxx xxxx xxxx */
-	/* LDRB (immediate, Thumb)	0111 1xxx xxxx xxxx */
-	DECODE_EMULATE	(0xc000, 0x4000, t16_emulate_loregs_rwflags),
-	/* STRH (immediate, Thumb)	1000 0xxx xxxx xxxx */
-	/* LDRH (immediate, Thumb)	1000 1xxx xxxx xxxx */
-	DECODE_EMULATE	(0xf000, 0x8000, t16_emulate_loregs_rwflags),
-	/* STR (immediate, Thumb)	1001 0xxx xxxx xxxx */
-	/* LDR (immediate, Thumb)	1001 1xxx xxxx xxxx */
-	DECODE_SIMULATE	(0xf000, 0x9000, t16_simulate_ldrstr_sp_relative),
-
-	/*
-	 * Generate PC-/SP-relative address
-	 * ADR (literal)		1010 0xxx xxxx xxxx
-	 * ADD (SP plus immediate)	1010 1xxx xxxx xxxx
-	 */
-	DECODE_SIMULATE	(0xf000, 0xa000, t16_simulate_reladr),
-
-	/*
-	 * Miscellaneous 16-bit instructions
-	 *				1011 xxxx xxxx xxxx
-	 */
-	DECODE_TABLE	(0xf000, 0xb000, t16_table_1011),
-
-	/* STM				1100 0xxx xxxx xxxx */
-	/* LDM				1100 1xxx xxxx xxxx */
-	DECODE_EMULATE	(0xf000, 0xc000, t16_emulate_loregs_rwflags),
-
-	/*
-	 * Conditional branch, and Supervisor Call
-	 */
-
-	/* Permanently UNDEFINED	1101 1110 xxxx xxxx */
-	/* SVC				1101 1111 xxxx xxxx */
-	DECODE_REJECT	(0xfe00, 0xde00),
-
-	/* Conditional branch		1101 xxxx xxxx xxxx */
-	DECODE_CUSTOM	(0xf000, 0xd000, t16_decode_cond_branch),
-
-	/*
-	 * Unconditional branch
-	 * B				1110 0xxx xxxx xxxx
-	 */
-	DECODE_SIMULATE	(0xf800, 0xe000, t16_simulate_branch),
-
-	DECODE_END
+const union decode_action kprobes_t32_actions[NUM_PROBES_T32_ACTIONS] = {
+	[PROBES_T32_LDMSTM] = {.decoder = t32_decode_ldmstm},
+	[PROBES_T32_LDRDSTRD] = {.handler = t32_emulate_ldrdstrd},
+	[PROBES_T32_TABLE_BRANCH] = {.handler = t32_simulate_table_branch},
+	[PROBES_T32_TST] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_MOV] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_ADDSUB] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_LOGICAL] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_CMP] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_ADDWSUBW_PC] = {.handler = t32_emulate_rd8pc16_noflags,},
+	[PROBES_T32_ADDWSUBW] = {.handler = t32_emulate_rd8rn16_noflags},
+	[PROBES_T32_MOVW] = {.handler = t32_emulate_rd8rn16_noflags},
+	[PROBES_T32_SAT] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_BITFIELD] = {.handler = t32_emulate_rd8rn16_noflags},
+	[PROBES_T32_SEV] = {.handler = probes_emulate_none},
+	[PROBES_T32_WFE] = {.handler = probes_simulate_nop},
+	[PROBES_T32_MRS] = {.handler = t32_simulate_mrs},
+	[PROBES_T32_BRANCH_COND] = {.decoder = t32_decode_cond_branch},
+	[PROBES_T32_BRANCH] = {.handler = t32_simulate_branch},
+	[PROBES_T32_PLDI] = {.handler = probes_simulate_nop},
+	[PROBES_T32_LDR_LIT] = {.handler = t32_simulate_ldr_literal},
+	[PROBES_T32_LDRSTR] = {.handler = t32_emulate_ldrstr},
+	[PROBES_T32_SIGN_EXTEND] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_MEDIA] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_REVERSE] = {.handler = t32_emulate_rd8rn16_noflags},
+	[PROBES_T32_MUL_ADD] = {.handler = t32_emulate_rd8rn16rm0_rwflags},
+	[PROBES_T32_MUL_ADD2] = {.handler = t32_emulate_rd8rn16rm0ra12_noflags},
+	[PROBES_T32_MUL_ADD_LONG] = {
+		.handler = t32_emulate_rdlo12rdhi8rn16rm0_noflags},
 };
-#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
-EXPORT_SYMBOL_GPL(kprobe_decode_thumb16_table);
-#endif
-
-static unsigned long __kprobes thumb_check_cc(unsigned long cpsr)
-{
-	if (unlikely(in_it_block(cpsr)))
-		return kprobe_condition_checks[current_cond(cpsr)](cpsr);
-	return true;
-}
-
-static void __kprobes thumb16_singlestep(struct kprobe *p, struct pt_regs *regs)
-{
-	regs->ARM_pc += 2;
-	p->ainsn.insn_handler(p, regs);
-	regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
-}
-
-static void __kprobes thumb32_singlestep(struct kprobe *p, struct pt_regs *regs)
-{
-	regs->ARM_pc += 4;
-	p->ainsn.insn_handler(p, regs);
-	regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
-}
-
-enum kprobe_insn __kprobes
-thumb16_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
-{
-	asi->insn_singlestep = thumb16_singlestep;
-	asi->insn_check_cc = thumb_check_cc;
-	return kprobe_decode_insn(insn, asi, kprobe_decode_thumb16_table, true);
-}
-
-enum kprobe_insn __kprobes
-thumb32_kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi)
-{
-	asi->insn_singlestep = thumb32_singlestep;
-	asi->insn_check_cc = thumb_check_cc;
-	return kprobe_decode_insn(insn, asi, kprobe_decode_thumb32_table, true);
-}

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/kprobes.h

@@ -19,6 +19,8 @@
 #ifndef _ARM_KERNEL_KPROBES_H
 #define _ARM_KERNEL_KPROBES_H
 
+#include "probes.h"
+
 /*
  * These undefined instructions must be unique and
  * reserved solely for kprobes' use.
@@ -27,402 +29,24 @@
 #define KPROBE_THUMB16_BREAKPOINT_INSTRUCTION	0xde18
 #define KPROBE_THUMB32_BREAKPOINT_INSTRUCTION	0xf7f0a018
 
+enum probes_insn __kprobes
+kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_probes_insn *asi,
+		const struct decode_header *h);
 
-enum kprobe_insn {
-	INSN_REJECTED,
-	INSN_GOOD,
-	INSN_GOOD_NO_SLOT
-};
-
-typedef enum kprobe_insn (kprobe_decode_insn_t)(kprobe_opcode_t,
-						struct arch_specific_insn *);
+typedef enum probes_insn (kprobe_decode_insn_t)(probes_opcode_t,
+						struct arch_probes_insn *,
+						bool,
+						const union decode_action *);
 
 #ifdef CONFIG_THUMB2_KERNEL
 
-enum kprobe_insn thumb16_kprobe_decode_insn(kprobe_opcode_t,
-						struct arch_specific_insn *);
-enum kprobe_insn thumb32_kprobe_decode_insn(kprobe_opcode_t,
-						struct arch_specific_insn *);
+extern const union decode_action kprobes_t32_actions[];
+extern const union decode_action kprobes_t16_actions[];
 
 #else /* !CONFIG_THUMB2_KERNEL */
 
-enum kprobe_insn arm_kprobe_decode_insn(kprobe_opcode_t,
-					struct arch_specific_insn *);
-#endif
-
-void __init arm_kprobe_decode_init(void);
-
-extern kprobe_check_cc * const kprobe_condition_checks[16];
-
-
-#if __LINUX_ARM_ARCH__ >= 7
-
-/* str_pc_offset is architecturally defined from ARMv7 onwards */
-#define str_pc_offset 8
-#define find_str_pc_offset()
-
-#else /* __LINUX_ARM_ARCH__ < 7 */
-
-/* We need a run-time check to determine str_pc_offset */
-extern int str_pc_offset;
-void __init find_str_pc_offset(void);
+extern const union decode_action kprobes_arm_actions[];
 
 #endif
 
-
-/*
- * Update ITSTATE after normal execution of an IT block instruction.
- *
- * The 8 IT state bits are split into two parts in CPSR:
- *	ITSTATE<1:0> are in CPSR<26:25>
- *	ITSTATE<7:2> are in CPSR<15:10>
- */
-static inline unsigned long it_advance(unsigned long cpsr)
-	{
-	if ((cpsr & 0x06000400) == 0) {
-		/* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */
-		cpsr &= ~PSR_IT_MASK;
-	} else {
-		/* We need to shift left ITSTATE<4:0> */
-		const unsigned long mask = 0x06001c00;  /* Mask ITSTATE<4:0> */
-		unsigned long it = cpsr & mask;
-		it <<= 1;
-		it |= it >> (27 - 10);  /* Carry ITSTATE<2> to correct place */
-		it &= mask;
-		cpsr &= ~mask;
-		cpsr |= it;
-	}
-	return cpsr;
-}
-
-static inline void __kprobes bx_write_pc(long pcv, struct pt_regs *regs)
-{
-	long cpsr = regs->ARM_cpsr;
-	if (pcv & 0x1) {
-		cpsr |= PSR_T_BIT;
-		pcv &= ~0x1;
-	} else {
-		cpsr &= ~PSR_T_BIT;
-		pcv &= ~0x2;	/* Avoid UNPREDICTABLE address allignment */
-	}
-	regs->ARM_cpsr = cpsr;
-	regs->ARM_pc = pcv;
-}
-
-
-#if __LINUX_ARM_ARCH__ >= 6
-
-/* Kernels built for >= ARMv6 should never run on <= ARMv5 hardware, so... */
-#define load_write_pc_interworks true
-#define test_load_write_pc_interworking()
-
-#else /* __LINUX_ARM_ARCH__ < 6 */
-
-/* We need run-time testing to determine if load_write_pc() should interwork. */
-extern bool load_write_pc_interworks;
-void __init test_load_write_pc_interworking(void);
-
-#endif
-
-static inline void __kprobes load_write_pc(long pcv, struct pt_regs *regs)
-{
-	if (load_write_pc_interworks)
-		bx_write_pc(pcv, regs);
-	else
-		regs->ARM_pc = pcv;
-}
-
-
-#if __LINUX_ARM_ARCH__ >= 7
-
-#define alu_write_pc_interworks true
-#define test_alu_write_pc_interworking()
-
-#elif __LINUX_ARM_ARCH__ <= 5
-
-/* Kernels built for <= ARMv5 should never run on >= ARMv6 hardware, so... */
-#define alu_write_pc_interworks false
-#define test_alu_write_pc_interworking()
-
-#else /* __LINUX_ARM_ARCH__ == 6 */
-
-/* We could be an ARMv6 binary on ARMv7 hardware so we need a run-time check. */
-extern bool alu_write_pc_interworks;
-void __init test_alu_write_pc_interworking(void);
-
-#endif /* __LINUX_ARM_ARCH__ == 6 */
-
-static inline void __kprobes alu_write_pc(long pcv, struct pt_regs *regs)
-{
-	if (alu_write_pc_interworks)
-		bx_write_pc(pcv, regs);
-	else
-		regs->ARM_pc = pcv;
-}
-
-
-void __kprobes kprobe_simulate_nop(struct kprobe *p, struct pt_regs *regs);
-void __kprobes kprobe_emulate_none(struct kprobe *p, struct pt_regs *regs);
-
-enum kprobe_insn __kprobes
-kprobe_decode_ldmstm(kprobe_opcode_t insn, struct arch_specific_insn *asi);
-
-/*
- * Test if load/store instructions writeback the address register.
- * if P (bit 24) == 0 or W (bit 21) == 1
- */
-#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000)
-
-/*
- * The following definitions and macros are used to build instruction
- * decoding tables for use by kprobe_decode_insn.
- *
- * These tables are a concatenation of entries each of which consist of one of
- * the decode_* structs. All of the fields in every type of decode structure
- * are of the union type decode_item, therefore the entire decode table can be
- * viewed as an array of these and declared like:
- *
- *	static const union decode_item table_name[] = {};
- *
- * In order to construct each entry in the table, macros are used to
- * initialise a number of sequential decode_item values in a layout which
- * matches the relevant struct. E.g. DECODE_SIMULATE initialise a struct
- * decode_simulate by initialising four decode_item objects like this...
- *
- *	{.bits = _type},
- *	{.bits = _mask},
- *	{.bits = _value},
- *	{.handler = _handler},
- *
- * Initialising a specified member of the union means that the compiler
- * will produce a warning if the argument is of an incorrect type.
- *
- * Below is a list of each of the macros used to initialise entries and a
- * description of the action performed when that entry is matched to an
- * instruction. A match is found when (instruction & mask) == value.
- *
- * DECODE_TABLE(mask, value, table)
- *	Instruction decoding jumps to parsing the new sub-table 'table'.
- *
- * DECODE_CUSTOM(mask, value, decoder)
- *	The custom function 'decoder' is called to the complete decoding
- *	of an instruction.
- *
- * DECODE_SIMULATE(mask, value, handler)
- *	Set the probes instruction handler to 'handler', this will be used
- *	to simulate the instruction when the probe is hit. Decoding returns
- *	with INSN_GOOD_NO_SLOT.
- *
- * DECODE_EMULATE(mask, value, handler)
- *	Set the probes instruction handler to 'handler', this will be used
- *	to emulate the instruction when the probe is hit. The modified
- *	instruction (see below) is placed in the probes instruction slot so it
- *	may be called by the emulation code. Decoding returns with INSN_GOOD.
- *
- * DECODE_REJECT(mask, value)
- *	Instruction decoding fails with INSN_REJECTED
- *
- * DECODE_OR(mask, value)
- *	This allows the mask/value test of multiple table entries to be
- *	logically ORed. Once an 'or' entry is matched the decoding action to
- *	be performed is that of the next entry which isn't an 'or'. E.g.
- *
- *		DECODE_OR	(mask1, value1)
- *		DECODE_OR	(mask2, value2)
- *		DECODE_SIMULATE	(mask3, value3, simulation_handler)
- *
- *	This means that if any of the three mask/value pairs match the
- *	instruction being decoded, then 'simulation_handler' will be used
- *	for it.
- *
- * Both the SIMULATE and EMULATE macros have a second form which take an
- * additional 'regs' argument.
- *
- *	DECODE_SIMULATEX(mask, value, handler, regs)
- *	DECODE_EMULATEX	(mask, value, handler, regs)
- *
- * These are used to specify what kind of CPU register is encoded in each of the
- * least significant 5 nibbles of the instruction being decoded. The regs value
- * is specified using the REGS macro, this takes any of the REG_TYPE_* values
- * from enum decode_reg_type as arguments; only the '*' part of the name is
- * given. E.g.
- *
- *	REGS(0, ANY, NOPC, 0, ANY)
- *
- * This indicates an instruction is encoded like:
- *
- *	bits 19..16	ignore
- *	bits 15..12	any register allowed here
- *	bits 11.. 8	any register except PC allowed here
- *	bits  7.. 4	ignore
- *	bits  3.. 0	any register allowed here
- *
- * This register specification is checked after a decode table entry is found to
- * match an instruction (through the mask/value test). Any invalid register then
- * found in the instruction will cause decoding to fail with INSN_REJECTED. In
- * the above example this would happen if bits 11..8 of the instruction were
- * 1111, indicating R15 or PC.
- *
- * As well as checking for legal combinations of registers, this data is also
- * used to modify the registers encoded in the instructions so that an
- * emulation routines can use it. (See decode_regs() and INSN_NEW_BITS.)
- *
- * Here is a real example which matches ARM instructions of the form
- * "AND <Rd>,<Rn>,<Rm>,<shift> <Rs>"
- *
- *	DECODE_EMULATEX	(0x0e000090, 0x00000010, emulate_rd12rn16rm0rs8_rwflags,
- *						 REGS(ANY, ANY, NOPC, 0, ANY)),
- *						      ^    ^    ^        ^
- *						      Rn   Rd   Rs       Rm
- *
- * Decoding the instruction "AND R4, R5, R6, ASL R15" will be rejected because
- * Rs == R15
- *
- * Decoding the instruction "AND R4, R5, R6, ASL R7" will be accepted and the
- * instruction will be modified to "AND R0, R2, R3, ASL R1" and then placed into
- * the kprobes instruction slot. This can then be called later by the handler
- * function emulate_rd12rn16rm0rs8_rwflags in order to simulate the instruction.
- */
-
-enum decode_type {
-	DECODE_TYPE_END,
-	DECODE_TYPE_TABLE,
-	DECODE_TYPE_CUSTOM,
-	DECODE_TYPE_SIMULATE,
-	DECODE_TYPE_EMULATE,
-	DECODE_TYPE_OR,
-	DECODE_TYPE_REJECT,
-	NUM_DECODE_TYPES /* Must be last enum */
-};
-
-#define DECODE_TYPE_BITS	4
-#define DECODE_TYPE_MASK	((1 << DECODE_TYPE_BITS) - 1)
-
-enum decode_reg_type {
-	REG_TYPE_NONE = 0, /* Not a register, ignore */
-	REG_TYPE_ANY,	   /* Any register allowed */
-	REG_TYPE_SAMEAS16, /* Register should be same as that at bits 19..16 */
-	REG_TYPE_SP,	   /* Register must be SP */
-	REG_TYPE_PC,	   /* Register must be PC */
-	REG_TYPE_NOSP,	   /* Register must not be SP */
-	REG_TYPE_NOSPPC,   /* Register must not be SP or PC */
-	REG_TYPE_NOPC,	   /* Register must not be PC */
-	REG_TYPE_NOPCWB,   /* No PC if load/store write-back flag also set */
-
-	/* The following types are used when the encoding for PC indicates
-	 * another instruction form. This distiction only matters for test
-	 * case coverage checks.
-	 */
-	REG_TYPE_NOPCX,	   /* Register must not be PC */
-	REG_TYPE_NOSPPCX,  /* Register must not be SP or PC */
-
-	/* Alias to allow '0' arg to be used in REGS macro. */
-	REG_TYPE_0 = REG_TYPE_NONE
-};
-
-#define REGS(r16, r12, r8, r4, r0)	\
-	((REG_TYPE_##r16) << 16) +	\
-	((REG_TYPE_##r12) << 12) +	\
-	((REG_TYPE_##r8) << 8) +	\
-	((REG_TYPE_##r4) << 4) +	\
-	(REG_TYPE_##r0)
-
-union decode_item {
-	u32			bits;
-	const union decode_item	*table;
-	kprobe_insn_handler_t	*handler;
-	kprobe_decode_insn_t	*decoder;
-};
-
-
-#define DECODE_END			\
-	{.bits = DECODE_TYPE_END}
-
-
-struct decode_header {
-	union decode_item	type_regs;
-	union decode_item	mask;
-	union decode_item	value;
-};
-
-#define DECODE_HEADER(_type, _mask, _value, _regs)		\
-	{.bits = (_type) | ((_regs) << DECODE_TYPE_BITS)},	\
-	{.bits = (_mask)},					\
-	{.bits = (_value)}
-
-
-struct decode_table {
-	struct decode_header	header;
-	union decode_item	table;
-};
-
-#define DECODE_TABLE(_mask, _value, _table)			\
-	DECODE_HEADER(DECODE_TYPE_TABLE, _mask, _value, 0),	\
-	{.table = (_table)}
-
-
-struct decode_custom {
-	struct decode_header	header;
-	union decode_item	decoder;
-};
-
-#define DECODE_CUSTOM(_mask, _value, _decoder)			\
-	DECODE_HEADER(DECODE_TYPE_CUSTOM, _mask, _value, 0),	\
-	{.decoder = (_decoder)}
-
-
-struct decode_simulate {
-	struct decode_header	header;
-	union decode_item	handler;
-};
-
-#define DECODE_SIMULATEX(_mask, _value, _handler, _regs)		\
-	DECODE_HEADER(DECODE_TYPE_SIMULATE, _mask, _value, _regs),	\
-	{.handler = (_handler)}
-
-#define DECODE_SIMULATE(_mask, _value, _handler)	\
-	DECODE_SIMULATEX(_mask, _value, _handler, 0)
-
-
-struct decode_emulate {
-	struct decode_header	header;
-	union decode_item	handler;
-};
-
-#define DECODE_EMULATEX(_mask, _value, _handler, _regs)			\
-	DECODE_HEADER(DECODE_TYPE_EMULATE, _mask, _value, _regs),	\
-	{.handler = (_handler)}
-
-#define DECODE_EMULATE(_mask, _value, _handler)		\
-	DECODE_EMULATEX(_mask, _value, _handler, 0)
-
-
-struct decode_or {
-	struct decode_header	header;
-};
-
-#define DECODE_OR(_mask, _value)				\
-	DECODE_HEADER(DECODE_TYPE_OR, _mask, _value, 0)
-
-
-struct decode_reject {
-	struct decode_header	header;
-};
-
-#define DECODE_REJECT(_mask, _value)				\
-	DECODE_HEADER(DECODE_TYPE_REJECT, _mask, _value, 0)
-
-
-#ifdef CONFIG_THUMB2_KERNEL
-extern const union decode_item kprobe_decode_thumb16_table[];
-extern const union decode_item kprobe_decode_thumb32_table[];
-#else
-extern const union decode_item kprobe_decode_arm_table[];
-#endif
-
-
-int kprobe_decode_insn(kprobe_opcode_t insn, struct arch_specific_insn *asi,
-			const union decode_item *table, bool thumb16);
-
-
 #endif /* _ARM_KERNEL_KPROBES_H */

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/perf_event_v7.c

@@ -18,6 +18,10 @@
 
 #ifdef CONFIG_CPU_V7
 
+#include <asm/cp15.h>
+#include <asm/vfp.h>
+#include "../vfp/vfpinstr.h"
+
 /*
  * Common ARMv7 event types
  *
@@ -109,6 +113,33 @@ enum armv7_a15_perf_types {
 	ARMV7_A15_PERFCTR_PC_WRITE_SPEC			= 0x76,
 };
 
+/* ARMv7 Cortex-A12 specific event types */
+enum armv7_a12_perf_types {
+	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ		= 0x40,
+	ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE	= 0x41,
+
+	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ		= 0x50,
+	ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE		= 0x51,
+
+	ARMV7_A12_PERFCTR_PC_WRITE_SPEC			= 0x76,
+
+	ARMV7_A12_PERFCTR_PF_TLB_REFILL			= 0xe7,
+};
+
+/* ARMv7 Krait specific event types */
+enum krait_perf_types {
+	KRAIT_PMRESR0_GROUP0				= 0xcc,
+	KRAIT_PMRESR1_GROUP0				= 0xd0,
+	KRAIT_PMRESR2_GROUP0				= 0xd4,
+	KRAIT_VPMRESR0_GROUP0				= 0xd8,
+
+	KRAIT_PERFCTR_L1_ICACHE_ACCESS			= 0x10011,
+	KRAIT_PERFCTR_L1_ICACHE_MISS			= 0x10010,
+
+	KRAIT_PERFCTR_L1_ITLB_ACCESS			= 0x12222,
+	KRAIT_PERFCTR_L1_DTLB_ACCESS			= 0x12210,
+};
+
 /*
  * Cortex-A8 HW events mapping
  *
@@ -731,6 +762,262 @@ static const unsigned armv7_a7_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
 	},
 };
 
+/*
+ * Cortex-A12 HW events mapping
+ */
+static const unsigned armv7_a12_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]		= ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+	[PERF_COUNT_HW_CACHE_MISSES]		= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS]	= ARMV7_A12_PERFCTR_PC_WRITE_SPEC,
+	[PERF_COUNT_HW_BRANCH_MISSES]		= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]		= ARMV7_PERFCTR_BUS_CYCLES,
+	[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND]	= HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_STALLED_CYCLES_BACKEND]	= HW_OP_UNSUPPORTED,
+};
+
+static const unsigned armv7_a12_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					[PERF_COUNT_HW_CACHE_OP_MAX]
+					[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_READ,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L1_DCACHE_ACCESS_WRITE,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		/*
+		 * Not all performance counters differentiate between read
+		 * and write accesses/misses so we're not always strictly
+		 * correct, but it's the best we can do. Writes and reads get
+		 * combined in these cases.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_ICACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_READ,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_A12_PERFCTR_L2_CACHE_ACCESS_WRITE,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L2_CACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_DTLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_A12_PERFCTR_PF_TLB_REFILL,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_ITLB_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
+/*
+ * Krait HW events mapping
+ */
+static const unsigned krait_perf_map[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = ARMV7_PERFCTR_PC_WRITE,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned krait_perf_map_no_branch[PERF_COUNT_HW_MAX] = {
+	[PERF_COUNT_HW_CPU_CYCLES]	    = ARMV7_PERFCTR_CPU_CYCLES,
+	[PERF_COUNT_HW_INSTRUCTIONS]	    = ARMV7_PERFCTR_INSTR_EXECUTED,
+	[PERF_COUNT_HW_CACHE_REFERENCES]    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_CACHE_MISSES]	    = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = HW_OP_UNSUPPORTED,
+	[PERF_COUNT_HW_BRANCH_MISSES]	    = ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+	[PERF_COUNT_HW_BUS_CYCLES]	    = ARMV7_PERFCTR_CLOCK_CYCLES,
+};
+
+static const unsigned krait_perf_cache_map[PERF_COUNT_HW_CACHE_MAX]
+					  [PERF_COUNT_HW_CACHE_OP_MAX]
+					  [PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+	[C(L1D)] = {
+		/*
+		 * The performance counters don't differentiate between read
+		 * and write accesses/misses so this isn't strictly correct,
+		 * but it's the best we can do. Writes and reads get
+		 * combined.
+		 */
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_L1_DCACHE_ACCESS,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_L1_DCACHE_REFILL,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(L1I)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ICACHE_ACCESS,
+			[C(RESULT_MISS)]	= KRAIT_PERFCTR_L1_ICACHE_MISS,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(LL)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(DTLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_DTLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(ITLB)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= KRAIT_PERFCTR_L1_ITLB_ACCESS,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(BPU)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= ARMV7_PERFCTR_PC_BRANCH_PRED,
+			[C(RESULT_MISS)]	= ARMV7_PERFCTR_PC_BRANCH_MIS_PRED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+	[C(NODE)] = {
+		[C(OP_READ)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_WRITE)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+		[C(OP_PREFETCH)] = {
+			[C(RESULT_ACCESS)]	= CACHE_OP_UNSUPPORTED,
+			[C(RESULT_MISS)]	= CACHE_OP_UNSUPPORTED,
+		},
+	},
+};
+
 /*
  * Perf Events' indices
  */
@@ -1212,6 +1499,24 @@ static int armv7_a7_map_event(struct perf_event *event)
 				&armv7_a7_perf_cache_map, 0xFF);
 }
 
+static int armv7_a12_map_event(struct perf_event *event)
+{
+	return armpmu_map_event(event, &armv7_a12_perf_map,
+				&armv7_a12_perf_cache_map, 0xFF);
+}
+
+static int krait_map_event(struct perf_event *event)
+{
+	return armpmu_map_event(event, &krait_perf_map,
+				&krait_perf_cache_map, 0xFFFFF);
+}
+
+static int krait_map_event_no_branch(struct perf_event *event)
+{
+	return armpmu_map_event(event, &krait_perf_map_no_branch,
+				&krait_perf_cache_map, 0xFFFFF);
+}
+
 static void armv7pmu_init(struct arm_pmu *cpu_pmu)
 {
 	cpu_pmu->handle_irq	= armv7pmu_handle_irq;
@@ -1283,6 +1588,408 @@ static int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
 	return 0;
 }
+
+static int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7pmu_init(cpu_pmu);
+	cpu_pmu->name		= "ARMv7 Cortex-A12";
+	cpu_pmu->map_event	= armv7_a12_map_event;
+	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
+	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	return 0;
+}
+
+/*
+ * Krait Performance Monitor Region Event Selection Register (PMRESRn)
+ *
+ *            31   30     24     16     8      0
+ *            +--------------------------------+
+ *  PMRESR0   | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 0
+ *            +--------------------------------+
+ *  PMRESR1   | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 1
+ *            +--------------------------------+
+ *  PMRESR2   | EN |  CC  |  CC  |  CC  |  CC  |   N = 1, R = 2
+ *            +--------------------------------+
+ *  VPMRESR0  | EN |  CC  |  CC  |  CC  |  CC  |   N = 2, R = ?
+ *            +--------------------------------+
+ *              EN | G=3  | G=2  | G=1  | G=0
+ *
+ *  Event Encoding:
+ *
+ *      hwc->config_base = 0xNRCCG
+ *
+ *      N  = prefix, 1 for Krait CPU (PMRESRn), 2 for Venum VFP (VPMRESR)
+ *      R  = region register
+ *      CC = class of events the group G is choosing from
+ *      G  = group or particular event
+ *
+ *  Example: 0x12021 is a Krait CPU event in PMRESR2's group 1 with code 2
+ *
+ *  A region (R) corresponds to a piece of the CPU (execution unit, instruction
+ *  unit, etc.) while the event code (CC) corresponds to a particular class of
+ *  events (interrupts for example). An event code is broken down into
+ *  groups (G) that can be mapped into the PMU (irq, fiqs, and irq+fiqs for
+ *  example).
+ */
+
+#define KRAIT_EVENT		(1 << 16)
+#define VENUM_EVENT		(2 << 16)
+#define KRAIT_EVENT_MASK	(KRAIT_EVENT | VENUM_EVENT)
+#define PMRESRn_EN		BIT(31)
+
+static u32 krait_read_pmresrn(int n)
+{
+	u32 val;
+
+	switch (n) {
+	case 0:
+		asm volatile("mrc p15, 1, %0, c9, c15, 0" : "=r" (val));
+		break;
+	case 1:
+		asm volatile("mrc p15, 1, %0, c9, c15, 1" : "=r" (val));
+		break;
+	case 2:
+		asm volatile("mrc p15, 1, %0, c9, c15, 2" : "=r" (val));
+		break;
+	default:
+		BUG(); /* Should be validated in krait_pmu_get_event_idx() */
+	}
+
+	return val;
+}
+
+static void krait_write_pmresrn(int n, u32 val)
+{
+	switch (n) {
+	case 0:
+		asm volatile("mcr p15, 1, %0, c9, c15, 0" : : "r" (val));
+		break;
+	case 1:
+		asm volatile("mcr p15, 1, %0, c9, c15, 1" : : "r" (val));
+		break;
+	case 2:
+		asm volatile("mcr p15, 1, %0, c9, c15, 2" : : "r" (val));
+		break;
+	default:
+		BUG(); /* Should be validated in krait_pmu_get_event_idx() */
+	}
+}
+
+static u32 krait_read_vpmresr0(void)
+{
+	u32 val;
+	asm volatile("mrc p10, 7, %0, c11, c0, 0" : "=r" (val));
+	return val;
+}
+
+static void krait_write_vpmresr0(u32 val)
+{
+	asm volatile("mcr p10, 7, %0, c11, c0, 0" : : "r" (val));
+}
+
+static void krait_pre_vpmresr0(u32 *venum_orig_val, u32 *fp_orig_val)
+{
+	u32 venum_new_val;
+	u32 fp_new_val;
+
+	BUG_ON(preemptible());
+	/* CPACR Enable CP10 and CP11 access */
+	*venum_orig_val = get_copro_access();
+	venum_new_val = *venum_orig_val | CPACC_SVC(10) | CPACC_SVC(11);
+	set_copro_access(venum_new_val);
+
+	/* Enable FPEXC */
+	*fp_orig_val = fmrx(FPEXC);
+	fp_new_val = *fp_orig_val | FPEXC_EN;
+	fmxr(FPEXC, fp_new_val);
+}
+
+static void krait_post_vpmresr0(u32 venum_orig_val, u32 fp_orig_val)
+{
+	BUG_ON(preemptible());
+	/* Restore FPEXC */
+	fmxr(FPEXC, fp_orig_val);
+	isb();
+	/* Restore CPACR */
+	set_copro_access(venum_orig_val);
+}
+
+static u32 krait_get_pmresrn_event(unsigned int region)
+{
+	static const u32 pmresrn_table[] = { KRAIT_PMRESR0_GROUP0,
+					     KRAIT_PMRESR1_GROUP0,
+					     KRAIT_PMRESR2_GROUP0 };
+	return pmresrn_table[region];
+}
+
+static void krait_evt_setup(int idx, u32 config_base)
+{
+	u32 val;
+	u32 mask;
+	u32 vval, fval;
+	unsigned int region;
+	unsigned int group;
+	unsigned int code;
+	unsigned int group_shift;
+	bool venum_event;
+
+	venum_event = !!(config_base & VENUM_EVENT);
+	region = (config_base >> 12) & 0xf;
+	code   = (config_base >> 4) & 0xff;
+	group  = (config_base >> 0)  & 0xf;
+
+	group_shift = group * 8;
+	mask = 0xff << group_shift;
+
+	/* Configure evtsel for the region and group */
+	if (venum_event)
+		val = KRAIT_VPMRESR0_GROUP0;
+	else
+		val = krait_get_pmresrn_event(region);
+	val += group;
+	/* Mix in mode-exclusion bits */
+	val |= config_base & (ARMV7_EXCLUDE_USER | ARMV7_EXCLUDE_PL1);
+	armv7_pmnc_write_evtsel(idx, val);
+
+	asm volatile("mcr p15, 0, %0, c9, c15, 0" : : "r" (0));
+
+	if (venum_event) {
+		krait_pre_vpmresr0(&vval, &fval);
+		val = krait_read_vpmresr0();
+		val &= ~mask;
+		val |= code << group_shift;
+		val |= PMRESRn_EN;
+		krait_write_vpmresr0(val);
+		krait_post_vpmresr0(vval, fval);
+	} else {
+		val = krait_read_pmresrn(region);
+		val &= ~mask;
+		val |= code << group_shift;
+		val |= PMRESRn_EN;
+		krait_write_pmresrn(region, val);
+	}
+}
+
+static u32 krait_clear_pmresrn_group(u32 val, int group)
+{
+	u32 mask;
+	int group_shift;
+
+	group_shift = group * 8;
+	mask = 0xff << group_shift;
+	val &= ~mask;
+
+	/* Don't clear enable bit if entire region isn't disabled */
+	if (val & ~PMRESRn_EN)
+		return val |= PMRESRn_EN;
+
+	return 0;
+}
+
+static void krait_clearpmu(u32 config_base)
+{
+	u32 val;
+	u32 vval, fval;
+	unsigned int region;
+	unsigned int group;
+	bool venum_event;
+
+	venum_event = !!(config_base & VENUM_EVENT);
+	region = (config_base >> 12) & 0xf;
+	group  = (config_base >> 0)  & 0xf;
+
+	if (venum_event) {
+		krait_pre_vpmresr0(&vval, &fval);
+		val = krait_read_vpmresr0();
+		val = krait_clear_pmresrn_group(val, group);
+		krait_write_vpmresr0(val);
+		krait_post_vpmresr0(vval, fval);
+	} else {
+		val = krait_read_pmresrn(region);
+		val = krait_clear_pmresrn_group(val, group);
+		krait_write_pmresrn(region, val);
+	}
+}
+
+static void krait_pmu_disable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+
+	/* Disable counter and interrupt */
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Disable counter */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Clear pmresr code (if destined for PMNx counters)
+	 */
+	if (hwc->config_base & KRAIT_EVENT_MASK)
+		krait_clearpmu(hwc->config_base);
+
+	/* Disable interrupt for this counter */
+	armv7_pmnc_disable_intens(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void krait_pmu_enable_event(struct perf_event *event)
+{
+	unsigned long flags;
+	struct hw_perf_event *hwc = &event->hw;
+	int idx = hwc->idx;
+	struct pmu_hw_events *events = cpu_pmu->get_hw_events();
+
+	/*
+	 * Enable counter and interrupt, and set the counter to count
+	 * the event that we're interested in.
+	 */
+	raw_spin_lock_irqsave(&events->pmu_lock, flags);
+
+	/* Disable counter */
+	armv7_pmnc_disable_counter(idx);
+
+	/*
+	 * Set event (if destined for PMNx counters)
+	 * We set the event for the cycle counter because we
+	 * have the ability to perform event filtering.
+	 */
+	if (hwc->config_base & KRAIT_EVENT_MASK)
+		krait_evt_setup(idx, hwc->config_base);
+	else
+		armv7_pmnc_write_evtsel(idx, hwc->config_base);
+
+	/* Enable interrupt for this counter */
+	armv7_pmnc_enable_intens(idx);
+
+	/* Enable counter */
+	armv7_pmnc_enable_counter(idx);
+
+	raw_spin_unlock_irqrestore(&events->pmu_lock, flags);
+}
+
+static void krait_pmu_reset(void *info)
+{
+	u32 vval, fval;
+
+	armv7pmu_reset(info);
+
+	/* Clear all pmresrs */
+	krait_write_pmresrn(0, 0);
+	krait_write_pmresrn(1, 0);
+	krait_write_pmresrn(2, 0);
+
+	krait_pre_vpmresr0(&vval, &fval);
+	krait_write_vpmresr0(0);
+	krait_post_vpmresr0(vval, fval);
+}
+
+static int krait_event_to_bit(struct perf_event *event, unsigned int region,
+			      unsigned int group)
+{
+	int bit;
+	struct hw_perf_event *hwc = &event->hw;
+	struct arm_pmu *cpu_pmu = to_arm_pmu(event->pmu);
+
+	if (hwc->config_base & VENUM_EVENT)
+		bit = KRAIT_VPMRESR0_GROUP0;
+	else
+		bit = krait_get_pmresrn_event(region);
+	bit -= krait_get_pmresrn_event(0);
+	bit += group;
+	/*
+	 * Lower bits are reserved for use by the counters (see
+	 * armv7pmu_get_event_idx() for more info)
+	 */
+	bit += ARMV7_IDX_COUNTER_LAST(cpu_pmu) + 1;
+
+	return bit;
+}
+
+/*
+ * We check for column exclusion constraints here.
+ * Two events cant use the same group within a pmresr register.
+ */
+static int krait_pmu_get_event_idx(struct pmu_hw_events *cpuc,
+				   struct perf_event *event)
+{
+	int idx;
+	int bit;
+	unsigned int prefix;
+	unsigned int region;
+	unsigned int code;
+	unsigned int group;
+	bool krait_event;
+	struct hw_perf_event *hwc = &event->hw;
+
+	region = (hwc->config_base >> 12) & 0xf;
+	code   = (hwc->config_base >> 4) & 0xff;
+	group  = (hwc->config_base >> 0) & 0xf;
+	krait_event = !!(hwc->config_base & KRAIT_EVENT_MASK);
+
+	if (krait_event) {
+		/* Ignore invalid events */
+		if (group > 3 || region > 2)
+			return -EINVAL;
+		prefix = hwc->config_base & KRAIT_EVENT_MASK;
+		if (prefix != KRAIT_EVENT && prefix != VENUM_EVENT)
+			return -EINVAL;
+		if (prefix == VENUM_EVENT && (code & 0xe0))
+			return -EINVAL;
+
+		bit = krait_event_to_bit(event, region, group);
+		if (test_and_set_bit(bit, cpuc->used_mask))
+			return -EAGAIN;
+	}
+
+	idx = armv7pmu_get_event_idx(cpuc, event);
+	if (idx < 0 && krait_event)
+		clear_bit(bit, cpuc->used_mask);
+
+	return idx;
+}
+
+static void krait_pmu_clear_event_idx(struct pmu_hw_events *cpuc,
+				      struct perf_event *event)
+{
+	int bit;
+	struct hw_perf_event *hwc = &event->hw;
+	unsigned int region;
+	unsigned int group;
+	bool krait_event;
+
+	region = (hwc->config_base >> 12) & 0xf;
+	group  = (hwc->config_base >> 0) & 0xf;
+	krait_event = !!(hwc->config_base & KRAIT_EVENT_MASK);
+
+	if (krait_event) {
+		bit = krait_event_to_bit(event, region, group);
+		clear_bit(bit, cpuc->used_mask);
+	}
+}
+
+static int krait_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	armv7pmu_init(cpu_pmu);
+	cpu_pmu->name		= "ARMv7 Krait";
+	/* Some early versions of Krait don't support PC write events */
+	if (of_property_read_bool(cpu_pmu->plat_device->dev.of_node,
+				  "qcom,no-pc-write"))
+		cpu_pmu->map_event = krait_map_event_no_branch;
+	else
+		cpu_pmu->map_event = krait_map_event;
+	cpu_pmu->num_events	= armv7_read_num_pmnc_events();
+	cpu_pmu->set_event_filter = armv7pmu_set_event_filter;
+	cpu_pmu->reset		= krait_pmu_reset;
+	cpu_pmu->enable		= krait_pmu_enable_event;
+	cpu_pmu->disable	= krait_pmu_disable_event;
+	cpu_pmu->get_event_idx	= krait_pmu_get_event_idx;
+	cpu_pmu->clear_event_idx = krait_pmu_clear_event_idx;
+	return 0;
+}
 #else
 static inline int armv7_a8_pmu_init(struct arm_pmu *cpu_pmu)
 {
@@ -1308,4 +2015,14 @@ static inline int armv7_a7_pmu_init(struct arm_pmu *cpu_pmu)
 {
 	return -ENODEV;
 }
+
+static inline int armv7_a12_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
+
+static inline int krait_pmu_init(struct arm_pmu *cpu_pmu)
+{
+	return -ENODEV;
+}
 #endif	/* CONFIG_CPU_V7 */

arch/arm/kernel/probes-arm.c

@@ -0,0 +1,734 @@
+/*
+ * arch/arm/kernel/probes-arm.c
+ *
+ * Some code moved here from arch/arm/kernel/kprobes-arm.c
+ *
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/stddef.h>
+#include <linux/ptrace.h>
+
+#include "probes.h"
+#include "probes-arm.h"
+
+#define sign_extend(x, signbit) ((x) | (0 - ((x) & (1 << (signbit)))))
+
+#define branch_displacement(insn) sign_extend(((insn) & 0xffffff) << 2, 25)
+
+/*
+ * To avoid the complications of mimicing single-stepping on a
+ * processor without a Next-PC or a single-step mode, and to
+ * avoid having to deal with the side-effects of boosting, we
+ * simulate or emulate (almost) all ARM instructions.
+ *
+ * "Simulation" is where the instruction's behavior is duplicated in
+ * C code.  "Emulation" is where the original instruction is rewritten
+ * and executed, often by altering its registers.
+ *
+ * By having all behavior of the kprobe'd instruction completed before
+ * returning from the kprobe_handler(), all locks (scheduler and
+ * interrupt) can safely be released.  There is no need for secondary
+ * breakpoints, no race with MP or preemptable kernels, nor having to
+ * clean up resources counts at a later time impacting overall system
+ * performance.  By rewriting the instruction, only the minimum registers
+ * need to be loaded and saved back optimizing performance.
+ *
+ * Calling the insnslot_*_rwflags version of a function doesn't hurt
+ * anything even when the CPSR flags aren't updated by the
+ * instruction.  It's just a little slower in return for saving
+ * a little space by not having a duplicate function that doesn't
+ * update the flags.  (The same optimization can be said for
+ * instructions that do or don't perform register writeback)
+ * Also, instructions can either read the flags, only write the
+ * flags, or read and write the flags.  To save combinations
+ * rather than for sheer performance, flag functions just assume
+ * read and write of flags.
+ */
+
+void __kprobes simulate_bbl(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
+{
+	long iaddr = (long) regs->ARM_pc - 4;
+	int disp  = branch_displacement(insn);
+
+	if (insn & (1 << 24))
+		regs->ARM_lr = iaddr + 4;
+
+	regs->ARM_pc = iaddr + 8 + disp;
+}
+
+void __kprobes simulate_blx1(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
+{
+	long iaddr = (long) regs->ARM_pc - 4;
+	int disp = branch_displacement(insn);
+
+	regs->ARM_lr = iaddr + 4;
+	regs->ARM_pc = iaddr + 8 + disp + ((insn >> 23) & 0x2);
+	regs->ARM_cpsr |= PSR_T_BIT;
+}
+
+void __kprobes simulate_blx2bx(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
+{
+	int rm = insn & 0xf;
+	long rmv = regs->uregs[rm];
+
+	if (insn & (1 << 5))
+		regs->ARM_lr = (long) regs->ARM_pc;
+
+	regs->ARM_pc = rmv & ~0x1;
+	regs->ARM_cpsr &= ~PSR_T_BIT;
+	if (rmv & 0x1)
+		regs->ARM_cpsr |= PSR_T_BIT;
+}
+
+void __kprobes simulate_mrs(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
+{
+	int rd = (insn >> 12) & 0xf;
+	unsigned long mask = 0xf8ff03df; /* Mask out execution state */
+	regs->uregs[rd] = regs->ARM_cpsr & mask;
+}
+
+void __kprobes simulate_mov_ipsp(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
+{
+	regs->uregs[12] = regs->uregs[13];
+}
+
+/*
+ * For the instruction masking and comparisons in all the "space_*"
+ * functions below, Do _not_ rearrange the order of tests unless
+ * you're very, very sure of what you are doing.  For the sake of
+ * efficiency, the masks for some tests sometimes assume other test
+ * have been done prior to them so the number of patterns to test
+ * for an instruction set can be as broad as possible to reduce the
+ * number of tests needed.
+ */
+
+static const union decode_item arm_1111_table[] = {
+	/* Unconditional instructions					*/
+
+	/* memory hint		1111 0100 x001 xxxx xxxx xxxx xxxx xxxx */
+	/* PLDI (immediate)	1111 0100 x101 xxxx xxxx xxxx xxxx xxxx */
+	/* PLDW (immediate)	1111 0101 x001 xxxx xxxx xxxx xxxx xxxx */
+	/* PLD (immediate)	1111 0101 x101 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_SIMULATE	(0xfe300000, 0xf4100000, PROBES_PRELOAD_IMM),
+
+	/* memory hint		1111 0110 x001 xxxx xxxx xxxx xxx0 xxxx */
+	/* PLDI (register)	1111 0110 x101 xxxx xxxx xxxx xxx0 xxxx */
+	/* PLDW (register)	1111 0111 x001 xxxx xxxx xxxx xxx0 xxxx */
+	/* PLD (register)	1111 0111 x101 xxxx xxxx xxxx xxx0 xxxx */
+	DECODE_SIMULATE	(0xfe300010, 0xf6100000, PROBES_PRELOAD_REG),
+
+	/* BLX (immediate)	1111 101x xxxx xxxx xxxx xxxx xxxx xxxx */
+	DECODE_SIMULATE	(0xfe000000, 0xfa000000, PROBES_BRANCH_IMM),
+
+	/* CPS			1111 0001 0000 xxx0 xxxx xxxx xx0x xxxx */
+	/* SETEND		1111 0001 0000 0001 xxxx xxxx 0000 xxxx */
+	/* SRS			1111 100x x1x0 xxxx xxxx xxxx xxxx xxxx */
+	/* RFE			1111 100x x0x1 xxxx xxxx xxxx xxxx xxxx */
+
+	/* Coprocessor instructions... */
+	/* MCRR2		1111 1100 0100 xxxx xxxx xxxx xxxx xxxx */
+	/* MRRC2		1111 1100 0101 xxxx xxxx xxxx xxxx xxxx */
+	/* LDC2			1111 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
+	/* STC2			1111 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
+	/* CDP2			1111 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
+	/* MCR2			1111 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
+	/* MRC2			1111 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
+
+	/* Other unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_0001_0xx0____0xxx_table[] = {
+	/* Miscellaneous instructions					*/
+
+	/* MRS cpsr		cccc 0001 0000 xxxx xxxx xxxx 0000 xxxx */
+	DECODE_SIMULATEX(0x0ff000f0, 0x01000000, PROBES_MRS,
+						 REGS(0, NOPC, 0, 0, 0)),
+
+	/* BX			cccc 0001 0010 xxxx xxxx xxxx 0001 xxxx */
+	DECODE_SIMULATE	(0x0ff000f0, 0x01200010, PROBES_BRANCH_REG),
+
+	/* BLX (register)	cccc 0001 0010 xxxx xxxx xxxx 0011 xxxx */
+	DECODE_SIMULATEX(0x0ff000f0, 0x01200030, PROBES_BRANCH_REG,
+						 REGS(0, 0, 0, 0, NOPC)),
+
+	/* CLZ			cccc 0001 0110 xxxx xxxx xxxx 0001 xxxx */
+	DECODE_EMULATEX	(0x0ff000f0, 0x01600010, PROBES_CLZ,
+						 REGS(0, NOPC, 0, 0, NOPC)),
+
+	/* QADD			cccc 0001 0000 xxxx xxxx xxxx 0101 xxxx */
+	/* QSUB			cccc 0001 0010 xxxx xxxx xxxx 0101 xxxx */
+	/* QDADD		cccc 0001 0100 xxxx xxxx xxxx 0101 xxxx */
+	/* QDSUB		cccc 0001 0110 xxxx xxxx xxxx 0101 xxxx */
+	DECODE_EMULATEX	(0x0f9000f0, 0x01000050, PROBES_SATURATING_ARITHMETIC,
+						 REGS(NOPC, NOPC, 0, 0, NOPC)),
+
+	/* BXJ			cccc 0001 0010 xxxx xxxx xxxx 0010 xxxx */
+	/* MSR			cccc 0001 0x10 xxxx xxxx xxxx 0000 xxxx */
+	/* MRS spsr		cccc 0001 0100 xxxx xxxx xxxx 0000 xxxx */
+	/* BKPT			1110 0001 0010 xxxx xxxx xxxx 0111 xxxx */
+	/* SMC			cccc 0001 0110 xxxx xxxx xxxx 0111 xxxx */
+	/* And unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_0001_0xx0____1xx0_table[] = {
+	/* Halfword multiply and multiply-accumulate			*/
+
+	/* SMLALxy		cccc 0001 0100 xxxx xxxx xxxx 1xx0 xxxx */
+	DECODE_EMULATEX	(0x0ff00090, 0x01400080, PROBES_MUL1,
+						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
+
+	/* SMULWy		cccc 0001 0010 xxxx xxxx xxxx 1x10 xxxx */
+	DECODE_OR	(0x0ff000b0, 0x012000a0),
+	/* SMULxy		cccc 0001 0110 xxxx xxxx xxxx 1xx0 xxxx */
+	DECODE_EMULATEX	(0x0ff00090, 0x01600080, PROBES_MUL2,
+						 REGS(NOPC, 0, NOPC, 0, NOPC)),
+
+	/* SMLAxy		cccc 0001 0000 xxxx xxxx xxxx 1xx0 xxxx */
+	DECODE_OR	(0x0ff00090, 0x01000080),
+	/* SMLAWy		cccc 0001 0010 xxxx xxxx xxxx 1x00 xxxx */
+	DECODE_EMULATEX	(0x0ff000b0, 0x01200080, PROBES_MUL2,
+						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_0000_____1001_table[] = {
+	/* Multiply and multiply-accumulate				*/
+
+	/* MUL			cccc 0000 0000 xxxx xxxx xxxx 1001 xxxx */
+	/* MULS			cccc 0000 0001 xxxx xxxx xxxx 1001 xxxx */
+	DECODE_EMULATEX	(0x0fe000f0, 0x00000090, PROBES_MUL2,
+						 REGS(NOPC, 0, NOPC, 0, NOPC)),
+
+	/* MLA			cccc 0000 0010 xxxx xxxx xxxx 1001 xxxx */
+	/* MLAS			cccc 0000 0011 xxxx xxxx xxxx 1001 xxxx */
+	DECODE_OR	(0x0fe000f0, 0x00200090),
+	/* MLS			cccc 0000 0110 xxxx xxxx xxxx 1001 xxxx */
+	DECODE_EMULATEX	(0x0ff000f0, 0x00600090, PROBES_MUL2,
+						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
+
+	/* UMAAL		cccc 0000 0100 xxxx xxxx xxxx 1001 xxxx */
+	DECODE_OR	(0x0ff000f0, 0x00400090),
+	/* UMULL		cccc 0000 1000 xxxx xxxx xxxx 1001 xxxx */
+	/* UMULLS		cccc 0000 1001 xxxx xxxx xxxx 1001 xxxx */
+	/* UMLAL		cccc 0000 1010 xxxx xxxx xxxx 1001 xxxx */
+	/* UMLALS		cccc 0000 1011 xxxx xxxx xxxx 1001 xxxx */
+	/* SMULL		cccc 0000 1100 xxxx xxxx xxxx 1001 xxxx */
+	/* SMULLS		cccc 0000 1101 xxxx xxxx xxxx 1001 xxxx */
+	/* SMLAL		cccc 0000 1110 xxxx xxxx xxxx 1001 xxxx */
+	/* SMLALS		cccc 0000 1111 xxxx xxxx xxxx 1001 xxxx */
+	DECODE_EMULATEX	(0x0f8000f0, 0x00800090, PROBES_MUL1,
+						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_0001_____1001_table[] = {
+	/* Synchronization primitives					*/
+
+#if __LINUX_ARM_ARCH__ < 6
+	/* Deprecated on ARMv6 and may be UNDEFINED on v7		*/
+	/* SMP/SWPB		cccc 0001 0x00 xxxx xxxx xxxx 1001 xxxx */
+	DECODE_EMULATEX	(0x0fb000f0, 0x01000090, PROBES_SWP,
+						 REGS(NOPC, NOPC, 0, 0, NOPC)),
+#endif
+	/* LDREX/STREX{,D,B,H}	cccc 0001 1xxx xxxx xxxx xxxx 1001 xxxx */
+	/* And unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_000x_____1xx1_table[] = {
+	/* Extra load/store instructions				*/
+
+	/* STRHT		cccc 0000 xx10 xxxx xxxx xxxx 1011 xxxx */
+	/* ???			cccc 0000 xx10 xxxx xxxx xxxx 11x1 xxxx */
+	/* LDRHT		cccc 0000 xx11 xxxx xxxx xxxx 1011 xxxx */
+	/* LDRSBT		cccc 0000 xx11 xxxx xxxx xxxx 1101 xxxx */
+	/* LDRSHT		cccc 0000 xx11 xxxx xxxx xxxx 1111 xxxx */
+	DECODE_REJECT	(0x0f200090, 0x00200090),
+
+	/* LDRD/STRD lr,pc,{...	cccc 000x x0x0 xxxx 111x xxxx 1101 xxxx */
+	DECODE_REJECT	(0x0e10e0d0, 0x0000e0d0),
+
+	/* LDRD (register)	cccc 000x x0x0 xxxx xxxx xxxx 1101 xxxx */
+	/* STRD (register)	cccc 000x x0x0 xxxx xxxx xxxx 1111 xxxx */
+	DECODE_EMULATEX	(0x0e5000d0, 0x000000d0, PROBES_LDRSTRD,
+						 REGS(NOPCWB, NOPCX, 0, 0, NOPC)),
+
+	/* LDRD (immediate)	cccc 000x x1x0 xxxx xxxx xxxx 1101 xxxx */
+	/* STRD (immediate)	cccc 000x x1x0 xxxx xxxx xxxx 1111 xxxx */
+	DECODE_EMULATEX	(0x0e5000d0, 0x004000d0, PROBES_LDRSTRD,
+						 REGS(NOPCWB, NOPCX, 0, 0, 0)),
+
+	/* STRH (register)	cccc 000x x0x0 xxxx xxxx xxxx 1011 xxxx */
+	DECODE_EMULATEX	(0x0e5000f0, 0x000000b0, PROBES_STORE_EXTRA,
+						 REGS(NOPCWB, NOPC, 0, 0, NOPC)),
+
+	/* LDRH (register)	cccc 000x x0x1 xxxx xxxx xxxx 1011 xxxx */
+	/* LDRSB (register)	cccc 000x x0x1 xxxx xxxx xxxx 1101 xxxx */
+	/* LDRSH (register)	cccc 000x x0x1 xxxx xxxx xxxx 1111 xxxx */
+	DECODE_EMULATEX	(0x0e500090, 0x00100090, PROBES_LOAD_EXTRA,
+						 REGS(NOPCWB, NOPC, 0, 0, NOPC)),
+
+	/* STRH (immediate)	cccc 000x x1x0 xxxx xxxx xxxx 1011 xxxx */
+	DECODE_EMULATEX	(0x0e5000f0, 0x004000b0, PROBES_STORE_EXTRA,
+						 REGS(NOPCWB, NOPC, 0, 0, 0)),
+
+	/* LDRH (immediate)	cccc 000x x1x1 xxxx xxxx xxxx 1011 xxxx */
+	/* LDRSB (immediate)	cccc 000x x1x1 xxxx xxxx xxxx 1101 xxxx */
+	/* LDRSH (immediate)	cccc 000x x1x1 xxxx xxxx xxxx 1111 xxxx */
+	DECODE_EMULATEX	(0x0e500090, 0x00500090, PROBES_LOAD_EXTRA,
+						 REGS(NOPCWB, NOPC, 0, 0, 0)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_000x_table[] = {
+	/* Data-processing (register)					*/
+
+	/* <op>S PC, ...	cccc 000x xxx1 xxxx 1111 xxxx xxxx xxxx */
+	DECODE_REJECT	(0x0e10f000, 0x0010f000),
+
+	/* MOV IP, SP		1110 0001 1010 0000 1100 0000 0000 1101 */
+	DECODE_SIMULATE	(0xffffffff, 0xe1a0c00d, PROBES_MOV_IP_SP),
+
+	/* TST (register)	cccc 0001 0001 xxxx xxxx xxxx xxx0 xxxx */
+	/* TEQ (register)	cccc 0001 0011 xxxx xxxx xxxx xxx0 xxxx */
+	/* CMP (register)	cccc 0001 0101 xxxx xxxx xxxx xxx0 xxxx */
+	/* CMN (register)	cccc 0001 0111 xxxx xxxx xxxx xxx0 xxxx */
+	DECODE_EMULATEX	(0x0f900010, 0x01100000, PROBES_DATA_PROCESSING_REG,
+						 REGS(ANY, 0, 0, 0, ANY)),
+
+	/* MOV (register)	cccc 0001 101x xxxx xxxx xxxx xxx0 xxxx */
+	/* MVN (register)	cccc 0001 111x xxxx xxxx xxxx xxx0 xxxx */
+	DECODE_EMULATEX	(0x0fa00010, 0x01a00000, PROBES_DATA_PROCESSING_REG,
+						 REGS(0, ANY, 0, 0, ANY)),
+
+	/* AND (register)	cccc 0000 000x xxxx xxxx xxxx xxx0 xxxx */
+	/* EOR (register)	cccc 0000 001x xxxx xxxx xxxx xxx0 xxxx */
+	/* SUB (register)	cccc 0000 010x xxxx xxxx xxxx xxx0 xxxx */
+	/* RSB (register)	cccc 0000 011x xxxx xxxx xxxx xxx0 xxxx */
+	/* ADD (register)	cccc 0000 100x xxxx xxxx xxxx xxx0 xxxx */
+	/* ADC (register)	cccc 0000 101x xxxx xxxx xxxx xxx0 xxxx */
+	/* SBC (register)	cccc 0000 110x xxxx xxxx xxxx xxx0 xxxx */
+	/* RSC (register)	cccc 0000 111x xxxx xxxx xxxx xxx0 xxxx */
+	/* ORR (register)	cccc 0001 100x xxxx xxxx xxxx xxx0 xxxx */
+	/* BIC (register)	cccc 0001 110x xxxx xxxx xxxx xxx0 xxxx */
+	DECODE_EMULATEX	(0x0e000010, 0x00000000, PROBES_DATA_PROCESSING_REG,
+						 REGS(ANY, ANY, 0, 0, ANY)),
+
+	/* TST (reg-shift reg)	cccc 0001 0001 xxxx xxxx xxxx 0xx1 xxxx */
+	/* TEQ (reg-shift reg)	cccc 0001 0011 xxxx xxxx xxxx 0xx1 xxxx */
+	/* CMP (reg-shift reg)	cccc 0001 0101 xxxx xxxx xxxx 0xx1 xxxx */
+	/* CMN (reg-shift reg)	cccc 0001 0111 xxxx xxxx xxxx 0xx1 xxxx */
+	DECODE_EMULATEX	(0x0f900090, 0x01100010, PROBES_DATA_PROCESSING_REG,
+						 REGS(ANY, 0, NOPC, 0, ANY)),
+
+	/* MOV (reg-shift reg)	cccc 0001 101x xxxx xxxx xxxx 0xx1 xxxx */
+	/* MVN (reg-shift reg)	cccc 0001 111x xxxx xxxx xxxx 0xx1 xxxx */
+	DECODE_EMULATEX	(0x0fa00090, 0x01a00010, PROBES_DATA_PROCESSING_REG,
+						 REGS(0, ANY, NOPC, 0, ANY)),
+
+	/* AND (reg-shift reg)	cccc 0000 000x xxxx xxxx xxxx 0xx1 xxxx */
+	/* EOR (reg-shift reg)	cccc 0000 001x xxxx xxxx xxxx 0xx1 xxxx */
+	/* SUB (reg-shift reg)	cccc 0000 010x xxxx xxxx xxxx 0xx1 xxxx */
+	/* RSB (reg-shift reg)	cccc 0000 011x xxxx xxxx xxxx 0xx1 xxxx */
+	/* ADD (reg-shift reg)	cccc 0000 100x xxxx xxxx xxxx 0xx1 xxxx */
+	/* ADC (reg-shift reg)	cccc 0000 101x xxxx xxxx xxxx 0xx1 xxxx */
+	/* SBC (reg-shift reg)	cccc 0000 110x xxxx xxxx xxxx 0xx1 xxxx */
+	/* RSC (reg-shift reg)	cccc 0000 111x xxxx xxxx xxxx 0xx1 xxxx */
+	/* ORR (reg-shift reg)	cccc 0001 100x xxxx xxxx xxxx 0xx1 xxxx */
+	/* BIC (reg-shift reg)	cccc 0001 110x xxxx xxxx xxxx 0xx1 xxxx */
+	DECODE_EMULATEX	(0x0e000090, 0x00000010, PROBES_DATA_PROCESSING_REG,
+						 REGS(ANY, ANY, NOPC, 0, ANY)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_001x_table[] = {
+	/* Data-processing (immediate)					*/
+
+	/* MOVW			cccc 0011 0000 xxxx xxxx xxxx xxxx xxxx */
+	/* MOVT			cccc 0011 0100 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0fb00000, 0x03000000, PROBES_DATA_PROCESSING_IMM,
+						 REGS(0, NOPC, 0, 0, 0)),
+
+	/* YIELD		cccc 0011 0010 0000 xxxx xxxx 0000 0001 */
+	DECODE_OR	(0x0fff00ff, 0x03200001),
+	/* SEV			cccc 0011 0010 0000 xxxx xxxx 0000 0100 */
+	DECODE_EMULATE	(0x0fff00ff, 0x03200004, PROBES_EMULATE_NONE),
+	/* NOP			cccc 0011 0010 0000 xxxx xxxx 0000 0000 */
+	/* WFE			cccc 0011 0010 0000 xxxx xxxx 0000 0010 */
+	/* WFI			cccc 0011 0010 0000 xxxx xxxx 0000 0011 */
+	DECODE_SIMULATE	(0x0fff00fc, 0x03200000, PROBES_SIMULATE_NOP),
+	/* DBG			cccc 0011 0010 0000 xxxx xxxx ffff xxxx */
+	/* unallocated hints	cccc 0011 0010 0000 xxxx xxxx xxxx xxxx */
+	/* MSR (immediate)	cccc 0011 0x10 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0x0fb00000, 0x03200000),
+
+	/* <op>S PC, ...	cccc 001x xxx1 xxxx 1111 xxxx xxxx xxxx */
+	DECODE_REJECT	(0x0e10f000, 0x0210f000),
+
+	/* TST (immediate)	cccc 0011 0001 xxxx xxxx xxxx xxxx xxxx */
+	/* TEQ (immediate)	cccc 0011 0011 xxxx xxxx xxxx xxxx xxxx */
+	/* CMP (immediate)	cccc 0011 0101 xxxx xxxx xxxx xxxx xxxx */
+	/* CMN (immediate)	cccc 0011 0111 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0f900000, 0x03100000, PROBES_DATA_PROCESSING_IMM,
+						 REGS(ANY, 0, 0, 0, 0)),
+
+	/* MOV (immediate)	cccc 0011 101x xxxx xxxx xxxx xxxx xxxx */
+	/* MVN (immediate)	cccc 0011 111x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0fa00000, 0x03a00000, PROBES_DATA_PROCESSING_IMM,
+						 REGS(0, ANY, 0, 0, 0)),
+
+	/* AND (immediate)	cccc 0010 000x xxxx xxxx xxxx xxxx xxxx */
+	/* EOR (immediate)	cccc 0010 001x xxxx xxxx xxxx xxxx xxxx */
+	/* SUB (immediate)	cccc 0010 010x xxxx xxxx xxxx xxxx xxxx */
+	/* RSB (immediate)	cccc 0010 011x xxxx xxxx xxxx xxxx xxxx */
+	/* ADD (immediate)	cccc 0010 100x xxxx xxxx xxxx xxxx xxxx */
+	/* ADC (immediate)	cccc 0010 101x xxxx xxxx xxxx xxxx xxxx */
+	/* SBC (immediate)	cccc 0010 110x xxxx xxxx xxxx xxxx xxxx */
+	/* RSC (immediate)	cccc 0010 111x xxxx xxxx xxxx xxxx xxxx */
+	/* ORR (immediate)	cccc 0011 100x xxxx xxxx xxxx xxxx xxxx */
+	/* BIC (immediate)	cccc 0011 110x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0e000000, 0x02000000, PROBES_DATA_PROCESSING_IMM,
+						 REGS(ANY, ANY, 0, 0, 0)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_0110_____xxx1_table[] = {
+	/* Media instructions						*/
+
+	/* SEL			cccc 0110 1000 xxxx xxxx xxxx 1011 xxxx */
+	DECODE_EMULATEX	(0x0ff000f0, 0x068000b0, PROBES_SATURATE,
+						 REGS(NOPC, NOPC, 0, 0, NOPC)),
+
+	/* SSAT			cccc 0110 101x xxxx xxxx xxxx xx01 xxxx */
+	/* USAT			cccc 0110 111x xxxx xxxx xxxx xx01 xxxx */
+	DECODE_OR(0x0fa00030, 0x06a00010),
+	/* SSAT16		cccc 0110 1010 xxxx xxxx xxxx 0011 xxxx */
+	/* USAT16		cccc 0110 1110 xxxx xxxx xxxx 0011 xxxx */
+	DECODE_EMULATEX	(0x0fb000f0, 0x06a00030, PROBES_SATURATE,
+						 REGS(0, NOPC, 0, 0, NOPC)),
+
+	/* REV			cccc 0110 1011 xxxx xxxx xxxx 0011 xxxx */
+	/* REV16		cccc 0110 1011 xxxx xxxx xxxx 1011 xxxx */
+	/* RBIT			cccc 0110 1111 xxxx xxxx xxxx 0011 xxxx */
+	/* REVSH		cccc 0110 1111 xxxx xxxx xxxx 1011 xxxx */
+	DECODE_EMULATEX	(0x0fb00070, 0x06b00030, PROBES_REV,
+						 REGS(0, NOPC, 0, 0, NOPC)),
+
+	/* ???			cccc 0110 0x00 xxxx xxxx xxxx xxx1 xxxx */
+	DECODE_REJECT	(0x0fb00010, 0x06000010),
+	/* ???			cccc 0110 0xxx xxxx xxxx xxxx 1011 xxxx */
+	DECODE_REJECT	(0x0f8000f0, 0x060000b0),
+	/* ???			cccc 0110 0xxx xxxx xxxx xxxx 1101 xxxx */
+	DECODE_REJECT	(0x0f8000f0, 0x060000d0),
+	/* SADD16		cccc 0110 0001 xxxx xxxx xxxx 0001 xxxx */
+	/* SADDSUBX		cccc 0110 0001 xxxx xxxx xxxx 0011 xxxx */
+	/* SSUBADDX		cccc 0110 0001 xxxx xxxx xxxx 0101 xxxx */
+	/* SSUB16		cccc 0110 0001 xxxx xxxx xxxx 0111 xxxx */
+	/* SADD8		cccc 0110 0001 xxxx xxxx xxxx 1001 xxxx */
+	/* SSUB8		cccc 0110 0001 xxxx xxxx xxxx 1111 xxxx */
+	/* QADD16		cccc 0110 0010 xxxx xxxx xxxx 0001 xxxx */
+	/* QADDSUBX		cccc 0110 0010 xxxx xxxx xxxx 0011 xxxx */
+	/* QSUBADDX		cccc 0110 0010 xxxx xxxx xxxx 0101 xxxx */
+	/* QSUB16		cccc 0110 0010 xxxx xxxx xxxx 0111 xxxx */
+	/* QADD8		cccc 0110 0010 xxxx xxxx xxxx 1001 xxxx */
+	/* QSUB8		cccc 0110 0010 xxxx xxxx xxxx 1111 xxxx */
+	/* SHADD16		cccc 0110 0011 xxxx xxxx xxxx 0001 xxxx */
+	/* SHADDSUBX		cccc 0110 0011 xxxx xxxx xxxx 0011 xxxx */
+	/* SHSUBADDX		cccc 0110 0011 xxxx xxxx xxxx 0101 xxxx */
+	/* SHSUB16		cccc 0110 0011 xxxx xxxx xxxx 0111 xxxx */
+	/* SHADD8		cccc 0110 0011 xxxx xxxx xxxx 1001 xxxx */
+	/* SHSUB8		cccc 0110 0011 xxxx xxxx xxxx 1111 xxxx */
+	/* UADD16		cccc 0110 0101 xxxx xxxx xxxx 0001 xxxx */
+	/* UADDSUBX		cccc 0110 0101 xxxx xxxx xxxx 0011 xxxx */
+	/* USUBADDX		cccc 0110 0101 xxxx xxxx xxxx 0101 xxxx */
+	/* USUB16		cccc 0110 0101 xxxx xxxx xxxx 0111 xxxx */
+	/* UADD8		cccc 0110 0101 xxxx xxxx xxxx 1001 xxxx */
+	/* USUB8		cccc 0110 0101 xxxx xxxx xxxx 1111 xxxx */
+	/* UQADD16		cccc 0110 0110 xxxx xxxx xxxx 0001 xxxx */
+	/* UQADDSUBX		cccc 0110 0110 xxxx xxxx xxxx 0011 xxxx */
+	/* UQSUBADDX		cccc 0110 0110 xxxx xxxx xxxx 0101 xxxx */
+	/* UQSUB16		cccc 0110 0110 xxxx xxxx xxxx 0111 xxxx */
+	/* UQADD8		cccc 0110 0110 xxxx xxxx xxxx 1001 xxxx */
+	/* UQSUB8		cccc 0110 0110 xxxx xxxx xxxx 1111 xxxx */
+	/* UHADD16		cccc 0110 0111 xxxx xxxx xxxx 0001 xxxx */
+	/* UHADDSUBX		cccc 0110 0111 xxxx xxxx xxxx 0011 xxxx */
+	/* UHSUBADDX		cccc 0110 0111 xxxx xxxx xxxx 0101 xxxx */
+	/* UHSUB16		cccc 0110 0111 xxxx xxxx xxxx 0111 xxxx */
+	/* UHADD8		cccc 0110 0111 xxxx xxxx xxxx 1001 xxxx */
+	/* UHSUB8		cccc 0110 0111 xxxx xxxx xxxx 1111 xxxx */
+	DECODE_EMULATEX	(0x0f800010, 0x06000010, PROBES_MMI,
+						 REGS(NOPC, NOPC, 0, 0, NOPC)),
+
+	/* PKHBT		cccc 0110 1000 xxxx xxxx xxxx x001 xxxx */
+	/* PKHTB		cccc 0110 1000 xxxx xxxx xxxx x101 xxxx */
+	DECODE_EMULATEX	(0x0ff00030, 0x06800010, PROBES_PACK,
+						 REGS(NOPC, NOPC, 0, 0, NOPC)),
+
+	/* ???			cccc 0110 1001 xxxx xxxx xxxx 0111 xxxx */
+	/* ???			cccc 0110 1101 xxxx xxxx xxxx 0111 xxxx */
+	DECODE_REJECT	(0x0fb000f0, 0x06900070),
+
+	/* SXTB16		cccc 0110 1000 1111 xxxx xxxx 0111 xxxx */
+	/* SXTB			cccc 0110 1010 1111 xxxx xxxx 0111 xxxx */
+	/* SXTH			cccc 0110 1011 1111 xxxx xxxx 0111 xxxx */
+	/* UXTB16		cccc 0110 1100 1111 xxxx xxxx 0111 xxxx */
+	/* UXTB			cccc 0110 1110 1111 xxxx xxxx 0111 xxxx */
+	/* UXTH			cccc 0110 1111 1111 xxxx xxxx 0111 xxxx */
+	DECODE_EMULATEX	(0x0f8f00f0, 0x068f0070, PROBES_EXTEND,
+						 REGS(0, NOPC, 0, 0, NOPC)),
+
+	/* SXTAB16		cccc 0110 1000 xxxx xxxx xxxx 0111 xxxx */
+	/* SXTAB		cccc 0110 1010 xxxx xxxx xxxx 0111 xxxx */
+	/* SXTAH		cccc 0110 1011 xxxx xxxx xxxx 0111 xxxx */
+	/* UXTAB16		cccc 0110 1100 xxxx xxxx xxxx 0111 xxxx */
+	/* UXTAB		cccc 0110 1110 xxxx xxxx xxxx 0111 xxxx */
+	/* UXTAH		cccc 0110 1111 xxxx xxxx xxxx 0111 xxxx */
+	DECODE_EMULATEX	(0x0f8000f0, 0x06800070, PROBES_EXTEND_ADD,
+						 REGS(NOPCX, NOPC, 0, 0, NOPC)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_0111_____xxx1_table[] = {
+	/* Media instructions						*/
+
+	/* UNDEFINED		cccc 0111 1111 xxxx xxxx xxxx 1111 xxxx */
+	DECODE_REJECT	(0x0ff000f0, 0x07f000f0),
+
+	/* SMLALD		cccc 0111 0100 xxxx xxxx xxxx 00x1 xxxx */
+	/* SMLSLD		cccc 0111 0100 xxxx xxxx xxxx 01x1 xxxx */
+	DECODE_EMULATEX	(0x0ff00090, 0x07400010, PROBES_MUL_ADD_LONG,
+						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
+
+	/* SMUAD		cccc 0111 0000 xxxx 1111 xxxx 00x1 xxxx */
+	/* SMUSD		cccc 0111 0000 xxxx 1111 xxxx 01x1 xxxx */
+	DECODE_OR	(0x0ff0f090, 0x0700f010),
+	/* SMMUL		cccc 0111 0101 xxxx 1111 xxxx 00x1 xxxx */
+	DECODE_OR	(0x0ff0f0d0, 0x0750f010),
+	/* USAD8		cccc 0111 1000 xxxx 1111 xxxx 0001 xxxx */
+	DECODE_EMULATEX	(0x0ff0f0f0, 0x0780f010, PROBES_MUL_ADD,
+						 REGS(NOPC, 0, NOPC, 0, NOPC)),
+
+	/* SMLAD		cccc 0111 0000 xxxx xxxx xxxx 00x1 xxxx */
+	/* SMLSD		cccc 0111 0000 xxxx xxxx xxxx 01x1 xxxx */
+	DECODE_OR	(0x0ff00090, 0x07000010),
+	/* SMMLA		cccc 0111 0101 xxxx xxxx xxxx 00x1 xxxx */
+	DECODE_OR	(0x0ff000d0, 0x07500010),
+	/* USADA8		cccc 0111 1000 xxxx xxxx xxxx 0001 xxxx */
+	DECODE_EMULATEX	(0x0ff000f0, 0x07800010, PROBES_MUL_ADD,
+						 REGS(NOPC, NOPCX, NOPC, 0, NOPC)),
+
+	/* SMMLS		cccc 0111 0101 xxxx xxxx xxxx 11x1 xxxx */
+	DECODE_EMULATEX	(0x0ff000d0, 0x075000d0, PROBES_MUL_ADD,
+						 REGS(NOPC, NOPC, NOPC, 0, NOPC)),
+
+	/* SBFX			cccc 0111 101x xxxx xxxx xxxx x101 xxxx */
+	/* UBFX			cccc 0111 111x xxxx xxxx xxxx x101 xxxx */
+	DECODE_EMULATEX	(0x0fa00070, 0x07a00050, PROBES_BITFIELD,
+						 REGS(0, NOPC, 0, 0, NOPC)),
+
+	/* BFC			cccc 0111 110x xxxx xxxx xxxx x001 1111 */
+	DECODE_EMULATEX	(0x0fe0007f, 0x07c0001f, PROBES_BITFIELD,
+						 REGS(0, NOPC, 0, 0, 0)),
+
+	/* BFI			cccc 0111 110x xxxx xxxx xxxx x001 xxxx */
+	DECODE_EMULATEX	(0x0fe00070, 0x07c00010, PROBES_BITFIELD,
+						 REGS(0, NOPC, 0, 0, NOPCX)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_01xx_table[] = {
+	/* Load/store word and unsigned byte				*/
+
+	/* LDRB/STRB pc,[...]	cccc 01xx x0xx xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0x0c40f000, 0x0440f000),
+
+	/* STRT			cccc 01x0 x010 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRT			cccc 01x0 x011 xxxx xxxx xxxx xxxx xxxx */
+	/* STRBT		cccc 01x0 x110 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRBT		cccc 01x0 x111 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0x0d200000, 0x04200000),
+
+	/* STR (immediate)	cccc 010x x0x0 xxxx xxxx xxxx xxxx xxxx */
+	/* STRB (immediate)	cccc 010x x1x0 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0e100000, 0x04000000, PROBES_STORE,
+						 REGS(NOPCWB, ANY, 0, 0, 0)),
+
+	/* LDR (immediate)	cccc 010x x0x1 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRB (immediate)	cccc 010x x1x1 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0e100000, 0x04100000, PROBES_LOAD,
+						 REGS(NOPCWB, ANY, 0, 0, 0)),
+
+	/* STR (register)	cccc 011x x0x0 xxxx xxxx xxxx xxxx xxxx */
+	/* STRB (register)	cccc 011x x1x0 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0e100000, 0x06000000, PROBES_STORE,
+						 REGS(NOPCWB, ANY, 0, 0, NOPC)),
+
+	/* LDR (register)	cccc 011x x0x1 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRB (register)	cccc 011x x1x1 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0x0e100000, 0x06100000, PROBES_LOAD,
+						 REGS(NOPCWB, ANY, 0, 0, NOPC)),
+
+	DECODE_END
+};
+
+static const union decode_item arm_cccc_100x_table[] = {
+	/* Block data transfer instructions				*/
+
+	/* LDM			cccc 100x x0x1 xxxx xxxx xxxx xxxx xxxx */
+	/* STM			cccc 100x x0x0 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_CUSTOM	(0x0e400000, 0x08000000, PROBES_LDMSTM),
+
+	/* STM (user registers)	cccc 100x x1x0 xxxx xxxx xxxx xxxx xxxx */
+	/* LDM (user registers)	cccc 100x x1x1 xxxx 0xxx xxxx xxxx xxxx */
+	/* LDM (exception ret)	cccc 100x x1x1 xxxx 1xxx xxxx xxxx xxxx */
+	DECODE_END
+};
+
+const union decode_item probes_decode_arm_table[] = {
+	/*
+	 * Unconditional instructions
+	 *			1111 xxxx xxxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xf0000000, 0xf0000000, arm_1111_table),
+
+	/*
+	 * Miscellaneous instructions
+	 *			cccc 0001 0xx0 xxxx xxxx xxxx 0xxx xxxx
+	 */
+	DECODE_TABLE	(0x0f900080, 0x01000000, arm_cccc_0001_0xx0____0xxx_table),
+
+	/*
+	 * Halfword multiply and multiply-accumulate
+	 *			cccc 0001 0xx0 xxxx xxxx xxxx 1xx0 xxxx
+	 */
+	DECODE_TABLE	(0x0f900090, 0x01000080, arm_cccc_0001_0xx0____1xx0_table),
+
+	/*
+	 * Multiply and multiply-accumulate
+	 *			cccc 0000 xxxx xxxx xxxx xxxx 1001 xxxx
+	 */
+	DECODE_TABLE	(0x0f0000f0, 0x00000090, arm_cccc_0000_____1001_table),
+
+	/*
+	 * Synchronization primitives
+	 *			cccc 0001 xxxx xxxx xxxx xxxx 1001 xxxx
+	 */
+	DECODE_TABLE	(0x0f0000f0, 0x01000090, arm_cccc_0001_____1001_table),
+
+	/*
+	 * Extra load/store instructions
+	 *			cccc 000x xxxx xxxx xxxx xxxx 1xx1 xxxx
+	 */
+	DECODE_TABLE	(0x0e000090, 0x00000090, arm_cccc_000x_____1xx1_table),
+
+	/*
+	 * Data-processing (register)
+	 *			cccc 000x xxxx xxxx xxxx xxxx xxx0 xxxx
+	 * Data-processing (register-shifted register)
+	 *			cccc 000x xxxx xxxx xxxx xxxx 0xx1 xxxx
+	 */
+	DECODE_TABLE	(0x0e000000, 0x00000000, arm_cccc_000x_table),
+
+	/*
+	 * Data-processing (immediate)
+	 *			cccc 001x xxxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0x0e000000, 0x02000000, arm_cccc_001x_table),
+
+	/*
+	 * Media instructions
+	 *			cccc 011x xxxx xxxx xxxx xxxx xxx1 xxxx
+	 */
+	DECODE_TABLE	(0x0f000010, 0x06000010, arm_cccc_0110_____xxx1_table),
+	DECODE_TABLE	(0x0f000010, 0x07000010, arm_cccc_0111_____xxx1_table),
+
+	/*
+	 * Load/store word and unsigned byte
+	 *			cccc 01xx xxxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0x0c000000, 0x04000000, arm_cccc_01xx_table),
+
+	/*
+	 * Block data transfer instructions
+	 *			cccc 100x xxxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0x0e000000, 0x08000000, arm_cccc_100x_table),
+
+	/* B			cccc 1010 xxxx xxxx xxxx xxxx xxxx xxxx */
+	/* BL			cccc 1011 xxxx xxxx xxxx xxxx xxxx xxxx */
+	DECODE_SIMULATE	(0x0e000000, 0x0a000000, PROBES_BRANCH),
+
+	/*
+	 * Supervisor Call, and coprocessor instructions
+	 */
+
+	/* MCRR			cccc 1100 0100 xxxx xxxx xxxx xxxx xxxx */
+	/* MRRC			cccc 1100 0101 xxxx xxxx xxxx xxxx xxxx */
+	/* LDC			cccc 110x xxx1 xxxx xxxx xxxx xxxx xxxx */
+	/* STC			cccc 110x xxx0 xxxx xxxx xxxx xxxx xxxx */
+	/* CDP			cccc 1110 xxxx xxxx xxxx xxxx xxx0 xxxx */
+	/* MCR			cccc 1110 xxx0 xxxx xxxx xxxx xxx1 xxxx */
+	/* MRC			cccc 1110 xxx1 xxxx xxxx xxxx xxx1 xxxx */
+	/* SVC			cccc 1111 xxxx xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0x0c000000, 0x0c000000),
+
+	DECODE_END
+};
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(probes_decode_arm_table);
+#endif
+
+static void __kprobes arm_singlestep(probes_opcode_t insn,
+		struct arch_probes_insn *asi, struct pt_regs *regs)
+{
+	regs->ARM_pc += 4;
+	asi->insn_handler(insn, asi, regs);
+}
+
+/* Return:
+ *   INSN_REJECTED     If instruction is one not allowed to kprobe,
+ *   INSN_GOOD         If instruction is supported and uses instruction slot,
+ *   INSN_GOOD_NO_SLOT If instruction is supported but doesn't use its slot.
+ *
+ * For instructions we don't want to kprobe (INSN_REJECTED return result):
+ *   These are generally ones that modify the processor state making
+ *   them "hard" to simulate such as switches processor modes or
+ *   make accesses in alternate modes.  Any of these could be simulated
+ *   if the work was put into it, but low return considering they
+ *   should also be very rare.
+ */
+enum probes_insn __kprobes
+arm_probes_decode_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+		       bool emulate, const union decode_action *actions)
+{
+	asi->insn_singlestep = arm_singlestep;
+	asi->insn_check_cc = probes_condition_checks[insn>>28];
+	return probes_decode_insn(insn, asi, probes_decode_arm_table, false,
+				  emulate, actions);
+}

arch/arm/kernel/probes-arm.h

@@ -0,0 +1,73 @@
+/*
+ * 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.c

@@ -0,0 +1,882 @@
+/*
+ * arch/arm/kernel/probes-thumb.c
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * 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.
+ */
+
+#include <linux/stddef.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+#include "probes.h"
+#include "probes-thumb.h"
+
+
+static const union decode_item t32_table_1110_100x_x0xx[] = {
+	/* Load/store multiple instructions */
+
+	/* Rn is PC		1110 100x x0xx 1111 xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfe4f0000, 0xe80f0000),
+
+	/* SRS			1110 1000 00x0 xxxx xxxx xxxx xxxx xxxx */
+	/* RFE			1110 1000 00x1 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xffc00000, 0xe8000000),
+	/* SRS			1110 1001 10x0 xxxx xxxx xxxx xxxx xxxx */
+	/* RFE			1110 1001 10x1 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xffc00000, 0xe9800000),
+
+	/* STM Rn, {...pc}	1110 100x x0x0 xxxx 1xxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfe508000, 0xe8008000),
+	/* LDM Rn, {...lr,pc}	1110 100x x0x1 xxxx 11xx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfe50c000, 0xe810c000),
+	/* LDM/STM Rn, {...sp}	1110 100x x0xx xxxx xx1x xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfe402000, 0xe8002000),
+
+	/* STMIA		1110 1000 10x0 xxxx xxxx xxxx xxxx xxxx */
+	/* LDMIA		1110 1000 10x1 xxxx xxxx xxxx xxxx xxxx */
+	/* STMDB		1110 1001 00x0 xxxx xxxx xxxx xxxx xxxx */
+	/* LDMDB		1110 1001 00x1 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_CUSTOM	(0xfe400000, 0xe8000000, PROBES_T32_LDMSTM),
+
+	DECODE_END
+};
+
+static const union decode_item t32_table_1110_100x_x1xx[] = {
+	/* Load/store dual, load/store exclusive, table branch */
+
+	/* STRD (immediate)	1110 1000 x110 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRD (immediate)	1110 1000 x111 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_OR	(0xff600000, 0xe8600000),
+	/* STRD (immediate)	1110 1001 x1x0 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRD (immediate)	1110 1001 x1x1 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xff400000, 0xe9400000, PROBES_T32_LDRDSTRD,
+						 REGS(NOPCWB, NOSPPC, NOSPPC, 0, 0)),
+
+	/* TBB			1110 1000 1101 xxxx xxxx xxxx 0000 xxxx */
+	/* TBH			1110 1000 1101 xxxx xxxx xxxx 0001 xxxx */
+	DECODE_SIMULATEX(0xfff000e0, 0xe8d00000, PROBES_T32_TABLE_BRANCH,
+						 REGS(NOSP, 0, 0, 0, NOSPPC)),
+
+	/* STREX		1110 1000 0100 xxxx xxxx xxxx xxxx xxxx */
+	/* LDREX		1110 1000 0101 xxxx xxxx xxxx xxxx xxxx */
+	/* STREXB		1110 1000 1100 xxxx xxxx xxxx 0100 xxxx */
+	/* STREXH		1110 1000 1100 xxxx xxxx xxxx 0101 xxxx */
+	/* STREXD		1110 1000 1100 xxxx xxxx xxxx 0111 xxxx */
+	/* LDREXB		1110 1000 1101 xxxx xxxx xxxx 0100 xxxx */
+	/* LDREXH		1110 1000 1101 xxxx xxxx xxxx 0101 xxxx */
+	/* LDREXD		1110 1000 1101 xxxx xxxx xxxx 0111 xxxx */
+	/* And unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item t32_table_1110_101x[] = {
+	/* Data-processing (shifted register)				*/
+
+	/* TST			1110 1010 0001 xxxx xxxx 1111 xxxx xxxx */
+	/* TEQ			1110 1010 1001 xxxx xxxx 1111 xxxx xxxx */
+	DECODE_EMULATEX	(0xff700f00, 0xea100f00, PROBES_T32_TST,
+						 REGS(NOSPPC, 0, 0, 0, NOSPPC)),
+
+	/* CMN			1110 1011 0001 xxxx xxxx 1111 xxxx xxxx */
+	DECODE_OR	(0xfff00f00, 0xeb100f00),
+	/* CMP			1110 1011 1011 xxxx xxxx 1111 xxxx xxxx */
+	DECODE_EMULATEX	(0xfff00f00, 0xebb00f00, PROBES_T32_TST,
+						 REGS(NOPC, 0, 0, 0, NOSPPC)),
+
+	/* MOV			1110 1010 010x 1111 xxxx xxxx xxxx xxxx */
+	/* MVN			1110 1010 011x 1111 xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xffcf0000, 0xea4f0000, PROBES_T32_MOV,
+						 REGS(0, 0, NOSPPC, 0, NOSPPC)),
+
+	/* ???			1110 1010 101x xxxx xxxx xxxx xxxx xxxx */
+	/* ???			1110 1010 111x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xffa00000, 0xeaa00000),
+	/* ???			1110 1011 001x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xffe00000, 0xeb200000),
+	/* ???			1110 1011 100x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xffe00000, 0xeb800000),
+	/* ???			1110 1011 111x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xffe00000, 0xebe00000),
+
+	/* ADD/SUB SP, SP, Rm, LSL #0..3				*/
+	/*			1110 1011 x0xx 1101 x000 1101 xx00 xxxx */
+	DECODE_EMULATEX	(0xff4f7f30, 0xeb0d0d00, PROBES_T32_ADDSUB,
+						 REGS(SP, 0, SP, 0, NOSPPC)),
+
+	/* ADD/SUB SP, SP, Rm, shift					*/
+	/*			1110 1011 x0xx 1101 xxxx 1101 xxxx xxxx */
+	DECODE_REJECT	(0xff4f0f00, 0xeb0d0d00),
+
+	/* ADD/SUB Rd, SP, Rm, shift					*/
+	/*			1110 1011 x0xx 1101 xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xff4f0000, 0xeb0d0000, PROBES_T32_ADDSUB,
+						 REGS(SP, 0, NOPC, 0, NOSPPC)),
+
+	/* AND			1110 1010 000x xxxx xxxx xxxx xxxx xxxx */
+	/* BIC			1110 1010 001x xxxx xxxx xxxx xxxx xxxx */
+	/* ORR			1110 1010 010x xxxx xxxx xxxx xxxx xxxx */
+	/* ORN			1110 1010 011x xxxx xxxx xxxx xxxx xxxx */
+	/* EOR			1110 1010 100x xxxx xxxx xxxx xxxx xxxx */
+	/* PKH			1110 1010 110x xxxx xxxx xxxx xxxx xxxx */
+	/* ADD			1110 1011 000x xxxx xxxx xxxx xxxx xxxx */
+	/* ADC			1110 1011 010x xxxx xxxx xxxx xxxx xxxx */
+	/* SBC			1110 1011 011x xxxx xxxx xxxx xxxx xxxx */
+	/* SUB			1110 1011 101x xxxx xxxx xxxx xxxx xxxx */
+	/* RSB			1110 1011 110x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfe000000, 0xea000000, PROBES_T32_LOGICAL,
+						 REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)),
+
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_0x0x___0[] = {
+	/* Data-processing (modified immediate)				*/
+
+	/* TST			1111 0x00 0001 xxxx 0xxx 1111 xxxx xxxx */
+	/* TEQ			1111 0x00 1001 xxxx 0xxx 1111 xxxx xxxx */
+	DECODE_EMULATEX	(0xfb708f00, 0xf0100f00, PROBES_T32_TST,
+						 REGS(NOSPPC, 0, 0, 0, 0)),
+
+	/* CMN			1111 0x01 0001 xxxx 0xxx 1111 xxxx xxxx */
+	DECODE_OR	(0xfbf08f00, 0xf1100f00),
+	/* CMP			1111 0x01 1011 xxxx 0xxx 1111 xxxx xxxx */
+	DECODE_EMULATEX	(0xfbf08f00, 0xf1b00f00, PROBES_T32_CMP,
+						 REGS(NOPC, 0, 0, 0, 0)),
+
+	/* MOV			1111 0x00 010x 1111 0xxx xxxx xxxx xxxx */
+	/* MVN			1111 0x00 011x 1111 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfbcf8000, 0xf04f0000, PROBES_T32_MOV,
+						 REGS(0, 0, NOSPPC, 0, 0)),
+
+	/* ???			1111 0x00 101x xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfbe08000, 0xf0a00000),
+	/* ???			1111 0x00 110x xxxx 0xxx xxxx xxxx xxxx */
+	/* ???			1111 0x00 111x xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfbc08000, 0xf0c00000),
+	/* ???			1111 0x01 001x xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfbe08000, 0xf1200000),
+	/* ???			1111 0x01 100x xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfbe08000, 0xf1800000),
+	/* ???			1111 0x01 111x xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfbe08000, 0xf1e00000),
+
+	/* ADD Rd, SP, #imm	1111 0x01 000x 1101 0xxx xxxx xxxx xxxx */
+	/* SUB Rd, SP, #imm	1111 0x01 101x 1101 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfb4f8000, 0xf10d0000, PROBES_T32_ADDSUB,
+						 REGS(SP, 0, NOPC, 0, 0)),
+
+	/* AND			1111 0x00 000x xxxx 0xxx xxxx xxxx xxxx */
+	/* BIC			1111 0x00 001x xxxx 0xxx xxxx xxxx xxxx */
+	/* ORR			1111 0x00 010x xxxx 0xxx xxxx xxxx xxxx */
+	/* ORN			1111 0x00 011x xxxx 0xxx xxxx xxxx xxxx */
+	/* EOR			1111 0x00 100x xxxx 0xxx xxxx xxxx xxxx */
+	/* ADD			1111 0x01 000x xxxx 0xxx xxxx xxxx xxxx */
+	/* ADC			1111 0x01 010x xxxx 0xxx xxxx xxxx xxxx */
+	/* SBC			1111 0x01 011x xxxx 0xxx xxxx xxxx xxxx */
+	/* SUB			1111 0x01 101x xxxx 0xxx xxxx xxxx xxxx */
+	/* RSB			1111 0x01 110x xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfa008000, 0xf0000000, PROBES_T32_LOGICAL,
+						 REGS(NOSPPC, 0, NOSPPC, 0, 0)),
+
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_0x1x___0[] = {
+	/* Data-processing (plain binary immediate)			*/
+
+	/* ADDW Rd, PC, #imm	1111 0x10 0000 1111 0xxx xxxx xxxx xxxx */
+	DECODE_OR	(0xfbff8000, 0xf20f0000),
+	/* SUBW	Rd, PC, #imm	1111 0x10 1010 1111 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfbff8000, 0xf2af0000, PROBES_T32_ADDWSUBW_PC,
+						 REGS(PC, 0, NOSPPC, 0, 0)),
+
+	/* ADDW SP, SP, #imm	1111 0x10 0000 1101 0xxx 1101 xxxx xxxx */
+	DECODE_OR	(0xfbff8f00, 0xf20d0d00),
+	/* SUBW	SP, SP, #imm	1111 0x10 1010 1101 0xxx 1101 xxxx xxxx */
+	DECODE_EMULATEX	(0xfbff8f00, 0xf2ad0d00, PROBES_T32_ADDWSUBW,
+						 REGS(SP, 0, SP, 0, 0)),
+
+	/* ADDW			1111 0x10 0000 xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_OR	(0xfbf08000, 0xf2000000),
+	/* SUBW			1111 0x10 1010 xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfbf08000, 0xf2a00000, PROBES_T32_ADDWSUBW,
+						 REGS(NOPCX, 0, NOSPPC, 0, 0)),
+
+	/* MOVW			1111 0x10 0100 xxxx 0xxx xxxx xxxx xxxx */
+	/* MOVT			1111 0x10 1100 xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfb708000, 0xf2400000, PROBES_T32_MOVW,
+						 REGS(0, 0, NOSPPC, 0, 0)),
+
+	/* SSAT16		1111 0x11 0010 xxxx 0000 xxxx 00xx xxxx */
+	/* SSAT			1111 0x11 00x0 xxxx 0xxx xxxx xxxx xxxx */
+	/* USAT16		1111 0x11 1010 xxxx 0000 xxxx 00xx xxxx */
+	/* USAT			1111 0x11 10x0 xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfb508000, 0xf3000000, PROBES_T32_SAT,
+						 REGS(NOSPPC, 0, NOSPPC, 0, 0)),
+
+	/* SFBX			1111 0x11 0100 xxxx 0xxx xxxx xxxx xxxx */
+	/* UFBX			1111 0x11 1100 xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfb708000, 0xf3400000, PROBES_T32_BITFIELD,
+						 REGS(NOSPPC, 0, NOSPPC, 0, 0)),
+
+	/* BFC			1111 0x11 0110 1111 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfbff8000, 0xf36f0000, PROBES_T32_BITFIELD,
+						 REGS(0, 0, NOSPPC, 0, 0)),
+
+	/* BFI			1111 0x11 0110 xxxx 0xxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfbf08000, 0xf3600000, PROBES_T32_BITFIELD,
+						 REGS(NOSPPCX, 0, NOSPPC, 0, 0)),
+
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_0xxx___1[] = {
+	/* Branches and miscellaneous control				*/
+
+	/* YIELD		1111 0011 1010 xxxx 10x0 x000 0000 0001 */
+	DECODE_OR	(0xfff0d7ff, 0xf3a08001),
+	/* SEV			1111 0011 1010 xxxx 10x0 x000 0000 0100 */
+	DECODE_EMULATE	(0xfff0d7ff, 0xf3a08004, PROBES_T32_SEV),
+	/* NOP			1111 0011 1010 xxxx 10x0 x000 0000 0000 */
+	/* WFE			1111 0011 1010 xxxx 10x0 x000 0000 0010 */
+	/* WFI			1111 0011 1010 xxxx 10x0 x000 0000 0011 */
+	DECODE_SIMULATE	(0xfff0d7fc, 0xf3a08000, PROBES_T32_WFE),
+
+	/* MRS Rd, CPSR		1111 0011 1110 xxxx 10x0 xxxx xxxx xxxx */
+	DECODE_SIMULATEX(0xfff0d000, 0xf3e08000, PROBES_T32_MRS,
+						 REGS(0, 0, NOSPPC, 0, 0)),
+
+	/*
+	 * Unsupported instructions
+	 *			1111 0x11 1xxx xxxx 10x0 xxxx xxxx xxxx
+	 *
+	 * MSR			1111 0011 100x xxxx 10x0 xxxx xxxx xxxx
+	 * DBG hint		1111 0011 1010 xxxx 10x0 x000 1111 xxxx
+	 * Unallocated hints	1111 0011 1010 xxxx 10x0 x000 xxxx xxxx
+	 * CPS			1111 0011 1010 xxxx 10x0 xxxx xxxx xxxx
+	 * CLREX/DSB/DMB/ISB	1111 0011 1011 xxxx 10x0 xxxx xxxx xxxx
+	 * BXJ			1111 0011 1100 xxxx 10x0 xxxx xxxx xxxx
+	 * SUBS PC,LR,#<imm8>	1111 0011 1101 xxxx 10x0 xxxx xxxx xxxx
+	 * MRS Rd, SPSR		1111 0011 1111 xxxx 10x0 xxxx xxxx xxxx
+	 * SMC			1111 0111 1111 xxxx 1000 xxxx xxxx xxxx
+	 * UNDEFINED		1111 0111 1111 xxxx 1010 xxxx xxxx xxxx
+	 * ???			1111 0111 1xxx xxxx 1010 xxxx xxxx xxxx
+	 */
+	DECODE_REJECT	(0xfb80d000, 0xf3808000),
+
+	/* Bcc			1111 0xxx xxxx xxxx 10x0 xxxx xxxx xxxx */
+	DECODE_CUSTOM	(0xf800d000, 0xf0008000, PROBES_T32_BRANCH_COND),
+
+	/* BLX			1111 0xxx xxxx xxxx 11x0 xxxx xxxx xxx0 */
+	DECODE_OR	(0xf800d001, 0xf000c000),
+	/* B			1111 0xxx xxxx xxxx 10x1 xxxx xxxx xxxx */
+	/* BL			1111 0xxx xxxx xxxx 11x1 xxxx xxxx xxxx */
+	DECODE_SIMULATE	(0xf8009000, 0xf0009000, PROBES_T32_BRANCH),
+
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_100x_x0x1__1111[] = {
+	/* Memory hints							*/
+
+	/* PLD (literal)	1111 1000 x001 1111 1111 xxxx xxxx xxxx */
+	/* PLI (literal)	1111 1001 x001 1111 1111 xxxx xxxx xxxx */
+	DECODE_SIMULATE	(0xfe7ff000, 0xf81ff000, PROBES_T32_PLDI),
+
+	/* PLD{W} (immediate)	1111 1000 10x1 xxxx 1111 xxxx xxxx xxxx */
+	DECODE_OR	(0xffd0f000, 0xf890f000),
+	/* PLD{W} (immediate)	1111 1000 00x1 xxxx 1111 1100 xxxx xxxx */
+	DECODE_OR	(0xffd0ff00, 0xf810fc00),
+	/* PLI (immediate)	1111 1001 1001 xxxx 1111 xxxx xxxx xxxx */
+	DECODE_OR	(0xfff0f000, 0xf990f000),
+	/* PLI (immediate)	1111 1001 0001 xxxx 1111 1100 xxxx xxxx */
+	DECODE_SIMULATEX(0xfff0ff00, 0xf910fc00, PROBES_T32_PLDI,
+						 REGS(NOPCX, 0, 0, 0, 0)),
+
+	/* PLD{W} (register)	1111 1000 00x1 xxxx 1111 0000 00xx xxxx */
+	DECODE_OR	(0xffd0ffc0, 0xf810f000),
+	/* PLI (register)	1111 1001 0001 xxxx 1111 0000 00xx xxxx */
+	DECODE_SIMULATEX(0xfff0ffc0, 0xf910f000, PROBES_T32_PLDI,
+						 REGS(NOPCX, 0, 0, 0, NOSPPC)),
+
+	/* Other unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_100x[] = {
+	/* Store/Load single data item					*/
+
+	/* ???			1111 100x x11x xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfe600000, 0xf8600000),
+
+	/* ???			1111 1001 0101 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xfff00000, 0xf9500000),
+
+	/* ???			1111 100x 0xxx xxxx xxxx 10x0 xxxx xxxx */
+	DECODE_REJECT	(0xfe800d00, 0xf8000800),
+
+	/* STRBT		1111 1000 0000 xxxx xxxx 1110 xxxx xxxx */
+	/* STRHT		1111 1000 0010 xxxx xxxx 1110 xxxx xxxx */
+	/* STRT			1111 1000 0100 xxxx xxxx 1110 xxxx xxxx */
+	/* LDRBT		1111 1000 0001 xxxx xxxx 1110 xxxx xxxx */
+	/* LDRSBT		1111 1001 0001 xxxx xxxx 1110 xxxx xxxx */
+	/* LDRHT		1111 1000 0011 xxxx xxxx 1110 xxxx xxxx */
+	/* LDRSHT		1111 1001 0011 xxxx xxxx 1110 xxxx xxxx */
+	/* LDRT			1111 1000 0101 xxxx xxxx 1110 xxxx xxxx */
+	DECODE_REJECT	(0xfe800f00, 0xf8000e00),
+
+	/* STR{,B,H} Rn,[PC...]	1111 1000 xxx0 1111 xxxx xxxx xxxx xxxx */
+	DECODE_REJECT	(0xff1f0000, 0xf80f0000),
+
+	/* STR{,B,H} PC,[Rn...]	1111 1000 xxx0 xxxx 1111 xxxx xxxx xxxx */
+	DECODE_REJECT	(0xff10f000, 0xf800f000),
+
+	/* LDR (literal)	1111 1000 x101 1111 xxxx xxxx xxxx xxxx */
+	DECODE_SIMULATEX(0xff7f0000, 0xf85f0000, PROBES_T32_LDR_LIT,
+						 REGS(PC, ANY, 0, 0, 0)),
+
+	/* STR (immediate)	1111 1000 0100 xxxx xxxx 1xxx xxxx xxxx */
+	/* LDR (immediate)	1111 1000 0101 xxxx xxxx 1xxx xxxx xxxx */
+	DECODE_OR	(0xffe00800, 0xf8400800),
+	/* STR (immediate)	1111 1000 1100 xxxx xxxx xxxx xxxx xxxx */
+	/* LDR (immediate)	1111 1000 1101 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xffe00000, 0xf8c00000, PROBES_T32_LDRSTR,
+						 REGS(NOPCX, ANY, 0, 0, 0)),
+
+	/* STR (register)	1111 1000 0100 xxxx xxxx 0000 00xx xxxx */
+	/* LDR (register)	1111 1000 0101 xxxx xxxx 0000 00xx xxxx */
+	DECODE_EMULATEX	(0xffe00fc0, 0xf8400000, PROBES_T32_LDRSTR,
+						 REGS(NOPCX, ANY, 0, 0, NOSPPC)),
+
+	/* LDRB (literal)	1111 1000 x001 1111 xxxx xxxx xxxx xxxx */
+	/* LDRSB (literal)	1111 1001 x001 1111 xxxx xxxx xxxx xxxx */
+	/* LDRH (literal)	1111 1000 x011 1111 xxxx xxxx xxxx xxxx */
+	/* LDRSH (literal)	1111 1001 x011 1111 xxxx xxxx xxxx xxxx */
+	DECODE_SIMULATEX(0xfe5f0000, 0xf81f0000, PROBES_T32_LDR_LIT,
+						 REGS(PC, NOSPPCX, 0, 0, 0)),
+
+	/* STRB (immediate)	1111 1000 0000 xxxx xxxx 1xxx xxxx xxxx */
+	/* STRH (immediate)	1111 1000 0010 xxxx xxxx 1xxx xxxx xxxx */
+	/* LDRB (immediate)	1111 1000 0001 xxxx xxxx 1xxx xxxx xxxx */
+	/* LDRSB (immediate)	1111 1001 0001 xxxx xxxx 1xxx xxxx xxxx */
+	/* LDRH (immediate)	1111 1000 0011 xxxx xxxx 1xxx xxxx xxxx */
+	/* LDRSH (immediate)	1111 1001 0011 xxxx xxxx 1xxx xxxx xxxx */
+	DECODE_OR	(0xfec00800, 0xf8000800),
+	/* STRB (immediate)	1111 1000 1000 xxxx xxxx xxxx xxxx xxxx */
+	/* STRH (immediate)	1111 1000 1010 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRB (immediate)	1111 1000 1001 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRSB (immediate)	1111 1001 1001 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRH (immediate)	1111 1000 1011 xxxx xxxx xxxx xxxx xxxx */
+	/* LDRSH (immediate)	1111 1001 1011 xxxx xxxx xxxx xxxx xxxx */
+	DECODE_EMULATEX	(0xfec00000, 0xf8800000, PROBES_T32_LDRSTR,
+						 REGS(NOPCX, NOSPPCX, 0, 0, 0)),
+
+	/* STRB (register)	1111 1000 0000 xxxx xxxx 0000 00xx xxxx */
+	/* STRH (register)	1111 1000 0010 xxxx xxxx 0000 00xx xxxx */
+	/* LDRB (register)	1111 1000 0001 xxxx xxxx 0000 00xx xxxx */
+	/* LDRSB (register)	1111 1001 0001 xxxx xxxx 0000 00xx xxxx */
+	/* LDRH (register)	1111 1000 0011 xxxx xxxx 0000 00xx xxxx */
+	/* LDRSH (register)	1111 1001 0011 xxxx xxxx 0000 00xx xxxx */
+	DECODE_EMULATEX	(0xfe800fc0, 0xf8000000, PROBES_T32_LDRSTR,
+						 REGS(NOPCX, NOSPPCX, 0, 0, NOSPPC)),
+
+	/* Other unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_1010___1111[] = {
+	/* Data-processing (register)					*/
+
+	/* ???			1111 1010 011x xxxx 1111 xxxx 1xxx xxxx */
+	DECODE_REJECT	(0xffe0f080, 0xfa60f080),
+
+	/* SXTH			1111 1010 0000 1111 1111 xxxx 1xxx xxxx */
+	/* UXTH			1111 1010 0001 1111 1111 xxxx 1xxx xxxx */
+	/* SXTB16		1111 1010 0010 1111 1111 xxxx 1xxx xxxx */
+	/* UXTB16		1111 1010 0011 1111 1111 xxxx 1xxx xxxx */
+	/* SXTB			1111 1010 0100 1111 1111 xxxx 1xxx xxxx */
+	/* UXTB			1111 1010 0101 1111 1111 xxxx 1xxx xxxx */
+	DECODE_EMULATEX	(0xff8ff080, 0xfa0ff080, PROBES_T32_SIGN_EXTEND,
+						 REGS(0, 0, NOSPPC, 0, NOSPPC)),
+
+
+	/* ???			1111 1010 1xxx xxxx 1111 xxxx 0x11 xxxx */
+	DECODE_REJECT	(0xff80f0b0, 0xfa80f030),
+	/* ???			1111 1010 1x11 xxxx 1111 xxxx 0xxx xxxx */
+	DECODE_REJECT	(0xffb0f080, 0xfab0f000),
+
+	/* SADD16		1111 1010 1001 xxxx 1111 xxxx 0000 xxxx */
+	/* SASX			1111 1010 1010 xxxx 1111 xxxx 0000 xxxx */
+	/* SSAX			1111 1010 1110 xxxx 1111 xxxx 0000 xxxx */
+	/* SSUB16		1111 1010 1101 xxxx 1111 xxxx 0000 xxxx */
+	/* SADD8		1111 1010 1000 xxxx 1111 xxxx 0000 xxxx */
+	/* SSUB8		1111 1010 1100 xxxx 1111 xxxx 0000 xxxx */
+
+	/* QADD16		1111 1010 1001 xxxx 1111 xxxx 0001 xxxx */
+	/* QASX			1111 1010 1010 xxxx 1111 xxxx 0001 xxxx */
+	/* QSAX			1111 1010 1110 xxxx 1111 xxxx 0001 xxxx */
+	/* QSUB16		1111 1010 1101 xxxx 1111 xxxx 0001 xxxx */
+	/* QADD8		1111 1010 1000 xxxx 1111 xxxx 0001 xxxx */
+	/* QSUB8		1111 1010 1100 xxxx 1111 xxxx 0001 xxxx */
+
+	/* SHADD16		1111 1010 1001 xxxx 1111 xxxx 0010 xxxx */
+	/* SHASX		1111 1010 1010 xxxx 1111 xxxx 0010 xxxx */
+	/* SHSAX		1111 1010 1110 xxxx 1111 xxxx 0010 xxxx */
+	/* SHSUB16		1111 1010 1101 xxxx 1111 xxxx 0010 xxxx */
+	/* SHADD8		1111 1010 1000 xxxx 1111 xxxx 0010 xxxx */
+	/* SHSUB8		1111 1010 1100 xxxx 1111 xxxx 0010 xxxx */
+
+	/* UADD16		1111 1010 1001 xxxx 1111 xxxx 0100 xxxx */
+	/* UASX			1111 1010 1010 xxxx 1111 xxxx 0100 xxxx */
+	/* USAX			1111 1010 1110 xxxx 1111 xxxx 0100 xxxx */
+	/* USUB16		1111 1010 1101 xxxx 1111 xxxx 0100 xxxx */
+	/* UADD8		1111 1010 1000 xxxx 1111 xxxx 0100 xxxx */
+	/* USUB8		1111 1010 1100 xxxx 1111 xxxx 0100 xxxx */
+
+	/* UQADD16		1111 1010 1001 xxxx 1111 xxxx 0101 xxxx */
+	/* UQASX		1111 1010 1010 xxxx 1111 xxxx 0101 xxxx */
+	/* UQSAX		1111 1010 1110 xxxx 1111 xxxx 0101 xxxx */
+	/* UQSUB16		1111 1010 1101 xxxx 1111 xxxx 0101 xxxx */
+	/* UQADD8		1111 1010 1000 xxxx 1111 xxxx 0101 xxxx */
+	/* UQSUB8		1111 1010 1100 xxxx 1111 xxxx 0101 xxxx */
+
+	/* UHADD16		1111 1010 1001 xxxx 1111 xxxx 0110 xxxx */
+	/* UHASX		1111 1010 1010 xxxx 1111 xxxx 0110 xxxx */
+	/* UHSAX		1111 1010 1110 xxxx 1111 xxxx 0110 xxxx */
+	/* UHSUB16		1111 1010 1101 xxxx 1111 xxxx 0110 xxxx */
+	/* UHADD8		1111 1010 1000 xxxx 1111 xxxx 0110 xxxx */
+	/* UHSUB8		1111 1010 1100 xxxx 1111 xxxx 0110 xxxx */
+	DECODE_OR	(0xff80f080, 0xfa80f000),
+
+	/* SXTAH		1111 1010 0000 xxxx 1111 xxxx 1xxx xxxx */
+	/* UXTAH		1111 1010 0001 xxxx 1111 xxxx 1xxx xxxx */
+	/* SXTAB16		1111 1010 0010 xxxx 1111 xxxx 1xxx xxxx */
+	/* UXTAB16		1111 1010 0011 xxxx 1111 xxxx 1xxx xxxx */
+	/* SXTAB		1111 1010 0100 xxxx 1111 xxxx 1xxx xxxx */
+	/* UXTAB		1111 1010 0101 xxxx 1111 xxxx 1xxx xxxx */
+	DECODE_OR	(0xff80f080, 0xfa00f080),
+
+	/* QADD			1111 1010 1000 xxxx 1111 xxxx 1000 xxxx */
+	/* QDADD		1111 1010 1000 xxxx 1111 xxxx 1001 xxxx */
+	/* QSUB			1111 1010 1000 xxxx 1111 xxxx 1010 xxxx */
+	/* QDSUB		1111 1010 1000 xxxx 1111 xxxx 1011 xxxx */
+	DECODE_OR	(0xfff0f0c0, 0xfa80f080),
+
+	/* SEL			1111 1010 1010 xxxx 1111 xxxx 1000 xxxx */
+	DECODE_OR	(0xfff0f0f0, 0xfaa0f080),
+
+	/* LSL			1111 1010 000x xxxx 1111 xxxx 0000 xxxx */
+	/* LSR			1111 1010 001x xxxx 1111 xxxx 0000 xxxx */
+	/* ASR			1111 1010 010x xxxx 1111 xxxx 0000 xxxx */
+	/* ROR			1111 1010 011x xxxx 1111 xxxx 0000 xxxx */
+	DECODE_EMULATEX	(0xff80f0f0, 0xfa00f000, PROBES_T32_MEDIA,
+						 REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)),
+
+	/* CLZ			1111 1010 1010 xxxx 1111 xxxx 1000 xxxx */
+	DECODE_OR	(0xfff0f0f0, 0xfab0f080),
+
+	/* REV			1111 1010 1001 xxxx 1111 xxxx 1000 xxxx */
+	/* REV16		1111 1010 1001 xxxx 1111 xxxx 1001 xxxx */
+	/* RBIT			1111 1010 1001 xxxx 1111 xxxx 1010 xxxx */
+	/* REVSH		1111 1010 1001 xxxx 1111 xxxx 1011 xxxx */
+	DECODE_EMULATEX	(0xfff0f0c0, 0xfa90f080, PROBES_T32_REVERSE,
+						 REGS(NOSPPC, 0, NOSPPC, 0, SAMEAS16)),
+
+	/* Other unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_1011_0[] = {
+	/* Multiply, multiply accumulate, and absolute difference	*/
+
+	/* ???			1111 1011 0000 xxxx 1111 xxxx 0001 xxxx */
+	DECODE_REJECT	(0xfff0f0f0, 0xfb00f010),
+	/* ???			1111 1011 0111 xxxx 1111 xxxx 0001 xxxx */
+	DECODE_REJECT	(0xfff0f0f0, 0xfb70f010),
+
+	/* SMULxy		1111 1011 0001 xxxx 1111 xxxx 00xx xxxx */
+	DECODE_OR	(0xfff0f0c0, 0xfb10f000),
+	/* MUL			1111 1011 0000 xxxx 1111 xxxx 0000 xxxx */
+	/* SMUAD{X}		1111 1011 0010 xxxx 1111 xxxx 000x xxxx */
+	/* SMULWy		1111 1011 0011 xxxx 1111 xxxx 000x xxxx */
+	/* SMUSD{X}		1111 1011 0100 xxxx 1111 xxxx 000x xxxx */
+	/* SMMUL{R}		1111 1011 0101 xxxx 1111 xxxx 000x xxxx */
+	/* USAD8		1111 1011 0111 xxxx 1111 xxxx 0000 xxxx */
+	DECODE_EMULATEX	(0xff80f0e0, 0xfb00f000, PROBES_T32_MUL_ADD,
+						 REGS(NOSPPC, 0, NOSPPC, 0, NOSPPC)),
+
+	/* ???			1111 1011 0111 xxxx xxxx xxxx 0001 xxxx */
+	DECODE_REJECT	(0xfff000f0, 0xfb700010),
+
+	/* SMLAxy		1111 1011 0001 xxxx xxxx xxxx 00xx xxxx */
+	DECODE_OR	(0xfff000c0, 0xfb100000),
+	/* MLA			1111 1011 0000 xxxx xxxx xxxx 0000 xxxx */
+	/* MLS			1111 1011 0000 xxxx xxxx xxxx 0001 xxxx */
+	/* SMLAD{X}		1111 1011 0010 xxxx xxxx xxxx 000x xxxx */
+	/* SMLAWy		1111 1011 0011 xxxx xxxx xxxx 000x xxxx */
+	/* SMLSD{X}		1111 1011 0100 xxxx xxxx xxxx 000x xxxx */
+	/* SMMLA{R}		1111 1011 0101 xxxx xxxx xxxx 000x xxxx */
+	/* SMMLS{R}		1111 1011 0110 xxxx xxxx xxxx 000x xxxx */
+	/* USADA8		1111 1011 0111 xxxx xxxx xxxx 0000 xxxx */
+	DECODE_EMULATEX	(0xff8000c0, 0xfb000000,  PROBES_T32_MUL_ADD2,
+						 REGS(NOSPPC, NOSPPCX, NOSPPC, 0, NOSPPC)),
+
+	/* Other unallocated instructions...				*/
+	DECODE_END
+};
+
+static const union decode_item t32_table_1111_1011_1[] = {
+	/* Long multiply, long multiply accumulate, and divide		*/
+
+	/* UMAAL		1111 1011 1110 xxxx xxxx xxxx 0110 xxxx */
+	DECODE_OR	(0xfff000f0, 0xfbe00060),
+	/* SMLALxy		1111 1011 1100 xxxx xxxx xxxx 10xx xxxx */
+	DECODE_OR	(0xfff000c0, 0xfbc00080),
+	/* SMLALD{X}		1111 1011 1100 xxxx xxxx xxxx 110x xxxx */
+	/* SMLSLD{X}		1111 1011 1101 xxxx xxxx xxxx 110x xxxx */
+	DECODE_OR	(0xffe000e0, 0xfbc000c0),
+	/* SMULL		1111 1011 1000 xxxx xxxx xxxx 0000 xxxx */
+	/* UMULL		1111 1011 1010 xxxx xxxx xxxx 0000 xxxx */
+	/* SMLAL		1111 1011 1100 xxxx xxxx xxxx 0000 xxxx */
+	/* UMLAL		1111 1011 1110 xxxx xxxx xxxx 0000 xxxx */
+	DECODE_EMULATEX	(0xff9000f0, 0xfb800000, PROBES_T32_MUL_ADD_LONG,
+						 REGS(NOSPPC, NOSPPC, NOSPPC, 0, NOSPPC)),
+
+	/* SDIV			1111 1011 1001 xxxx xxxx xxxx 1111 xxxx */
+	/* UDIV			1111 1011 1011 xxxx xxxx xxxx 1111 xxxx */
+	/* Other unallocated instructions...				*/
+	DECODE_END
+};
+
+const union decode_item probes_decode_thumb32_table[] = {
+
+	/*
+	 * Load/store multiple instructions
+	 *			1110 100x x0xx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xfe400000, 0xe8000000, t32_table_1110_100x_x0xx),
+
+	/*
+	 * Load/store dual, load/store exclusive, table branch
+	 *			1110 100x x1xx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xfe400000, 0xe8400000, t32_table_1110_100x_x1xx),
+
+	/*
+	 * Data-processing (shifted register)
+	 *			1110 101x xxxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xfe000000, 0xea000000, t32_table_1110_101x),
+
+	/*
+	 * Coprocessor instructions
+	 *			1110 11xx xxxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_REJECT	(0xfc000000, 0xec000000),
+
+	/*
+	 * Data-processing (modified immediate)
+	 *			1111 0x0x xxxx xxxx 0xxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xfa008000, 0xf0000000, t32_table_1111_0x0x___0),
+
+	/*
+	 * Data-processing (plain binary immediate)
+	 *			1111 0x1x xxxx xxxx 0xxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xfa008000, 0xf2000000, t32_table_1111_0x1x___0),
+
+	/*
+	 * Branches and miscellaneous control
+	 *			1111 0xxx xxxx xxxx 1xxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xf8008000, 0xf0008000, t32_table_1111_0xxx___1),
+
+	/*
+	 * Advanced SIMD element or structure load/store instructions
+	 *			1111 1001 xxx0 xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_REJECT	(0xff100000, 0xf9000000),
+
+	/*
+	 * Memory hints
+	 *			1111 100x x0x1 xxxx 1111 xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xfe50f000, 0xf810f000, t32_table_1111_100x_x0x1__1111),
+
+	/*
+	 * Store single data item
+	 *			1111 1000 xxx0 xxxx xxxx xxxx xxxx xxxx
+	 * Load single data items
+	 *			1111 100x xxx1 xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xfe000000, 0xf8000000, t32_table_1111_100x),
+
+	/*
+	 * Data-processing (register)
+	 *			1111 1010 xxxx xxxx 1111 xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xff00f000, 0xfa00f000, t32_table_1111_1010___1111),
+
+	/*
+	 * Multiply, multiply accumulate, and absolute difference
+	 *			1111 1011 0xxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xff800000, 0xfb000000, t32_table_1111_1011_0),
+
+	/*
+	 * Long multiply, long multiply accumulate, and divide
+	 *			1111 1011 1xxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xff800000, 0xfb800000, t32_table_1111_1011_1),
+
+	/*
+	 * Coprocessor instructions
+	 *			1111 11xx xxxx xxxx xxxx xxxx xxxx xxxx
+	 */
+	DECODE_END
+};
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(probes_decode_thumb32_table);
+#endif
+
+static const union decode_item t16_table_1011[] = {
+	/* Miscellaneous 16-bit instructions		    */
+
+	/* ADD (SP plus immediate)	1011 0000 0xxx xxxx */
+	/* SUB (SP minus immediate)	1011 0000 1xxx xxxx */
+	DECODE_SIMULATE	(0xff00, 0xb000, PROBES_T16_ADD_SP),
+
+	/* CBZ				1011 00x1 xxxx xxxx */
+	/* CBNZ				1011 10x1 xxxx xxxx */
+	DECODE_SIMULATE	(0xf500, 0xb100, PROBES_T16_CBZ),
+
+	/* SXTH				1011 0010 00xx xxxx */
+	/* SXTB				1011 0010 01xx xxxx */
+	/* UXTH				1011 0010 10xx xxxx */
+	/* UXTB				1011 0010 11xx xxxx */
+	/* REV				1011 1010 00xx xxxx */
+	/* REV16			1011 1010 01xx xxxx */
+	/* ???				1011 1010 10xx xxxx */
+	/* REVSH			1011 1010 11xx xxxx */
+	DECODE_REJECT	(0xffc0, 0xba80),
+	DECODE_EMULATE	(0xf500, 0xb000, PROBES_T16_SIGN_EXTEND),
+
+	/* PUSH				1011 010x xxxx xxxx */
+	DECODE_CUSTOM	(0xfe00, 0xb400, PROBES_T16_PUSH),
+	/* POP				1011 110x xxxx xxxx */
+	DECODE_CUSTOM	(0xfe00, 0xbc00, PROBES_T16_POP),
+
+	/*
+	 * If-Then, and hints
+	 *				1011 1111 xxxx xxxx
+	 */
+
+	/* YIELD			1011 1111 0001 0000 */
+	DECODE_OR	(0xffff, 0xbf10),
+	/* SEV				1011 1111 0100 0000 */
+	DECODE_EMULATE	(0xffff, 0xbf40, PROBES_T16_SEV),
+	/* NOP				1011 1111 0000 0000 */
+	/* WFE				1011 1111 0010 0000 */
+	/* WFI				1011 1111 0011 0000 */
+	DECODE_SIMULATE	(0xffcf, 0xbf00, PROBES_T16_WFE),
+	/* Unassigned hints		1011 1111 xxxx 0000 */
+	DECODE_REJECT	(0xff0f, 0xbf00),
+	/* IT				1011 1111 xxxx xxxx */
+	DECODE_CUSTOM	(0xff00, 0xbf00, PROBES_T16_IT),
+
+	/* SETEND			1011 0110 010x xxxx */
+	/* CPS				1011 0110 011x xxxx */
+	/* BKPT				1011 1110 xxxx xxxx */
+	/* And unallocated instructions...		    */
+	DECODE_END
+};
+
+const union decode_item probes_decode_thumb16_table[] = {
+
+	/*
+	 * Shift (immediate), add, subtract, move, and compare
+	 *				00xx xxxx xxxx xxxx
+	 */
+
+	/* CMP (immediate)		0010 1xxx xxxx xxxx */
+	DECODE_EMULATE	(0xf800, 0x2800, PROBES_T16_CMP),
+
+	/* ADD (register)		0001 100x xxxx xxxx */
+	/* SUB (register)		0001 101x xxxx xxxx */
+	/* LSL (immediate)		0000 0xxx xxxx xxxx */
+	/* LSR (immediate)		0000 1xxx xxxx xxxx */
+	/* ASR (immediate)		0001 0xxx xxxx xxxx */
+	/* ADD (immediate, Thumb)	0001 110x xxxx xxxx */
+	/* SUB (immediate, Thumb)	0001 111x xxxx xxxx */
+	/* MOV (immediate)		0010 0xxx xxxx xxxx */
+	/* ADD (immediate, Thumb)	0011 0xxx xxxx xxxx */
+	/* SUB (immediate, Thumb)	0011 1xxx xxxx xxxx */
+	DECODE_EMULATE	(0xc000, 0x0000, PROBES_T16_ADDSUB),
+
+	/*
+	 * 16-bit Thumb data-processing instructions
+	 *				0100 00xx xxxx xxxx
+	 */
+
+	/* TST (register)		0100 0010 00xx xxxx */
+	DECODE_EMULATE	(0xffc0, 0x4200, PROBES_T16_CMP),
+	/* CMP (register)		0100 0010 10xx xxxx */
+	/* CMN (register)		0100 0010 11xx xxxx */
+	DECODE_EMULATE	(0xff80, 0x4280, PROBES_T16_CMP),
+	/* AND (register)		0100 0000 00xx xxxx */
+	/* EOR (register)		0100 0000 01xx xxxx */
+	/* LSL (register)		0100 0000 10xx xxxx */
+	/* LSR (register)		0100 0000 11xx xxxx */
+	/* ASR (register)		0100 0001 00xx xxxx */
+	/* ADC (register)		0100 0001 01xx xxxx */
+	/* SBC (register)		0100 0001 10xx xxxx */
+	/* ROR (register)		0100 0001 11xx xxxx */
+	/* RSB (immediate)		0100 0010 01xx xxxx */
+	/* ORR (register)		0100 0011 00xx xxxx */
+	/* MUL				0100 0011 00xx xxxx */
+	/* BIC (register)		0100 0011 10xx xxxx */
+	/* MVN (register)		0100 0011 10xx xxxx */
+	DECODE_EMULATE	(0xfc00, 0x4000, PROBES_T16_LOGICAL),
+
+	/*
+	 * Special data instructions and branch and exchange
+	 *				0100 01xx xxxx xxxx
+	 */
+
+	/* BLX pc			0100 0111 1111 1xxx */
+	DECODE_REJECT	(0xfff8, 0x47f8),
+
+	/* BX (register)		0100 0111 0xxx xxxx */
+	/* BLX (register)		0100 0111 1xxx xxxx */
+	DECODE_SIMULATE (0xff00, 0x4700, PROBES_T16_BLX),
+
+	/* ADD pc, pc			0100 0100 1111 1111 */
+	DECODE_REJECT	(0xffff, 0x44ff),
+
+	/* ADD (register)		0100 0100 xxxx xxxx */
+	/* CMP (register)		0100 0101 xxxx xxxx */
+	/* MOV (register)		0100 0110 xxxx xxxx */
+	DECODE_CUSTOM	(0xfc00, 0x4400, PROBES_T16_HIREGOPS),
+
+	/*
+	 * Load from Literal Pool
+	 * LDR (literal)		0100 1xxx xxxx xxxx
+	 */
+	DECODE_SIMULATE	(0xf800, 0x4800, PROBES_T16_LDR_LIT),
+
+	/*
+	 * 16-bit Thumb Load/store instructions
+	 *				0101 xxxx xxxx xxxx
+	 *				011x xxxx xxxx xxxx
+	 *				100x xxxx xxxx xxxx
+	 */
+
+	/* STR (register)		0101 000x xxxx xxxx */
+	/* STRH (register)		0101 001x xxxx xxxx */
+	/* STRB (register)		0101 010x xxxx xxxx */
+	/* LDRSB (register)		0101 011x xxxx xxxx */
+	/* LDR (register)		0101 100x xxxx xxxx */
+	/* LDRH (register)		0101 101x xxxx xxxx */
+	/* LDRB (register)		0101 110x xxxx xxxx */
+	/* LDRSH (register)		0101 111x xxxx xxxx */
+	/* STR (immediate, Thumb)	0110 0xxx xxxx xxxx */
+	/* LDR (immediate, Thumb)	0110 1xxx xxxx xxxx */
+	/* STRB (immediate, Thumb)	0111 0xxx xxxx xxxx */
+	/* LDRB (immediate, Thumb)	0111 1xxx xxxx xxxx */
+	DECODE_EMULATE	(0xc000, 0x4000, PROBES_T16_LDRHSTRH),
+	/* STRH (immediate, Thumb)	1000 0xxx xxxx xxxx */
+	/* LDRH (immediate, Thumb)	1000 1xxx xxxx xxxx */
+	DECODE_EMULATE	(0xf000, 0x8000, PROBES_T16_LDRHSTRH),
+	/* STR (immediate, Thumb)	1001 0xxx xxxx xxxx */
+	/* LDR (immediate, Thumb)	1001 1xxx xxxx xxxx */
+	DECODE_SIMULATE	(0xf000, 0x9000, PROBES_T16_LDRSTR),
+
+	/*
+	 * Generate PC-/SP-relative address
+	 * ADR (literal)		1010 0xxx xxxx xxxx
+	 * ADD (SP plus immediate)	1010 1xxx xxxx xxxx
+	 */
+	DECODE_SIMULATE	(0xf000, 0xa000, PROBES_T16_ADR),
+
+	/*
+	 * Miscellaneous 16-bit instructions
+	 *				1011 xxxx xxxx xxxx
+	 */
+	DECODE_TABLE	(0xf000, 0xb000, t16_table_1011),
+
+	/* STM				1100 0xxx xxxx xxxx */
+	/* LDM				1100 1xxx xxxx xxxx */
+	DECODE_EMULATE	(0xf000, 0xc000, PROBES_T16_LDMSTM),
+
+	/*
+	 * Conditional branch, and Supervisor Call
+	 */
+
+	/* Permanently UNDEFINED	1101 1110 xxxx xxxx */
+	/* SVC				1101 1111 xxxx xxxx */
+	DECODE_REJECT	(0xfe00, 0xde00),
+
+	/* Conditional branch		1101 xxxx xxxx xxxx */
+	DECODE_CUSTOM	(0xf000, 0xd000, PROBES_T16_BRANCH_COND),
+
+	/*
+	 * Unconditional branch
+	 * B				1110 0xxx xxxx xxxx
+	 */
+	DECODE_SIMULATE	(0xf800, 0xe000, PROBES_T16_BRANCH),
+
+	DECODE_END
+};
+#ifdef CONFIG_ARM_KPROBES_TEST_MODULE
+EXPORT_SYMBOL_GPL(probes_decode_thumb16_table);
+#endif
+
+static unsigned long __kprobes thumb_check_cc(unsigned long cpsr)
+{
+	if (unlikely(in_it_block(cpsr)))
+		return probes_condition_checks[current_cond(cpsr)](cpsr);
+	return true;
+}
+
+static void __kprobes thumb16_singlestep(probes_opcode_t opcode,
+		struct arch_probes_insn *asi,
+		struct pt_regs *regs)
+{
+	regs->ARM_pc += 2;
+	asi->insn_handler(opcode, asi, regs);
+	regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
+}
+
+static void __kprobes thumb32_singlestep(probes_opcode_t opcode,
+		struct arch_probes_insn *asi,
+		struct pt_regs *regs)
+{
+	regs->ARM_pc += 4;
+	asi->insn_handler(opcode, asi, regs);
+	regs->ARM_cpsr = it_advance(regs->ARM_cpsr);
+}
+
+enum probes_insn __kprobes
+thumb16_probes_decode_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+			   bool emulate, const union decode_action *actions)
+{
+	asi->insn_singlestep = thumb16_singlestep;
+	asi->insn_check_cc = thumb_check_cc;
+	return probes_decode_insn(insn, asi, probes_decode_thumb16_table, true,
+				  emulate, 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)
+{
+	asi->insn_singlestep = thumb32_singlestep;
+	asi->insn_check_cc = thumb_check_cc;
+	return probes_decode_insn(insn, asi, probes_decode_thumb32_table, true,
+				  emulate, actions);
+}

arch/arm/kernel/probes-thumb.h

@@ -0,0 +1,97 @@
+/*
+ * 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/probes.c

@@ -0,0 +1,455 @@
+/*
+ * arch/arm/kernel/probes.c
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * Some contents moved here from arch/arm/include/asm/kprobes-arm.c which is
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <asm/system_info.h>
+#include <asm/ptrace.h>
+#include <linux/bug.h>
+
+#include "probes.h"
+
+
+#ifndef find_str_pc_offset
+
+/*
+ * For STR and STM instructions, an ARM core may choose to use either
+ * a +8 or a +12 displacement from the current instruction's address.
+ * Whichever value is chosen for a given core, it must be the same for
+ * both instructions and may not change.  This function measures it.
+ */
+
+int str_pc_offset;
+
+void __init find_str_pc_offset(void)
+{
+	int addr, scratch, ret;
+
+	__asm__ (
+		"sub	%[ret], pc, #4		\n\t"
+		"str	pc, %[addr]		\n\t"
+		"ldr	%[scr], %[addr]		\n\t"
+		"sub	%[ret], %[scr], %[ret]	\n\t"
+		: [ret] "=r" (ret), [scr] "=r" (scratch), [addr] "+m" (addr));
+
+	str_pc_offset = ret;
+}
+
+#endif /* !find_str_pc_offset */
+
+
+#ifndef test_load_write_pc_interworking
+
+bool load_write_pc_interworks;
+
+void __init test_load_write_pc_interworking(void)
+{
+	int arch = cpu_architecture();
+	BUG_ON(arch == CPU_ARCH_UNKNOWN);
+	load_write_pc_interworks = arch >= CPU_ARCH_ARMv5T;
+}
+
+#endif /* !test_load_write_pc_interworking */
+
+
+#ifndef test_alu_write_pc_interworking
+
+bool alu_write_pc_interworks;
+
+void __init test_alu_write_pc_interworking(void)
+{
+	int arch = cpu_architecture();
+	BUG_ON(arch == CPU_ARCH_UNKNOWN);
+	alu_write_pc_interworks = arch >= CPU_ARCH_ARMv7;
+}
+
+#endif /* !test_alu_write_pc_interworking */
+
+
+void __init arm_probes_decode_init(void)
+{
+	find_str_pc_offset();
+	test_load_write_pc_interworking();
+	test_alu_write_pc_interworking();
+}
+
+
+static unsigned long __kprobes __check_eq(unsigned long cpsr)
+{
+	return cpsr & PSR_Z_BIT;
+}
+
+static unsigned long __kprobes __check_ne(unsigned long cpsr)
+{
+	return (~cpsr) & PSR_Z_BIT;
+}
+
+static unsigned long __kprobes __check_cs(unsigned long cpsr)
+{
+	return cpsr & PSR_C_BIT;
+}
+
+static unsigned long __kprobes __check_cc(unsigned long cpsr)
+{
+	return (~cpsr) & PSR_C_BIT;
+}
+
+static unsigned long __kprobes __check_mi(unsigned long cpsr)
+{
+	return cpsr & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_pl(unsigned long cpsr)
+{
+	return (~cpsr) & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_vs(unsigned long cpsr)
+{
+	return cpsr & PSR_V_BIT;
+}
+
+static unsigned long __kprobes __check_vc(unsigned long cpsr)
+{
+	return (~cpsr) & PSR_V_BIT;
+}
+
+static unsigned long __kprobes __check_hi(unsigned long cpsr)
+{
+	cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+	return cpsr & PSR_C_BIT;
+}
+
+static unsigned long __kprobes __check_ls(unsigned long cpsr)
+{
+	cpsr &= ~(cpsr >> 1); /* PSR_C_BIT &= ~PSR_Z_BIT */
+	return (~cpsr) & PSR_C_BIT;
+}
+
+static unsigned long __kprobes __check_ge(unsigned long cpsr)
+{
+	cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	return (~cpsr) & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_lt(unsigned long cpsr)
+{
+	cpsr ^= (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	return cpsr & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_gt(unsigned long cpsr)
+{
+	unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	temp |= (cpsr << 1);			 /* PSR_N_BIT |= PSR_Z_BIT */
+	return (~temp) & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_le(unsigned long cpsr)
+{
+	unsigned long temp = cpsr ^ (cpsr << 3); /* PSR_N_BIT ^= PSR_V_BIT */
+	temp |= (cpsr << 1);			 /* PSR_N_BIT |= PSR_Z_BIT */
+	return temp & PSR_N_BIT;
+}
+
+static unsigned long __kprobes __check_al(unsigned long cpsr)
+{
+	return true;
+}
+
+probes_check_cc * const probes_condition_checks[16] = {
+	&__check_eq, &__check_ne, &__check_cs, &__check_cc,
+	&__check_mi, &__check_pl, &__check_vs, &__check_vc,
+	&__check_hi, &__check_ls, &__check_ge, &__check_lt,
+	&__check_gt, &__check_le, &__check_al, &__check_al
+};
+
+
+void __kprobes probes_simulate_nop(probes_opcode_t opcode,
+	struct arch_probes_insn *asi,
+	struct pt_regs *regs)
+{
+}
+
+void __kprobes probes_emulate_none(probes_opcode_t opcode,
+	struct arch_probes_insn *asi,
+	struct pt_regs *regs)
+{
+	asi->insn_fn();
+}
+
+/*
+ * Prepare an instruction slot to receive an instruction for emulating.
+ * This is done by placing a subroutine return after the location where the
+ * instruction will be placed. We also modify ARM instructions to be
+ * unconditional as the condition code will already be checked before any
+ * emulation handler is called.
+ */
+static probes_opcode_t __kprobes
+prepare_emulated_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+		      bool thumb)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	if (thumb) {
+		u16 *thumb_insn = (u16 *)asi->insn;
+		thumb_insn[1] = 0x4770; /* Thumb bx lr */
+		thumb_insn[2] = 0x4770; /* Thumb bx lr */
+		return insn;
+	}
+	asi->insn[1] = 0xe12fff1e; /* ARM bx lr */
+#else
+	asi->insn[1] = 0xe1a0f00e; /* mov pc, lr */
+#endif
+	/* Make an ARM instruction unconditional */
+	if (insn < 0xe0000000)
+		insn = (insn | 0xe0000000) & ~0x10000000;
+	return insn;
+}
+
+/*
+ * Write a (probably modified) instruction into the slot previously prepared by
+ * prepare_emulated_insn
+ */
+static void  __kprobes
+set_emulated_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+		  bool thumb)
+{
+#ifdef CONFIG_THUMB2_KERNEL
+	if (thumb) {
+		u16 *ip = (u16 *)asi->insn;
+		if (is_wide_instruction(insn))
+			*ip++ = insn >> 16;
+		*ip++ = insn;
+		return;
+	}
+#endif
+	asi->insn[0] = insn;
+}
+
+/*
+ * When we modify the register numbers encoded in an instruction to be emulated,
+ * the new values come from this define. For ARM and 32-bit Thumb instructions
+ * this gives...
+ *
+ *	bit position	  16  12   8   4   0
+ *	---------------+---+---+---+---+---+
+ *	register	 r2  r0  r1  --  r3
+ */
+#define INSN_NEW_BITS		0x00020103
+
+/* Each nibble has same value as that at INSN_NEW_BITS bit 16 */
+#define INSN_SAMEAS16_BITS	0x22222222
+
+/*
+ * Validate and modify each of the registers encoded in an instruction.
+ *
+ * Each nibble in regs contains a value from enum decode_reg_type. For each
+ * non-zero value, the corresponding nibble in pinsn is validated and modified
+ * according to the type.
+ */
+static bool __kprobes decode_regs(probes_opcode_t *pinsn, u32 regs, bool modify)
+{
+	probes_opcode_t insn = *pinsn;
+	probes_opcode_t mask = 0xf; /* Start at least significant nibble */
+
+	for (; regs != 0; regs >>= 4, mask <<= 4) {
+
+		probes_opcode_t new_bits = INSN_NEW_BITS;
+
+		switch (regs & 0xf) {
+
+		case REG_TYPE_NONE:
+			/* Nibble not a register, skip to next */
+			continue;
+
+		case REG_TYPE_ANY:
+			/* Any register is allowed */
+			break;
+
+		case REG_TYPE_SAMEAS16:
+			/* Replace register with same as at bit position 16 */
+			new_bits = INSN_SAMEAS16_BITS;
+			break;
+
+		case REG_TYPE_SP:
+			/* Only allow SP (R13) */
+			if ((insn ^ 0xdddddddd) & mask)
+				goto reject;
+			break;
+
+		case REG_TYPE_PC:
+			/* Only allow PC (R15) */
+			if ((insn ^ 0xffffffff) & mask)
+				goto reject;
+			break;
+
+		case REG_TYPE_NOSP:
+			/* Reject SP (R13) */
+			if (((insn ^ 0xdddddddd) & mask) == 0)
+				goto reject;
+			break;
+
+		case REG_TYPE_NOSPPC:
+		case REG_TYPE_NOSPPCX:
+			/* Reject SP and PC (R13 and R15) */
+			if (((insn ^ 0xdddddddd) & 0xdddddddd & mask) == 0)
+				goto reject;
+			break;
+
+		case REG_TYPE_NOPCWB:
+			if (!is_writeback(insn))
+				break; /* No writeback, so any register is OK */
+			/* fall through... */
+		case REG_TYPE_NOPC:
+		case REG_TYPE_NOPCX:
+			/* Reject PC (R15) */
+			if (((insn ^ 0xffffffff) & mask) == 0)
+				goto reject;
+			break;
+		}
+
+		/* Replace value of nibble with new register number... */
+		insn &= ~mask;
+		insn |= new_bits & mask;
+	}
+
+	if (modify)
+		*pinsn = insn;
+
+	return true;
+
+reject:
+	return false;
+}
+
+static const int decode_struct_sizes[NUM_DECODE_TYPES] = {
+	[DECODE_TYPE_TABLE]	= sizeof(struct decode_table),
+	[DECODE_TYPE_CUSTOM]	= sizeof(struct decode_custom),
+	[DECODE_TYPE_SIMULATE]	= sizeof(struct decode_simulate),
+	[DECODE_TYPE_EMULATE]	= sizeof(struct decode_emulate),
+	[DECODE_TYPE_OR]	= sizeof(struct decode_or),
+	[DECODE_TYPE_REJECT]	= sizeof(struct decode_reject)
+};
+
+/*
+ * probes_decode_insn operates on data tables in order to decode an ARM
+ * architecture instruction onto which a kprobe has been placed.
+ *
+ * These instruction decoding tables are a concatenation of entries each
+ * of which consist of one of the following structs:
+ *
+ *	decode_table
+ *	decode_custom
+ *	decode_simulate
+ *	decode_emulate
+ *	decode_or
+ *	decode_reject
+ *
+ * Each of these starts with a struct decode_header which has the following
+ * fields:
+ *
+ *	type_regs
+ *	mask
+ *	value
+ *
+ * The least significant DECODE_TYPE_BITS of type_regs contains a value
+ * from enum decode_type, this indicates which of the decode_* structs
+ * the entry contains. The value DECODE_TYPE_END indicates the end of the
+ * table.
+ *
+ * When the table is parsed, each entry is checked in turn to see if it
+ * matches the instruction to be decoded using the test:
+ *
+ *	(insn & mask) == value
+ *
+ * If no match is found before the end of the table is reached then decoding
+ * fails with INSN_REJECTED.
+ *
+ * When a match is found, decode_regs() is called to validate and modify each
+ * of the registers encoded in the instruction; the data it uses to do this
+ * is (type_regs >> DECODE_TYPE_BITS). A validation failure will cause decoding
+ * to fail with INSN_REJECTED.
+ *
+ * Once the instruction has passed the above tests, further processing
+ * depends on the type of the table entry's decode struct.
+ *
+ */
+int __kprobes
+probes_decode_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+		   const union decode_item *table, bool thumb,
+		   bool emulate, const union decode_action *actions)
+{
+	const struct decode_header *h = (struct decode_header *)table;
+	const struct decode_header *next;
+	bool matched = false;
+
+	if (emulate)
+		insn = prepare_emulated_insn(insn, asi, thumb);
+
+	for (;; h = next) {
+		enum decode_type type = h->type_regs.bits & DECODE_TYPE_MASK;
+		u32 regs = h->type_regs.bits >> DECODE_TYPE_BITS;
+
+		if (type == DECODE_TYPE_END)
+			return INSN_REJECTED;
+
+		next = (struct decode_header *)
+				((uintptr_t)h + decode_struct_sizes[type]);
+
+		if (!matched && (insn & h->mask.bits) != h->value.bits)
+			continue;
+
+		if (!decode_regs(&insn, regs, emulate))
+			return INSN_REJECTED;
+
+		switch (type) {
+
+		case DECODE_TYPE_TABLE: {
+			struct decode_table *d = (struct decode_table *)h;
+			next = (struct decode_header *)d->table.table;
+			break;
+		}
+
+		case DECODE_TYPE_CUSTOM: {
+			struct decode_custom *d = (struct decode_custom *)h;
+			return actions[d->decoder.action].decoder(insn, asi, h);
+		}
+
+		case DECODE_TYPE_SIMULATE: {
+			struct decode_simulate *d = (struct decode_simulate *)h;
+			asi->insn_handler = actions[d->handler.action].handler;
+			return INSN_GOOD_NO_SLOT;
+		}
+
+		case DECODE_TYPE_EMULATE: {
+			struct decode_emulate *d = (struct decode_emulate *)h;
+
+			if (!emulate)
+				return actions[d->handler.action].decoder(insn,
+					asi, h);
+
+			asi->insn_handler = actions[d->handler.action].handler;
+			set_emulated_insn(insn, asi, thumb);
+			return INSN_GOOD;
+		}
+
+		case DECODE_TYPE_OR:
+			matched = true;
+			break;
+
+		case DECODE_TYPE_REJECT:
+		default:
+			return INSN_REJECTED;
+		}
+	}
+}

arch/arm/kernel/probes.h

@@ -0,0 +1,407 @@
+/*
+ * arch/arm/kernel/probes.h
+ *
+ * Copyright (C) 2011 Jon Medhurst <tixy@yxit.co.uk>.
+ *
+ * Some contents moved here from arch/arm/include/asm/kprobes.h which is
+ * 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 _ARM_KERNEL_PROBES_H
+#define  _ARM_KERNEL_PROBES_H
+
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <asm/probes.h>
+
+void __init arm_probes_decode_init(void);
+
+extern probes_check_cc * const probes_condition_checks[16];
+
+#if __LINUX_ARM_ARCH__ >= 7
+
+/* str_pc_offset is architecturally defined from ARMv7 onwards */
+#define str_pc_offset 8
+#define find_str_pc_offset()
+
+#else /* __LINUX_ARM_ARCH__ < 7 */
+
+/* We need a run-time check to determine str_pc_offset */
+extern int str_pc_offset;
+void __init find_str_pc_offset(void);
+
+#endif
+
+
+/*
+ * Update ITSTATE after normal execution of an IT block instruction.
+ *
+ * The 8 IT state bits are split into two parts in CPSR:
+ *	ITSTATE<1:0> are in CPSR<26:25>
+ *	ITSTATE<7:2> are in CPSR<15:10>
+ */
+static inline unsigned long it_advance(unsigned long cpsr)
+	{
+	if ((cpsr & 0x06000400) == 0) {
+		/* ITSTATE<2:0> == 0 means end of IT block, so clear IT state */
+		cpsr &= ~PSR_IT_MASK;
+	} else {
+		/* We need to shift left ITSTATE<4:0> */
+		const unsigned long mask = 0x06001c00;  /* Mask ITSTATE<4:0> */
+		unsigned long it = cpsr & mask;
+		it <<= 1;
+		it |= it >> (27 - 10);  /* Carry ITSTATE<2> to correct place */
+		it &= mask;
+		cpsr &= ~mask;
+		cpsr |= it;
+	}
+	return cpsr;
+}
+
+static inline void __kprobes bx_write_pc(long pcv, struct pt_regs *regs)
+{
+	long cpsr = regs->ARM_cpsr;
+	if (pcv & 0x1) {
+		cpsr |= PSR_T_BIT;
+		pcv &= ~0x1;
+	} else {
+		cpsr &= ~PSR_T_BIT;
+		pcv &= ~0x2;	/* Avoid UNPREDICTABLE address allignment */
+	}
+	regs->ARM_cpsr = cpsr;
+	regs->ARM_pc = pcv;
+}
+
+
+#if __LINUX_ARM_ARCH__ >= 6
+
+/* Kernels built for >= ARMv6 should never run on <= ARMv5 hardware, so... */
+#define load_write_pc_interworks true
+#define test_load_write_pc_interworking()
+
+#else /* __LINUX_ARM_ARCH__ < 6 */
+
+/* We need run-time testing to determine if load_write_pc() should interwork. */
+extern bool load_write_pc_interworks;
+void __init test_load_write_pc_interworking(void);
+
+#endif
+
+static inline void __kprobes load_write_pc(long pcv, struct pt_regs *regs)
+{
+	if (load_write_pc_interworks)
+		bx_write_pc(pcv, regs);
+	else
+		regs->ARM_pc = pcv;
+}
+
+
+#if __LINUX_ARM_ARCH__ >= 7
+
+#define alu_write_pc_interworks true
+#define test_alu_write_pc_interworking()
+
+#elif __LINUX_ARM_ARCH__ <= 5
+
+/* Kernels built for <= ARMv5 should never run on >= ARMv6 hardware, so... */
+#define alu_write_pc_interworks false
+#define test_alu_write_pc_interworking()
+
+#else /* __LINUX_ARM_ARCH__ == 6 */
+
+/* We could be an ARMv6 binary on ARMv7 hardware so we need a run-time check. */
+extern bool alu_write_pc_interworks;
+void __init test_alu_write_pc_interworking(void);
+
+#endif /* __LINUX_ARM_ARCH__ == 6 */
+
+static inline void __kprobes alu_write_pc(long pcv, struct pt_regs *regs)
+{
+	if (alu_write_pc_interworks)
+		bx_write_pc(pcv, regs);
+	else
+		regs->ARM_pc = pcv;
+}
+
+
+/*
+ * Test if load/store instructions writeback the address register.
+ * if P (bit 24) == 0 or W (bit 21) == 1
+ */
+#define is_writeback(insn) ((insn ^ 0x01000000) & 0x01200000)
+
+/*
+ * The following definitions and macros are used to build instruction
+ * decoding tables for use by probes_decode_insn.
+ *
+ * These tables are a concatenation of entries each of which consist of one of
+ * the decode_* structs. All of the fields in every type of decode structure
+ * are of the union type decode_item, therefore the entire decode table can be
+ * viewed as an array of these and declared like:
+ *
+ *	static const union decode_item table_name[] = {};
+ *
+ * In order to construct each entry in the table, macros are used to
+ * initialise a number of sequential decode_item values in a layout which
+ * matches the relevant struct. E.g. DECODE_SIMULATE initialise a struct
+ * decode_simulate by initialising four decode_item objects like this...
+ *
+ *	{.bits = _type},
+ *	{.bits = _mask},
+ *	{.bits = _value},
+ *	{.action = _handler},
+ *
+ * Initialising a specified member of the union means that the compiler
+ * will produce a warning if the argument is of an incorrect type.
+ *
+ * Below is a list of each of the macros used to initialise entries and a
+ * description of the action performed when that entry is matched to an
+ * instruction. A match is found when (instruction & mask) == value.
+ *
+ * DECODE_TABLE(mask, value, table)
+ *	Instruction decoding jumps to parsing the new sub-table 'table'.
+ *
+ * DECODE_CUSTOM(mask, value, decoder)
+ *	The value of 'decoder' is used as an index into the array of
+ *	action functions, and the retrieved decoder function is invoked
+ *	to complete decoding of the instruction.
+ *
+ * DECODE_SIMULATE(mask, value, handler)
+ *	The probes instruction handler is set to the value found by
+ *	indexing into the action array using the value of 'handler'. This
+ *	will be used to simulate the instruction when the probe is hit.
+ *	Decoding returns with INSN_GOOD_NO_SLOT.
+ *
+ * DECODE_EMULATE(mask, value, handler)
+ *	The probes instruction handler is set to the value found by
+ *	indexing into the action array using the value of 'handler'. This
+ *	will be used to emulate the instruction when the probe is hit. The
+ *	modified instruction (see below) is placed in the probes instruction
+ *	slot so it may be called by the emulation code. Decoding returns
+ *	with INSN_GOOD.
+ *
+ * DECODE_REJECT(mask, value)
+ *	Instruction decoding fails with INSN_REJECTED
+ *
+ * DECODE_OR(mask, value)
+ *	This allows the mask/value test of multiple table entries to be
+ *	logically ORed. Once an 'or' entry is matched the decoding action to
+ *	be performed is that of the next entry which isn't an 'or'. E.g.
+ *
+ *		DECODE_OR	(mask1, value1)
+ *		DECODE_OR	(mask2, value2)
+ *		DECODE_SIMULATE	(mask3, value3, simulation_handler)
+ *
+ *	This means that if any of the three mask/value pairs match the
+ *	instruction being decoded, then 'simulation_handler' will be used
+ *	for it.
+ *
+ * Both the SIMULATE and EMULATE macros have a second form which take an
+ * additional 'regs' argument.
+ *
+ *	DECODE_SIMULATEX(mask, value, handler, regs)
+ *	DECODE_EMULATEX	(mask, value, handler, regs)
+ *
+ * These are used to specify what kind of CPU register is encoded in each of the
+ * least significant 5 nibbles of the instruction being decoded. The regs value
+ * is specified using the REGS macro, this takes any of the REG_TYPE_* values
+ * from enum decode_reg_type as arguments; only the '*' part of the name is
+ * given. E.g.
+ *
+ *	REGS(0, ANY, NOPC, 0, ANY)
+ *
+ * This indicates an instruction is encoded like:
+ *
+ *	bits 19..16	ignore
+ *	bits 15..12	any register allowed here
+ *	bits 11.. 8	any register except PC allowed here
+ *	bits  7.. 4	ignore
+ *	bits  3.. 0	any register allowed here
+ *
+ * This register specification is checked after a decode table entry is found to
+ * match an instruction (through the mask/value test). Any invalid register then
+ * found in the instruction will cause decoding to fail with INSN_REJECTED. In
+ * the above example this would happen if bits 11..8 of the instruction were
+ * 1111, indicating R15 or PC.
+ *
+ * As well as checking for legal combinations of registers, this data is also
+ * used to modify the registers encoded in the instructions so that an
+ * emulation routines can use it. (See decode_regs() and INSN_NEW_BITS.)
+ *
+ * Here is a real example which matches ARM instructions of the form
+ * "AND <Rd>,<Rn>,<Rm>,<shift> <Rs>"
+ *
+ *	DECODE_EMULATEX	(0x0e000090, 0x00000010, PROBES_DATA_PROCESSING_REG,
+ *						 REGS(ANY, ANY, NOPC, 0, ANY)),
+ *						      ^    ^    ^        ^
+ *						      Rn   Rd   Rs       Rm
+ *
+ * Decoding the instruction "AND R4, R5, R6, ASL R15" will be rejected because
+ * Rs == R15
+ *
+ * Decoding the instruction "AND R4, R5, R6, ASL R7" will be accepted and the
+ * instruction will be modified to "AND R0, R2, R3, ASL R1" and then placed into
+ * the kprobes instruction slot. This can then be called later by the handler
+ * function emulate_rd12rn16rm0rs8_rwflags (a pointer to which is retrieved from
+ * the indicated slot in the action array), in order to simulate the instruction.
+ */
+
+enum decode_type {
+	DECODE_TYPE_END,
+	DECODE_TYPE_TABLE,
+	DECODE_TYPE_CUSTOM,
+	DECODE_TYPE_SIMULATE,
+	DECODE_TYPE_EMULATE,
+	DECODE_TYPE_OR,
+	DECODE_TYPE_REJECT,
+	NUM_DECODE_TYPES /* Must be last enum */
+};
+
+#define DECODE_TYPE_BITS	4
+#define DECODE_TYPE_MASK	((1 << DECODE_TYPE_BITS) - 1)
+
+enum decode_reg_type {
+	REG_TYPE_NONE = 0, /* Not a register, ignore */
+	REG_TYPE_ANY,	   /* Any register allowed */
+	REG_TYPE_SAMEAS16, /* Register should be same as that at bits 19..16 */
+	REG_TYPE_SP,	   /* Register must be SP */
+	REG_TYPE_PC,	   /* Register must be PC */
+	REG_TYPE_NOSP,	   /* Register must not be SP */
+	REG_TYPE_NOSPPC,   /* Register must not be SP or PC */
+	REG_TYPE_NOPC,	   /* Register must not be PC */
+	REG_TYPE_NOPCWB,   /* No PC if load/store write-back flag also set */
+
+	/* The following types are used when the encoding for PC indicates
+	 * another instruction form. This distiction only matters for test
+	 * case coverage checks.
+	 */
+	REG_TYPE_NOPCX,	   /* Register must not be PC */
+	REG_TYPE_NOSPPCX,  /* Register must not be SP or PC */
+
+	/* Alias to allow '0' arg to be used in REGS macro. */
+	REG_TYPE_0 = REG_TYPE_NONE
+};
+
+#define REGS(r16, r12, r8, r4, r0)	\
+	(((REG_TYPE_##r16) << 16) +	\
+	((REG_TYPE_##r12) << 12) +	\
+	((REG_TYPE_##r8) << 8) +	\
+	((REG_TYPE_##r4) << 4) +	\
+	(REG_TYPE_##r0))
+
+union decode_item {
+	u32			bits;
+	const union decode_item	*table;
+	int			action;
+};
+
+struct decode_header;
+typedef enum probes_insn (probes_custom_decode_t)(probes_opcode_t,
+						  struct arch_probes_insn *,
+						  const struct decode_header *);
+
+union decode_action {
+	probes_insn_handler_t	*handler;
+	probes_custom_decode_t	*decoder;
+};
+
+#define DECODE_END			\
+	{.bits = DECODE_TYPE_END}
+
+
+struct decode_header {
+	union decode_item	type_regs;
+	union decode_item	mask;
+	union decode_item	value;
+};
+
+#define DECODE_HEADER(_type, _mask, _value, _regs)		\
+	{.bits = (_type) | ((_regs) << DECODE_TYPE_BITS)},	\
+	{.bits = (_mask)},					\
+	{.bits = (_value)}
+
+
+struct decode_table {
+	struct decode_header	header;
+	union decode_item	table;
+};
+
+#define DECODE_TABLE(_mask, _value, _table)			\
+	DECODE_HEADER(DECODE_TYPE_TABLE, _mask, _value, 0),	\
+	{.table = (_table)}
+
+
+struct decode_custom {
+	struct decode_header	header;
+	union decode_item	decoder;
+};
+
+#define DECODE_CUSTOM(_mask, _value, _decoder)			\
+	DECODE_HEADER(DECODE_TYPE_CUSTOM, _mask, _value, 0),	\
+	{.action = (_decoder)}
+
+
+struct decode_simulate {
+	struct decode_header	header;
+	union decode_item	handler;
+};
+
+#define DECODE_SIMULATEX(_mask, _value, _handler, _regs)		\
+	DECODE_HEADER(DECODE_TYPE_SIMULATE, _mask, _value, _regs),	\
+	{.action = (_handler)}
+
+#define DECODE_SIMULATE(_mask, _value, _handler)	\
+	DECODE_SIMULATEX(_mask, _value, _handler, 0)
+
+
+struct decode_emulate {
+	struct decode_header	header;
+	union decode_item	handler;
+};
+
+#define DECODE_EMULATEX(_mask, _value, _handler, _regs)			\
+	DECODE_HEADER(DECODE_TYPE_EMULATE, _mask, _value, _regs),	\
+	{.action = (_handler)}
+
+#define DECODE_EMULATE(_mask, _value, _handler)		\
+	DECODE_EMULATEX(_mask, _value, _handler, 0)
+
+
+struct decode_or {
+	struct decode_header	header;
+};
+
+#define DECODE_OR(_mask, _value)				\
+	DECODE_HEADER(DECODE_TYPE_OR, _mask, _value, 0)
+
+enum probes_insn {
+	INSN_REJECTED,
+	INSN_GOOD,
+	INSN_GOOD_NO_SLOT
+};
+
+struct decode_reject {
+	struct decode_header	header;
+};
+
+#define DECODE_REJECT(_mask, _value)				\
+	DECODE_HEADER(DECODE_TYPE_REJECT, _mask, _value, 0)
+
+probes_insn_handler_t probes_simulate_nop;
+probes_insn_handler_t probes_emulate_none;
+
+int __kprobes
+probes_decode_insn(probes_opcode_t insn, struct arch_probes_insn *asi,
+		const union decode_item *table, bool thumb, 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-arm.c

@@ -0,0 +1,234 @@
+/*
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/types.h>
+#include <linux/stddef.h>
+#include <linux/wait.h>
+#include <linux/uprobes.h>
+#include <linux/module.h>
+
+#include "probes.h"
+#include "probes-arm.h"
+#include "uprobes.h"
+
+static int uprobes_substitute_pc(unsigned long *pinsn, u32 oregs)
+{
+	probes_opcode_t insn = __mem_to_opcode_arm(*pinsn);
+	probes_opcode_t temp;
+	probes_opcode_t mask;
+	int freereg;
+	u32 free = 0xffff;
+	u32 regs;
+
+	for (regs = oregs; regs; regs >>= 4, insn >>= 4) {
+		if ((regs & 0xf) == REG_TYPE_NONE)
+			continue;
+
+		free &= ~(1 << (insn & 0xf));
+	}
+
+	/* No PC, no problem */
+	if (free & (1 << 15))
+		return 15;
+
+	if (!free)
+		return -1;
+
+	/*
+	 * fls instead of ffs ensures that for "ldrd r0, r1, [pc]" we would
+	 * pick LR instead of R1.
+	 */
+	freereg = free = fls(free) - 1;
+
+	temp = __mem_to_opcode_arm(*pinsn);
+	insn = temp;
+	regs = oregs;
+	mask = 0xf;
+
+	for (; regs; regs >>= 4, mask <<= 4, free <<= 4, temp >>= 4) {
+		if ((regs & 0xf) == REG_TYPE_NONE)
+			continue;
+
+		if ((temp & 0xf) != 15)
+			continue;
+
+		insn &= ~mask;
+		insn |= free & mask;
+	}
+
+	*pinsn = __opcode_to_mem_arm(insn);
+	return freereg;
+}
+
+static void uprobe_set_pc(struct arch_uprobe *auprobe,
+			  struct arch_uprobe_task *autask,
+			  struct pt_regs *regs)
+{
+	u32 pcreg = auprobe->pcreg;
+
+	autask->backup = regs->uregs[pcreg];
+	regs->uregs[pcreg] = regs->ARM_pc + 8;
+}
+
+static void uprobe_unset_pc(struct arch_uprobe *auprobe,
+			    struct arch_uprobe_task *autask,
+			    struct pt_regs *regs)
+{
+	/* PC will be taken care of by common code */
+	regs->uregs[auprobe->pcreg] = autask->backup;
+}
+
+static void uprobe_aluwrite_pc(struct arch_uprobe *auprobe,
+			       struct arch_uprobe_task *autask,
+			       struct pt_regs *regs)
+{
+	u32 pcreg = auprobe->pcreg;
+
+	alu_write_pc(regs->uregs[pcreg], regs);
+	regs->uregs[pcreg] = autask->backup;
+}
+
+static void uprobe_write_pc(struct arch_uprobe *auprobe,
+			    struct arch_uprobe_task *autask,
+			    struct pt_regs *regs)
+{
+	u32 pcreg = auprobe->pcreg;
+
+	load_write_pc(regs->uregs[pcreg], regs);
+	regs->uregs[pcreg] = autask->backup;
+}
+
+enum probes_insn
+decode_pc_ro(probes_opcode_t insn, struct arch_probes_insn *asi,
+	     const struct decode_header *d)
+{
+	struct arch_uprobe *auprobe = container_of(asi, struct arch_uprobe,
+						   asi);
+	struct decode_emulate *decode = (struct decode_emulate *) d;
+	u32 regs = decode->header.type_regs.bits >> DECODE_TYPE_BITS;
+	int reg;
+
+	reg = uprobes_substitute_pc(&auprobe->ixol[0], regs);
+	if (reg == 15)
+		return INSN_GOOD;
+
+	if (reg == -1)
+		return INSN_REJECTED;
+
+	auprobe->pcreg = reg;
+	auprobe->prehandler = uprobe_set_pc;
+	auprobe->posthandler = uprobe_unset_pc;
+
+	return INSN_GOOD;
+}
+
+enum probes_insn
+decode_wb_pc(probes_opcode_t insn, struct arch_probes_insn *asi,
+	     const struct decode_header *d, bool alu)
+{
+	struct arch_uprobe *auprobe = container_of(asi, struct arch_uprobe,
+						   asi);
+	enum probes_insn ret = decode_pc_ro(insn, asi, d);
+
+	if (((insn >> 12) & 0xf) == 15)
+		auprobe->posthandler = alu ? uprobe_aluwrite_pc
+					   : uprobe_write_pc;
+
+	return ret;
+}
+
+enum probes_insn
+decode_rd12rn16rm0rs8_rwflags(probes_opcode_t insn,
+			      struct arch_probes_insn *asi,
+			      const struct decode_header *d)
+{
+	return decode_wb_pc(insn, asi, d, true);
+}
+
+enum probes_insn
+decode_ldr(probes_opcode_t insn, struct arch_probes_insn *asi,
+	   const struct decode_header *d)
+{
+	return decode_wb_pc(insn, asi, d, false);
+}
+
+enum probes_insn
+uprobe_decode_ldmstm(probes_opcode_t insn,
+		     struct arch_probes_insn *asi,
+		     const struct decode_header *d)
+{
+	struct arch_uprobe *auprobe = container_of(asi, struct arch_uprobe,
+						   asi);
+	unsigned reglist = insn & 0xffff;
+	int rn = (insn >> 16) & 0xf;
+	int lbit = insn & (1 << 20);
+	unsigned used = reglist | (1 << rn);
+
+	if (rn == 15)
+		return INSN_REJECTED;
+
+	if (!(used & (1 << 15)))
+		return INSN_GOOD;
+
+	if (used & (1 << 14))
+		return INSN_REJECTED;
+
+	/* Use LR instead of PC */
+	insn ^= 0xc000;
+
+	auprobe->pcreg = 14;
+	auprobe->ixol[0] = __opcode_to_mem_arm(insn);
+
+	auprobe->prehandler = uprobe_set_pc;
+	if (lbit)
+		auprobe->posthandler = uprobe_write_pc;
+	else
+		auprobe->posthandler = uprobe_unset_pc;
+
+	return INSN_GOOD;
+}
+
+const union decode_action uprobes_probes_actions[] = {
+	[PROBES_EMULATE_NONE] = {.handler = probes_simulate_nop},
+	[PROBES_SIMULATE_NOP] = {.handler = probes_simulate_nop},
+	[PROBES_PRELOAD_IMM] = {.handler = probes_simulate_nop},
+	[PROBES_PRELOAD_REG] = {.handler = probes_simulate_nop},
+	[PROBES_BRANCH_IMM] = {.handler = simulate_blx1},
+	[PROBES_MRS] = {.handler = simulate_mrs},
+	[PROBES_BRANCH_REG] = {.handler = simulate_blx2bx},
+	[PROBES_CLZ] = {.handler = probes_simulate_nop},
+	[PROBES_SATURATING_ARITHMETIC] = {.handler = probes_simulate_nop},
+	[PROBES_MUL1] = {.handler = probes_simulate_nop},
+	[PROBES_MUL2] = {.handler = probes_simulate_nop},
+	[PROBES_SWP] = {.handler = probes_simulate_nop},
+	[PROBES_LDRSTRD] = {.decoder = decode_pc_ro},
+	[PROBES_LOAD_EXTRA] = {.decoder = decode_pc_ro},
+	[PROBES_LOAD] = {.decoder = decode_ldr},
+	[PROBES_STORE_EXTRA] = {.decoder = decode_pc_ro},
+	[PROBES_STORE] = {.decoder = decode_pc_ro},
+	[PROBES_MOV_IP_SP] = {.handler = simulate_mov_ipsp},
+	[PROBES_DATA_PROCESSING_REG] = {
+		.decoder = decode_rd12rn16rm0rs8_rwflags},
+	[PROBES_DATA_PROCESSING_IMM] = {
+		.decoder = decode_rd12rn16rm0rs8_rwflags},
+	[PROBES_MOV_HALFWORD] = {.handler = probes_simulate_nop},
+	[PROBES_SEV] = {.handler = probes_simulate_nop},
+	[PROBES_WFE] = {.handler = probes_simulate_nop},
+	[PROBES_SATURATE] = {.handler = probes_simulate_nop},
+	[PROBES_REV] = {.handler = probes_simulate_nop},
+	[PROBES_MMI] = {.handler = probes_simulate_nop},
+	[PROBES_PACK] = {.handler = probes_simulate_nop},
+	[PROBES_EXTEND] = {.handler = probes_simulate_nop},
+	[PROBES_EXTEND_ADD] = {.handler = probes_simulate_nop},
+	[PROBES_MUL_ADD_LONG] = {.handler = probes_simulate_nop},
+	[PROBES_MUL_ADD] = {.handler = probes_simulate_nop},
+	[PROBES_BITFIELD] = {.handler = probes_simulate_nop},
+	[PROBES_BRANCH] = {.handler = simulate_bbl},
+	[PROBES_LDMSTM] = {.decoder = uprobe_decode_ldmstm}
+};

arch/arm/kernel/uprobes.c

@@ -0,0 +1,210 @@
+/*
+ * 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.
+ */
+
+#include <linux/kernel.h>
+#include <linux/stddef.h>
+#include <linux/errno.h>
+#include <linux/highmem.h>
+#include <linux/sched.h>
+#include <linux/uprobes.h>
+#include <linux/notifier.h>
+
+#include <asm/opcodes.h>
+#include <asm/traps.h>
+
+#include "probes.h"
+#include "probes-arm.h"
+#include "uprobes.h"
+
+#define UPROBE_TRAP_NR	UINT_MAX
+
+bool is_swbp_insn(uprobe_opcode_t *insn)
+{
+	return (__mem_to_opcode_arm(*insn) & 0x0fffffff) ==
+		(UPROBE_SWBP_ARM_INSN & 0x0fffffff);
+}
+
+int set_swbp(struct arch_uprobe *auprobe, struct mm_struct *mm,
+	     unsigned long vaddr)
+{
+	return uprobe_write_opcode(mm, vaddr,
+		   __opcode_to_mem_arm(auprobe->bpinsn));
+}
+
+bool arch_uprobe_ignore(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	if (!auprobe->asi.insn_check_cc(regs->ARM_cpsr)) {
+		regs->ARM_pc += 4;
+		return true;
+	}
+
+	return false;
+}
+
+bool arch_uprobe_skip_sstep(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	probes_opcode_t opcode;
+
+	if (!auprobe->simulate)
+		return false;
+
+	opcode = __mem_to_opcode_arm(*(unsigned int *) auprobe->insn);
+
+	auprobe->asi.insn_singlestep(opcode, &auprobe->asi, regs);
+
+	return true;
+}
+
+unsigned long
+arch_uretprobe_hijack_return_addr(unsigned long trampoline_vaddr,
+				  struct pt_regs *regs)
+{
+	unsigned long orig_ret_vaddr;
+
+	orig_ret_vaddr = regs->ARM_lr;
+	/* Replace the return addr with trampoline addr */
+	regs->ARM_lr = trampoline_vaddr;
+	return orig_ret_vaddr;
+}
+
+int arch_uprobe_analyze_insn(struct arch_uprobe *auprobe, struct mm_struct *mm,
+			     unsigned long addr)
+{
+	unsigned int insn;
+	unsigned int bpinsn;
+	enum probes_insn ret;
+
+	/* Thumb not yet support */
+	if (addr & 0x3)
+		return -EINVAL;
+
+	insn = __mem_to_opcode_arm(*(unsigned int *)auprobe->insn);
+	auprobe->ixol[0] = __opcode_to_mem_arm(insn);
+	auprobe->ixol[1] = __opcode_to_mem_arm(UPROBE_SS_ARM_INSN);
+
+	ret = arm_probes_decode_insn(insn, &auprobe->asi, false,
+				     uprobes_probes_actions);
+	switch (ret) {
+	case INSN_REJECTED:
+		return -EINVAL;
+
+	case INSN_GOOD_NO_SLOT:
+		auprobe->simulate = true;
+		break;
+
+	case INSN_GOOD:
+	default:
+		break;
+	}
+
+	bpinsn = UPROBE_SWBP_ARM_INSN & 0x0fffffff;
+	if (insn >= 0xe0000000)
+		bpinsn |= 0xe0000000;  /* Unconditional instruction */
+	else
+		bpinsn |= insn & 0xf0000000;  /* Copy condition from insn */
+
+	auprobe->bpinsn = bpinsn;
+
+	return 0;
+}
+
+int arch_uprobe_pre_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	if (auprobe->prehandler)
+		auprobe->prehandler(auprobe, &utask->autask, regs);
+
+	utask->autask.saved_trap_no = current->thread.trap_no;
+	current->thread.trap_no = UPROBE_TRAP_NR;
+	regs->ARM_pc = utask->xol_vaddr;
+
+	return 0;
+}
+
+int arch_uprobe_post_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	WARN_ON_ONCE(current->thread.trap_no != UPROBE_TRAP_NR);
+
+	current->thread.trap_no = utask->autask.saved_trap_no;
+	regs->ARM_pc = utask->vaddr + 4;
+
+	if (auprobe->posthandler)
+		auprobe->posthandler(auprobe, &utask->autask, regs);
+
+	return 0;
+}
+
+bool arch_uprobe_xol_was_trapped(struct task_struct *t)
+{
+	if (t->thread.trap_no != UPROBE_TRAP_NR)
+		return true;
+
+	return false;
+}
+
+void arch_uprobe_abort_xol(struct arch_uprobe *auprobe, struct pt_regs *regs)
+{
+	struct uprobe_task *utask = current->utask;
+
+	current->thread.trap_no = utask->autask.saved_trap_no;
+	instruction_pointer_set(regs, utask->vaddr);
+}
+
+int arch_uprobe_exception_notify(struct notifier_block *self,
+				 unsigned long val, void *data)
+{
+	return NOTIFY_DONE;
+}
+
+static int uprobe_trap_handler(struct pt_regs *regs, unsigned int instr)
+{
+	unsigned long flags;
+
+	local_irq_save(flags);
+	instr &= 0x0fffffff;
+	if (instr == (UPROBE_SWBP_ARM_INSN & 0x0fffffff))
+		uprobe_pre_sstep_notifier(regs);
+	else if (instr == (UPROBE_SS_ARM_INSN & 0x0fffffff))
+		uprobe_post_sstep_notifier(regs);
+	local_irq_restore(flags);
+
+	return 0;
+}
+
+unsigned long uprobe_get_swbp_addr(struct pt_regs *regs)
+{
+	return instruction_pointer(regs);
+}
+
+static struct undef_hook uprobes_arm_break_hook = {
+	.instr_mask	= 0x0fffffff,
+	.instr_val	= (UPROBE_SWBP_ARM_INSN & 0x0fffffff),
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= USR_MODE,
+	.fn		= uprobe_trap_handler,
+};
+
+static struct undef_hook uprobes_arm_ss_hook = {
+	.instr_mask	= 0x0fffffff,
+	.instr_val	= (UPROBE_SS_ARM_INSN & 0x0fffffff),
+	.cpsr_mask	= MODE_MASK,
+	.cpsr_val	= USR_MODE,
+	.fn		= uprobe_trap_handler,
+};
+
+static int arch_uprobes_init(void)
+{
+	register_undef_hook(&uprobes_arm_break_hook);
+	register_undef_hook(&uprobes_arm_ss_hook);
+
+	return 0;
+}
+device_initcall(arch_uprobes_init);

arch/arm/kernel/uprobes.h

@@ -0,0 +1,35 @@
+/*
+ * 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/lib/csumpartialcopygeneric.S

@@ -141,7 +141,7 @@ FN_ENTRY
 		tst	len, #2
 		mov	r5, r4, get_byte_0
 		beq	.Lexit
-		adcs	sum, sum, r4, push #16
+		adcs	sum, sum, r4, lspush #16
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_1
 		strb	r5, [dst], #1
@@ -171,23 +171,23 @@ FN_ENTRY
 		cmp	ip, #2
 		beq	.Lsrc2_aligned
 		bhi	.Lsrc3_aligned
-		mov	r4, r5, pull #8		@ C = 0
+		mov	r4, r5, lspull #8		@ C = 0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
-		mov	r7, r7, pull #8
-		orr	r7, r7, r8, push #24
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
+		mov	r7, r7, lspull #8
+		orr	r7, r7, r8, lspush #24
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #8
+		mov	r4, r8, lspull #8
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -196,50 +196,50 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #8
+		mov	r4, r6, lspull #8
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #24
+		orr	r4, r4, r5, lspush #24
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #8
+		mov	r4, r5, lspull #8
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
 		tst	len, #2
 		beq	.Lexit
-		adcs	sum, sum, r4, push #16
+		adcs	sum, sum, r4, lspush #16
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_1
 		strb	r5, [dst], #1
 		mov	r5, r4, get_byte_2
 		b	.Lexit
 
-.Lsrc2_aligned:	mov	r4, r5, pull #16
+.Lsrc2_aligned:	mov	r4, r5, lspull #16
 		adds	sum, sum, #0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
-		mov	r7, r7, pull #16
-		orr	r7, r7, r8, push #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
+		mov	r7, r7, lspull #16
+		orr	r7, r7, r8, lspush #16
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #16
+		mov	r4, r8, lspull #16
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -248,20 +248,20 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #16
+		mov	r4, r6, lspull #16
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #16
+		orr	r4, r4, r5, lspush #16
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #16
+		mov	r4, r5, lspull #16
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
@@ -276,24 +276,24 @@ FN_ENTRY
 		load1b	r5
 		b	.Lexit
 
-.Lsrc3_aligned:	mov	r4, r5, pull #24
+.Lsrc3_aligned:	mov	r4, r5, lspull #24
 		adds	sum, sum, #0
 		bics	ip, len, #15
 		beq	2f
 1:		load4l	r5, r6, r7, r8
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
-		mov	r7, r7, pull #24
-		orr	r7, r7, r8, push #8
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
+		mov	r7, r7, lspull #24
+		orr	r7, r7, r8, lspush #8
 		stmia	dst!, {r4, r5, r6, r7}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
 		adcs	sum, sum, r6
 		adcs	sum, sum, r7
-		mov	r4, r8, pull #24
+		mov	r4, r8, lspull #24
 		sub	ip, ip, #16
 		teq	ip, #0
 		bne	1b
@@ -302,20 +302,20 @@ FN_ENTRY
 		tst	ip, #8
 		beq	3f
 		load2l	r5, r6
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
 		stmia	dst!, {r4, r5}
 		adcs	sum, sum, r4
 		adcs	sum, sum, r5
-		mov	r4, r6, pull #24
+		mov	r4, r6, lspull #24
 		tst	ip, #4
 		beq	4f
 3:		load1l	r5
-		orr	r4, r4, r5, push #8
+		orr	r4, r4, r5, lspush #8
 		str	r4, [dst], #4
 		adcs	sum, sum, r4
-		mov	r4, r5, pull #24
+		mov	r4, r5, lspull #24
 4:		ands	len, len, #3
 		beq	.Ldone
 		mov	r5, r4, get_byte_0
@@ -326,7 +326,7 @@ FN_ENTRY
 		load1l	r4
 		mov	r5, r4, get_byte_0
 		strb	r5, [dst], #1
-		adcs	sum, sum, r4, push #24
+		adcs	sum, sum, r4, lspush #24
 		mov	r5, r4, get_byte_1
 		b	.Lexit
 FN_EXIT

arch/arm/lib/io-readsl.S

@@ -47,25 +47,25 @@ ENTRY(__raw_readsl)
 		strb	ip, [r1], #1
 
 4:		subs	r2, r2, #1
-		mov	ip, r3, pull #24
+		mov	ip, r3, lspull #24
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #8
+		orrne	ip, ip, r3, lspush #8
 		strne	ip, [r1], #4
 		bne	4b
 		b	8f
 
 5:		subs	r2, r2, #1
-		mov	ip, r3, pull #16
+		mov	ip, r3, lspull #16
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #16
+		orrne	ip, ip, r3, lspush #16
 		strne	ip, [r1], #4
 		bne	5b
 		b	7f
 
 6:		subs	r2, r2, #1
-		mov	ip, r3, pull #8
+		mov	ip, r3, lspull #8
 		ldrne	r3, [r0]
-		orrne	ip, ip, r3, push #24
+		orrne	ip, ip, r3, lspush #24
 		strne	ip, [r1], #4
 		bne	6b
 

arch/arm/lib/io-writesl.S

@@ -41,26 +41,26 @@ ENTRY(__raw_writesl)
 		blt	5f
 		bgt	6f
 
-4:		mov	ip, r3, pull #16
+4:		mov	ip, r3, lspull #16
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #16
+		orr	ip, ip, r3, lspush #16
 		str	ip, [r0]
 		bne	4b
 		mov	pc, lr
 
-5:		mov	ip, r3, pull #8
+5:		mov	ip, r3, lspull #8
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #24
+		orr	ip, ip, r3, lspush #24
 		str	ip, [r0]
 		bne	5b
 		mov	pc, lr
 
-6:		mov	ip, r3, pull #24
+6:		mov	ip, r3, lspull #24
 		ldr	r3, [r1], #4
 		subs	r2, r2, #1
-		orr	ip, ip, r3, push #8
+		orr	ip, ip, r3, lspush #8
 		str	ip, [r0]
 		bne	6b
 		mov	pc, lr

arch/arm/lib/memmove.S

@@ -147,24 +147,24 @@ ENTRY(memmove)
 
 12:	PLD(	pld	[r1, #-128]		)
 13:		ldmdb   r1!, {r7, r8, r9, ip}
-		mov     lr, r3, push #\push
+		mov     lr, r3, lspush #\push
 		subs    r2, r2, #32
 		ldmdb   r1!, {r3, r4, r5, r6}
-		orr     lr, lr, ip, pull #\pull
-		mov     ip, ip, push #\push
-		orr     ip, ip, r9, pull #\pull
-		mov     r9, r9, push #\push
-		orr     r9, r9, r8, pull #\pull
-		mov     r8, r8, push #\push
-		orr     r8, r8, r7, pull #\pull
-		mov     r7, r7, push #\push
-		orr     r7, r7, r6, pull #\pull
-		mov     r6, r6, push #\push
-		orr     r6, r6, r5, pull #\pull
-		mov     r5, r5, push #\push
-		orr     r5, r5, r4, pull #\pull
-		mov     r4, r4, push #\push
-		orr     r4, r4, r3, pull #\pull
+		orr     lr, lr, ip, lspull #\pull
+		mov     ip, ip, lspush #\push
+		orr     ip, ip, r9, lspull #\pull
+		mov     r9, r9, lspush #\push
+		orr     r9, r9, r8, lspull #\pull
+		mov     r8, r8, lspush #\push
+		orr     r8, r8, r7, lspull #\pull
+		mov     r7, r7, lspush #\push
+		orr     r7, r7, r6, lspull #\pull
+		mov     r6, r6, lspush #\push
+		orr     r6, r6, r5, lspull #\pull
+		mov     r5, r5, lspush #\push
+		orr     r5, r5, r4, lspull #\pull
+		mov     r4, r4, lspush #\push
+		orr     r4, r4, r3, lspull #\pull
 		stmdb   r0!, {r4 - r9, ip, lr}
 		bge	12b
 	PLD(	cmn	r2, #96			)
@@ -175,10 +175,10 @@ ENTRY(memmove)
 14:		ands	ip, r2, #28
 		beq	16f
 
-15:		mov     lr, r3, push #\push
+15:		mov     lr, r3, lspush #\push
 		ldr	r3, [r1, #-4]!
 		subs	ip, ip, #4
-		orr	lr, lr, r3, pull #\pull
+		orr	lr, lr, r3, lspull #\pull
 		str	lr, [r0, #-4]!
 		bgt	15b
 	CALGN(	cmp	r2, #0			)

arch/arm/lib/uaccess.S

@@ -117,9 +117,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_1fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_1nowords
-		mov	r3, r7, pull #8
+		mov	r3, r7, lspull #8
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #24
+		orr	r3, r3, r7, lspush #24
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -131,30 +131,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_1rem8lp
 
-.Lc2u_1cpy8lp:	mov	r3, r7, pull #8
+.Lc2u_1cpy8lp:	mov	r3, r7, lspull #8
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #24
-		mov	r4, r4, pull #8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
+		orr	r3, r3, r4, lspush #24
+		mov	r4, r4, lspull #8
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_1cpy8lp
 
 .Lc2u_1rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #24
-		movne	r4, r4, pull #8
-		orrne	r4, r4, r7, push #24
+		orrne	r3, r3, r4, lspush #24
+		movne	r4, r4, lspull #8
+		orrne	r4, r4, r7, lspush #24
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #24
+		orrne	r3, r3, r7, lspush #24
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_1fupi
@@ -172,9 +172,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_2fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_2nowords
-		mov	r3, r7, pull #16
+		mov	r3, r7, lspull #16
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #16
+		orr	r3, r3, r7, lspush #16
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -186,30 +186,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_2rem8lp
 
-.Lc2u_2cpy8lp:	mov	r3, r7, pull #16
+.Lc2u_2cpy8lp:	mov	r3, r7, lspull #16
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #16
-		mov	r4, r4, pull #16
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
+		orr	r3, r3, r4, lspush #16
+		mov	r4, r4, lspull #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_2cpy8lp
 
 .Lc2u_2rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #16
-		movne	r4, r4, pull #16
-		orrne	r4, r4, r7, push #16
+		orrne	r3, r3, r4, lspush #16
+		movne	r4, r4, lspull #16
+		orrne	r4, r4, r7, lspush #16
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #16
+		orrne	r3, r3, r7, lspush #16
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_2fupi
@@ -227,9 +227,9 @@ USER(	TUSER(	strgtb) r3, [r0], #1)			@ May fault
 .Lc2u_3fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lc2u_3nowords
-		mov	r3, r7, pull #24
+		mov	r3, r7, lspull #24
 		ldr	r7, [r1], #4
-		orr	r3, r3, r7, push #8
+		orr	r3, r3, r7, lspush #8
 USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		mov	ip, r0, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -241,30 +241,30 @@ USER(	TUSER(	str)	r3, [r0], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lc2u_3rem8lp
 
-.Lc2u_3cpy8lp:	mov	r3, r7, pull #24
+.Lc2u_3cpy8lp:	mov	r3, r7, lspull #24
 		ldmia	r1!, {r4 - r7}
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #8
-		mov	r4, r4, pull #24
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
+		orr	r3, r3, r4, lspush #8
+		mov	r4, r4, lspull #24
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
 		stmia	r0!, {r3 - r6}			@ Shouldnt fault
 		bpl	.Lc2u_3cpy8lp
 
 .Lc2u_3rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldmneia	r1!, {r4, r7}
-		orrne	r3, r3, r4, push #8
-		movne	r4, r4, pull #24
-		orrne	r4, r4, r7, push #8
+		orrne	r3, r3, r4, lspush #8
+		movne	r4, r4, lspull #24
+		orrne	r4, r4, r7, lspush #8
 		stmneia	r0!, {r3 - r4}			@ Shouldnt fault
 		tst	ip, #4
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldrne	r7, [r1], #4
-		orrne	r3, r3, r7, push #8
+		orrne	r3, r3, r7, lspush #8
 	TUSER(	strne) r3, [r0], #4			@ Shouldnt fault
 		ands	ip, ip, #3
 		beq	.Lc2u_3fupi
@@ -382,9 +382,9 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 .Lcfu_1fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_1nowords
-		mov	r3, r7, pull #8
+		mov	r3, r7, lspull #8
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #24
+		orr	r3, r3, r7, lspush #24
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -396,30 +396,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lcfu_1rem8lp
 
-.Lcfu_1cpy8lp:	mov	r3, r7, pull #8
+.Lcfu_1cpy8lp:	mov	r3, r7, lspull #8
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #24
-		mov	r4, r4, pull #8
-		orr	r4, r4, r5, push #24
-		mov	r5, r5, pull #8
-		orr	r5, r5, r6, push #24
-		mov	r6, r6, pull #8
-		orr	r6, r6, r7, push #24
+		orr	r3, r3, r4, lspush #24
+		mov	r4, r4, lspull #8
+		orr	r4, r4, r5, lspush #24
+		mov	r5, r5, lspull #8
+		orr	r5, r5, r6, lspush #24
+		mov	r6, r6, lspull #8
+		orr	r6, r6, r7, lspush #24
 		stmia	r0!, {r3 - r6}
 		bpl	.Lcfu_1cpy8lp
 
 .Lcfu_1rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #24
-		movne	r4, r4, pull #8
-		orrne	r4, r4, r7, push #24
+		orrne	r3, r3, r4, lspush #24
+		movne	r4, r4, lspull #8
+		orrne	r4, r4, r7, lspush #24
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #8
+		movne	r3, r7, lspull #8
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #24
+		orrne	r3, r3, r7, lspush #24
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_1fupi
@@ -437,9 +437,9 @@ USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
 .Lcfu_2fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_2nowords
-		mov	r3, r7, pull #16
+		mov	r3, r7, lspull #16
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #16
+		orr	r3, r3, r7, lspush #16
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -452,30 +452,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		blt	.Lcfu_2rem8lp
 
 
-.Lcfu_2cpy8lp:	mov	r3, r7, pull #16
+.Lcfu_2cpy8lp:	mov	r3, r7, lspull #16
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
 		subs	ip, ip, #16
-		orr	r3, r3, r4, push #16
-		mov	r4, r4, pull #16
-		orr	r4, r4, r5, push #16
-		mov	r5, r5, pull #16
-		orr	r5, r5, r6, push #16
-		mov	r6, r6, pull #16
-		orr	r6, r6, r7, push #16
+		orr	r3, r3, r4, lspush #16
+		mov	r4, r4, lspull #16
+		orr	r4, r4, r5, lspush #16
+		mov	r5, r5, lspull #16
+		orr	r5, r5, r6, lspush #16
+		mov	r6, r6, lspull #16
+		orr	r6, r6, r7, lspush #16
 		stmia	r0!, {r3 - r6}
 		bpl	.Lcfu_2cpy8lp
 
 .Lcfu_2rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #16
-		movne	r4, r4, pull #16
-		orrne	r4, r4, r7, push #16
+		orrne	r3, r3, r4, lspush #16
+		movne	r4, r4, lspull #16
+		orrne	r4, r4, r7, lspush #16
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #16
+		movne	r3, r7, lspull #16
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #16
+		orrne	r3, r3, r7, lspush #16
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_2fupi
@@ -493,9 +493,9 @@ USER(	TUSER(	ldrgtb) r3, [r1], #0)			@ May fault
 .Lcfu_3fupi:	subs	r2, r2, #4
 		addmi	ip, r2, #4
 		bmi	.Lcfu_3nowords
-		mov	r3, r7, pull #24
+		mov	r3, r7, lspull #24
 USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
-		orr	r3, r3, r7, push #8
+		orr	r3, r3, r7, lspush #8
 		str	r3, [r0], #4
 		mov	ip, r1, lsl #32 - PAGE_SHIFT
 		rsb	ip, ip, #0
@@ -507,30 +507,30 @@ USER(	TUSER(	ldr)	r7, [r1], #4)			@ May fault
 		subs	ip, ip, #16
 		blt	.Lcfu_3rem8lp
 
-.Lcfu_3cpy8lp:	mov	r3, r7, pull #24
+.Lcfu_3cpy8lp:	mov	r3, r7, lspull #24
 		ldmia	r1!, {r4 - r7}			@ Shouldnt fault
-		orr	r3, r3, r4, push #8
-		mov	r4, r4, pull #24
-		orr	r4, r4, r5, push #8
-		mov	r5, r5, pull #24
-		orr	r5, r5, r6, push #8
-		mov	r6, r6, pull #24
-		orr	r6, r6, r7, push #8
+		orr	r3, r3, r4, lspush #8
+		mov	r4, r4, lspull #24
+		orr	r4, r4, r5, lspush #8
+		mov	r5, r5, lspull #24
+		orr	r5, r5, r6, lspush #8
+		mov	r6, r6, lspull #24
+		orr	r6, r6, r7, lspush #8
 		stmia	r0!, {r3 - r6}
 		subs	ip, ip, #16
 		bpl	.Lcfu_3cpy8lp
 
 .Lcfu_3rem8lp:	tst	ip, #8
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 		ldmneia	r1!, {r4, r7}			@ Shouldnt fault
-		orrne	r3, r3, r4, push #8
-		movne	r4, r4, pull #24
-		orrne	r4, r4, r7, push #8
+		orrne	r3, r3, r4, lspush #8
+		movne	r4, r4, lspull #24
+		orrne	r4, r4, r7, lspush #8
 		stmneia	r0!, {r3 - r4}
 		tst	ip, #4
-		movne	r3, r7, pull #24
+		movne	r3, r7, lspull #24
 USER(	TUSER(	ldrne) r7, [r1], #4)			@ May fault
-		orrne	r3, r3, r7, push #8
+		orrne	r3, r3, r7, lspush #8
 		strne	r3, [r0], #4
 		ands	ip, ip, #3
 		beq	.Lcfu_3fupi

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,
 };
 

arch/arm/mach-ebsa110/core.c

@@ -206,7 +206,7 @@ ebsa110_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction ebsa110_timer_irq = {
 	.name		= "EBSA110 Timer Tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= ebsa110_timer_interrupt,
 };
 

arch/arm/mach-footbridge/dc21285-timer.c

@@ -105,7 +105,7 @@ static irqreturn_t timer1_interrupt(int irq, void *dev_id)
 static struct irqaction footbridge_timer_irq = {
 	.name		= "dc21285_timer1",
 	.handler	= timer1_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.dev_id		= &ckevt_dc21285,
 };
 
@@ -125,7 +125,7 @@ void __init footbridge_timer_init(void)
 	clockevents_config_and_register(ce, rate, 0x4, 0xffffff);
 }
 
-static u32 notrace footbridge_read_sched_clock(void)
+static u64 notrace footbridge_read_sched_clock(void)
 {
 	return ~*CSR_TIMER3_VALUE;
 }
@@ -138,5 +138,5 @@ void __init footbridge_sched_clock(void)
 	*CSR_TIMER3_CLR = 0;
 	*CSR_TIMER3_CNTL = TIMER_CNTL_ENABLE | TIMER_CNTL_DIV16;
 
-	setup_sched_clock(footbridge_read_sched_clock, 24, rate);
+	sched_clock_register(footbridge_read_sched_clock, 24, rate);
 }

arch/arm/mach-footbridge/dc21285.c

@@ -334,15 +334,15 @@ void __init dc21285_preinit(void)
 	/*
 	 * We don't care if these fail.
 	 */
-	dc21285_request_irq(IRQ_PCI_SERR, dc21285_serr_irq, IRQF_DISABLED,
+	dc21285_request_irq(IRQ_PCI_SERR, dc21285_serr_irq, 0,
 			    "PCI system error", &serr_timer);
-	dc21285_request_irq(IRQ_PCI_PERR, dc21285_parity_irq, IRQF_DISABLED,
+	dc21285_request_irq(IRQ_PCI_PERR, dc21285_parity_irq, 0,
 			    "PCI parity error", &perr_timer);
-	dc21285_request_irq(IRQ_PCI_ABORT, dc21285_abort_irq, IRQF_DISABLED,
+	dc21285_request_irq(IRQ_PCI_ABORT, dc21285_abort_irq, 0,
 			    "PCI abort", NULL);
-	dc21285_request_irq(IRQ_DISCARD_TIMER, dc21285_discard_irq, IRQF_DISABLED,
+	dc21285_request_irq(IRQ_DISCARD_TIMER, dc21285_discard_irq, 0,
 			    "Discard timer", NULL);
-	dc21285_request_irq(IRQ_PCI_DPERR, dc21285_dparity_irq, IRQF_DISABLED,
+	dc21285_request_irq(IRQ_PCI_DPERR, dc21285_dparity_irq, 0,
 			    "PCI data parity", NULL);
 
 	if (cfn_mode) {

arch/arm/mach-footbridge/isa-timer.c

@@ -27,7 +27,7 @@ static irqreturn_t pit_timer_interrupt(int irq, void *dev_id)
 static struct irqaction pit_timer_irq = {
 	.name		= "pit",
 	.handler	= pit_timer_interrupt,
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.dev_id		= &i8253_clockevent,
 };
 

arch/arm/mach-gemini/idle.c

@@ -3,7 +3,7 @@
  */
 
 #include <linux/init.h>
-#include <asm/system.h>
+#include <asm/system_misc.h>
 #include <asm/proc-fns.h>
 
 static void gemini_idle(void)

arch/arm/mach-integrator/integrator_ap.c

@@ -358,7 +358,7 @@ static struct clock_event_device integrator_clockevent = {
 
 static struct irqaction integrator_timer_irq = {
 	.name		= "timer",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= integrator_timer_interrupt,
 	.dev_id		= &integrator_clockevent,
 };

arch/arm/mach-ixp4xx/common.c

@@ -312,7 +312,7 @@ static irqreturn_t ixp4xx_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction ixp4xx_timer_irq = {
 	.name		= "timer1",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= ixp4xx_timer_interrupt,
 	.dev_id		= &clockevent_ixp4xx,
 };

arch/arm/mach-ixp4xx/dsmg600-setup.c

@@ -233,8 +233,7 @@ static int __init dsmg600_gpio_init(void)
 
 	gpio_request(DSMG600_RB_GPIO, "reset button");
 	if (request_irq(gpio_to_irq(DSMG600_RB_GPIO), &dsmg600_reset_handler,
-		IRQF_DISABLED | IRQF_TRIGGER_LOW,
-		"DSM-G600 reset button", NULL) < 0) {
+		IRQF_TRIGGER_LOW, "DSM-G600 reset button", NULL) < 0) {
 
 		printk(KERN_DEBUG "Reset Button IRQ %d not available\n",
 			gpio_to_irq(DSMG600_RB_GPIO));

arch/arm/mach-ixp4xx/fsg-setup.c

@@ -208,16 +208,14 @@ static void __init fsg_init(void)
 	platform_add_devices(fsg_devices, ARRAY_SIZE(fsg_devices));
 
 	if (request_irq(gpio_to_irq(FSG_RB_GPIO), &fsg_reset_handler,
-			IRQF_DISABLED | IRQF_TRIGGER_LOW,
-			"FSG reset button", NULL) < 0) {
+			IRQF_TRIGGER_LOW, "FSG reset button", NULL) < 0) {
 
 		printk(KERN_DEBUG "Reset Button IRQ %d not available\n",
 			gpio_to_irq(FSG_RB_GPIO));
 	}
 
 	if (request_irq(gpio_to_irq(FSG_SB_GPIO), &fsg_power_handler,
-			IRQF_DISABLED | IRQF_TRIGGER_LOW,
-			"FSG power button", NULL) < 0) {
+			IRQF_TRIGGER_LOW, "FSG power button", NULL) < 0) {
 
 		printk(KERN_DEBUG "Power Button IRQ %d not available\n",
 			gpio_to_irq(FSG_SB_GPIO));

arch/arm/mach-ixp4xx/nas100d-setup.c

@@ -295,8 +295,7 @@ static void __init nas100d_init(void)
 	pm_power_off = nas100d_power_off;
 
 	if (request_irq(gpio_to_irq(NAS100D_RB_GPIO), &nas100d_reset_handler,
-		IRQF_DISABLED | IRQF_TRIGGER_LOW,
-		"NAS100D reset button", NULL) < 0) {
+		IRQF_TRIGGER_LOW, "NAS100D reset button", NULL) < 0) {
 
 		printk(KERN_DEBUG "Reset Button IRQ %d not available\n",
 			gpio_to_irq(NAS100D_RB_GPIO));

arch/arm/mach-ixp4xx/nslu2-setup.c

@@ -265,16 +265,14 @@ static void __init nslu2_init(void)
 	pm_power_off = nslu2_power_off;
 
 	if (request_irq(gpio_to_irq(NSLU2_RB_GPIO), &nslu2_reset_handler,
-		IRQF_DISABLED | IRQF_TRIGGER_LOW,
-		"NSLU2 reset button", NULL) < 0) {
+		IRQF_TRIGGER_LOW, "NSLU2 reset button", NULL) < 0) {
 
 		printk(KERN_DEBUG "Reset Button IRQ %d not available\n",
 			gpio_to_irq(NSLU2_RB_GPIO));
 	}
 
 	if (request_irq(gpio_to_irq(NSLU2_PB_GPIO), &nslu2_power_handler,
-		IRQF_DISABLED | IRQF_TRIGGER_HIGH,
-		"NSLU2 power button", NULL) < 0) {
+		IRQF_TRIGGER_HIGH, "NSLU2 power button", NULL) < 0) {
 
 		printk(KERN_DEBUG "Power Button IRQ %d not available\n",
 			gpio_to_irq(NSLU2_PB_GPIO));

arch/arm/mach-ks8695/time.c

@@ -122,7 +122,7 @@ static irqreturn_t ks8695_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction ks8695_timer_irq = {
 	.name		= "ks8695_tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER,
+	.flags		= IRQF_TIMER,
 	.handler	= ks8695_timer_interrupt,
 };
 

arch/arm/mach-lpc32xx/timer.c

@@ -90,7 +90,7 @@ static irqreturn_t lpc32xx_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction lpc32xx_timer_irq = {
 	.name		= "LPC32XX Timer Tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= lpc32xx_timer_interrupt,
 };
 

arch/arm/mach-mmp/time.c

@@ -186,7 +186,7 @@ static void __init timer_config(void)
 
 static struct irqaction timer_irq = {
 	.name		= "timer",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= timer_interrupt,
 	.dev_id		= &ckevt,
 };

arch/arm/mach-netx/time.c

@@ -99,7 +99,7 @@ netx_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction netx_timer_irq = {
 	.name		= "NetX Timer Tick",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= netx_timer_interrupt,
 };
 

arch/arm/mach-omap1/dma.c

@@ -32,55 +32,51 @@
 
 #define OMAP1_DMA_BASE			(0xfffed800)
 #define OMAP1_LOGICAL_DMA_CH_COUNT	17
-#define OMAP1_DMA_STRIDE		0x40
 
-static u32 errata;
 static u32 enable_1510_mode;
-static u8 dma_stride;
-static enum omap_reg_offsets dma_common_ch_start, dma_common_ch_end;
-
-static u16 reg_map[] = {
-	[GCR]		= 0x400,
-	[GSCR]		= 0x404,
-	[GRST1]		= 0x408,
-	[HW_ID]		= 0x442,
-	[PCH2_ID]	= 0x444,
-	[PCH0_ID]	= 0x446,
-	[PCH1_ID]	= 0x448,
-	[PCHG_ID]	= 0x44a,
-	[PCHD_ID]	= 0x44c,
-	[CAPS_0]	= 0x44e,
-	[CAPS_1]	= 0x452,
-	[CAPS_2]	= 0x456,
-	[CAPS_3]	= 0x458,
-	[CAPS_4]	= 0x45a,
-	[PCH2_SR]	= 0x460,
-	[PCH0_SR]	= 0x480,
-	[PCH1_SR]	= 0x482,
-	[PCHD_SR]	= 0x4c0,
+
+static const struct omap_dma_reg reg_map[] = {
+	[GCR]		= { 0x0400, 0x00, OMAP_DMA_REG_16BIT },
+	[GSCR]		= { 0x0404, 0x00, OMAP_DMA_REG_16BIT },
+	[GRST1]		= { 0x0408, 0x00, OMAP_DMA_REG_16BIT },
+	[HW_ID]		= { 0x0442, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH2_ID]	= { 0x0444, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH0_ID]	= { 0x0446, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH1_ID]	= { 0x0448, 0x00, OMAP_DMA_REG_16BIT },
+	[PCHG_ID]	= { 0x044a, 0x00, OMAP_DMA_REG_16BIT },
+	[PCHD_ID]	= { 0x044c, 0x00, OMAP_DMA_REG_16BIT },
+	[CAPS_0]	= { 0x044e, 0x00, OMAP_DMA_REG_2X16BIT },
+	[CAPS_1]	= { 0x0452, 0x00, OMAP_DMA_REG_2X16BIT },
+	[CAPS_2]	= { 0x0456, 0x00, OMAP_DMA_REG_16BIT },
+	[CAPS_3]	= { 0x0458, 0x00, OMAP_DMA_REG_16BIT },
+	[CAPS_4]	= { 0x045a, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH2_SR]	= { 0x0460, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH0_SR]	= { 0x0480, 0x00, OMAP_DMA_REG_16BIT },
+	[PCH1_SR]	= { 0x0482, 0x00, OMAP_DMA_REG_16BIT },
+	[PCHD_SR]	= { 0x04c0, 0x00, OMAP_DMA_REG_16BIT },
 
 	/* Common Registers */
-	[CSDP]		= 0x00,
-	[CCR]		= 0x02,
-	[CICR]		= 0x04,
-	[CSR]		= 0x06,
-	[CEN]		= 0x10,
-	[CFN]		= 0x12,
-	[CSFI]		= 0x14,
-	[CSEI]		= 0x16,
-	[CPC]		= 0x18,	/* 15xx only */
-	[CSAC]		= 0x18,
-	[CDAC]		= 0x1a,
-	[CDEI]		= 0x1c,
-	[CDFI]		= 0x1e,
-	[CLNK_CTRL]	= 0x28,
+	[CSDP]		= { 0x0000, 0x40, OMAP_DMA_REG_16BIT },
+	[CCR]		= { 0x0002, 0x40, OMAP_DMA_REG_16BIT },
+	[CICR]		= { 0x0004, 0x40, OMAP_DMA_REG_16BIT },
+	[CSR]		= { 0x0006, 0x40, OMAP_DMA_REG_16BIT },
+	[CEN]		= { 0x0010, 0x40, OMAP_DMA_REG_16BIT },
+	[CFN]		= { 0x0012, 0x40, OMAP_DMA_REG_16BIT },
+	[CSFI]		= { 0x0014, 0x40, OMAP_DMA_REG_16BIT },
+	[CSEI]		= { 0x0016, 0x40, OMAP_DMA_REG_16BIT },
+	[CPC]		= { 0x0018, 0x40, OMAP_DMA_REG_16BIT },	/* 15xx only */
+	[CSAC]		= { 0x0018, 0x40, OMAP_DMA_REG_16BIT },
+	[CDAC]		= { 0x001a, 0x40, OMAP_DMA_REG_16BIT },
+	[CDEI]		= { 0x001c, 0x40, OMAP_DMA_REG_16BIT },
+	[CDFI]		= { 0x001e, 0x40, OMAP_DMA_REG_16BIT },
+	[CLNK_CTRL]	= { 0x0028, 0x40, OMAP_DMA_REG_16BIT },
 
 	/* Channel specific register offsets */
-	[CSSA]		= 0x08,
-	[CDSA]		= 0x0c,
-	[COLOR]		= 0x20,
-	[CCR2]		= 0x24,
-	[LCH_CTRL]	= 0x2a,
+	[CSSA]		= { 0x0008, 0x40, OMAP_DMA_REG_2X16BIT },
+	[CDSA]		= { 0x000c, 0x40, OMAP_DMA_REG_2X16BIT },
+	[COLOR]		= { 0x0020, 0x40, OMAP_DMA_REG_2X16BIT },
+	[CCR2]		= { 0x0024, 0x40, OMAP_DMA_REG_16BIT },
+	[LCH_CTRL]	= { 0x002a, 0x40, OMAP_DMA_REG_16BIT },
 };
 
 static struct resource res[] __initdata = {
@@ -181,44 +177,36 @@ static struct resource res[] __initdata = {
 static void __iomem *dma_base;
 static inline void dma_write(u32 val, int reg, int lch)
 {
-	u8  stride;
-	u32 offset;
+	void __iomem *addr = dma_base;
 
-	stride = (reg >= dma_common_ch_start) ? dma_stride : 0;
-	offset = reg_map[reg] + (stride * lch);
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
 
-	__raw_writew(val, dma_base + offset);
-	if ((reg > CLNK_CTRL && reg < CCEN) ||
-			(reg > PCHD_ID && reg < CAPS_2)) {
-		u32 offset2 = reg_map[reg] + 2 + (stride * lch);
-		__raw_writew(val >> 16, dma_base + offset2);
-	}
+	__raw_writew(val, addr);
+	if (reg_map[reg].type == OMAP_DMA_REG_2X16BIT)
+		__raw_writew(val >> 16, addr + 2);
 }
 
 static inline u32 dma_read(int reg, int lch)
 {
-	u8 stride;
-	u32 offset, val;
-
-	stride = (reg >= dma_common_ch_start) ? dma_stride : 0;
-	offset = reg_map[reg] + (stride * lch);
-
-	val = __raw_readw(dma_base + offset);
-	if ((reg > CLNK_CTRL && reg < CCEN) ||
-			(reg > PCHD_ID && reg < CAPS_2)) {
-		u16 upper;
-		u32 offset2 = reg_map[reg] + 2 + (stride * lch);
-		upper = __raw_readw(dma_base + offset2);
-		val |= (upper << 16);
-	}
+	void __iomem *addr = dma_base;
+	uint32_t val;
+
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
+
+	val = __raw_readw(addr);
+	if (reg_map[reg].type == OMAP_DMA_REG_2X16BIT)
+		val |= __raw_readw(addr + 2) << 16;
+
 	return val;
 }
 
 static void omap1_clear_lch_regs(int lch)
 {
-	int i = dma_common_ch_start;
+	int i;
 
-	for (; i <= dma_common_ch_end; i += 1)
+	for (i = CPC; i <= COLOR; i += 1)
 		dma_write(0, i, lch);
 }
 
@@ -255,8 +243,9 @@ static void omap1_show_dma_caps(void)
 	return;
 }
 
-static u32 configure_dma_errata(void)
+static unsigned configure_dma_errata(void)
 {
+	unsigned errata = 0;
 
 	/*
 	 * Erratum 3.2/3.3: sometimes 0 is returned if CSAC/CDAC is
@@ -272,11 +261,23 @@ static const struct platform_device_info omap_dma_dev_info = {
 	.name = "omap-dma-engine",
 	.id = -1,
 	.dma_mask = DMA_BIT_MASK(32),
+	.res = res,
+	.num_res = 1,
+};
+
+static struct omap_system_dma_plat_info dma_plat_info __initdata = {
+	.reg_map	= reg_map,
+	.channel_stride	= 0x40,
+	.show_dma_caps	= omap1_show_dma_caps,
+	.clear_lch_regs	= omap1_clear_lch_regs,
+	.clear_dma	= omap1_clear_dma,
+	.dma_write	= dma_write,
+	.dma_read	= dma_read,
 };
 
 static int __init omap1_system_dma_init(void)
 {
-	struct omap_system_dma_plat_info	*p;
+	struct omap_system_dma_plat_info	p;
 	struct omap_dma_dev_attr		*d;
 	struct platform_device			*pdev, *dma_pdev;
 	int ret;
@@ -302,20 +303,12 @@ static int __init omap1_system_dma_init(void)
 		goto exit_iounmap;
 	}
 
-	p = kzalloc(sizeof(struct omap_system_dma_plat_info), GFP_KERNEL);
-	if (!p) {
-		dev_err(&pdev->dev, "%s: Unable to allocate 'p' for %s\n",
-			__func__, pdev->name);
-		ret = -ENOMEM;
-		goto exit_iounmap;
-	}
-
 	d = kzalloc(sizeof(struct omap_dma_dev_attr), GFP_KERNEL);
 	if (!d) {
 		dev_err(&pdev->dev, "%s: Unable to allocate 'd' for %s\n",
 			__func__, pdev->name);
 		ret = -ENOMEM;
-		goto exit_release_p;
+		goto exit_iounmap;
 	}
 
 	d->lch_count		= OMAP1_LOGICAL_DMA_CH_COUNT;
@@ -336,17 +329,6 @@ static int __init omap1_system_dma_init(void)
 	d->dev_caps		|= CLEAR_CSR_ON_READ;
 	d->dev_caps		|= IS_WORD_16;
 
-
-	d->chan = kzalloc(sizeof(struct omap_dma_lch) *
-					(d->lch_count), GFP_KERNEL);
-	if (!d->chan) {
-		dev_err(&pdev->dev,
-			"%s: Memory allocation failed for d->chan!\n",
-			__func__);
-		ret = -ENOMEM;
-		goto exit_release_d;
-	}
-
 	if (cpu_is_omap15xx())
 		d->chan_count = 9;
 	else if (cpu_is_omap16xx() || cpu_is_omap7xx()) {
@@ -356,35 +338,24 @@ static int __init omap1_system_dma_init(void)
 			d->chan_count = 9;
 	}
 
-	p->dma_attr = d;
-
-	p->show_dma_caps	= omap1_show_dma_caps;
-	p->clear_lch_regs	= omap1_clear_lch_regs;
-	p->clear_dma		= omap1_clear_dma;
-	p->dma_write		= dma_write;
-	p->dma_read		= dma_read;
-	p->disable_irq_lch	= NULL;
-
-	p->errata = configure_dma_errata();
+	p = dma_plat_info;
+	p.dma_attr = d;
+	p.errata = configure_dma_errata();
 
-	ret = platform_device_add_data(pdev, p, sizeof(*p));
+	ret = platform_device_add_data(pdev, &p, sizeof(p));
 	if (ret) {
 		dev_err(&pdev->dev, "%s: Unable to add resources for %s%d\n",
 			__func__, pdev->name, pdev->id);
-		goto exit_release_chan;
+		goto exit_release_d;
 	}
 
 	ret = platform_device_add(pdev);
 	if (ret) {
 		dev_err(&pdev->dev, "%s: Unable to add resources for %s%d\n",
 			__func__, pdev->name, pdev->id);
-		goto exit_release_chan;
+		goto exit_release_d;
 	}
 
-	dma_stride		= OMAP1_DMA_STRIDE;
-	dma_common_ch_start	= CPC;
-	dma_common_ch_end	= COLOR;
-
 	dma_pdev = platform_device_register_full(&omap_dma_dev_info);
 	if (IS_ERR(dma_pdev)) {
 		ret = PTR_ERR(dma_pdev);
@@ -395,12 +366,8 @@ static int __init omap1_system_dma_init(void)
 
 exit_release_pdev:
 	platform_device_del(pdev);
-exit_release_chan:
-	kfree(d->chan);
 exit_release_d:
 	kfree(d);
-exit_release_p:
-	kfree(p);
 exit_iounmap:
 	iounmap(dma_base);
 exit_device_put:

arch/arm/mach-omap2/am35xx-emac.c

@@ -17,7 +17,6 @@
 
 #include <linux/err.h>
 #include <linux/davinci_emac.h>
-#include <asm/system.h>
 #include "omap_device.h"
 #include "am35xx.h"
 #include "control.h"

arch/arm/mach-omap2/dma.c

@@ -35,97 +35,80 @@
 #include "omap_hwmod.h"
 #include "omap_device.h"
 
-#define OMAP2_DMA_STRIDE	0x60
-
-static u32 errata;
-static u8 dma_stride;
-
-static struct omap_dma_dev_attr *d;
-
-static enum omap_reg_offsets dma_common_ch_start, dma_common_ch_end;
-
-static u16 reg_map[] = {
-	[REVISION]		= 0x00,
-	[GCR]			= 0x78,
-	[IRQSTATUS_L0]		= 0x08,
-	[IRQSTATUS_L1]		= 0x0c,
-	[IRQSTATUS_L2]		= 0x10,
-	[IRQSTATUS_L3]		= 0x14,
-	[IRQENABLE_L0]		= 0x18,
-	[IRQENABLE_L1]		= 0x1c,
-	[IRQENABLE_L2]		= 0x20,
-	[IRQENABLE_L3]		= 0x24,
-	[SYSSTATUS]		= 0x28,
-	[OCP_SYSCONFIG]		= 0x2c,
-	[CAPS_0]		= 0x64,
-	[CAPS_2]		= 0x6c,
-	[CAPS_3]		= 0x70,
-	[CAPS_4]		= 0x74,
+static enum omap_reg_offsets dma_common_ch_end;
+
+static const struct omap_dma_reg reg_map[] = {
+	[REVISION]	= { 0x0000, 0x00, OMAP_DMA_REG_32BIT },
+	[GCR]		= { 0x0078, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L0]	= { 0x0008, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L1]	= { 0x000c, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L2]	= { 0x0010, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQSTATUS_L3]	= { 0x0014, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L0]	= { 0x0018, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L1]	= { 0x001c, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L2]	= { 0x0020, 0x00, OMAP_DMA_REG_32BIT },
+	[IRQENABLE_L3]	= { 0x0024, 0x00, OMAP_DMA_REG_32BIT },
+	[SYSSTATUS]	= { 0x0028, 0x00, OMAP_DMA_REG_32BIT },
+	[OCP_SYSCONFIG]	= { 0x002c, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_0]	= { 0x0064, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_2]	= { 0x006c, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_3]	= { 0x0070, 0x00, OMAP_DMA_REG_32BIT },
+	[CAPS_4]	= { 0x0074, 0x00, OMAP_DMA_REG_32BIT },
 
 	/* Common register offsets */
-	[CCR]			= 0x80,
-	[CLNK_CTRL]		= 0x84,
-	[CICR]			= 0x88,
-	[CSR]			= 0x8c,
-	[CSDP]			= 0x90,
-	[CEN]			= 0x94,
-	[CFN]			= 0x98,
-	[CSEI]			= 0xa4,
-	[CSFI]			= 0xa8,
-	[CDEI]			= 0xac,
-	[CDFI]			= 0xb0,
-	[CSAC]			= 0xb4,
-	[CDAC]			= 0xb8,
+	[CCR]		= { 0x0080, 0x60, OMAP_DMA_REG_32BIT },
+	[CLNK_CTRL]	= { 0x0084, 0x60, OMAP_DMA_REG_32BIT },
+	[CICR]		= { 0x0088, 0x60, OMAP_DMA_REG_32BIT },
+	[CSR]		= { 0x008c, 0x60, OMAP_DMA_REG_32BIT },
+	[CSDP]		= { 0x0090, 0x60, OMAP_DMA_REG_32BIT },
+	[CEN]		= { 0x0094, 0x60, OMAP_DMA_REG_32BIT },
+	[CFN]		= { 0x0098, 0x60, OMAP_DMA_REG_32BIT },
+	[CSEI]		= { 0x00a4, 0x60, OMAP_DMA_REG_32BIT },
+	[CSFI]		= { 0x00a8, 0x60, OMAP_DMA_REG_32BIT },
+	[CDEI]		= { 0x00ac, 0x60, OMAP_DMA_REG_32BIT },
+	[CDFI]		= { 0x00b0, 0x60, OMAP_DMA_REG_32BIT },
+	[CSAC]		= { 0x00b4, 0x60, OMAP_DMA_REG_32BIT },
+	[CDAC]		= { 0x00b8, 0x60, OMAP_DMA_REG_32BIT },
 
 	/* Channel specific register offsets */
-	[CSSA]			= 0x9c,
-	[CDSA]			= 0xa0,
-	[CCEN]			= 0xbc,
-	[CCFN]			= 0xc0,
-	[COLOR]			= 0xc4,
+	[CSSA]		= { 0x009c, 0x60, OMAP_DMA_REG_32BIT },
+	[CDSA]		= { 0x00a0, 0x60, OMAP_DMA_REG_32BIT },
+	[CCEN]		= { 0x00bc, 0x60, OMAP_DMA_REG_32BIT },
+	[CCFN]		= { 0x00c0, 0x60, OMAP_DMA_REG_32BIT },
+	[COLOR]		= { 0x00c4, 0x60, OMAP_DMA_REG_32BIT },
 
 	/* OMAP4 specific registers */
-	[CDP]			= 0xd0,
-	[CNDP]			= 0xd4,
-	[CCDN]			= 0xd8,
+	[CDP]		= { 0x00d0, 0x60, OMAP_DMA_REG_32BIT },
+	[CNDP]		= { 0x00d4, 0x60, OMAP_DMA_REG_32BIT },
+	[CCDN]		= { 0x00d8, 0x60, OMAP_DMA_REG_32BIT },
 };
 
 static void __iomem *dma_base;
 static inline void dma_write(u32 val, int reg, int lch)
 {
-	u8  stride;
-	u32 offset;
+	void __iomem *addr = dma_base;
 
-	stride = (reg >= dma_common_ch_start) ? dma_stride : 0;
-	offset = reg_map[reg] + (stride * lch);
-	__raw_writel(val, dma_base + offset);
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
+
+	__raw_writel(val, addr);
 }
 
 static inline u32 dma_read(int reg, int lch)
 {
-	u8 stride;
-	u32 offset, val;
-
-	stride = (reg >= dma_common_ch_start) ? dma_stride : 0;
-	offset = reg_map[reg] + (stride * lch);
-	val = __raw_readl(dma_base + offset);
-	return val;
-}
+	void __iomem *addr = dma_base;
 
-static inline void omap2_disable_irq_lch(int lch)
-{
-	u32 val;
+	addr += reg_map[reg].offset;
+	addr += reg_map[reg].stride * lch;
 
-	val = dma_read(IRQENABLE_L0, lch);
-	val &= ~(1 << lch);
-	dma_write(val, IRQENABLE_L0, lch);
+	return __raw_readl(addr);
 }
 
 static void omap2_clear_dma(int lch)
 {
-	int i = dma_common_ch_start;
+	int i;
 
-	for (; i <= dma_common_ch_end; i += 1)
+	for (i = CSDP; i <= dma_common_ch_end; i += 1)
 		dma_write(0, i, lch);
 }
 
@@ -137,8 +120,9 @@ static void omap2_show_dma_caps(void)
 	return;
 }
 
-static u32 configure_dma_errata(void)
+static unsigned configure_dma_errata(void)
 {
+	unsigned errata = 0;
 
 	/*
 	 * Errata applicable for OMAP2430ES1.0 and all omap2420
@@ -220,48 +204,50 @@ static u32 configure_dma_errata(void)
 	return errata;
 }
 
+static struct omap_system_dma_plat_info dma_plat_info __initdata = {
+	.reg_map	= reg_map,
+	.channel_stride	= 0x60,
+	.show_dma_caps	= omap2_show_dma_caps,
+	.clear_dma	= omap2_clear_dma,
+	.dma_write	= dma_write,
+	.dma_read	= dma_read,
+};
+
+static struct platform_device_info omap_dma_dev_info = {
+	.name = "omap-dma-engine",
+	.id = -1,
+	.dma_mask = DMA_BIT_MASK(32),
+};
+
 /* One time initializations */
 static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 {
 	struct platform_device			*pdev;
-	struct omap_system_dma_plat_info	*p;
+	struct omap_system_dma_plat_info	p;
+	struct omap_dma_dev_attr		*d;
 	struct resource				*mem;
 	char					*name = "omap_dma_system";
 
-	dma_stride		= OMAP2_DMA_STRIDE;
-	dma_common_ch_start	= CSDP;
-
-	p = kzalloc(sizeof(struct omap_system_dma_plat_info), GFP_KERNEL);
-	if (!p) {
-		pr_err("%s: Unable to allocate pdata for %s:%s\n",
-			__func__, name, oh->name);
-		return -ENOMEM;
-	}
-
-	p->dma_attr		= (struct omap_dma_dev_attr *)oh->dev_attr;
-	p->disable_irq_lch	= omap2_disable_irq_lch;
-	p->show_dma_caps	= omap2_show_dma_caps;
-	p->clear_dma		= omap2_clear_dma;
-	p->dma_write		= dma_write;
-	p->dma_read		= dma_read;
-
-	p->clear_lch_regs	= NULL;
-
-	p->errata		= configure_dma_errata();
+	p = dma_plat_info;
+	p.dma_attr = (struct omap_dma_dev_attr *)oh->dev_attr;
+	p.errata = configure_dma_errata();
 
-	pdev = omap_device_build(name, 0, oh, p, sizeof(*p));
-	kfree(p);
+	pdev = omap_device_build(name, 0, oh, &p, sizeof(p));
 	if (IS_ERR(pdev)) {
 		pr_err("%s: Can't build omap_device for %s:%s.\n",
 			__func__, name, oh->name);
 		return PTR_ERR(pdev);
 	}
 
+	omap_dma_dev_info.res = pdev->resource;
+	omap_dma_dev_info.num_res = pdev->num_resources;
+
 	mem = platform_get_resource(pdev, IORESOURCE_MEM, 0);
 	if (!mem) {
 		dev_err(&pdev->dev, "%s: no mem resource\n", __func__);
 		return -EINVAL;
 	}
+
 	dma_base = ioremap(mem->start, resource_size(mem));
 	if (!dma_base) {
 		dev_err(&pdev->dev, "%s: ioremap fail\n", __func__);
@@ -269,13 +255,6 @@ static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 	}
 
 	d = oh->dev_attr;
-	d->chan = kzalloc(sizeof(struct omap_dma_lch) *
-					(d->lch_count), GFP_KERNEL);
-
-	if (!d->chan) {
-		dev_err(&pdev->dev, "%s: kzalloc fail\n", __func__);
-		return -ENOMEM;
-	}
 
 	if (cpu_is_omap34xx() && (omap_type() != OMAP2_DEVICE_TYPE_GP))
 		d->dev_caps |= HS_CHANNELS_RESERVED;
@@ -289,12 +268,6 @@ static int __init omap2_system_dma_init_dev(struct omap_hwmod *oh, void *unused)
 	return 0;
 }
 
-static const struct platform_device_info omap_dma_dev_info = {
-	.name = "omap-dma-engine",
-	.id = -1,
-	.dma_mask = DMA_BIT_MASK(32),
-};
-
 static int __init omap2_system_dma_init(void)
 {
 	struct platform_device *pdev;

arch/arm/mach-rpc/dma.c

@@ -141,7 +141,7 @@ static int iomd_request_dma(unsigned int chan, dma_t *dma)
 	struct iomd_dma *idma = container_of(dma, struct iomd_dma, dma);
 
 	return request_irq(idma->irq, iomd_dma_handle,
-			   IRQF_DISABLED, idma->dma.device_id, idma);
+			   0, idma->dma.device_id, idma);
 }
 
 static void iomd_free_dma(unsigned int chan, dma_t *dma)

arch/arm/mach-rpc/time.c

@@ -75,7 +75,6 @@ ioc_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction ioc_timer_irq = {
 	.name		= "timer",
-	.flags		= IRQF_DISABLED,
 	.handler	= ioc_timer_interrupt
 };
 

arch/arm/mach-sa1100/collie.c

@@ -43,6 +43,7 @@
 #include <asm/mach/arch.h>
 #include <asm/mach/flash.h>
 #include <asm/mach/map.h>
+#include <asm/mach/irda.h>
 
 #include <asm/hardware/scoop.h>
 #include <asm/mach/sharpsl_param.h>
@@ -96,6 +97,37 @@ static struct mcp_plat_data collie_mcp_data = {
 	.codec_pdata	= &collie_ucb1x00_data,
 };
 
+static int collie_ir_startup(struct device *dev)
+{
+	int rc = gpio_request(COLLIE_GPIO_IR_ON, "IrDA");
+	if (rc)
+		return rc;
+	rc = gpio_direction_output(COLLIE_GPIO_IR_ON, 1);
+
+	if (!rc)
+		return 0;
+
+	gpio_free(COLLIE_GPIO_IR_ON);
+	return rc;
+}
+
+static void collie_ir_shutdown(struct device *dev)
+{
+	gpio_free(COLLIE_GPIO_IR_ON);
+}
+
+static int collie_ir_set_power(struct device *dev, unsigned int state)
+{
+	gpio_set_value(COLLIE_GPIO_IR_ON, !state);
+	return 0;
+}
+
+static struct irda_platform_data collie_ir_data = {
+	.startup = collie_ir_startup,
+	.shutdown = collie_ir_shutdown,
+	.set_power = collie_ir_set_power,
+};
+
 /*
  * Collie AC IN
  */
@@ -400,6 +432,7 @@ static void __init collie_init(void)
 	sa11x0_register_mtd(&collie_flash_data, collie_flash_resources,
 			    ARRAY_SIZE(collie_flash_resources));
 	sa11x0_register_mcp(&collie_mcp_data);
+	sa11x0_register_irda(&collie_ir_data);
 
 	sharpsl_save_param();
 }

arch/arm/mach-sa1100/h3100.c

@@ -122,15 +122,8 @@ static struct irda_platform_data h3100_irda_data = {
 	.shutdown	= h3100_irda_shutdown,
 };
 
-static struct gpio_default_state h3100_default_gpio[] = {
-	{ H3XXX_GPIO_COM_DCD,	GPIO_MODE_IN,	"COM DCD" },
-	{ H3XXX_GPIO_COM_CTS,	GPIO_MODE_IN,	"COM CTS" },
-	{ H3XXX_GPIO_COM_RTS,	GPIO_MODE_OUT0,	"COM RTS" },
-};
-
 static void __init h3100_mach_init(void)
 {
-	h3xxx_init_gpio(h3100_default_gpio, ARRAY_SIZE(h3100_default_gpio));
 	h3xxx_mach_init();
 
 	sa11x0_register_lcd(&h3100_lcd_info);

arch/arm/mach-sa1100/h3600.c

@@ -130,15 +130,8 @@ static struct irda_platform_data h3600_irda_data = {
 	.shutdown	= h3600_irda_shutdown,
 };
 
-static struct gpio_default_state h3600_default_gpio[] = {
-	{ H3XXX_GPIO_COM_DCD,	GPIO_MODE_IN,	"COM DCD" },
-	{ H3XXX_GPIO_COM_CTS,	GPIO_MODE_IN,	"COM CTS" },
-	{ H3XXX_GPIO_COM_RTS,	GPIO_MODE_OUT0,	"COM RTS" },
-};
-
 static void __init h3600_mach_init(void)
 {
-	h3xxx_init_gpio(h3600_default_gpio, ARRAY_SIZE(h3600_default_gpio));
 	h3xxx_mach_init();
 
 	sa11x0_register_lcd(&h3600_lcd_info);

arch/arm/mach-sa1100/h3xxx.c

@@ -28,37 +28,6 @@
 
 #include "generic.h"
 
-void h3xxx_init_gpio(struct gpio_default_state *s, size_t n)
-{
-	while (n--) {
-		const char *name = s->name;
-		int err;
-
-		if (!name)
-			name = "[init]";
-		err = gpio_request(s->gpio, name);
-		if (err) {
-			printk(KERN_ERR "gpio%u: unable to request: %d\n",
-				s->gpio, err);
-			continue;
-		}
-		if (s->mode >= 0) {
-			err = gpio_direction_output(s->gpio, s->mode);
-		} else {
-			err = gpio_direction_input(s->gpio);
-		}
-		if (err) {
-			printk(KERN_ERR "gpio%u: unable to set direction: %d\n",
-				s->gpio, err);
-			continue;
-		}
-		if (!s->name)
-			gpio_free(s->gpio);
-		s++;
-	}
-}
-
-
 /*
  * H3xxx flash support
  */
@@ -116,9 +85,34 @@ static struct resource h3xxx_flash_resource =
 /*
  * H3xxx uart support
  */
+static struct gpio h3xxx_uart_gpio[] = {
+	{ H3XXX_GPIO_COM_DCD,	GPIOF_IN,		"COM DCD" },
+	{ H3XXX_GPIO_COM_CTS,	GPIOF_IN,		"COM CTS" },
+	{ H3XXX_GPIO_COM_RTS,	GPIOF_OUT_INIT_LOW,	"COM RTS" },
+};
+
+static bool h3xxx_uart_request_gpios(void)
+{
+	static bool h3xxx_uart_gpio_ok;
+	int rc;
+
+	if (h3xxx_uart_gpio_ok)
+		return true;
+
+	rc = gpio_request_array(h3xxx_uart_gpio, ARRAY_SIZE(h3xxx_uart_gpio));
+	if (rc)
+		pr_err("h3xxx_uart_request_gpios: error %d\n", rc);
+	else
+		h3xxx_uart_gpio_ok = true;
+
+	return h3xxx_uart_gpio_ok;
+}
+
 static void h3xxx_uart_set_mctrl(struct uart_port *port, u_int mctrl)
 {
 	if (port->mapbase == _Ser3UTCR0) {
+		if (!h3xxx_uart_request_gpios())
+			return;
 		gpio_set_value(H3XXX_GPIO_COM_RTS, !(mctrl & TIOCM_RTS));
 	}
 }
@@ -128,6 +122,8 @@ static u_int h3xxx_uart_get_mctrl(struct uart_port *port)
 	u_int ret = TIOCM_CD | TIOCM_CTS | TIOCM_DSR;
 
 	if (port->mapbase == _Ser3UTCR0) {
+		if (!h3xxx_uart_request_gpios())
+			return ret;
 		/*
 		 * DCD and CTS bits are inverted in GPLR by RS232 transceiver
 		 */

arch/arm/mach-sa1100/include/mach/collie.h

@@ -80,7 +80,7 @@ extern void locomolcd_power(int on);
 #define COLLIE_TC35143_GPIO_VERSION0    UCB_IO_0
 #define COLLIE_TC35143_GPIO_TBL_CHK     UCB_IO_1
 #define COLLIE_TC35143_GPIO_VPEN_ON     UCB_IO_2
-#define COLLIE_TC35143_GPIO_IR_ON       UCB_IO_3
+#define COLLIE_GPIO_IR_ON		(COLLIE_TC35143_GPIO_BASE + 3)
 #define COLLIE_TC35143_GPIO_AMP_ON      UCB_IO_4
 #define COLLIE_TC35143_GPIO_VERSION1    UCB_IO_5
 #define COLLIE_TC35143_GPIO_FS8KLPF     UCB_IO_5

arch/arm/mach-sa1100/include/mach/h3xxx.h

@@ -79,17 +79,6 @@
 #define H3600_EGPIO_LCD_5V_ON		(H3XXX_EGPIO_BASE + 14) /* enable 5V to LCD. active high. */
 #define H3600_EGPIO_LVDD_ON		(H3XXX_EGPIO_BASE + 15) /* enable 9V and -6.5V to LCD. */
 
-struct gpio_default_state {
-	int gpio;
-	int mode;
-	const char *name;
-};
-
-#define GPIO_MODE_IN	-1
-#define GPIO_MODE_OUT0	0
-#define GPIO_MODE_OUT1	1
-
-void h3xxx_init_gpio(struct gpio_default_state *s, size_t n);
 void __init h3xxx_map_io(void);
 void __init h3xxx_mach_init(void);
 

arch/arm/mach-sa1100/time.c

@@ -112,7 +112,7 @@ static struct clock_event_device ckevt_sa1100_osmr0 = {
 
 static struct irqaction sa1100_timer_irq = {
 	.name		= "ost0",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= sa1100_ost0_interrupt,
 	.dev_id		= &ckevt_sa1100_osmr0,
 };

arch/arm/mach-spear/time.c

@@ -172,7 +172,7 @@ static irqreturn_t spear_timer_interrupt(int irq, void *dev_id)
 
 static struct irqaction spear_timer_irq = {
 	.name = "timer",
-	.flags = IRQF_DISABLED | IRQF_TIMER,
+	.flags = IRQF_TIMER,
 	.handler = spear_timer_interrupt
 };
 

arch/arm/mach-vexpress/Makefile

@@ -8,8 +8,11 @@ obj-y					:= v2m.o
 obj-$(CONFIG_ARCH_VEXPRESS_CA9X4)	+= ct-ca9x4.o
 obj-$(CONFIG_ARCH_VEXPRESS_DCSCB)	+= dcscb.o	dcscb_setup.o
 CFLAGS_dcscb.o				+= -march=armv7-a
+CFLAGS_REMOVE_dcscb.o			= -pg
 obj-$(CONFIG_ARCH_VEXPRESS_SPC)		+= spc.o
+CFLAGS_REMOVE_spc.o			= -pg
 obj-$(CONFIG_ARCH_VEXPRESS_TC2_PM)	+= tc2_pm.o
 CFLAGS_tc2_pm.o				+= -march=armv7-a
+CFLAGS_REMOVE_tc2_pm.o			= -pg
 obj-$(CONFIG_SMP)			+= platsmp.o
 obj-$(CONFIG_HOTPLUG_CPU)		+= hotplug.o

arch/arm/mach-w90x900/time.c

@@ -111,7 +111,7 @@ static irqreturn_t nuc900_timer0_interrupt(int irq, void *dev_id)
 
 static struct irqaction nuc900_timer0_irq = {
 	.name		= "nuc900-timer0",
-	.flags		= IRQF_DISABLED | IRQF_TIMER | IRQF_IRQPOLL,
+	.flags		= IRQF_TIMER | IRQF_IRQPOLL,
 	.handler	= nuc900_timer0_interrupt,
 };
 

arch/arm/mm/Kconfig

@@ -446,7 +446,6 @@ config CPU_32v5
 
 config CPU_32v6
 	bool
-	select CPU_USE_DOMAINS if CPU_V6 && MMU
 	select TLS_REG_EMUL if !CPU_32v6K && !MMU
 
 config CPU_32v6K
@@ -671,7 +670,7 @@ config ARM_VIRT_EXT
 
 config SWP_EMULATE
 	bool "Emulate SWP/SWPB instructions"
-	depends on !CPU_USE_DOMAINS && CPU_V7
+	depends on CPU_V7
 	default y if SMP
 	select HAVE_PROC_CPU if PROC_FS
 	help

arch/arm/mm/cache-feroceon-l2.c

@@ -331,7 +331,9 @@ static void __init enable_l2(void)
 			enable_icache();
 		if (d)
 			enable_dcache();
-	}
+	} else
+		pr_err(FW_BUG
+		       "Feroceon L2: bootloader left the L2 cache on!\n");
 }
 
 void __init feroceon_l2_init(int __l2_wt_override)

arch/arm/mm/dma-mapping.c

@@ -284,9 +284,6 @@ static void __dma_free_buffer(struct page *page, size_t size)
 }
 
 #ifdef CONFIG_MMU
-#ifdef CONFIG_HUGETLB_PAGE
-#warning ARM Coherent DMA allocator does not (yet) support huge TLB
-#endif
 
 static void *__alloc_from_contiguous(struct device *dev, size_t size,
 				     pgprot_t prot, struct page **ret_page,

arch/arm/mm/mmu.c

@@ -515,6 +515,16 @@ static void __init build_mem_type_table(void)
 	hyp_device_pgprot = mem_types[MT_DEVICE].prot_pte;
 	s2_device_pgprot = mem_types[MT_DEVICE].prot_pte_s2;
 
+	/*
+	 * We don't use domains on ARMv6 (since this causes problems with
+	 * v6/v7 kernels), so we must use a separate memory type for user
+	 * r/o, kernel r/w to map the vectors page.
+	 */
+#ifndef CONFIG_ARM_LPAE
+	if (cpu_arch == CPU_ARCH_ARMv6)
+		vecs_pgprot |= L_PTE_MT_VECTORS;
+#endif
+
 	/*
 	 * ARMv6 and above have extended page tables.
 	 */

arch/arm/mm/proc-macros.S

@@ -112,13 +112,9 @@
  *  100x   1   0   1	r/o	no acc
  *  10x0   1   0   1	r/o	no acc
  *  1011   0   0   1	r/w	no acc
- *  110x   0   1   0	r/w	r/o
- *  11x0   0   1   0	r/w	r/o
- *  1111   0   1   1	r/w	r/w
- *
- * If !CONFIG_CPU_USE_DOMAINS, the following permissions are changed:
  *  110x   1   1   1	r/o	r/o
  *  11x0   1   1   1	r/o	r/o
+ *  1111   0   1   1	r/w	r/w
  */
 	.macro	armv6_mt_table pfx
 \pfx\()_mt_table:
@@ -137,7 +133,7 @@
 	.long	PTE_EXT_TEX(2)					@ L_PTE_MT_DEV_NONSHARED
 	.long	0x00						@ unused
 	.long	0x00						@ unused
-	.long	0x00						@ unused
+	.long	PTE_CACHEABLE | PTE_BUFFERABLE | PTE_EXT_APX	@ L_PTE_MT_VECTORS
 	.endm
 
 	.macro	armv6_set_pte_ext pfx
@@ -158,24 +154,21 @@
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
 	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
+
+	@ user read-only -> kernel read-only
+	bicne	r3, r3, #PTE_EXT_AP0
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
-	orr	r3, r3, r2
+	eor	r3, r3, r2
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_PRESENT
 	moveq	r3, #0
-#ifndef CONFIG_CPU_USE_DOMAINS
 	tstne	r1, #L_PTE_NONE
 	movne	r3, #0
-#endif
 
 	str	r3, [r0]
 	mcr	p15, 0, r0, c7, c10, 1		@ flush_pte

arch/arm/mm/proc-v7-2level.S

@@ -90,21 +90,14 @@ ENTRY(cpu_v7_set_pte_ext)
 
 	tst	r1, #L_PTE_USER
 	orrne	r3, r3, #PTE_EXT_AP1
-#ifdef CONFIG_CPU_USE_DOMAINS
-	@ allow kernel read/write access to read-only user pages
-	tstne	r3, #PTE_EXT_APX
-	bicne	r3, r3, #PTE_EXT_APX | PTE_EXT_AP0
-#endif
 
 	tst	r1, #L_PTE_XN
 	orrne	r3, r3, #PTE_EXT_XN
 
 	tst	r1, #L_PTE_YOUNG
 	tstne	r1, #L_PTE_VALID
-#ifndef CONFIG_CPU_USE_DOMAINS
 	eorne	r1, r1, #L_PTE_NONE
 	tstne	r1, #L_PTE_NONE
-#endif
 	moveq	r3, #0
 
  ARM(	str	r3, [r0, #2048]! )